Compare commits
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
829fc44cbc | ||
|
|
6b4049c9f5 | ||
|
|
934ba16c72 | ||
|
|
9f1dc44673 | ||
|
|
24258e215f | ||
|
|
793eec6e51 | ||
|
|
6785750729 | ||
|
|
72fa043f47 | ||
|
|
cc7397787b | ||
|
|
cef476aca3 | ||
|
|
f50444594f | ||
|
|
275d337032 | ||
|
|
b314470281 | ||
|
|
eb3add5b89 | ||
|
|
c126d5a24a | ||
|
|
1a3e79502d | ||
|
|
fcc6a7974e | ||
|
|
f4ed542b00 | ||
|
|
d06be5ca32 | ||
|
|
8d48a08b13 | ||
|
|
f6ee43bf55 | ||
|
|
268f99051a | ||
|
|
60a09e7def | ||
|
|
bf1dc2e33e | ||
|
|
f34714ea07 | ||
|
|
c2cfba1129 | ||
|
|
cea8bfee98 | ||
|
|
2f8107d5ca | ||
|
|
a67a142139 | ||
|
|
48416af5bc | ||
|
|
cca80ac2e8 | ||
|
|
52d267683b | ||
|
|
0b00682fac | ||
|
|
d1b8bff5ce | ||
|
|
ae8f0d42ef | ||
|
|
39b61a0340 | ||
|
|
06334ca3f9 | ||
|
|
f9e97b561f | ||
|
|
d7f6f502a8 | ||
|
|
54e36ff8b7 | ||
|
|
a1c69c5b28 | ||
|
|
bf68866dca | ||
|
|
87d52938b5 | ||
|
|
90a4189db4 | ||
|
|
013fcd0919 | ||
|
|
00209ebe87 | ||
|
|
96e54e963f | ||
|
|
2f05ed81b1 | ||
|
|
822f8b63d4 | ||
|
|
e0ec9b87e6 | ||
|
|
27bad9f1fa | ||
|
|
403ace1cef | ||
|
|
761a1271a4 | ||
|
|
c5a8942976 | ||
|
|
fb0424b729 | ||
|
|
52b8b6dcca | ||
|
|
d7178250ae | ||
|
|
9b282177e0 | ||
|
|
59273c9544 | ||
|
|
86e706dff7 | ||
|
|
ad5caf88a6 | ||
|
|
a7efb9bb00 | ||
|
|
34f47a4bd0 | ||
|
|
d60fcad18f | ||
|
|
8124c5af54 | ||
|
|
bfc8d4b1b7 | ||
|
|
0b8e9ae7f1 | ||
|
|
662a5ee336 | ||
|
|
8cbbdb20b5 | ||
|
|
cadbc6d1ca | ||
|
|
64128645c2 | ||
|
|
8155cc915a | ||
|
|
150dde5a7d | ||
|
|
a65f558d35 | ||
|
|
0dff130682 | ||
|
|
2d1d4ed632 | ||
|
|
67c5447ebc | ||
|
|
db6e8d321e | ||
|
|
cbeab6afd2 | ||
|
|
ed698fced1 | ||
|
|
081ee4a8ba | ||
|
|
5de07fac0e | ||
|
|
03335f49c1 | ||
|
|
d0d759d216 | ||
|
|
67ead19dd9 | ||
|
|
f7c646163b | ||
|
|
8d05f99526 | ||
|
|
625ead95b3 | ||
|
|
0acc922d9a | ||
|
|
595956cc75 | ||
|
|
929784667b | ||
|
|
d4e254b349 | ||
|
|
89c5f8e2ad | ||
|
|
2ffe924a44 | ||
|
|
c9f677f35b | ||
|
|
d60f024e74 | ||
|
|
1fa3acdbe9 | ||
|
|
d10b070a2e | ||
|
|
b93909c5aa | ||
|
|
42a4e2465d | ||
|
|
608403c1f9 | ||
|
|
e9e52c1f1f | ||
|
|
fc5d24c9f7 | ||
|
|
0b82f1c9a5 | ||
|
|
cdc3e83740 | ||
|
|
807d1dfc15 | ||
|
|
dbaa7284a3 | ||
|
|
5734e194c9 | ||
|
|
e16ba86b30 | ||
|
|
a2650eb5e9 | ||
|
|
1686fba12b | ||
|
|
519604405a | ||
|
|
2aea3ce0dc | ||
|
|
e7b21b9e5d | ||
|
|
e992d4256e | ||
|
|
41823ab336 | ||
|
|
fe2a3a7565 | ||
|
|
36981c2024 | ||
|
|
2bcfc19837 | ||
|
|
416df69b00 | ||
|
|
6c405333b7 | ||
|
|
3f0071e27b | ||
|
|
c07c04e45a | ||
|
|
a6ab4ef538 | ||
|
|
2604cd4cf4 | ||
|
|
cc6d606de4 | ||
|
|
de47bf2398 | ||
|
|
b8f5d0fc3d | ||
|
|
64cc0a5e29 | ||
|
|
d6f33ddd11 | ||
|
|
1e669b4a9f | ||
|
|
c3175c6939 | ||
|
|
7a38d9b79f | ||
|
|
b6357c8fd4 | ||
|
|
5f5494893c | ||
|
|
2c4d8af59e | ||
|
|
ce7478664a | ||
|
|
d1cba5c1ab | ||
|
|
a83b9afdce | ||
|
|
6f0e889bcf | ||
|
|
02328c1880 | ||
|
|
ea39923248 | ||
|
|
9c5eeba281 | ||
|
|
68e6dc0229 | ||
|
|
9219252bd4 | ||
|
|
3de20cdf9e | ||
|
|
e6a5a9d3d8 | ||
|
|
e9fe50b364 | ||
|
|
257a1fbf1f | ||
|
|
e720d3dcd8 | ||
|
|
ca3b53bccd | ||
|
|
3b04ac1196 | ||
|
|
9c053def88 | ||
|
|
4c3d4f94e4 | ||
|
|
fd6b568fa4 | ||
|
|
49c44b4a03 | ||
|
|
3827561ab0 | ||
|
|
0a05a30df0 | ||
|
|
4040e42d2b | ||
|
|
2a03741929 | ||
|
|
fb49ebd268 | ||
|
|
17465f240b | ||
|
|
78833a9c2c | ||
|
|
5ca398d0d9 | ||
|
|
d42731e5ae | ||
|
|
3186184964 | ||
|
|
0c14c4b892 | ||
|
|
82dc7641fe | ||
|
|
fcc9322237 | ||
|
|
62e9e9cb28 | ||
|
|
d6e24e1f81 | ||
|
|
643d2ed665 | ||
|
|
9b581a1326 | ||
|
|
93e96b8de5 |
No files matched your search
@@ -66,6 +66,14 @@ packages the moment it merged; formatting and lint drifted the same way, and onl
|
||||
the repository gate saw it. Both failures are paid for inside the lane when the
|
||||
gate runs the build and the linter, and at merge when it does not.
|
||||
|
||||
Gate the **candidate** before `main` moves. Check the merge candidate out
|
||||
detached — or gate the lane branch — and advance the ref only on a green result:
|
||||
gating after a fast-forward lands the failure on the branch of record and leaves
|
||||
only fix-forward or reset as exits. The lane brief must name the linter as well,
|
||||
`golangci-lint run ./<package>/...` beside the scoped tests, because a scoped
|
||||
test run cannot see a complexity or style limit and `task check` is where that
|
||||
failure otherwise surfaces — once it is already merged.
|
||||
|
||||
A copy of the script under `.pi/control-plane-run/` is that run's disposable
|
||||
state and may lag the skill's version. The skill's copy is the one to trust.
|
||||
|
||||
@@ -126,6 +134,36 @@ ln -sfn /work/apps/archie-core/.pi/agents /work/apps/cp-<lane>/.pi/agents
|
||||
`.pi/` is gitignored, so the worktree stays clean and the symlink cannot reach a
|
||||
commit. This costs an hour to rediscover.
|
||||
|
||||
## Peer sessions over intercom
|
||||
|
||||
A fleet here can also run as **sibling sessions** coordinated over `intercom` —
|
||||
a peer per lane — rather than pi-subagents children under one orchestrator.
|
||||
These facts are peer-specific, and each has cost a real run.
|
||||
|
||||
- **Name the channel in the brief.** A peer's knowledge of how to report lives in
|
||||
its context, not its configuration. Write "report to <peer> over intercom" as
|
||||
an instruction; a convention that is only assumed evaporates.
|
||||
- **A compaction erases conventions, not just facts.** A peer that compacts
|
||||
mid-task keeps its task state and loses its transport: it reverts to
|
||||
addressing its operator, and the coordinator reads that as idleness or death.
|
||||
**Peer silence is not evidence of either** — ask for a one-line ack over the
|
||||
channel before concluding anything. Re-priming restores the channel; the
|
||||
transport itself survives compaction intact.
|
||||
- **Match the task's shape to the session's window, not its strength.** A sweep
|
||||
over hundreds of items needs the largest window available; a bounded hard
|
||||
artifact (a PRD, a conformance review, a design decision) belongs in a smaller,
|
||||
reasoning-strong session. A wide task in a small window stalls the task — too
|
||||
wide is not the same as too hard, and it is the coordinator's assignment error,
|
||||
not the peer's failure.
|
||||
- **Checkpoint at ~70%, never compact mid-task.** A terse ledger sent to the
|
||||
coordinator before the window fills survives; one reconstructed afterwards
|
||||
loses exactly the identifiers — bead IDs, exact counts — that made it worth
|
||||
having. Instruct every long-running peer to report and stop there.
|
||||
- **One writer per resource.** Exactly one session writes the tracker. Two
|
||||
writers produce double-closes, contradictory verdicts, and counts nobody can
|
||||
reconcile. When a sweep changes hands, the successor re-derives them rather
|
||||
than inheriting the predecessor's ledger as fact.
|
||||
|
||||
## Traps worth carrying
|
||||
|
||||
- **`touch` does not invalidate a Task source.** Task hashes file _content_, so a
|
||||
@@ -143,11 +181,41 @@ build` still reports the binary up to date, shipping the old value. Tracked as
|
||||
reaches, or changes a wire type, passes its own gate and fails
|
||||
`task check` on a missing `tools/go.sum` entry or a stale schema. Such a
|
||||
lane runs `go -C tools mod tidy` and `task docs:generate` and commits both.
|
||||
Adding or editing a page under `docs/` — a PRD included — changes
|
||||
`docs/data/generated/dev-docs.json`, which gains or loses a page: regenerate it
|
||||
and commit it in the same commit, or `docs:artifact:check` fails. That failure
|
||||
lands on `main`, not in the lane, if the ref moves first.
|
||||
- **Untracked files in the shared checkout are other sessions'.** prdlint
|
||||
scratch (`docs/prds/rules.jsonl`), editor state, and gate-written artifacts
|
||||
appear and vanish under a lane. Never chase, add, stage or commit them: a
|
||||
merge train's scope is its own lanes' files, and nothing else.
|
||||
|
||||
## codegraph answers symbol questions cheaply
|
||||
|
||||
The maintainer's `codegraph` MCP server indexes this repository. Prefer it to
|
||||
grep or whole-file reading for "who calls X", "is this dead", "what does this
|
||||
change touch": it enumerates call sites that a grep only summarises, and labels
|
||||
each caller's confidence so interface fan-out is not mistaken for direct calls.
|
||||
|
||||
- **`pr_impact <base> <head>`** lists changed symbols with per-symbol caller and
|
||||
test counts. Read `interface_dispatch` and the inferred tests alongside
|
||||
`test_count`: a method reached through an interface reports a low direct test
|
||||
count while many indirect tests reach it, and the compact line alone invites
|
||||
the wrong conclusion.
|
||||
- **It is a derived cache.** `scip-go` and tree-sitter rebuild it, and a query
|
||||
indexes the revisions it names, so a cold query is slow and losing the index
|
||||
costs a rebuild rather than data. `list_repositories` reports the indexed
|
||||
revision — compare it with the tree before trusting a default-revision answer.
|
||||
- **Stagger heavy queries.** Concurrent sessions share one instance, and
|
||||
**name-based** `symbol_context` is what locks: it returns `database is locked`
|
||||
or times out, while the same symbol **by id** returns immediately. Query
|
||||
serially and retry rather than assuming a hang.
|
||||
- **Report problems one line at a time** in
|
||||
`/work/apps/codegraph/data/feedback.jsonl` — one JSON object per line, keys
|
||||
`date`, `repo`, `task`, `tools`, `helped`, `missed`, `wrong`, `slow`. A raw
|
||||
newline inside a string makes the line invalid and breaks every reader; a
|
||||
multi-line entry corrupted that file once. Validate, append, never rewrite.
|
||||
|
||||
## Tracker conventions
|
||||
|
||||
`bd` is the only tracker; no markdown TODO lists, no local trackers.
|
||||
|
||||
@@ -107,7 +107,7 @@ Do not expose these helper flags as daemon settings.
|
||||
| Keys | Default, validation, and consumer | Status |
|
||||
| -------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------- |
|
||||
| `work_dir`, `state_dir` | Derive from `$XDG_DATA_HOME/archie`, else `$HOME/.local/share/archie`; explicit `~` paths are home-expanded. `state_dir` holds the embedded NATS store and endpoint file, task logs and the readiness disk target. | production-wired |
|
||||
| `skills_dir` | Empty falls back to `work_dir` for startup workflow registry. | partially-wired |
|
||||
| `skills_dir` | Empty falls back to `work_dir` for startup workflow registry. Also the skills store `kitrun.Launcher` mounts read-only at a Kit's `agent-skills@1` path, read live per launch; empty withholds the mount. | partially-wired |
|
||||
| `plugin_dir` | Empty disables daemon plugin loading; configured directory loaded in `internal/app/archied`. | production-wired |
|
||||
| `poll_interval` | Default `60s`; root poll loop uses it, identities may override only interval. | production-wired |
|
||||
| `label` | No default or validation; used for `dispatch.trigger = "label"` or `"either"`. | production-wired |
|
||||
@@ -175,6 +175,9 @@ looking at before reporting one:
|
||||
| `volume_ttl` | Default `72h` only when enabled; negative rejected. |
|
||||
| `pull_policy` | Default `missing` when enabled. Pool code recognises `missing` and `always`; other strings silently skip pre-pull. |
|
||||
| `network` | Empty uses best-effort self-network detection. Repository overlay pins `archie-core_default`. |
|
||||
| `profiles` | Named agent execution environments (image or Kit); resolved per task dispatch (`ContainerConfig.Profile`). Own control-plane resource `agent-profiles` (`json:"-"` on the field so `container-runtime-policies` never carries it), `ApplyMode: live` -- a profile change applies without a restart, unlike the rest of `[containers]`. |
|
||||
| `credentials` | Maps a Kit `credential@1` service to a secret (`config.CredentialBinding`). Own control-plane resource `credential-bindings`, `ApplyMode: live`, `json:"-"` on the field. `kitrun.Launcher` reads it fresh from the live `config.Holder` on every `Launch`, never a value captured at boot -- see `internal/infrastructure/kitrun/launcher.go`'s `resolveCredentials`. A binding alone grants nothing; see `org`/`granted_credentials` below. |
|
||||
| `org` / `granted_credentials` (root and per-identity) | An identity's org and the `credentials` service names it may resolve. `daemon.runKitTask` reads both fresh per dispatch (`d.configFor(task)`) and passes them to `kitrun.Request`; `config.ContainerConfig.BoundCredentials` computes the declared (Kit) ∩ granted (identity) ∩ org-matched intersection -- neither declared nor granted widens the other. |
|
||||
|
||||
### Channel settings
|
||||
|
||||
|
||||
+132
@@ -5,6 +5,138 @@ release's per-component sections are labelled beneath its heading.
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
## [1.45.0] - 2026-09-30
|
||||
|
||||
### archied
|
||||
|
||||
- fix(eda): reject a result map missing a field or needing a conversion
|
||||
- feat(eda): per-org workflow enable/disable gating bindings
|
||||
- feat(telegram): carry inbound media through the chat turn
|
||||
- fix(prsource): use a CodeQL-recognised containment guard when extracting archives
|
||||
- feat(store): key control-plane resources by (org, kind)
|
||||
- fix(store): refuse resource keys the audit key cannot disambiguate
|
||||
- fix(daemon): resume the task branch before container acquisition
|
||||
- feat(webui): show attachment metadata in the session transcript
|
||||
- feat(webui): name a workflow's declared inputs on the work-request form
|
||||
- feat(controlplane): carry the caller org from the request principal
|
||||
- fix(webui): the workflow handlers act in the caller's org
|
||||
- feat(kitrun): render the OAuth credential file with sentinels
|
||||
- feat(store): record accepted package authority against the pin
|
||||
- fix(workflow): the own-PR flow no longer parks on the operator-approval gate
|
||||
- feat(gateway): a TTL-bounded dedup gate for redelivered platform messages
|
||||
- feat(egress): capture the OAuth scope set and carry it to the harness secret
|
||||
- feat(kitrun): render the OAuth scopes and omit an uncaptured primary key
|
||||
- feat(store): project installed package contributions into org resources
|
||||
- feat(gateway): coalesce rapid-fire text events into one turn
|
||||
- fix(config): expand plugin, module and skills dirs like every other operator path
|
||||
- fix(webui): drop the config schema's editability advert
|
||||
- feat(webui): events counts, YAML reading, log rows and dashboard filters
|
||||
|
||||
### archie-agent
|
||||
|
||||
- feat(eda): per-org workflow enable/disable gating bindings
|
||||
- feat(telegram): carry inbound media through the chat turn
|
||||
- fix(prsource): use a CodeQL-recognised containment guard when extracting archives
|
||||
- feat(store): key control-plane resources by (org, kind)
|
||||
- feat(controlplane): carry the caller org from the request principal
|
||||
- feat(kitrun): render the OAuth credential file with sentinels
|
||||
- feat(store): record accepted package authority against the pin
|
||||
- fix(workflow): the own-PR flow no longer parks on the operator-approval gate
|
||||
- feat(egress): capture the OAuth scope set and carry it to the harness secret
|
||||
- feat(kitrun): render the OAuth scopes and omit an uncaptured primary key
|
||||
- feat(store): project installed package contributions into org resources
|
||||
|
||||
## [1.44.1] - 2026-09-29
|
||||
|
||||
### archied
|
||||
|
||||
Two fixes to tasks that could not get past their workflow definition.
|
||||
|
||||
- **Approving a task no longer parks it again.** A task requeued under a
|
||||
different workflow kept the previous run's definition pinned, so the worker
|
||||
refused to compile the dispatch — it named `feasibility` while the row named
|
||||
`implement` — and the task parked immediately, identically on every further
|
||||
approval, which left `decline` as the only working operator action.
|
||||
The daemon now re-pins whenever the pinned definition's id disagrees with the
|
||||
task's workflow. A pin that is present, digest-valid and id-consistent is
|
||||
still a strict no-op, so an operator's own definition override survives a
|
||||
dispatch unchanged.
|
||||
- **A shipped workflow definition now reaches an existing install.** A stored
|
||||
seed was consulted only for a resource the store did not already hold, so a
|
||||
document that changed in the build never reached a database an earlier
|
||||
release had seeded. For workflow definitions that is a total outage rather
|
||||
than a stale setting: the collection validates as one document, so a stored
|
||||
step type this build no longer has failed every task's pin, whatever workflow
|
||||
the task named — and the documented recovery, removing the resource and
|
||||
restarting, wrote nothing either, because the store answered the seed's known
|
||||
request ID from a history that outlives the resource. A seed now refreshes a
|
||||
kind it wrote the newest revision of and re-creates a resource that is gone,
|
||||
while an operator's own replacement is never undone.
|
||||
|
||||
### archie-agent
|
||||
|
||||
The runtime image is rebuilt with this release and links the shared workflow
|
||||
package carrying the definition-id helper above. Hosts that run agent
|
||||
containers need `docker compose pull agent` after updating to pick it up.
|
||||
|
||||
## [1.44.0] - 2026-09-29
|
||||
|
||||
### archied
|
||||
|
||||
Archie can now review pull requests.
|
||||
|
||||
- **Reviews on request and by watch.** Ask in chat or on the dashboard work form, add a repository to the watch list, or just let archie review its own PRs before it opens them. Review intensity follows a depth dial (quick/standard/deep) classified from the size of the change, and every finished review passes a verification layer — coverage-gap and cross-finding consistency checks — before it is produced.
|
||||
- **No forge credential reaches the review sandbox.** The daemon prefetches the pull request's data and rebuilds its source snapshot over the forge's HTTP API, so the agent container works from an isolated copy with no read access to the repository's credentials.
|
||||
- **Reviews stop at the operator gate before posting.** `review.precision_gate` / `approve_before_post` decide whether a finished review posts itself or parks for operator approval. With this release the parked state is a stop sign, not a checkpoint: the approve/reject/re-review responses behind the gate are not wired yet, and the gate's settings are not yet editable in the dashboard (configure them in `config.toml`). A parked review sits until that follow-up lands.
|
||||
- The adversarial self-review pass archie previously ran before opening its own PRs is superseded by this pipeline and has been removed.
|
||||
- Hardened harness input handling: harness identifiers are bounded to integer types.
|
||||
|
||||
### archie-agent
|
||||
|
||||
The runtime image is rebuilt with this release; it links the shared pr-review workflow packages behind the reviews above. Hosts that run agent containers need `docker compose pull agent` after updating to pick it up.
|
||||
|
||||
## [1.43.0] - 2026-09-28
|
||||
|
||||
### archied
|
||||
|
||||
- **Organisations.** Tasks, identities and settings now belong to an org. An
|
||||
existing install is upgraded into a default org when the State Store first
|
||||
starts; the upgrade resumes if interrupted. Task de-duplication is scoped
|
||||
per org and identity.
|
||||
- **Access policies are enforced** at the dashboard, the API and task
|
||||
dispatch, with shipped roles and a rule that nothing crosses between orgs.
|
||||
Denials are recorded and reported on the health page. If a policy locks
|
||||
you out, `archied access reset --org <org>` (or `--instance`) on the State
|
||||
Store host restores the shipped defaults.
|
||||
- **Workflows can call workflows** with a `workflow.call` step. Inputs and
|
||||
call cycles are checked when the workflow is saved, and the caller waits
|
||||
on the callee's result.
|
||||
- **Runs record each step.** A run's stages and agent calls are stored as
|
||||
steps, the task detail page reads them, and stopping a task or archiving
|
||||
it goes through one cancel path. After a crash, steps left running are
|
||||
marked interrupted. Archiving a task removes its worktree.
|
||||
- **Model roles, repositories, scheduling policy, providers and agent
|
||||
profiles apply without a restart.**
|
||||
- **Kit harness profiles:**
|
||||
- `kit` is now one digest-pinned reference, a workload Kit or a published
|
||||
Kit set, not a list. **Rewrite `kit = [...]` in `config.toml` or the
|
||||
agent-profiles settings as the single reference**; a list no longer
|
||||
loads. Compose mixins by publishing a Kit set.
|
||||
- OAuth logins are handled on the host: the egress proxy refreshes tokens,
|
||||
stores them encrypted, and gives the container only placeholders.
|
||||
- A Kit's skills request mounts `skills_dir` read-only, and its
|
||||
instructions file (such as `CLAUDE.md`) is written beside the workspace,
|
||||
which is now `/archie/workspace`.
|
||||
- A run still cannot be granted the credential a Kit needs, so a Kit that
|
||||
requires one is refused at launch.
|
||||
- Rate-limited webhook deliveries get `429`.
|
||||
- `archie-gateway` and `archie-state-store` report ready to systemd.
|
||||
|
||||
### archie-agent
|
||||
|
||||
- Runs workflow calls, records its steps and agent calls, and runs Kit
|
||||
harness stages under the profile's Kit.
|
||||
|
||||
## [1.42.0] - 2026-09-26
|
||||
|
||||
### archied
|
||||
|
||||
@@ -35,7 +35,18 @@ plugin engine, satisfy
|
||||
|
||||
Before changing an area (frontend UI, agent, workflows, daemon, State Store,
|
||||
control plane), read its page in `docs/development/`: it names every layer the
|
||||
change must reach.
|
||||
change must reach. This is not optional colour reading -- archie-core is built
|
||||
as an extensible, customisable surface, not a fixed product, so a change that
|
||||
looks complete inside one package routinely is not: a new setting that never
|
||||
reaches the control-plane schema descriptor and dashboard parses but never
|
||||
renders, is never editable, and never live-applies, exactly like a config
|
||||
field with no consumer. The dev-docs page for the area is where that
|
||||
cross-layer reach is written down; read it before starting, not after
|
||||
something downstream turns out silently unwired. This applies whether the
|
||||
work is yours directly or handed to a subagent or crew worker -- carry the
|
||||
relevant docs/development page into their prompt, the same way a bead ID is
|
||||
carried; "figure out what else needs updating" left implicit is exactly the
|
||||
gap this note exists to close.
|
||||
|
||||
## Scope Discipline
|
||||
|
||||
@@ -288,6 +299,29 @@ StateStoreGrantIssuer` (`staterpc.GrantIssuer`) registers a fresh
|
||||
Verify the failure originates from test assertions, not compilation errors.
|
||||
Do not write tests that restate an assignment or a constant: a test that
|
||||
cannot fail for an interesting reason is noise in the gate.
|
||||
- **A test is a maintenance liability, not free insurance.** Every test
|
||||
added is code the project now carries forever: it must compile, it must
|
||||
keep passing as the code around it changes, and someone reads it during
|
||||
every future change to that area. Write one because a real regression
|
||||
would slip through without it, not because the function was touched.
|
||||
- **Never pin a literal end-user config value, database row, or settings
|
||||
document as the thing under test.** Test the validation rule, the
|
||||
migration's shape, or the round-trip contract -- not one operator's
|
||||
specific `config.toml` value, a hand-picked DB fixture that mirrors real
|
||||
data, or a setting's current default. Those change for reasons that have
|
||||
nothing to do with a regression, and a test pinned to one breaks on
|
||||
every such change, which is cost with no signal.
|
||||
- **Test-only helpers, fakes and fixtures live in `_test.go` files (or a
|
||||
package no production `.go` file imports), never in a file the binary
|
||||
ships.** `go build` does not compile `_test.go` files into the binary,
|
||||
but an exported "test helper" living in a regular source file compiles
|
||||
into every binary that imports the package, whether or not a test ever
|
||||
runs. If a helper must be shared across packages, put it behind a
|
||||
build-tagged or `_test.go`-suffixed file in an `xtest`-style package,
|
||||
not behind a normal export.
|
||||
- **Coverage is not the goal.** A codebase that grows mostly because tests
|
||||
multiplied faster than the feature they cover is a symptom, not
|
||||
progress -- prefer fewer, sharper tests over one per line changed.
|
||||
2. **Green (Implementation):** Implement minimal code to satisfy the failing
|
||||
tests.
|
||||
3. **Quality Gate:** Run `task check`.
|
||||
@@ -307,10 +341,12 @@ StateStoreGrantIssuer` (`staterpc.GrantIssuer`) registers a fresh
|
||||
separate fresh-context reviewer pass on every change as a matter of course.
|
||||
Red-green TDD plus `task check` is the gate; a manual adversarial pass is
|
||||
opt-in per request — ask before running one. This is the rule for a human or
|
||||
agent _contributor_. Separately, archied runs the same adversarial review
|
||||
automatically on the PRs it opens (gated per repo by `repo.review_enabled`)
|
||||
— see `docs/architecture/adversarial-review.md`. The two paths are distinct:
|
||||
you run one when asked; archied runs one before it opens a PR.
|
||||
agent _contributor_. Separately, archied runs its own PR review pipeline
|
||||
(`docs/prds/pr-review-agent.md`) before it opens a PR of its own — see that
|
||||
PRD's Triggers section ("archie's own PRs"). It supersedes the older
|
||||
single-reviewer stage `docs/architecture/adversarial-review.md` described
|
||||
(`repo.review_enabled` no longer exists). The two paths are distinct: you
|
||||
run a manual pass when asked; archied runs its own before it opens a PR.
|
||||
6. **Linter Guard:**
|
||||
|
||||
- When using `errorlint` fixes, ensure boolean predicates (e.g.
|
||||
|
||||
@@ -0,0 +1,202 @@
|
||||
|
||||
Apache License
|
||||
Version 2.0, January 2004
|
||||
http://www.apache.org/licenses/
|
||||
|
||||
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||
|
||||
1. Definitions.
|
||||
|
||||
"License" shall mean the terms and conditions for use, reproduction,
|
||||
and distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
"Licensor" shall mean the copyright owner or entity authorized by
|
||||
the copyright owner that is granting the License.
|
||||
|
||||
"Legal Entity" shall mean the union of the acting entity and all
|
||||
other entities that control, are controlled by, or are under common
|
||||
control with that entity. For the purposes of this definition,
|
||||
"control" means (i) the power, direct or indirect, to cause the
|
||||
direction or management of such entity, whether by contract or
|
||||
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||
|
||||
"You" (or "Your") shall mean an individual or Legal Entity
|
||||
exercising permissions granted by this License.
|
||||
|
||||
"Source" form shall mean the preferred form for making modifications,
|
||||
including but not limited to software source code, documentation
|
||||
source, and configuration files.
|
||||
|
||||
"Object" form shall mean any form resulting from mechanical
|
||||
transformation or translation of a Source form, including but
|
||||
not limited to compiled object code, generated documentation,
|
||||
and conversions to other media types.
|
||||
|
||||
"Work" shall mean the work of authorship, whether in Source or
|
||||
Object form, made available under the License, as indicated by a
|
||||
copyright notice that is included in or attached to the work
|
||||
(an example is provided in the Appendix below).
|
||||
|
||||
"Derivative Works" shall mean any work, whether in Source or Object
|
||||
form, that is based on (or derived from) the Work and for which the
|
||||
editorial revisions, annotations, elaborations, or other modifications
|
||||
represent, as a whole, an original work of authorship. For the purposes
|
||||
of this License, Derivative Works shall not include works that remain
|
||||
separable from, or merely link (or bind by name) to the interfaces of,
|
||||
the Work and Derivative Works thereof.
|
||||
|
||||
"Contribution" shall mean any work of authorship, including
|
||||
the original version of the Work and any modifications or additions
|
||||
to that Work or Derivative Works thereof, that is intentionally
|
||||
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||
or by an individual or Legal Entity authorized to submit on behalf of
|
||||
the copyright owner. For the purposes of this definition, "submitted"
|
||||
means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems,
|
||||
and issue tracking systems that are managed by, or on behalf of, the
|
||||
Licensor for the purpose of discussing and improving the Work, but
|
||||
excluding communication that is conspicuously marked or otherwise
|
||||
designated in writing by the copyright owner as "Not a Contribution."
|
||||
|
||||
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||
on behalf of whom a Contribution has been received by Licensor and
|
||||
subsequently incorporated within the Work.
|
||||
|
||||
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the
|
||||
Work and such Derivative Works in Source or Object form.
|
||||
|
||||
3. Grant of Patent License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
(except as stated in this section) patent license to make, have made,
|
||||
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||
where such license applies only to those patent claims licensable
|
||||
by such Contributor that are necessarily infringed by their
|
||||
Contribution(s) alone or by combination of their Contribution(s)
|
||||
with the Work to which such Contribution(s) was submitted. If You
|
||||
institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||
or a Contribution incorporated within the Work constitutes direct
|
||||
or contributory patent infringement, then any patent licenses
|
||||
granted to You under this License for that Work shall terminate
|
||||
as of the date such litigation is filed.
|
||||
|
||||
4. Redistribution. You may reproduce and distribute copies of the
|
||||
Work or Derivative Works thereof in any medium, with or without
|
||||
modifications, and in Source or Object form, provided that You
|
||||
meet the following conditions:
|
||||
|
||||
(a) You must give any other recipients of the Work or
|
||||
Derivative Works a copy of this License; and
|
||||
|
||||
(b) You must cause any modified files to carry prominent notices
|
||||
stating that You changed the files; and
|
||||
|
||||
(c) You must retain, in the Source form of any Derivative Works
|
||||
that You distribute, all copyright, patent, trademark, and
|
||||
attribution notices from the Source form of the Work,
|
||||
excluding those notices that do not pertain to any part of
|
||||
the Derivative Works; and
|
||||
|
||||
(d) If the Work includes a "NOTICE" text file as part of its
|
||||
distribution, then any Derivative Works that You distribute must
|
||||
include a readable copy of the attribution notices contained
|
||||
within such NOTICE file, excluding those notices that do not
|
||||
pertain to any part of the Derivative Works, in at least one
|
||||
of the following places: within a NOTICE text file distributed
|
||||
as part of the Derivative Works; within the Source form or
|
||||
documentation, if provided along with the Derivative Works; or,
|
||||
within a display generated by the Derivative Works, if and
|
||||
wherever such third-party notices normally appear. The contents
|
||||
of the NOTICE file are for informational purposes only and
|
||||
do not modify the License. You may add Your own attribution
|
||||
notices within Derivative Works that You distribute, alongside
|
||||
or as an addendum to the NOTICE text from the Work, provided
|
||||
that such additional attribution notices cannot be construed
|
||||
as modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and
|
||||
may provide additional or different license terms and conditions
|
||||
for use, reproduction, or distribution of Your modifications, or
|
||||
for any such Derivative Works as a whole, provided Your use,
|
||||
reproduction, and distribution of the Work otherwise complies with
|
||||
the conditions stated in this License.
|
||||
|
||||
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||
any Contribution intentionally submitted for inclusion in the Work
|
||||
by You to the Licensor shall be under the terms and conditions of
|
||||
this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify
|
||||
the terms of any separate license agreement you may have executed
|
||||
with Licensor regarding such Contributions.
|
||||
|
||||
6. Trademarks. This License does not grant permission to use the trade
|
||||
names, trademarks, service marks, or product names of the Licensor,
|
||||
except as required for reasonable and customary use in describing the
|
||||
origin of the Work and reproducing the content of the NOTICE file.
|
||||
|
||||
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||
agreed to in writing, Licensor provides the Work (and each
|
||||
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
implied, including, without limitation, any warranties or conditions
|
||||
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||
appropriateness of using or redistributing the Work and assume any
|
||||
risks associated with Your exercise of permissions under this License.
|
||||
|
||||
8. Limitation of Liability. In no event and under no legal theory,
|
||||
whether in tort (including negligence), contract, or otherwise,
|
||||
unless required by applicable law (such as deliberate and grossly
|
||||
negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special,
|
||||
incidental, or consequential damages of any character arising as a
|
||||
result of this License or out of the use or inability to use the
|
||||
Work (including but not limited to damages for loss of goodwill,
|
||||
work stoppage, computer failure or malfunction, or any and all
|
||||
other commercial damages or losses), even if such Contributor
|
||||
has been advised of the possibility of such damages.
|
||||
|
||||
9. Accepting Warranty or Additional Liability. While redistributing
|
||||
the Work or Derivative Works thereof, You may choose to offer,
|
||||
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||
or other liability obligations and/or rights consistent with this
|
||||
License. However, in accepting such obligations, You may act only
|
||||
on Your own behalf and on Your sole responsibility, not on behalf
|
||||
of any other Contributor, and only if You agree to indemnify,
|
||||
defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason
|
||||
of your accepting any such warranty or additional liability.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
APPENDIX: How to apply the Apache License to your work.
|
||||
|
||||
To apply the Apache License to your work, attach the following
|
||||
boilerplate notice, with the fields enclosed by brackets "[]"
|
||||
replaced with your own identifying information. (Don't include
|
||||
the brackets!) The text should be enclosed in the appropriate
|
||||
comment syntax for the file format. We also recommend that a
|
||||
file or class name and description of purpose be included on the
|
||||
same "printed page" as the copyright notice for easier
|
||||
identification within third-party archives.
|
||||
|
||||
Copyright [yyyy] [name of copyright owner]
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
@@ -11,3 +11,9 @@ deduplication, line mapping and review-event selection.
|
||||
PR-AF declares the Apache License, Version 2.0 in its pyproject.toml and
|
||||
ships no license file. A copy of the License is available at
|
||||
https://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
This product includes software from the Cedar project
|
||||
(https://github.com/cedar-policy/cedar), Copyright Amazon.com, Inc. or its
|
||||
affiliates, licensed under the Apache License, Version 2.0, as implemented by
|
||||
github.com/cedar-policy/cedar-go, which declares the same license in its
|
||||
repository. This repository links the library; it derives no source from it.
|
||||
@@ -177,3 +177,7 @@ but systemd is optional.
|
||||
|
||||
Contributions should follow [AGENTS.md](AGENTS.md), including its testing,
|
||||
generated-file, and commit rules.
|
||||
|
||||
## License
|
||||
|
||||
Copyright 2026 Sam Catlow. Licensed under the [Apache License, Version 2.0](LICENSE). Third-party attributions are in [NOTICE](NOTICE).
|
||||
+1
-1
@@ -154,7 +154,7 @@ tasks:
|
||||
- bash tools/webhook-send.sh {{.CLI_ARGS}}
|
||||
|
||||
bench:prreview:
|
||||
desc: Score PR review findings on the Martian benchmark (-- -findings DIR; --help for flags)
|
||||
desc: Review or rescore the Martian benchmark (-- -review-model PROVIDER/MODEL -classification-model PROVIDER/MODEL; --help for flags)
|
||||
cmds:
|
||||
- go run ./cmd/archie-prbench {{.CLI_ARGS}}
|
||||
|
||||
|
||||
@@ -20,13 +20,20 @@ func main() { os.Exit(run()) }
|
||||
func run() int {
|
||||
var opts prbench.Options
|
||||
var problems string
|
||||
flag.StringVar(&opts.Config, "config", configuration.DefaultConfigPath(), "configuration file whose providers serve the judge model")
|
||||
flag.StringVar(&opts.Fixtures, "findings", "", "directory of <problem id>.json findings to score")
|
||||
flag.StringVar(&opts.Config, "config", configuration.DefaultConfigPath(), "configuration file whose providers serve the reviewer and judge")
|
||||
flag.StringVar(&opts.Fixtures, "findings", "", "directory of <problem id>.json findings to rescore; omit to review live")
|
||||
flag.StringVar(&opts.ReviewModel, "review-model", "", "provider/model for the review role in live runs")
|
||||
flag.StringVar(&opts.ClassifyModel, "classification-model", "", "provider/model for the classification role in live runs")
|
||||
flag.StringVar(&opts.JudgeModel, "judge-model", "anthropic/claude-sonnet-4.6", "provider/model of the independent judge")
|
||||
flag.StringVar(&opts.Out, "out", "prbench-out", "directory for per-problem results and summary.json")
|
||||
flag.StringVar(&opts.Out, "out", "bin/prbench-results", "directory for per-problem results and summary.json")
|
||||
flag.StringVar(&opts.Resume, "resume", "", "reuse complete results from a previous run with the same models")
|
||||
flag.StringVar(&problems, "problems", "", "comma-separated problem ids (default: all)")
|
||||
flag.IntVar(&opts.Concurrency, "concurrency", 4, "problems judged at once")
|
||||
flag.Parse()
|
||||
opts.GitHubToken = os.Getenv("GH_TOKEN")
|
||||
if opts.GitHubToken == "" {
|
||||
opts.GitHubToken = os.Getenv("GITHUB_TOKEN")
|
||||
}
|
||||
if problems != "" {
|
||||
opts.Problems = strings.Split(problems, ",")
|
||||
}
|
||||
|
||||
@@ -338,6 +338,7 @@ func TestStateStoreRealProcessSmoke(t *testing.T) {
|
||||
if testing.Short() {
|
||||
t.Skip("real-process smoke test builds and execs the binary; skip under -short")
|
||||
}
|
||||
t.Parallel()
|
||||
dir := t.TempDir()
|
||||
bin := buildBinary(t, dir)
|
||||
cfg := writeConfigWithServiceListen(t, dir)
|
||||
@@ -355,7 +356,7 @@ func TestStateStoreRealProcessSmoke(t *testing.T) {
|
||||
// Combined task/event/capture view: a task, an event on that task, and an
|
||||
// unrelated capture written through one consumer, read back across all
|
||||
// three surfaces in a single pass (the dashboard/observability read path).
|
||||
task, err := cl.EnqueueChatTask(ctx, "acme", "widget", "verify state store", "body", "implement", "")
|
||||
task, err := cl.EnqueueChatTask(ctx, "acme", "widget", "verify state store", "body", "implement", "", nil)
|
||||
if err != nil || task == nil {
|
||||
t.Fatalf("EnqueueChatTask = %+v, %v", task, err)
|
||||
}
|
||||
@@ -453,6 +454,7 @@ func TestStateStoreRealProcessDeadline(t *testing.T) {
|
||||
if testing.Short() {
|
||||
t.Skip("real-process smoke test builds and execs the binary; skip under -short")
|
||||
}
|
||||
t.Parallel()
|
||||
dir := t.TempDir()
|
||||
bin := buildBinary(t, dir)
|
||||
cfg := writeMinimalConfig(t, dir)
|
||||
@@ -479,13 +481,14 @@ func TestStateStoreRealProcessRestartRecovery(t *testing.T) {
|
||||
if testing.Short() {
|
||||
t.Skip("real-process smoke test builds and execs the binary; skip under -short")
|
||||
}
|
||||
t.Parallel()
|
||||
dir := t.TempDir()
|
||||
bin := buildBinary(t, dir)
|
||||
cfg := writeMinimalConfig(t, dir)
|
||||
|
||||
first := startStateStoreProcess(t, bin, cfg)
|
||||
s1 := dial(t, first.addr)
|
||||
task, err := s1.EnqueueChatTask(t.Context(), "acme", "widget", "survive restart", "body", "implement", "")
|
||||
task, err := s1.EnqueueChatTask(t.Context(), "acme", "widget", "survive restart", "body", "implement", "", nil)
|
||||
if err != nil || task == nil {
|
||||
t.Fatalf("first EnqueueChatTask = %+v, %v", task, err)
|
||||
}
|
||||
@@ -525,6 +528,7 @@ func TestStateStoreRealProcessTokenProtectedCaptureStream(t *testing.T) {
|
||||
if testing.Short() {
|
||||
t.Skip("real-process smoke test builds and execs the binary; skip under -short")
|
||||
}
|
||||
t.Parallel()
|
||||
const token = "operator-secret-token"
|
||||
dir := t.TempDir()
|
||||
bin := buildBinary(t, dir)
|
||||
@@ -572,6 +576,7 @@ func TestStateStoreRealProcessRemoteSurfaces(t *testing.T) {
|
||||
if testing.Short() {
|
||||
t.Skip("real-process smoke test builds and execs the binary; skip under -short")
|
||||
}
|
||||
t.Parallel()
|
||||
dir := t.TempDir()
|
||||
bin := buildBinary(t, dir)
|
||||
cfg := writeMinimalConfig(t, dir)
|
||||
|
||||
@@ -52,7 +52,7 @@ func recoveryFixture(t *testing.T) (string, *pgstore.TaskDB) {
|
||||
// seedTask writes one task so the database holds more than its settings.
|
||||
func seedTask(t *testing.T, st *pgstore.TaskDB, title string) {
|
||||
t.Helper()
|
||||
if _, err := st.EnqueueChatTask(t.Context(), "acme", "widget", title, "body", "implement", ""); err != nil {
|
||||
if _, err := st.EnqueueChatTask(t.Context(), "acme", "widget", title, "body", "implement", "", nil); err != nil {
|
||||
t.Fatalf("seed task %q: %v", title, err)
|
||||
}
|
||||
}
|
||||
@@ -259,7 +259,7 @@ func TestRecoveryRollbackReplaysTheRevisionThroughReplace(t *testing.T) {
|
||||
if !strings.Contains(stdout, controlplane.ModelRoleAssignmentsKind) {
|
||||
t.Errorf("rollback must name the resource it replayed; stdout = %q", stdout)
|
||||
}
|
||||
resource, err := st.Resource(t.Context(), controlplane.ModelRoleAssignmentsKind)
|
||||
resource, err := st.Resource(t.Context(), storecontract.DefaultOrgID, controlplane.ModelRoleAssignmentsKind)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
@@ -269,7 +269,7 @@ func TestRecoveryRollbackReplaysTheRevisionThroughReplace(t *testing.T) {
|
||||
if resource.Version != 3 {
|
||||
t.Errorf("resource version = %d, want a new revision (3) rather than a rewrite of the old one", resource.Version)
|
||||
}
|
||||
history, err := st.ResourceHistory(t.Context(), controlplane.ModelRoleAssignmentsKind, 0)
|
||||
history, err := st.ResourceHistory(t.Context(), storecontract.DefaultOrgID, controlplane.ModelRoleAssignmentsKind, 0)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
@@ -293,7 +293,7 @@ func TestRecoveryRollbackRestoresANamedRevision(t *testing.T) {
|
||||
if code != 0 {
|
||||
t.Fatalf("rollback exited %d: %s", code, stderr)
|
||||
}
|
||||
resource, err := st.Resource(t.Context(), controlplane.ModelRoleAssignmentsKind)
|
||||
resource, err := st.Resource(t.Context(), storecontract.DefaultOrgID, controlplane.ModelRoleAssignmentsKind)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
@@ -463,7 +463,7 @@ func storedResourceCount(t *testing.T, stdout string) int {
|
||||
// a silent no-op.
|
||||
func seedResource(t *testing.T, st *pgstore.TaskDB, kind, value, label string) {
|
||||
t.Helper()
|
||||
current, err := st.Resource(t.Context(), kind)
|
||||
current, err := st.Resource(t.Context(), storecontract.DefaultOrgID, kind)
|
||||
expected := int64(0)
|
||||
if err == nil {
|
||||
expected = current.Version
|
||||
@@ -477,7 +477,8 @@ func seedResource(t *testing.T, st *pgstore.TaskDB, kind, value, label string) {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := st.PutResource(t.Context(), storecontract.ResourceWrite{
|
||||
Kind: kind, Value: encoded, Actor: label, Source: "test",
|
||||
OrgID: storecontract.DefaultOrgID,
|
||||
Kind: kind, Value: encoded, Actor: label, Source: "test",
|
||||
RequestID: fmt.Sprintf("%s-%d", label, expected+1), ExpectedVersion: expected,
|
||||
}); err != nil {
|
||||
t.Fatalf("seed resource %s: %v", kind, err)
|
||||
|
||||
@@ -2,6 +2,7 @@
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"os"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/app/archied"
|
||||
@@ -15,5 +16,10 @@ func main() {
|
||||
if archied.IsSetupArgs(args) {
|
||||
os.Exit(archied.RunSetup(args[1:], os.Stdin, os.Stdout, os.Stderr))
|
||||
}
|
||||
// The access recovery command runs before the daemon's flags are parsed:
|
||||
// it is a State Store host operation, not a daemon run.
|
||||
if archied.IsAccessResetArgs(args) {
|
||||
os.Exit(archied.RunAccessReset(context.Background(), args[2:], os.Stderr))
|
||||
}
|
||||
os.Exit(archied.Run())
|
||||
}
|
||||
+17
-5
@@ -34,6 +34,8 @@ label = "archie"
|
||||
bot_user = "vectis-labs-archie"
|
||||
# 0 switches the cap off; omit the key to take the built-in default (400).
|
||||
diff_cap_lines = 400
|
||||
# org = "acme" # empty means the default org (a single-operator install's one identity)
|
||||
# granted_credentials = ["openai"] # credential@1 services the root identity may resolve (see [containers.credentials])
|
||||
|
||||
# how many operator-triggered retries a parked task gets
|
||||
# before it moves to dead (global default; set per-repo to
|
||||
@@ -75,6 +77,8 @@ token = { engine = "env", key = "ARCHIE_GITHUB_TOKEN" }
|
||||
# name = "personal" # required; namespaces logs/events/NATS subjects
|
||||
# bot_user = "your-bot" # required
|
||||
# forge = { type = "github", host = "https://github.com", token = { engine = "env", key = "ARCHIE_GITHUB_TOKEN_PERSONAL" } }
|
||||
# org = "acme" # empty inherits the shared org (empty = default)
|
||||
# granted_credentials = ["openai"] # credential@1 services this identity may resolve (see [containers.credentials])
|
||||
|
||||
[dispatch]
|
||||
# Can be of "assignee", "label", or "either"
|
||||
@@ -446,10 +450,21 @@ target = "127.0.0.1:9090" # REQUIRED. The State Store gRPC address arch
|
||||
# image = "archie-agent-net:local" # docker compose build agent-net; empty uses [containers].image
|
||||
# tools = [] # allowlist over MCP, script and plugin tools; empty allows all
|
||||
# A Kit profile runs every agent stage on an external CLI packaged as a Kit v3
|
||||
# image: the workload Kit, then mixins, each pinned by digest.
|
||||
# image: one workload Kit or published Kit set (which merges a workload with
|
||||
# its mixins), pinned by digest.
|
||||
# [containers.profiles.claude]
|
||||
# kit = ["docker/claude-code-kit@sha256:<digest>"]
|
||||
# kit = "docker/claude-code-kit@sha256:<digest>"
|
||||
# adapter = "claude-code" # claude-code, codex, pi, omp or copilot; empty runs without capture tools or usage
|
||||
#
|
||||
# Credential bindings map a Kit's credential@1 service name to a secret. A
|
||||
# binding alone grants nothing -- an identity resolves it only when its own
|
||||
# org matches and the service is in its granted_credentials (see
|
||||
# [[identities]] above). Once the State Store holds it, edit bindings in the
|
||||
# dashboard (Settings, Advanced); a stored set replaces the file's.
|
||||
# [[containers.credentials]]
|
||||
# service = "openai"
|
||||
# org = "acme" # empty means the default org
|
||||
# secret = {engine = "env", key = "OPENAI_API_KEY"}
|
||||
|
||||
# At least one [[repos]] entry is required before archied will poll
|
||||
# anything -- it is deliberately left commented rather than shipped active:
|
||||
@@ -481,9 +496,6 @@ target = "127.0.0.1:9090" # REQUIRED. The State Store gRPC address arch
|
||||
# # [containers].max_concurrency globally.
|
||||
# # persistent_storage = true # reuse a per-repo Docker volume and Git object cache until volume_ttl
|
||||
# # max_retries = 5 # per-repo override of the global max_retries above
|
||||
# # review_enabled = true # run a fresh adversarial reviewer (no path to the implementer's
|
||||
# # context) after gates pass and before the PR opens. Default false --
|
||||
# # an uncalibrated reviewer that cries wolf is worse than no review.
|
||||
|
||||
# ── Tools ───────────────────────────────────────────────────────────────────
|
||||
# Limits on what a tool may return. These bound how much of the context window
|
||||
|
||||
@@ -1,6 +1,29 @@
|
||||
# Adversarial self-review
|
||||
|
||||
Archie runs a fresh adversarial review of the diff before it opens a pull
|
||||
> **Removed, not shipped (2026-09-28, `d73e0748`). This page records a system
|
||||
> that no longer exists in the tree.**
|
||||
>
|
||||
> `d73e0748` ("remove the superseded adversarial-self-review system") deleted the
|
||||
> stage and its contract: `workflow.Reviewer`, `ReviewRequest`, `ReviewReport`
|
||||
> and `StageReview` are gone from `internal/domain/workflow`, so everything under
|
||||
> "Contract" below describes types that cannot be found.
|
||||
>
|
||||
> The authority is `docs/prds/pr-review-agent.md`, which says so itself: it
|
||||
> "supersedes the reviewer executor and blocking rule in
|
||||
> `docs/architecture/adversarial-review.md`". archied now runs its PR review
|
||||
> pipeline before it opens a pull request; there is no separate adversarial
|
||||
> self-review pass and no `repo.review_enabled` setting.
|
||||
>
|
||||
> The page is kept rather than deleted because PRDs link to it
|
||||
> (`docs/prds/adversarial-self-review.md`, `docs/prds/inline-review.md`,
|
||||
> `docs/prds/pr-review-agent.md`). Read it as history.
|
||||
>
|
||||
> One section is stale in a second, older way: "Operator-triggered review" below
|
||||
> describes the synchronous `review_pr` (fetch the head, snapshot it, run the
|
||||
> reviewer, return findings), which `archie-core-afbk.14` replaced with a queued
|
||||
> pr-review task.
|
||||
|
||||
Archie ran a fresh adversarial review of the diff before it opened a pull
|
||||
request, so a PR arrives with a findings record rather than an unreviewed
|
||||
claim. The reviewer provably cannot see the implementer's context: it reviews a
|
||||
`.git`-free snapshot of the committed tree, not the worktree, the commit
|
||||
|
||||
@@ -311,9 +311,6 @@ implemented in different packages:
|
||||
|
||||
## Current workflow-feature hazards
|
||||
|
||||
- There is no enforced WorkflowExecution state machine. `Store.Transition`
|
||||
guards on the supplied `from` state but accepts any `from` to `to` pair. See
|
||||
`docs/prds/execution-tree-state-machine.md`.
|
||||
- State update and transition-history insertion are separate operations, so
|
||||
state and audit can diverge.
|
||||
- Callers frequently discard persistence and transition errors.
|
||||
|
||||
@@ -334,6 +334,18 @@ Two properties matter to anyone changing this area:
|
||||
ones. Workflow execution budgets arrive on a watch rather than in a resource
|
||||
query, so boot records the last published settings and the reload re-applies
|
||||
them from there.
|
||||
- **Live kinds arrive on a watch.** Provider settings, model role assignments,
|
||||
repository policies and scheduling policy are `ApplyMode: live`
|
||||
(archie-core-zfb0.1): the daemon keeps a watch per kind and, on a new
|
||||
version, re-runs `boot.runtimeConfig` over the published snapshot and
|
||||
republishes through `config.Holder`. A candidate the layered document cannot
|
||||
run is refused before it is published — last-known-good keeps running and
|
||||
the refusal is reported through apply status. The kinds stay
|
||||
restart-required while a startup-built component still holds their value
|
||||
(tool, plugin, container and channel settings today); a kind joins the live
|
||||
list only with a consumer that re-reads it, and the model/provider half of
|
||||
it also rebuilds the gateway chat runtime's provider set and the chat model
|
||||
list the chat surfaces offer.
|
||||
|
||||
## Completion criteria
|
||||
|
||||
|
||||
@@ -1,45 +0,0 @@
|
||||
# archied -- design notes
|
||||
|
||||
Archie is a resident daemon that keeps personal projects moving: it polls GitHub for issues labelled
|
||||
`archie`, works each one in an isolated fresh-clone worktree through a routed **workflow**, and opens a
|
||||
pull request for human review. Sam reviews and merges; the machine grinds in between.
|
||||
|
||||
Guiding principle: **environmental constraints over prompt instructions.** Agents don't get asked nicely
|
||||
to write good code -- the quality gate (vet/build/test/lint, configurable per repo and per workflow stage)
|
||||
refuses to let a run succeed until it passes. The gate mechanics live in `ai-sdk/agentloop`; this repo
|
||||
owns orchestration only.
|
||||
|
||||
## Workflows, not a pipeline
|
||||
|
||||
`internal/workflow` is the engine: a Workflow is an ordered list of stages over a shared TaskContext;
|
||||
stages are deterministic steps (worktree, gate, diff cap, PR, comments -- the shared step library in
|
||||
`steps.go`) or agent stages (`agentloop.Run` with a stage-specific mission/toolset/gate). Routing is
|
||||
label-driven (`bug` → tdd, `feature` → feasibility, default → implement), refinable by an LLM triage
|
||||
stage. Adding a workflow must never require touching the engine or reimplementing steps.
|
||||
|
||||
Planned workflows:
|
||||
|
||||
- **bootstrap** (registered): deterministic marker-file PR proving invites/clone/push/PR plumbing.
|
||||
- **implement**: planner (read-only agentloop, plan posted to the issue) → builder (full toolset,
|
||||
repo gate) → diff cap → PR.
|
||||
- **tdd** (bugfixes): analyse → problem surface → write failing repro tests (gate stage with
|
||||
`ExpectFailure`) → fix (gate: suite passes) → PR.
|
||||
- **feasibility** (features): read-only analysis → roadmap fit → won't-do close with reasons, or
|
||||
plan + PRD → email Sam → `waiting_human` → LLM-judged reply → hand off to implement.
|
||||
|
||||
## Task lifecycle
|
||||
|
||||
`queued → running(workflow:stage) → waiting_human | pr_open → merged | parked | rejected | closed_wont_do`
|
||||
|
||||
SQLite (`internal/store`), WAL, one row per issue with a transitions audit table. Crash recovery:
|
||||
`running` tasks re-queue on startup with attempt++. Parks are never silent -- every park comments on the
|
||||
issue with the reason and gate output.
|
||||
|
||||
## Security posture
|
||||
|
||||
- Fine-grained PAT on the bot account only (Contents RW, PRs RW, Issues RW, Metadata R), via
|
||||
`ARCHIE_GITHUB_TOKEN`; git auth through an askpass helper so the token stays out of argv and
|
||||
`.git/config`.
|
||||
- The model never runs git: `internal/worktree` owns all repo operations deterministically.
|
||||
- Agent tools are jailed to the task worktree (toolkit path jail); intended deployment is a dedicated
|
||||
Incus container so the blast radius is environmental, not prompt-negotiated.
|
||||
@@ -1,519 +0,0 @@
|
||||
# archie-core v2 Architecture -- Design Document
|
||||
|
||||
**Author:** Archie
|
||||
**Date:** 2026-07-21 (implementation status updated 2026-07-22)
|
||||
**Status:** Final (substantially implemented -- remaining aspirational items are pluggable storage backends and Layer 2 daemon plugin loader)
|
||||
|
||||
---
|
||||
|
||||
## 0. Implementation status (as of 2026-07-22, updated 2026-07-22)
|
||||
|
||||
This document describes a target end state. The table below is the ground truth; read it before treating any section as already built.
|
||||
|
||||
| Area | Status | What actually exists today (post-e4d11b1) |
|
||||
| --------------------------------------------------------- | ------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
|
||||
| Daemon/agent binary split | **Implemented** | `cmd/archied` and `cmd/archie-agent` both exist. `archie-agent` is a 189-line NATS-connected per-task worker that subscribes to task subjects, runs the full multi-stage workflow, and reports results. Workflow routing and sequencing (`workflow.Route`, `workflow.Run`) now run inside the agent, not the daemon. Three agent modes: `inprocess`, `subprocess`, `nats`. |
|
||||
| Sandbox / "daemon never runs untrusted code" | **Partial** | Default mode is still `inprocess` for development. Docker sandbox mode (`agent.mode = "nats"` + `containers.enabled = true`) runs each task in an ephemeral Docker container with workspace bind-mounted at `/workspace`. `internal/container/pool.go` manages full lifecycle: pull, create, start, release, orphan recovery. Daemon dispatch and container lifecycle both enforce `max_concurrency`; same-repo tasks remain serialised. |
|
||||
| NATS / JetStream messaging | **Implemented** | `internal/nats/client.go`: JetStream connect, stream creation (WorkQueue retention, file storage), pull consumer (durable, ack-wait 5min, max-deliver 3, dedup by Msg-Id), `PublishTask`, `Fetch`, `NewReplyInbox`, and optional token authentication. Subject hierarchy lives in `internal/nats/subjects.go`; `internal/agentexec/nats.go` implements request/reply agent execution. |
|
||||
| Docker container sandbox | **Implemented** | `internal/container/pool.go` (210 lines): Docker API client, image pull (always/missing/never), container create with workspace bind mount, start, release (stop+remove), orphan recovery on daemon restart. `Dockerfile` at repo root builds archie-agent fat image. `[containers]` config block: enabled, image, max_concurrency, max_uptime, pull_policy. `agent.mode = "nats"` required when containers enabled. |
|
||||
| `/data/` volume, `task.json` | **Partial** | `container.WriteTaskJSON()` writes task payload to the worktree before container acquire. The container pool bind-mounts the isolated task worktree at `/data/worktree`; configured repos also receive a persistent `/data/repo` Docker volume. Task payload travels over NATS as the primary channel; `/data/task.json` is a boot-time brief for the container. |
|
||||
| `[containers]` config block | **Implemented** | `ContainerConfig` struct in config.go: enabled, image, max_concurrency, max_uptime, pull_policy. Validated on load. |
|
||||
| Yaegi extensibility (gates, custom stages, skill scripts) | **Implemented** | Three surfaces: `.archie/gate.go`, `.archie/stages/*.go`, skill scripts via `run_go_script` tool. All in-process via Yaegi with generated symbol tables and panic recovery. Full detail in `docs/prds/yaegi-plugin-system.md`. |
|
||||
| Layer 1: skill-bundled plugins | **Implemented** | `skill.DiscoverPlugins()` scans `.agents/skills/<name>/plugins/*.go`. `skill.Plugin.Run()` executes them via Yaegi. `skillbuild.BuildWorkflow()` constructs `workflow.Workflow` from plugin-defined stages. `TaskContext.SkillPlugins` makes them available during stage execution. `skillbuild.BuildRegistry()` replaces the hardcoded `workflow.Registry` with catalogue-driven construction -- skills define workflows, plugins define stages. |
|
||||
| Layer 2: core daemon plugins | **Partial** | `internal/plugin/plugin.go`: `Plugin` interface (`Name()`, `Version()`), `Registry` type, `LoadDir()` using Yaegi to interpret `.go` files. No `~/.config/archie/plugins/` loader wired into `cmd/archied/main.go` yet -- the interface and registry exist but are not connected to the daemon's startup. |
|
||||
| Skills (agentskills.io spec) | **Implemented** | `internal/skill/skill.go`: parses SKILL.md YAML frontmatter, discovers skills from `.agents/skills/*/SKILL.md`, extracts body. Skills follow `archie-wf-*` naming convention. Progressive disclosure: `Catalog()` (Tier 1 -- frontmatter-only scan, ~100 tokens per entry), `LoadBody()` (Tier 2 -- full body on activation), `Discover()` (Tier 3 -- full parse with plugins). `metadata.archie.workflow` declares skill→workflow affinity. `skill.SkillForWorkflow()` is catalogue-driven, no hardcoded maps. `skillbuild.BuildRegistry()` constructs the daemon's workflow registry from the catalogue. |
|
||||
| Worktree/repo management | **Implemented** | Each issue keeps an isolated worktree. Repos with `persistent_storage = true` use a per-repo bare Git object cache to avoid repeated full network clones; caches and Archie-owned repo volumes expire via `containers.volume_ttl`. |
|
||||
| Config schema | **Closer to sec.4** | `[agent]` block: mode (inprocess/subprocess/nats) + command + env. `[nats]` block: url + token_env. `[containers]` block: enabled, image, max_concurrency, max_uptime, volume_ttl, pull_policy. Per-repo `persistent_storage` is supported as a boolean Docker-volume/Git-cache opt-in. |
|
||||
|
||||
**Net read post-1dca419:** Phases 1, 2, and 3 are substantially implemented. NATS, Docker sandbox, skill parsing, skill-bundled plugins (Layer 1), skill progressive disclosure, and catalogue-driven workflow construction (`skillbuild.BuildRegistry()`) all landed. The remaining aspirational work is Layer 2 daemon plugin loader (interface exists, not wired), pluggable storage backends, and per-worktree dynamic registry augmentation.
|
||||
|
||||
---
|
||||
|
||||
## 1. Binary split
|
||||
|
||||
### archied (daemon)
|
||||
|
||||
The resident orchestrator. Owns:
|
||||
|
||||
- **Task discovery** -- polls configured forges for issues labelled `archie` (or configured label)
|
||||
- **NATS publishing** -- publishes discovered tasks to JetStream subjects
|
||||
- **Container lifecycle** -- spawns Docker containers, kills them after grace period, cleans up volumes
|
||||
- **Message gatekeeping** -- reads agent responses from NATS, reviews them, forwards to human channels
|
||||
- **Core plugin loading** -- loads Yaegi `.go` plugins from `~/.config/archie/plugins/` at startup
|
||||
- **Web dashboard** -- SSE observability endpoint
|
||||
- **Human communication** -- issue comments, labels, PR management, notify webhook
|
||||
|
||||
The daemon never runs untrusted code. Agent containers are the sandbox boundary.
|
||||
|
||||
> **Target state, not current state.** Today, default `[agent] mode = "inprocess"` runs the agent loop (and therefore
|
||||
> all LLM-directed tool calls) directly inside `archied`. `subprocess` mode exists (`internal/agentexec/subprocess.go`)
|
||||
> but its own code comment says: _"This is not an OS security boundary: a same-UID subprocess may still access
|
||||
> daemon-readable host resources."_ This claim becomes true only once the Docker sandbox (sec.4, Phase 2) lands.
|
||||
|
||||
### archie-agent (ephemeral container)
|
||||
|
||||
Spawned per task. Lives in a Docker container. Receives its brief via `/data/task.json` (volume-mounted). Owns:
|
||||
|
||||
- **Workflow execution** -- runs the routed workflow stages (implement, tdd, feasibility, bootstrap)
|
||||
- **LLM orchestration** -- via `ai-sdk/agentloop`, the agent drives LLM calls
|
||||
- **Bundled plugin loading** -- loads Yaegi `.go` plugins from the skill's `plugins/` directory and the `/data/plugins/`
|
||||
volume
|
||||
- **Skill loading** -- reads `.agents/skills/archie-wf-*` from the worktree, follows the agentskills.io progressive
|
||||
disclosure model
|
||||
- **NATS reporting** -- publishes results to `archie.agent.<task_id>.response`, system messages to
|
||||
`archie.agent.<task_id>.system`
|
||||
|
||||
Lifecycle: spawn -> load task -> run workflow -> report -> wait for follow-ups (grace period) -> killed by daemon.
|
||||
|
||||
> **Target state, not current state.** `cmd/archie-agent/main.go` today is 28 lines: read one JSON `Invocation` from
|
||||
> stdin, run one stage via `agentexec.ServeOne`, write one `Response` to stdout, exit. It is a single-stage subprocess
|
||||
> worker invoked by `archied`'s `SubprocessRunner`, not a persistent per-task container process. Workflow routing and
|
||||
> multi-stage sequencing (`workflow.Route`, `workflow.Run`) run entirely inside `archied`
|
||||
> (`internal/daemon/daemon.go:process()`), not inside archie-agent. There is no `/data/task.json`, no bundled-plugin
|
||||
> loading, no `.agents/skills/archie-wf-*` discovery, and no NATS reporting -- see sec.0, sec.2, sec.3, sec.5. The
|
||||
> existing `agentexec.Runner` interface (`InProcessRunner`/`SubprocessRunner`) is, however, deliberately shaped so a
|
||||
> future container-backed runner can be a drop-in swap without changing workflow orchestration.
|
||||
|
||||
---
|
||||
|
||||
## 2. NATS subject hierarchy
|
||||
|
||||
> **Status: aspirational, zero code.** No NATS/JetStream dependency exists anywhere in `go.mod` or the codebase. Today,
|
||||
> task discovery is GitHub-poll-driven (`daemon.Run()` ticks on `PollInterval`, calls `pollIssues()`), distribution is a
|
||||
> SQLite `tasks` table used as a FIFO queue (`store.ClaimNext` atomically claims the oldest `queued` row), and
|
||||
> results/status flow through an in-process `internal/events.Bus` (Go channels, multi-subscriber fan-out,
|
||||
> drop-on-overflow) that already feeds both a SQLite `events` table and the SSE dashboard. `events.Bus` has roughly the
|
||||
> right shape to become the NATS publish path -- same `Event` schema, swap the transport -- which meaningfully de-risks
|
||||
> this phase, but it is currently single-process only with no network transport.
|
||||
|
||||
### Task distribution
|
||||
|
||||
```events
|
||||
archie.task.bug -- TDD workflow tasks
|
||||
archie.task.feature -- Feasibility workflow tasks
|
||||
archie.task.default -- Implement workflow tasks
|
||||
archie.task.bootstrap -- Bootstrap diagnostic tasks
|
||||
```
|
||||
|
||||
Daemon publishes to the appropriate subject based on label routing. Agents subscribe to subjects they're configured to
|
||||
handle.
|
||||
|
||||
### Agent communication (per-task)
|
||||
|
||||
```events
|
||||
archie.agent.<task_id>.response -- Agent output: summaries, PR bodies, results. Daemon reviews before human delivery.
|
||||
archie.agent.<task_id>.system -- Internal comms: log dumps, data requests, health, PII warnings. Never forwarded unprompted.
|
||||
archie.agent.<task_id>.request -- Optional: agent requests additional data from the daemon.
|
||||
```
|
||||
|
||||
The daemon gatekeeps the response channel -- no agent output reaches a human without daemon review.
|
||||
|
||||
### JetStream durability
|
||||
|
||||
Tasks are published with JetStream persistence. On agent container failure, NATS redelivers. The daemon doesn't need
|
||||
retry logic -- NATS handles it.
|
||||
|
||||
---
|
||||
|
||||
## 3. Persistent volume
|
||||
|
||||
> **Status: partially implemented.** `task.json`, `/data/worktree`, optional per-repo `/data/repo` Docker volumes,
|
||||
> ecosystem cache volumes, and TTL cleanup exist. Task worktrees remain isolated by issue, while configured repos use a
|
||||
> per-repo bare Git object cache to seed clones without repeating full network transfers. `session.jsonl`,
|
||||
> `memory.jsonl`, and staged plugin volumes remain unimplemented.
|
||||
|
||||
### /data/ layout
|
||||
|
||||
```tree
|
||||
/data/
|
||||
|---- task.json # Full task payload (owner, repo, issue, title, body, labels, workflow)
|
||||
|---- session.jsonl # Agent session transcript (appended per stage)
|
||||
|---- memory.jsonl # Optional: cross-session memory (persisted per project)
|
||||
|---- plugins/ # Bundled plugins from the skill (daemon-staged, overrides worktree)
|
||||
|---- worktree/ # Read-only mount of the cloned repo (managed by daemon)
|
||||
```
|
||||
|
||||
### task.json
|
||||
|
||||
```json
|
||||
{
|
||||
"id": 42,
|
||||
"owner": "sam",
|
||||
"repo": "example-service",
|
||||
"issue_number": 170,
|
||||
"title": "Add /copy command for messages and session transcripts",
|
||||
"body": "...",
|
||||
"labels": ["enhancement", "archie"],
|
||||
"workflow": "implement",
|
||||
"branch": "archie/issue-170",
|
||||
"plan": "",
|
||||
"config": {
|
||||
"base_branch": "main",
|
||||
"gate": [
|
||||
["gofumpt", "-w", "."],
|
||||
["go", "vet", "./..."],
|
||||
["go", "test", "-race", "./..."]
|
||||
],
|
||||
"protect": ["_templ.go"],
|
||||
"ecosystem": "go",
|
||||
"test_glob": "*_test.go"
|
||||
},
|
||||
"nats": {
|
||||
"url": "nats://archie-core:4222",
|
||||
"response_subject": "archie.agent.42.response",
|
||||
"system_subject": "archie.agent.42.system",
|
||||
"request_subject": "archie.agent.42.request"
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
The daemon writes `task.json` to the volume before the container starts. The agent reads it on boot.
|
||||
|
||||
### Volume lifecycle
|
||||
|
||||
- Created on task start (persistent per-repo if configured)
|
||||
- Kept until terminal outcome (`pr_open`, `merged`, `rejected`, `closed_wont_do`) OR TTL expiry
|
||||
- Parked tasks keep their volume for inspection and requeue reuse
|
||||
- Cleanup is a daemon responsibility
|
||||
|
||||
---
|
||||
|
||||
## 4. Container management
|
||||
|
||||
> **Status: implemented with a flatter schema than the sketch below.** `[containers]` configures the image,
|
||||
> concurrency, uptime, pull policy, and persistent-storage TTL. `Repo.PersistentStorage` opts a repository into the
|
||||
> per-repo Docker volume and Git object cache. The backend abstraction exists in `internal/storage`; additional storage
|
||||
> types and structured per-backend configuration remain future work.
|
||||
|
||||
### Daemon config
|
||||
|
||||
```toml
|
||||
# Container lifecycle
|
||||
[containers]
|
||||
max_concurrency = 4 # max simultaneous agent containers
|
||||
max_uptime = "30m" # grace period after task completion before kill
|
||||
volume_ttl = "72h" # max volume age before cleanup (overrides terminal wait)
|
||||
|
||||
# Image strategy
|
||||
[containers.image]
|
||||
registry = "ghcr.io/sam/archie-agent:latest" # primary: pull from registry
|
||||
registry_pull = true # allow pulls
|
||||
dockerfile = "./Dockerfile.agent" # fallback: build locally
|
||||
dockerfile_build = true # allow builds
|
||||
|
||||
# Persistent storage
|
||||
[containers.persistent_storage]
|
||||
type = "docker" # docker (volume), bind, s3, sftp, nfs
|
||||
path = "archie-data" # volume name or mount path
|
||||
```
|
||||
|
||||
### Per-repo persistent storage override
|
||||
|
||||
```toml
|
||||
[[repos]]
|
||||
owner = "sam"
|
||||
name = "example-service"
|
||||
persistent_storage = { type = "bind", path = "./archie-core-data/projects/example-service" }
|
||||
```
|
||||
|
||||
When configured, each task for this repo mounts the same bind path. Memory persists across sessions. The agent writes to
|
||||
`MEMORY.md` in this directory.
|
||||
|
||||
### Agent image
|
||||
|
||||
A fat Docker image containing:
|
||||
|
||||
- archie-agent binary
|
||||
- NATS client library
|
||||
- LLM provider SDKs (ai-sdk runtime)
|
||||
- Base tools: git, gh, go, golangci-lint, gofumpt, node, python, ruff, pytest, etc.
|
||||
- esbuild (for TypeScript plugin transpilation)
|
||||
- Yaegi interpreter (bundled in the binary)
|
||||
|
||||
Pre-built and published to a registry. The daemon pulls on startup. Users can provide their own image via config.
|
||||
|
||||
---
|
||||
|
||||
## 5. Extensibility layers
|
||||
|
||||
> **Reconciliation note.** This section describes a two-layer plugin architecture (skill-bundled plugins loaded
|
||||
> per-task, core daemon plugins loaded at startup) that does not exist in code. What _does_ exist -- and is implemented,
|
||||
> tested, and already in production -- is described in the sibling PRD `docs/prds/yaegi-plugin-system.md`, whose three
|
||||
> phases (custom gate functions, custom workflow stages, skill scripts) are marked "implemented" and match disk state
|
||||
> exactly as of commit `d45f21d`. That implementation is narrower and shaped differently than what follows:
|
||||
>
|
||||
> - It has **no skill-bundling concept** -- `.archie/gate.go` and `.archie/stages/*.go` are repo-level, not shipped
|
||||
> inside a skill's `plugins/` directory; skill scripts (`.archie/skills/<skill>/scripts/*.go`) are the closest analog
|
||||
> but none of the five current skills ship a `scripts/` directory yet.
|
||||
> - It has **no daemon-side core plugin registry** -- no `Plugin` interface, no `Register(daemon *Daemon)`, no
|
||||
> `~/.config/archie/plugins/` loader. Yaegi today only interprets small, narrowly-scoped `.go` files (gates, stages,
|
||||
> scripts) in-process inside `archied`, using generated symbol tables (`internal/gate/gateextract`,
|
||||
> `internal/workflow/wfextract`) rather than a general extension-registration interface.
|
||||
> - Custom stages are **auto-discovered and run in filename order**, not routed by name from `config.toml` -- the
|
||||
> workflow engine has no data-driven stage graph today, so the `[[workflows.stages]]` config sketch below does not
|
||||
> correspond to real config.
|
||||
>
|
||||
> Before implementation begins, decide: does Layer 1/Layer 2 as described below _replace_ the existing three Yaegi
|
||||
> surfaces, or does it _extend_ them (e.g., teach the existing loaders to also read from a skill's `plugins/` directory,
|
||||
> and add a genuinely new daemon-side `Plugin` interface as a separate, later addition)? The existing surfaces are
|
||||
> working code with real symbol-table generation and panic recovery -- treat them as the implementation substrate for
|
||||
> Layer 1, not as something to discard.
|
||||
|
||||
### Layer 1: Skills (`archie-wf-*`)
|
||||
|
||||
> **Status: cosmetic only.** Five `SKILL.md` files exist today (`ecosystem-node`, `ecosystem-python`, `go-quality-gate`,
|
||||
> `security-audit`, `tdd-bugfix`) at `.archie/skills/<name>/SKILL.md` -- a single flat repo-relative location, no
|
||||
> worktree-vs-user-level split, no `archie-wf-*` naming. Each has a `metadata.archie` block with only `tools` and
|
||||
> `engine` keys (no `plugins`, no `budget_usd`). **No Go code parses SKILL.md frontmatter, discovers skills, or does
|
||||
> progressive disclosure** -- grepping for a skill loader, catalog, or frontmatter parser across the repo returns
|
||||
> nothing. The workflow `Mission` strings that drive agent behavior today are hand-written Go string literals in
|
||||
> `internal/workflow/{implement,tdd,feasibility}.go`, not content injected from SKILL.md. The stage names described in
|
||||
> the PRD's SKILL.md prose closely mirror the hardcoded Go stage names (one drift found: `tdd-bugfix/SKILL.md` says the
|
||||
> last stage is "deliver"; the code calls it `open-pr`) -- these read as retrofitted documentation of existing v1
|
||||
> behavior wearing v2-flavored frontmatter, not a functioning specification the daemon consumes.
|
||||
|
||||
Skills are Markdown documents following the [agentskills.io](https://agentskills.io/specification) specification with
|
||||
archie-specific extensions.
|
||||
|
||||
#### Discovery
|
||||
|
||||
```tree
|
||||
.agents/skills/archie-wf-tdd/SKILL.md (worktree -- highest precedence)
|
||||
.agents/skills/archie-wf-implement/SKILL.md
|
||||
.agents/skills/archie-wf-feasibility/SKILL.md
|
||||
~/.archie/skills/archie-wf-default/SKILL.md (user-level -- fallback)
|
||||
```
|
||||
|
||||
The agent discovers skills at workflow start. The skill matching the task's workflow type is loaded first. If absent,
|
||||
falls back to `archie-wf-default`. If that's absent too, the agent works from AGENTS.md conventions and best practices.
|
||||
|
||||
#### Extended agentskills.io format
|
||||
|
||||
Skills follow the standard spec (`name`, `description`, `version`, `SKILL.md` body) with archie-specific metadata:
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: archie-wf-tdd
|
||||
description: >
|
||||
Test-driven bugfix workflow for archie-core. Reproduce the bug with failing tests, prove the repro, fix the code
|
||||
without touching tests.
|
||||
version: 1.0.0
|
||||
metadata:
|
||||
archie:
|
||||
plugins: # bundled Yaegi plugins shipped with this skill
|
||||
- plugins/custom-gate.go # repo-specific gate logic
|
||||
- plugins/gosec-check.go # security scanner integration
|
||||
tools: [go, golangci-lint, gofumpt, task]
|
||||
engine: any
|
||||
budget_usd: 2.00
|
||||
---
|
||||
```
|
||||
|
||||
#### Progressive disclosure
|
||||
|
||||
Per the agentskills.io spec:
|
||||
|
||||
1. **Catalogue** (~100 tokens): `name` + `description` loaded at workflow start
|
||||
2. **Instructions** (<5000 tokens): Full `SKILL.md` body when the skill is activated
|
||||
3. **Resources** (as needed): References, scripts, and bundled plugins loaded on demand
|
||||
|
||||
#### Bundled plugins
|
||||
|
||||
A skill's `plugins/` directory contains Yaegi `.go` files. These are loaded by the agent at workflow start alongside the
|
||||
skill instructions. The daemon copies them to `/data/plugins/` before the container starts.
|
||||
|
||||
If `/data/plugins/` already has a plugin with the same name (from persistent project storage), the volume version wins.
|
||||
Conflicts are logged by the daemon.
|
||||
|
||||
### Layer 2: Core plugins
|
||||
|
||||
> **Status: aspirational, zero code.** No `Plugin` interface, no plugin registry, no `~/.config/archie/plugins/` loader
|
||||
> exists anywhere in the repo (confirmed by grep for `Plugin`, plugin registry, and `Register(daemon` -- zero matches).
|
||||
> Yaegi is a real dependency (`traefik/yaegi v0.16.1`) and is genuinely wired up, but only for the three narrow surfaces
|
||||
> in sec.5's reconciliation note above, all interpreted in-process inside `archied` -- not for extending the daemon with
|
||||
> new forge/ticketing/storage/secrets/notify implementations as described below.
|
||||
|
||||
Core plugins live at `~/.config/archie/plugins/` and extend the daemon itself:
|
||||
|
||||
```tree
|
||||
~/.config/archie/plugins/
|
||||
|---- forge-gitea.go # Gitea forge implementation
|
||||
|---- forge-gitlab.go # GitLab forge implementation
|
||||
|---- ticketing-jira.go # Jira ticketing integration
|
||||
|---- ticketing-linear.go # Linear ticketing integration
|
||||
|---- storage-s3.go # S3 persistent storage backend
|
||||
|---- vault-secrets.go # HashiCorp Vault integration
|
||||
|---- notify-servicenow.go # ServiceNow integration
|
||||
```
|
||||
|
||||
#### Loading
|
||||
|
||||
Loaded by the daemon at startup via Yaegi. Each plugin registers itself with the daemon's extension registry:
|
||||
|
||||
```go
|
||||
// Plugin interface (Go, interpreted via Yaegi)
|
||||
type Plugin interface {
|
||||
Name() string
|
||||
Version() string
|
||||
Register(daemon *Daemon) error
|
||||
}
|
||||
```
|
||||
|
||||
The daemon discovers `.go` files, evaluates them, extracts the plugin symbol, and calls `Register()`. Failed plugins are
|
||||
logged and skipped -- the daemon starts with remaining plugins.
|
||||
|
||||
#### What core plugins can do
|
||||
|
||||
- **Forges** -- implement the `forge.Forge` interface. Register themselves as available forge types.
|
||||
- **Ticketing** -- implement a ticketing interface. Poll external systems, format issues into the standard `forge.Issue`
|
||||
struct.
|
||||
- **Storage backends** -- implement a storage interface. Provide volume population and cleanup.
|
||||
- **Secrets** -- implement a vault interface. Inject credentials into `/data/secrets/` before agent start.
|
||||
- **Notifications** -- implement a notify interface. Deliver PRDs, status updates beyond the built-in webhook.
|
||||
|
||||
---
|
||||
|
||||
## 6. Task lifecycle (v2)
|
||||
|
||||
> **Status: implemented.** NATS JetStream is now the task distribution path (`internal/nats/client.go`, `internal/daemon/daemon.go:drainNATS()`). Docker containers spawn per task (`internal/container/pool.go`). The flow below matches the running code post-e4d11b1.
|
||||
|
||||
```
|
||||
Discover -> Publish to JetStream -> Agent consumes -> running(workflow:stage)
|
||||
v
|
||||
pr_open -> merged | rejected
|
||||
v
|
||||
waiting_human -> (approved) -> requeue
|
||||
v
|
||||
parked
|
||||
```
|
||||
|
||||
### Detailed flow
|
||||
|
||||
1. **Discover** -- daemon polls forges for labelled/assigned issues
|
||||
2. **Publish** -- daemon publishes task to `archie.task.<workflow_type>` JetStream subject
|
||||
3. **Spawn** -- daemon creates task volume, writes `task.json`, stages bundled plugins
|
||||
4. **Start container** -- `docker run` with volume mounts, network (NATS), resource limits
|
||||
5. **Agent boots** -- reads `task.json` from `/data/`, connects to NATS, discovers skills, loads bundled plugins
|
||||
6. **Run workflow** -- agent executes routed workflow stages. Reports progress to system channel. Result to response
|
||||
channel.
|
||||
7. **Daemon reviews** -- reads agent response. Forwards to human channels (issue comment, label update, PR). System
|
||||
messages stay internal.
|
||||
8. **Grace period** -- agent stays alive for `max_uptime`. Handles follow-ups (gate re-runs, human replies forwarded by
|
||||
daemon).
|
||||
9. **Kill** -- daemon kills container. Volume cleaned up on terminal outcome or TTL expiry.
|
||||
|
||||
---
|
||||
|
||||
## 7. Agent -> daemon -> human flow
|
||||
|
||||
```flow
|
||||
,---------, response ,---------, reviewed ,----------,
|
||||
| Agent |------------ -> | Daemon |------------ -> | Human |
|
||||
| | system | | queried | channels |
|
||||
| |------------ -> | |<-------------| |
|
||||
|------------ |------------ |-------------
|
||||
|
|
||||
|---- Issue comments (parked, PR, waiting)
|
||||
|---- Label updates (archie:queued -> archie:working -> archie:pr)
|
||||
|---- Notify webhook (feasibility PRD delivered)
|
||||
|---- SSE dashboard (real-time observability)
|
||||
```
|
||||
|
||||
The agent writes whatever it wants to `response`. The daemon reviews it. No agent output reaches a human unprompted. The
|
||||
`system` channel is purely internal -- the daemon reads it for observability and debugging, never forwards it.
|
||||
|
||||
---
|
||||
|
||||
## 8. Implementation phases
|
||||
|
||||
> Updated 2026-07-24 against actual repo state (see sec.0). Items marked **done** exist in the current tree; nothing else in
|
||||
> this document is implemented beyond them. Phase ordering below is unchanged from the original sketch except Phase 3,
|
||||
> which now builds on top of existing Yaegi work instead of assuming a blank slate.
|
||||
|
||||
### Phase 1: Binary split + NATS
|
||||
|
||||
- ~~Split `archied` into daemon binary~~ -- **done**, `cmd/archied` exists
|
||||
- ~~Create `archie-agent` binary~~ -- **done, but partial**: `cmd/archie-agent` exists and executes one workflow _stage_
|
||||
per invocation over a versioned stdin/stdout JSON protocol (`internal/agentexec`, protocol v1). Still needed: promote
|
||||
it from a single-stage subprocess worker to the PRD's per-task process, and move workflow routing/sequencing
|
||||
(`workflow.Route`/`workflow.Run`) out of `archied` and into it.
|
||||
- ~~Add NATS to both (JetStream for task queue, request-reply for comms)~~ -- **done**. `[nats]` is optional, supports
|
||||
anonymous local mode and token authentication via `token_env`, and leaves `internal/events.Bus` as the local
|
||||
observability fan-out.
|
||||
- ~~Daemon publishes, agent consumes, results return via NATS~~ -- **done**. Task discovery uses JetStream work-queue
|
||||
subjects; autonomous stages use JetStream requests plus core NATS reply inboxes.
|
||||
- Current single-process mode preserved for development (`--local` flag) -- effectively already true: `inprocess`
|
||||
`[agent] mode` is the _default_, not an opt-in fallback, so this constraint is satisfied but should be revisited once
|
||||
subprocess/container modes are the default.
|
||||
|
||||
### Phase 2: Docker sandbox
|
||||
|
||||
- Docker agent image (fat, with tools) -- not started
|
||||
- Daemon container lifecycle: spawn, volume create, env inject, kill -- not started
|
||||
- ~~Persistent volumes with TTL~~ -- **done**: configured repos receive a persistent Docker volume plus a per-repo Git
|
||||
object cache; both are automatically reaped using `containers.volume_ttl`.
|
||||
- ~~`max_concurrency` enforcement~~ -- **done**: SQLite and NATS drains dispatch different repositories concurrently
|
||||
up to `[containers].max_concurrency`; same-repo tasks remain serialised by default.
|
||||
- Grace period `max_uptime` -- not started
|
||||
- **Groundwork already in place:** `agentexec.Runner` (`InProcessRunner`/`SubprocessRunner`) is an interface designed,
|
||||
per its own doc comments, to be swapped for a container-backed runner without touching workflow orchestration --
|
||||
implement `ContainerRunner` against this interface rather than redesigning the execution boundary.
|
||||
|
||||
### Phase 3: Skills + bundled plugins
|
||||
|
||||
- agentskills.io spec implementation (progressive disclosure) -- not started; current SKILL.md files are unparsed
|
||||
documentation (see sec.5)
|
||||
- `archie-wf-*` skill discovery from worktree and user paths -- not started; current skills live at a single flat
|
||||
`.archie/skills/` path with different naming
|
||||
- Bundled plugin loading via Yaegi from skill's `plugins/` directory -- not started, but **has a working substrate to
|
||||
extend**: `internal/gate/gateeval`, `internal/workflow/wfeval`, and `internal/skillscript` already interpret `.go`
|
||||
files via Yaegi with generated symbol tables and panic recovery (see `docs/prds/yaegi-plugin-system.md`, Phases 1--3,
|
||||
done). This phase should teach those loaders to also discover files from a skill's `plugins/` directory, not build a
|
||||
second Yaegi integration from scratch.
|
||||
- Volume-staged plugins with conflict resolution -- not started, and depends on Phase 2's volume work existing first
|
||||
|
||||
### Phase 4: Core plugins
|
||||
|
||||
- Yaegi plugin loader for `~/.config/archie/plugins/` -- not started (no `Plugin` interface, no registry, no loader
|
||||
exist today)
|
||||
- Plugin registry in daemon -- not started
|
||||
- Gitea forge as first core plugin (proof of concept) -- not started (current `internal/forge` only implements GitHub
|
||||
REST polling)
|
||||
- Linear ticketing as second core plugin -- not started
|
||||
|
||||
### Phase 5: Pluggable storage
|
||||
|
||||
- Docker volume backend (built-in) -- not started
|
||||
- Bind mount backend (built-in) -- not started
|
||||
- S3, SFTP, NFS backends as core plugins -- not started
|
||||
|
||||
---
|
||||
|
||||
## 9. Open questions
|
||||
|
||||
1. **Agent image versioning:** Use tagged versions (`:v1.2.3`) with a "never repoint tags" policy. `:latest` is for dev
|
||||
only, not the config default. No digest complexity needed -- archie-core is self-hosted, not a public registry.
|
||||
|
||||
2. **NATS auth:** Anonymous for single-node deployments (daemon + NATS + agents on same host). Credentials required for
|
||||
multi-node/cluster. Add an optional `[nats]` config block (default: anonymous, validated only when present).
|
||||
|
||||
3. **Worktree ownership:** ~~Answered by current implementation.~~ Fresh `git clone` per task attempt, no shared cache.
|
||||
This is fine for v2. Revisit if concurrent agents on the same repo become a bottleneck.
|
||||
|
||||
4. **Grace period interaction:** Reset `max_uptime` on human reply -- the agent just did useful work. But cap total
|
||||
lifetime with `max_total_uptime` (e.g. 4 hours) to prevent infinite hanging. `max_uptime` = grace after inactivity,
|
||||
`max_total_uptime` = absolute kill switch.
|
||||
|
||||
5. **Concurrent agents on the same repo:** ~~Resolved.~~ Serialised by default (dispatcher chains tasks per
|
||||
`owner/repo`). `[[repos]]` now supports `allow_concurrent = true` (`config.Repo.AllowConcurrent`) to opt a repo out
|
||||
of that serialisation; the global `[containers].max_concurrency` slot limit still applies. Worktrees are already
|
||||
keyed per issue number (`worktree.Manager.Dir`), so opted-in repos don't collide on disk.
|
||||
|
||||
6. **Plugin architecture reconciliation:** Extend the existing Yaegi surfaces (`internal/gate/gateeval`,
|
||||
`internal/workflow/wfeval`, `internal/skillscript`) rather than building a parallel `Plugin.Register(daemon)`
|
||||
interface. Core plugins follow the same pattern: `Eval()` a `.go` file, extract known symbols. Settled before Phase
|
||||
3/4.
|
||||
|
||||
7. **Skill loading scope:** "Parse frontmatter, inject body into system prompt" is sufficient for v2. The gap is that
|
||||
nothing reads SKILL.md today -- closing that gap is the value. Full progressive disclosure (catalogue -> activate ->
|
||||
resources) is deferred to a later phase.
|
||||
@@ -1,389 +0,0 @@
|
||||
# archie-core Skills System -- PRD
|
||||
|
||||
**Author:** Archie
|
||||
**Date:** 2026-07-18
|
||||
**Status:** Draft
|
||||
|
||||
---
|
||||
|
||||
## What archie-core is
|
||||
|
||||
arcie-core is an LLM coding agent that responds to issues, queries, and commands on connected interfaces. The current MVP runs on GitHub: it receives issue assignments, analyses scope and requirements, implements changes in isolated worktrees, runs quality gates, and opens pull requests.
|
||||
|
||||
The skills system extends this with reusable playbooks that tell archie-core **how** to work on any given project.
|
||||
|
||||
---
|
||||
|
||||
## 1. The workflow file (`archie.yaml`)
|
||||
|
||||
Every project can ship an `archie.yaml` that defines how archie-core should behave when working on that codebase. Without one, archie-core uses sensible defaults (read files, run bash, open PRs). With one, it knows the exact gates to pass, tools available, commit format, and which skills are relevant.
|
||||
|
||||
### 1.1 Discovery
|
||||
|
||||
```
|
||||
.archie.yaml (root of repo -- highest precedence)
|
||||
archie.yaml (repo root)
|
||||
.archie/archie.yaml (subdirectory, one level deep)
|
||||
```
|
||||
|
||||
### 1.2 Schema
|
||||
|
||||
```yaml
|
||||
# archie.yaml
|
||||
version: "1"
|
||||
|
||||
# Project identity
|
||||
project:
|
||||
name: my-go-service
|
||||
language: go
|
||||
repo: github.com/sam/my-go-service
|
||||
|
||||
# How archie-core connects to this project
|
||||
connection:
|
||||
interfaces:
|
||||
- github # respond to assigned issues
|
||||
- linear # respond to labelled tickets
|
||||
- webhook # respond to HTTP POSTs
|
||||
github:
|
||||
repo: sam/my-go-service
|
||||
issue_labels:
|
||||
ready: "archie:ready" # issues with this label get claimed
|
||||
claimed: "archie:claimed" # archie sets this when working
|
||||
done: "archie:done" # archie sets this after PR
|
||||
pr:
|
||||
base: main
|
||||
draft: false
|
||||
|
||||
# Skills -- playbooks archie-core loads to know how to work
|
||||
skills:
|
||||
paths:
|
||||
- .archie/skills/ # project-local skills
|
||||
- ~/.archie/skills/ # per-user skills
|
||||
remotes:
|
||||
- github.com/sam/archie-skills@v1 # shared skill library
|
||||
|
||||
# Sandbox -- what's available in the container
|
||||
sandbox:
|
||||
image: ghcr.io/sam/archie-sandbox:latest
|
||||
tools:
|
||||
- go
|
||||
- golangci-lint
|
||||
- gofumpt
|
||||
- task
|
||||
- gh
|
||||
- docker
|
||||
env:
|
||||
GOFLAGS: "-mod=readonly"
|
||||
|
||||
# Gates -- archie-core must pass these before committing
|
||||
gates:
|
||||
test:
|
||||
run: go test -race -count=1 ./...
|
||||
timeout: 300
|
||||
lint:
|
||||
run: golangci-lint run ./...
|
||||
timeout: 120
|
||||
format:
|
||||
run: gofumpt -w . && git diff --exit-code
|
||||
deadcode:
|
||||
run: task deadcode
|
||||
optional: true
|
||||
|
||||
# Quality pipeline -- which gates run when
|
||||
quality:
|
||||
pre_commit: [test, lint, format]
|
||||
pre_push: [deadcode]
|
||||
|
||||
# Commit conventions
|
||||
commit:
|
||||
format: conventional
|
||||
signoff: false
|
||||
|
||||
# Branch conventions
|
||||
branch:
|
||||
format: "{type}/cat-{number}-{kebab-description}"
|
||||
types:
|
||||
feat: "Feature work"
|
||||
fix: "Bug fixes"
|
||||
test: "Test additions"
|
||||
chore: "Maintenance"
|
||||
refactor: "Code restructuring"
|
||||
docs: "Documentation"
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 2. Skills (playbooks)
|
||||
|
||||
Skills are Markdown documents that tell archie-core **how** to perform specific tasks. They follow the [agentskills.io](https://agentskills.io/specification) format, making them portable across compatible LLM coding agents.
|
||||
|
||||
### 2.1 Format
|
||||
|
||||
```
|
||||
go-testing/
|
||||
├── SKILL.md # Required: frontmatter + instructions
|
||||
├── references/ # Optional: supplementary docs
|
||||
│ └── coverage.md
|
||||
├── scripts/ # Optional: executable helpers
|
||||
│ └── bench.sh
|
||||
└── assets/ # Optional: templates
|
||||
└── test.vscode.code-snippets
|
||||
```
|
||||
|
||||
### 2.2 SKILL.md
|
||||
|
||||
```markdown
|
||||
---
|
||||
name: go-quality-gate
|
||||
description: >
|
||||
Run the full Go quality pipeline:
|
||||
gofumpt, go fix, golangci-lint, go test -race, and task deadcode.
|
||||
Use before any commit in a Go project.
|
||||
version: 1.0.0
|
||||
metadata:
|
||||
archie:
|
||||
# Which gates this skill covers
|
||||
gates: [test, lint, format, deadcode]
|
||||
# Required sandbox tools
|
||||
tools: [go, golangci-lint, gofumpt, task]
|
||||
# Preferred engine (if multiple available)
|
||||
engine: any
|
||||
# Max spend for this skill
|
||||
budget_usd: 2.00
|
||||
---
|
||||
|
||||
# Go Quality Gate
|
||||
|
||||
## When to use
|
||||
|
||||
Before committing any Go change. After implementing a feature or fix.
|
||||
|
||||
## Procedure
|
||||
|
||||
Run in this exact order. If any step fails, fix the issue before continuing.
|
||||
|
||||
1. `gofumpt -w .`
|
||||
2. `go fix ./...`
|
||||
3. `golangci-lint run ./...`
|
||||
4. `go test -race -count=1 ./...`
|
||||
5. `task deadcode`
|
||||
|
||||
## Verification
|
||||
|
||||
All five steps must exit 0. If `task deadcode` fails on unrelated packages,
|
||||
scope it to only changed packages: `golangci-lint run --tests=false --enable-only=unused,staticcheck ./changed/pkg/...`
|
||||
|
||||
## Common failures
|
||||
|
||||
- `golangci-lint`: unused function -- remove it or add `//nolint:unused` comment
|
||||
- `go test -race`: data race -- protect with mutex or channel
|
||||
- `task deadcode`: pre-existing dead code in unrelated package -- scope to changed packages
|
||||
```
|
||||
|
||||
### 2.3 Skill metadata (arcie-specific)
|
||||
|
||||
Skills carry archie-specific metadata under `metadata.archie`:
|
||||
|
||||
| Field | Purpose |
|
||||
| ------------ | ------------------------------------------------ |
|
||||
| `gates` | Which gates from `archie.yaml` this skill covers |
|
||||
| `tools` | Sandbox tools this skill needs |
|
||||
| `engine` | Preferred execution engine |
|
||||
| `model` | Preferred model for this skill |
|
||||
| `budget_usd` | Max spend ceiling |
|
||||
| `timeout` | Max seconds |
|
||||
| `worktree` | Whether to create isolated worktree |
|
||||
|
||||
### 2.4 Progressive disclosure
|
||||
|
||||
Following the skills.sh model to keep context lean:
|
||||
|
||||
1. **Advertise** (~100 tokens per skill): `name` + `description` loaded at startup
|
||||
2. **Activate** (<5000 tokens): Full SKILL.md body loaded when skill is relevant
|
||||
3. **Resources** (as needed): References, scripts, assets loaded on demand
|
||||
|
||||
---
|
||||
|
||||
## 3. How archie-core processes an issue
|
||||
|
||||
This is the core loop. When an issue lands with the configured label:
|
||||
|
||||
### 3.1 Analyse
|
||||
|
||||
1. Read issue title, body, labels, comments
|
||||
2. Load relevant skills from the project's `archie.yaml`
|
||||
3. Determine scope: which packages, files, and gates are in play
|
||||
4. Determine branch type (`feat/`, `fix/`, `test/`, etc.) from issue labels or conventional commit prefix
|
||||
|
||||
### 3.2 Claim
|
||||
|
||||
1. Set issue label to `archie:claimed`
|
||||
2. Comment: "Archie claimed this. Branch: `<branch>`"
|
||||
3. Create isolated worktree from `main`
|
||||
|
||||
### 3.3 Implement
|
||||
|
||||
1. Load full skill bodies for each relevant skill
|
||||
2. Read project source and tests in the affected area
|
||||
3. Implement changes, writing tests first where applicable
|
||||
4. Run targeted tests iteratively
|
||||
|
||||
### 3.4 Gate
|
||||
|
||||
1. Run all gates from the quality pipeline in order
|
||||
2. Fix any failures, re-running from the failing gate
|
||||
3. Audit diff for secrets, unrelated changes, attribution
|
||||
|
||||
### 3.5 Deliver
|
||||
|
||||
1. Commit with conventional format: `feat(scope): description`
|
||||
2. Push branch
|
||||
3. Open PR to `main` with:
|
||||
- Summary of changes
|
||||
- Acceptance criteria addressed
|
||||
- Gate results
|
||||
- Link back to source issue/Linear ticket
|
||||
4. Set issue label to `archie:done`
|
||||
5. Comment with PR URL
|
||||
|
||||
### 3.6 On failure
|
||||
|
||||
If any gate fails irrecoverably:
|
||||
|
||||
1. Leave issue as `archie:claimed`
|
||||
2. Comment with exact blocker, failed command, and worktree path
|
||||
3. Preserve worktree for inspection
|
||||
4. Do not open a broken PR
|
||||
|
||||
---
|
||||
|
||||
## 4. Engine abstraction
|
||||
|
||||
arcie-core can delegate implementation to different LLM engines. The workflow file declares preference order; archie-core resolves the first available engine at runtime.
|
||||
|
||||
```yaml
|
||||
engines:
|
||||
- type: claude # Claude Code CLI -- full agent loop
|
||||
model: sonnet
|
||||
budget_usd: 5.00
|
||||
- type: codex # OpenAI Codex CLI
|
||||
model: gpt-5.1-codex-max
|
||||
- type: raw # Direct LLM -- no agent loop, single prompt
|
||||
model: gpt-4o-mini
|
||||
```
|
||||
|
||||
Each engine provides the same interface:
|
||||
|
||||
```
|
||||
Engine:
|
||||
- Run(prompt, tools, budget, timeout) -> Result
|
||||
- Skills() -> []SkillName
|
||||
- Capabilities() -> {streaming, reasoning, vision, agentic}
|
||||
```
|
||||
|
||||
For skills that need a specific engine, the skill metadata overrides:
|
||||
|
||||
```yaml
|
||||
metadata:
|
||||
archie:
|
||||
engine: claude # this skill only works with Claude
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 5. Skills in practice
|
||||
|
||||
### 5.1 Shared skill library
|
||||
|
||||
```yaml
|
||||
# archie.yaml
|
||||
skills:
|
||||
remotes:
|
||||
- github.com/sam/archie-skills@v1
|
||||
```
|
||||
|
||||
Skills from the shared library are available alongside project-local skills. The agent loads them on demand when an issue references relevant concepts.
|
||||
|
||||
### 5.3 Skill that wraps an external tool
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: trivy-scan
|
||||
description: >
|
||||
Scan container images and filesystems for vulnerabilities using Trivy.
|
||||
Use when asked about security scanning, CVEs, or container hardening.
|
||||
metadata:
|
||||
archie:
|
||||
tools: [docker, trivy]
|
||||
engine: any
|
||||
---
|
||||
## Procedure
|
||||
1. `trivy image --severity HIGH,CRITICAL <image>`
|
||||
2. If findings exist, report each CVE with package, version, and fixed version
|
||||
3. If no findings, report clean
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 6. Comparison: archie-core vs existing systems
|
||||
|
||||
| | archie-core | Claude Code | Codex CLI | GitHub Actions | External Agent |
|
||||
| ------------------------ | ---------------------------------------------- | ------------------------------- | ------------------------------- | ---------------------------------- | ------------------------------- |
|
||||
| **How it receives work** | GitHub issue assignment, Linear label, webhook | Chat, slash commands | Chat, slash commands | YAML triggers (push, PR, schedule) | Chat, cron, webhooks |
|
||||
| **What it does** | Analyse → implement → gate → PR | Analyse → implement → gate → PR | Analyse → implement → gate → PR | Run arbitrary shell commands | Analyse → implement → gate → PR |
|
||||
| **Skills** | SKILL.md (agentskills.io) | SKILL.md (native) | SKILL.md (agentskills.io) | Composite actions | SKILL.md (native) |
|
||||
| **Gates** | Named checkpoints in archie.yaml | Ad-hoc (CLAUDE.md + lint) | Ad-hoc | Steps in jobs | Skills with gates |
|
||||
| **Engine pluggable** | Yes | No (fixed to Claude) | No (fixed to Codex) | No (fixed to GitHub) | Yes (provider config) |
|
||||
| **Worktree isolation** | Yes | Yes (`--worktree`) | No | No (ephemeral runner) | No |
|
||||
| **Blueprint/cron** | Export externally | No | No | Schedule trigger | Native |
|
||||
| **Where it runs** | Docker sandbox | Host | Host or sandbox | GitHub runner | Host, Docker, Modal, SSH |
|
||||
|
||||
---
|
||||
|
||||
## 7. Implementation phases
|
||||
|
||||
### Phase 1: Workflow file and gates (current MVP)
|
||||
|
||||
- `archie.yaml` parser
|
||||
- Gate runner executing shell commands and checking exit codes
|
||||
- Skill discovery from project and user paths
|
||||
- GitHub interface: claim issues, create worktrees, open PRs
|
||||
|
||||
### Phase 2: Skills
|
||||
|
||||
- SKILL.md progressive disclosure (advertise → activate → resources)
|
||||
- archie-specific metadata parsing
|
||||
- Skill chaining: skills that depend on other skills
|
||||
- `archie skills list/install` CLI
|
||||
|
||||
### Phase 3: Engine abstraction
|
||||
|
||||
- Engine interface definition
|
||||
- Claude Code adapter
|
||||
- Raw LLM adapter
|
||||
- Engine fallback chain
|
||||
- Per-skill engine preferences
|
||||
|
||||
### Phase 4: Advanced features
|
||||
|
||||
- Gate overrides per skill
|
||||
- Skill templates for project scaffolding (`archie init --skill go-service`)
|
||||
- Remote skill libraries (git repos as skill sources)
|
||||
- Blueprint export to an external scheduler
|
||||
|
||||
### Phase 5: Additional interfaces
|
||||
|
||||
- Linear webhook integration
|
||||
- Generic webhook interface for arbitrary sources
|
||||
- CLI command interface (`archie run <command>`)
|
||||
|
||||
---
|
||||
|
||||
## 8. Open questions
|
||||
|
||||
1. **Claim protocol:** Single-claim (arcie takes one issue at a time) or queue-based (claims N issues, works through them sequentially)?
|
||||
2. **Concurrent worktrees:** Allow multiple archie-core instances working on different issues simultaneously?
|
||||
3. **PR merging:** Should archie-core ever auto-merge, or always require human review?
|
||||
4. **Skill registry:** Self-host on git.catlow.cloud, use agentskills.io, or both?
|
||||
5. **Engine budget enforcement:** Per-issue, per-skill, or monthly cap?
|
||||
6. **Sandbox building:** Pre-built Docker images vs. project-defined Dockerfiles vs. Nix shells?
|
||||
@@ -1,400 +0,0 @@
|
||||
# archie-core Workflows & Skills -- Product Requirements Document
|
||||
|
||||
**Author:** Archie
|
||||
**Date:** 2026-07-18
|
||||
**Status:** Draft
|
||||
|
||||
---
|
||||
|
||||
## Overview
|
||||
|
||||
This PRD defines a workflow and skills system for archie-core. Workflow files declare gates, tool availability, execution engines, and skill references. Skills are reusable playbook documents the agent loads on demand. Together they enable any project to define how agents work within their sandbox and select an available execution engine.
|
||||
|
||||
---
|
||||
|
||||
## 1. Workflow Files (`archie.yaml`)
|
||||
|
||||
### 1.1 Discovery
|
||||
|
||||
A project declares its workflow in `archie.yaml` at the project root. archie-core discovers it the same way Task (Taskfile) and devcontainers do:
|
||||
|
||||
```
|
||||
.archie.yaml (root of repo -- highest precedence)
|
||||
archie.yaml (repo root)
|
||||
.archie/archie.yaml (subdirectory, one level deep)
|
||||
```
|
||||
|
||||
If no file is found, archie-core uses built-in defaults (read, write, bash).
|
||||
|
||||
### 1.2 Schema
|
||||
|
||||
```yaml
|
||||
# archie.yaml -- complete schema
|
||||
version: "1"
|
||||
|
||||
# Project identity
|
||||
project:
|
||||
name: my-go-service
|
||||
language: go
|
||||
|
||||
# Available skills (directories or individual files)
|
||||
skills:
|
||||
paths:
|
||||
- .archie/skills/ # project-local skills
|
||||
- ~/.archie/skills/ # per-user skills
|
||||
- github.com/org/shared-skills@v1 # remote skill repo
|
||||
skills:
|
||||
- go-testing # named skill from any path
|
||||
- security-audit
|
||||
|
||||
# Execution engines in preference order
|
||||
engines:
|
||||
- type: claude # Claude Code CLI
|
||||
model: sonnet
|
||||
- type: codex # OpenAI Codex
|
||||
- type: pi # Pi agent harness
|
||||
- type: raw # Direct LLM without agent wrapper
|
||||
|
||||
# Sandbox definition (what the Docker container provides)
|
||||
sandbox:
|
||||
image: ghcr.io/samcharles93/archie-sandbox:latest
|
||||
tools:
|
||||
- go
|
||||
- golangci-lint
|
||||
- gofumpt
|
||||
- task
|
||||
- gh
|
||||
- docker
|
||||
mounts:
|
||||
- source: /var/run/docker.sock
|
||||
target: /var/run/docker.sock
|
||||
env:
|
||||
GOFLAGS: "-mod=readonly"
|
||||
CGO_ENABLED: "0"
|
||||
|
||||
# Gates -- ordered checkpoints that must pass
|
||||
gates:
|
||||
test:
|
||||
run: go test -race -count=1 ./...
|
||||
timeout: 300
|
||||
description: "All tests must pass"
|
||||
lint:
|
||||
run: golangci-lint run ./...
|
||||
timeout: 120
|
||||
description: "Zero lint issues"
|
||||
format:
|
||||
run: gofumpt -w . && git diff --exit-code
|
||||
description: "No formatting drift"
|
||||
vet:
|
||||
run: go vet ./...
|
||||
description: "No vet warnings"
|
||||
deadcode:
|
||||
run: task deadcode
|
||||
optional: true # non-blocking gate
|
||||
description: "Dead code check (advisory)"
|
||||
|
||||
# Quality pipeline -- ordered sequence of gate groups
|
||||
quality:
|
||||
pre_commit:
|
||||
- test
|
||||
- lint
|
||||
- format
|
||||
- vet
|
||||
pre_push:
|
||||
- deadcode
|
||||
|
||||
# Commit conventions
|
||||
commit:
|
||||
format: conventional # conventional commits
|
||||
signoff: false
|
||||
template: "feat({scope}): {description}"
|
||||
|
||||
# PR conventions
|
||||
pr:
|
||||
template: .github/PULL_REQUEST_TEMPLATE.md
|
||||
checks:
|
||||
- test
|
||||
- lint
|
||||
|
||||
# Project-specific commands (what `archie run <name>` executes)
|
||||
commands:
|
||||
build:
|
||||
run: go build -o bin/app ./cmd/server
|
||||
description: "Build the binary"
|
||||
serve:
|
||||
run: go run ./cmd/server
|
||||
description: "Start dev server"
|
||||
test:
|
||||
run: go test ./...
|
||||
description: "Run all tests"
|
||||
lint:
|
||||
run: golangci-lint run ./...
|
||||
description: "Run linter"
|
||||
all:
|
||||
run:
|
||||
- gofumpt -w .
|
||||
- go fix ./...
|
||||
- golangci-lint run ./...
|
||||
- go test -race ./...
|
||||
- task deadcode
|
||||
description: "Full quality pipeline"
|
||||
```
|
||||
|
||||
### 1.3 Design decisions (with rationale)
|
||||
|
||||
| Decision | Rationale |
|
||||
| -------------------------------------- | ------------------------------------------------------------------------------------------------------------------------ |
|
||||
| YAML over TOML/JSON | Already dominant in CI (GitHub Actions, GitLab CI, Taskfile). Human-readable with comments. |
|
||||
| Single file over multi-file | Task discovery (like `Taskfile.yml`), devcontainer conventions. Avoids directory sprawl. |
|
||||
| Gates as named checkpoints | GitHub Actions job model. Gates can be composed into quality pipelines, selected individually, or skipped with `--skip`. |
|
||||
| Engines as ordered preference list | Supports deterministic fallback between available engines. Each engine declares its own tool surface. |
|
||||
| Skills as paths + references | Matches devcontainer features (paths resolve to directories) and skills.sh (namespaced references). |
|
||||
| Commands section for direct invocation | Arnie can `archie run test` without an agent turn. Thin wrapper over the sandbox. |
|
||||
| Quality pipeline groups gates | Pre-commit vs pre-push vs pre-merge distinction. Some gates are required, some advisory. |
|
||||
|
||||
---
|
||||
|
||||
## 2. Skills
|
||||
|
||||
### 2.1 Format
|
||||
|
||||
Skills follow the [agentskills.io](https://agentskills.io/specification) specification:
|
||||
|
||||
```
|
||||
skill-name/
|
||||
├── SKILL.md # Required: YAML frontmatter + Markdown instructions
|
||||
├── scripts/ # Optional: executable helpers
|
||||
├── references/ # Optional: longer docs, checklists
|
||||
└── assets/ # Optional: templates, configs
|
||||
```
|
||||
|
||||
**SKILL.md frontmatter:**
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: go-testing
|
||||
description: >
|
||||
Run Go tests with race detection, coverage, and benchmark analysis.
|
||||
Use when asked to test Go code, run the test suite, or check coverage.
|
||||
version: 1.0.0
|
||||
metadata:
|
||||
archie:
|
||||
gates: [test] # gates this skill requires
|
||||
tools: [go, golangci-lint] # sandbox tools it needs
|
||||
engine: any # engine preference
|
||||
compatibility: Requires Go 1.22+
|
||||
---
|
||||
```
|
||||
|
||||
### 2.2 Progressive disclosure
|
||||
|
||||
Following the skills.sh and Claude Code patterns:
|
||||
|
||||
1. **Advertise** (~100 tokens): `name` + `description` loaded at session start
|
||||
2. **Load** (<5000 tokens recommended): Full SKILL.md body when skill activates
|
||||
3. **Resources** (as needed): Scripts, references, assets loaded on demand
|
||||
|
||||
### 2.3 archie-specific metadata
|
||||
|
||||
Skills can carry archie-specific frontmatter under `metadata.archie`:
|
||||
|
||||
```yaml
|
||||
metadata:
|
||||
archie:
|
||||
gates: [test, lint] # must-pass gates before skill runs
|
||||
tools: [go, docker] # sandbox tools required
|
||||
engine: any # preferred engine
|
||||
model: gpt-4o # preferred model
|
||||
budget_usd: 2.00 # max spend ceiling
|
||||
timeout: 600 # max seconds
|
||||
worktree: true # create isolated worktree
|
||||
```
|
||||
|
||||
### 2.4 Skill sources (inspired by devcontainer features + Dagger modules)
|
||||
|
||||
```
|
||||
skills:
|
||||
paths:
|
||||
- .archie/skills/ # project-local (committed)
|
||||
- ~/.archie/skills/ # per-user (personal)
|
||||
skills:
|
||||
- go-testing # by name from any path
|
||||
remotes:
|
||||
- github.com/samcharles93/archie-skills@v1 # tagged git repo
|
||||
- https://agentskills.io/registry # community registry
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## 3. Execution Engine Model
|
||||
|
||||
### 3.1 Engine abstraction
|
||||
|
||||
Each engine provides the same interface. The workflow file declares preference order; archie-core resolves the first available engine at runtime.
|
||||
|
||||
```
|
||||
Engine interface:
|
||||
- Run(prompt, tools[], budget, timeout) -> Result
|
||||
- Tools() -> []ToolSchema
|
||||
- Capabilities() -> {streaming, reasoning, vision, agentic}
|
||||
```
|
||||
|
||||
### 3.2 Supported engines
|
||||
|
||||
| Engine | Type | What it provides |
|
||||
| -------- | ---------------- | ------------------------------------------------------ |
|
||||
| `claude` | Claude Code CLI | Full agent loop, tool use, worktrees, subagents |
|
||||
| `codex` | OpenAI Codex CLI | Agentic coding with sandbox |
|
||||
| `pi` | Pi agent harness | Minimalist coding agent, stdio protocol |
|
||||
| `raw` | Direct LLM call | Single-turn prompt, no agent loop. For simple scripts. |
|
||||
|
||||
### 3.3 Engine selection logic
|
||||
|
||||
```yaml
|
||||
engines:
|
||||
- type: claude
|
||||
model: sonnet
|
||||
budget_usd: 5.00
|
||||
- type: raw
|
||||
model: gpt-4o-mini
|
||||
```
|
||||
|
||||
arcie-core tries engines in order and selects the first available,
|
||||
authenticated engine. Each engine declares its budget ceiling.
|
||||
|
||||
---
|
||||
|
||||
## 4. Additional Features
|
||||
|
||||
### 4.1 Worktree isolation (`worktree: true`)
|
||||
|
||||
Inspired by Claude Code's `--worktree` flag. When a skill or command sets `worktree: true`, archie-core:
|
||||
|
||||
1. Creates an isolated git worktree at `.archie/worktrees/<skill-name>-<timestamp>/`
|
||||
2. Runs all gates and implementation in that worktree
|
||||
3. Cleans up on success, preserves on failure for inspection
|
||||
|
||||
This prevents concurrent agent sessions from conflicting and enables parallel agent execution.
|
||||
|
||||
### 4.2 Skill chaining and composition
|
||||
|
||||
Skills can declare dependencies, forming a DAG:
|
||||
|
||||
```yaml
|
||||
---
|
||||
name: full-ci
|
||||
description: Complete CI pipeline including security audit
|
||||
metadata:
|
||||
archie:
|
||||
requires: [go-testing, security-audit]
|
||||
run_sequential: true
|
||||
---
|
||||
```
|
||||
|
||||
arcie-core resolves the dependency graph and runs skills in order (parallel where possible, respecting `run_sequential`). This is conceptually similar to GitHub Actions `needs` and Taskfile `deps`.
|
||||
|
||||
### 4.3 Gate overrides per skill
|
||||
|
||||
A skill can override project-level gates:
|
||||
|
||||
```yaml
|
||||
metadata:
|
||||
archie:
|
||||
gates:
|
||||
test:
|
||||
run: go test -short ./... # override: faster test for this skill
|
||||
lint: skip # skip lint for this skill
|
||||
```
|
||||
|
||||
Three override modes: `override` (replace command), `skip` (omit gate), `add` (add new gate requirement).
|
||||
|
||||
### 4.4 Skill templates (scaffolding)
|
||||
|
||||
Skills can carry an `assets/` directory with templates. When archie-core initialises a new project, it can apply skill templates:
|
||||
|
||||
```
|
||||
skill-name/
|
||||
├── SKILL.md
|
||||
└── assets/
|
||||
├── .archie.yaml.tmpl # Template workflow file
|
||||
├── Taskfile.yml.tmpl # Template task runner
|
||||
└── .golangci.yml.tmpl # Template linter config
|
||||
```
|
||||
|
||||
`archie init --skill go-service` scaffolds a new project with the go-service skill's templates applied.
|
||||
|
||||
### 4.5 Blueprint export (external cron integration)
|
||||
|
||||
Any archie-core workflow can be exported as an automation blueprint:
|
||||
|
||||
```yaml
|
||||
metadata:
|
||||
archie:
|
||||
blueprint:
|
||||
schedule: "every 6h"
|
||||
deliver: telegram
|
||||
name: "CI monitor"
|
||||
```
|
||||
|
||||
The export produces a `SKILL.md` with scheduler metadata. The blueprint's prompt is the archie workflow's quality pipeline.
|
||||
|
||||
---
|
||||
|
||||
## 5. Comparison to Existing Systems
|
||||
|
||||
| Feature | archie-core | GitHub Actions | Dagger | Taskfile | devcontainer | External Skills |
|
||||
| ---------------------- | ------------------- | ----------------- | -------------- | ---------- | ----------------- | --------------- |
|
||||
| Language | YAML | YAML | Go/Python/TS | YAML | JSON | Markdown |
|
||||
| Gates | Named + composable | Steps in jobs | Functions | Tasks | Lifecycle scripts | N/A |
|
||||
| Engine abstraction | First-class | GitHub only | Dagger Engine | Shell only | None | Provider |
|
||||
| Skills | agentskills.io spec | Composite actions | Dagger Modules | Includes | Features | SKILL.md |
|
||||
| Worktree isolation | Built-in | No | Containers | No | Container | No |
|
||||
| Blueprint export | To external cron | No | No | No | No | Native |
|
||||
| Multi-engine fallback | Yes (ordered list) | No | No | No | No | Provider config |
|
||||
| Progressive disclosure | Yes (skill spec) | No | No | No | Feature metadata | Yes |
|
||||
|
||||
---
|
||||
|
||||
## 6. Implementation Phases
|
||||
|
||||
### Phase 1: Core workflow file
|
||||
|
||||
- `archie.yaml` parser and schema validation
|
||||
- Gate runner (test, lint, format, vet)
|
||||
- `archie run <command>` CLI
|
||||
- Sandbox Docker integration
|
||||
|
||||
### Phase 2: Skills
|
||||
|
||||
- SKILL.md discovery and progressive disclosure
|
||||
- Skill metadata with gate/tool/engine requirements
|
||||
- `archie skills list/install/search`
|
||||
|
||||
### Phase 3: Engine abstraction
|
||||
|
||||
- Engine interface definition
|
||||
- Claude Code adapter
|
||||
- Raw LLM adapter
|
||||
- Engine fallback chain
|
||||
|
||||
### Phase 4: Advanced features
|
||||
|
||||
- Worktree isolation
|
||||
- Skill chaining (dependency DAG)
|
||||
- Gate overrides
|
||||
- Blueprint export
|
||||
|
||||
### Phase 5: Ecosystem
|
||||
|
||||
- Public skill registry
|
||||
- `archie init --skill <name>` scaffolding
|
||||
- Community skill contributions
|
||||
|
||||
---
|
||||
|
||||
## 7. Open Questions
|
||||
|
||||
1. **Skill registry hosting:** Self-hosted on git.catlow.cloud, or use agentskills.io?
|
||||
2. **External integration:** Should archie-core be exposed as a tool, a skill, or standalone?
|
||||
3. **Budget enforcement:** Per-skill budget vs. per-workflow budget vs. monthly cap?
|
||||
4. **Sandbox image building:** Pre-built images vs. Dockerfile in each skill?
|
||||
File diff suppressed because it is too large.
Load diff
@@ -1,220 +0,0 @@
|
||||
# Archie Design Decisions
|
||||
|
||||
Record of architectural choices, reversals, and lessons learned during
|
||||
development. Each entry has a date, a decision, the reasoning, and the
|
||||
context that led to it. This document is the first thing to read before
|
||||
changing anything that contradicts a prior decision.
|
||||
|
||||
---
|
||||
|
||||
## 2026-08-24 -- Turn continuation is never output-volume or token gated
|
||||
|
||||
**Decision**: A turn is never stopped because an aggregate token count or
|
||||
aggregate tool-result character count was reached. `max_tokens` and
|
||||
`turn_budget_chars` are not runtime continuation controls. Tool output is
|
||||
bounded only per invocation with `max_result_chars`; oversized individual
|
||||
results are spilled when a workspace-readable spill directory is configured,
|
||||
or explicitly truncated otherwise.
|
||||
|
||||
**Reasoning**: Aggregate caps discard useful work and caused the model to emit
|
||||
repeated `turn budget exceeded (200000 chars)` tool failures instead of
|
||||
finishing. Model context/output accounting and tool-result volume are distinct:
|
||||
provider output limits may describe one model response, but they must never be
|
||||
used to terminate the multi-step turn.
|
||||
|
||||
**Context**: GitHub #604 showed full file and module listings followed by four
|
||||
identical read failures and a shell failure at the old 200,000-character cap.
|
||||
The renderer now summarises those legacy events for replay, while current
|
||||
dispatch never creates them. Find and grep are confined to the active
|
||||
workspace/worktree; the Go module cache remains readable only by explicit
|
||||
path, not by discovery.
|
||||
|
||||
---
|
||||
|
||||
## 2026-07-23 -- Forge-agnostic issue creation via CreateIssue
|
||||
|
||||
**Decision**: Add `CreateIssue(ctx, owner, repo, title, body, labels)
|
||||
(int, error)` to the `forge.Forge` interface. Every forge backend
|
||||
(Gitea, GitHub, future beads) implements it.
|
||||
|
||||
**Reasoning**: Agents discover out-of-scope findings during planning
|
||||
and building. These should be filed as tickets immediately rather than
|
||||
lost. Making `CreateIssue` part of the Forge interface means the agent
|
||||
calls one method regardless of the underlying ticketing system.
|
||||
|
||||
**Future**: A `beads` forge backend will implement `CreateIssue` by
|
||||
calling `bd create`. This makes beads the internal/default issue tracker
|
||||
while Gitea/GitHub are external forges. The agent doesn't know which
|
||||
it's talking to -- the daemon resolves the forge from repo config.
|
||||
|
||||
---
|
||||
|
||||
## 2026-07-23 -- Dolt and Beads for agent-native issue tracking
|
||||
|
||||
**Decision**: Install dolt (version-controlled SQL) and beads (`bd`,
|
||||
a graph-based issue tracker for AI agents) as the foundation for
|
||||
multi-repo scaling and multi-agent coordination.
|
||||
|
||||
**Reasoning**: Beads provides persistent memory across sessions, first-
|
||||
class dependency tracking, JSON output for programmatic use, and hash-
|
||||
based IDs that prevent merge conflicts in multi-agent workflows. It's
|
||||
built on Dolt which gives cell-level merge, native branching, and
|
||||
remote sync -- the same primitives git gives code but applied to issues.
|
||||
|
||||
**Context**: Gas Town (`~/gt/`) is cloned for reference -- it implements
|
||||
a multi-agent workspace on top of beads. The archie-core scaling
|
||||
strategy will follow a similar model: a coordinator daemon with per-repo
|
||||
agents, all sharing a beads-backed task graph.
|
||||
|
||||
**Current state**: dolt 2.2.2, beads 1.1.0 installed. Beads initialised
|
||||
in archie-core (`.beads/`). Six issues seeded for the scaling roadmap.
|
||||
|
||||
---
|
||||
|
||||
## 2026-07-23 -- Token budgets must be generous, not predictive
|
||||
|
||||
> **Superseded by the 2026-08-24 decision above.** There is no configured
|
||||
> aggregate token cap; model token usage remains accounting only.
|
||||
|
||||
**Decision**: Set `max_tokens` to 100,000,000 (100M). Do not attempt to
|
||||
predict what a task needs without data. Lower limits later based on
|
||||
actual per-workflow/per-repo metrics.
|
||||
|
||||
**Reasoning**: An agent killed mid-task at 1M tokens wastes every token
|
||||
it already consumed. There is no compaction or checkpointing yet, so a
|
||||
killed agent is a total loss. Long-running agents regularly use 160+ steps and
|
||||
hundreds of thousands of tokens per request. Large repositories need
|
||||
proportionally more.
|
||||
|
||||
**Context**: The planner burned 357K tokens just to discover a fix
|
||||
already existed. The builder hit 1M at step 25 of 90. Neither task was
|
||||
unreasonable -- they were just exploring a large codebase.
|
||||
|
||||
**Future**: Track actual token consumption per workflow/stage/repo. Use
|
||||
that data to set informed limits. Build compaction or checkpointing so
|
||||
a killed agent can resume rather than restart.
|
||||
|
||||
---
|
||||
|
||||
## 2026-07-23 -- baseline-fix: auto-repair pre-existing gate failures
|
||||
|
||||
**Decision**: When `StageBaselineGate` detects a red gate (gofumpt, go
|
||||
vet, etc. failing on clean main), launch the builder to fix the
|
||||
failures via TDD rather than parking. Only park if the builder cannot
|
||||
fix them.
|
||||
|
||||
**Reasoning**: A red baseline means the repo was broken before archie
|
||||
touched it. Parking creates an infinite loop -- the next retry hits the
|
||||
same failure. The agent should fix pre-existing issues, not fail on them.
|
||||
|
||||
**Implementation**: `StageBaselineGate` now calls `tc.Agent.Run()` with
|
||||
a TDD mission when the gate fails. Uses the same builder agent. Note:
|
||||
this required wiring `tc.Agent` (the runner) through the stage context.
|
||||
|
||||
---
|
||||
|
||||
## 2026-07-23 -- No hardcoded MaxSteps in workflow stages
|
||||
|
||||
**Decision**: Remove all hardcoded `MaxSteps` values from workflow
|
||||
stages. Every stage inherits from `[budgets].max_steps` in the config.
|
||||
|
||||
**Reasoning**: Hardcoded values (15 for plan, 15 for TDD analyse, 15
|
||||
for feasibility assess, 20 for PRD) were arbitrary and broke on large
|
||||
repos. The config should be the single source of truth.
|
||||
|
||||
**Files affected**: `implement.go`, `tdd.go`, `feasibility.go`.
|
||||
|
||||
---
|
||||
|
||||
## 2026-07-23 -- No-op detection: close issues when build has 0 changes
|
||||
|
||||
**Decision**: When the builder completes with `StatusPassed` and 0 file
|
||||
changes, close the issue with a comment rather than parking on "worktree
|
||||
has no changes to commit".
|
||||
|
||||
**Reasoning**: A builder that passes with 0 changes means the fix
|
||||
already exists or the issue is a no-op. The old behaviour parked in an
|
||||
infinite loop (commit-push fails because nothing changed, task re-queues,
|
||||
builder runs again, same result).
|
||||
|
||||
**Implementation**: `TaskContext.BuildNoChanges` is set in the build
|
||||
stage's `OnResult` when `Status == Passed && len(Changes) == 0`.
|
||||
`StageCommitPush` checks this flag and calls `Forge.CloseIssue()` +
|
||||
sets `Outcome = Merged` to stop the workflow.
|
||||
|
||||
**Test**: `TestStageCommitPushClosesIssueWhenBuildNoChanges` in
|
||||
`implement_test.go`.
|
||||
|
||||
---
|
||||
|
||||
## 2026-07-23 -- assignee trigger over label trigger
|
||||
|
||||
**Decision**: Default to `trigger = "assignee"` instead of `trigger =
|
||||
"label"`. The daemon only claims issues explicitly assigned to the bot
|
||||
user.
|
||||
|
||||
**Reasoning**: Codex created 80+ issues with the `archie` label, and
|
||||
the daemon auto-claimed every one. Label-based triggering is too
|
||||
promiscuous for repos shared between humans and agents.
|
||||
|
||||
---
|
||||
|
||||
## 2026-07-23 -- DeepSeek v4 Pro as primary model
|
||||
|
||||
**Decision**: Use `deepseek/deepseek-v4-pro` as the planner and builder
|
||||
model. Qwythos-9B (local llama.cpp) is the fallback for offline/cheap
|
||||
tasks.
|
||||
|
||||
**Reasoning**: Qwythos couldn't complete a representative large-repository
|
||||
plan stage before timing out. DeepSeek completed it in 21 iterations. Large
|
||||
repositories need a larger model.
|
||||
|
||||
**Provider setup**: `class = "deepseek"`, API key via `DEEPSEEK_API_KEY`
|
||||
env var from Bitwarden Secrets Manager (bws).
|
||||
|
||||
---
|
||||
|
||||
## 2026-07-22 -- v1.0.0 tagged
|
||||
|
||||
**Decision**: Tagged `v1.0.0` at commit incorporating the daemon/agent
|
||||
split, NATS JetStream, Docker sandbox, Yaegi plugins, agentskills.io
|
||||
skills, and Gitea forge support.
|
||||
|
||||
---
|
||||
|
||||
## 2026-07-22 -- Docker Compose stack with NATS + containers
|
||||
|
||||
**Decision**: The production deployment uses `docker-compose.yml` with
|
||||
NATS, archied, and archie-agent containers. Config at `config.docker.toml`.
|
||||
|
||||
**Key fixes**:
|
||||
|
||||
- NATS healthcheck uses `wget localhost:8222/healthz` (not `nats-server check`)
|
||||
- `host.docker.internal:host-gateway` extra_hosts for Linux
|
||||
- Config mount path: `config.docker.toml` → `/etc/archie/config.toml`
|
||||
- No stale `image:` tag on archied service (forces local build)
|
||||
|
||||
---
|
||||
|
||||
## 2026-07-22 -- Worktree Prepare before Container Acquire
|
||||
|
||||
**Decision**: Clone the worktree (`Trees.Prepare()`) before acquiring
|
||||
a Docker container. Made `Prepare()` idempotent -- skips if `.git`
|
||||
already exists.
|
||||
|
||||
**Reasoning**: Docker bind-mounts fail with "bind source path does not
|
||||
exist" if the worktree hasn't been cloned yet. The old code acquired
|
||||
the container first, then the prepare stage cloned into a path that
|
||||
didn't exist on the host.
|
||||
|
||||
---
|
||||
|
||||
## 2026-07-22 -- Gofumpt and Go tools must be on PATH
|
||||
|
||||
**Decision**: The daemon's `exec.Command` for gate checks inherits the
|
||||
process PATH. `~/go/bin` (where `gofumpt`, `golangci-lint`, etc. live)
|
||||
must be in the PATH before starting the daemon.
|
||||
|
||||
**Symptom**: `baseline red -- gofumpt -w . fails` but manual run passes.
|
||||
Root cause: `which gofumpt` returns nothing because `~/go/bin` isn't on
|
||||
PATH in external agent sessions.
|
||||
@@ -1,235 +0,0 @@
|
||||
# Multi-Agent Collaboration -- PRD
|
||||
|
||||
**Status:** Draft (discovery interview complete, 2026-07-25)
|
||||
**Author:** Discovery interview (archie-core-abg.1), synthesised from Sam's answers
|
||||
**Parent epic:** archie-core-abg
|
||||
|
||||
---
|
||||
|
||||
## 0. Framing
|
||||
|
||||
Today, "running multiple agents" means running multiple independent `archied`
|
||||
processes on the same host (`carina`): `archie` (bot_user=archie, multiple
|
||||
repositories, deepseek models) and `winter` (bot_user=winter, a restricted
|
||||
repository set, local llama.cpp models). Confirmed by diffing
|
||||
`~/.config/archie/config.toml` and `~/.config/archie/winter.toml` on carina:
|
||||
they differ in `bot_user`, `[[repos]]` list, and `[models]`/`[providers]` --
|
||||
not just identity. `Config.BotUser` is a single global field, so one process
|
||||
= one identity today.
|
||||
|
||||
The goal stated for archie-core overall is to become a fully extensible
|
||||
agentic workhorse. This PRD
|
||||
scopes the "multi-agent" slice of that: what it takes to go from N processes
|
||||
to one daemon that can do what N processes do, plus the surrounding
|
||||
capabilities (chat channels, plugins, memory) needed to reach that bar.
|
||||
|
||||
## 1. Scope (confirmed in interview)
|
||||
|
||||
All of the following are **in scope** for the epic (not necessarily the first
|
||||
implementation slice -- see section 6):
|
||||
|
||||
1. **Daemon-side concurrency** -- one daemon process running multiple bot
|
||||
identities concurrently, replacing N separate `archied` processes.
|
||||
2. **Cross-repo / cross-config flexibility** -- identities are not statically
|
||||
bound to one repo list at process startup; repo/model/provider
|
||||
configuration varies per identity within a single daemon.
|
||||
3. **Agent-to-agent collaboration on a single task** -- one agent's output
|
||||
feeding another (e.g. plan -> implement -> review handoff), not just N
|
||||
identities running in parallel unaware of each other.
|
||||
4. **Conversational access** -- chat channels (Telegram, web UI, more via
|
||||
plugins) where Sam talks to archie directly, outside the Gitea
|
||||
issue-driven flow. Confirmed requirement: **full parity** with the
|
||||
issue-driven flow -- chat is an alternate entry point into the same
|
||||
triage/planner/builder dispatch pipeline, not a separate toy Q&A surface.
|
||||
Chat must be able to: answer questions read-only, spawn/control real work
|
||||
(start an agent, check status, approve/reject a PR, cancel a run), and
|
||||
drive the same pipeline Gitea assignment drives today.
|
||||
5. **General extensibility** -- plugins/channels/integrations should be
|
||||
addable, not hardcoded:
|
||||
- Additional forges beyond GitHub/Gitea (e.g. GitLab) via the existing
|
||||
`forge.Forge` interface, as Layer 2 core plugins (see
|
||||
`docs/prds/archie-core-v2-architecture.md` sec.5).
|
||||
- MCP server connections (archie as an MCP client, to consume external
|
||||
tools/data sources).
|
||||
- SSH / remote execution as an agent capability.
|
||||
- Arbitrary API integrations, callable by agents as tools.
|
||||
- Additional chat channels beyond Telegram/web UI, as plugins.
|
||||
6. **Memory systems for multi-session chat** -- conversations with archie
|
||||
need to persist across sessions (distinct from the existing per-task
|
||||
`/data/memory.jsonl` sketch in the v2 PRD, which is task/project scoped,
|
||||
not conversation scoped).
|
||||
7. **Slash-command capabilities** in chat channels (e.g. `/status`, `/spawn`,
|
||||
`/approve`) for direct channel interaction.
|
||||
8. **Multi-user support**, as a capability the architecture should not
|
||||
foreclose -- "if I want to extend my agent to multiple people, I should be
|
||||
able to." Not required to ship in the first slice (see section 5), but
|
||||
the identity/session model must not assume single-operator forever.
|
||||
|
||||
## 2. Explicitly out of scope (for now)
|
||||
|
||||
- **Voice/audio interfaces.** Text-based chat only.
|
||||
- **Building GitHub support** -- it already exists (`internal/forge`
|
||||
implements GitHub REST polling per `ARCHITECTURE.md`).
|
||||
- Anything not listed in section 1 that isn't a natural extension of the
|
||||
plugin/forge/channel interfaces below.
|
||||
|
||||
Note: multi-user auth and GitLab support are **in scope as capabilities the
|
||||
architecture must support**, but are not committed to the first
|
||||
implementation slice -- see section 5.
|
||||
|
||||
## 3. Constraints from existing architecture
|
||||
|
||||
From `ARCHITECTURE.md` and `docs/prds/archie-core-v2-architecture.md`
|
||||
(read in full before implementation; summarised here):
|
||||
|
||||
- **`Config.BotUser` is a single global field** (`internal/config`) -- the
|
||||
root blocker for daemon-side multi-identity. Becomes a per-identity field
|
||||
in a new config shape (see section 4).
|
||||
- **NATS/JetStream task distribution is implemented**: `internal/nats`
|
||||
publishes tasks to `archie.task.<workflow_type>` subjects; agents
|
||||
(in-process, subprocess, or Docker containers per `internal/container`)
|
||||
consume and report back over `archie.agent.<task_id>.{response,system,request}`.
|
||||
This subject hierarchy is a natural fit for routing by identity too
|
||||
(e.g. `archie.<identity>.task.<type>`) but that's a design decision, not
|
||||
yet made.
|
||||
- **Dispatch is `daemon.Run()` polling per configured forge/repo list**,
|
||||
serialised per `owner/repo` by default (`AllowConcurrent` opts out).
|
||||
Multi-identity daemon means multiple poll loops (or one loop iterating
|
||||
multiple identity configs) feeding the same NATS/container dispatch
|
||||
machinery.
|
||||
- **Layer 2 core plugins (`~/.config/archie/plugins/`, Yaegi-loaded,
|
||||
`Plugin.Register(daemon)`) are designed but not wired** -- interface
|
||||
exists (`internal/plugin/plugin.go`), no loader in `cmd/archied/main.go`.
|
||||
This is the natural extension point for new forges, MCP client
|
||||
connections, and chat channel plugins. Building the multi-agent epic on
|
||||
top of an unwired plugin layer means **wiring Layer 2 is a prerequisite**,
|
||||
not parallel work.
|
||||
- **No chat/messaging code exists today** -- no Telegram, no web UI beyond
|
||||
the read-only SSE dashboard (`internal/webui`). This is greenfield.
|
||||
- **The daemon gatekeeps all agent output** -- "no agent output reaches a
|
||||
human without daemon review" (`archie-core-v2-architecture.md` sec.7).
|
||||
Chat channels must respect this: a chat message that triggers a spawn goes
|
||||
through the same review/labelling machinery PRs and comments do today, not
|
||||
a side channel that bypasses it.
|
||||
- **Environmental constraints over prompt rules** (`ARCHITECTURE.md` design
|
||||
decision #1) -- chat-triggered actions (spawn, approve, cancel) should be
|
||||
enforced by code (permission checks, rate limits), not by asking the LLM
|
||||
nicely.
|
||||
|
||||
## 4. Identity model (design direction, not yet finalized)
|
||||
|
||||
Confirmed requirement: within one daemon, identities differ by bot identity,
|
||||
repo list, _and_ model/provider config (per the archie/winter diff). Proposed
|
||||
shape -- **not yet approved, needs a follow-up design pass before
|
||||
implementation**:
|
||||
|
||||
```toml
|
||||
# ~/.config/archie/config.toml (sketch)
|
||||
[[identities]]
|
||||
name = "archie"
|
||||
bot_user = "archie"
|
||||
forge = { type = "gitea", host = "...", token_env = "..." }
|
||||
models = { triage = "...", planner = "...", builder = "..." }
|
||||
repos = [ ... ]
|
||||
|
||||
[[identities]]
|
||||
name = "winter"
|
||||
bot_user = "winter"
|
||||
forge = { type = "gitea", host = "...", token_env = "..." }
|
||||
models = { triage = "...", planner = "...", builder = "..." }
|
||||
repos = [ ... ]
|
||||
```
|
||||
|
||||
```
|
||||
|
||||
**Design answer (2026-07-25): per-identity goroutine, shared infrastructure.**
|
||||
|
||||
Each identity gets its own goroutine running an independent poll loop with
|
||||
its own forge client, worktree manager, and NATS subject namespace
|
||||
(`archie.<identity>.task.<type>`). They share only the infrastructure
|
||||
pieces where isolation adds cost without benefit:
|
||||
|
||||
| Shared (one instance for all identities) | Per-identity (one per goroutine) |
|
||||
|---|---|
|
||||
| SQLite store (`internal/store`) | Forge client (different token per identity) |
|
||||
| NATS connection (`internal/nats`) | Worktree manager (different `BotUser` per identity) |
|
||||
| Container pool (`internal/container`) | Config subset: forge, repos, models, providers, dispatch, poll_interval, bot_user, bot_email |
|
||||
| Event bus (`internal/events`) | NATS subject namespace: `archie.<identity>.task.<type>` |
|
||||
| Web UI (`internal/webui`) | Poll loop goroutine |
|
||||
| Plugin registry (`internal/plugin`) | |
|
||||
| Gateway router (`internal/gateway`) | |
|
||||
|
||||
Decision rationale: per-identity goroutines guarantee failure isolation (one
|
||||
identity's forge outage cannot block another's poll tick), each identity
|
||||
gets its own forge rate-limit domain, and the existing `Daemon` struct maps
|
||||
cleanly -- each goroutine holds a thin `Identity` value (forge client + config
|
||||
subset + worktree manager + NATS subject prefix) and dispatches tasks with
|
||||
an `identity_name` column on the task row. The shared NATS connection
|
||||
multiplexes subjects by identity prefix; the shared store already handles
|
||||
concurrent ClaimNext via SQLite's serialized writes. NATS subjects carry
|
||||
the identity name so agent containers (which consume from NATS) route
|
||||
responses back to the correct daemon identity.
|
||||
|
||||
This design resolves the open question in section 4 of the original PRD
|
||||
draft (per-identity goroutine vs single loop iterating identities -- the
|
||||
former, for failure isolation).
|
||||
|
||||
## 5. Priority / phasing
|
||||
|
||||
Sam deferred ordering to this PRD (interview answer: "let the interview
|
||||
settle scope, I'll decide after seeing it written up"). Proposed
|
||||
dependency-ordered phases, for Sam to confirm or reorder:
|
||||
|
||||
**Phase A -- Foundation (blocks everything else)**
|
||||
- Wire Layer 2 core plugin loading (`~/.config/archie/plugins/`,
|
||||
`Plugin.Register(daemon)`) into `cmd/archied/main.go`. Currently designed,
|
||||
unwired -- both chat channels and new forges depend on this existing.
|
||||
|
||||
**Phase B -- Multi-identity daemon core**
|
||||
- Replace single `Config.BotUser` with the `[[identities]]` shape (section
|
||||
4, after design confirmation).
|
||||
- Multi-identity poll/dispatch, still issue-driven (Gitea only, no chat yet).
|
||||
- Migrate the two carina processes (archie, winter) onto one daemon as a
|
||||
real-world validation.
|
||||
|
||||
**Phase C -- Chat channel foundation**
|
||||
- Chat channel plugin interface (parallel to `forge.Forge`).
|
||||
- Telegram channel plugin: read-only Q&A against task/daemon state first,
|
||||
then spawn/control actions gated through the same review pipeline as
|
||||
issue-driven dispatch.
|
||||
- Web UI: extend `internal/webui` from read-only SSE dashboard to
|
||||
bidirectional chat.
|
||||
- Multi-session conversation memory (distinct persistence from per-task
|
||||
`/data/memory.jsonl`).
|
||||
- Slash commands (`/status`, `/spawn`, `/approve`, `/cancel`).
|
||||
|
||||
**Phase D -- Agent-to-agent collaboration**
|
||||
- Plan -> implement -> review handoff within a single task's workflow
|
||||
(builds on existing `workflow.Stage` sequencing -- this may already be
|
||||
close given the `implement` workflow's plan/build stage split; needs
|
||||
investigation into how much is genuinely new vs. reframing).
|
||||
|
||||
**Phase E -- Extended integrations (as needed, each is an independent
|
||||
plugin, no fixed order)**
|
||||
- GitLab forge plugin.
|
||||
- MCP client capability (archie consuming external MCP servers as tools).
|
||||
- SSH / remote execution tool.
|
||||
- Additional chat channels.
|
||||
- Multi-user support (identity/session model extended beyond
|
||||
single-operator -- needs its own design pass; not blocking Phase A-D).
|
||||
|
||||
Sam's explicit instruction was to identify next requirements **and begin
|
||||
work**, not just deliver a document. Phase A (wiring the Layer 2 plugin
|
||||
loader) is the correct starting point: it's small, well-specified already in
|
||||
`docs/prds/archie-core-v2-architecture.md` sec.5, and unblocks both the chat
|
||||
channel work and new forge plugins that everything else in this PRD depends
|
||||
on.
|
||||
|
||||
## 6. Acceptance criteria for this PRD
|
||||
|
||||
- [x] Reflects Sam's actual interview answers, not assumptions.
|
||||
- [x] Confirms the archie/winter config diff (repo lists differ, not just
|
||||
identity).
|
||||
- [ ] Broken into scoped, dependency-ordered beads issues under
|
||||
`archie-core-abg`, the way the 5zh epic was. (Next step, this session.)
|
||||
```
|
||||
@@ -1,461 +0,0 @@
|
||||
# archie-core TypeScript Plugin Engine -- PRD
|
||||
|
||||
**Author:** Archie
|
||||
**Date:** 2026-07-21
|
||||
**Status:** Draft
|
||||
|
||||
---
|
||||
|
||||
## Summary
|
||||
|
||||
A TypeScript-based plugin engine that lets repositories ship interpreted, dynamically-loaded workflow extensions. Plugins are `.ts` files placed in `.archie/workflows/`. archie-core discovers them on its next poll cycle, transpiles them to JavaScript via esbuild, and executes them in an embedded [goja](https://github.com/dop251/goja) runtime -- a pure-Go ECMAScript interpreter with zero CGO dependencies.
|
||||
|
||||
---
|
||||
|
||||
## Why TypeScript + goja
|
||||
|
||||
### TypeScript as the plugin language
|
||||
|
||||
TypeScript is the most widely understood language among developers writing automation, CI, and workflow scripts. It already ships in most projects. Gate authors already know it. The ecosystem for linting, formatting, and type-checking is mature and free.
|
||||
|
||||
Having a TypeScript-native plugin engine means:
|
||||
|
||||
- Plugin authors get familiar syntax, type safety, and IDE support
|
||||
- No separate toolchain -- just `.ts` files in a folder
|
||||
- Skills, gates, and workflow stages share the same language
|
||||
|
||||
### Why goja
|
||||
|
||||
| Competitor | Problem |
|
||||
| ------------------ | -------------------------------------------------------------------- |
|
||||
| V8 CGO bindings | Requires CGO, ~50MB static libraries, platform-specific builds |
|
||||
| QuickJS CGO | Requires CGO, smaller than V8 but still a C dependency |
|
||||
| QJS (Wazero) | Pure Go WASM, but sandboxed -- can't expose Go functions efficiently |
|
||||
| Ramune | Heavy dependency, bundles an entire TypeScript 7 compiler |
|
||||
| Node.js subprocess | Process overhead per execution, IPC serialisation cost |
|
||||
|
||||
goja is a pure-Go ECMAScript 5.1+ interpreter at ~20k lines. It:
|
||||
|
||||
- Has **zero CGO** -- cross-compiles everywhere Go does
|
||||
- Passes nearly all TC39 Test262 tests for ES5.1 + significant ES6 coverage
|
||||
- Can run Babel and the TypeScript compiler itself (proven capability)
|
||||
- Provides direct Go↔JS interop via `Set()`/`Get()`/`Runtime.RunString()`
|
||||
- Has a companion `goja_nodejs` package for `require()`, `setTimeout`, and `console`
|
||||
- Is used in production by k6 (Grafana's load testing tool, 30k+ stars)
|
||||
|
||||
### How TypeScript becomes JavaScript
|
||||
|
||||
arcie-core bundles esbuild via `go:embed`. On plugin load, TypeScript source is transpiled to ES2017 JavaScript in-process:
|
||||
|
||||
```
|
||||
.archie/workflows/security-gate.ts → esbuild.Transform() → goja.Runtime.RunString()
|
||||
```
|
||||
|
||||
esbuild is pure Go, takes ~3ms for typical gate scripts, and strips type annotations without type-checking (the plugin author does that in their editor). If the transpilation fails, the plugin is skipped with a diagnostic comment on the issue.
|
||||
|
||||
---
|
||||
|
||||
## Design
|
||||
|
||||
### Plugin discovery
|
||||
|
||||
During the poll cycle, archie-core scans each repo's worktree for `.archie/workflows/*.ts`:
|
||||
|
||||
```
|
||||
.archie/workflows/
|
||||
├── custom-gate.ts # gate functions: exported `check()`
|
||||
├── db-migration.ts # custom stage: exported `stage()`
|
||||
└── notify-slack.ts # skill script: exported `run()`
|
||||
```
|
||||
|
||||
Each file is a self-contained module. No `package.json`, no `node_modules`, no external imports. If you need external deps, they need to be exposed via archie-core's Go→JS bridge.
|
||||
|
||||
### Plugin types
|
||||
|
||||
A plugin declares its role via an exported symbol:
|
||||
|
||||
| Export | Role | When called |
|
||||
| ---------------------------------------------------- | -------------- | --------------------------------------------- |
|
||||
| `export function check(ctx: GateContext): Finding[]` | Gate function | After shell-based gate, before commit |
|
||||
| `export function stage(): Stage` | Workflow stage | When a workflow references the stage name |
|
||||
| `export function run(ctx: ScriptContext): void` | Skill script | When a skill's instructions invoke the script |
|
||||
|
||||
arcie-core discovers the role by checking which exports exist. A file can export multiple roles.
|
||||
|
||||
### Gate functions
|
||||
|
||||
```typescript
|
||||
// .archie/workflows/custom-gate.ts
|
||||
|
||||
interface GateContext {
|
||||
diff: string; // unified diff of changes
|
||||
changedFiles: string[]; // list of changed file paths
|
||||
dir: string; // absolute worktree path
|
||||
repo: string; // "owner/name"
|
||||
baseRef: string; // "origin/main"
|
||||
}
|
||||
|
||||
interface Finding {
|
||||
level: "error" | "warn";
|
||||
file?: string;
|
||||
line?: number;
|
||||
message: string;
|
||||
}
|
||||
|
||||
interface Block {
|
||||
name: string;
|
||||
message: string;
|
||||
}
|
||||
|
||||
export function check(ctx: GateContext): Finding[] {
|
||||
const findings: Finding[] = [];
|
||||
|
||||
// Rule: no new panic() calls
|
||||
for (const line of ctx.diff.split("\n")) {
|
||||
if (line.startsWith("+") && !line.startsWith("+++")) {
|
||||
if (line.includes("panic(")) {
|
||||
findings.push({
|
||||
level: "error",
|
||||
message: "new panic() call -- use error returns instead",
|
||||
});
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Rule: no time.Sleep in non-test files
|
||||
for (const file of ctx.changedFiles) {
|
||||
if (file.endsWith("_test.go")) continue;
|
||||
const content = archie.readFile(`${ctx.dir}/${file}`);
|
||||
if (content.includes("time.Sleep")) {
|
||||
findings.push({
|
||||
level: "warn",
|
||||
file: file,
|
||||
message: "time.Sleep in non-test code -- use time.Ticker instead",
|
||||
});
|
||||
}
|
||||
}
|
||||
|
||||
return findings;
|
||||
}
|
||||
```
|
||||
|
||||
After transpilation and execution, archie-core calls `check(ctx)` via goja. Error-level findings park the task. Warn-level findings are logged.
|
||||
|
||||
### Custom workflow stages
|
||||
|
||||
```typescript
|
||||
// .archie/workflows/run-migrations.ts
|
||||
|
||||
export function stage(): Stage {
|
||||
return {
|
||||
name: "db-migration",
|
||||
run: (ctx: TaskContext): string | null => {
|
||||
// Check if migrations directory exists
|
||||
const hasMigrations = archie.fileExists(`${ctx.dir}/migrations`);
|
||||
if (!hasMigrations) return null; // nothing to do
|
||||
|
||||
// Run migration tests
|
||||
const result = archie.exec("go", ["test", "./migrations/..."]);
|
||||
if (result.exitCode !== 0) {
|
||||
return `migration tests failed: ${result.stderr}`;
|
||||
}
|
||||
return null; // success
|
||||
},
|
||||
};
|
||||
}
|
||||
```
|
||||
|
||||
### Skill scripts
|
||||
|
||||
```typescript
|
||||
// .archie/workflows/security-audit.ts
|
||||
|
||||
export function run(ctx: ScriptContext): void {
|
||||
const result = archie.exec("gitleaks", ["detect", "--no-git"]);
|
||||
if (result.exitCode !== 0) {
|
||||
archie.log("warn", `gitleaks found secrets:\n${result.stdout}`);
|
||||
}
|
||||
archie.log("info", "security audit complete");
|
||||
}
|
||||
```
|
||||
|
||||
### archie Go→JS bridge
|
||||
|
||||
arcie-core exposes a `archie` global in the goja runtime:
|
||||
|
||||
```typescript
|
||||
interface Archie {
|
||||
// File operations (scoped to worktree)
|
||||
readFile(path: string): string;
|
||||
fileExists(path: string): boolean;
|
||||
listDir(path: string): string[];
|
||||
walkDir(path: string): string[];
|
||||
|
||||
// Shell execution
|
||||
exec(command: string, args?: string[]): ExecResult;
|
||||
|
||||
// Logging
|
||||
log(level: string, message: string): void;
|
||||
|
||||
// Path utilities
|
||||
resolve(...parts: string[]): string;
|
||||
ext(path: string): string;
|
||||
|
||||
// Environment
|
||||
env(key: string): string;
|
||||
|
||||
// HTTP (optional, gated)
|
||||
fetch(url: string, options?: FetchOptions): FetchResult;
|
||||
}
|
||||
|
||||
interface ExecResult {
|
||||
stdout: string;
|
||||
stderr: string;
|
||||
exitCode: number;
|
||||
}
|
||||
```
|
||||
|
||||
All file operations are **jailed to the worktree**. `archie.readFile("/etc/passwd")` fails. The bridge enforces this in Go before passing the path to the OS.
|
||||
|
||||
### Reload cycle
|
||||
|
||||
Plugins are loaded fresh on every poll cycle -- archie-core already fresh-clones per task. No hot-reload complexity, no cache invalidation. The worktree is the source of truth.
|
||||
|
||||
For the rare case where a plugin errors at parse/transpile time, archie-core comments on the issue with the diagnostic and parks the task. The plugin author fixes the `.ts` file and requeues.
|
||||
|
||||
---
|
||||
|
||||
## Implementation
|
||||
|
||||
### Architecture
|
||||
|
||||
```
|
||||
internal/plugins/
|
||||
├── loader.go # scan .archie/workflows/, transpile, evaluate
|
||||
├── runtime.go # goja runtime pool management
|
||||
├── bridge.go # archie global (file I/O, exec, log, fetch)
|
||||
├── types.go # GateContext, Finding, Stage, TaskContext → JS types
|
||||
├── loader_test.go
|
||||
└── testdata/
|
||||
└── workflows/
|
||||
├── gate.ts # test gate plugin
|
||||
└── stage.ts # test stage plugin
|
||||
```
|
||||
|
||||
### goja runtime pool
|
||||
|
||||
Workflow stages and gates need a clean goja runtime per execution. Creating a new runtime per call is slow (~50ms for stdlib setup). A pool of pre-warmed runtimes solves this:
|
||||
|
||||
```go
|
||||
type Pool struct {
|
||||
warm chan *goja.Runtime
|
||||
}
|
||||
|
||||
func NewPool(size int) *Pool {
|
||||
p := &Pool{warm: make(chan *goja.Runtime, size)}
|
||||
for i := 0; i < size; i++ {
|
||||
rt := goja.New()
|
||||
installBridge(rt) // register the `archie` global
|
||||
installStdlib(rt) // console, setTimeout, etc.
|
||||
p.warm <- rt
|
||||
}
|
||||
return p
|
||||
}
|
||||
|
||||
func (p *Pool) Run(ctx context.Context, src string, globals map[string]any) (goja.Value, error) {
|
||||
rt := <-p.warm
|
||||
defer func() { p.warm <- rt }()
|
||||
// Set per-execution globals
|
||||
for k, v := range globals {
|
||||
rt.Set(k, v)
|
||||
}
|
||||
return rt.RunString(src)
|
||||
}
|
||||
```
|
||||
|
||||
### Transpile pipeline
|
||||
|
||||
```go
|
||||
func (l *Loader) transpile(filename string, ts []byte) (string, error) {
|
||||
result := l.esbuild.Transform(string(ts), api.TransformOptions{
|
||||
Loader: api.LoaderTS,
|
||||
Target: api.ES2017,
|
||||
Sourcefile: filename,
|
||||
})
|
||||
if len(result.Errors) > 0 {
|
||||
return "", fmt.Errorf("transpile %s: %v", filename, result.Errors)
|
||||
}
|
||||
return string(result.Code), nil
|
||||
}
|
||||
```
|
||||
|
||||
### load pipeline
|
||||
|
||||
```go
|
||||
func (l *Loader) LoadPlugins(worktreeDir string) ([]Plugin, error) {
|
||||
dir := filepath.Join(worktreeDir, ".archie", "workflows")
|
||||
entries, err := os.ReadDir(dir)
|
||||
if os.IsNotExist(err) {
|
||||
return nil, nil // no plugins -- not an error
|
||||
}
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
var plugins []Plugin
|
||||
for _, e := range entries {
|
||||
if !strings.HasSuffix(e.Name(), ".ts") {
|
||||
continue
|
||||
}
|
||||
path := filepath.Join(dir, e.Name())
|
||||
src, err := os.ReadFile(path)
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
js, err := l.transpile(e.Name(), src)
|
||||
if err != nil {
|
||||
l.log.Warn("plugin transpile failed", "file", e.Name(), "err", err)
|
||||
continue
|
||||
}
|
||||
rt := l.pool.Acquire()
|
||||
_, err = rt.RunString(js)
|
||||
l.pool.Release(rt)
|
||||
if err != nil {
|
||||
l.log.Warn("plugin eval failed", "file", e.Name(), "err", err)
|
||||
continue
|
||||
}
|
||||
plugins = append(plugins, discover(rt, e.Name())...)
|
||||
}
|
||||
return plugins, nil
|
||||
}
|
||||
```
|
||||
|
||||
### Export discovery
|
||||
|
||||
```go
|
||||
func discover(rt *goja.Runtime, filename string) []Plugin {
|
||||
var out []Plugin
|
||||
if check := rt.Get("check"); check != nil {
|
||||
out = append(out, Plugin{Kind: "gate", Name: filename, Func: check})
|
||||
}
|
||||
if stage := rt.Get("stage"); stage != nil {
|
||||
out = append(out, Plugin{Kind: "stage", Name: filename, Func: stage})
|
||||
}
|
||||
if run := rt.Get("run"); run != nil {
|
||||
out = append(out, Plugin{Kind: "script", Name: filename, Func: run})
|
||||
}
|
||||
return out
|
||||
}
|
||||
```
|
||||
|
||||
### Wiring into the daemon
|
||||
|
||||
In `daemon.process()`:
|
||||
|
||||
```go
|
||||
// After worktree prepare, before gate stage:
|
||||
plugins, err := d.Plugins.LoadPlugins(tc.Dir)
|
||||
if err != nil {
|
||||
d.Log.Warn("plugin load failed", "err", err)
|
||||
}
|
||||
tc.Plugins = plugins // available to all stages via TaskContext
|
||||
|
||||
// In the gate stage:
|
||||
if gatePlugin := tc.Plugins.Gate(); gatePlugin != nil {
|
||||
findings := callGatePlugin(gatePlugin, gateContext(tc))
|
||||
for _, f := range findings {
|
||||
if f.Level == "error" {
|
||||
// park the task
|
||||
}
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Limitations
|
||||
|
||||
### goja's ECMAScript coverage
|
||||
|
||||
goja natively supports ES5.1 with significant ES6 features. Modern syntax like `async/await`, `??`, `?.`, or `class` fields may not parse. The transpile step (esbuild targeting ES2017) handles most of this, but there will be edge cases:
|
||||
|
||||
| Feature | Status |
|
||||
| ----------------- | -------------------------------------- |
|
||||
| Arrow functions | ✅ via transpile |
|
||||
| Template literals | ✅ via transpile |
|
||||
| Destructuring | ✅ via transpile |
|
||||
| `const`/`let` | ✅ via transpile |
|
||||
| `async/await` | ❌ not supported (goja is synchronous) |
|
||||
| `Promise` | ❌ requires `goja_nodejs` event loop |
|
||||
| Generators | ❌ not supported |
|
||||
| `Proxy` | ❌ not supported |
|
||||
|
||||
For gate scripts, this is fine -- gates are synchronous by nature. If async is genuinely needed later, the Bun backend (via `tsgo`) is the escape hatch.
|
||||
|
||||
### Performance
|
||||
|
||||
Gate scripts run once per task. Even a 100ms transpile+eval overhead is negligible compared to the LLM calls in the workflow. If a plugin becomes hot-path, it should be promoted to a compiled Go stage.
|
||||
|
||||
### No external imports
|
||||
|
||||
Plugins can't `import` from npm or other files. They're self-contained modules. Complexity that needs external deps should be a compiled Go stage, not a plugin. The `archie` global provides filesystem and shell access, which covers the common cases.
|
||||
|
||||
---
|
||||
|
||||
## Comparison: Yaegi vs goja
|
||||
|
||||
| | Yaegi (Go) | goja + esbuild (TypeScript) |
|
||||
| -------------------- | ----------------------------------------------------------- | --------------------------------------------------------- |
|
||||
| **Language** | Go | TypeScript |
|
||||
| **Pure Go** | ✅ | ✅ (goja + esbuild both pure Go) |
|
||||
| **CGO** | None | None |
|
||||
| **Transpile step** | None (interpreted directly) | esbuild TS→JS (~3ms) |
|
||||
| **Author audience** | Go developers | Anyone who knows TypeScript |
|
||||
| **Type annotations** | N/A (Go is typed) | Stripped by esbuild (no type-check at runtime) |
|
||||
| **Interop** | Direct Go↔Go via `Use()` | Bridge via `archie` global |
|
||||
| **Performance** | Interpreted Go (~10x slower than compiled) | Interpreted JS (~50x slower than V8, fine for gates) |
|
||||
| **Maturity** | 8k stars, used by Traefik for plugins | 7k stars, used by k6, goja is battle-tested |
|
||||
| **File extension** | `.go` | `.ts` |
|
||||
| **Plugin folder** | `.archie/workflows/` | `.archie/workflows/` |
|
||||
| **Best for** | Custom stages needing Go's stdlib, tight daemon integration | Custom gates and scripts where author familiarity matters |
|
||||
|
||||
**Recommendation: support both.** They solve different problems. Yaegi for repo owners who want full Go power in their custom stages. goja for repo owners who want to write gates and scripts in TypeScript. Both load from `.archie/workflows/` -- archie-core discovers which engine to use by file extension (`.go` → Yaegi, `.ts` → goja+esbuild).
|
||||
|
||||
---
|
||||
|
||||
## Implementation phases
|
||||
|
||||
### Phase 1: goja runtime + esbuild
|
||||
|
||||
- Add `github.com/dop251/goja` and `github.com/evanw/esbuild` as dependencies
|
||||
- Build `internal/plugins/` with loader, runtime pool, bridge
|
||||
- Wire gate plugin discovery into the implement and TDD workflows
|
||||
- Gate plugins run after shell-based gate, before commit
|
||||
|
||||
### Phase 2: Custom stages
|
||||
|
||||
- Stage plugins discovered and registered alongside built-in stages
|
||||
- `config.toml` can reference plugin stages by name
|
||||
- TaskContext exposed to JS plugins
|
||||
|
||||
### Phase 3: Skill scripts
|
||||
|
||||
- Skill SKILL.md can reference `scripts/security-audit.ts`
|
||||
- archie-core loads, transpiles, and evaluates when the skill activates
|
||||
- Script stdout captured and returned to the agent as tool output
|
||||
|
||||
### Phase 4: Yaegi side-by-side
|
||||
|
||||
- Go plugin files (`.go`) loaded via Yaegi from the same `.archie/workflows/` directory
|
||||
- Same discovery pattern, different interpreter
|
||||
- archie-core chooses engine by file extension
|
||||
|
||||
---
|
||||
|
||||
## Open questions
|
||||
|
||||
1. **Jailing:** How strict should the `archie` bridge be? File I/O jailed to worktree, no network access by default? Or trust the repo author?
|
||||
2. **Error UX:** When a plugin fails to transpile, should archie-core comment on the issue with the specific error, or just park silently?
|
||||
3. **Runtime pool sizing:** 4 warmed runtimes? Dynamic?
|
||||
4. **Plugin versioning:** Do plugins get a `version` export? Or is the git commit the version?
|
||||
5. **TypeScript type definitions:** Ship a `.d.ts` file for the `archie` global so plugin authors get IntelliSense?
|
||||
@@ -1,337 +0,0 @@
|
||||
# archie-core Yaegi Plugin System -- PRD
|
||||
|
||||
**Author:** Archie
|
||||
**Date:** 2026-07-21
|
||||
**Status:** Draft
|
||||
|
||||
---
|
||||
|
||||
## Summary
|
||||
|
||||
Embed the [Yaegi](https://github.com/traefik/yaegi) Go interpreter to let
|
||||
archie-core load and execute `.go` files at runtime. This enables three things
|
||||
that shell commands can't do: **custom gates with deep worktree inspection**,
|
||||
**custom workflow stages defined per-repo**, and **skill scripts written in Go
|
||||
instead of shell**.
|
||||
|
||||
---
|
||||
|
||||
## Why Yaegi
|
||||
|
||||
### The problem with shell-only gates
|
||||
|
||||
`[[repos.gate]]` is command lists. That's fine for standard tooling (`go vet`,
|
||||
`golangci-lint`), but it can't express project-specific rules:
|
||||
|
||||
- "No new `panic()` calls in the diff"
|
||||
- "No new dependencies in `go.mod` without justification"
|
||||
- "All public functions in `pkg/api/` must be documented"
|
||||
- "No `time.Sleep` in production code paths"
|
||||
|
||||
These are rules that need to read the diff, parse Go ASTs, or walk the worktree
|
||||
-- things shell scripts can do but shouldn't have to.
|
||||
|
||||
### Why not shell scripts?
|
||||
|
||||
Shell scripts for gates are fine until they're not. They can't import the
|
||||
archie-core types, can't use the Go parser, and are a second language to
|
||||
maintain alongside the daemon. Yaegi runs Go -- the same language as the daemon,
|
||||
the same language as the repos archie-core works on.
|
||||
|
||||
### Why not Go's native `plugin` package?
|
||||
|
||||
Go's `plugin` package (`.so` files) requires:
|
||||
|
||||
- Exact same Go version and deps as the host binary
|
||||
- Linux/macOS only
|
||||
- No unload
|
||||
- Painful distribution
|
||||
|
||||
Yaegi interprets `.go` source files directly -- no compilation step, portable
|
||||
everywhere, loads from filesystem paths.
|
||||
|
||||
### Production precedent
|
||||
|
||||
- **Traefik:** 200+ community plugins via Yaegi, loaded from plugins.traefik.io
|
||||
- **Vikunja:** Adopted Yaegi for plugin system (see PR #2178), loads plugins
|
||||
from `plugins/` directory
|
||||
|
||||
---
|
||||
|
||||
## Design
|
||||
|
||||
### Three extension surfaces
|
||||
|
||||
| Surface | Location | When loaded | What it does |
|
||||
| -------------------------- | ------------------------------------- | -------------------------------------------- | --------------------------------------------------------------------- |
|
||||
| **Custom gate functions** | `.archie/gate.go` | During the gate stage (after shell commands) | Returns `[]Finding` -- each finding has severity, message, file, line |
|
||||
| **Custom workflow stages** | `.archie/stages/<name>.go` | When the workflow references the stage name | Returns a `workflow.Stage` implementation |
|
||||
| **Skill scripts** | `.archie/skills/<skill>/scripts/*.go` | When the parent skill is activated | Called by the skill's instructions |
|
||||
|
||||
### Gate functions (`.archie/gate.go`)
|
||||
|
||||
The most important extension surface. After the shell-based gate passes,
|
||||
archie-core loads and evaluates `.archie/gate.go` in the worktree directory. The
|
||||
script exposes a `Check` function:
|
||||
|
||||
```go
|
||||
// .archie/gate.go -- per-repo gate rules interpreted at runtime
|
||||
package gate
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
)
|
||||
|
||||
// GateContext carries everything the gate checker can inspect.
|
||||
type GateContext struct {
|
||||
Diff string // unified diff of all changes
|
||||
ChangedFiles []string // list of changed file paths (repo-relative)
|
||||
Dir string // absolute worktree path
|
||||
BaseRef string // base branch (e.g. "origin/main")
|
||||
Repo string // "owner/name"
|
||||
}
|
||||
|
||||
// Finding is one gate violation.
|
||||
type Finding struct {
|
||||
Level string // "error" (blocks commit) or "warn" (advisory)
|
||||
File string // optional file path
|
||||
Line int // optional line number
|
||||
Message string
|
||||
}
|
||||
|
||||
// Block defines a named rule that can prevent passing.
|
||||
type Block struct {
|
||||
Name string
|
||||
Message string
|
||||
}
|
||||
|
||||
// Check returns findings for the gate. Return nil for a clean gate.
|
||||
func Check(ctx GateContext) []Finding {
|
||||
var findings []Finding
|
||||
|
||||
// Rule: no new panic() calls in committed code
|
||||
for _, line := range strings.Split(ctx.Diff, "\n") {
|
||||
if strings.HasPrefix(line, "+") && !strings.HasPrefix(line, "+++") {
|
||||
if strings.Contains(line, "panic(") {
|
||||
findings = append(findings, Finding{
|
||||
Level: "error",
|
||||
Message: "new panic() call -- use error returns instead",
|
||||
})
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// Rule: no time.Sleep in non-test files
|
||||
for _, f := range ctx.ChangedFiles {
|
||||
if strings.HasSuffix(f, "_test.go") {
|
||||
continue
|
||||
}
|
||||
path := filepath.Join(ctx.Dir, f)
|
||||
b, err := os.ReadFile(path)
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
if strings.Contains(string(b), "time.Sleep") {
|
||||
findings = append(findings, Finding{
|
||||
Level: "warn",
|
||||
File: f,
|
||||
Message: "time.Sleep in non-test code -- use time.Ticker or context.WithTimeout instead",
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
return findings
|
||||
}
|
||||
```
|
||||
|
||||
The daemon:
|
||||
|
||||
1. Reads `.archie/gate.go` from the worktree
|
||||
2. Creates a Yaegi interpreter with `GateContext` and `Finding` types pre-loaded
|
||||
via `Use()`
|
||||
3. Evaluates the file
|
||||
4. Calls `Check(ctx)` via `Eval("gate.Check")` + `Interface()`
|
||||
5. Logs findings and blocks the gate if any have `Level: "error"`
|
||||
|
||||
### Custom workflow stages (`.archie/stages/`)
|
||||
|
||||
A repo can define custom pipeline stages that archie-core discovers and makes
|
||||
routable:
|
||||
|
||||
```go
|
||||
// .archie/stages/run-migrations.go
|
||||
package stages
|
||||
|
||||
import "github.com/samcharles93/archie-core/internal/workflow"
|
||||
|
||||
func Stage() workflow.Stage {
|
||||
return workflow.Stage{
|
||||
Name: "db-migration",
|
||||
Run: func(ctx context.Context, tc *workflow.TaskContext) error {
|
||||
// Check if go.mod contains migration tools
|
||||
// Run migration tests
|
||||
// Verify schema compatibility
|
||||
return nil
|
||||
},
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
Registered stages appear alongside built-in stages. A workflow in `config.toml`
|
||||
can reference them by name:
|
||||
|
||||
```toml
|
||||
[[workflows.stages]]
|
||||
name = "db-migration" # matches the .go file
|
||||
source = "repo" # loaded from .archie/stages/
|
||||
```
|
||||
|
||||
### Skill scripts (`.archie/skills/<skill>/scripts/`)
|
||||
|
||||
Skills can ship Go scripts that archie-core interprets:
|
||||
|
||||
```go
|
||||
// .archie/skills/security-audit/scripts/gitleaks.go
|
||||
package main
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"os/exec"
|
||||
"context"
|
||||
)
|
||||
|
||||
func main() {
|
||||
ctx := context.Background()
|
||||
cmd := exec.CommandContext(ctx, "gitleaks", "detect", "--no-git", "--verbose")
|
||||
out, _ := cmd.CombinedOutput()
|
||||
fmt.Println(string(out))
|
||||
}
|
||||
```
|
||||
|
||||
Skills reference these scripts naturally in their instructions: "Run
|
||||
`scripts/gitleaks.go` to scan for secrets."
|
||||
|
||||
---
|
||||
|
||||
## API surface archie-core exposes to Yaegi
|
||||
|
||||
Via `i.Use()`, the daemon pre-loads symbols that interpreted code can import:
|
||||
|
||||
| Package | What's exposed |
|
||||
| ------------------------------- | ----------------------------------------- |
|
||||
| `archie-core/internal/workflow` | `Stage`, `TaskContext`, `Outcome` |
|
||||
| `archie-core/internal/gate` | `GateContext`, `Finding`, `Block` |
|
||||
| `stdlib` | Full Go standard library (stdlib.Symbols) |
|
||||
|
||||
Generated with `yaegi extract` -- same approach Traefik and Vikunja use. A
|
||||
`//go:generate yaegi extract ...` line in the source triggers symbol table
|
||||
generation during `go generate`.
|
||||
|
||||
---
|
||||
|
||||
## Limitations
|
||||
|
||||
From Yaegi's own docs:
|
||||
|
||||
- **No assembly files** (`.s` not supported)
|
||||
- **No CGo** (can't call C code -- the daemon is pure Go, so this doesn't
|
||||
matter)
|
||||
- **No compiler/linker directives** (no `//go:embed`, etc. -- fine for gate
|
||||
scripts)
|
||||
- **Interfaces from pre-compiled code can't be added dynamically** -- the daemon
|
||||
must pre-compile wrapper types for any interface interpreted code needs to
|
||||
implement
|
||||
- **Slower than compiled code** -- gate scripts run once per commit, not in hot
|
||||
paths; negligible impact
|
||||
|
||||
The Vikunja PR documents a specific Yaegi quirk: **typed factory functions
|
||||
required.** You can't do `v.Interface().(MyInterface)` on a value returned from
|
||||
interpreted code. Each interface needs its own factory:
|
||||
|
||||
```go
|
||||
func NewGate() Gate { return &MyGate{} }
|
||||
func NewReportable() Reportable { return &MyGate{} }
|
||||
```
|
||||
|
||||
---
|
||||
|
||||
## Implementation phases
|
||||
|
||||
### Phase 1: Gate functions -- implemented
|
||||
|
||||
- `yaegi` added as a dependency
|
||||
- Symbol table for `GateContext`, `Finding` generated via `yaegi extract` into
|
||||
`internal/gate/gateextract` (a separate package from `internal/gate` itself,
|
||||
avoiding the self-import cycle extracting a package's own symbols creates)
|
||||
- `internal/gate/gateeval.Evaluate`: loads `.archie/gate.go` from the worktree,
|
||||
interprets it, calls `Check()`; panics are recovered
|
||||
- Wired in as `workflow.StageYaegiGate`, run after the final commit in both the
|
||||
`implement` and `tdd` workflows
|
||||
- Error findings park the task; warn findings are logged only
|
||||
|
||||
### Phase 2: Custom stages -- implemented
|
||||
|
||||
- Symbol table for `workflow.Stage`/`TaskContext`/`Outcome` generated into
|
||||
`internal/workflow/wfextract`
|
||||
- `internal/workflow/wfeval.Discover` scans `.archie/stages/*.go` in filename
|
||||
order and calls each file's exported `Stage()` function
|
||||
- `TaskContext.CustomStages` is an injected `func(dir string) ([]Stage, error)`
|
||||
-- the composition root (`cmd/archied`) wires it to `wfeval.Discover`, keeping
|
||||
`internal/workflow` decoupled from its own generated symbol table
|
||||
- `workflow.StageRepoStages` runs discovered stages in order right after the
|
||||
worktree is prepared, in both `implement` and `tdd`
|
||||
- Simplification vs. the original sketch: stages are auto-discovered and always
|
||||
run (like `.archie/gate.go`) rather than referenced by name from `config.toml`
|
||||
-- the workflow engine has no data-driven stage graph today, so wiring
|
||||
arbitrary named stages into arbitrary positions would need a larger
|
||||
config-driven rework. Auto-run-in-order covers the PRD's actual use case (a
|
||||
repo-defined pre-flight/setup hook) without it.
|
||||
|
||||
### Phase 3: Skill scripts -- implemented
|
||||
|
||||
- `internal/skillscript.Run` interprets a `.go` file via `i.EvalPath`, which
|
||||
(like `go run`) evaluates and calls its `main()`; stdout/stderr are captured
|
||||
via `interp.Options`
|
||||
- Uses `stdlib.Symbols` + `stdlib/unrestricted.Symbols` (not just `stdlib`) --
|
||||
`os/exec` lives in the unrestricted set, and the PRD's own example script
|
||||
shells out via `os/exec`
|
||||
- No archie-core-specific symbol table needed here -- skill scripts only touch
|
||||
the Go standard library
|
||||
- Exposed to the agent loop as a new `run_go_script` tool
|
||||
(`internal/agentexec/inprocess.go`), available in every agent stage; path is
|
||||
validated to stay inside the workspace
|
||||
- This is how "the skill's instructions reference a script" cashes out
|
||||
concretely: the agent calls `run_go_script` with the path instead of needing a
|
||||
Go toolchain in the sandbox
|
||||
|
||||
### Phase 4: Hot reload -- not needed, by construction
|
||||
|
||||
- All three loaders (`gate.Evaluate`, `wfeval.Discover`, `skillscript.Run`) read
|
||||
their `.go` source from disk on every call -- no in-memory cache exists
|
||||
anywhere in the implementation
|
||||
- Every task additionally gets a fresh `git clone` (`worktree.Manager.Prepare`
|
||||
removes and re-clones the worktree directory per task)
|
||||
- Consequently every stage already re-reads `.archie/gate.go`,
|
||||
`.archie/stages/*.go`, and skill scripts fresh, every run -- there is no stale
|
||||
state a file watcher would ever need to invalidate
|
||||
- A file-watching daemon-runtime reload mechanism would add machinery with
|
||||
nothing to do given this architecture; revisit only if the daemon starts
|
||||
reusing long-lived worktrees across tasks
|
||||
|
||||
---
|
||||
|
||||
## Open questions
|
||||
|
||||
1. **Symbol table generation:** Run `yaegi extract` as a `go generate` step, or
|
||||
generate on daemon startup?
|
||||
2. **Error handling:** If the interpreted gate panics or times out, park the
|
||||
task? Or fall back to shell-only gate?
|
||||
3. **Budget:** Interpreted gate scripts run in the gate stage -- should they
|
||||
have their own timeout/step budget?
|
||||
4. **Template system:** Should archie-core ship with common gate templates (e.g.
|
||||
`go: no panic, no Sleep, no hardcoded paths`)?
|
||||
5. **Remote gates:** Could `.archie/gate.go` be pulled from a shared remote
|
||||
registry, like skills?
|
||||
@@ -312,6 +312,11 @@
|
||||
"additionalProperties": false,
|
||||
"description": "MediaAttachment describes a file attached to a message.",
|
||||
"properties": {
|
||||
"data": {
|
||||
"contentEncoding": "base64",
|
||||
"description": "Data carries the attachment bytes in-process. An inbound path sets\nit after downloading the file; outbound senders never set it and\nread Path or URL instead. It never crosses a wire or persistence\nboundary -- it is a turn-scoped value, not a stored one.",
|
||||
"type": "string"
|
||||
},
|
||||
"duration": {
|
||||
"description": "Duration is the play time in seconds for audio and video.",
|
||||
"type": "integer"
|
||||
|
||||
@@ -10,13 +10,13 @@
|
||||
"url": "/dev/architecture/adversarial-review/",
|
||||
"title": "Adversarial self-review",
|
||||
"section": "Architecture",
|
||||
"body": "# Adversarial self-review\n\nArchie runs a fresh adversarial review of the diff before it opens a pull\nrequest, so a PR arrives with a findings record rather than an unreviewed\nclaim. The reviewer provably cannot see the implementer's context: it reviews a\n`.git`-free snapshot of the committed tree, not the worktree, the commit\nhistory, or the implementer's transcript.\n\nPromoted from `docs/prds/adversarial-self-review.md` (the design decision;\n`archie-core-h019`). Describes the stage as shipped.\n\n## Contract (`internal/domain/workflow`)\n\nThe workflow domain owns the contract and the blocking decision; it never names\nthe executor.\n\n- `Reviewer.Review(ctx, ReviewRequest) ReviewReport` — the interface the\n workflow stage consumes.\n- `ReviewRequest` is the reviewer's entire input: `SnapshotDir` (a `.git`-free\n export of the reviewed commit), `Diff` (base...head), `IssueText` (the\n originating issue title/body), and `MaxSteps`.\n- `ReviewFinding` / `ReviewReport` are the structured result. The load-bearing\n rule is `Blocking() == (Verdict == confirmed \u0026\u0026 Level == error)`: only a\n confirmed error-level finding blocks; a plausible finding never blocks\n however severe it claims to be.\n\n`ReviewReport` distinguishes `not_run`, `skipped`, and `completed` (zero\nfindings) structurally, so \"ran and found nothing\" is not the same as \"never\nran\" — collapsing them would make an outage indistinguishable from a clean\nreview.\n\n## Execution (`internal/app/agentworker`)\n\nThe executor is an ai-sdk `agent.Subagent`: a nested synchronous generation in\nthe same worker process, with its own model, system prompt, toolset and step\nbudget.\n\n- **Conversation isolation is structural.** `Subagent.Run` sends only a prompt\n string, never the implementer's message history.\n- **Workspace isolation is the `.git`-free snapshot.** The reviewer's toolset is\n read-only (`read`, `grep`, `find`) and rooted at `SnapshotDir` — never the\n worker's own toolset, which carries the `worktreerpc` publication grant.\n- **Findings return through a typed capture tool** (`record_finding`), validated\n on the way in, so the reviewer reports through the contract rather than free\n text the caller regexes.\n- **Fail-closed.** A reviewer that errors, truncates, or reaches no conclusion\n yields `ReviewStatusNotRun`, which the stage treats as a park — never a silent\n \"PR opened unreviewed\".\n\n## Lifecycle effect\n\n`StageReview` runs in the implement workflow after the deterministic gates and\nbefore `StageOpenPR`, gated by `repo.review_enabled` (opt-in, default off). A\nsurviving blocking finding — or a review that failed to run — parks the task\n(`StatusParked`, not `waiting_human`) with the findings rendered into the park\nreason; `StageOpenPR` never runs. Warn/plausible findings and the zero-finding\ncase leave the outcome unset, so the PR opens with a findings section rendered\nonto its body. `StagePostReviewComments` then runs after `StageOpenPR` and posts\nthe **line-anchored** findings as inline review comments, carrying a one-click\nsuggestion on a confirmed finding the reviewer could state a fix for. That stage\nis best-effort — a comment that fails to post is logged, never a park — because\nthe body section already lists every finding, and it is the record a whole-file\nfinding (no line to anchor to) only ever appears in.\n\n## Model and budget\n\nThe reviewer model is `models.reviewer`, falling back to `models.builder`.\nEffort is the per-stage `MaxSteps` budget, mapped onto `Subagent.MaxSteps`\n(default 10).\n\n## Operator-triggered review\n\nThe same reviewer runs against an _existing_ PR via the channel-neutral\n`review_pr` chat command: fetch the PR's head, snapshot it, run the isolated\nreviewer, and return the structured findings. Authorisation is identity-scoped\nto the operator's configured repositories; duplicate or concurrent reviews of\nthe same PR are deduplicated.\n"
|
||||
"body": "# Adversarial self-review\n\n\u003e **Removed, not shipped (2026-09-28, `d73e0748`). This page records a system\n\u003e that no longer exists in the tree.**\n\u003e\n\u003e `d73e0748` (\"remove the superseded adversarial-self-review system\") deleted the\n\u003e stage and its contract: `workflow.Reviewer`, `ReviewRequest`, `ReviewReport`\n\u003e and `StageReview` are gone from `internal/domain/workflow`, so everything under\n\u003e \"Contract\" below describes types that cannot be found.\n\u003e\n\u003e The authority is `docs/prds/pr-review-agent.md`, which says so itself: it\n\u003e \"supersedes the reviewer executor and blocking rule in\n\u003e `docs/architecture/adversarial-review.md`\". archied now runs its PR review\n\u003e pipeline before it opens a pull request; there is no separate adversarial\n\u003e self-review pass and no `repo.review_enabled` setting.\n\u003e\n\u003e The page is kept rather than deleted because PRDs link to it\n\u003e (`docs/prds/adversarial-self-review.md`, `docs/prds/inline-review.md`,\n\u003e `docs/prds/pr-review-agent.md`). Read it as history.\n\u003e\n\u003e One section is stale in a second, older way: \"Operator-triggered review\" below\n\u003e describes the synchronous `review_pr` (fetch the head, snapshot it, run the\n\u003e reviewer, return findings), which `archie-core-afbk.14` replaced with a queued\n\u003e pr-review task.\n\nArchie ran a fresh adversarial review of the diff before it opened a pull\nrequest, so a PR arrives with a findings record rather than an unreviewed\nclaim. The reviewer provably cannot see the implementer's context: it reviews a\n`.git`-free snapshot of the committed tree, not the worktree, the commit\nhistory, or the implementer's transcript.\n\nPromoted from `docs/prds/adversarial-self-review.md` (the design decision;\n`archie-core-h019`). Describes the stage as shipped.\n\n## Contract (`internal/domain/workflow`)\n\nThe workflow domain owns the contract and the blocking decision; it never names\nthe executor.\n\n- `Reviewer.Review(ctx, ReviewRequest) ReviewReport` — the interface the\n workflow stage consumes.\n- `ReviewRequest` is the reviewer's entire input: `SnapshotDir` (a `.git`-free\n export of the reviewed commit), `Diff` (base...head), `IssueText` (the\n originating issue title/body), and `MaxSteps`.\n- `ReviewFinding` / `ReviewReport` are the structured result. The load-bearing\n rule is `Blocking() == (Verdict == confirmed \u0026\u0026 Level == error)`: only a\n confirmed error-level finding blocks; a plausible finding never blocks\n however severe it claims to be.\n\n`ReviewReport` distinguishes `not_run`, `skipped`, and `completed` (zero\nfindings) structurally, so \"ran and found nothing\" is not the same as \"never\nran\" — collapsing them would make an outage indistinguishable from a clean\nreview.\n\n## Execution (`internal/app/agentworker`)\n\nThe executor is an ai-sdk `agent.Subagent`: a nested synchronous generation in\nthe same worker process, with its own model, system prompt, toolset and step\nbudget.\n\n- **Conversation isolation is structural.** `Subagent.Run` sends only a prompt\n string, never the implementer's message history.\n- **Workspace isolation is the `.git`-free snapshot.** The reviewer's toolset is\n read-only (`read`, `grep`, `find`) and rooted at `SnapshotDir` — never the\n worker's own toolset, which carries the `worktreerpc` publication grant.\n- **Findings return through a typed capture tool** (`record_finding`), validated\n on the way in, so the reviewer reports through the contract rather than free\n text the caller regexes.\n- **Fail-closed.** A reviewer that errors, truncates, or reaches no conclusion\n yields `ReviewStatusNotRun`, which the stage treats as a park — never a silent\n \"PR opened unreviewed\".\n\n## Lifecycle effect\n\n`StageReview` runs in the implement workflow after the deterministic gates and\nbefore `StageOpenPR`, gated by `repo.review_enabled` (opt-in, default off). A\nsurviving blocking finding — or a review that failed to run — parks the task\n(`StatusParked`, not `waiting_human`) with the findings rendered into the park\nreason; `StageOpenPR` never runs. Warn/plausible findings and the zero-finding\ncase leave the outcome unset, so the PR opens with a findings section rendered\nonto its body. `StagePostReviewComments` then runs after `StageOpenPR` and posts\nthe **line-anchored** findings as inline review comments, carrying a one-click\nsuggestion on a confirmed finding the reviewer could state a fix for. That stage\nis best-effort — a comment that fails to post is logged, never a park — because\nthe body section already lists every finding, and it is the record a whole-file\nfinding (no line to anchor to) only ever appears in.\n\n## Model and budget\n\nThe reviewer model is `models.reviewer`, falling back to `models.builder`.\nEffort is the per-stage `MaxSteps` budget, mapped onto `Subagent.MaxSteps`\n(default 10).\n\n## OperatorLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/architecture/agent-system/",
|
||||
"title": "Agent System",
|
||||
"section": "Architecture",
|
||||
"body": "# Agent System\n\n**Status:** Current-state investigation in progress \n**Date:** 2026-07-28 \n**Tracking issue:** [#73](https://github.com/samcharles93/archie-core/issues/73)\n\n## Domain framing\n\nThe domain is the Agent System.\n\n`Task` is not a core Agent System concept. Forge tasks, forge issues, Jira\nissues, email, Telegram messages, webhooks, and future external inputs are\nchannel-specific messages. Channels translate those messages into requests to\nthe Agent System; external issue or task models MUST NOT shape execution state.\n\nThe current `store.Task` is a persisted workflow execution. Treating that row as\na task-domain aggregate would incorrectly turn Archie into an agentic issue\nboard.\n\n## Canonical agent interaction model\n\nAn **Agent** is a persistent assistant selected for an interaction. It is not a\nmodel invocation and is not a WorkflowExecution.\n\nEach Agent has its own:\n\n- immutable acting `IdentityID` for ownership and audit;\n- durable memory and learned information about the user;\n- perspective, specialisation, instructions, and communication behaviour;\n- conversation history and channel bindings;\n- available tools, capabilities, and policy;\n- continuity across model or provider changes.\n\nThe underlying model is a replaceable runtime dependency. Changing a model,\nprovider, or model version MUST NOT create a new Agent, discard its memory, or\nchange ownership of its history.\n\nA user MAY create multiple Agents. Each Agent develops its own memory and view\nof the user from the interactions and responsibilities assigned to it. Memories\nMUST NOT be silently pooled merely because Agents belong to the same user or\napplication.\n\nAgent and Identity are separate aggregates. Every Agent references exactly one\nacting IdentityID, and no two Agents share an agent identity. User, system, and\nservice-account identities may exist without an Agent.\n\nAn action initiated through an Agent records the Agent's acting IdentityID and,\nwhen applicable, the initiating user's IdentityID. A future fully automated\nWorkflowExecution MAY use an explicitly selected service-account identity for a\nconcrete unattended use case; this is not the default execution identity.\n\n## Workflow execution identity\n\nA Workflow is owned by an IdentityID. By default, every WorkflowExecution acts\nas the Workflow owner's identity.\n\nFuture delegated execution MAY add an explicit `RunAsIdentityID` assignment to a\nWorkflow. This allows a Workflow owner to select another user or service-account\nidentity for execution without changing Workflow ownership. Until that\ncapability is deliberately introduced, owner identity and execution identity are\nthe same.\n\nWorkflowExecution audit records MUST preserve the Workflow owner, effective\nexecution identity, initiating user when one exists, and any explicit delegation\nthat selected a different run-as identity.\n\n## Memory scopes\n\nThe Agent System requires four distinct durable memory scopes:\n\n- **global shared memory**: information intentionally available across the\n Archie application;\n- **agent-wide memory**: general expertise, operating knowledge, and perspective\n owned by one Agent and safe for that Agent to use across users;\n- **user-wide memory**: information associated with one user and available to\n authorised Agents serving that user;\n- **Agent-user relationship memory**: private history and learned context from\n one particular Agent's relationship with one particular user.\n\nAgent-wide memory is private to its owning Agent by default. Another Agent MUST\nNOT read, inherit, search, or mutate it implicitly.\n\nAgent-user relationship memory is addressed by both AgentID and User IdentityID.\nNeither another Agent serving the same user nor another user speaking to the\nsame Agent may access it implicitly.\n\nArchie is a multi-user system even when initially deployed for one person.\nMultiple users, including family members, may interact with the same configured\nAgents. Per-user memory is therefore an isolation and personalisation boundary,\nnot merely an attribution tag on the primary user's records.\n\nAn Agent MUST resolve the initiating user before assembling memory context.\nMemory belonging to one user MUST NOT become visible to another user merely\nbecause both users interact with the same Agent.\n\nShared memory does not erase provenance. Every memory record retains its scope,\nauthor or acting identity, originating user when applicable, source, and\nrevision history. The rules for selecting a write scope, granting access\nto global and user-wide memory, and authorising explicit cross-scope sharing are\nsettled by [`docs/prds/memory-engine-unification.md`](/dev/prds/memory-engine-unification/)\nand recorded in [`migration-decisions.md`](/dev/architecture/migration-decisions/#5-memory-placement-and-storage)\nsection 5.\n\nAn Agent interaction may answer conversationally, use a tool or capability, read\norLine truncated
|
||||
"body": "# Agent System\n\n**Status:** Current-state investigation in progress \n**Date:** 2026-07-28 \n**Tracking issue:** [#73](https://github.com/samcharles93/archie-core/issues/73)\n\n## Domain framing\n\nThe domain is the Agent System.\n\n`Task` is not a core Agent System concept. Forge tasks, forge issues, Jira\nissues, email, Telegram messages, webhooks, and future external inputs are\nchannel-specific messages. Channels translate those messages into requests to\nthe Agent System; external issue or task models MUST NOT shape execution state.\n\nThe current `store.Task` is a persisted workflow execution. Treating that row as\na task-domain aggregate would incorrectly turn Archie into an agentic issue\nboard.\n\n## Canonical agent interaction model\n\nAn **Agent** is a persistent assistant selected for an interaction. It is not a\nmodel invocation and is not a WorkflowExecution.\n\nEach Agent has its own:\n\n- immutable acting `IdentityID` for ownership and audit;\n- durable memory and learned information about the user;\n- perspective, specialisation, instructions, and communication behaviour;\n- conversation history and channel bindings;\n- available tools, capabilities, and policy;\n- continuity across model or provider changes.\n\nThe underlying model is a replaceable runtime dependency. Changing a model,\nprovider, or model version MUST NOT create a new Agent, discard its memory, or\nchange ownership of its history.\n\nA user MAY create multiple Agents. Each Agent develops its own memory and view\nof the user from the interactions and responsibilities assigned to it. Memories\nMUST NOT be silently pooled merely because Agents belong to the same user or\napplication.\n\nAgent and Identity are separate aggregates. Every Agent references exactly one\nacting IdentityID, and no two Agents share an agent identity. User, system, and\nservice-account identities may exist without an Agent.\n\nAn action initiated through an Agent records the Agent's acting IdentityID and,\nwhen applicable, the initiating user's IdentityID. A future fully automated\nWorkflowExecution MAY use an explicitly selected service-account identity for a\nconcrete unattended use case; this is not the default execution identity.\n\n## Workflow execution identity\n\nA Workflow is owned by an IdentityID. By default, every WorkflowExecution acts\nas the Workflow owner's identity.\n\nFuture delegated execution MAY add an explicit `RunAsIdentityID` assignment to a\nWorkflow. This allows a Workflow owner to select another user or service-account\nidentity for execution without changing Workflow ownership. Until that\ncapability is deliberately introduced, owner identity and execution identity are\nthe same.\n\nWorkflowExecution audit records MUST preserve the Workflow owner, effective\nexecution identity, initiating user when one exists, and any explicit delegation\nthat selected a different run-as identity.\n\n## Memory scopes\n\nThe Agent System requires four distinct durable memory scopes:\n\n- **global shared memory**: information intentionally available across the\n Archie application;\n- **agent-wide memory**: general expertise, operating knowledge, and perspective\n owned by one Agent and safe for that Agent to use across users;\n- **user-wide memory**: information associated with one user and available to\n authorised Agents serving that user;\n- **Agent-user relationship memory**: private history and learned context from\n one particular Agent's relationship with one particular user.\n\nAgent-wide memory is private to its owning Agent by default. Another Agent MUST\nNOT read, inherit, search, or mutate it implicitly.\n\nAgent-user relationship memory is addressed by both AgentID and User IdentityID.\nNeither another Agent serving the same user nor another user speaking to the\nsame Agent may access it implicitly.\n\nArchie is a multi-user system even when initially deployed for one person.\nMultiple users, including family members, may interact with the same configured\nAgents. Per-user memory is therefore an isolation and personalisation boundary,\nnot merely an attribution tag on the primary user's records.\n\nAn Agent MUST resolve the initiating user before assembling memory context.\nMemory belonging to one user MUST NOT become visible to another user merely\nbecause both users interact with the same Agent.\n\nShared memory does not erase provenance. Every memory record retains its scope,\nauthor or acting identity, originating user when applicable, source, and\nrevision history. The rules for selecting a write scope, granting access\nto global and user-wide memory, and authorising explicit cross-scope sharing are\nsettled by [`docs/prds/memory-engine-unification.md`](/dev/prds/memory-engine-unification/)\nand recorded in [`migration-decisions.md`](/dev/architecture/migration-decisions/#5-memory-placement-and-storage)\nsection 5.\n\nAn Agent interaction may answer conversationally, use a tool or capability, read\norLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/architecture/bindings/",
|
||||
@@ -28,7 +28,7 @@
|
||||
"url": "/dev/architecture/configuration/",
|
||||
"title": "Configuration",
|
||||
"section": "Architecture",
|
||||
"body": "# Configuration\n\n**Status:** Approved; existing-type assignment is ongoing \n**Date:** 2026-07-28 \n**Tracking issue:** [#73](https://github.com/samcharles93/archie-core/issues/73)\n\n## Ownership\n\nConfiguration has two separate responsibilities:\n\n1. `internal/infrastructure/configuration` loads files, environment variables,\n secret references, overlays, and compatibility representations.\n2. Each domain and plugin owns the typed runtime settings required for its\n behaviour.\n\n`internal/app` translates external input into those settings, validates\ncross-capability combinations, and supplies each component only its own\nsettings.\n\nThe following are prohibited:\n\n- passing complete application configuration into a domain;\n- making a domain depend on TOML, YAML, environment-variable names, secret\n references, or a configuration library;\n- defining a central runtime configuration type imported across the system;\n- placing plugin options in an unrelated global configuration model.\n\n## Private input document\n\n`internal/infrastructure/configuration` MAY use a complete decoded document\nwhile discovering files, decoding sections, and applying overlays. It is an\ninput-boundary DTO only.\n\nThe document:\n\n- remains private to the configuration infrastructure;\n- is composed from separately defined feature sections;\n- is immediately translated by application composition;\n- is never returned as the application's runtime model;\n- is never passed through runtime components.\n\nExternal DTOs and domain runtime settings are separate types.\n\nPlugins supply external configuration definitions through a narrow extension\ncontract. The core loader MUST NOT gain a field or recognised filename for every\nplugin.\n\nInvalid configuration input MUST NOT replace active valid settings or terminate\nunaffected capabilities. Configuration changes use the candidate validation,\npromotion, audit, and recovery requirements in\n[safe-change-and-recovery.md](/dev/architecture/safe-change-and-recovery/).\n\n## Dissolution of `internal/config`\n\n`internal/config` has no target location. It MUST be dissolved and MUST NOT\nsurvive as a shared package, configuration domain, or renamed global model.\n\nIts loading behaviour moves to `internal/infrastructure/configuration`. Existing\ntypes and methods are reassigned by behaviour. Repository execution policy,\ndispatch policy, retry policy, ecosystem defaults, tool policy, memory settings,\nprovider settings, and channel settings move to their\nrespective owners.\n\n## Repository settings\n\nThe existing `config.Repo` MUST NOT move intact into a repository domain or\nshared settings package. A managed repository is an application association:\n\n- work intake owns which repository references an identity monitors;\n- task execution owns gates, preflight, test protection, ecosystem behaviour,\n and change limits;\n- task lifecycle owns retry behaviour;\n- scheduling owns concurrency policy;\n- workspace management owns base branch and persistent-storage requirements.\n\nApplication composition correlates these settings by repository reference. No\ndomain receives a universal repository profile.\n\n## Documentation\n\nGenerated configuration reference describes external sections and their owning\ncapabilities. It MUST NOT establish a global Go configuration structure as the\npublic contract.\n\n## Value classification rule\n\nEvery value that controls behaviour MUST have an explicit owner and MUST be\nclassified as exactly one of:\n\n1. **Invariant** — changing it changes the meaning of the program, a wire\n protocol, or a domain concept. It may be a Go constant.\n2. **Runtime setting** — an operator, identity, domain, plugin, or deployment\n may legitimately choose a different value. It is typed configuration owned by\n the affected capability.\n3. **Policy value** — it expresses what is allowed, limited, routed, retried,\n protected, or gated. Its typed definition belongs to the owning domain and it\n is evaluated through the policy system.\n4. **Derived value** — it is computed from other settings and is not\n independently mutable.\n5. **Runtime state** — it changes as the application operates, such as the\n active model for a conversation. It is changed by a domain command and is not\n configuration merely because it can be changed.\n\nAn unclassified behavioural literal is a defect.\n\n`const` MUST NOT be used merely because a value currently has one default.\nConstants are reserved for actual invariants: enum discriminants, protocol\nversions, fixed compatibility tokens, and values whose alteration would change\nthe program's semantics rather than configure an installation.\n\nIn Go, a constant is a compile-time value and does not represent mutable runtime\nstorage. It generally has no address that can be observed or changed.\nArchitecturally, a constant therefore asserts that the value cannot change for\nthe lifetiLine truncated
|
||||
"body": "# Configuration\n\n**Status:** Approved; existing-type assignment is ongoing \n**Date:** 2026-07-28 \n**Tracking issue:** [#73](https://github.com/samcharles93/archie-core/issues/73)\n\n## Ownership\n\nConfiguration has two separate responsibilities:\n\n1. `internal/infrastructure/configuration` loads files, environment variables,\n secret references, overlays, and compatibility representations.\n2. Each domain and plugin owns the typed runtime settings required for its\n behaviour.\n\n`internal/app` translates external input into those settings, validates\ncross-capability combinations, and supplies each component only its own\nsettings.\n\nThe following are prohibited:\n\n- passing complete application configuration into a domain;\n- making a domain depend on TOML, YAML, environment-variable names, secret\n references, or a configuration library;\n- defining a central runtime configuration type imported across the system;\n- placing plugin options in an unrelated global configuration model.\n\n## Private input document\n\n`internal/infrastructure/configuration` MAY use a complete decoded document\nwhile discovering files, decoding sections, and applying overlays. It is an\ninput-boundary DTO only.\n\nThe document:\n\n- remains private to the configuration infrastructure;\n- is composed from separately defined feature sections;\n- is immediately translated by application composition;\n- is never returned as the application's runtime model;\n- is never passed through runtime components.\n\nExternal DTOs and domain runtime settings are separate types.\n\nPlugins supply external configuration definitions through a narrow extension\ncontract. The core loader MUST NOT gain a field or recognised filename for every\nplugin.\n\nInvalid configuration input MUST NOT replace active valid settings or terminate\nunaffected capabilities. Configuration changes use the candidate validation,\npromotion, audit, and recovery requirements in\n[safe-change-and-recovery.md](/dev/architecture/safe-change-and-recovery/).\n\n## Dissolution of `internal/config`\n\n`internal/config` has no target location. It MUST be dissolved and MUST NOT\nsurvive as a shared package, configuration domain, or renamed global model.\n\nIts loading behaviour moves to `internal/infrastructure/configuration`. Existing\ntypes and methods are reassigned by behaviour. Repository execution policy,\ndispatch policy, retry policy, ecosystem defaults, tool policy, memory settings,\nprovider settings, and channel settings move to their\nrespective owners.\n\n## Repository settings\n\nThe existing `config.Repo` MUST NOT move intact into a repository domain or\nshared settings package. A managed repository is an application association:\n\n- work intake owns which repository references an identity monitors;\n- task execution owns gates, preflight, test protection, ecosystem behaviour,\n and change limits;\n- task lifecycle owns retry behaviour;\n- scheduling owns concurrency policy;\n- workspace management owns base branch and persistent-storage requirements.\n\nApplication composition correlates these settings by repository reference. No\ndomain receives a universal repository profile.\n\n## Documentation\n\nGenerated configuration reference describes external sections and their owning\ncapabilities. It MUST NOT establish a global Go configuration structure as the\npublic contract.\n\n## Value classification rule\n\nEvery value that controls behaviour MUST have an explicit owner and MUST be\nclassified as exactly one of:\n\n1. **Invariant** — changing it changes the meaning of the program, a wire\n protocol, or a domain concept. It may be a Go constant.\n2. **Runtime setting** — an operator, identity, domain, plugin, or deployment\n may legitimately choose a different value. It is typed configuration owned by\n the affected capability.\n3. **Policy value** — it expresses what is allowed, limited, routed, retried,\n protected, or gated. Its typed definition belongs to the owning domain and it\n is evaluated through the policy system.\n4. **Derived value** — it is computed from other settings and is not\n independently mutable.\n5. **Runtime state** — it changes as the application operates, such as the\n active model for a conversation. It is changed by a domain command and is not\n configuration merely because it can be changed.\n\nAn unclassified behavioural literal is a defect.\n\n`const` MUST NOT be used merely because a value currently has one default.\nConstants are reserved for actual invariants: enum discriminants, protocol\nversions, fixed compatibility tokens, and values whose alteration would change\nthe program's semantics rather than configure an installation.\n\nIn Go, a constant is a compile-time value and does not represent mutable runtime\nstorage. It generally has no address that can be observed or changed.\nArchitecturally, a constant therefore asserts that the value cannot change for\nthe lifetiLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/architecture/dashboard-agent-tools/",
|
||||
@@ -106,7 +106,7 @@
|
||||
"url": "/dev/development/",
|
||||
"title": "Development guides",
|
||||
"section": "Development",
|
||||
"body": "# Development guides\n\nChecklists for changing Archie, one page per area. Each names every place a\nchange must reach, so a feature that works in one layer does not silently stop\nat the next. A change that spans areas starts on the page for the area it\nbegins in, which points to the others. The pages point at the documents that\nown the design (`docs/architecture/`, the PRDs, `CLAUDE.md`) rather than\nrestating them.\n\n| Area | Covers |\n| ---------------------------------------------- | -------------------------------------------------------------------------------- |\n| [Frontend UI](/dev/development/frontend-ui/) | Anything under `ui/`, and the dashboard's API routes |\n| [Agent](/dev/development/agent/) | The agent container, its image, profiles, tools and workspace |\n| [Workflows](/dev/development/workflows/) | Workflow definitions and step types |\n| [Daemon](/dev/development/daemon/) | Task statuses, fields and the brief; sources, event types, mappings and bindings |\n| [State Store](/dev/development/state-store/) | Stored fields, tables, RPCs and errors |\n| [Control plane and settings](/dev/development/control-plane/) | Settings in `config.toml` or the dashboard |\n| [Processes and wiring](/dev/development/wiring/) | Where code goes, processes, plugin engines, channels, NATS subjects |\n| [Merging work](/dev/development/merging-work/) | Merging a lane or a branch |\n\n## Every change\n\n- Write the failing test first for anything with logic, branching or a\n contract, and check it fails on an assertion, not a compile error.\n- Test through the path production uses. A test that sets a value directly on\n the consumer proves nothing about the layers that normally deliver it.\n- Run `task check` and let its exit status decide the commit:\n `task check \u0026\u0026 git commit ...`. `task test` passes `-short`, which skips the\n process and Postgres tests, so run `go test -count=1 ./cmd/... ./internal/...`\n too when a change crosses a process or the database.\n- Regenerate, never hand-edit, generated output: `task proto:generate`,\n `go -C tools tool sqlc generate -f $PWD/internal/infrastructure/postgres/sqlc.yaml`,\n `task ui`, `task docs:artifact`. `task proto:check` compares against the git\n index, so stage regenerated contracts before running it.\n- Stage by path, or read `git status` before `git add -A`. Tests that start\n embedded NATS or write logs must use `t.TempDir()`; anything they leave in the\n tree gets committed. `task check` also adds linter-tool lines to `go.sum`\n (bead 1e37); restore `go.sum` before committing unless you changed a\n dependency.\n- A change to `docs/prds/`, `docs/architecture/` **or `docs/development/`**\n carries the regenerated `docs/data/generated/dev-docs.json`: run\n `task docs:artifact` (not `task docs:check`, which checks contracts only).\n PRD edits also follow `docs/prds/RULES.md` and pass `task docs:prds`.\n"
|
||||
"body": "# Development guides\n\nChecklists for changing Archie, one page per area. Each names every place a\nchange must reach, so a feature that works in one layer does not silently stop\nat the next. A change that spans areas starts on the page for the area it\nbegins in, which points to the others. The pages point at the documents that\nown the design (`docs/architecture/`, the PRDs, `CLAUDE.md`) rather than\nrestating them.\n\n| Area | Covers |\n| ---------------------------------------------- | -------------------------------------------------------------------------------- |\n| [Frontend UI](/dev/development/frontend-ui/) | Anything under `ui/`, and the dashboard's API routes |\n| [Agent](/dev/development/agent/) | The agent container, its image, profiles, tools and workspace |\n| [Workflows](/dev/development/workflows/) | Workflow definitions and step types |\n| [Daemon](/dev/development/daemon/) | Task statuses, fields and the brief; sources, event types, mappings and bindings |\n| [State Store](/dev/development/state-store/) | Stored fields, tables, RPCs and errors |\n| [Control plane and settings](/dev/development/control-plane/) | Settings in `config.toml` or the dashboard |\n| [Processes and wiring](/dev/development/wiring/) | Where code goes, processes, plugin engines, channels, NATS subjects |\n| [Merging work](/dev/development/merging-work/) | Merging a lane or a branch |\n\n## Every change\n\n- Write the failing test first for anything with logic, branching or a\n contract, and check it fails on an assertion, not a compile error.\n- Test through the path production uses. A test that sets a value directly on\n the consumer proves nothing about the layers that normally deliver it.\n- Run `task check` and let its exit status decide the commit:\n `task check \u0026\u0026 git commit ...`. `task test` passes `-short`, which skips the\n process and Postgres tests, so run `go test -count=1 ./cmd/... ./internal/...`\n too when a change crosses a process or the database.\n- Regenerate, never hand-edit, generated output: `task proto:generate`,\n `go -C tools tool sqlc generate -f $PWD/internal/infrastructure/postgres/sqlc.yaml`,\n `task ui`, `task docs:artifact`. `task proto:check` compares against the git\n index, so stage regenerated contracts before running it.\n- Stage by path, or read `git status` before `git add -A`. Tests that start\n embedded NATS or write logs must use `t.TempDir()`; anything they leave in the\n tree gets committed. `task check` writes no module file on a consistent tree,\n root or `tools/` (verified at HEAD with `GOFLAGS` unset and with `-mod=mod`):\n a stale `go.mod` or `go.sum` fails it, with `missing go.sum entry` or\n `updates to go.mod needed`, rather than being repaired. Only a global\n `GOFLAGS=-mod=mod` in `go env` re-enables that repair, which is why the\n `go -C tools` steps pass `-mod=readonly`; if `go.sum` goes dirty, run\n `go mod tidy` and commit the result on its own.\n- A change to `docs/prds/`, `docs/architecture/` **or `docs/development/`**\n carries the regenerated `docs/data/generated/dev-docs.json`: run\n `task docs:artifact` (not `task docs:check`, which checks contracts only).\n PRD edits also follow `docs/prds/RULES.md` and pass `task docs:prds`.\n"
|
||||
},
|
||||
{
|
||||
"url": "/dev/development/agent/",
|
||||
@@ -118,31 +118,31 @@
|
||||
"url": "/dev/development/control-plane/",
|
||||
"title": "Control plane and settings",
|
||||
"section": "Development",
|
||||
"body": "# Control plane and settings\n\nAuthority: `docs/architecture/configuration.md`. The wiring matrix, the\ndecoded-but-unwired ledger and the three shapes an unwired field takes are in\n`.agents/skills/archie-config-and-flags`.\n\nA field that parses is not a field that works. Before adding one, name the code\nthat reads it and the path the value takes to get there.\n\n## Decide what kind of setting it is\n\n- **Bootstrap-only** (read once at process start: `database_url`, `state_dir`,\n `work_dir`). It stays in the file, is checked by `validateBootstrap` in\n `internal/infrastructure/configuration/validate.go`, and the runtime overlay\n refuses changes to it.\n- **Database-owned** (repository policies, scheduling, tools, plugins,\n channels, containers). The file only seeds it. Once the State Store holds the\n control-plane resource, the stored document is layered over the file\n (`controlplane.Client.RuntimeConfig`) and the file key stops mattering. It is\n checked by `validateDatabaseOwned` and by the resource's validator.\n- **Worker-carried.** A value the agent container needs travels in\n `config.TaskConfig` (`Config.ForTask`) or on `taskrun.Request`. Never pass it\n as an environment variable the daemon did not already define, and never carry\n a secret this way.\n\n## Adding a database-owned field\n\n1. Add it to the struct the resource's `Document` names in\n `internal/app/controlplane/operational_settings.go`. The resource's JSON\n schema and the dashboard's Advanced settings editor are generated from that\n type, so no UI work is needed for the editor itself.\n2. Stored documents use Go field names as keys (`Image`, `MaxConcurrency`).\n Give the field no `json` tag unless its neighbours have one.\n3. A map or a nested struct needs its layering checked. `json.Unmarshal`\n merges into an existing map, so a stored map would add to the file's rather\n than replace it. A field the stored document omits keeps the file's value\n (a document stored before the field existed). Add a case to\n `internal/app/controlplane/runtime_config_test.go` for both.\n4. Validate it in one function both sides call, and add a case to\n `TestResourceValidatorsRejectWhatEffectiveValidationRejects` in\n `validators_agree_test.go`, so the file and the resource cannot disagree.\n5. Decide whether it reloads: it does only if every consumer re-reads it from\n `config.Holder`. The allowlist is `internal/app/archied/reload.go`; anything\n not on it requires a restart.\n6. If the settings page shows it as a plain field, add it to\n `internal/webui/config_schema.go` and the view in `api_config.go`.\n7. A generic catalog resource (`replace` command, not domain-managed, no\n query service) is watched **once per archie-ui process** by `webui.RunLive`,\n then published to every browser through `/api/stream`. Do not add an\n EventSource per resource to a settings store or a gRPC Watch per HTTP client.\n The control-plane server polls `Resource` every 250ms per upstream Watch;\n verify watch count is independent of client count and that late clients get\n the hub's current value (`internal/webui/live_hub_test.go`, real server over\n bufconn). Reopens resume after the last delivered version and charge failed\n attempts; accepting a gRPC stream does not establish its health.\n\n## Every new field\n\n- Test through the layering: build the effective config the way boot does,\n not by setting the field on the consumer.\n- Add a commented example to `config.example.toml`. Touch `deployments/*.toml`\n only when a profile there needs a value different from the default.\n- Update the wiring matrix in `.agents/skills/archie-config-and-flags`.\n- Secrets are `SecretRef`s resolved through the secret registry. Never inspect\n a resolved value, even in a test.\n- Reject a configuration that sets a field with no consumer rather than\n accepting and ignoring it (per-identity `forge.intake` is the precedent).\n"
|
||||
"body": "# Control plane and settings\n\nAuthority: `docs/architecture/configuration.md`. The wiring matrix, the\ndecoded-but-unwired ledger and the three shapes an unwired field takes are in\n`.agents/skills/archie-config-and-flags`.\n\nA field that parses is not a field that works. Before adding one, name the code\nthat reads it and the path the value takes to get there.\n\n## Decide what kind of setting it is\n\n- **Bootstrap-only** (read once at process start: `database_url`, `state_dir`,\n `work_dir`). It stays in the file, is checked by `validateBootstrap` in\n `internal/infrastructure/configuration/validate.go`, and the runtime overlay\n refuses changes to it.\n- **Database-owned** (repository policies, scheduling, tools, plugins,\n channels, containers). The file only seeds it. Once the State Store holds the\n control-plane resource, the stored document is layered over the file\n (`controlplane.Client.RuntimeConfig`) and the file key stops mattering. It is\n checked by `validateDatabaseOwned` and by the resource's validator. A stored\n value is refreshed from the file only when the store has no value for the kind\n at all; a kind that ships a document of its own (workflow definitions,\n personas) is refreshed whenever the seed itself wrote the stored copy, since\n that copy is a previous release's document rather than an operator's\n (`controlplane.Server.seedKind`).\n- **Worker-carried.** A value the agent container needs travels in\n `config.TaskConfig` (`Config.ForTask`) or on `taskrun.Request`. Never pass it\n as an environment variable the daemon did not already define, and never carry\n a secret this way.\n\n## Adding a database-owned field\n\n1. Add it to the wire-shape type the resource's `Document` names — a dedicated\n struct in `internal/app/controlplane/` with explicit snake_case json tags\n (`channel_settings.go`, `tool_settings.go`, `container_settings.go` are the\n precedents), never the internal config struct itself. A struct fed straight\n into the document falls back to Go field names (`Window`, `MaxRequests`),\n and a bare `time.Duration` marshals as nanoseconds — both render unusable\n in the Web UI. The resource's JSON schema and the dashboard's Advanced\n settings editor are generated from that type, so no UI work is needed for\n the editor itself.\n2. Map to and from the internal config type at the resource boundary (`Seed`,\n the layering in `runtime_config.go`, and the validator all use the same\n mapping). Durations in the document are a string-marshalling type\n (`config.Duration` or a document-local one), never a bare `time.Duration`.\n3. A document stored before the shape existed carries Go-cased keys. Read them\n with `controlplanerpc.DecodeRenamingLegacyKeys` (an `UnmarshalJSON` on the\n wire type) while keeping `DisallowUnknownFields` — dropping unknown keys\n would decode a misspelling as \"unset\" — and register a `Normalize` on the\n `Definition` that re-encodes the document, so a legacy document converges\n the next time it is written. A map or a nested struct needs its layering\n checked: a stored map replaces the file's, not merges into it, and a field\n the stored document omits keeps the file's value. Add a case to\n `internal/app/controlplane/runtime_config_test.go` for both.\n4. Validate it in one function both sides call, and add a case to\n `TestResourceValidatorsRejectWhatEffectiveValidationRejects` in\n `validators_agree_test.go`, so the file and the resource cannot disagree.\n5. Decide whether it reloads: it does only if every consumer re-reads it from\n `config.Holder`. The allowlist is `internal/app/archied/reload.go`; anything\n not on it requires a restart.\n6. If the settings page shows it as a plain field, add it to\n `internal/webui/config_schema.go` and the view in `api_config.go`.\n7. A generic catalog resource (`replace` command, not domain-managed, no\n query service) is watched **once per archie-ui process** by `webui.RunLive`,\n then published to every browser through `/api/stream`. Do not add an\n EventSource per resource to a settings store or a gRPC Watch per HTTP client.\n The control-plane server polls `Resource` every 250ms per upstream Watch;\n verify watch count is independent of client count and that late clients get\n the hub's current value (`internal/webui/live_hub_test.go`, real server over\n bufconn). Reopens resume after the last delivered version and charge failed\n attempts; accepting a gRPC stream does not establish its health.\n\n## Every new field\n\n- Test through the layering: build the effective config the way boot does,\n not by setting the field on the consumer.\n- Add a commented example to `config.example.toml`. Touch `deployments/*.toml`\n only when a profile there needs a value different from the default.\n- Update the wiring matrix in `.agents/skills/archie-config-and-flags`.\n- Secrets are `SecretRef`s resolved throLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/development/daemon/",
|
||||
"title": "Daemon",
|
||||
"section": "Development",
|
||||
"body": "# Daemon\n\nThe daemon claims and runs tasks, and turns captured events into tasks through\nbindings. This page covers both.\n\n## Task lifecycle\n\nAuthority: `docs/architecture/agent-system.md`. The status vocabulary lives in\n`internal/taskstate`, which imports no internal package.\n\n### Adding a status\n\n1. Add the constant to `internal/taskstate/taskstate.go` and place it in\n `Terminal`, `Actions` and `Statuses`. Its value is stored, so renaming it\n later is a migration.\n2. Alias it in `internal/domain/workflow/task/task.go` and\n `internal/domain/workflow/task_aliases.go`.\n3. Add it to the default catalogue in `ui/src/lib/task-meta.ts`. The server\n catalogue replaces the defaults when it loads, but the defaults render first.\n4. Find every hand-written status list in SQL:\n `grep -rn \"'merged'\" internal/infrastructure/postgres/queries`.\n `ClearTerminalTasks` must match `taskstate.Terminal`, which\n `TestClearTerminalTasksMatchesTaskstate` enforces. The stats queries count\n outcomes by name; decide whether the new status counts.\n5. Extend the table in `taskstate_test.go`.\n\n### Adding a task field\n\nFollow [State Store](/dev/development/state-store/) for the\ncolumn and the wire. Then decide who writes it: `UpdateTask` writes a fixed\ncolumn set, so a field set at enqueue needs its own statement (as\n`StampTaskBinding` does for binding provenance and inputs).\n\n### Changing what the agent receives\n\n- The task brief is `container.TaskPayload`, written to\n `\u003cworkspace\u003e/.git/task.json` by `WriteTaskJSON`. Never write it to the\n workspace root: the commit stage stages everything there.\n- The run request is `taskrun.Request`. `Validate` rejects a request that\n cannot run; a new requirement goes there.\n- Parking always carries a class (`taskstate.ParkTransient`,\n `ParkNeedsHuman`, `ParkTerminal`) chosen by the code that parks. Pick the one\n that says what an operator must do.\n- A task with no repository (`Task.HasRepository`) runs in a scratch workspace\n with no worktree grant. Code that assumes an owner and repo must check first.\n\n## Event automation\n\nAuthority: `docs/prds/event-automation.md` (the model: source, event type,\nmapping, binding, workflow, profile) and `docs/architecture/bindings.md`\n(threat model).\n\n### Where each check lives\n\nA binding is checked twice, and a new rule usually belongs in both places:\n\n- **On save**, in `checkedBinding` (`internal/webui/api_binding.go`), so the\n operator sees the problem while editing. It calls the domain checks\n `binding.Validate`, `binding.CompileFilter` and `Binding.CheckWorkflow`.\n- **At dispatch**, in `dispatchOneBinding` and `resolveBindingTarget`\n (`internal/daemon`), because the workflow or mapping may have changed since\n the save. A refusal is recorded with `recordDispatchFailure` and starts no\n task.\n\nPut the rule itself in `internal/domain/binding` or\n`internal/domain/workflow/task` and call it from both, rather than writing it\ntwice.\n\n### Adding a binding field\n\n1. Domain type and `Validate` in `internal/domain/binding`.\n2. Column, queries, store mapping, wire field, `newColumns`\n ([State Store](/dev/development/state-store/)).\n3. The request type and `checkedBinding` in `api_binding.go`.\n4. The draft, payload and editor in `ui/src/bindings/`\n ([Frontend UI](/dev/development/frontend-ui/)).\n5. Its effect at dispatch, with a case in\n `internal/daemon/dispatch_inputs_test.go` or `dispatch_bindings_test.go`.\n\n### Rules that must hold\n\n- Signing belongs to the source. Intake verifies the HMAC against the source's\n secret before the payload is parsed.\n- An event must be identified as an event type before anything dispatches it,\n and a binding applies only to its mapping's event type. Dispatch test\n fixtures therefore create an event type before inserting captures.\n- The dispatch ledger is claimed before the task is enqueued (at most once).\n- Anything an event supplies that selects what the agent acts on, such as a\n repository, must be checked against configuration. An event never widens\n what an agent can reach.\n"
|
||||
"body": "# Daemon\n\nThe daemon claims and runs tasks, and turns captured events into tasks through\nbindings. This page covers both.\n\n## Task lifecycle\n\nAuthority: `docs/architecture/agent-system.md`. The status vocabulary lives in\n`internal/taskstate`, which imports no internal package.\n\n### Adding a status\n\n1. Add the constant to `internal/taskstate/taskstate.go` and place it in\n `Terminal`, `Actions` and `Statuses`. Its value is stored, so renaming it\n later is a migration.\n2. Alias it in `internal/domain/workflow/task/task.go` and\n `internal/domain/workflow/task_aliases.go`.\n3. Add it to the default catalogue in `ui/src/lib/task-meta.ts`. The server\n catalogue replaces the defaults when it loads, but the defaults render first.\n4. Find every hand-written status list in SQL:\n `grep -rn \"'merged'\" internal/infrastructure/postgres/queries`.\n `ClearTerminalTasks` must match `taskstate.Terminal`, which\n `TestClearTerminalTasksMatchesTaskstate` enforces. The stats queries count\n outcomes by name; decide whether the new status counts.\n5. Extend the table in `taskstate_test.go`.\n\n### Adding a task field\n\nFollow [State Store](/dev/development/state-store/) for the\ncolumn and the wire. Then decide who writes it: `UpdateTask` writes a fixed\ncolumn set, so a field set at enqueue belongs in the insert that creates the\nrow (as `InsertChatTask` does for inputs), or in its own statement when only\nsome producers set it (as `StampTaskBinding` does for binding provenance).\n\n### Changing what the agent receives\n\n- The task brief is `container.TaskPayload`, written to\n `\u003cworkspace\u003e/.git/task.json` by `WriteTaskJSON`. Never write it to the\n workspace root: the commit stage stages everything there.\n- The run request is `taskrun.Request`. `Validate` rejects a request that\n cannot run; a new requirement goes there.\n- Parking always carries a class (`taskstate.ParkTransient`,\n `ParkNeedsHuman`, `ParkTerminal`) chosen by the code that parks. Pick the one\n that says what an operator must do.\n- A task with no repository (`Task.HasRepository`) runs in a scratch workspace\n with no worktree grant. Code that assumes an owner and repo must check first.\n\n## Event automation\n\nAuthority: `docs/prds/event-automation.md` (the model: source, event type,\nmapping, binding, workflow, profile) and `docs/architecture/bindings.md`\n(threat model).\n\n### Where each check lives\n\nA binding is checked twice, and a new rule usually belongs in both places:\n\n- **On save**, in `checkedBinding` (`internal/webui/api_binding.go`), so the\n operator sees the problem while editing. It calls the domain checks\n `binding.Validate`, `binding.CompileFilter` and `Binding.CheckWorkflow`.\n- **At dispatch**, in `dispatchOneBinding` and `resolveBindingTarget`\n (`internal/daemon`), because the workflow or mapping may have changed since\n the save. A refusal is recorded with `recordDispatchFailure` and starts no\n task.\n\nPut the rule itself in `internal/domain/binding` or\n`internal/domain/workflow/task` and call it from both, rather than writing it\ntwice.\n\n### Adding a binding field\n\n1. Domain type and `Validate` in `internal/domain/binding`.\n2. Column, queries, store mapping, wire field, `newColumns`\n ([State Store](/dev/development/state-store/)).\n3. The request type and `checkedBinding` in `api_binding.go`.\n4. The draft, payload and editor in `ui/src/bindings/`\n ([Frontend UI](/dev/development/frontend-ui/)).\n5. Its effect at dispatch, with a case in\n `internal/daemon/dispatch_inputs_test.go` or `dispatch_bindings_test.go`.\n\n### Rules that must hold\n\n- Signing belongs to the source. Intake verifies the HMAC against the source's\n secret before the payload is parsed.\n- An event must be identified as an event type before anything dispatches it,\n and a binding applies only to its mapping's event type. Dispatch test\n fixtures therefore create an event type before inserting captures.\n- The dispatch ledger is claimed before the task is enqueued (at most once).\n- Anything an event supplies that selects what the agent acts on, such as a\n repository, must be checked against configuration. An event never widens\n what an agent can reach.\n"
|
||||
},
|
||||
{
|
||||
"url": "/dev/development/frontend-ui/",
|
||||
"title": "Frontend UI",
|
||||
"section": "Development",
|
||||
"body": "# Frontend UI\n\nAuthority: `.agents/skills/archie-web-ui` (stack facts, design-system rules,\ntone and accessibility). This page covers what a change must reach, not how it\nshould look.\n\n## Adding or changing a feature\n\n1. The feature lives in `ui/src/\u003cfeature\u003e/`. Move a helper to `ui/src/base/`\n only when a second feature needs it.\n2. Keep wire shapes, draft state and payload building in a plain `.ts` module\n beside the components (`ui/src/bindings/binding-draft.ts` is the pattern),\n and test it in `ui/test/*.test.ts`. Components stay thin.\n3. Every mutation goes through `api.*` in `ui/src/lib/api`, which sends the\n CSRF and Content-Type headers the server's mutation guard requires. A bare\n `fetch` is refused.\n4. A value the server also describes (task statuses, actions, workflow inputs)\n comes from the server. Keep a local default only so the first render works,\n and keep it in step (`ui/src/lib/task-meta.ts`).\n5. Run `task ui`, `task test:ui` and `cd ui \u0026\u0026 npm run typecheck`. Commit the\n regenerated `ui/dist/`; the Go binaries embed it. A fresh git worktree has\n no ignored `ui/node_modules`: run `cd ui \u0026\u0026 npm ci` before these commands.\n6. **One long-lived browser connection:** `ui/src/lib/api.ts` has the only\n `new EventSource`, owned by `stores/live-updates.ts`. Feature stores consume\n topics with `live.subscribe(topic, callback)`; do not open a page-owned SSE\n stream. Logs alone opt in while mounted, replacing that same EventSource\n with `?topics=logs\u0026since=\u003clast cursor\u003e`; a browser's `Last-Event-ID` only\n survives its own automatic reconnect, not a newly constructed EventSource.\n Task and log topics resume by cursor; control-plane, identity and apply-status\n topics replay the latest snapshot. Test a fetch and same-origin navigation\n after visiting Settings and Logs: the UI process serves HTTP/1.1 and six\n persistent streams can starve every later browser request.\n\n## Adding an API route\n\n1. The handler goes in the `internal/webui/api_\u003cconcern\u003e.go` file for its\n concern. Check the request fully on the server; the UI's checks are only a\n convenience.\n2. A mutation calls `authorizeTaskMutation` first.\n3. A route whose store is not configured answers 503, and\n `internal/app/archieui/degraded_routes_test.go` pins what each route\n returns without its contract. Add the route there.\n4. The dashboard runs in its own process (`archie-ui`) and must not link the\n daemon or the workflow engine (`cmd/archie-ui/architecture_test.go`). Reach\n stored data through `storecontract` interfaces wired in\n `internal/app/archieui/compose.go`.\n5. Settings that live in a control-plane resource need no new route: the\n Advanced settings page edits every resource from its generated schema.\n6. For a new live topic, add one process-wide producer to `internal/webui`'s\n `RunLive` and fan it through the `/api/stream` hub; `internal/app/archieui/run.go`\n starts the producers with the process context. Never create an upstream\n watch or poller in an HTTP handler. A slow client must reconnect for cursor\n and snapshot repair rather than silently lose an update. Prove the producer\n with several browser clients against the real peer, not just a scripted\n stream; `live_hub_test.go` is the example.\n"
|
||||
"body": "# Frontend UI\n\nAuthority: `.agents/skills/archie-web-ui` (stack facts, design-system rules,\ntone and accessibility). This page covers what a change must reach, not how it\nshould look.\n\n## Adding or changing a feature\n\n1. The feature lives in `ui/src/\u003cfeature\u003e/`. Move a helper to `ui/src/base/`\n only when a second feature needs it.\n2. Keep wire shapes, draft state and payload building in a plain `.ts` module\n beside the components (`ui/src/bindings/binding-draft.ts` is the pattern),\n and test it in `ui/test/*.test.ts`. Components stay thin.\n3. Every mutation goes through `api.*` in `ui/src/lib/api`, which sends the\n CSRF and Content-Type headers the server's mutation guard requires. A bare\n `fetch` is refused.\n4. A value the server also describes (task statuses, actions, workflow inputs)\n comes from the server. Keep a local default only so the first render works,\n and keep it in step (`ui/src/lib/task-meta.ts`).\n5. Run `task ui`, `task test:ui` and `cd ui \u0026\u0026 npm run typecheck`. Commit the\n regenerated `ui/dist/`; the Go binaries embed it. A fresh git worktree has\n no ignored `ui/node_modules`: run `cd ui \u0026\u0026 npm ci` before these commands.\n6. **One long-lived browser connection:** `ui/src/lib/api.ts` has the only\n `new EventSource`, owned by `stores/live-updates.ts`. Feature stores consume\n topics with `live.subscribe(topic, callback)`; do not open a page-owned SSE\n stream. Logs alone opt in while mounted, replacing that same EventSource\n with `?topics=logs\u0026since=\u003clast cursor\u003e`; a browser's `Last-Event-ID` only\n survives its own automatic reconnect, not a newly constructed EventSource.\n Task and log topics resume by cursor; control-plane, identity and apply-status\n topics replay the latest snapshot. Test a fetch and same-origin navigation\n after visiting Settings and Logs: the UI process serves HTTP/1.1 and six\n persistent streams can starve every later browser request.\n\n## Testing the dashboard\n\nAuthority: the runner itself is `ui/package.json`'s `test` script: `node --test\n--experimental-strip-types test/*.test.ts` over `ui/test/*.test.ts`. It runs\npure TypeScript modules with `node`'s type stripping — no SFC loader, no DOM,\nno second dependency beyond what the app already carries. That is the standard,\nand a decision record for when it is deliberately not enough:\n\n- **Test archie's logic in a module; leave SFC wiring alone.** Wire shapes,\n draft state, copy conditions, filters and payload building live in plain\n `.ts` files beside the components and are tested in `ui/test/`. Components\n stay thin, so there is normally nothing in an SFC that is archie logic.\n- **Installed primitives are upstream-tested, not re-tested here.**\n `reka-ui` (2.10.5 here) maintains colocated tests per component in its own\n repo (Vitest/jsdom + axe: Switch, TagsInput, NumberField, Select, the\n arrow-navigation composables). The npm package ships none of those files, so\n this coverage is inherited through the version bound, not the tarball —\n `grep -l test node_modules/reka-ui` finds nothing. Duplicating them as local\n mount tests would test a dependency.\n- **A `.vue` import cannot run under the module runner.** `node --test` fails\n such a module with `ERR_UNKNOWN_FILE_EXTENSION: .vue` and the runner has no\n built-in loader for SFCs. A file under `ui/test/` that imports a `.vue` is\n therefore a broken test, not a weak one.\n- **If a DOM mount harness is ever needed** (a page-level accessibility\n contract, cross-component interaction, focus behaviour): `happy-dom` +\n `@vue/test-utils` + `vitest` scoped to a separate DOM test glob, keeping the\n module runner for everything else. Measured on the ui tree (vitest 5.0.2,\n happy-dom 20.14.5, @vue/test-utils 2.5.1): they add 24 top-level\n `node_modules` entries and 27 MB on a 296 MB install, a working 2-test mount\n suite (role=radiogroup vs role=switch, aria-label, click activation against\n the real SFCs) runs in 1.2 s on top of the current 0.5 s module suite, and\n `vue-tsc` (7.4 s) dominates `task test:ui` either way. The single-runner\n alternative (absorbing the existing suite into vitest) was measured\n infeasible as-is: all 29 existing files import `node:test`, which vitest\n cannot collect (\"No test suite found in file\" for every one), so it would be\n a rewrite of the whole suite, and its runtime was not measured. Nothing in\n `ui/dist` or CI changes either way; happy-dom is pure JS, no browser binary.\n- **What the module standard does not verify:** whether a call site passes an\n `aria-label` or which `v-if` branch shows. Those live in SFC templates and\n are only visible with a mount. If a page's accessible-name wiring is the\n risk, say so in the page's task and reach for the harness decision above\n rather than quietly growing mount tests. Never suppress a lint rule or a\n test to keep Line truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/development/merging-work/",
|
||||
"title": "Merging work",
|
||||
"section": "Development",
|
||||
"body": "# Merging work\n\nParallel lanes (see `.agents/skills/archie-agent-fleet`) merge into an\nintegration branch before `main`. Each merge is a change in its own right and\npasses the same gate.\n\n## Resolving conflicts\n\n- **Generated files** (`*.pb.go`, `postgresdb/*.go`, `ui/dist/`,\n `docs/data/generated/*.json`): take either side, then regenerate. Never merge\n them by hand.\n- **One side deletes a file, the other edits it**: the deletion wins when the\n deleting lane replaced the thing the file served. Move the other side's\n change onto its replacement.\n- **One side changes how code is built (a new store, renamed packages), the\n other what it does**: take the behaviour side's version and reapply the\n mechanical change to it. That is usually cleaner than merging line by line.\n- **Error sentinels** are rows in `wireErrors`, not switch cases.\n\n## After resolving\n\n1. Search for leftovers of anything the other side removed: the old package\n path, the old type, and comments describing the old behaviour.\n2. Tests written against one side's semantics may pass there and fail after\n the merge. A test that used to pass on the old store may be asserting a rule\n the other side deliberately changed. Fix the test's setup to the merged\n rule; do not loosen the rule to the test.\n3. Run the full suite without `-short`, then `task check`, then commit. Check\n `git status` for files a test wrote into the tree before staging.\n"
|
||||
"body": "# Merging work\n\nParallel lanes (see `.agents/skills/archie-agent-fleet`) merge into an\nintegration branch before `main`. Each merge is a change in its own right and\npasses the same gate.\n\n## Resolving conflicts\n\n- **Generated files** (`*.pb.go`, `postgresdb/*.go`, `ui/dist/`,\n `docs/data/generated/*.json`): take either side, then regenerate. Never merge\n them by hand.\n- **One side deletes a file, the other edits it**: the deletion wins when the\n deleting lane replaced the thing the file served. Move the other side's\n change onto its replacement.\n- **One side changes how code is built (a new store, renamed packages), the\n other what it does**: take the behaviour side's version and reapply the\n mechanical change to it. That is usually cleaner than merging line by line.\n- **Error sentinels** are rows in `wireErrors`, not switch cases.\n\n## After resolving\n\n1. Search for leftovers of anything the other side removed: the old package\n path, the old type, and comments describing the old behaviour.\n2. Tests written against one side's semantics may pass there and fail after\n the merge. A test that used to pass on the old store may be asserting a rule\n the other side deliberately changed. Fix the test's setup to the merged\n rule; do not loosen the rule to the test.\n3. Run the full suite without `-short`, then `task check`, then commit. Check\n `git status` for files a test wrote into the tree before staging.\n4. **A merge can surface a bug neither lane's own tests exposed alone.** Two\n real cases from 2026-09-26: a test that dialled no NATS URL passed on a\n machine with an ambient dev server running and failed the moment it landed\n on a clean CI runner (start an ephemeral server per test, never rely on a\n default port resolving to something); and a cycle-detector that walked a\n Go map in range order reported the same cycle two different ways from run\n to run, invisible until enough fresh (uncached) runs hit the unlucky\n ordering. Both looked like \"the merge broke a passing test\" but were\n latent defects the merge only had the opportunity to expose. Fix the\n defect the failure is pointing at, not the assertion that caught it — see\n CLAUDE.md's test-quality bar before writing the replacement.\n5. `go test`'s cache reuses a package's last result when nothing in its\n dependency graph changed. A merge that touches one package can leave a\n sibling's flaky test silently cached \"pass\" locally while CI runs it\n fresh. `task check` passing on your machine is not proof a merge is\n clean — rerun anything nondeterminism-prone with `-count=1` before\n trusting it, and let CI's from-scratch run be the tiebreaker it is.\n"
|
||||
},
|
||||
{
|
||||
"url": "/dev/development/state-store/",
|
||||
"title": "State Store",
|
||||
"section": "Development",
|
||||
"body": "# State Store\n\nAuthority: `docs/prds/state-store-contract.md` and the State Store section of\n`CLAUDE.md`. All persistence is PostgreSQL behind the standalone State Store\nprocess; nothing else opens the database.\n\n## Adding a column\n\n1. Write the next migration in `internal/infrastructure/postgres/migrations/`\n (`00NN_name.sql`, goose Up and Down). Give the column a `NOT NULL DEFAULT`\n that is correct for existing rows.\n2. Update the queries in `internal/infrastructure/postgres/queries/` and\n regenerate with sqlc. A query that lists columns (`ListTaskSummaries`, the\n binding selects) does not pick the new one up; `SELECT *` queries do.\n3. Map it in the store (`taskFromRow`, `bindingValue` and friends). If the\n column holds encoded data, the package that owns the type owns the encoding\n (`task.EncodeInputs`), and the store and the wire both use it.\n4. Carry it over the wire (next section) if any process other than the State\n Store reads it.\n\n## Adding a field to a wire message\n\n1. Add it to `proto/state/v1/state.proto` with a new field number. Never reuse\n a number; retire one with `deprecated = true`.\n2. `task proto:generate`, then map it both ways in\n `internal/infrastructure/staterpc/values.go`.\n3. `TestTaskProtoCarriesEveryDomainField` fills every `task.Task` field and\n fails on one the mapping forgets. If it cannot fill the field's kind, extend\n it. Other messages have no such test, so add a round trip to\n `conformance_test.go`.\n\n## Adding an RPC or a store method\n\n1. Put the Go method on the narrow consumer interface in\n `internal/domain/storecontract` (keep each at eight methods or fewer) and add\n the matching RPC. A Go method without an RPC does not cross the process.\n2. Implement it in the Postgres store, in `staterpc.Client` (with its `var _`\n assertion) and in `staterpc.server`. A missing dependency answers\n `codes.Unavailable`, never a fabricated default.\n3. Wire the dependency in every composition that serves or consumes it:\n `stateStoreDeps` in `internal/app/archied/state_store.go`, the daemon's\n assertions in `bootstrap.go`, and `internal/app/archieui/compose.go` for the\n dashboard process.\n4. Task-scoped tokens may call only `Update`, `Transition` and `InsertEvent` on\n their own task (`staterpc.TaskGrants`). A new RPC is admin-only unless it is\n added there deliberately.\n5. Add it to `conformance_test.go`, which runs every surface over a real gRPC\n connection.\n\n## Adding an error sentinel\n\nAdd the sentinel to `storecontract`, a row to `wireErrors` in `values.go`, and\na case to `error_test.go`. The canonical message is part of the wire contract:\nchanging it breaks `errors.Is` on the client silently.\n"
|
||||
"body": "# State Store\n\nAuthority: `docs/prds/state-store-contract.md` and the State Store section of\n`CLAUDE.md`. All persistence is PostgreSQL behind the standalone State Store\nprocess; nothing else opens the database.\n\n## Adding a column\n\n1. Write the next migration in `internal/infrastructure/postgres/migrations/`\n (`00NN_name.sql`, goose Up and Down). Give the column a `NOT NULL DEFAULT`\n that is correct for existing rows.\n2. Update the queries in `internal/infrastructure/postgres/queries/` and\n regenerate with sqlc. A query that lists columns (`ListTaskSummaries`, the\n binding selects) does not pick the new one up; `SELECT *` queries do.\n3. Map it in the store (`taskFromRow`, `bindingValue` and friends). If the\n column holds encoded data, the package that owns the type owns the encoding\n (`task.EncodeInputs`), and the store and the wire both use it.\n4. Carry it over the wire (next section) if any process other than the State\n Store reads it.\n\n## Adding a field to a wire message\n\n1. Add it to `proto/state/v1/state.proto` with a new field number. Never reuse\n a number; retire one with `deprecated = true`.\n2. `task proto:generate`, then map it both ways in\n `internal/infrastructure/staterpc/values.go`.\n3. `TestTaskProtoCarriesEveryDomainField` fills every `task.Task` field and\n fails on one the mapping forgets. If it cannot fill the field's kind, extend\n it. Other messages have no such test, so add a round trip to\n `conformance_test.go`.\n\n## Adding an RPC or a store method\n\n1. Put the Go method on the narrow consumer interface in\n `internal/domain/storecontract` (keep each at eight methods or fewer) and add\n the matching RPC. A Go method without an RPC does not cross the process.\n2. Implement it in the Postgres store, in `staterpc.Client` (with its `var _`\n assertion) and in `staterpc.server`. A missing dependency answers\n `codes.Unavailable`, never a fabricated default.\n3. Wire the dependency in every composition that serves or consumes it:\n `stateStoreDeps` in `internal/app/archied/state_store.go`, the daemon's\n assertions in `bootstrap.go`, and `internal/app/archieui/compose.go` for the\n dashboard process.\n4. Task-scoped tokens may call only `Update`, `Transition` and `InsertEvent` on\n their own task (`staterpc.TaskGrants`). A new RPC is admin-only unless it is\n added there deliberately.\n5. Add it to `conformance_test.go`, which runs every surface over a real gRPC\n connection.\n\n## Adding an error sentinel\n\nAdd the sentinel to `storecontract`, a row to `wireErrors` in `values.go`, and\na case to `error_test.go`. The canonical message is part of the wire contract:\nchanging it breaks `errors.Is` on the client silently.\n\n## Harness OAuth secrets\n\n`HarnessSecretStore` stores token sets by org and credential service through\nadmin-only State Store RPCs. The EDA store seals them with the binding cipher's\nkeyring and a separate `HarnessSecretDomain`. OAuth writes require a configured\nbinding encryption key; the legacy binding plaintext fallback does not apply.\nThe daemon's egress proxy (`internal/infrastructure/egress/oauth.go`) is the\nonly daemon consumer: for a run granted the service it swaps sentinels for the\nstored tokens and writes every refresh back. The setup terminal is a separate\nharness slice.\n"
|
||||
},
|
||||
{
|
||||
"url": "/dev/development/wiring/",
|
||||
@@ -154,7 +154,7 @@
|
||||
"url": "/dev/development/workflows/",
|
||||
"title": "Workflows",
|
||||
"section": "Development",
|
||||
"body": "# Workflows\n\nAuthority: `docs/architecture/agent-system.md` for the lifecycle,\n`docs/prds/event-automation.md` for inputs, repository modes and profiles.\n\nWorkflow definitions are YAML stored as a control-plane resource. The State\nStore validates them and the agent compiles them, each against the step\nvocabulary it registers, so both must see the same step types.\n\n## Adding a step type\n\n1. Write the factory in `internal/domain/workflow` as a `StepType`. It decodes\n and validates its settings and returns an error for anything it cannot\n honour. The factory runs when a definition is saved and again when it is\n compiled, so a bad definition is refused on save.\n2. Register it through a provider in\n `internal/infrastructure/workflowsteps/workflowsteps.go`. That one list is\n what every process registers, which is how the validating and executing\n sides agree.\n3. An agent-driven step builds on `AgentStage`; do not start a second path to\n the agent runner.\n4. A step that needs no repository goes in `repoFreeStepTypes` in\n `definition.go`, or workflows declaring `repository: none` or `optional`\n cannot use it. A step that needs one may assume `tc.Dir` holds a worktree\n only when the workflow's repository is `required`.\n5. A step that ends the workflow sets `tc.Outcome`. A workflow that runs out of\n steps without an outcome is parked as a definition bug.\n6. Add a parse test (settings accepted and refused) and a run test with fake\n `Trees` and agent runner.\n\n## Changing the definition format\n\n- The fields a caller needs without the engine (inputs, repository, profile)\n live in `task.WorkflowInterface`, because the dashboard process must not\n import the workflow engine (`cmd/archie-ui/architecture_test.go`). Anything a\n binding or the dashboard checks goes there.\n- The YAML decoder rejects unknown keys. Existing stored definitions must keep\n parsing, so a new key is optional with a default that preserves today's\n behaviour.\n- Examples in `examples/workflows/` are parsed against the registered\n vocabulary by `TestExampleWorkflowsParse`. Add one for a new capability.\n"
|
||||
"body": "# Workflows\n\nAuthority: `docs/architecture/agent-system.md` for the lifecycle,\n`docs/prds/event-automation.md` for inputs, repository modes and profiles.\n\nWorkflow definitions are YAML stored as a control-plane resource. The State\nStore validates them and the agent compiles them, each against the step\nvocabulary it registers, so both must see the same step types.\n\n## Adding a step type\n\n1. Write the factory in `internal/domain/workflow` as a `StepType`. It decodes\n and validates its settings and returns an error for anything it cannot\n honour. The factory runs when a definition is saved and again when it is\n compiled, so a bad definition is refused on save.\n2. Register it through a provider in\n `internal/infrastructure/workflowsteps/workflowsteps.go`. That one list is\n what every process registers, which is how the validating and executing\n sides agree.\n3. An agent-driven step builds on `AgentStage`; do not start a second path to\n the agent runner.\n4. A step that needs no repository goes in `repoFreeStepTypes` in\n `definition.go`, or workflows declaring `repository: none` or `optional`\n cannot use it. A step that needs one may assume `tc.Dir` holds a worktree\n only when the workflow's repository is `required`.\n5. A step that ends the workflow sets `tc.Outcome`. A workflow that runs out of\n steps without an outcome is parked as a definition bug.\n6. Add a parse test (settings accepted and refused) and a run test with fake\n `Trees` and agent runner.\n\n## Changing the definition format\n\n- The fields a caller needs without the engine (inputs, repository, profile)\n live in `task.WorkflowInterface`, because the dashboard process must not\n import the workflow engine (`cmd/archie-ui/architecture_test.go`). Anything a\n binding or the dashboard checks goes there.\n- The YAML decoder rejects unknown keys. Existing stored definitions must keep\n parsing, so a new key is optional with a default that preserves today's\n behaviour.\n- Examples in `examples/workflows/` are parsed against the registered\n vocabulary by `TestExampleWorkflowsParse`. Add one for a new capability.\n\n## Enabling and disabling\n\nThe `workflow-enablement` control-plane resource lists, per org, the workflows\nthat org has disabled; anything unlisted is enabled. Its readers are the\ndaemon's binding dispatch (a disabled workflow's binding is skipped like an\nunarmed one), the dashboard's binding save (refused) and binding list\n(`workflow_disabled`), and work requests. A new reader of \"may this org run\nthis workflow\" goes through `task.WorkflowEnablement.Enabled`, never a second\nlist. The dashboard acts in the default org until access resolves a caller's\nown.\n\n## Starting a workflow from chat\n\n`task_spawn` accepts `workflow` and an `inputs` object. The gateway forwards\ninputs through the task creation contract; it does not interpret individual\nworkflows. The daemon checks inputs against the pinned `WorkflowInterface`\nbefore acquiring a container and parks invalid requests with the reason.\n"
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/01-project-management/",
|
||||
@@ -232,7 +232,7 @@
|
||||
"url": "/dev/prds/control-plane-apply-status/",
|
||||
"title": "Control-plane apply status",
|
||||
"section": "PRDs",
|
||||
"body": "# Control-plane apply status\n\n**Status:** Approved\n**Date:** 2026-09-21\n**Tracking:** `archie-core-pskb`, and `archie-core-nwa0` which depends on it\n\n## Outcome\n\nAn operator who edits a control-plane resource can see which processes are\nrunning that version, which are still on an older one, which rejected it, and\nwhich have stopped reporting.\n\n`docs/prds/runtime-control-plane.md` requires this and does not say where the\nreport goes. This decides that.\n\n## Where the report goes\n\nApply status is a State Store contract surface. `ControlPlaneService` is the\nsurface for editing a resource, and a status report is not an edit. The\nprecedent is the config snapshot pair: a process publishes what it knows, the\nUI process reads it, and both RPCs are administrative, so a task-scoped grant\nreaches neither. That denial needs no new rule: `authorizesTaskScopedCall`\nnames three methods and denies everything else.\n\n`docs/prds/state-store-contract.md` gains the pair in its inventory, and its\nRPC count at two places moves from 45 to 47.\n\nThe read returns all records as a list, including an empty one. The\n`found=false` convention for absent single rows does not apply.\n\n## What is reported\n\nOne record per process and resource kind, replaced in place. It holds the\nprocess name, the resource kind, the version applied, the error if the process\ncould not apply it, and the time it reported.\n\nEach process re-stamps its records every 30 seconds. A record is stale once it\nis older than 90 seconds, and a stale record means the process that wrote it is\nno longer running. The report time is therefore a liveness signal, not only a\nwrite timestamp.\n\nA process reports at the point it applies a resource, so the record says what\nhappened rather than what was intended. Nothing probes.\n\nProcess names come from one shared constant naming `archied`, `archie-gateway`\nand `archie-messaging`. A deployment runs at most one of each. Writer and\nreader are bound to that constant by test, because a drifted name is\nindistinguishable from a process that never reported.\n\n## Which processes report\n\n- `archied` and `archie-gateway` apply every restart-required kind through\n `boot.runtimeConfig`, at boot and on SIGHUP.\n- `archied` also applies the live kinds it watches, and reports each update it\n applies.\n- `archie-messaging` applies channel settings at startup and reports that kind.\n\n## What can be reported, and what cannot\n\nA process reaches its apply point only after the State Store has answered it.\nWhen the State Store is unreachable, the process exits or refuses to start and\nwrites no record. An unreachable store is never reported as a failure by the\nprocess it affected. A record carries the other failure: the store answered,\nand the value would not validate.\n\nAbsence has two meanings and the UI never collapses them: no process applies\nthis kind, or a process that applies other kinds has not reported this one.\n\n## Relationship to the reload status\n\nApply status covers control-plane resource kinds. `ReloadStatus` covers the\nfile document and stays the only report for a SIGHUP that failed to resolve or\nvalidate it. Neither is derived from the other.\n\nWriting a record is best-effort. On the SIGHUP path it takes its own bounded\ncontext, separate from the budget the reload spends reading the control plane,\nand a failed write is logged rather than turned into a failed reload.\n\n## What the UI shows\n\nThe settings page shows, per resource, the stored version beside each process's\napplied version, error, and report time. A process on an older version of a\nrestart-required resource is pending a restart. A process with an error is\nfailed, with the error beside it. A process whose record is stale is unknown,\nnever current.\n\n## A record outlives the process that wrote it\n\nRecords are replaced in place, so a process that applies a version and then\nstops would otherwise leave a record asserting that version indefinitely, and\nthe settings page would show a dead process as current.\n`docs/prds/status-health-surface.md` faced the same choice and stamped the start\nof a poll pass so a wedged poller reads as stale rather than healthy.\n\nSettled: the re-stamp above. The alternatives considered were\ncarrying the instance identity generated at process start, which detects a\nrestart but not a death, and accepting the limitation with the page saying so.\n\n## Verification\n\n- A process that applies a resource writes a record carrying that version.\n- A process whose apply fails validation writes a record carrying the error and\n no new version.\n- A reload that fails leaves the previously applied version recorded.\n- A record written under a process name outside the shared constant fails the\n test binding writer to reader.\n- A task-scoped credential is refused by both RPCs.\n- A failed report does not fail the reload that produced it.\n- A record that stops being re-Line truncated
|
||||
"body": "# Control-plane apply status\n\n**Status:** Approved\n**Date:** 2026-09-21\n**Tracking:** `archie-core-pskb`, and `archie-core-nwa0` which depends on it\n\n## Outcome\n\nAn operator who edits a control-plane resource can see which processes are\nrunning that version, which are still on an older one, which rejected it, and\nwhich have stopped reporting.\n\n`docs/prds/runtime-control-plane.md` requires this and does not say where the\nreport goes. This decides that.\n\n## Where the report goes\n\nApply status is a State Store contract surface. `ControlPlaneService` is the\nsurface for editing a resource, and a status report is not an edit. The\nprecedent is the config snapshot pair: a process publishes what it knows, the\nUI process reads it, and both RPCs are administrative, so a task-scoped grant\nreaches neither. That denial needs no new rule: `authorizesTaskScopedCall`\nnames three methods and denies everything else.\n\n`docs/prds/state-store-contract.md` gains the pair in its inventory, and its\nRPC count at two places moves from 45 to 47.\n\nThe read returns all records as a list, including an empty one. The\n`found=false` convention for absent single rows does not apply.\n\n## What is reported\n\nOne record per process and resource kind, replaced in place. It holds the\nprocess name, the resource kind, the version applied, the error if the process\ncould not apply it, and the time it reported.\n\nEach process re-stamps its records every 30 seconds. A record is stale once it\nis older than 90 seconds, and a stale record means the process that wrote it is\nno longer running. The report time is therefore a liveness signal, not only a\nwrite timestamp.\n\nA process reports at the point it applies a resource, so the record says what\nhappened rather than what was intended. Nothing probes.\n\nProcess names come from one shared constant naming `archied`, `archie-gateway`\nand `archie-messaging`. A deployment runs at most one of each. Writer and\nreader are bound to that constant by test, because a drifted name is\nindistinguishable from a process that never reported.\n\n## Which processes report\n\n- `archied` and `archie-gateway` apply every restart-required kind through\n `boot.runtimeConfig`, at boot and on SIGHUP.\n- `archied` also applies the live kinds it watches, and reports each update it\n applies.\n- `archie-messaging` applies channel settings at startup and reports that kind.\n\n## What can be reported, and what cannot\n\nA process reaches its apply point only after the State Store has answered it.\nAt startup, when the State Store is unreachable, the process exits or refuses\nto start and writes no record. A live watcher that loses its established\ncontrol-plane stream reports the connection failure against its last applied\nversion while it retries. Re-establishing the stream clears that outage record\nwithout clearing a versioned document rejection. A transport failure is not a\ndocument rejection; it reports that live delivery is unavailable.\n\nAbsence has two meanings and the UI never collapses them: no process applies\nthis kind, or a process that applies other kinds has not reported this one.\n\n## Relationship to the reload status\n\nApply status covers control-plane resource kinds. `ReloadStatus` covers the\nfile document and stays the only report for a SIGHUP that failed to resolve or\nvalidate it. Neither is derived from the other.\n\nWriting a record is best-effort. On the SIGHUP path it takes its own bounded\ncontext, separate from the budget the reload spends reading the control plane,\nand a failed write is logged rather than turned into a failed reload.\n\n## What the UI shows\n\nThe settings page shows, per resource, the stored version beside each process's\napplied version, error, and report time. A process on an older version of a\nrestart-required resource is pending a restart. A process with an error is\nfailed, with the error beside it. A process whose record is stale is unknown,\nnever current.\n\n## A record outlives the process that wrote it\n\nRecords are replaced in place, so a process that applies a version and then\nstops would otherwise leave a record asserting that version indefinitely, and\nthe settings page would show a dead process as current.\n`docs/prds/status-health-surface.md` faced the same choice and stamped the start\nof a poll pass so a wedged poller reads as stale rather than healthy.\n\nSettled: the re-stamp above. The alternatives considered were\ncarrying the instance identity generated at process start, which detects a\nrestart but not a death, and accepting the limitation with the page saying so.\n\n## Verification\n\n- A process that applies a resource writes a record carrying that version.\n- A process whose apply fails validation writes a record carrying the error and\n no new version.\n- A live watch outage is reported against the last applied version until the\n stream is re-established; re-establishment preserves any outstanLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/curator-sampler-wave1/",
|
||||
@@ -328,7 +328,7 @@
|
||||
"url": "/dev/prds/external-agent-harness/",
|
||||
"title": "External agent harnesses",
|
||||
"section": "PRDs",
|
||||
"body": "# External agent harnesses\n\n**Status:** Approved\n**Authority:** `docs/architecture/agent-system.md` (agent execution as a data\nboundary); settles the harness non-goal deferred by\n`docs/prds/service-decomposition.md`.\n**Compounds with:** `docs/prds/execution-tree-state-machine.md` (a harness\nrun is one `agent` StepExecution), `docs/prds/binding-secret-encryption.md`\n(the at-rest envelope reused for harness credentials).\n\n## Decision\n\nA workflow stage can run on an external coding-agent CLI instead of the\nbuilt-in agent loop: Claude Code, Codex, Pi, OMP, GitHub Copilot CLI, or any\nother CLI packaged as a Docker Sandbox Kit v3. Each authenticates with an API\nkey or the operator's subscription login, and can carry the operator's own\nskills, plugins, subagents and instructions.\n\nTwo boundaries hold regardless of what the harness does:\n\n- **The real credential never enters the container.** The container sees\n sentinel values; archie's egress proxy substitutes the real credential on\n outbound requests and performs OAuth refresh on the host.\n- **Archie's workflow guarantees are enforced outside the harness.** Git,\n protected paths, read-only stages, gates and budgets are checked by archie\n around the process and against the worktree afterwards.\n\n## Kits\n\nA harness is packaged as a Kit v3 image: an OCI image whose\n`vnd.docker.sandbox.kit.descriptor` manifest annotation declares what the\nharness needs. Archie reads descriptors with the published\n`github.com/docker/sandbox-kit-spec/v3/spec` package and does not maintain\nits own descriptor format. Published Kits run unmodified.\n\nArchie is a partial Kit runtime. It implements these capability types:\n\n| Type | Archie behaviour |\n| ------------------- | ----------------------------------------------------------------------------------------- |\n| `credential@1` | Proxy-managed only, described below. |\n| `network-policy@1` | Enforced by the egress proxy. |\n| `volume@1` | A Docker volume keyed by WorkflowExecution, deleted with it. |\n| `lifecycle@1` | Install and startup hooks run on container create. |\n| `agent-sessions@1` | The headless `prompt` and `resume` invocations for the stage. |\n| `agent-skills@1` | The operator's skills store, mounted read-only whatever the Kit asks. |\n| `agent-context@1` | Archie's stage instructions, delivered where the Kit declares. |\n| `resources@1` | Container CPU and memory limits. |\n\nEvery other type fails closed: a required entry refuses the launch, an\noptional one is skipped and recorded on the step. `credential@1` with\n`passthrough: true` and any credential for a forge service are refused.\n\nThe operator's own setup (plugins, subagents, instructions, settings) is a\nmixin Kit the operator builds `FROM` or alongside the harness Kit. It is\nversioned image content, rewritten on every create, never state a run can\nmodify.\n\n## Contract\n\nA harness run is a second implementation of `agentexec.Runner`. It takes the\nsame `Request` and returns the same `Result`, so workflows, the daemon and\nthe State Store do not know which runner ran a stage.\n\n`agent-sessions@1` supplies the invocation. Archie supplies, per CLI, an\noutput adapter that translates the CLI's JSON output stream into\n`ToolCallReporter` calls, `Usage` and a session ID. A CLI with no adapter can\nrun stages with no capture tools, reporting no usage; its token budget falls\nback to wall clock.\n\nWorkflow definition validation rejects, at load time, a stage whose needs the\nselected harness cannot meet: capture tools without an adapter, or a gate\nretry without a `resume` verb.\n\n## Selection\n\nA harness is an agent profile. `docs/prds/event-automation.md` defines a\nprofile as the execution environment a workflow selects; a harness profile\nnames a Kit composition (the workload Kit pinned by digest, and zero or more\nmixin Kits) in place of a container image. Everything else about profiles\nholds: a workflow names its profile, a stage may name a different one, and a\nprofile holds no secrets.\n\n`archie-agent` builds the stage's runner from the stage's profile: the\nai-sdk agent loop for an image profile, the harness runner for a Kit\nprofile. Image profiles, and every workflow already written against them,\nare unchanged. A Kit profile named by no workflow is a validation error.\n\nProfiles are org resources in the State Store, so a Kit profile belongs to\none org, is granted to its workspaces like any profile, and applies without\na restart.\n\n## Organisations\n\n`docs/prds/Line truncated
|
||||
"body": "# External agent harnesses\n\n**Status:** Approved\n**Authority:** `docs/architecture/agent-system.md` (agent execution as a data\nboundary); settles the harness non-goal deferred by\n`docs/prds/service-decomposition.md`.\n**Compounds with:** `docs/prds/execution-tree-state-machine.md` (a harness\nrun is one `agent` StepExecution), `docs/prds/binding-secret-encryption.md`\n(the at-rest envelope reused for harness credentials).\n\n## Decision\n\nA workflow stage can run on an external coding-agent CLI instead of the\nbuilt-in agent loop: Claude Code, Codex, Pi, OMP, GitHub Copilot CLI, or any\nother CLI packaged as a Docker Sandbox Kit v3. Each authenticates with an API\nkey or the operator's subscription login, and can carry the operator's own\nskills, plugins, subagents and instructions.\n\nTwo boundaries hold regardless of what the harness does:\n\n- **The real credential never enters the container.** The container sees\n sentinel values; archie's egress proxy substitutes the real credential on\n outbound requests and performs OAuth refresh on the host.\n- **Archie's workflow guarantees are enforced outside the harness.** Git,\n protected paths, read-only stages, gates and budgets are checked by archie\n around the process and against the worktree afterwards.\n\n## Kits\n\nA harness is packaged as a Kit v3 image: an OCI image whose\n`vnd.docker.sandbox.kit.descriptor` manifest annotation declares what the\nharness needs. Archie reads descriptors with the published\n`github.com/docker/sandbox-kit-spec/v3/spec` package and does not maintain\nits own descriptor format. Published Kits run unmodified.\n\nArchie is a partial Kit runtime. It implements these capability types:\n\n| Type | Archie behaviour |\n| ------------------- | ----------------------------------------------------------------------------------------- |\n| `credential@1` | Proxy-managed only, described below. |\n| `network-policy@1` | Enforced by the egress proxy. |\n| `volume@1` | A Docker volume keyed by WorkflowExecution, deleted with it. |\n| `lifecycle@1` | Install and startup hooks run on container create. |\n| `agent-sessions@1` | The headless `prompt` and `resume` invocations for the stage. |\n| `agent-skills@1` | The operator's skills store (`skills_dir`), mounted read-only whatever the Kit asks. |\n| `agent-context@1` | The workload's profile file beside the workspace, indexing each Kit's guidance. |\n| `resources@1` | Container CPU and memory limits. |\n\nEvery other type fails closed: a required entry refuses the launch, an\noptional one is skipped and recorded on the step. `credential@1` with\n`passthrough: true` and any credential for a forge service are refused.\n\nThe operator's own setup (plugins, subagents, instructions, settings) is a\nmixin Kit, published with the harness Kit as a Kit set: the set merges their\nlayers into one image. It is versioned image content, rewritten on every\ncreate, never state a run can modify.\n\n## Contract\n\nA harness run is a second implementation of `agentexec.Runner`. It takes the\nsame `Request` and returns the same `Result`, so workflows, the daemon and\nthe State Store do not know which runner ran a stage.\n\n`agent-sessions@1` supplies the invocation. Archie supplies, per CLI, an\noutput adapter that translates the CLI's JSON output stream into\n`ToolCallReporter` calls, `Usage` and a session ID. A CLI with no adapter can\nrun stages with no capture tools, reporting no usage; its token budget falls\nback to wall clock.\n\nWorkflow definition validation rejects, at load time, a stage whose needs the\nselected harness cannot meet: capture tools without an adapter, or a gate\nretry without a `resume` verb.\n\n## Selection\n\nA harness is an agent profile. `docs/prds/event-automation.md` defines a\nprofile as the execution environment a workflow selects; a harness profile\nnames one Kit pinned by digest, a workload Kit or a published Kit set, in\nplace of a container image. Archie runs that Kit's image and composes no Kits\nitself; a bare mixin is refused. Everything else about profiles\nholds: a workflow names its profile, a stage may name a different one, and a\nprofile holds no secrets.\n\n`archie-agent` builds the stage's runner from the stage's profile: the\nai-sdk agent loop for an image profile, the harness runner for a Kit\nprofile. Image profiles, and every workflow already written against them,\nare unchanged. A Kit profile named by no workflow is a validation error.\n\nA stage naming a different profile than its workflow's is a separate run,\nnot a mid-container runnLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/identity-decision/",
|
||||
@@ -376,7 +376,7 @@
|
||||
"url": "/dev/prds/multi-action-playbooks/",
|
||||
"title": "Multi-action playbooks and typed action results",
|
||||
"section": "PRDs",
|
||||
"body": "# Multi-action playbooks and typed action results\n\n**Status:** Approved\n**Date:** 2026-09-22\n**Parent:** `docs/prds/eda-playbook-engine.md`, epic `archie-core-t2db`\n**Beads issue:** `archie-core-nx30` (unblocks `archie-core-t2db.27` and `archie-core-t2db.31`)\n\n## Why this exists\n\n`eda-playbook-engine.md`'s hard boundary rejects any playbook that is not\nexactly one `workflow` action, so the parent document's data-flow, Module and\nChannel/Forge decisions have no loadable shape to attach to. The boundary's own\nstated condition is now met: both execution-time gaps are resolved\n(`eda-playbook-engine.md`, \"Execution-time gaps\"; the `playbook_dispatches`\nledger). This document designs the relaxation.\n\n## A playbook is one of two shapes\n\n- A **workflow playbook** is exactly one `workflow` action. Unchanged: it names\n a workflow definition and is routed by the daemon's definition pin.\n- An **action playbook** is one or more `module` actions in order. Each action\n has an optional `id`, a `kind` naming a registered Module kind, `args`, and an\n optional `when`.\n\nOne playbook does not mix the two shapes.\n\n```yaml\ntrigger: { kind: bug }\nactions:\n - id: build\n position: module\n kind: log\n args: { message: '\"build started\"' }\n - id: done\n position: module\n kind: log\n args: { message: '\"done: \" + string(actions.build.result.written)' }\n when: actions.build.result.written == true\n```\n\nThe first Module kind is the side-effect-free `log` kind\n(`module-position.md`, \"Recommended first slice\"). A Module kind with an\nexternal side effect, and the Channel and Forge positions, are out of scope.\n\n## A result type is the kind's generated Result struct\n\nEach Module kind owns a hand-written `Args` and `Result` struct\n(`internal/domain/eda/module/log` is the worked example); `ModuleRegistry.Invoke`\nreturns the result as a flat `map[string]any`. `ModuleRegistry.DecodeResult`\n(`internal/domain/eda/module`) is the single site that converts that map into\nthe kind's `Result` struct before a later expression reads it, so the value the\nchecker validates and the value the run reads have one definition.\n\n`actions.\u003cid\u003e` is typed by the kind of the action that declares `\u003cid\u003e`:\n`{ result: \u003cKindResult\u003e }`. `event` stays `dyn` (J4,\n`playbook-expression-syntax.md`).\n\n## Reject-at-load, preserved\n\nRelaxing the boundary must not make a bad reference resolvable. The load fails,\nnaming the playbook and the offending action, for:\n\n- an `id` missing where a later action references it, duplicated, or outside\n its shape's grammar: a workflow action id keeps the shared\n stable-identifier grammar (J1, already enforced), while a module action id\n must be a lowercase CEL field name writable as `actions.\u003cid\u003e` (so a CEL\n keyword such as `in`, `true`, `false`, or `null` is rejected at load);\n- an `actions.\u003cid\u003e` read of an id no earlier action declares;\n- an `actions` read that is not statically resolvable to an id (any map index,\n literal or dynamic, `in`, a comprehension): the typed `actions` root is an\n object type, so only field selection `actions.\u003cid\u003e` resolves and the\n `actions[\"id\"]` spelling is not accepted;\n- a `result` field the referenced kind's `Result` does not define;\n- a reference to an earlier action that produces no result;\n- an unknown `position`, an unknown `kind`, or a `module` action with no `kind`;\n- a field belonging to the other shape (`kind` on a `workflow` action, or\n `workflow` on a `module` action);\n- an arg KEY the kind's `Args` schema does not define;\n- an arg value whose checked CEL type cannot fill its `Args` field (`'123'`\n for a string field). A `dyn` value, such as an `event` read, passes: its\n type is known only per event, and the module decode refuses a bad one at\n run.\n\nDeclaring the kind's `Result` schema to CEL at load makes a result-field typo a\nload failure rather than a dispatch failure. Matching arg keys against the\nkind's `Args` schema makes an arg-key typo or a wrongly typed value a load\nfailure.\n\n## The environment is per playbook\n\nResult typing depends on the ids a playbook declares and the kind each id runs,\nso the CEL environment is built from one playbook's action list rather than once\nper `Store`, and `expr.NewEnv` takes that list: each declared id becomes a field\nof the `actions` object typed by its kind's `Result`.\n\n## Running an action playbook is out of scope\n\nThis document makes an action playbook load and its references type-check.\nRunning one is designed in `docs/prds/action-playbook-run.md`.\n\n## Decisions\n\n**D1 — dispatch before `t2db.31`.** Superseded by\n`docs/prds/action-playbook-run.md`. Was: an action playbook loads and\nvalidates but is not routed; the definition-pin dispatch reports no match for it,\nand the daemon logs a visible warning naming it.\n\n**D2 — mixing positions.*Line truncated
|
||||
"body": "# Multi-action playbooks and typed action results\n\n**Status:** Approved\n**Date:** 2026-09-22\n**Parent:** `docs/prds/eda-playbook-engine.md`, epic `archie-core-t2db`\n**Beads issue:** `archie-core-nx30` (unblocks `archie-core-t2db.27` and `archie-core-t2db.31`)\n\n## Why this exists\n\n`eda-playbook-engine.md`'s hard boundary rejects any playbook that is not\nexactly one `workflow` action, so the parent document's data-flow, Module and\nChannel/Forge decisions have no loadable shape to attach to. The boundary's own\nstated condition is now met: both execution-time gaps are resolved\n(`eda-playbook-engine.md`, \"Execution-time gaps\"; the `playbook_dispatches`\nledger). This document designs the relaxation.\n\n## A playbook is one of two shapes\n\n- A **workflow playbook** is exactly one `workflow` action. Unchanged: it names\n a workflow definition and is routed by the daemon's definition pin.\n- An **action playbook** is one or more `module` actions in order. Each action\n has an optional `id`, a `kind` naming a registered Module kind, `args`, and an\n optional `when`.\n\nOne playbook does not mix the two shapes.\n\n```yaml\ntrigger: { kind: bug }\nactions:\n - id: build\n position: module\n kind: log\n args: { message: '\"build started\"' }\n - id: done\n position: module\n kind: log\n args: { message: '\"done: \" + string(actions.build.result.written)' }\n when: actions.build.result.written == true\n```\n\nThe first Module kind is the side-effect-free `log` kind\n(`module-position.md`, \"Recommended first slice\"). A Module kind with an\nexternal side effect, and the Channel and Forge positions, are out of scope.\n\n## A result type is the kind's generated Result struct\n\nEach Module kind owns a hand-written `Args` and `Result` struct\n(`internal/domain/eda/module/log` is the worked example); `ModuleRegistry.Invoke`\nreturns the result as a flat `map[string]any`. `ModuleRegistry.DecodeResult`\n(`internal/domain/eda/module`) is the single site that converts that map into\nthe kind's `Result` struct before a later expression reads it, so the value the\nchecker validates and the value the run reads have one definition.\n\n`actions.\u003cid\u003e` is typed by the kind of the action that declares `\u003cid\u003e`:\n`{ result: \u003cKindResult\u003e }`. `event` stays `dyn` (J4,\n`playbook-expression-syntax.md`).\n\n## Reject-at-load, preserved\n\nRelaxing the boundary must not make a bad reference resolvable. The load fails,\nnaming the playbook and the offending action, for:\n\n- an `id` missing where a later action references it, duplicated, or outside\n its shape's grammar: a workflow action id keeps the shared\n stable-identifier grammar (J1, already enforced), while a module action id\n must be a lowercase CEL field name writable as `actions.\u003cid\u003e` (so a CEL\n keyword such as `in`, `true`, `false`, or `null` is rejected at load);\n- an `actions.\u003cid\u003e` read of an id no earlier action declares;\n- an `actions` read that is not statically resolvable to an id (any map index,\n literal or dynamic, `in`, a comprehension): the typed `actions` root is an\n object type, so only field selection `actions.\u003cid\u003e` resolves and the\n `actions[\"id\"]` spelling is not accepted;\n- a `result` field the referenced kind's `Result` does not define;\n- a reference to an earlier action that produces no result;\n- an unknown `position`, an unknown `kind`, or a `module` action with no `kind`;\n- a field belonging to the other shape (`kind` on a `workflow` action, or\n `workflow` on a `module` action);\n- an arg KEY the kind's `Args` schema does not define;\n- an arg value whose checked CEL type cannot fill its `Args` field (`'123'`\n for a string field). A `dyn` value, such as an `event` read, passes: its\n type is known only per event, and the module decode refuses a bad one at\n run.\n\nDeclaring the kind's `Result` schema to CEL at load makes a result-field typo a\nload failure rather than a dispatch failure. Matching arg keys against the\nkind's `Args` schema makes an arg-key typo or a wrongly typed value a load\nfailure.\n\n## The environment is per playbook\n\nResult typing depends on the ids a playbook declares and the kind each id runs,\nso the CEL environment is built from one playbook's action list rather than once\nper `Store`, and `expr.NewEnv` takes that list: each declared id becomes a field\nof the `actions` object typed by its kind's `Result`.\n\n## Running an action playbook is out of scope\n\nThis document makes an action playbook load and its references type-check.\nRunning one is designed in `docs/prds/action-playbook-run.md`.\n\n## Decisions\n\n**D1 — dispatch before `t2db.31`.** Superseded by\n`docs/prds/action-playbook-run.md`. Was: an action playbook loads and\nvalidates but is not routed; the definition-pin dispatch reports no match for it,\nand the daemon logs a visible warning naming it.\n\n**D2 — mixing positions.*Line truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/news-and-releases/",
|
||||
@@ -406,13 +406,25 @@
|
||||
"url": "/dev/prds/playbook-expression-syntax/",
|
||||
"title": "Playbook data-flow and condition syntax",
|
||||
"section": "PRDs",
|
||||
"body": "# Playbook data-flow and condition syntax\n\n**Status:** Approved\n**Date:** 2026-09-03\n**Parent:** `docs/prds/eda-playbook-engine.md`, epic `archie-core-t2db`\n**Beads issue:** `archie-core-t2db.14` (expression environment).\nUnbuilt decisions: `archie-core-t2db.25` (J1 action ids),\n`archie-core-t2db.26` (J2 args as CEL),\n`archie-core-t2db.27` (Result schemas declared to CEL).\n\n**Decision:** CEL via `cel.dev/cel-go` (v0.32.0), pinned. One expression\nmechanism covers both an action's `when` condition and its `args` values.\n\n## The requirement, stated directly\n\nA playbook action is gated and parametrised by runtime data: (a) a condition\ndeciding whether the action runs; (b) a later action's `args` values referencing\nan earlier action's `Result` and the triggering event's fields. Both are **CEL\nexpressions**, evaluated against one evaluation context. There is no separate\ninterpolation syntax: CEL reads nested maps and fields natively, so `args`\nvalues that need data are written as CEL, and only plain literal args remain\nplain YAML scalars.\n\nBoth halves are read-only: expressions may read context values and compute a\nresult from them, never mutate, never call host functions, never perform I/O.\nCEL enforces this structurally (no side effects, linear evaluation when macros\nare bounded, cost-limited).\n\n```yaml\nactions:\n - id: build\n position: module\n kind: log\n args:\n message: '\"build finished\"' # literal\n when: 'event.label == \"bugfix\"' # gate on event field\n - position: module\n kind: log\n args:\n message: '\"done: \" + string(actions.build.result.written)'\n when: \"actions.build.result.written == true\"\n```\n\n## Trust boundary of the expression\n\nA playbook YAML is **operator-installed, in-process, daemon-privileged** -- the\nsame tier as `ModuleDir`/`PluginDir`/`SecretEngineDir` (module-position.md's\ntrust-boundary section): loaded from a configured directory at startup, never\nfrom a webhook body or task worktree. The schema-by-example flow uses live\nevents to _design against_; the saved playbook is operator-authored file content\nin an operator-configured location.\n\nTwo consequences:\n\n1. The expression string is **trusted**. Operator-authored config, not attacker\n input; no sandboxing against a hostile expression string is required. If a\n future playbook source is less trusted (auto-generated bindings from\n unauthenticated captures), that is the playbook-file trust tier moving -- the\n loader's acceptance check is the right place, not the evaluator.\n2. The **data the expression reads is NOT trusted** (decoded webhook body, prior\n results through the same pipeline). Robustness against hostile data is\n required: no panic on wrong-typed/missing fields, no unbounded cost on\n deep/cyclic maps, bounded evaluation time. CEL provides this structurally\n (cost limits, linear non-Turing-complete evaluation, error values instead of\n panics -- verified in the vetting record below).\n\n## The gate precedent is deliberately NOT copied\n\n`internal/gate/gateeval` evaluates arbitrary interpreted Go (`.archie/gate.go`)\nas the repo's conditional-logic precedent. That is the wrong precedent for\nplaybook conditions because this document's premise is: **YAML is pure\norchestration data; Yaegi is where imperative logic lives** (Problem section;\nmodule-position.md's \"no generic hook\" section). Yaegi snippets in YAML would\nmove imperative logic into the data layer -- the inversion this design exists to\nprevent -- and make playbooks un-lintable.\n\nThe line: conditions are **declarative predicates over runtime data, not\nprograms**. CEL is non-Turing-complete and side-effect-free, so it cannot become\na program; a condition that needs real logic gets a Module kind (Yaegi),\nreferenced by the action, not a stronger expression body.\n\n## Plugin-engine-rule interaction\n\nThe plugin engine rule forbids a generic `Module` interface with an `any`\npayload; it exists to keep static implementation contracts typed. Evaluating CEL\nagainst runtime `map[string]any` is **not the same problem**: the rule concerns\n_implementation contracts_ (static operations a capability family exposes), not\n_runtime data values_ (legitimately dynamic -- an event payload's shape is\nunknown until it arrives). The Module contract stays fully typed (generated\n`Args`/`Result` schemas); CEL is a read-only data reader under the playbook\nengine family, not a new capability contract. Stated once.\n\n## Minimum viable evaluation context (what expressions see)\n\nOne flat context, namespaced from the playbook run, built at dispatch time:\n\n| Name | Type | Source Line truncated
|
||||
"body": "# Playbook data-flow and condition syntax\n\n**Status:** Approved\n**Date:** 2026-09-03\n**Parent:** `docs/prds/eda-playbook-engine.md`, epic `archie-core-t2db`\n**Beads issue:** `archie-core-t2db.14` (expression environment).\n\n**Decision:** CEL via `cel.dev/cel-go` (v0.32.0), pinned. One expression\nmechanism covers both an action's `when` condition and its `args` values.\n\n## The requirement, stated directly\n\nA playbook action is gated and parametrised by runtime data: (a) a condition\ndeciding whether the action runs; (b) a later action's `args` values referencing\nan earlier action's `Result` and the triggering event's fields. Both are **CEL\nexpressions**, evaluated against one evaluation context. There is no separate\ninterpolation syntax: CEL reads nested maps and fields natively, so `args`\nvalues that need data are written as CEL, and only plain literal args remain\nplain YAML scalars.\n\nBoth halves are read-only: expressions may read context values and compute a\nresult from them, never mutate, never call host functions, never perform I/O.\nCEL enforces this structurally (no side effects, linear evaluation when macros\nare bounded, cost-limited).\n\n```yaml\nactions:\n - id: build\n position: module\n kind: log\n args:\n message: '\"build finished\"' # literal\n when: 'event.label == \"bugfix\"' # gate on event field\n - position: module\n kind: log\n args:\n message: '\"done: \" + string(actions.build.result.written)'\n when: \"actions.build.result.written == true\"\n```\n\n## Trust boundary of the expression\n\nA playbook YAML is **operator-installed, in-process, daemon-privileged** -- the\nsame tier as `ModuleDir`/`PluginDir`/`SecretEngineDir` (module-position.md's\ntrust-boundary section): loaded from a configured directory at startup, never\nfrom a webhook body or task worktree. The schema-by-example flow uses live\nevents to _design against_; the saved playbook is operator-authored file content\nin an operator-configured location.\n\nTwo consequences:\n\n1. The expression string is **trusted**. Operator-authored config, not attacker\n input; no sandboxing against a hostile expression string is required. If a\n future playbook source is less trusted (auto-generated bindings from\n unauthenticated captures), that is the playbook-file trust tier moving -- the\n loader's acceptance check is the right place, not the evaluator.\n2. The **data the expression reads is NOT trusted** (decoded webhook body, prior\n results through the same pipeline). Robustness against hostile data is\n required: no panic on wrong-typed/missing fields, no unbounded cost on\n deep/cyclic maps, bounded evaluation time. CEL provides this structurally\n (cost limits, linear non-Turing-complete evaluation, error values instead of\n panics -- verified in the vetting record below).\n\n## The gate precedent is deliberately NOT copied\n\n`internal/gate/gateeval` evaluates arbitrary interpreted Go (`.archie/gate.go`)\nas the repo's conditional-logic precedent. That is the wrong precedent for\nplaybook conditions because this document's premise is: **YAML is pure\norchestration data; Yaegi is where imperative logic lives** (Problem section;\nmodule-position.md's \"no generic hook\" section). Yaegi snippets in YAML would\nmove imperative logic into the data layer -- the inversion this design exists to\nprevent -- and make playbooks un-lintable.\n\nThe line: conditions are **declarative predicates over runtime data, not\nprograms**. CEL is non-Turing-complete and side-effect-free, so it cannot become\na program; a condition that needs real logic gets a Module kind (Yaegi),\nreferenced by the action, not a stronger expression body.\n\n## Plugin-engine-rule interaction\n\nThe plugin engine rule forbids a generic `Module` interface with an `any`\npayload; it exists to keep static implementation contracts typed. Evaluating CEL\nagainst runtime `map[string]any` is **not the same problem**: the rule concerns\n_implementation contracts_ (static operations a capability family exposes), not\n_runtime data values_ (legitimately dynamic -- an event payload's shape is\nunknown until it arrives). The Module contract stays fully typed (generated\n`Args`/`Result` schemas); CEL is a read-only data reader under the playbook\nengine family, not a new capability contract. Stated once.\n\n## Minimum viable evaluation context (what expressions see)\n\nOne flat context, namespaced from the playbook run, built at dispatch time:\n\n| Name | Type | Source |\n| --------- | ------------------------ | ---------------------------------------------------------------------------------Line truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/plugin-settings-live/",
|
||||
"title": "Plugin settings reconcile live",
|
||||
"section": "PRDs",
|
||||
"body": "# Plugin settings reconcile live\n\n**Status:** Draft\n**Tracking:** GitHub [#1154](https://github.com/samcharles93/archie-core/issues/1154), epic [#998](https://github.com/samcharles93/archie-core/issues/998)\n**Authority:** `docs/prds/runtime-control-plane.md` decides each feature owns how\nits changes take effect; `docs/architecture/plugins-and-extensions.md` owns the\nplugin engine rule; `docs/prds/control-plane-apply-status.md` owns where apply\nreports go.\n\n## Outcome\n\nAn operator drops a plugin, module or secret-engine file into the configured\ndirectory while archied runs, and the daemon loads it without a restart. An\nedit to an installed file replaces what is running. Deleting an installed file\nnever stops running code; apply status says so. A stored change to\n`plugin-settings` applies live for additions instead of requiring a restart.\n\n## Triggers\n\n`plugin-settings` joins the kinds archied watches (`PluginSettingsKind` moves\nto the live list in `internal/app/archied/control_plane.go`). After the daemon\nlayers a new version it reconciles the three directories the document names.\nA second trigger needs no document change: a poller reconciles on an interval,\nso a file dropped into a directory loads on its own. The poll interval is the\napply-status restamp constant; no filesystem-watch dependency is added. The\npoller reads the current document's directories from the running config each\ntick, so a changed `plugin_dir`, `module_dir` or `secret_engine_dir` retargets\nreconciliation without a restart.\n\n## Rules\n\n- Adding and changing load; removing never unloads. Yaegi interpreters are not\n reclaimed while a caller still exists and there is no unload path; the\n running set can only grow.\n- Each file is loaded through a fresh interpreter (the boot pattern). A changed\n file therefore loads cleanly, and replacement switches consumers to the new\n interpretation; files are content-hashed so only new and changed files load.\n- A file that fails to load is skipped and reported; already-running code keeps\n running. This is the degrade-and-skip convention `plugin.LoadDir` and\n `Registry.LoadDir` already apply at boot. Boot keeps its reject-at-load rule\n for the module directory; a broken file at runtime skips without aborting.\n- A directory that does not exist reconciles to an empty set.\n\n## The three registries\n\n- **Secret engines** (`internal/secret`). Reconciliation re-runs\n `Registry.LoadDir` against the live directory. `Register` replaces by name,\n so an edited engine takes effect for the next resolution. A deleted engine\n stays registered: existing references keep resolving through it until\n restart, and the record says so. Engines are stateless resolvers, so a swap\n needs no lifecycle step.\n- **Modules** (`internal/domain/eda/module`): reconciliation re-runs\n `ModuleRegistry.Register` for the kind's file. The invoker maps\n last-write-wins, and playbook dispatch resolves through the registry at\n invoke time, so the swap reaches a running playbook store unchanged. A file\n deleted for a kind leaves the old invoker in place, running; reported.\n- **Plugins** (`internal/plugin`): `Host` grows running-state operations beside\n `Register`, `Start` and `Stop`. One adds a single module while the host is\n running: it is inserted in dependency order, started alone, and on failure\n rolled back alone, leaving every previously started module running. The\n other replaces a module whose manifest id matches: stop it, start the new\n one, and restart the old one when the new start fails. Replacing a module\n that another depends on is refused, not swapped. These operations obey the\n plugin engine rule: the host still invokes start and stop itself, isolates\n the failure to the one module, and keeps a rollback. A deleted file makes no\n host call: the module runs on and is reported.\n\n## `skills_dir`\n\n`skills_dir` is not part of this change. The daemon refuses a candidate\n`plugin-settings` document whose `skills_dir` differs from the value it is\nrunning, reporting that the field applies on restart, until a skill\nreconciliation exists to carry it. The refusal is the existing rejected-edit\napply-status shape: the store keeps the version, the document is not applied,\nlast-known-good keeps running.\n\n## Apply status\n\nOne record: `archied` on `plugin-settings`. The reconciliation outcome is\nreported against the version the process is running. The record's error field\ncarries the outstanding reconciliation problem: a deleted file still running, a\nfile that failed to load, or the directory failing to read. A reconciliation\nwith nothing outstanding clears the error. The version stays the version the\nprocess is running; an add that succeeded is live even while a removal is\noutstanding, and the error says so rather than showing the kind as\nrestart-required. archie-gateway keeps boot-time loading; its record simply\nstays on the vLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/pr-review-agent/",
|
||||
"title": "PR review agent",
|
||||
"section": "PRDs",
|
||||
"body": "# PR review agent\n\n**Status:** Approved\n**Authority:** `docs/architecture/agent-system.md`; supersedes the reviewer\nexecutor and blocking rule in `docs/architecture/adversarial-review.md`, and\nthe designs in `docs/prds/operator-pr-review.md` and\n`docs/prds/review-calibration.md`.\n**Compounds with:** `docs/prds/execution-tree-state-machine.md` (every agent\ncall is a StepExecution), `docs/prds/external-agent-harness.md` (any agent\nstep may run on a harness), `docs/prds/inline-review.md` (posting),\n`docs/prds/pr-review-remediation.md` (consumes the findings).\n\n## Decision\n\nArchie ships a pull request reviewer as its first end-to-end product. It\nreviews any pull request on a watched repository, a PR an operator names, and\narchie's own PRs before they open.\n\nThe reviewer is a fixed pipeline, not a single agent. The review strategy is\ngenerated per PR: three lens agents propose review dimensions from the PR's\ncontent, one reviewer definition runs once per dimension, and later agents\nverify, challenge and combine the findings. Everything that can be computed\nis code: diff parsing, clustering, blast radius, evidence extraction,\nscoring, deduplication, line mapping and the review event.\n\nThe pipeline is **recall-first**. It posts every evidenced finding above the\nconfidence threshold, up to the comment cap. A precision gate exists as an\noperator dial and is off by default.\n\nAcceptance is measured, not asserted: see Verification.\n\n## Pipeline\n\nEach numbered phase is a stage of the `pr-review` workflow. Each agent call is\nan `agent` StepExecution; fan-out phases record one child per call.\n\n1. **Intake.** Code reads the PR metadata and diff statistics: type,\n complexity, languages, areas touched, risk signals. Depth comes from lines\n changed: under 100 is `quick` (at most 3 dimensions), under 500 is\n `standard` (6), otherwise `deep` (12). An operator may set depth\n explicitly.\n2. **Anatomy.** Code parses the diff into files and hunks, clusters related\n files, and computes the blast radius: unchanged files that import or are\n imported by changed files. One agent writes the PR narrative, risk\n surfaces, changes that do not fit the narrative, and gaps between the\n description and the diff.\n3. **Dimension selection.** Three lens agents run in parallel over the intake,\n anatomy and diff, each able to read the repository:\n - **behaviour:** where the old and new code diverge for any input; API\n contracts, concurrency and state, security, error handling, data flow;\n - **mechanics:** whether the code runs at the language and framework\n level; types, signatures and every caller, decorators and middleware,\n framework contracts, imports;\n - **fit:** patterns, complexity, abstraction, test adequacy, documentation\n that no longer matches, dependencies, migration completeness.\n\n Each lens returns review dimensions: a name, a reviewer prompt written for\n this PR, target files, context files and a priority. Code merges them,\n drops duplicates and keeps the highest-priority dimensions up to the\n depth's cap.\n4. **Review.** One reviewer definition runs once per dimension, in parallel,\n at most 8 at a time. Each reads its target and context files and may\n follow references. Each finding carries file, line range, severity\n (`critical`, `important`, `suggestion`, `nitpick`), title, body, an\n optional suggested fix, quoted evidence, confidence and tags.\n5. **Verification layer**, over the review findings:\n - code extracts an evidence package per finding: the code at the cited\n lines and snippets from its callers;\n - an evidence verifier checks high-priority findings against their\n packages;\n - an adversary confirms or challenges each finding, looks for issues every\n reviewer missed, and is more sceptical when intake scores the PR as\n likely machine-written;\n - a compound agent looks, within each cluster of confirmed findings, for\n defects that only exist in combination.\n6. **Coverage and consistency**, in parallel:\n - a coverage gate checks every cluster and high-exposure blast-radius file\n was reviewed, and runs gap reviewers for what was not, at most 2 rounds;\n - consistency verification lists every cross-location obligation the\n changed code creates (what must be true elsewhere for this line to be\n correct), then verifies each by reading both ends. A broken obligation\n becomes a finding.\n7. **Synthesis**, code only:\n - score = severity weight (1.0, 0.7, 0.3, 0.1) × confidence × multipliers:\n compound 1.5, adversary-confirmed 1.3, adversary-challenged 0.5, likely\n machine-written PR 1.2, blast radius over 10 files 1.2;\n - drop findings under the severity's confidence floor: critical 0.2,\n important 0.3, suggestion 0.4, nitpick 0.4;\n - merge exact duplicates (file, overlapping lines, category) in code, and\n nearLine truncated
|
||||
"body": "# PR review agent\n\n**Status:** Approved\n**Authority:** `docs/architecture/agent-system.md`; supersedes the reviewer\nexecutor and blocking rule in `docs/architecture/adversarial-review.md`, and\nthe designs in `docs/prds/operator-pr-review.md` and\n`docs/prds/review-calibration.md`.\n**Compounds with:** `docs/prds/execution-tree-state-machine.md` (every agent\ncall is a StepExecution), `docs/prds/external-agent-harness.md` (any agent\nstep may run on a harness), `docs/prds/inline-review.md` (posting),\n`docs/prds/pr-review-remediation.md` (consumes the findings).\n\n## Decision\n\nArchie ships a pull request reviewer as its first end-to-end product. It\nreviews any pull request on a watched repository, a PR an operator names, and\narchie's own PRs before they open.\n\nThe reviewer is a fixed pipeline, not a single agent. The review strategy is\ngenerated per PR: three lens agents propose review dimensions from the PR's\ncontent, one reviewer definition runs once per dimension, and later agents\nverify, challenge and combine the findings. Everything that can be computed\nis code: diff parsing, clustering, blast radius, evidence extraction,\nscoring, deduplication, line mapping and the review event.\n\nThe pipeline is **recall-first**. It posts every evidenced finding above the\nconfidence threshold, up to the comment cap. A precision gate exists as an\noperator dial and is off by default.\n\nAcceptance is measured, not asserted: see Verification.\n\n## Pipeline\n\nEach numbered phase is a stage of the `pr-review` workflow. Each agent call is\nan `agent` StepExecution; fan-out phases record one child per call.\n\n1. **Intake.** Code reads the PR metadata and diff statistics: type,\n complexity, languages, areas touched, risk signals. Depth comes from lines\n changed: under 100 is `quick` (at most 3 dimensions), under 500 is\n `standard` (6), otherwise `deep` (12). An operator may set depth\n explicitly.\n2. **Anatomy.** Code parses the diff into files and hunks, clusters related\n files, and computes the blast radius: unchanged files that import or are\n imported by changed files. One agent writes the PR narrative, risk\n surfaces, changes that do not fit the narrative, and gaps between the\n description and the diff.\n3. **Dimension selection.** Three lens agents run in parallel over the intake\n (including its machine-written score), anatomy and diff, each able to read\n the repository. A PR that intake scores as likely machine-written adds a\n hallucination-check dimension: claims, citations and behaviour the diff\n does not actually implement.\n - **behaviour:** where the old and new code diverge for any input; API\n contracts, concurrency and state, security, error handling, data flow;\n - **mechanics:** whether the code runs at the language and framework\n level; types, signatures and every caller, decorators and middleware,\n framework contracts, imports;\n - **fit:** patterns, complexity, abstraction, test adequacy, documentation\n that no longer matches, dependencies, migration completeness.\n\n Each lens returns review dimensions: a name, a reviewer prompt written for\n this PR, target files, context files and a priority. Code merges them,\n drops duplicates and keeps the highest-priority dimensions up to the\n depth's cap.\n4. **Review.** One reviewer definition runs once per dimension, in parallel,\n at most 8 at a time. Each reads its target and context files and may\n follow references. Each finding carries file, line range, severity\n (`critical`, `important`, `suggestion`, `nitpick`), title, body, an\n optional suggested fix, quoted evidence, confidence and tags. A reviewer\n that exhausts its turn cap or deadline before its terminal tool call\n records a distinct StepExecution status from a reviewer that completed\n and found nothing; synthesis and the posted review treat the two\n differently (the former is unreviewed, the latter is reviewed-clean).\n5. **Verification layer**, over the review findings:\n - code extracts an evidence package per finding: the code at the cited\n lines and snippets from its callers;\n - an evidence verifier checks high-priority findings against their\n packages;\n - an adversary confirms or challenges each finding, looks for issues every\n reviewer missed, and is more sceptical when intake scores the PR as\n likely machine-written;\n - a compound agent looks, within each cluster of confirmed findings, for\n defects that only exist in combination.\n6. **Coverage and consistency**, in parallel:\n - a coverage gate checks every cluster and high-exposure blast-radius file\n was reviewed, and runs gap reviewers for what was not, at most 2 rounds;\n - consistency verification lists every cross-location obligation the\n changed code creates (what must be true elsewhere for this line to be\n correct), then verifies each by reading both endLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/pr-review-operator-response/",
|
||||
"title": "PR review: the operator's answer to the approval gate",
|
||||
"section": "PRDs",
|
||||
"body": "# PR review: the operator's answer to the approval gate\n\n**Status:** Draft\n**Authority:** `docs/prds/pr-review-agent.md` (\"Operator approval\") for the gate, and `docs/prds/state-store-contract.md` (rev. 2e) for every task field that crosses the State Store.\n**Compounds with:** `docs/prds/execution-tree-state-machine.md` (a run cannot resume partway through its stage list).\n\n## Decision 1 — where the operator answers\n\nThe dashboard's `POST /api/tasks/{id}/action` (`internal/webui/api_tasks.go`, `handleTaskAction`) is the authoritative surface: the only one that resolves the actor from a credential and can carry a payload. Chat is a shortcut, not a second authority — `/approve` (`internal/gateway/gateway.go`, `Router.handleApprove`) answers the post decision with every offered finding selected, and gains no instruction or selection syntax.\n\n`taskstate.Action` gains `rereview`, and `taskstate.Actions` returns `approve`, `reject` and `rereview` for `WaitingHuman`. `approve` posts the review, `reject` discards it through the existing terminal decline, `rereview` reruns the review phases with instructions. The action body carries `instructions`, required by `rereview`, and `findings`, the finding keys `approve` posts; an absent selection means all of them.\n\nThe path is `handleTaskAction` → `applyOperatorTaskAction` → `Chat.Contract.ApplyOperatorTaskAction` → the daemon's `LocalChatAdapter` → `taskactions.Client` (NATS `archie.gateway.task-action`) → `taskactions.Service.Apply` → one guarded store write that records the decision and requeues. Chat's `/approve` path (`StoreTaskController.Approve` → `chatTaskControllerAdapter.ApproveChatTask`) must reach that same write through the same function, so the two surfaces cannot record different decisions for one operator intent.\n\nA requeue resumes the workflow the waiting state names, never a name the handler hardcodes. `taskactions.Service.apply` and `chatTaskControllerAdapter.ApproveChatTask` requeue every approval under `implement`, which is the feasibility handoff: an approval whose wait recorded `pr-review` would run the implement workflow. Feasibility must keep that handoff by naming `implement` on the task before it enters the wait, which is the invariant the handler needs — the workflow a task carries is the workflow it runs next. `Requeue` treats an empty workflow as \"keep the task's\".\n\n### The review the operator answers\n\nThe gate writes the review it is holding onto the task before it ends the run: one JSON column, `review_gate`, a sibling of `review_payload`, holding the scored findings, the head SHA, the pull request's identity and the workflow the wait resumes. The run's existing `Store.Update` persists it. The same column carries the answer back: the response path's guarded write fills in the outcome, the selection and the instructions, and clears the offer for a re-review.\n\nThe operator reads the offer through the existing task read — `taskView.Task` on `GET /api/tasks` and `GET /api/tasks/{id}/debug` — so no new read endpoint is needed.\n\nThis record is load-bearing because the run that computed the findings ends at the gate and the engine cannot resume it partway. Without it, \"post the selected findings\" cannot mean the findings the operator saw: the resumed run recomputes them with agent calls. An `approve` resume therefore posts the recorded review filtered by the selection, and the review the resumed phases recompute never reaches the output.\n\n## Decision 2 — the cap\n\nThe cap is a column: `rereview_rounds` on `tasks`, `bigint NOT NULL DEFAULT 0`, read by the response path and incremented in the same guarded write that requeues a re-review. A re-review at the cap is refused with the conflict sentinel the dashboard answers 409 with, and nothing is requeued. Two is a constant in the domain, not a config knob: the PRD fixes it.\n\n`Task.Attempt` cannot carry the count, because it counts every requeue. The two alternatives are worse.\n\n- The execution tree measures passes through the gate, not operator requests. A crash recovery (`RecoverStale`) or an operator retry re-runs the pipeline to the gate and would consume the cap; and a stage has no step read (`task.Store` carries none), so this route needs a new interface method anyway.\n- `Task.Notes` is the agent memory ledger, not scratch. `AgentStage.buildRequest` passes it into every generic agent request, `agentexec` renders it as a prompt section, and `persistAppendedNotes` appends to it. A counter parsed out of a field agents write to is the encoded-state defect this repository rejects, and instructions parked there would reach every unrelated workflow's agents.\n\n`RemediationRounds` is the precedent: one writer, one reader, one meaning, kept separate from `RetryCount` so unrelated retries cannot draw a budget down.\n\nThe write crosses the State Store. A goose migration adds the column; `internal/infrastructure/postgres/queriesLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/pr-review-remediation/",
|
||||
@@ -444,11 +456,17 @@
|
||||
"section": "PRDs",
|
||||
"body": "# Review calibration -- decision\n\n**Status:** Draft\n**Beads issue:** `archie-core-h019.5` (parent `archie-core-h019`)\n\n\u003e Superseded by `docs/prds/pr-review-agent.md`.\n\nDecides the half of calibration `docs/prds/adversarial-self-review.md` left\nopen: \"the adversarial-confirmation mechanism that keeps a finding from\nsurfacing on a single reviewer's say-so.\"\n\n## The problem, precisely\n\nThe shipped contract (`internal/domain/workflow/review_findings.go`, h019.2)\nalready makes only a **confirmed** error-level finding block\n(`Blocking() == Verdict == confirmed \u0026\u0026 Level == error`), and a zero-finding\nreview is already distinguishable from one that never ran (`ReviewStatus`).\nWhat is missing is the other half: a reviewer can report _nothing_\nand say only \"I found nothing\" in free text. The operator cannot tell \"I\nchecked the five things that matter and they are clean\" from \"I did not look.\"\nThat is the failure the epic names -- a findings surface that consumes attention\nwithout earning trust.\n\n## Decisions\n\n### 1. \"Checked and cleared\" becomes structured, not prose\n\n`ReviewReport` gains `Checked []ReviewCheck`:\n\n```go\ntype ReviewCheck struct {\n Property string // what was verified clean, e.g. \"nil-safety of Foo callers\"\n Evidence string // how it was verified, e.g. \"read all 4 callers; each nil-checks\"\n}\n```\n\n`Evidence` is required, for the same reason `ReviewFinding.FailureScenario` is:\na check without evidence is an assertion, and the whole point is to separate a\nverified property from an unexamined one. A zero-finding review is credible\nonly when it lists what it checked.\n\n### 2. Report checks through a typed tool, like findings\n\nThe reviewer calls a new capture tool `record_checked` (mirroring\n`record_finding`) once per property it verified clean. The same environmental\nargument as findings applies: the reviewer cannot end its turn having silently\nskipped the checklist. `ReviewReport.Summary` stays as the human overview.\n\n### 3. Style nits are out of contract\n\nA finding must describe wrong behaviour or a crash. Style, formatting, naming,\nand preference nits are explicitly out of contract -- they are the padding that\ntrains the operator to skim. Stated in the reviewer prompt and in the\n`ReviewFinding` type's own documentation. Not machine-enforced: deciding \"is\nthis a style nit\" from free text is unreliable, and a wrong rejection is worse\nthan a tolerated one. The category enum already has no style bucket; the rule\ncloses the gap that would otherwise let one hide under `other`.\n\n### 4. Surfacing\n\nThe PR-body findings section lists the cleared properties alongside findings,\nso \"ran and found nothing\" arrives with its evidence. (Park reasons keep\nrendering only blocking findings -- what a human needs to act on, not the full\nchecklist.)\n\n## What this does not decide\n\n- Adding a second, independent reviewer pass. The verdict distinction plus the\n recorded checks is the confirmation mechanism; a second model pass is a\n separate, heavier decision and nothing in `h019.5` requires it.\n- How many findings can survive before `MaxSteps` is exhausted (a budget\n question, already satisfied by the per-stage budget).\n\n## Packages this touches\n\n- `internal/domain/workflow` -- `ReviewCheck`, `ReviewReport.Checked`, validation.\n- `internal/app/agentworker` -- `record_checked` tool, prompt rules.\n- `internal/domain/workflow/review.go` -- render cleared properties on the PR body.\n"
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/review-settings-resource/",
|
||||
"title": "Review settings resource",
|
||||
"section": "PRDs",
|
||||
"body": "# Review settings resource\n\n**Status:** Draft\n**Beads issue:** `archie-core-0ry6`\n**Authority:** `docs/prds/runtime-control-plane.md` for the resource model,\n`docs/architecture/configuration.md` for ownership, and\n`docs/prds/pr-review-agent.md` for what the two dials do.\n\n## Decision\n\n`review.precision_gate` and `review.approve_before_post` are one control-plane\nresource, `review-settings`. The file's `[review]` section seeds it, the stored\ndocument outranks the file from then on, and the dashboard writes it through the\nsame settings machinery as every other resource.\n\nThe resource is deployment-wide, like every definition the State Store seeds\n(`storecontract.DefaultOrgID`): not per-repository, per-identity, or per-run.\n\n## Why its own kind\n\nThe two dials are pr-review policy — what a review may post, and whether a human\ndecides — not a limit on a task run. The document that carries task limits\nbelongs to that feature. `runtime-control-plane.md` splits settings by feature\nand refuses documents unrelated features share; `configuration.md` puts a typed\nruntime setting with the domain whose behaviour it describes. One document per\nfeature is the rule, not one document per settings page.\n\nA new kind also has no legacy documents. Its first value is the seed derived\nfrom the file, so \"the store outranks the file\" begins from an explicit copy of\nboth fields rather than from a document that predates them.\n\n## Document\n\nNew file `internal/app/controlplane/review_settings.go`:\n\n```go\nconst ReviewSettingsKind = \"review-settings\"\n\ntype reviewSettings struct {\n PrecisionGate bool `json:\"precision_gate\"`\n ApproveBeforePost bool `json:\"approve_before_post\"`\n}\n```\n\nIts `Definition` sets `ApplyMode: \"live\"`, `Document: reviewSettings{}`, and a\n`Seed` returning `reviewSettings{cfg.Review.PrecisionGate, cfg.Review.ApproveBeforePost}`,\nand a `Validate` wrapping `validateAs`: both fields are free booleans with no cross-field\nrule, so the validator is a named place to put one rather than an inline no-op\n(`validatePluginSettings` is the precedent). No `Normalize`, because the kind\nhas no second wire shape to converge.\n\n## Seeding\n\n`ImportConfig`/`seededValues` write the seed for a kind the store does not hold,\nso a deployment that never edited the dials runs the values in `[review]`. Once\na document is stored, the file key stops mattering, which is the rule for every\ndatabase-owned setting.\n\n## Apply\n\n`runtimeConfigFrom` in `internal/app/controlplane/runtime_config.go` layers the\nstored document over the file's `Review`, assigning `out.Review.PrecisionGate`\nand `out.Review.ApproveBeforePost` field by field. Field-by-field, not\n`out.Review = ...`: a field added to `config.Review` later keeps the file's value\nuntil the document carries it.\n\n`ReviewSettingsKind` joins `runtimeResourceKinds` in\n`internal/app/archied/control_plane.go`, so a new stored version re-runs the\nlayering and republishes through `config.Holder`. Live rather than\nrestart-required, because every consumer re-reads it: `Review` is on\n`reloadableFields` in `internal/app/archied/reload.go`, and the value reaches a\nrun through `Daemon.configFor` → `Config.ForTask` → `TaskConfig.ToConfig` →\n`TaskContext.Cfg`, which `stagePRPrecisionGate` and `stagePROperatorApproval`\nread. The next task run uses the new value; a run in flight keeps the value it\nstarted with.\n\n## Projection and page\n\n`BuildConfigView` gains a plain `Review` field carrying both values out of\n`cfg.Review`, the way `BudgetsView` carries the layered budgets, so the published\nconfig snapshot tells any reader what is in force. The Review page renders the\ntwo toggles from the control-plane store's draft for `review-settings` — the\nshape `SystemTasksPage.vue` uses for `workflow-execution-settings` — and shows\nthe projected value beside them; a Settings route plus a `PAGE_RESOURCES` entry\n(`ui/src/stores/control-plane.ts`) bind the page to the kind.\n\nNothing else re-advertises them. `configFieldDescriptors` and `ConfigView.Schema`\ngain no `review.*` row: the config catalog's generic renderer was deleted, so a\ndescriptor row adds a field nothing can edit, which is the shape `becb0b5e`\nremoved.\n\n## What the test proves\n\n`internal/app/controlplane/runtime_config_test.go` adds the round trip that\nbuilds the effective config the way boot does: seed the kind from a file config\nwith both dials set one way, store a document with both flipped, layer it\nthrough `runtimeConfigFrom`, and assert the effective `cfg.Review` equals the\nstored document. A second case covers the absent kind, where the file's values\nstay in effect. The assertion is on `cfg.Review` — the value `TaskContext.Cfg`\ncarries into the two stages — not on a struct the test set directly.\n`TestRuntimeResourceKindsApplyLive` gains `review-settings` as live. The\nvalidator needs no `validators_agree_test.goLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/runtime-control-plane/",
|
||||
"title": "Runtime control plane",
|
||||
"section": "PRDs",
|
||||
"body": "# Runtime control plane\n\n**Status:** Approved \n**Date:** 2026-09-20 \n**Tracking:** `archie-core-j28m`, `archie-core-1786637498420-327-bacadaae`\n\n## Outcome\n\nArchie can be managed from the Web UI or a messaging channel. Both use the same\nAPI.\n\n## Model\n\nEach feature owns its settings and commands. The database stores them. There is\nno global configuration document.\n\nThis includes:\n\n- workflows;\n- identities and bindings;\n- providers and models;\n- repository policies;\n- channels and schedules;\n- capture mappings and bindings;\n- tool settings;\n- prompts and personas;\n- plugin settings.\n\nPlugin code remains installed code. Only its settings are stored in the\ndatabase.\n\nEach feature defines its data, validation, permissions, editor fields, and how\nchanges take effect. Each feature also defines its allowed actions. For example,\nidentities can be created, suspended, and retired.\n\nRepository and identity settings remain separate. They are not stored as large\nrecords that unrelated features must share.\n\nThe State Store process hosts the control-plane API on its existing gRPC server.\nNo new process is added. Feature code validates changes. Storage code only\nwrites versions and audit records.\n\nEvery write records who made it, where it came from, a request ID, and the\nversion being edited. The API layer sets the actor; the request body cannot.\nThe server validates the change, then writes it with its audit record. It rejects\nedits to an old version.\n\n## API\n\nThe API has four operations:\n\n1. **Catalogue** tells clients what can be viewed or changed and how to edit it.\n2. **Query** reads data and versions without exposing secrets.\n3. **Command** asks the owning feature to make a change.\n4. **Watch** streams changes and errors to clients.\n\nComplex features can use custom screens. They still use the same commands.\n\nA dashboard session or channel sender must map to an Archie identity before it\ncan run a command. Messaging syntax maps to the same commands as the Web UI.\n\n`archie-ui` receives only an API client. It does not receive a database handle,\ndaemon pointer, global configuration object, or secret value.\n\nThe database stores the requested settings. Each process reports the version it\nis using or why it failed. The UI shows both.\n\nSome changes require a restart. The UI shows them as pending. When a live change\nreplaces a running component, Archie starts and checks the new one before\nswitching. If the check fails, the old one keeps running.\n\n## Bootstrap, migration, and recovery\n\nBootstrap contains only the database path, listen addresses, credentials, TLS,\nand encryption-key references. State Store and control-plane RPCs use the same\nendpoint.\n\nWhen upgraded, existing instances are migrated to the database. Existing\ndatabase values are not overwritten. After migration, settings in TOML are\nignored and cannot block State Store startup.\n\nThe Web UI remains available when `archied` or Gateway is down. It shows failed\nchanges and can correct or roll them back.\n\nOffline commands can back up, restore, validate, and roll back the database.\nRecovery does not require `archied` or the Web UI. The database stores secret\nreferences, not secret values.\n\n## Workflows\n\nUsers create and edit workflows in the Web UI. Workflows are stored as versioned\nYAML. Built-in workflows can be overridden and restored.\n\nA workflow is a list of steps. Each step has a known type and its own settings.\nPlugins can add step types. Each run keeps the workflow version it started with.\n\nYaegi, `.archie/stages/*.go`, and `.archie/gate.go` will be removed. Their useful\nbehaviour must first be available as normal workflow steps.\n\n## First implementation\n\nThe first implementation makes task limits editable: maximum model steps,\nmaximum runtime, and maximum consecutive gate failures.\n\nIt includes:\n\n- validated task-limit fields;\n- version history and audit records;\n- the four API operations;\n- authenticated Web UI and messaging access;\n- live updates and apply status;\n- a Pinia-backed editor in the Web UI;\n- a messaging command using the same API;\n- migration of existing `[budgets]` values;\n- an end-to-end restart test.\n\nRunning tasks keep the limits they started with. New tasks use the latest applied\nversion. This replaces the old settings overlay instead of extending it.\n\n## Not included in the first implementation\n\n- Moving bootstrap or secret values into normal settings.\n- A generic JSON editor.\n- Rebuilding every settings screen at once.\n- Changing the limits of a running task.\n"
|
||||
"body": "# Runtime control plane\n\n**Status:** Approved \n**Date:** 2026-09-20 \n**Tracking:** `archie-core-j28m`, `archie-core-1786637498420-327-bacadaae`\n\n## Outcome\n\nArchie can be managed from the Web UI or a messaging channel. Both use the same\nAPI.\n\n## Model\n\nEach feature owns its settings and commands. The database stores them. There is\nno global configuration document.\n\nThis includes:\n\n- workflows;\n- identities and bindings;\n- providers and models;\n- repository policies;\n- channels and schedules;\n- capture mappings and bindings;\n- tool settings;\n- prompts and personas;\n- plugin settings.\n\nPlugin code remains installed code. Only its settings are stored in the\ndatabase.\n\nEach feature defines its data, validation, permissions, editor fields, and how\nchanges take effect. Each feature also defines its allowed actions. For example,\nidentities can be created, suspended, and retired.\n\nRepository and identity settings remain separate. They are not stored as large\nrecords that unrelated features must share.\n\nThe State Store process hosts the control-plane API on its existing gRPC server.\nNo new process is added. Feature code validates changes. Storage code only\nwrites versions and audit records.\n\nEvery write records who made it, where it came from, a request ID, and the\nversion being edited. The API layer sets the actor; the request body cannot.\nThe server validates the change, then writes it with its audit record. It rejects\nedits to an old version.\n\nThe request ID is the write's idempotency key, and it is scoped per org and\nper kind, never global. The key is `(org_id, kind, request_id)` — the unique\nindex `idx_resource_history_org_kind_request` (migration `0021_resources_per_org.sql`)\n— so replaying a request ID is the same org's prior write of the same kind, and\na request ID reused across orgs or across kinds is a separate write. This is the\nsame scoping as the task idempotency key `org/identity/owner/repo/number`\n(`docs/prds/orgs-and-access.md`).\n\n## API\n\nThe API has four operations:\n\n1. **Catalogue** tells clients what can be viewed or changed and how to edit it.\n2. **Query** reads data and versions without exposing secrets.\n3. **Command** asks the owning feature to make a change.\n4. **Watch** streams changes and errors to clients.\n\nComplex features can use custom screens. They still use the same commands.\n\nA dashboard session or channel sender must map to an Archie identity before it\ncan run a command. Messaging syntax maps to the same commands as the Web UI.\n\n`archie-ui` receives only an API client. It does not receive a database handle,\ndaemon pointer, global configuration object, or secret value.\n\nThe database stores the requested settings. Each process reports the version it\nis using or why it failed. The UI shows both.\n\nSome changes require a restart. The UI shows them as pending. When a live change\nreplaces a running component, Archie starts and checks the new one before\nswitching. If the check fails, the old one keeps running.\n\n## Bootstrap, migration, and recovery\n\nBootstrap contains only the database path, listen addresses, credentials, TLS,\nand encryption-key references. State Store and control-plane RPCs use the same\nendpoint.\n\nWhen upgraded, existing instances are migrated to the database. Existing\ndatabase values are not overwritten, with one exception: a resource whose\ndocument the build ships is refreshed when the seed itself wrote the stored\ncopy, because that copy is a previous release's document rather than an\noperator's. After migration, settings in TOML are ignored and cannot block\nState Store startup.\n\nThe Web UI remains available when `archied` or Gateway is down. It shows failed\nchanges and can correct or roll them back.\n\nOffline commands can back up, restore, validate, and roll back the database.\nRecovery does not require `archied` or the Web UI. The database stores secret\nreferences, not secret values.\n\n## Workflows\n\nUsers create and edit workflows in the Web UI. Workflows are stored as versioned\nYAML. Built-in workflows can be overridden and restored.\n\nA workflow is a list of steps. Each step has a known type and its own settings.\nPlugins can add step types. Each run keeps the workflow version it started with.\n\nYaegi, `.archie/stages/*.go`, and `.archie/gate.go` will be removed. Their useful\nbehaviour must first be available as normal workflow steps.\n\n## First implementation\n\nThe first implementation makes task limits editable: maximum model steps,\nmaximum runtime, and maximum consecutive gate failures.\n\nIt includes:\n\n- validated task-limit fields;\n- version history and audit records;\n- the four API operations;\n- authenticated Web UI and messaging access;\n- live updates and apply status;\n- a Pinia-backed editor in the Web UI;\n- a messaging command using the same API;\n- migration of existing `[budgets]` values;\n- an end-to-end restart test.\n\nRuLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/self-update-transaction/",
|
||||
@@ -480,11 +498,17 @@
|
||||
"section": "PRDs",
|
||||
"body": "# Skill curator (reference implementation) -- decision\n\n**Status:** Approved\n**Date:** 2026-09-02\n**Beads issue:** `archie-core-1786637499206`\n**Parent epic:** `archie-core-1786637500725` (curator engine)\n\n## Decision\n\nThe skill curator's v1 scope is **mechanical validation and safe\nnormalisation only** -- it never rewrites skill prose, never deletes a\nskill, and never calls the model. Each pass:\n\n1. Lists every skill under one configured root.\n2. Reads each `SKILL.md` and attempts to parse its frontmatter\n (`internal/skill.Parse`).\n3. Records an `Action` for any structural problem: a parse failure, or a\n missing `name`/`description` in the frontmatter that parsed.\n4. Normalises trivial whitespace (trailing whitespace per line, exactly\n one trailing newline) and writes back **only** when normalisation\n actually changes the bytes, recording an `Action` for that write.\n\nNothing here needs judgement. \"Review, prune, and improve\" -- the epic's\nframing -- is real for v1 but deliberately narrow: review is structural\nvalidation, improve is whitespace normalisation, and prune is _reporting_\na problem, never removing a skill. `Manifest.Skills = true` still marks\nthis curator agentic (existing `agentic()` rule), so it receives model\naccess from the registrar -- unused but nothing about the contract\nor the runtime needs to change to let a later version reason about\ncontent quality using it.\n\n## Why this scope, not more\n\nAn autonomous process that rewrites or deletes a user's skill content\nis a real risk with no undo path (no draft/approval flow for\ncurator writes exists yet, unlike the workflow engine's PR-based review).\nThe epic's own stated purpose for this issue is proving the curator\ncontract holds for a second, structurally different consumer than the\nsession-memory curator (files-as-skills vs. observations-as-memory), not\nsolving \"what makes a skill good.\" Mechanical validation is real,\nuseful, safe to run unattended, and fully exercises\nList/Read/Write -- every method `curator.SkillStore` declares except\n`Delete`, which this curator's Pass never has a safe reason to call in\nv1 (kept implemented on the store adapter regardless, since the\ninterface requires it and a future consumer may).\n\n## Why `internal/skill` isn't `curator.SkillStore` directly\n\n`internal/skill.Discover` parses every `SKILL.md` under a root and\nreturns an error for the **whole** call if any one of them fails to\nparse -- the read side was built for \"load the catalogue to start the\ndaemon,\" where one bad skill failing the whole boot is arguably correct,\nnot for \"review each skill and report what's wrong with it\nindividually.\" A per-skill parse failure must become one `Action`, not\nabort the pass before any skill is reviewed. So\n`internal/infrastructure/skillcurator` gets its own thin store adapter\nthat lists raw directory names and reads/writes raw `SKILL.md` bytes\nper name; the skill curator itself calls `internal/skill.Parse` on each\none, isolated per skill.\n\n## Root scope\n\nOne root only, resolved the same way `loadWorkflows` already resolves\n`skillsBase` (`cfg.SkillsDir`, falling back to `cfg.WorkDir`) -- not\nevery root `skill.CatalogRoots`/`DefaultRoots` would read for a model\n(which layers a shared dir over the per-profile one). Write and Delete\nneed one unambiguous target; a curator that could write into a shared,\nmulti-tenant skills directory is a bigger decision than this issue\ncovers. The model still sees the full multi-root catalogue through the\nexisting read path -- this curator only maintains the local one.\n\n## Shape\n\n### `internal/infrastructure/skillcurator/store.go`\n\n```go\n// Store implements curator.SkillStore over one root directory's\n// .agents/skills/*/SKILL.md files, tolerating a per-skill parse failure\n// as the curator's problem to report rather than this store's problem\n// to abort on.\ntype Store struct { root string }\n\nfunc NewStore(root string) *Store\n\nfunc (s *Store) List(ctx context.Context) ([]curator.SkillRef, error)\nfunc (s *Store) Read(ctx context.Context, name string) (curator.Skill, error)\nfunc (s *Store) Write(ctx context.Context, sk curator.Skill) error\nfunc (s *Store) Delete(ctx context.Context, name string) error\n```\n\n`Read` best-effort parses frontmatter for `Skill.Description` (empty on\nparse failure -- not this method's job to report that; `Pass` does, via\nits own `skill.Parse` call on `Skill.Content`). `Write` rejects a name\nthat does not already exist as a directory (this store curates existing\nskills; creating a new one is out of scope). `Delete` removes the whole\nskill directory, matching \"delete a skill,\" not just `SKILL.md`.\n\n### `internal/infrastructure/skillcurator/skillcurator.go`\n\n```go\n// Curator implements domain/curator.CuratorEngine. See\n// docs/prds/skill-curator.md for what a pass does and why.\ntype Curator struct { /* unexported: registrar view, interval *Line truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/soul/",
|
||||
"title": "SOUL: an agent's user-authored personality",
|
||||
"section": "PRDs",
|
||||
"body": "# SOUL: an agent's user-authored personality\n\n**Status:** Draft\n**Authority:** `docs/architecture/identity.md`, “Three-layer identity model”;\n`docs/prds/orgs-and-access.md` for identity and org ownership.\n\n## Decision\n\nSOUL supplies an agent's name, register and warmth. It belongs to the agent's\nimmutable `IdentityID`, not its session, model, installation or container\nprofile. Rename preserves it; changing a profile does not change who acts.\nSOUL never changes attribution, credentials, grants or identity lifecycle.\n`config.AgentProfile` remains an execution environment, not another identity.\n\nUse the existing three layers: invariants, user-authored SOUL, and curator-derived\nrepresentation. Curators may propose SOUL changes but never apply them.\n\n## Files and ownership\n\nThe config directory is `${XDG_CONFIG_HOME:-~/.config}/archie`, or the directory\nof an explicitly selected config file. The default/root agent uses `SOUL.md`\ndirectly there; additional agents use `agents/\u003cidentity-id\u003e/SOUL.md`. The root is\nthe identity selected by application composition, never the initiating user or\na session's personality selection. No file creates or selects an identity.\n\nThe common case keeps a human-friendly filename; additional agents get separate\nasset directories, following `.agents/skills/\u003cname\u003e/SKILL.md` without confusing\nthese directories with `[containers.profiles.\u003cname\u003e]`. Reject display-name or\nslug directories: rename and same-name agents across orgs would require another\nname-resolution rule. Immutable IDs avoid both problems without an org directory.\n\nWhen a file-owned agent's file is absent, create the shipped default with\nexclusive creation. Never overwrite an existing file, including an empty one.\nA creation failure still permits the turn using the embedded shipped default.\nShip that document independently of `agent.ShippedPersonas`, so deleting personas\ncannot delete the fallback.\n\nResolve once at the start of every new generation:\n\n1. A stored SOUL entry for the acting identity is authoritative.\n2. Without an entry, read that identity's file again.\n3. An absent, empty, unreadable or invalid selected source uses the shipped default.\n\nThe first explicit dashboard/API save takes ownership permanently. Thereafter\nfile edits are ignored: emit one ownership notice and show the owning stored\nversion in the dashboard. Restoring the shipped default writes a stored value;\nit does not remove ownership. Refuse writes that remove an owned entry.\n\nThis ownership boundary is the design's one stateful rule. Files seed the\neditable value, not an automatic durable import. Reject seed-once import because\nit breaks next-message file editing; reject file-always-wins because it makes\ndashboard saves ineffective. Neither a restart nor an upgrade overwrites an\nowned value, following the precedence of `controlplane.AgentProfileKind` without\ncopying its startup import timing.\n\n## Prompt and failure contract\n\nKeep `archie.md.tpl`'s XML-escaped\n`\u003csoul purpose=\"identity_and_style\" trust=\"data\"\u003e` block before\n`\u003cinstruction_precedence\u003e`. SOUL is style reference data; the invariant sections,\ntool inventory and runtime metadata remain authoritative and uneditable.\nPreserve `TestBuildSystemPromptSoulCannotOverrideInvariants`.\n\nAccept UTF-8 plain Markdown with at most 8 KiB in its XML-escaped body. This bounds\npersonality to a small prompt contribution; count the complete rendered prompt\nin the turn's context budget and never truncate invariant sections. Bound file\nreads before decoding; reject oversize input rather than truncating instructions.\nFile and stored writes use the same validator; an invalid save leaves the stored\nversion unchanged. The shipped default must pass that validator.\n\nRead and creation errors never fail a turn. Log once per identity/source failure\nepisode, retry on the next turn, and allow a new warning after recovery. If the\nstore cannot establish whether an owned entry exists, use the shipped default,\nnot a potentially shadowed file. Do not log SOUL text. Each turn keeps its resolved\nsnapshot; edits affect the next generation without restart or SIGHUP.\n\n## Cross-layer delivery\n\n- `internal/domain/agent` owns SOUL content validation and the identity-keyed read\n contract; `internal/domain/identity` remains the actor/lifecycle authority.\n- The configuration infrastructure resolves the config directory and handles\n file discovery, exclusive default creation and bounded per-turn reads.\n Application composition resolves the acting `IdentityID` through the existing\n identity repository/bindings and supplies it to the gateway.\n- Register `SoulKind` (`agent-souls`) in the control plane with a live descriptor\n and an org-scoped document mapping identity IDs to `{text}`. Persist it through\n the State Store's existing resource/history contracts, not a new table,\nLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/state-store-contract/",
|
||||
"title": "State Store — contract boundary \u0026 transport (ratification)",
|
||||
"section": "PRDs",
|
||||
"body": "# State Store — contract boundary \u0026 transport (ratification)\n\n**Status:** Approved\n**Revision:** 2e\n**Date:** 2026-09-06\n\nThis is the pre-implementation design document that Phase 2 subtasks `.4.2` (generalise\n`storerpc` as the State Store gRPC contract) and `.4.3` (stand up `archie-state-store`)\nimplement against.\n**Beads milestone:** archie-core-8cda.4.1\n**Parent:** `docs/prds/service-decomposition.md` (open-question Q4 **RESOLVED**)\n\nThis document fixes the **contract boundary** and **transport** for the State Store service.\nIt does not redesign Archie's domain model, does not invent a second store, and does **not**\nsplit `archie.db`. It records method ownership, DTO/wire representation, error semantics,\nlimits, mode/config shape, local-adapter compatibility, and cutover/deletion rules so that\n`.4.2` and `.4.3` have exactly one authoritative surface to build against.\n\n\u003e **Storage superseded.** The store behind this contract is PostgreSQL:\n\u003e `internal/infrastructure/postgres` implements the producer-owned interfaces in\n\u003e `internal/domain/storecontract` and `workflow.Store`, over the database\n\u003e `database_url` names. `internal/store`, the SQLite file and the local adapter\n\u003e are gone; where this document says `archie.db`, `*store.Store` or\n\u003e `internal/store`, read the State Store's PostgreSQL database and\n\u003e `internal/infrastructure/postgres`. The contract, ownership split, error\n\u003e semantics and cutover rules stand.\n\n\u003e **Current state — read before `.4.2` starts.** The §12 step 2 relocation (`archie-core-8cda.\n4.8`) has landed: `Task`/`Status*`/`Source*` and the 3-method `workflow.Store` now live in\n\u003e `internal/domain/workflow`, the six production workflow files import no `internal/store`\n\u003e symbol, and `storerpc`/the NATS transport assert against `workflow.Store` instead of\n\u003e `store.WorkflowStore`. The broader Phase 2 acceptance criterion (State Store as its own\n\u003e service behind gRPC) is still open — that is what `.4.2`/`.4.3` build next.\n\n\u003e **Relationship to migration-decisions §4 — not replaced.** `docs/architecture/\nmigration-decisions.md` §4 (`store.Task → WorkflowExecution`, `mutable Stage →\nStepExecution history`, `RetryCount/Attempt → Attempt records`, versioned Workflow defs)\n\u003e **remains the authoritative, open document for the long-term Workflow migration.** This PRD\n\u003e does **not** replace it. It only pulls the minimal `Task`/`Status`/`Source` type + interface\n\u003e relocation forward as a Phase 2 prerequisite (because the acceptance criterion requires it);\n\u003e the rest of §4 stays its own migration and stays open.\n\n---\n\n## 1. Decision (the invariant everything follows)\n\nArchie is composed such that a single **`archie-state-store`** service owns the one existing\nSQLite file (`archie.db`) and exposes it over **gRPC behind narrow typed contracts**. There is\nexactly one store, one file, one service. No database-per-service, no distributed\ntransactions, no second store abstraction.\n\nTwo adapter families satisfy the contract interfaces:\n\n- **Local adapter** — `*store.Store` (the in-process SQLite implementation).\n- **Remote adapter** — `*staterpc.Client` (wraps the generated gRPC client).\n\nEach adapter carries an explicit compile-time assertion against the contract interfaces it\nserves. Composition picks local vs. remote by the presence of `[services.state].target`\n(empty = local; set = dial the gRPC service). Default is **local** (the State Store is not yet\nextracted), which is the PRD §3 posture; it differs from the gateway's remote-default only\nbecause the gateway is already a separate deployment and the State Store is not.\n\n\u003e **Contract-ownership fork, decided (rev. 2c — resolves the domain contradiction).**\n\u003e Ownership splits by the consumer's _layer_, per the dependency contract's rule #2\n\u003e (\"a domain defines the smallest interfaces required to perform its work\") and rule #7\n\u003e (\"database rows … MUST NOT leak into domain models\"):\n\u003e\n\u003e - The **workflow domain** (`internal/domain/workflow`) is the only domain-layer consumer of\n\u003e store state. It defines its own **consumer-owned** narrow `Store` interface\n\u003e (Update/Transition/InsertEvent) and its own **domain-owned** `Task` type plus\n\u003e `Status`/`Source` vocabulary. It imports **zero** `internal/store` symbols — satisfying the\n\u003e Phase 2 acceptance criterion. This is the minimal bound of migration-decisions §4\n\u003e (`store.Task → WorkflowExecution`), pulled forward **because** the acceptance criterion\n\u003e requires it.\n\u003e - The **daemon / webui / intake** store surfaces (`TaskStore`, `CaptureStore`,\n\u003e `MappingStore`, `BindingStore`, `BindingDispatcher`, `BindingTaskCreator`) stay\n\u003e **producer-owned** in `internal/store`, because those consumers are application Line truncated
|
||||
"body": "# State Store — contract boundary \u0026 transport (ratification)\n\n**Status:** Approved\n**Revision:** 2e\n**Date:** 2026-09-06\n\nThis is the pre-implementation design document that Phase 2 subtasks `.4.2` (generalise\n`storerpc` as the State Store gRPC contract) and `.4.3` (stand up `archie-state-store`)\nimplement against.\n**Beads milestone:** archie-core-8cda.4.1\n**Parent:** `docs/prds/service-decomposition.md` (open-question Q4 **RESOLVED**)\n\nThis document fixes the **contract boundary** and **transport** for the State Store service.\nIt does not redesign Archie's domain model, does not invent a second store, and does **not**\nsplit `archie.db`. It records method ownership, DTO/wire representation, error semantics,\nlimits, mode/config shape, local-adapter compatibility, and cutover/deletion rules so that\n`.4.2` and `.4.3` have exactly one authoritative surface to build against.\n\n\u003e **Storage superseded.** The store behind this contract is PostgreSQL:\n\u003e `internal/infrastructure/postgres` implements the producer-owned interfaces in\n\u003e `internal/domain/storecontract` and `workflow.Store`, over the database\n\u003e `database_url` names. `internal/store`, the SQLite file and the local adapter\n\u003e are gone; where this document says `archie.db`, `*store.Store` or\n\u003e `internal/store`, read the State Store's PostgreSQL database and\n\u003e `internal/infrastructure/postgres`. The contract, ownership split, error\n\u003e semantics and cutover rules stand.\n\n\u003e **Current state — read before `.4.2` starts.** The §12 step 2 relocation (`archie-core-8cda.\n4.8`) has landed: `Task`/`Status*`/`Source*` and the 3-method `workflow.Store` now live in\n\u003e `internal/domain/workflow`, the six production workflow files import no `internal/store`\n\u003e symbol, and `storerpc`/the NATS transport assert against `workflow.Store` instead of\n\u003e `store.WorkflowStore`. The broader Phase 2 acceptance criterion (State Store as its own\n\u003e service behind gRPC) is still open — that is what `.4.2`/`.4.3` build next.\n\n\u003e **Relationship to migration-decisions §4 — not replaced.** `docs/architecture/\nmigration-decisions.md` §4 (`store.Task → WorkflowExecution`, `mutable Stage →\nStepExecution history`, `RetryCount/Attempt → Attempt records`, versioned Workflow defs)\n\u003e **remains the authoritative, open document for the long-term Workflow migration.** This PRD\n\u003e does **not** replace it. It only pulls the minimal `Task`/`Status`/`Source` type + interface\n\u003e relocation forward as a Phase 2 prerequisite (because the acceptance criterion requires it);\n\u003e the rest of §4 stays its own migration and stays open.\n\n---\n\n## 1. Decision (the invariant everything follows)\n\nArchie is composed such that a single **`archie-state-store`** service owns the one existing\nSQLite file (`archie.db`) and exposes it over **gRPC behind narrow typed contracts**. There is\nexactly one store, one file, one service. No database-per-service, no distributed\ntransactions, no second store abstraction.\n\nTwo adapter families satisfy the contract interfaces:\n\n- **Local adapter** — `*store.Store` (the in-process SQLite implementation).\n- **Remote adapter** — `*staterpc.Client` (wraps the generated gRPC client).\n\nEach adapter carries an explicit compile-time assertion against the contract interfaces it\nserves. Composition picks local vs. remote by the presence of `[services.state].target`\n(empty = local; set = dial the gRPC service). Default is **local** (the State Store is not yet\nextracted), which is the PRD §3 posture; it differs from the gateway's remote-default only\nbecause the gateway is already a separate deployment and the State Store is not.\n\n\u003e **Contract-ownership fork, decided (rev. 2c — resolves the domain contradiction).**\n\u003e Ownership splits by the consumer's _layer_, per the dependency contract's rule #2\n\u003e (\"a domain defines the smallest interfaces required to perform its work\") and rule #7\n\u003e (\"database rows … MUST NOT leak into domain models\"):\n\u003e\n\u003e - The **workflow domain** (`internal/domain/workflow`) is the only domain-layer consumer of\n\u003e store state. It defines its own **consumer-owned** narrow `Store` interface\n\u003e (Update/Transition/InsertEvent) and its own **domain-owned** `Task` type plus\n\u003e `Status`/`Source` vocabulary. It imports **zero** `internal/store` symbols — satisfying the\n\u003e Phase 2 acceptance criterion. This is the minimal bound of migration-decisions §4\n\u003e (`store.Task → WorkflowExecution`), pulled forward **because** the acceptance criterion\n\u003e requires it.\n\u003e - The **daemon / webui / intake** store surfaces (`TaskStore`, `CaptureStore`,\n\u003e `MappingStore`, `BindingStore`, `BindingDispatcher`, `BindingTaskCreator`) stay\n\u003e **producer-owned** in `internal/store`, because those consumers are application Line truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/status-health-surface/",
|
||||
@@ -533,6 +557,24 @@
|
||||
"title": "Webhook intake security -- decision",
|
||||
"section": "PRDs",
|
||||
"body": "# Webhook intake security -- decision\n\n**Status:** Approved\n**Date:** 2026-08-22\n**Beads issue:** `archie-core-t2db.5`, blocks `archie-core-t2db.4`\n\n## Why this is decided ahead of the code it constrains\n\n`archie-core-t2db` (no-code playbooks) and `archie-core-7d5u` (typed event\nsources) both land a public intake surface whose eventual output is an agent\nwith tool access and a repo. Neither capture (`t2db.1`) nor the intake family\n(`7d5u.3`) has shipped yet, so this decision exists to be a contract the two\nepics build against, not a retrofit once the surface exists. A webhook URL\nthat can start an agent is remote code execution with extra steps if any of\nthe five points below is missing on day one.\n\n## 1. Per-source authentication\n\nReuse the per-route HMAC-SHA256 scheme already in\n`internal/channels/webhook/webhook.go` (`validateHMAC`), unchanged: a source\nregisters with a shared secret; the signature is checked against the raw\nbody. Do not invent a second scheme for intake.\n\n**Capture and triggering split at the signature, not at a separate flag.** An\nevent with a missing or invalid signature is still captured (visible in the\ninspector, marked unauthenticated) so an operator can diagnose a\nmisconfigured sender -- but an unauthenticated event can never be matched\nagainst a binding. Authentication is what promotes an event from \"something\narrived\" to \"something that can run a workflow.\"\n\n## 2. Human approval before a binding arms\n\nA binding has three states: `draft -\u003e pending_approval -\u003e armed`. Only\n`armed` bindings are evaluated against incoming events. Creating or editing a\nbinding's matcher, mapping, or target workflow always sets it to\n`pending_approval`, including edits to an already-armed binding -- an edit is\nnot silently re-armed, or the approval gate is decorative. Approval requires\nan authenticated dashboard session; there is no unattended approval path.\n\nModel: `internal/channels/telegram`'s dangerous-command approval flow\n(`dangerousAction` / `pendingApproval` in `dangerous.go` / `approval.go`) is\nthe existing precedent for \"a human decision gates code from running\" in this\ncodebase -- follow its shape rather than designing a new approval primitive.\n\n## 3. Rate and volume limits, per source\n\nA token-bucket limiter keyed by source ID, not global -- one noisy or hostile\nsender must not exhaust another source's capture budget. Precedent for\nper-key volume capping: `internal/pairing/store.go`'s `MaxPendingPerPlatform`.\n\nOn limit exceeded, the request is rejected (HTTP 429), not silently dropped.\nA silently dropped event is indistinguishable from a sender that never fired\n-- the same invisible-failure shape the update-verification work\n(`archie-core-522`) exists to prevent. The rejection itself is observable in\nthe inspector as a distinct outcome from \"not received.\"\n\n## 4. Blast radius bounded by code, not by prompt wording\n\nA playbook-triggered task runs through exactly the same enforcement as every\nother task: the `[[repos.gate]]` quality gate, `diff_cap_lines`, the\nsandboxed per-task container (`internal/container`), worktree isolation, and\n\"the model never runs git.\" No new relaxation is introduced for\nplaybook-triggered work, and none is needed -- the existing constraints are\nthe control.\n\nMapped payload fields are treated as ordinary user-controlled text inside an\nagent prompt, exactly like an inbound chat message never as trusted\ninstructions. \"The agent should ignore instructions in the payload\" is not a\ncontrol and must not appear as one anywhere in this feature -- per the\nenvironmental-enforcement principle (`docs/architecture/agent-system.md`,\n\"Existing invariants to preserve\"), the boundary is the gate and the sandbox,\nnot a sentence in the system prompt.\n\n## 5. Retention and redaction of captured payloads\n\n**Retention:** captured events (bound or not) are purged after 7 days,\nconfigurable per deployment. Unbound events exist to be mapped against; nothing\njustifies keeping them indefinitely once that window has passed, and an\nunbounded capture store is the same disk-exhaustion risk item 3 addresses at\nthe request-rate level.\n\n**Redaction:** before a captured payload is persisted, apply the same\nkey-name heuristic `internal/gateway/stream.go`'s `sensitiveParameterKey`\nalready uses for tool-call parameters (matches `token`, `secret`, `password`,\n`passwd`, `api_key`, `apikey`, `authorization`, `credential`, `cookie`,\n`private_key` against normalised JSON keys) and replace matching values with\nthe same `[redacted]` marker. This is best-effort, not a guarantee -- a\nsender that names a secret field something the heuristic misses will still\nhave it captured. Document that limitation where captured payloads are\ndisplayed, rather than implying the redaction is complete.\n\n**Visibility:** captured payloads, redacted or not, are visible only to an\nauthenticated dashboarLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/workflow-call-outputs/",
|
||||
"title": "Declared outputs of a workflow run",
|
||||
"section": "PRDs",
|
||||
"body": "# Declared outputs of a workflow run\n\n**Status:** Draft\n**Date:** 2026-09-30\n**Bead:** `archie-core-t2db.43`\n**Authority:** `docs/prds/event-automation.md` for what a declared output is,\n`docs/prds/workflow-calls.md` for the call and its grants,\n`docs/prds/state-store-contract.md` for the State Store contract the wire\nchange must satisfy.\n**Supersedes:** `docs/prds/workflow-calls.md`, \"Waiting on the callee\": the\ncallee's transition detail is the human summary, not the stand-in for\nstructured outputs.\n\nA workflow declares named, typed outputs. A run writes each one once. A\n`wait: true` caller receives them, and may publish one as its own.\n\n## Where outputs are declared\n\n`outputs:` on the workflow definition, beside `inputs:`, decoded into\n`task.WorkflowInterface.Outputs map[string]OutputSpec` where\n`OutputSpec{Type, Required}`:\n\n```yaml\nid: firewall-contain\noutputs:\n contained: { type: bool, required: true }\n summary: { type: string }\n```\n\nNames and types are the input grammar: the same identifier shape, the same\ntype set, and the same check in `WorkflowInterface.Validate`, which both\n`ParseDefinition` and `ParseWorkflowInterface` call.\n\n**Forced by:** `ParseDefinition` decodes with `KnownFields(true)`, so a key no\ndecoded struct declares is refused — the declaration must live on\n`WorkflowInterface` for an author to write it at all, and that is where\n`docs/development/workflows.md` puts every field a process without the engine\nmust read. The type set is the shared value vocabulary: `TypeAccepts` and\n`ValueType` already check a mapped parameter and an input with it. `required`\ndefaults to false, and the generated YAML for a builtin that declares no\noutputs is unchanged, because a definition's digest pins a run.\n\n**Rejected:** outputs per step, or per call step, because a workflow returns a\nresult as itself rather than as one of its stages. Also `task.Definition`\ngaining outputs: no reader needs them — a binding offers inputs, and a call's\noutputs assignment is checked against the callee's YAML in the same\ncollection — and a declared field with no reader parses and does nothing.\n\n## How a run writes one\n\nEach declared output is offered to the run's agent stages as a capture tool\nnamed after the output, whose arguments are `{\"value\": ...}`; the accepted\ncall's `value` member is the output's value. The engine holds the accepted\nvalues on the task context and writes them into its own task row in the\n`Store.Update` call the run already makes. A deterministic stage may set the\nsame values in Go, and the run's finish check validates them identically.\n\n**Forced by:** a run's only structured results are capture calls\n(`agentexec.CaptureTool`, `Result.Captures`), and the workflow interface\nalready declares when a stage needs them (`task.WorkflowNeeds.Captures`).\nDeriving the tools from the declaration means an output cannot be written\nunder a name nobody declared, and it keeps one route to structured agent\noutput rather than adding a second beside the capture path. The row write is\nthe run's existing write: the task row is where a run's own state lives, and\nthe container already holds `Update` on its own row.\n\nThe tool is offered with `MaxCalls: 1`, and a stage is not offered an output\nthe run has written, so a run writes each output once: a repeat within a stage\nis answered with the tool's rejection and the agent carries on, and a later\nstage cannot overwrite a value. A stage's own capture tool may not share a\nname with a declared output, because the value would otherwise be ambiguous.\n\n**Rejected:** a `workflow.output` step type, because assigning the run's\nresult from a step needs a grammar for \"the previous stage's result\" that does\nnot exist, and a step that reaches the agent would be the second path\n`docs/development/workflows.md` forbids. Also a write RPC of its own: the\ncontainer's `Update` already reaches its own row, and a second write verb for\none column is a second thing to keep in step.\n\n## How a caller receives one\n\nOn a successful `wait: true` call the caller's stage holds the callee's\noutputs as a `map[string]any`. A call step's `outputs:` setting publishes one\nas one of the caller's own outputs:\n\n```yaml\nsteps:\n - type: workflow.call\n workflow: firewall-contain\n wait: true\n inputs: { src_ip: inputs.src_ip }\n outputs: { contained: outputs.contained }\n```\n\nThe key names the callee's declared name; the value names one of the caller's\nown with the prefix the call's `inputs:` already uses. A published value joins\nthe caller's output set for its run, so a caller returns its callee's result to\nits own caller, and a run may publish a callee's output and write its own\nothers.\n\nLifetime is the attempt. The run starts with an empty output set, every later\nstage of that attempt sees the values, and the finish write replaces the row's\nset wholesale — so nothing an attemLine truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/workflow-calls/",
|
||||
"title": "Workflows calling workflows",
|
||||
"section": "PRDs",
|
||||
"body": "# Workflows calling workflows\n\n**Status:** Draft\n**Date:** 2026-09-26\n**Bead:** `archie-core-t2db.41`\n**Extends:** `docs/prds/event-automation.md` (workflow/binding/profile model), `docs/prds/state-store-contract.md` (two new RPCs), `docs/prds/execution-tree-state-machine.md` (call kind)\n\n## The call, end to end\n\n```\ncaller run (in agent container)\n workflow.call step ──StartCall──▶ State Store EnqueueCallTask(caller, workflow, inputs)\n │ callee task row: org/identity/owner/repo\n │ derived from the caller row server-side\n ▼\n callee task (queued, org of the caller)\n │ daemon claims, pins the callee's OWN\n │ definition → its OWN agent profile\n ▼\n callee run (its own container, own tree)\n wait: true ──poll──▶ State Store WorkflowCallStatus(caller, callee)\n wait: false ──continue\n```\n\nA `workflow.call` step starts the callee as a first-class task and, with\n`wait: true`, waits for its terminal state. The callee is never run \"inside\"\nthe caller: it gets its own task row, its own pinned definition, its own\nprofile, its own container, and its own outcome on its own run\n(`execution-tree-state-machine.md`).\n\n## Save-time checks (the collection is the authority)\n\nAll semantic checks run in `workflow.ValidateDefinitionCollection`, the gate\nevery save and load of the `workflow-definitions` resource passes through.\nA single-definition parse cannot see callees, so it validates shape only.\n\n- **Callee exists.** A call to a workflow outside the collection is refused.\n- **Inputs checked.** A call value is a literal or a reference\n (`inputs.\u003cname\u003e`) to the calling workflow's declared input. References must\n name a declared input; the resolved type must satisfy the callee's declared\n type; unknown callee inputs are refused; a required callee input must be\n assigned.\n- **Self-calls refused.** The call graph over the collection is walked from\n every workflow; a workflow that reaches itself, directly or through other\n workflows, is refused with the cycle path. (Cycles can otherwise deadlock:\n `wait: true` callers hold their containers.)\n- **Repository.** `workflow.call` needs no repository, so it is legal in a\n `repository: none` workflow: the callee inherits the caller's task record\n (owner/repo/identity/org), and the callee's own `repository` mode decides\n whether its run clones.\n- **Org enablement** (bead `archie-core-t2db.42`): the single\n instance-wide collection the current model serves is what \"enabled for\n the caller's org\" resolves against — an undefined callee parks. The\n callee's org is derived from the caller's row, so a callee is never\n visible outside its caller's org. The per-org enable/disable catalogue\n lands with `archie-core-t2db.42` and becomes the one source of this\n predicate.\n\n## Runtime\n\n**Depth limit.** `workflow.MaxCallDepth` (5). The calling stage refuses a call\nthat would exceed it; the store re-checks on insert (callee depth = caller\ndepth + 1), so no path can enqueue past the limit.\n\n**Starting the callee.** The caller runs inside a container whose task-scoped\nState Store grant authorizes only `Update`/`Transition`/`InsertEvent` on its\nown task — it can neither enqueue a task nor read another one. One new\ncontract RPC starts the callee:\n\n- `EnqueueCallTask(caller_task_id, workflow, inputs_json) → task`\n — the store reads the caller row, refuses a caller that is not `running`,\n refuses past the depth limit, and inserts the callee row deriving org,\n workspace, identity, owner, repo and a fresh synthetic issue number from\n the caller (the same org COALESCE `EnqueueIssue`/`InsertChatTask` use). The\n callee row carries `call_parent_task_id` and `call_depth`.\n\n**Waiting on the callee.** One new read RPC returns a call's callee:\n\n- `WorkflowCallStatus(caller_task_id, call_task_id) → (status, detail)` — the\n handler verifies `call_parent_task_id` matches, so a caller reads only its\n own callees, and returns the callee's status plus its latest transition\n detail (the callee's summary — the wait:true \"outputs\" until a structured\n outputs model lands).\n\nBoth RPCs are admitted to task-scoped grants on `caller_task_id == granted\ntask ID` (`authorizesTaskScopedCall` gains two request-shape cases). This is\nthe one sanctioned widening of a task grant: the callee is the caller's child,\nand starting it is the mechanism by which one event becomes several runs. The\nwidenings stay request-shape checks; the parent-child authorization is a\nhandler-side row check, so the interceptor never reads the database.\n\n**Schema.** `tasks` gains Line truncated
|
||||
},
|
||||
{
|
||||
"url": "/dev/prds/workflow-step-vocabulary/",
|
||||
"title": "Workflow step vocabulary: what a step type is and how binaries agree on it",
|
||||
"section": "PRDs",
|
||||
"body": "# Workflow step vocabulary: what a step type is and how binaries agree on it\n\n**Status:** Draft\n**Date:** 2026-09-29\n**Beads:** `archie-core-m7oc` (agreement between separately deployed binaries), `archie-core-ze7y` (the deleted `.archie/stages/*.go` equivalent)\n**Extends:** `docs/architecture/plugins-and-extensions.md` (plugin engine rule), `docs/prds/event-automation.md` (the workflow model step types serve)\n\n**Authority:** `docs/architecture/plugins-and-extensions.md` — the workflow step vocabulary is a Workflow capability family, and its extension point follows the plugin engine rule.\n\n## Decision\n\nA workflow step type is a named Go factory: the word a YAML workflow writes in\na step's `type` field, plus the factory that builds its stage. The name is a\nstable identifier; the identity also declares what plugin family claims it,\nso a contribution that shadows a shipped stage is refused instead of\noverriding it.\n\nThe Workflow domain owns the typed family contract — `StepTypeProvider` for a\ncontribution and `Manager` as the owning registry. A provider contributes a\nwhole set of step types under its own stable-identifier name; the manager\nvalidates the entire contribution before applying any of it (named provider,\nwell-formed step-type names, non-nil factories, no step type claimed twice,\nno claim on a name another provider holds) and applies it atomically. The\ngeneric `plugin.Plugin` contract stays metadata-only.\n\nThe vocabulary is a compiled-in, closed set. `internal/infrastructure/workflowsteps`\nis the one place a step type is bundled into any binary that resolves one: the\nshipped workflow stages, the repository-hook replacements (`workflow.diff-rules`)\nand the repository-free event steps each arrive as one provider, and adding a\nstep type means adding a provider to that set. Interpreted plugin sources\ncannot contribute step types: the Yaegi plugin host satisfies only the\nmetadata contract, and no bridge to `StepFactory` exists.\n\nEvery binary that resolves a step type builds its manager from that same\nprovider set at its composition root, before its first resolution, and\ninjects the manager everywhere it resolves definitions. Agreement is per\nbuild: the State Store, the daemon's workflow-definitions client and the agent\nworker built from the same source register identical vocabularies by\nconstruction; binaries built from different sources can disagree, and only a\nmatching deploy fixes that.\n\nAn unknown step type is refused twice, and never degraded. The validator\n`ParseDefinition` refuses a definition naming an unregistered type at save\ntime, on the validating side the composition root built (the State Store's\nworkflow-definitions resource validates there before anything is stored). The\ncompiler refuses the same definition at run, so a binary handed a definition\nwritten against a vocabulary it does not have fails that run loudly instead of\nsilently skipping steps. Both checks live in the Workflow domain against the\ninjected manager, which is why no binary can opt out of the check by\nsubstituting its own registry.\n\n## Relationship between the questions\n\n`archie-core-ze7y` is the same question seen from the deleted\nrepository-authored stages: those `.archie/stages/*.go` files held arbitrary\nstages, and their gate half landed as `workflow.diff-rules` settings rather\nthan interpreted Go. Their stage half has no replacement and does not get one\nthat approximates it: no interpreted-Go stage type is built, and no command\nstep type is created by this decision to stand in for them. The refusal of\n`.archie/stages/*.go` stays until the maintainer's trust decision\n(`archie-core-ndm8`) says otherwise.\n\nIf that decision ever allows a command step type, it arrives as a provider in\nthe compiled-in set under the rules above — a new contributor of exactly one\nstep type at a named provider. It is not a plugin contribution mechanism, and\nit does not change any answer in this document.\n\n## Rejected alternatives\n\n- **A vocabulary version or hash on the wire.** The executing side already\n refuses an unknown step type at its first compile, which is the mismatch\n detector, and it fails closed. A wire field would only narrow the\n deploy-skew window that a matching deploy closes, at the cost of a new\n contract field.\n- **A Yaegi-plugin-to-`StepFactory` bridge.** It would run repository-supplied\n interpreted code inside the daemon's process with daemon privileges. The\n trust boundary invariant requires repository-authored code to run in the\n task container, not in an interpreter embeddable into any binary.\n- **A package-level process-global registrar.** Global mutable registry state\n is unreadable at the composition root, collides with itself when one\n process builds the vocabulary twice, and is what made the first attempt at\n this question worse instead of better.\n- **Degrading on an unknown step type.** A run that skipsLine truncated
|
||||
}
|
||||
],
|
||||
"nav": [
|
||||
@@ -815,10 +857,18 @@
|
||||
"title": "Playbook data-flow and condition syntax",
|
||||
"url": "/dev/prds/playbook-expression-syntax/"
|
||||
},
|
||||
{
|
||||
"title": "Plugin settings reconcile live",
|
||||
"url": "/dev/prds/plugin-settings-live/"
|
||||
},
|
||||
{
|
||||
"title": "PR review agent",
|
||||
"url": "/dev/prds/pr-review-agent/"
|
||||
},
|
||||
{
|
||||
"title": "PR review: the operator's answer to the approval gate",
|
||||
"url": "/dev/prds/pr-review-operator-response/"
|
||||
},
|
||||
{
|
||||
"title": "PR review comment remediation -- decision",
|
||||
"url": "/dev/prds/pr-review-remediation/"
|
||||
@@ -839,6 +889,10 @@
|
||||
"title": "Review calibration -- decision",
|
||||
"url": "/dev/prds/review-calibration/"
|
||||
},
|
||||
{
|
||||
"title": "Review settings resource",
|
||||
"url": "/dev/prds/review-settings-resource/"
|
||||
},
|
||||
{
|
||||
"title": "Runtime control plane",
|
||||
"url": "/dev/prds/runtime-control-plane/"
|
||||
@@ -863,6 +917,10 @@
|
||||
"title": "Skill curator (reference implementation) -- decision",
|
||||
"url": "/dev/prds/skill-curator/"
|
||||
},
|
||||
{
|
||||
"title": "SOUL: an agent's user-authored personality",
|
||||
"url": "/dev/prds/soul/"
|
||||
},
|
||||
{
|
||||
"title": "State Store — contract boundary \u0026 transport (ratification)",
|
||||
"url": "/dev/prds/state-store-contract/"
|
||||
@@ -898,6 +956,18 @@
|
||||
{
|
||||
"title": "Webhook intake security -- decision",
|
||||
"url": "/dev/prds/webhook-intake-security/"
|
||||
},
|
||||
{
|
||||
"title": "Declared outputs of a workflow run",
|
||||
"url": "/dev/prds/workflow-call-outputs/"
|
||||
},
|
||||
{
|
||||
"title": "Workflows calling workflows",
|
||||
"url": "/dev/prds/workflow-calls/"
|
||||
},
|
||||
{
|
||||
"title": "Workflow step vocabulary: what a step type is and how binaries agree on it",
|
||||
"url": "/dev/prds/workflow-step-vocabulary/"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -11,6 +11,12 @@
|
||||
"title": "Building your first playbook binding",
|
||||
"section": "Guides",
|
||||
"body": "# Building your first playbook binding\n\nThis walks through the whole no-code path the event-capture epic promises:\npoint an external app's webhook at archie, see the real payload it sends,\nmap the fields you care about, bind them to a workflow, and watch the next\nmatching event turn into a task -- no code, no redeploy, no restart. See\n`docs/architecture/bindings.md` for the model and threat model behind each\nstep below.\n\n## 1. Send a test event\n\nPoint whatever external app you want archie to react to at:\n\n```\nPOST http://\u003cyour-archied-host\u003e:8484/webhooks/capture/\u003csource\u003e\n```\n\n`\u003csource\u003e` is a name you choose for this sender (e.g. `sentry`, `github-ci`,\n`stripe`) -- it's just a URL path segment, not a preset list. Send one real\nevent however is easiest for a first test, e.g.:\n\n```bash\ncurl -X POST http://localhost:8484/webhooks/capture/sentry \\\n -H \"Content-Type: application/json\" \\\n -d '{\"issue\": {\"title\": \"NullPointerException in checkout\"}, \"level\": \"error\"}'\n```\n\nThis event isn't signed yet, so it's captured but marked **unauthenticated**\n-- visible for you to design against, but incapable of triggering anything\n(`docs/architecture/bindings.md`'s threat-model section explains why: an\nunauthenticated event can never match a binding, no matter how it looks).\n\n## 2. Inspect the captured payload\n\nOpen the dashboard's **Event inspector** (`/captures`). Your test event\nappears there with its real body -- this is schema-by-example: you're\nlooking at an actual payload from the actual sender, not guessing at a\nschema in advance.\n\n## 3. Map the fields you care about\n\nOpen **Field mappings** (`/mappings`) → **New mapping**. Pick your captured\nevent from the dropdown, then click through its payload tree on the right --\nevery key and value is clickable. Clicking a value binds it as a field\n(name, JSON path, and an inferred type you can change). Add whichever fields\nyour workflow needs (e.g. the issue title), mark the ones that must be\npresent as **Required**, hit **Preview** to confirm they resolve correctly\nagainst the real payload, then **Save**.\n\n## 4. Create the binding\n\nOpen **Playbook bindings** (`/bindings`) → **New binding**:\n\n- **Name** -- anything descriptive.\n- **Source** -- the same `\u003csource\u003e` segment from step 1 (e.g. `sentry`).\n- **Field mapping** -- the one you just saved.\n- **Workflow** -- which registered workflow should run on a match.\n- **Repo pin** (optional) -- leave both blank to use the single configured\n repo; set owner/repo explicitly if you run a multi-repo deployment.\n- **Shared secret** -- a real secret (16+ bytes), never `test1234`. The\n sender signs every request body with this via HMAC-SHA256 so archie can\n tell a genuine event from anyone who finds the URL.\n\nSave. The binding starts in **draft** -- nothing fires yet.\n\n## 5. Approve it\n\nA **draft** or freshly-**edited** binding needs an explicit human approval\nbefore it can ever match a live event -- this is deliberate, not a missing\nstep: an operator authoring a binding is a considered act, an event arriving\nis not, and nothing should self-arm (`docs/architecture/bindings.md`'s\nthreat-model section, point 2). Click **Approve**. Status becomes **armed**.\n\n## 6. Fire it for real\n\nSend the same kind of event again, this time **signed** with the binding's\nsecret:\n\n```bash\nBODY='{\"issue\": {\"title\": \"NullPointerException in checkout\"}, \"level\": \"error\"}'\nSECRET=\"the-secret-you-set-in-step-4\"\nSIG=$(printf '%s' \"$BODY\" | openssl dgst -sha256 -hmac \"$SECRET\" | sed 's/^.* //')\n\ncurl -X POST http://localhost:8484/webhooks/capture/sentry \\\n -H \"Content-Type: application/json\" \\\n -H \"X-Hub-Signature-256: sha256=$SIG\" \\\n -d \"$BODY\"\n```\n\nThis event is captured as **authenticated**, matched against your armed\nbinding, and dispatched into a new task through the exact same\ngate/worktree/sandbox pipeline every other task goes through -- see\n`docs/architecture/messaging-and-work-intake.md`'s \"Intake provenance\". Check\nthe **Tasks** page; a new task should appear, its body built from the fields\nyour mapping resolved.\n\n## Editing a live binding\n\nAny edit to an armed binding -- even a typo fix -- drops it back to\n**pending_approval** automatically. This can't be bypassed by editing; it\nhas to be re-approved. When editing, leave the **Shared secret** field blank\nto keep the existing secret; only fill it in if you're deliberately\nrotating it.\n"
|
||||
},
|
||||
{
|
||||
"url": "/docs/guides/pr-review-benchmark/",
|
||||
"title": "PR review benchmark",
|
||||
"section": "Guides",
|
||||
"body": "# PR review benchmark\n\nRun `scripts/pr-review-benchmark.sh` with `PRBENCH_REVIEW_MODEL` and\n`PRBENCH_CLASSIFICATION_MODEL` set to configured `provider/model` references.\nThe judge defaults to `anthropic/claude-sonnet-4.6`; set\n`PRBENCH_JUDGE_MODEL` to another configured model when needed. The script uses\n`~/.config/archie/config.toml` for providers and `GH_TOKEN` or `GITHUB_TOKEN`\nfor read access to the benchmark pull requests. It posts no forge review.\n\nThe default run reviews the 38 runnable Martian pull requests once each at\n`deep`, judges the comments against 102 golden comments, and writes\n`bin/prbench-results/run.json`, `summary.json`, and one JSON result per pull\nrequest. That output directory is ignored by git. A completed full run fails\nwhen any problem fails or golden micro-recall is below 0.70. Golden-only\nprecision is reported alongside recall. Set `PRBENCH_OUT` to keep separate\nruns; `-problems ID` limits a smoke run to one pull request. Completed results\nare saved as each PR finishes. Pass `-resume DIR` to reuse completed results\nfrom a run with the same models; each reused problem must match the current\nbenchmark entry, and failed problems are rerun.\nA smoke run alone is not the acceptance run.\n\nThe benchmark passes only each problem's ID and pull request URL to the\nreviewer. The judge receives the golden comments after the review has ended.\nThe runner uses the production decision phases through the merge gate,\nincluding scoring and the 25-comment cap, then stops before polish and forge\nposting. A reviewer that fails to finish makes that problem fail. The results\nrecord budget-skipped phases and the selected models. Model substitutions do\nnot satisfy the PRD's named-model criterion even if recall clears the threshold.\n"
|
||||
}
|
||||
],
|
||||
"nav": [
|
||||
@@ -24,6 +30,10 @@
|
||||
{
|
||||
"title": "Building your first playbook binding",
|
||||
"url": "/docs/guides/first-playbook/"
|
||||
},
|
||||
{
|
||||
"title": "PR review benchmark",
|
||||
"url": "/docs/guides/pr-review-benchmark/"
|
||||
}
|
||||
]
|
||||
}
|
||||
|
||||
@@ -17,7 +17,12 @@ that reads it and the path the value takes to get there.
|
||||
channels, containers). The file only seeds it. Once the State Store holds the
|
||||
control-plane resource, the stored document is layered over the file
|
||||
(`controlplane.Client.RuntimeConfig`) and the file key stops mattering. It is
|
||||
checked by `validateDatabaseOwned` and by the resource's validator.
|
||||
checked by `validateDatabaseOwned` and by the resource's validator. A stored
|
||||
value is refreshed from the file only when the store has no value for the kind
|
||||
at all; a kind that ships a document of its own (workflow definitions,
|
||||
personas) is refreshed whenever the seed itself wrote the stored copy, since
|
||||
that copy is a previous release's document rather than an operator's
|
||||
(`controlplane.Server.seedKind`).
|
||||
- **Worker-carried.** A value the agent container needs travels in
|
||||
`config.TaskConfig` (`Config.ForTask`) or on `taskrun.Request`. Never pass it
|
||||
as an environment variable the daemon did not already define, and never carry
|
||||
@@ -25,16 +30,27 @@ that reads it and the path the value takes to get there.
|
||||
|
||||
## Adding a database-owned field
|
||||
|
||||
1. Add it to the struct the resource's `Document` names in
|
||||
`internal/app/controlplane/operational_settings.go`. The resource's JSON
|
||||
schema and the dashboard's Advanced settings editor are generated from that
|
||||
type, so no UI work is needed for the editor itself.
|
||||
2. Stored documents use Go field names as keys (`Image`, `MaxConcurrency`).
|
||||
Give the field no `json` tag unless its neighbours have one.
|
||||
3. A map or a nested struct needs its layering checked. `json.Unmarshal`
|
||||
merges into an existing map, so a stored map would add to the file's rather
|
||||
than replace it. A field the stored document omits keeps the file's value
|
||||
(a document stored before the field existed). Add a case to
|
||||
1. Add it to the wire-shape type the resource's `Document` names — a dedicated
|
||||
struct in `internal/app/controlplane/` with explicit snake_case json tags
|
||||
(`channel_settings.go`, `tool_settings.go`, `container_settings.go` are the
|
||||
precedents), never the internal config struct itself. A struct fed straight
|
||||
into the document falls back to Go field names (`Window`, `MaxRequests`),
|
||||
and a bare `time.Duration` marshals as nanoseconds — both render unusable
|
||||
in the Web UI. The resource's JSON schema and the dashboard's Advanced
|
||||
settings editor are generated from that type, so no UI work is needed for
|
||||
the editor itself.
|
||||
2. Map to and from the internal config type at the resource boundary (`Seed`,
|
||||
the layering in `runtime_config.go`, and the validator all use the same
|
||||
mapping). Durations in the document are a string-marshalling type
|
||||
(`config.Duration` or a document-local one), never a bare `time.Duration`.
|
||||
3. A document stored before the shape existed carries Go-cased keys. Read them
|
||||
with `controlplanerpc.DecodeRenamingLegacyKeys` (an `UnmarshalJSON` on the
|
||||
wire type) while keeping `DisallowUnknownFields` — dropping unknown keys
|
||||
would decode a misspelling as "unset" — and register a `Normalize` on the
|
||||
`Definition` that re-encodes the document, so a legacy document converges
|
||||
the next time it is written. A map or a nested struct needs its layering
|
||||
checked: a stored map replaces the file's, not merges into it, and a field
|
||||
the stored document omits keeps the file's value. Add a case to
|
||||
`internal/app/controlplane/runtime_config_test.go` for both.
|
||||
4. Validate it in one function both sides call, and add a case to
|
||||
`TestResourceValidatorsRejectWhatEffectiveValidationRejects` in
|
||||
|
||||
@@ -28,8 +28,9 @@ Authority: `docs/architecture/agent-system.md`. The status vocabulary lives in
|
||||
|
||||
Follow [State Store](state-store.md) for the
|
||||
column and the wire. Then decide who writes it: `UpdateTask` writes a fixed
|
||||
column set, so a field set at enqueue needs its own statement (as
|
||||
`StampTaskBinding` does for binding provenance and inputs).
|
||||
column set, so a field set at enqueue belongs in the insert that creates the
|
||||
row (as `InsertChatTask` does for inputs), or in its own statement when only
|
||||
some producers set it (as `StampTaskBinding` does for binding provenance).
|
||||
|
||||
### Changing what the agent receives
|
||||
|
||||
|
||||
@@ -31,6 +31,50 @@ should look.
|
||||
after visiting Settings and Logs: the UI process serves HTTP/1.1 and six
|
||||
persistent streams can starve every later browser request.
|
||||
|
||||
## Testing the dashboard
|
||||
|
||||
Authority: the runner itself is `ui/package.json`'s `test` script: `node --test
|
||||
--experimental-strip-types test/*.test.ts` over `ui/test/*.test.ts`. It runs
|
||||
pure TypeScript modules with `node`'s type stripping — no SFC loader, no DOM,
|
||||
no second dependency beyond what the app already carries. That is the standard,
|
||||
and a decision record for when it is deliberately not enough:
|
||||
|
||||
- **Test archie's logic in a module; leave SFC wiring alone.** Wire shapes,
|
||||
draft state, copy conditions, filters and payload building live in plain
|
||||
`.ts` files beside the components and are tested in `ui/test/`. Components
|
||||
stay thin, so there is normally nothing in an SFC that is archie logic.
|
||||
- **Installed primitives are upstream-tested, not re-tested here.**
|
||||
`reka-ui` (2.10.5 here) maintains colocated tests per component in its own
|
||||
repo (Vitest/jsdom + axe: Switch, TagsInput, NumberField, Select, the
|
||||
arrow-navigation composables). The npm package ships none of those files, so
|
||||
this coverage is inherited through the version bound, not the tarball —
|
||||
`grep -l test node_modules/reka-ui` finds nothing. Duplicating them as local
|
||||
mount tests would test a dependency.
|
||||
- **A `.vue` import cannot run under the module runner.** `node --test` fails
|
||||
such a module with `ERR_UNKNOWN_FILE_EXTENSION: .vue` and the runner has no
|
||||
built-in loader for SFCs. A file under `ui/test/` that imports a `.vue` is
|
||||
therefore a broken test, not a weak one.
|
||||
- **If a DOM mount harness is ever needed** (a page-level accessibility
|
||||
contract, cross-component interaction, focus behaviour): `happy-dom` +
|
||||
`@vue/test-utils` + `vitest` scoped to a separate DOM test glob, keeping the
|
||||
module runner for everything else. Measured on the ui tree (vitest 5.0.2,
|
||||
happy-dom 20.14.5, @vue/test-utils 2.5.1): they add 24 top-level
|
||||
`node_modules` entries and 27 MB on a 296 MB install, a working 2-test mount
|
||||
suite (role=radiogroup vs role=switch, aria-label, click activation against
|
||||
the real SFCs) runs in 1.2 s on top of the current 0.5 s module suite, and
|
||||
`vue-tsc` (7.4 s) dominates `task test:ui` either way. The single-runner
|
||||
alternative (absorbing the existing suite into vitest) was measured
|
||||
infeasible as-is: all 29 existing files import `node:test`, which vitest
|
||||
cannot collect ("No test suite found in file" for every one), so it would be
|
||||
a rewrite of the whole suite, and its runtime was not measured. Nothing in
|
||||
`ui/dist` or CI changes either way; happy-dom is pure JS, no browser binary.
|
||||
- **What the module standard does not verify:** whether a call site passes an
|
||||
`aria-label` or which `v-if` branch shows. Those live in SFC templates and
|
||||
are only visible with a mount. If a page's accessible-name wiring is the
|
||||
risk, say so in the page's task and reach for the harness decision above
|
||||
rather than quietly growing mount tests. Never suppress a lint rule or a
|
||||
test to keep SFC behaviour out of the gate.
|
||||
|
||||
## Adding an API route
|
||||
|
||||
1. The handler goes in the `internal/webui/api_<concern>.go` file for its
|
||||
|
||||
@@ -34,9 +34,13 @@ restating them.
|
||||
index, so stage regenerated contracts before running it.
|
||||
- Stage by path, or read `git status` before `git add -A`. Tests that start
|
||||
embedded NATS or write logs must use `t.TempDir()`; anything they leave in the
|
||||
tree gets committed. `task check` also adds linter-tool lines to `go.sum`
|
||||
(bead 1e37); restore `go.sum` before committing unless you changed a
|
||||
dependency.
|
||||
tree gets committed. `task check` writes no module file on a consistent tree,
|
||||
root or `tools/` (verified at HEAD with `GOFLAGS` unset and with `-mod=mod`):
|
||||
a stale `go.mod` or `go.sum` fails it, with `missing go.sum entry` or
|
||||
`updates to go.mod needed`, rather than being repaired. Only a global
|
||||
`GOFLAGS=-mod=mod` in `go env` re-enables that repair, which is why the
|
||||
`go -C tools` steps pass `-mod=readonly`; if `go.sum` goes dirty, run
|
||||
`go mod tidy` and commit the result on its own.
|
||||
- A change to `docs/prds/`, `docs/architecture/` **or `docs/development/`**
|
||||
carries the regenerated `docs/data/generated/dev-docs.json`: run
|
||||
`task docs:artifact` (not `task docs:check`, which checks contracts only).
|
||||
|
||||
@@ -27,3 +27,20 @@ passes the same gate.
|
||||
rule; do not loosen the rule to the test.
|
||||
3. Run the full suite without `-short`, then `task check`, then commit. Check
|
||||
`git status` for files a test wrote into the tree before staging.
|
||||
4. **A merge can surface a bug neither lane's own tests exposed alone.** Two
|
||||
real cases from 2026-09-26: a test that dialled no NATS URL passed on a
|
||||
machine with an ambient dev server running and failed the moment it landed
|
||||
on a clean CI runner (start an ephemeral server per test, never rely on a
|
||||
default port resolving to something); and a cycle-detector that walked a
|
||||
Go map in range order reported the same cycle two different ways from run
|
||||
to run, invisible until enough fresh (uncached) runs hit the unlucky
|
||||
ordering. Both looked like "the merge broke a passing test" but were
|
||||
latent defects the merge only had the opportunity to expose. Fix the
|
||||
defect the failure is pointing at, not the assertion that caught it — see
|
||||
CLAUDE.md's test-quality bar before writing the replacement.
|
||||
5. `go test`'s cache reuses a package's last result when nothing in its
|
||||
dependency graph changed. A merge that touches one package can leave a
|
||||
sibling's flaky test silently cached "pass" locally while CI runs it
|
||||
fresh. `task check` passing on your machine is not proof a merge is
|
||||
clean — rerun anything nondeterminism-prone with `-count=1` before
|
||||
trusting it, and let CI's from-scratch run be the tiebreaker it is.
|
||||
@@ -52,3 +52,14 @@ process; nothing else opens the database.
|
||||
Add the sentinel to `storecontract`, a row to `wireErrors` in `values.go`, and
|
||||
a case to `error_test.go`. The canonical message is part of the wire contract:
|
||||
changing it breaks `errors.Is` on the client silently.
|
||||
|
||||
## Harness OAuth secrets
|
||||
|
||||
`HarnessSecretStore` stores token sets by org and credential service through
|
||||
admin-only State Store RPCs. The EDA store seals them with the binding cipher's
|
||||
keyring and a separate `HarnessSecretDomain`. OAuth writes require a configured
|
||||
binding encryption key; the legacy binding plaintext fallback does not apply.
|
||||
The daemon's egress proxy (`internal/infrastructure/egress/oauth.go`) is the
|
||||
only daemon consumer: for a run granted the service it swaps sentinels for the
|
||||
stored tokens and writes every refresh back. The setup terminal is a separate
|
||||
harness slice.
|
||||
@@ -39,3 +39,21 @@ vocabulary it registers, so both must see the same step types.
|
||||
behaviour.
|
||||
- Examples in `examples/workflows/` are parsed against the registered
|
||||
vocabulary by `TestExampleWorkflowsParse`. Add one for a new capability.
|
||||
|
||||
## Enabling and disabling
|
||||
|
||||
The `workflow-enablement` control-plane resource lists, per org, the workflows
|
||||
that org has disabled; anything unlisted is enabled. Its readers are the
|
||||
daemon's binding dispatch (a disabled workflow's binding is skipped like an
|
||||
unarmed one), the dashboard's binding save (refused) and binding list
|
||||
(`workflow_disabled`), and work requests. A new reader of "may this org run
|
||||
this workflow" goes through `task.WorkflowEnablement.Enabled`, never a second
|
||||
list. The dashboard acts in the default org until access resolves a caller's
|
||||
own.
|
||||
|
||||
## Starting a workflow from chat
|
||||
|
||||
`task_spawn` accepts `workflow` and an `inputs` object. The gateway forwards
|
||||
inputs through the task creation contract; it does not interpret individual
|
||||
workflows. The daemon checks inputs against the pinned `WorkflowInterface`
|
||||
before acquiring a container and parks invalid requests with the reason.
|
||||
@@ -0,0 +1,28 @@
|
||||
# PR review benchmark
|
||||
|
||||
Run `scripts/pr-review-benchmark.sh` with `PRBENCH_REVIEW_MODEL` and
|
||||
`PRBENCH_CLASSIFICATION_MODEL` set to configured `provider/model` references.
|
||||
The judge defaults to `anthropic/claude-sonnet-4.6`; set
|
||||
`PRBENCH_JUDGE_MODEL` to another configured model when needed. The script uses
|
||||
`~/.config/archie/config.toml` for providers and `GH_TOKEN` or `GITHUB_TOKEN`
|
||||
for read access to the benchmark pull requests. It posts no forge review.
|
||||
|
||||
The default run reviews the 38 runnable Martian pull requests once each at
|
||||
`deep`, judges the comments against 102 golden comments, and writes
|
||||
`bin/prbench-results/run.json`, `summary.json`, and one JSON result per pull
|
||||
request. That output directory is ignored by git. A completed full run fails
|
||||
when any problem fails or golden micro-recall is below 0.70. Golden-only
|
||||
precision is reported alongside recall. Set `PRBENCH_OUT` to keep separate
|
||||
runs; `-problems ID` limits a smoke run to one pull request. Completed results
|
||||
are saved as each PR finishes. Pass `-resume DIR` to reuse completed results
|
||||
from a run with the same models; each reused problem must match the current
|
||||
benchmark entry, and failed problems are rerun.
|
||||
A smoke run alone is not the acceptance run.
|
||||
|
||||
The benchmark passes only each problem's ID and pull request URL to the
|
||||
reviewer. The judge receives the golden comments after the review has ended.
|
||||
The runner uses the production decision phases through the merge gate,
|
||||
including scoring and the 25-comment cap, then stops before polish and forge
|
||||
posting. A reviewer that fails to finish makes that problem fail. The results
|
||||
record budget-skipped phases and the selected models. Model substitutions do
|
||||
not satisfy the PRD's named-model criterion even if recall clears the threshold.
|
||||
@@ -56,6 +56,10 @@
|
||||
"/news/archie/1.41.1/": "/news/1.41.1/",
|
||||
"/news/archie/1.41.2/": "/news/1.41.2/",
|
||||
"/news/archie/1.42.0/": "/news/1.42.0/",
|
||||
"/news/archie/1.43.0/": "/news/1.43.0/",
|
||||
"/news/archie/1.44.0/": "/news/1.44.0/",
|
||||
"/news/archie/1.44.1/": "/news/1.44.1/",
|
||||
"/news/archie/1.45.0/": "/news/1.45.0/",
|
||||
"/news/archie/1.5.0/": "/news/1.5.0/",
|
||||
"/news/archie/1.6.0/": "/news/1.6.0/",
|
||||
"/news/archie/1.7.0/": "/news/1.7.0/",
|
||||
@@ -129,6 +133,10 @@
|
||||
"/news/archied/1.41.1/": "/news/1.41.1/",
|
||||
"/news/archied/1.41.2/": "/news/1.41.2/",
|
||||
"/news/archied/1.42.0/": "/news/1.42.0/",
|
||||
"/news/archied/1.43.0/": "/news/1.43.0/",
|
||||
"/news/archied/1.44.0/": "/news/1.44.0/",
|
||||
"/news/archied/1.44.1/": "/news/1.44.1/",
|
||||
"/news/archied/1.45.0/": "/news/1.45.0/",
|
||||
"/news/archied/1.5.0/": "/news/1.5.0/",
|
||||
"/news/archied/1.6.0/": "/news/1.6.0/",
|
||||
"/news/archied/1.7.0/": "/news/1.7.0/",
|
||||
|
||||
@@ -1,4 +1,24 @@
|
||||
[
|
||||
{
|
||||
"version": "1.45.0",
|
||||
"date": "2026-09-30",
|
||||
"body": "### archied\n\n- fix(eda): reject a result map missing a field or needing a conversion\n- feat(eda): per-org workflow enable/disable gating bindings\n- feat(telegram): carry inbound media through the chat turn\n- fix(prsource): use a CodeQL-recognised containment guard when extracting archives\n- feat(store): key control-plane resources by (org, kind)\n- fix(store): refuse resource keys the audit key cannot disambiguate\n- fix(daemon): resume the task branch before container acquisition\n- feat(webui): show attachment metadata in the session transcript\n- feat(webui): name a workflow's declared inputs on the work-request form\n- feat(controlplane): carry the caller org from the request principal\n- fix(webui): the workflow handlers act in the caller's org\n- feat(kitrun): render the OAuth credential file with sentinels\n- feat(store): record accepted package authority against the pin\n- fix(workflow): the own-PR flow no longer parks on the operator-approval gate\n- feat(gateway): a TTL-bounded dedup gate for redelivered platform messages\n- feat(egress): capture the OAuth scope set and carry it to the harness secret\n- feat(kitrun): render the OAuth scopes and omit an uncaptured primary key\n- feat(store): project installed package contributions into org resources\n- feat(gateway): coalesce rapid-fire text events into one turn\n- fix(config): expand plugin, module and skills dirs like every other operator path\n- fix(webui): drop the config schema's editability advert\n- feat(webui): events counts, YAML reading, log rows and dashboard filters\n\n### archie-agent\n\n- feat(eda): per-org workflow enable/disable gating bindings\n- feat(telegram): carry inbound media through the chat turn\n- fix(prsource): use a CodeQL-recognised containment guard when extracting archives\n- feat(store): key control-plane resources by (org, kind)\n- feat(controlplane): carry the caller org from the request principal\n- feat(kitrun): render the OAuth credential file with sentinels\n- feat(store): record accepted package authority against the pin\n- fix(workflow): the own-PR flow no longer parks on the operator-approval gate\n- feat(egress): capture the OAuth scope set and carry it to the harness secret\n- feat(kitrun): render the OAuth scopes and omit an uncaptured primary key\n- feat(store): project installed package contributions into org resources"
|
||||
},
|
||||
{
|
||||
"version": "1.44.1",
|
||||
"date": "2026-09-29",
|
||||
"body": "### archied\n\nTwo fixes to tasks that could not get past their workflow definition.\n\n- **Approving a task no longer parks it again.** A task requeued under a\n different workflow kept the previous run's definition pinned, so the worker\n refused to compile the dispatch — it named `feasibility` while the row named\n `implement` — and the task parked immediately, identically on every further\n approval, which left `decline` as the only working operator action.\n The daemon now re-pins whenever the pinned definition's id disagrees with the\n task's workflow. A pin that is present, digest-valid and id-consistent is\n still a strict no-op, so an operator's own definition override survives a\n dispatch unchanged.\n- **A shipped workflow definition now reaches an existing install.** A stored\n seed was consulted only for a resource the store did not already hold, so a\n document that changed in the build never reached a database an earlier\n release had seeded. For workflow definitions that is a total outage rather\n than a stale setting: the collection validates as one document, so a stored\n step type this build no longer has failed every task's pin, whatever workflow\n the task named — and the documented recovery, removing the resource and\n restarting, wrote nothing either, because the store answered the seed's known\n request ID from a history that outlives the resource. A seed now refreshes a\n kind it wrote the newest revision of and re-creates a resource that is gone,\n while an operator's own replacement is never undone.\n\n### archie-agent\n\nThe runtime image is rebuilt with this release and links the shared workflow\npackage carrying the definition-id helper above. Hosts that run agent\ncontainers need `docker compose pull agent` after updating to pick it up."
|
||||
},
|
||||
{
|
||||
"version": "1.44.0",
|
||||
"date": "2026-09-29",
|
||||
"body": "### archied\n\nArchie can now review pull requests.\n\n- **Reviews on request and by watch.** Ask in chat or on the dashboard work form, add a repository to the watch list, or just let archie review its own PRs before it opens them. Review intensity follows a depth dial (quick/standard/deep) classified from the size of the change, and every finished review passes a verification layer — coverage-gap and cross-finding consistency checks — before it is produced.\n- **No forge credential reaches the review sandbox.** The daemon prefetches the pull request's data and rebuilds its source snapshot over the forge's HTTP API, so the agent container works from an isolated copy with no read access to the repository's credentials.\n- **Reviews stop at the operator gate before posting.** `review.precision_gate` / `approve_before_post` decide whether a finished review posts itself or parks for operator approval. With this release the parked state is a stop sign, not a checkpoint: the approve/reject/re-review responses behind the gate are not wired yet, and the gate's settings are not yet editable in the dashboard (configure them in `config.toml`). A parked review sits until that follow-up lands.\n- The adversarial self-review pass archie previously ran before opening its own PRs is superseded by this pipeline and has been removed.\n- Hardened harness input handling: harness identifiers are bounded to integer types.\n\n### archie-agent\n\nThe runtime image is rebuilt with this release; it links the shared pr-review workflow packages behind the reviews above. Hosts that run agent containers need `docker compose pull agent` after updating to pick it up."
|
||||
},
|
||||
{
|
||||
"version": "1.43.0",
|
||||
"date": "2026-09-28",
|
||||
"body": "### archied\n\n- **Organisations.** Tasks, identities and settings now belong to an org. An\n existing install is upgraded into a default org when the State Store first\n starts; the upgrade resumes if interrupted. Task de-duplication is scoped\n per org and identity.\n- **Access policies are enforced** at the dashboard, the API and task\n dispatch, with shipped roles and a rule that nothing crosses between orgs.\n Denials are recorded and reported on the health page. If a policy locks\n you out, `archied access reset --org <org>` (or `--instance`) on the State\n Store host restores the shipped defaults.\n- **Workflows can call workflows** with a `workflow.call` step. Inputs and\n call cycles are checked when the workflow is saved, and the caller waits\n on the callee's result.\n- **Runs record each step.** A run's stages and agent calls are stored as\n steps, the task detail page reads them, and stopping a task or archiving\n it goes through one cancel path. After a crash, steps left running are\n marked interrupted. Archiving a task removes its worktree.\n- **Model roles, repositories, scheduling policy, providers and agent\n profiles apply without a restart.**\n- **Kit harness profiles:**\n - `kit` is now one digest-pinned reference, a workload Kit or a published\n Kit set, not a list. **Rewrite `kit = [...]` in `config.toml` or the\n agent-profiles settings as the single reference**; a list no longer\n loads. Compose mixins by publishing a Kit set.\n - OAuth logins are handled on the host: the egress proxy refreshes tokens,\n stores them encrypted, and gives the container only placeholders.\n - A Kit's skills request mounts `skills_dir` read-only, and its\n instructions file (such as `CLAUDE.md`) is written beside the workspace,\n which is now `/archie/workspace`.\n - A run still cannot be granted the credential a Kit needs, so a Kit that\n requires one is refused at launch.\n- Rate-limited webhook deliveries get `429`.\n- `archie-gateway` and `archie-state-store` report ready to systemd.\n\n### archie-agent\n\n- Runs workflow calls, records its steps and agent calls, and runs Kit\n harness stages under the profile's Kit."
|
||||
},
|
||||
{
|
||||
"version": "1.42.0",
|
||||
"date": "2026-09-26",
|
||||
|
||||
@@ -58,10 +58,12 @@ indistinguishable from a process that never reported.
|
||||
## What can be reported, and what cannot
|
||||
|
||||
A process reaches its apply point only after the State Store has answered it.
|
||||
When the State Store is unreachable, the process exits or refuses to start and
|
||||
writes no record. An unreachable store is never reported as a failure by the
|
||||
process it affected. A record carries the other failure: the store answered,
|
||||
and the value would not validate.
|
||||
At startup, when the State Store is unreachable, the process exits or refuses
|
||||
to start and writes no record. A live watcher that loses its established
|
||||
control-plane stream reports the connection failure against its last applied
|
||||
version while it retries. Re-establishing the stream clears that outage record
|
||||
without clearing a versioned document rejection. A transport failure is not a
|
||||
document rejection; it reports that live delivery is unavailable.
|
||||
|
||||
Absence has two meanings and the UI never collapses them: no process applies
|
||||
this kind, or a process that applies other kinds has not reported this one.
|
||||
@@ -101,6 +103,9 @@ restart but not a death, and accepting the limitation with the page saying so.
|
||||
- A process that applies a resource writes a record carrying that version.
|
||||
- A process whose apply fails validation writes a record carrying the error and
|
||||
no new version.
|
||||
- A live watch outage is reported against the last applied version until the
|
||||
stream is re-established; re-establishment preserves any outstanding
|
||||
versioned rejection.
|
||||
- A reload that fails leaves the previously applied version recorded.
|
||||
- A record written under a process name outside the shared constant fails the
|
||||
test binding writer to reader.
|
||||
|
||||
@@ -42,8 +42,8 @@ Archie is a partial Kit runtime. It implements these capability types:
|
||||
| `volume@1` | A Docker volume keyed by WorkflowExecution, deleted with it. |
|
||||
| `lifecycle@1` | Install and startup hooks run on container create. |
|
||||
| `agent-sessions@1` | The headless `prompt` and `resume` invocations for the stage. |
|
||||
| `agent-skills@1` | The operator's skills store, mounted read-only whatever the Kit asks. |
|
||||
| `agent-context@1` | Archie's stage instructions, delivered where the Kit declares. |
|
||||
| `agent-skills@1` | The operator's skills store (`skills_dir`), mounted read-only whatever the Kit asks. |
|
||||
| `agent-context@1` | The workload's profile file beside the workspace, indexing each Kit's guidance. |
|
||||
| `resources@1` | Container CPU and memory limits. |
|
||||
|
||||
Every other type fails closed: a required entry refuses the launch, an
|
||||
@@ -51,9 +51,9 @@ optional one is skipped and recorded on the step. `credential@1` with
|
||||
`passthrough: true` and any credential for a forge service are refused.
|
||||
|
||||
The operator's own setup (plugins, subagents, instructions, settings) is a
|
||||
mixin Kit the operator builds `FROM` or alongside the harness Kit. It is
|
||||
versioned image content, rewritten on every create, never state a run can
|
||||
modify.
|
||||
mixin Kit, published with the harness Kit as a Kit set: the set merges their
|
||||
layers into one image. It is versioned image content, rewritten on every
|
||||
create, never state a run can modify.
|
||||
|
||||
## Contract
|
||||
|
||||
@@ -75,8 +75,9 @@ retry without a `resume` verb.
|
||||
|
||||
A harness is an agent profile. `docs/prds/event-automation.md` defines a
|
||||
profile as the execution environment a workflow selects; a harness profile
|
||||
names a Kit composition (the workload Kit pinned by digest, and zero or more
|
||||
mixin Kits) in place of a container image. Everything else about profiles
|
||||
names one Kit pinned by digest, a workload Kit or a published Kit set, in
|
||||
place of a container image. Archie runs that Kit's image and composes no Kits
|
||||
itself; a bare mixin is refused. Everything else about profiles
|
||||
holds: a workflow names its profile, a stage may name a different one, and a
|
||||
profile holds no secrets.
|
||||
|
||||
@@ -85,6 +86,19 @@ ai-sdk agent loop for an image profile, the harness runner for a Kit
|
||||
profile. Image profiles, and every workflow already written against them,
|
||||
are unchanged. A Kit profile named by no workflow is a validation error.
|
||||
|
||||
A stage naming a different profile than its workflow's is a separate run,
|
||||
not a mid-container runner switch: a Kit task runs in one container
|
||||
provisioned for one profile (Container layout), so a stage that needs a
|
||||
different one is its own callee, started the way `workflow.call` already
|
||||
starts one (`docs/prds/event-automation.md` "Workflows call workflows"),
|
||||
with its own agent profile resolved off its own task row. This needs no
|
||||
mechanism beyond `workflow.call` plus per-task profile resolution
|
||||
(`daemon.pinTaskProfile`), both of which already treat every task's
|
||||
profile independently of any caller's -- see
|
||||
`TestWorkflowCallerConformance` (staterpc) for the callee's independent
|
||||
`Workflow` field and `TestWorkflowCallGivesACalleeItsOwnProfile` (daemon)
|
||||
for the Kit-vs-image runner selection that independence produces.
|
||||
|
||||
Profiles are org resources in the State Store, so a Kit profile belongs to
|
||||
one org, is granted to its workspaces like any profile, and applies without
|
||||
a restart.
|
||||
|
||||
@@ -118,7 +118,12 @@ typed values are checked at load; `dyn` values are checked by the module decode.
|
||||
|
||||
**D5 — where the result map becomes the `Result` struct.** Settled:
|
||||
`ModuleRegistry` stays schema-agnostic. `ModuleRegistry.DecodeResult`
|
||||
(`internal/domain/eda/module`) is the conversion site.
|
||||
(`internal/domain/eda/module`) is the conversion site. It accepts a value only
|
||||
when it already carries the field's declared type, and a map only when it
|
||||
carries every declared field. A conversion changes the value's representation --
|
||||
a number for a string field is the named case -- and an absent field reads as the
|
||||
zero value, so each is reported rather than becoming a quietly wrong value in a
|
||||
later expression.
|
||||
|
||||
## Verification
|
||||
|
||||
@@ -128,5 +133,8 @@ typed values are checked at load; `dyn` values are checked by the module decode.
|
||||
dynamically indexed `actions` read fails.
|
||||
- An arg KEY the kind's `Args` schema does not define fails the load, and so
|
||||
does `message: '123'` for the `log` kind. `message: event.title` loads.
|
||||
- A result map missing a declared field, and one whose value is not already the
|
||||
field's type, are both reported by the decode; a value that would only be
|
||||
convertible (a number for a string field) is not accepted.
|
||||
- The one-action `workflow` playbook shape, its dispatch, and its existing
|
||||
load-time checks are unchanged.
|
||||
@@ -4,9 +4,6 @@
|
||||
**Date:** 2026-09-03
|
||||
**Parent:** `docs/prds/eda-playbook-engine.md`, epic `archie-core-t2db`
|
||||
**Beads issue:** `archie-core-t2db.14` (expression environment).
|
||||
Unbuilt decisions: `archie-core-t2db.25` (J1 action ids),
|
||||
`archie-core-t2db.26` (J2 args as CEL),
|
||||
`archie-core-t2db.27` (Result schemas declared to CEL).
|
||||
|
||||
**Decision:** CEL via `cel.dev/cel-go` (v0.32.0), pinned. One expression
|
||||
mechanism covers both an action's `when` condition and its `args` values.
|
||||
@@ -222,6 +219,14 @@ cost of CEL is measured and bounded.
|
||||
applied to every expression; the linter and daemon use the same value so they
|
||||
agree. Alternative considered: exact number is a constant to tune at first
|
||||
use.
|
||||
- **J6 -- `args` failure semantics.** An `args` value that cannot be evaluated
|
||||
aborts its playbook run: the action and every later action in that playbook do
|
||||
not run, because data has no false value to fall back on and an action run
|
||||
without its arguments is a silent one. Other playbooks matching the same event
|
||||
still run, and the task is unaffected: a playbook run never changes routing.
|
||||
The daemon log reports the failure, naming the task, the playbook and the
|
||||
action; no task event is written. Alternative considered: mirroring J3,
|
||||
rejected because a predicate has a meaningful false and data does not.
|
||||
|
||||
## Interaction with the execution-time gaps
|
||||
|
||||
|
||||
@@ -0,0 +1,88 @@
|
||||
# Plugin settings reconcile live
|
||||
|
||||
**Status:** Draft
|
||||
**Tracking:** GitHub [#1154](https://github.com/samcharles93/archie-core/issues/1154), epic [#998](https://github.com/samcharles93/archie-core/issues/998)
|
||||
**Authority:** `docs/prds/runtime-control-plane.md` decides each feature owns how
|
||||
its changes take effect; `docs/architecture/plugins-and-extensions.md` owns the
|
||||
plugin engine rule; `docs/prds/control-plane-apply-status.md` owns where apply
|
||||
reports go.
|
||||
|
||||
## Outcome
|
||||
|
||||
An operator drops a plugin, module or secret-engine file into the configured
|
||||
directory while archied runs, and the daemon loads it without a restart. An
|
||||
edit to an installed file replaces what is running. Deleting an installed file
|
||||
never stops running code; apply status says so. A stored change to
|
||||
`plugin-settings` applies live for additions instead of requiring a restart.
|
||||
|
||||
## Triggers
|
||||
|
||||
`plugin-settings` joins the kinds archied watches (`PluginSettingsKind` moves
|
||||
to the live list in `internal/app/archied/control_plane.go`). After the daemon
|
||||
layers a new version it reconciles the three directories the document names.
|
||||
A second trigger needs no document change: a poller reconciles on an interval,
|
||||
so a file dropped into a directory loads on its own. The poll interval is the
|
||||
apply-status restamp constant; no filesystem-watch dependency is added. The
|
||||
poller reads the current document's directories from the running config each
|
||||
tick, so a changed `plugin_dir`, `module_dir` or `secret_engine_dir` retargets
|
||||
reconciliation without a restart.
|
||||
|
||||
## Rules
|
||||
|
||||
- Adding and changing load; removing never unloads. Yaegi interpreters are not
|
||||
reclaimed while a caller still exists and there is no unload path; the
|
||||
running set can only grow.
|
||||
- Each file is loaded through a fresh interpreter (the boot pattern). A changed
|
||||
file therefore loads cleanly, and replacement switches consumers to the new
|
||||
interpretation; files are content-hashed so only new and changed files load.
|
||||
- A file that fails to load is skipped and reported; already-running code keeps
|
||||
running. This is the degrade-and-skip convention `plugin.LoadDir` and
|
||||
`Registry.LoadDir` already apply at boot. Boot keeps its reject-at-load rule
|
||||
for the module directory; a broken file at runtime skips without aborting.
|
||||
- A directory that does not exist reconciles to an empty set.
|
||||
|
||||
## The three registries
|
||||
|
||||
- **Secret engines** (`internal/secret`). Reconciliation re-runs
|
||||
`Registry.LoadDir` against the live directory. `Register` replaces by name,
|
||||
so an edited engine takes effect for the next resolution. A deleted engine
|
||||
stays registered: existing references keep resolving through it until
|
||||
restart, and the record says so. Engines are stateless resolvers, so a swap
|
||||
needs no lifecycle step.
|
||||
- **Modules** (`internal/domain/eda/module`): reconciliation re-runs
|
||||
`ModuleRegistry.Register` for the kind's file. The invoker maps
|
||||
last-write-wins, and playbook dispatch resolves through the registry at
|
||||
invoke time, so the swap reaches a running playbook store unchanged. A file
|
||||
deleted for a kind leaves the old invoker in place, running; reported.
|
||||
- **Plugins** (`internal/plugin`): `Host` grows running-state operations beside
|
||||
`Register`, `Start` and `Stop`. One adds a single module while the host is
|
||||
running: it is inserted in dependency order, started alone, and on failure
|
||||
rolled back alone, leaving every previously started module running. The
|
||||
other replaces a module whose manifest id matches: stop it, start the new
|
||||
one, and restart the old one when the new start fails. Replacing a module
|
||||
that another depends on is refused, not swapped. These operations obey the
|
||||
plugin engine rule: the host still invokes start and stop itself, isolates
|
||||
the failure to the one module, and keeps a rollback. A deleted file makes no
|
||||
host call: the module runs on and is reported.
|
||||
|
||||
## `skills_dir`
|
||||
|
||||
`skills_dir` is not part of this change. The daemon refuses a candidate
|
||||
`plugin-settings` document whose `skills_dir` differs from the value it is
|
||||
running, reporting that the field applies on restart, until a skill
|
||||
reconciliation exists to carry it. The refusal is the existing rejected-edit
|
||||
apply-status shape: the store keeps the version, the document is not applied,
|
||||
last-known-good keeps running.
|
||||
|
||||
## Apply status
|
||||
|
||||
One record: `archied` on `plugin-settings`. The reconciliation outcome is
|
||||
reported against the version the process is running. The record's error field
|
||||
carries the outstanding reconciliation problem: a deleted file still running, a
|
||||
file that failed to load, or the directory failing to read. A reconciliation
|
||||
with nothing outstanding clears the error. The version stays the version the
|
||||
process is running; an add that succeeded is live even while a removal is
|
||||
outstanding, and the error says so rather than showing the kind as
|
||||
restart-required. archie-gateway keeps boot-time loading; its record simply
|
||||
stays on the version it last applied until it restarts, which the per-process
|
||||
apply-status page already reads correctly.
|
||||
@@ -44,8 +44,11 @@ an `agent` StepExecution; fan-out phases record one child per call.
|
||||
imported by changed files. One agent writes the PR narrative, risk
|
||||
surfaces, changes that do not fit the narrative, and gaps between the
|
||||
description and the diff.
|
||||
3. **Dimension selection.** Three lens agents run in parallel over the intake,
|
||||
anatomy and diff, each able to read the repository:
|
||||
3. **Dimension selection.** Three lens agents run in parallel over the intake
|
||||
(including its machine-written score), anatomy and diff, each able to read
|
||||
the repository. A PR that intake scores as likely machine-written adds a
|
||||
hallucination-check dimension: claims, citations and behaviour the diff
|
||||
does not actually implement.
|
||||
- **behaviour:** where the old and new code diverge for any input; API
|
||||
contracts, concurrency and state, security, error handling, data flow;
|
||||
- **mechanics:** whether the code runs at the language and framework
|
||||
@@ -62,7 +65,11 @@ an `agent` StepExecution; fan-out phases record one child per call.
|
||||
at most 8 at a time. Each reads its target and context files and may
|
||||
follow references. Each finding carries file, line range, severity
|
||||
(`critical`, `important`, `suggestion`, `nitpick`), title, body, an
|
||||
optional suggested fix, quoted evidence, confidence and tags.
|
||||
optional suggested fix, quoted evidence, confidence and tags. A reviewer
|
||||
that exhausts its turn cap or deadline before its terminal tool call
|
||||
records a distinct StepExecution status from a reviewer that completed
|
||||
and found nothing; synthesis and the posted review treat the two
|
||||
differently (the former is unreviewed, the latter is reviewed-clean).
|
||||
5. **Verification layer**, over the review findings:
|
||||
- code extracts an evidence package per finding: the code at the cited
|
||||
lines and snippets from its callers;
|
||||
@@ -94,8 +101,9 @@ an `agent` StepExecution; fan-out phases record one child per call.
|
||||
8. **Merge gate.** One classification call per finding decides blocking or
|
||||
advisory: blocking only for broken builds, security, data loss, contract
|
||||
breaks and regressions. A failed call means advisory.
|
||||
9. **Output.** One call per comment tightens its wording, keeping the
|
||||
original on failure. The review is posted as one forge review with inline
|
||||
9. **Output.** One call per comment tightens its wording, running in a
|
||||
bounded pool at most 8 at a time (matching phase 4), keeping the original
|
||||
on failure. The review is posted as one forge review with inline
|
||||
comments. Any blocking finding requests changes; otherwise the review is a
|
||||
comment. Archie never posts an approval.
|
||||
|
||||
@@ -113,7 +121,11 @@ With `review.approve_before_post = true`, synthesis ends in
|
||||
`waiting_human`. The operator chooses which findings to post, rejects the
|
||||
review, or asks for a re-review with instructions. A re-review reruns phases
|
||||
3 to 8 with the instructions added to the lens and reviewer prompts, at most
|
||||
2 times. A review with no findings posts nothing and does not wait.
|
||||
2 times. A review with no findings posts nothing and does not wait. The gate
|
||||
belongs to the standalone `pr-review` workflow only; archie's own-PR stage list
|
||||
drops it, because a park there would end an implement run before its PR
|
||||
exists (`docs/prds/pr-review-operator-response.md`,
|
||||
"The gate is not reachable from archie's own PRs").
|
||||
|
||||
## Isolation
|
||||
|
||||
|
||||
@@ -0,0 +1,69 @@
|
||||
# PR review: the operator's answer to the approval gate
|
||||
|
||||
**Status:** Draft
|
||||
**Authority:** `docs/prds/pr-review-agent.md` ("Operator approval") for the gate, and `docs/prds/state-store-contract.md` (rev. 2e) for every task field that crosses the State Store.
|
||||
**Compounds with:** `docs/prds/execution-tree-state-machine.md` (a run cannot resume partway through its stage list).
|
||||
|
||||
## Decision 1 — where the operator answers
|
||||
|
||||
The dashboard's `POST /api/tasks/{id}/action` (`internal/webui/api_tasks.go`, `handleTaskAction`) is the authoritative surface: the only one that resolves the actor from a credential and can carry a payload. Chat is a shortcut, not a second authority — `/approve` (`internal/gateway/gateway.go`, `Router.handleApprove`) answers the post decision with every offered finding selected, and gains no instruction or selection syntax.
|
||||
|
||||
`taskstate.Action` gains `rereview`, and `taskstate.Actions` returns `approve`, `reject` and `rereview` for `WaitingHuman`. `approve` posts the review, `reject` discards it through the existing terminal decline, `rereview` reruns the review phases with instructions. The action body carries `instructions`, required by `rereview`, and `findings`, the finding keys `approve` posts; an absent selection means all of them.
|
||||
|
||||
The path is `handleTaskAction` → `applyOperatorTaskAction` → `Chat.Contract.ApplyOperatorTaskAction` → the daemon's `LocalChatAdapter` → `taskactions.Client` (NATS `archie.gateway.task-action`) → `taskactions.Service.Apply` → one guarded store write that records the decision and requeues. Chat's `/approve` path (`StoreTaskController.Approve` → `chatTaskControllerAdapter.ApproveChatTask`) must reach that same write through the same function, so the two surfaces cannot record different decisions for one operator intent.
|
||||
|
||||
A requeue resumes the workflow the waiting state names, never a name the handler hardcodes. `taskactions.Service.apply` and `chatTaskControllerAdapter.ApproveChatTask` requeue every approval under `implement`, which is the feasibility handoff: an approval whose wait recorded `pr-review` would run the implement workflow. Feasibility must keep that handoff by naming `implement` on the task before it enters the wait, which is the invariant the handler needs — the workflow a task carries is the workflow it runs next. `Requeue` treats an empty workflow as "keep the task's".
|
||||
|
||||
### The review the operator answers
|
||||
|
||||
The gate writes the review it is holding onto the task before it ends the run: one JSON column, `review_gate`, a sibling of `review_payload`, holding the scored findings, the head SHA, the pull request's identity and the workflow the wait resumes. The run's existing `Store.Update` persists it. The same column carries the answer back: the response path's guarded write fills in the outcome, the selection and the instructions, and clears the offer for a re-review.
|
||||
|
||||
The operator reads the offer through the existing task read — `taskView.Task` on `GET /api/tasks` and `GET /api/tasks/{id}/debug` — so no new read endpoint is needed.
|
||||
|
||||
This record is load-bearing because the run that computed the findings ends at the gate and the engine cannot resume it partway. Without it, "post the selected findings" cannot mean the findings the operator saw: the resumed run recomputes them with agent calls. An `approve` resume therefore posts the recorded review filtered by the selection, and the review the resumed phases recompute never reaches the output.
|
||||
|
||||
## Decision 2 — the cap
|
||||
|
||||
The cap is a column: `rereview_rounds` on `tasks`, `bigint NOT NULL DEFAULT 0`, read by the response path and incremented in the same guarded write that requeues a re-review. A re-review at the cap is refused with the conflict sentinel the dashboard answers 409 with, and nothing is requeued. Two is a constant in the domain, not a config knob: the PRD fixes it.
|
||||
|
||||
`Task.Attempt` cannot carry the count, because it counts every requeue. The two alternatives are worse.
|
||||
|
||||
- The execution tree measures passes through the gate, not operator requests. A crash recovery (`RecoverStale`) or an operator retry re-runs the pipeline to the gate and would consume the cap; and a stage has no step read (`task.Store` carries none), so this route needs a new interface method anyway.
|
||||
- `Task.Notes` is the agent memory ledger, not scratch. `AgentStage.buildRequest` passes it into every generic agent request, `agentexec` renders it as a prompt section, and `persistAppendedNotes` appends to it. A counter parsed out of a field agents write to is the encoded-state defect this repository rejects, and instructions parked there would reach every unrelated workflow's agents.
|
||||
|
||||
`RemediationRounds` is the precedent: one writer, one reader, one meaning, kept separate from `RetryCount` so unrelated retries cannot draw a budget down.
|
||||
|
||||
The write crosses the State Store. A goose migration adds the column; `internal/infrastructure/postgres/queries/tasks.sql` and its sqlc output carry it; `internal/infrastructure/postgres/store.go` maps it; `proto/state/v1/state.proto` carries it as a new `Task` field with its regenerated contracts and `staterpc/values.go` mapping both ways; `internal/domain/workflow/task/task.go` declares it; `internal/infrastructure/taskactions/store.go` adds it to the `taskactions.Task` projection the response path reads. The write itself is a guarded requeue method beside `RetryTask`, which increments a counter, and `BeginRemediation`, which records a payload in the same transaction: one transition-table guard, one increment and one requeue in one write. It must join every column-listing query, which `docs/development/state-store.md` names.
|
||||
|
||||
Tests that prove it: the guarded write increments for a re-review and for no other requeue; a re-review at the cap is refused and leaves the task waiting; and the field survives the wire, which `TestTaskProtoCarriesEveryDomainField` asserts for every field of the domain task.
|
||||
|
||||
## Decision 3 — how the instructions reach the stages
|
||||
|
||||
The recorded instructions enter the pipeline at phase 3 and phase 4 only, which is what the PRD asks for: a labelled operator-instructions block appended to `runLens`'s mission in `stagePRLenses` and to `runReviewer`'s mission.
|
||||
|
||||
They cannot ride `AgentStage.buildRequest`. Every pr-review stage builds its `agentexec.Request` in `runPRReviewAgentRecorded`, which sets no `Request.Notes`, so nothing the generic path threads reaches these calls. The pipeline restores the instructions from the task record at the same point it restores the review, and the two mission builders read them there.
|
||||
|
||||
## The gate is not reachable from archie's own PRs
|
||||
|
||||
`StagePRReviewAndOpenPR` splices `prReviewDecisionStages()`, the list `PRReview()` uses, so the gate is reachable from the implement workflow too. It must not be. The change is one entry moving: `stagePROperatorApproval()` leaves the shared list for `PRReview()`'s own stage list, immediately before the merge gate, and the own-PR splice keeps taking the shared list unchanged. This is a prerequisite for the response channel and a change of its own.
|
||||
|
||||
Three reasons, the second deciding it alone.
|
||||
|
||||
- The gate's question is which findings to post, and on archie's own PRs there is no pull request to post to at the point the splice reaches the gate. That trigger's human decision point is its park on an unchallenged blocking finding.
|
||||
- Approving a wait inside the implement workflow re-enters that workflow at its first stage against a worktree that already carries the change. A builder that then reports no changes sets `BuildNoChanges`, `StageCommitPush` calls `closeNoChangesIssue`, and the issue is closed with no pull request ever opened. Nothing the gate decides is worth a route to silently closing an issue.
|
||||
- Short-circuiting instead would put a conditional no-op in every stage whose work a wait had completed, which changes the resume semantics of the whole pipeline rather than this gate.
|
||||
|
||||
## What a full restart gives, and what it costs
|
||||
|
||||
A requeue re-runs the workflow's stage list from its first stage; the engine has no partway resume. That satisfies the PRD's "reruns phases 3 to 8" for free, and it is acceptable for the standalone pipeline precisely because that pipeline has no stage that writes and then closes. The costs:
|
||||
|
||||
- Phases 1 and 2 recompute. Both are code except two agent calls — the machine-written score and the anatomy narrative — so those re-run, and a changed score can change whether the hallucination-check dimension is added.
|
||||
- The pull request's snapshot is checked out again.
|
||||
- The run's cost and wall-clock budgets are per attempt, so a re-review starts with a fresh allowance, which the cap bounds.
|
||||
|
||||
## Verification
|
||||
|
||||
- A gate wait on the standalone `pr-review` workflow answered `approve` posts exactly the findings the operator selected, and no finding the resumed phases produced.
|
||||
- A re-review at the cap is refused, the task stays waiting, and the count survives a store round trip.
|
||||
- A re-review's instructions reach the lens and reviewer missions; a first run's do not.
|
||||
- The gate is unreachable from the implement workflow's stage list.
|
||||
@@ -0,0 +1,123 @@
|
||||
# Review settings resource
|
||||
|
||||
**Status:** Draft
|
||||
**Beads issue:** `archie-core-0ry6`
|
||||
**Authority:** `docs/prds/runtime-control-plane.md` for the resource model,
|
||||
`docs/architecture/configuration.md` for ownership, and
|
||||
`docs/prds/pr-review-agent.md` for what the two dials do.
|
||||
|
||||
## Decision
|
||||
|
||||
`review.precision_gate` and `review.approve_before_post` are one control-plane
|
||||
resource, `review-settings`. The file's `[review]` section seeds it, the stored
|
||||
document outranks the file from then on, and the dashboard writes it through the
|
||||
same settings machinery as every other resource.
|
||||
|
||||
The resource is deployment-wide, like every definition the State Store seeds
|
||||
(`storecontract.DefaultOrgID`): not per-repository, per-identity, or per-run.
|
||||
|
||||
## Why its own kind
|
||||
|
||||
The two dials are pr-review policy — what a review may post, and whether a human
|
||||
decides — not a limit on a task run. The document that carries task limits
|
||||
belongs to that feature. `runtime-control-plane.md` splits settings by feature
|
||||
and refuses documents unrelated features share; `configuration.md` puts a typed
|
||||
runtime setting with the domain whose behaviour it describes. One document per
|
||||
feature is the rule, not one document per settings page.
|
||||
|
||||
A new kind also has no legacy documents. Its first value is the seed derived
|
||||
from the file, so "the store outranks the file" begins from an explicit copy of
|
||||
both fields rather than from a document that predates them.
|
||||
|
||||
## Document
|
||||
|
||||
New file `internal/app/controlplane/review_settings.go`:
|
||||
|
||||
```go
|
||||
const ReviewSettingsKind = "review-settings"
|
||||
|
||||
type reviewSettings struct {
|
||||
PrecisionGate bool `json:"precision_gate"`
|
||||
ApproveBeforePost bool `json:"approve_before_post"`
|
||||
}
|
||||
```
|
||||
|
||||
Its `Definition` sets `ApplyMode: "live"`, `Document: reviewSettings{}`, and a
|
||||
`Seed` returning `reviewSettings{cfg.Review.PrecisionGate, cfg.Review.ApproveBeforePost}`,
|
||||
and a `Validate` wrapping `validateAs`: both fields are free booleans with no cross-field
|
||||
rule, so the validator is a named place to put one rather than an inline no-op
|
||||
(`validatePluginSettings` is the precedent). No `Normalize`, because the kind
|
||||
has no second wire shape to converge.
|
||||
|
||||
## Seeding
|
||||
|
||||
`ImportConfig`/`seededValues` write the seed for a kind the store does not hold,
|
||||
so a deployment that never edited the dials runs the values in `[review]`. Once
|
||||
a document is stored, the file key stops mattering, which is the rule for every
|
||||
database-owned setting.
|
||||
|
||||
## Apply
|
||||
|
||||
`runtimeConfigFrom` in `internal/app/controlplane/runtime_config.go` layers the
|
||||
stored document over the file's `Review`, assigning `out.Review.PrecisionGate`
|
||||
and `out.Review.ApproveBeforePost` field by field. Field-by-field, not
|
||||
`out.Review = ...`: a field added to `config.Review` later keeps the file's value
|
||||
until the document carries it.
|
||||
|
||||
`ReviewSettingsKind` joins `runtimeResourceKinds` in
|
||||
`internal/app/archied/control_plane.go`, so a new stored version re-runs the
|
||||
layering and republishes through `config.Holder`. Live rather than
|
||||
restart-required, because every consumer re-reads it: `Review` is on
|
||||
`reloadableFields` in `internal/app/archied/reload.go`, and the value reaches a
|
||||
run through `Daemon.configFor` → `Config.ForTask` → `TaskConfig.ToConfig` →
|
||||
`TaskContext.Cfg`, which `stagePRPrecisionGate` and `stagePROperatorApproval`
|
||||
read. The next task run uses the new value; a run in flight keeps the value it
|
||||
started with.
|
||||
|
||||
## Projection and page
|
||||
|
||||
`BuildConfigView` gains a plain `Review` field carrying both values out of
|
||||
`cfg.Review`, the way `BudgetsView` carries the layered budgets, so the published
|
||||
config snapshot tells any reader what is in force. The Review page renders the
|
||||
two toggles from the control-plane store's draft for `review-settings` — the
|
||||
shape `SystemTasksPage.vue` uses for `workflow-execution-settings` — and shows
|
||||
the projected value beside them; a Settings route plus a `PAGE_RESOURCES` entry
|
||||
(`ui/src/stores/control-plane.ts`) bind the page to the kind.
|
||||
|
||||
Nothing else re-advertises them. `configFieldDescriptors` and `ConfigView.Schema`
|
||||
gain no `review.*` row: the config catalog's generic renderer was deleted, so a
|
||||
descriptor row adds a field nothing can edit, which is the shape `becb0b5e`
|
||||
removed.
|
||||
|
||||
## What the test proves
|
||||
|
||||
`internal/app/controlplane/runtime_config_test.go` adds the round trip that
|
||||
builds the effective config the way boot does: seed the kind from a file config
|
||||
with both dials set one way, store a document with both flipped, layer it
|
||||
through `runtimeConfigFrom`, and assert the effective `cfg.Review` equals the
|
||||
stored document. A second case covers the absent kind, where the file's values
|
||||
stay in effect. The assertion is on `cfg.Review` — the value `TaskContext.Cfg`
|
||||
carries into the two stages — not on a struct the test set directly.
|
||||
`TestRuntimeResourceKindsApplyLive` gains `review-settings` as live. The
|
||||
validator needs no `validators_agree_test.go` case: it wraps `validateAs` with
|
||||
no rule, because no combination of the two booleans is invalid, and a case that
|
||||
cannot fail is a test the project then carries for nothing.
|
||||
|
||||
## Rejected: extending workflow-execution-settings
|
||||
|
||||
That resource is `workflow.ExecutionSettings`, "the limits captured when a
|
||||
workflow execution starts". Putting review policy in it makes the review feature
|
||||
a field of the limits document, gives a boolean edit a ride on a document whose
|
||||
candidate is validated and swapped as one unit with the budgets, and forces
|
||||
absence-aware pointer fields onto booleans so a document stored before the fields
|
||||
existed does not turn a file's `precision_gate = true` into `false`. It buys one
|
||||
less kind at the cost of the ownership rule the model is built on.
|
||||
|
||||
## Out of scope
|
||||
|
||||
- Per-repository, per-identity, or per-workflow review settings. A scope key is
|
||||
a later decision with its own resource shape.
|
||||
- Any other review knob. A field joins the document only with a consumer, the
|
||||
rule every config field carries.
|
||||
- The reviewer pipeline's behaviour. This document places the settings; it does
|
||||
not change what they do.
|
||||
@@ -45,6 +45,14 @@ version being edited. The API layer sets the actor; the request body cannot.
|
||||
The server validates the change, then writes it with its audit record. It rejects
|
||||
edits to an old version.
|
||||
|
||||
The request ID is the write's idempotency key, and it is scoped per org and
|
||||
per kind, never global. The key is `(org_id, kind, request_id)` — the unique
|
||||
index `idx_resource_history_org_kind_request` (migration `0021_resources_per_org.sql`)
|
||||
— so replaying a request ID is the same org's prior write of the same kind, and
|
||||
a request ID reused across orgs or across kinds is a separate write. This is the
|
||||
same scoping as the task idempotency key `org/identity/owner/repo/number`
|
||||
(`docs/prds/orgs-and-access.md`).
|
||||
|
||||
## API
|
||||
|
||||
The API has four operations:
|
||||
@@ -76,8 +84,11 @@ and encryption-key references. State Store and control-plane RPCs use the same
|
||||
endpoint.
|
||||
|
||||
When upgraded, existing instances are migrated to the database. Existing
|
||||
database values are not overwritten. After migration, settings in TOML are
|
||||
ignored and cannot block State Store startup.
|
||||
database values are not overwritten, with one exception: a resource whose
|
||||
document the build ships is refreshed when the seed itself wrote the stored
|
||||
copy, because that copy is a previous release's document rather than an
|
||||
operator's. After migration, settings in TOML are ignored and cannot block
|
||||
State Store startup.
|
||||
|
||||
The Web UI remains available when `archied` or Gateway is down. It shows failed
|
||||
changes and can correct or roll them back.
|
||||
|
||||
@@ -0,0 +1,142 @@
|
||||
# SOUL: an agent's user-authored personality
|
||||
|
||||
**Status:** Draft
|
||||
**Authority:** `docs/architecture/identity.md`, “Three-layer identity model”;
|
||||
`docs/prds/orgs-and-access.md` for identity and org ownership.
|
||||
|
||||
## Decision
|
||||
|
||||
SOUL supplies an agent's name, register and warmth. It belongs to the agent's
|
||||
immutable `IdentityID`, not its session, model, installation or container
|
||||
profile. Rename preserves it; changing a profile does not change who acts.
|
||||
SOUL never changes attribution, credentials, grants or identity lifecycle.
|
||||
`config.AgentProfile` remains an execution environment, not another identity.
|
||||
|
||||
Use the existing three layers: invariants, user-authored SOUL, and curator-derived
|
||||
representation. Curators may propose SOUL changes but never apply them.
|
||||
|
||||
## Files and ownership
|
||||
|
||||
The config directory is `${XDG_CONFIG_HOME:-~/.config}/archie`, or the directory
|
||||
of an explicitly selected config file. The default/root agent uses `SOUL.md`
|
||||
directly there; additional agents use `agents/<identity-id>/SOUL.md`. The root is
|
||||
the identity selected by application composition, never the initiating user or
|
||||
a session's personality selection. No file creates or selects an identity.
|
||||
|
||||
The common case keeps a human-friendly filename; additional agents get separate
|
||||
asset directories, following `.agents/skills/<name>/SKILL.md` without confusing
|
||||
these directories with `[containers.profiles.<name>]`. Reject display-name or
|
||||
slug directories: rename and same-name agents across orgs would require another
|
||||
name-resolution rule. Immutable IDs avoid both problems without an org directory.
|
||||
|
||||
When a file-owned agent's file is absent, create the shipped default with
|
||||
exclusive creation. Never overwrite an existing file, including an empty one.
|
||||
A creation failure still permits the turn using the embedded shipped default.
|
||||
Ship that document independently of `agent.ShippedPersonas`, so deleting personas
|
||||
cannot delete the fallback.
|
||||
|
||||
Resolve once at the start of every new generation:
|
||||
|
||||
1. A stored SOUL entry for the acting identity is authoritative.
|
||||
2. Without an entry, read that identity's file again.
|
||||
3. An absent, empty, unreadable or invalid selected source uses the shipped default.
|
||||
|
||||
The first explicit dashboard/API save takes ownership permanently. Thereafter
|
||||
file edits are ignored: emit one ownership notice and show the owning stored
|
||||
version in the dashboard. Restoring the shipped default writes a stored value;
|
||||
it does not remove ownership. Refuse writes that remove an owned entry.
|
||||
|
||||
This ownership boundary is the design's one stateful rule. Files seed the
|
||||
editable value, not an automatic durable import. Reject seed-once import because
|
||||
it breaks next-message file editing; reject file-always-wins because it makes
|
||||
dashboard saves ineffective. Neither a restart nor an upgrade overwrites an
|
||||
owned value, following the precedence of `controlplane.AgentProfileKind` without
|
||||
copying its startup import timing.
|
||||
|
||||
## Prompt and failure contract
|
||||
|
||||
Keep `archie.md.tpl`'s XML-escaped
|
||||
`<soul purpose="identity_and_style" trust="data">` block before
|
||||
`<instruction_precedence>`. SOUL is style reference data; the invariant sections,
|
||||
tool inventory and runtime metadata remain authoritative and uneditable.
|
||||
Preserve `TestBuildSystemPromptSoulCannotOverrideInvariants`.
|
||||
|
||||
Accept UTF-8 plain Markdown with at most 8 KiB in its XML-escaped body. This bounds
|
||||
personality to a small prompt contribution; count the complete rendered prompt
|
||||
in the turn's context budget and never truncate invariant sections. Bound file
|
||||
reads before decoding; reject oversize input rather than truncating instructions.
|
||||
File and stored writes use the same validator; an invalid save leaves the stored
|
||||
version unchanged. The shipped default must pass that validator.
|
||||
|
||||
Read and creation errors never fail a turn. Log once per identity/source failure
|
||||
episode, retry on the next turn, and allow a new warning after recovery. If the
|
||||
store cannot establish whether an owned entry exists, use the shipped default,
|
||||
not a potentially shadowed file. Do not log SOUL text. Each turn keeps its resolved
|
||||
snapshot; edits affect the next generation without restart or SIGHUP.
|
||||
|
||||
## Cross-layer delivery
|
||||
|
||||
- `internal/domain/agent` owns SOUL content validation and the identity-keyed read
|
||||
contract; `internal/domain/identity` remains the actor/lifecycle authority.
|
||||
- The configuration infrastructure resolves the config directory and handles
|
||||
file discovery, exclusive default creation and bounded per-turn reads.
|
||||
Application composition resolves the acting `IdentityID` through the existing
|
||||
identity repository/bindings and supplies it to the gateway.
|
||||
- Register `SoulKind` (`agent-souls`) in the control plane with a live descriptor
|
||||
and an org-scoped document mapping identity IDs to `{text}`. Persist it through
|
||||
the State Store's existing resource/history contracts, not a new table,
|
||||
process or SOUL RPC. An empty map owns no identity; saves preserve other entries
|
||||
and use expected-version checks. Validate that each key is an agent identity
|
||||
in the resource's org; begin with the default org without inventing org setup.
|
||||
Every save records the authenticated editor's identity, source, request ID and
|
||||
timestamp; file installation records the system identity, not a fictitious user.
|
||||
- Replace `TurnRunnerConfig.Personas` / `PersonaPromptSource` with the per-identity
|
||||
source in `prepareTurn`; name the `SystemPromptConfig` input SOUL. Both normal
|
||||
and streaming turns use this assembly path. Do not add personality to the
|
||||
worker environment, `AgentProfile` or workflow-stage prompts.
|
||||
- On an agent identity's dashboard page, expose its effective SOUL, file/default
|
||||
or stored source, shadowed file path, owning version, and Markdown editing.
|
||||
Save to the control plane, never the host file; show validation/version
|
||||
conflicts and offer restoring shipped content or a history revision as a save.
|
||||
Read effective file/default content and ownership metadata through a gateway
|
||||
query using the turn resolver; the separate UI process never reads the
|
||||
gateway host's files. Apply identity-management access rules and the existing
|
||||
shared live-update hub.
|
||||
- Update `docs/development/agent.md` and `control-plane.md` with this reach and
|
||||
precedence, `frontend-ui.md` with the gateway query, and the config wiring
|
||||
guidance with a copyable file example.
|
||||
|
||||
## Persona removal gate
|
||||
|
||||
SOUL supersedes `PersonaRegistry` and the persona-reconciliation proposal;
|
||||
identity-per-action supersedes personas as an identity mechanism.
|
||||
`PersonaRegistry.GetActive` composes the baseline with one of five styles from
|
||||
`agent.ShippedPersonas`; SOUL replaces the baseline, not that style catalogue.
|
||||
Per-session switching disappears: remove `/personality`, Telegram personality
|
||||
callbacks, the dashboard persona page, and chat wire fields `personas`,
|
||||
`active_personas` and `personas_available` without reusing their field numbers.
|
||||
Do not merge session selections into SOUL or retain a separate style axis.
|
||||
Custom persona text must remain available to copy before deleting its stored
|
||||
resource; no migration guesses one agent's SOUL from several sessions.
|
||||
|
||||
Remove persona loading, selectors and commands only after every chat composition
|
||||
supplies the identity-aware SOUL source, the fallback renders without personas,
|
||||
and the dashboard can edit it. SOUL delivery does not wait for org creation or a
|
||||
new container-profile model.
|
||||
|
||||
## Acceptance
|
||||
|
||||
- Two agents use distinct files and stored entries; renaming one or sharing a
|
||||
container profile does not change or mix their SOULs.
|
||||
- Before ownership, a file edit changes the next normal or streaming prompt;
|
||||
creating defaults never clobbers an existing file.
|
||||
- After a save, conflicting file edits and restarts cannot override the stored
|
||||
value; the ignored file and owning version are visible. Updating one agent
|
||||
preserves the other; stale saves fail and history restores are audited saves.
|
||||
- Missing, empty, unreadable, malformed and oversize selected inputs render the
|
||||
shipped default. Repeated read failures log once, recover on a later turn,
|
||||
and never abort generation.
|
||||
- Hostile markup stays escaped before singular, unchanged invariant blocks;
|
||||
prompt budgeting includes SOUL and cannot drop the rules.
|
||||
- Dashboard edits reach the next generation without restart; persona removal
|
||||
leaves every channel with a nonempty identity slot and preserved custom text.
|
||||
@@ -265,13 +265,15 @@ _view_, not new RPCs — `Update`/`Transition`/`InsertEvent` are shared with
|
||||
| Binding | `InsertBinding`, `GetBinding`, `ListBindings`, `UpdateBinding`, `DeleteBinding`, `ApproveBinding` |
|
||||
| Dispatch | `ArmedBindingsForSource`, `RecordDispatch`, `ListUndispatchedCaptures` |
|
||||
| Playbook | `RecordPlaybookDispatch`, `DeletePlaybookDispatches` |
|
||||
| WorkflowCaller | `EnqueueCallTask`, `WorkflowCallStatus` |
|
||||
| Step executions | `StartStep`, `FinishStep` |
|
||||
| BindingTaskCreator | `EnqueueBindingTask` |
|
||||
| Config snapshot | `PutConfigSnapshot`, `GetConfigSnapshot` |
|
||||
| Apply status | `PutApplyStatus`, `ListApplyStatus` |
|
||||
| Channel status | `PutChannelStatus`, `ListChannelStatus` |
|
||||
| Task log | `ReadTaskLog`, `StreamTaskLogContent` |
|
||||
|
||||
That is **51 unique contract RPCs** across one service (the `TaskEvents.Close` method is dropped).
|
||||
That is **55 unique contract RPCs** across one service (the `TaskEvents.Close` method is dropped).
|
||||
`Close()` is **excluded** from the wire (it is server lifecycle, not a client call) — see §11.
|
||||
|
||||
The channel-status pair follows the config snapshot's split for the same reason: the writer is the process that HOSTS the channels -- the Messaging Service, which alone observes whether a channel is starting, running or failed -- and the reader is the UI process. Both RPCs are administrative, so a task-scoped grant reaches neither. A channel's state is runtime state rather than a settings document, which is why it is not a `ControlPlaneService` resource kind: a failed channel is not a document anybody edits. Asking for a reload travels on its own surface rather than through this one; see `docs/architecture/migration-decisions.md`, "Channel state to the dashboard".
|
||||
@@ -306,6 +308,25 @@ condition, and the panel that collapsed them told operators task logging was swi
|
||||
it was not. The Go facade is `storecontract.TaskLogStore` (2 methods), carried by
|
||||
`*staterpc.Client` alongside the rest.
|
||||
|
||||
The step-execution pair was added by the execution tree's plan item 3 (see
|
||||
`docs/prds/execution-tree-state-machine.md`), the surface a task-scoped grant reaches for
|
||||
its own execution beyond the three `task.Store` RPCs and the workflow-caller pair: the
|
||||
container records its stages and its own agent calls with the run credential. Both requests
|
||||
carry the caller's execution ID, which the grant check verifies; `FinishStep` additionally
|
||||
verifies, handler-side, that the step really is that execution's. The store writes each
|
||||
transition's `stage_start`/`stage_finish` event row in the same transaction and returns it
|
||||
for the caller's post-commit bus publish. `called_execution_id` is stored for the `call`
|
||||
kind but not yet carried on the wire: the named consumer is the workflow-call recording
|
||||
that will set it.
|
||||
|
||||
The workflow-caller pair was added by `archie-core-t2db.41` (see everything else from the caller's
|
||||
row and refuses a caller that is not running or a call past the depth limit
|
||||
(`ErrCallCallerNotRunning` / `ErrCallDepthExceeded`), and `WorkflowCallStatus`
|
||||
re-checks the parent-child relation against the row before answering
|
||||
(`ErrCallNotYours`), so the interceptor itself never reads the database. The
|
||||
facade is `workflow/task.Caller` (2 methods), carried by `*staterpc.Client`
|
||||
and the PostgreSQL store alike.
|
||||
|
||||
The playbook pair was added by `archie-core-t2db.17`'s implementation (see
|
||||
`docs/prds/eda-playbook-engine.md`, execution-time gap 2). It is administrative
|
||||
for the same reason as the config-snapshot and apply-status pairs, and
|
||||
@@ -551,9 +572,12 @@ stated explicitly rather than left implicit.
|
||||
cannot leave a grant valid indefinitely.
|
||||
- **Validation and scope (`.4.7`):** a gRPC interceptor (`staterpc.TaskGrants.UnaryInterceptor`)
|
||||
validates the token against the State Store's own issued-grant set; missing/unknown/expired →
|
||||
`codes.Unauthenticated`. Unlike the daemon's own administrative token (full access to all ~40
|
||||
RPCs), a task-scoped grant additionally authorises only `Update`/`Transition`/`InsertEvent` on
|
||||
its own task ID — every other RPC, including the streaming capture surface and
|
||||
`codes.Unauthenticated`. Unlike the daemon's own administrative token (full access to all RPCs),
|
||||
a task-scoped grant additionally authorises only `Update`/`Transition`/`InsertEvent` on
|
||||
its own task ID, plus the two workflow-caller RPCs naming that same task ID
|
||||
(`EnqueueCallTask`/`WorkflowCallStatus`, `docs/prds/workflow-calls.md` — the one
|
||||
sanctioned widening: the callee is the caller's child). Every other RPC, including the
|
||||
streaming capture surface and
|
||||
`RegisterTaskGrant`/`RevokeTaskGrant` themselves, is `codes.PermissionDenied` for a task-scoped
|
||||
caller. The token is carried in gRPC metadata, never in a URL.
|
||||
|
||||
|
||||
@@ -0,0 +1,213 @@
|
||||
# Declared outputs of a workflow run
|
||||
|
||||
**Status:** Draft
|
||||
**Date:** 2026-09-30
|
||||
**Bead:** `archie-core-t2db.43`
|
||||
**Authority:** `docs/prds/event-automation.md` for what a declared output is,
|
||||
`docs/prds/workflow-calls.md` for the call and its grants,
|
||||
`docs/prds/state-store-contract.md` for the State Store contract the wire
|
||||
change must satisfy.
|
||||
**Supersedes:** `docs/prds/workflow-calls.md`, "Waiting on the callee": the
|
||||
callee's transition detail is the human summary, not the stand-in for
|
||||
structured outputs.
|
||||
|
||||
A workflow declares named, typed outputs. A run writes each one once. A
|
||||
`wait: true` caller receives them, and may publish one as its own.
|
||||
|
||||
## Where outputs are declared
|
||||
|
||||
`outputs:` on the workflow definition, beside `inputs:`, decoded into
|
||||
`task.WorkflowInterface.Outputs map[string]OutputSpec` where
|
||||
`OutputSpec{Type, Required}`:
|
||||
|
||||
```yaml
|
||||
id: firewall-contain
|
||||
outputs:
|
||||
contained: { type: bool, required: true }
|
||||
summary: { type: string }
|
||||
```
|
||||
|
||||
Names and types are the input grammar: the same identifier shape, the same
|
||||
type set, and the same check in `WorkflowInterface.Validate`, which both
|
||||
`ParseDefinition` and `ParseWorkflowInterface` call.
|
||||
|
||||
**Forced by:** `ParseDefinition` decodes with `KnownFields(true)`, so a key no
|
||||
decoded struct declares is refused — the declaration must live on
|
||||
`WorkflowInterface` for an author to write it at all, and that is where
|
||||
`docs/development/workflows.md` puts every field a process without the engine
|
||||
must read. The type set is the shared value vocabulary: `TypeAccepts` and
|
||||
`ValueType` already check a mapped parameter and an input with it. `required`
|
||||
defaults to false, and the generated YAML for a builtin that declares no
|
||||
outputs is unchanged, because a definition's digest pins a run.
|
||||
|
||||
**Rejected:** outputs per step, or per call step, because a workflow returns a
|
||||
result as itself rather than as one of its stages. Also `task.Definition`
|
||||
gaining outputs: no reader needs them — a binding offers inputs, and a call's
|
||||
outputs assignment is checked against the callee's YAML in the same
|
||||
collection — and a declared field with no reader parses and does nothing.
|
||||
|
||||
## How a run writes one
|
||||
|
||||
Each declared output is offered to the run's agent stages as a capture tool
|
||||
named after the output, whose arguments are `{"value": ...}`; the accepted
|
||||
call's `value` member is the output's value. The engine holds the accepted
|
||||
values on the task context and writes them into its own task row in the
|
||||
`Store.Update` call the run already makes. A deterministic stage may set the
|
||||
same values in Go, and the run's finish check validates them identically.
|
||||
|
||||
**Forced by:** a run's only structured results are capture calls
|
||||
(`agentexec.CaptureTool`, `Result.Captures`), and the workflow interface
|
||||
already declares when a stage needs them (`task.WorkflowNeeds.Captures`).
|
||||
Deriving the tools from the declaration means an output cannot be written
|
||||
under a name nobody declared, and it keeps one route to structured agent
|
||||
output rather than adding a second beside the capture path. The row write is
|
||||
the run's existing write: the task row is where a run's own state lives, and
|
||||
the container already holds `Update` on its own row.
|
||||
|
||||
The tool is offered with `MaxCalls: 1`, and a stage is not offered an output
|
||||
the run has written, so a run writes each output once: a repeat within a stage
|
||||
is answered with the tool's rejection and the agent carries on, and a later
|
||||
stage cannot overwrite a value. A stage's own capture tool may not share a
|
||||
name with a declared output, because the value would otherwise be ambiguous.
|
||||
|
||||
**Rejected:** a `workflow.output` step type, because assigning the run's
|
||||
result from a step needs a grammar for "the previous stage's result" that does
|
||||
not exist, and a step that reaches the agent would be the second path
|
||||
`docs/development/workflows.md` forbids. Also a write RPC of its own: the
|
||||
container's `Update` already reaches its own row, and a second write verb for
|
||||
one column is a second thing to keep in step.
|
||||
|
||||
## How a caller receives one
|
||||
|
||||
On a successful `wait: true` call the caller's stage holds the callee's
|
||||
outputs as a `map[string]any`. A call step's `outputs:` setting publishes one
|
||||
as one of the caller's own outputs:
|
||||
|
||||
```yaml
|
||||
steps:
|
||||
- type: workflow.call
|
||||
workflow: firewall-contain
|
||||
wait: true
|
||||
inputs: { src_ip: inputs.src_ip }
|
||||
outputs: { contained: outputs.contained }
|
||||
```
|
||||
|
||||
The key names the callee's declared name; the value names one of the caller's
|
||||
own with the prefix the call's `inputs:` already uses. A published value joins
|
||||
the caller's output set for its run, so a caller returns its callee's result to
|
||||
its own caller, and a run may publish a callee's output and write its own
|
||||
others.
|
||||
|
||||
Lifetime is the attempt. The run starts with an empty output set, every later
|
||||
stage of that attempt sees the values, and the finish write replaces the row's
|
||||
set wholesale — so nothing an attempt wrote survives into the next, and a run
|
||||
that writes nothing stores nothing. Values reach a caller only from a
|
||||
successful terminal state: the caller assigns them after `callSucceeded`, so a
|
||||
parked or failed callee delivers nothing whatever its row holds. A call step
|
||||
with `wait: false` and an `outputs:` block is refused when the definition is
|
||||
saved, because nothing has finished when the caller moves on.
|
||||
|
||||
**Forced by:** caller and callee are separate runs in separate containers, so
|
||||
the caller's own row is the only durable place to hold a received value. The
|
||||
prefix rule is not a new grammar: in `inputs.<name>` the prefixed side is the
|
||||
caller's own value and the map key is the callee's, and `outputs.<name>` reads
|
||||
the same way in the other direction.
|
||||
|
||||
**Rejected:** an implicit same-name copy from callee to caller, because the
|
||||
caller's contract would then depend on a callee it does not name, and swapping
|
||||
the callee would silently change what the caller returns. Also letting a later
|
||||
stage read a callee's output in its mission text: that needs a stage-result
|
||||
reference namespace this model does not define.
|
||||
|
||||
## Failure rules
|
||||
|
||||
- **Undeclared value.** The agent path cannot produce one — the tool exists
|
||||
only for a declared output. A Go stage that sets an undeclared key parks the
|
||||
run before its outcome transition, and a stage capture tool sharing a
|
||||
declared output's name is refused when the run starts.
|
||||
- **Declared but never written.** With `required: true` the run parks naming
|
||||
the output and reaches no successful terminal state, so no caller observes a
|
||||
success missing a promised value. Without it the key is absent from the
|
||||
object rather than null, and a written `null` counts as not written, as
|
||||
`CheckInputs` treats a null input. A published output the callee never wrote
|
||||
leaves the caller's output absent, which the caller's own `required` then
|
||||
judges.
|
||||
- **Save time.** `WorkflowInterface.Validate` refuses an unknown type and a
|
||||
malformed name. A call step's `outputs:` assignment is checked by a
|
||||
`checkCallOutputs` beside `checkCallInputs`: the key must be declared by the
|
||||
callee, the reference must name an output the caller declares, and the
|
||||
callee's declared type must satisfy the caller's.
|
||||
- **Run time.** A captured value is re-validated against the declared type
|
||||
when the run reads it back, for the reason `readCaptures` re-checks every
|
||||
record: the captures file is writable by the harness user. A published
|
||||
callee value is re-checked against the caller's declared type before it
|
||||
enters the caller's set; a mismatch parks the caller naming the output.
|
||||
|
||||
**Rejected:** typing at save time only, because a captured value has no
|
||||
save-time form; and at run time only, because a definition error would surface
|
||||
as a failed run instead of a refused save.
|
||||
|
||||
## Storage and wire
|
||||
|
||||
- `tasks.outputs`, text, `NOT NULL DEFAULT ''`, written by the run's own row
|
||||
write — the shape `tasks.inputs` already has, with `EncodeOutputs` and
|
||||
`DecodeOutputs` beside `EncodeInputs`/`DecodeInputs`.
|
||||
- The `Task` message carries it as `outputs_json`, because the container's
|
||||
`Update` sends the whole row and a column the message cannot carry is a
|
||||
column that write drops.
|
||||
- `WorkflowCallStatusResponse` carries it as `outputs_json` beside `status`
|
||||
and `detail`, read from the callee's row by the handler that already
|
||||
verifies `call_parent_task_id`; `detail` keeps carrying the transition
|
||||
detail. The Go facade stays the two methods of `task.Caller`; no interface
|
||||
method is added.
|
||||
|
||||
**Forced by the grant:** a caller authenticates as its own task and may reach
|
||||
`WorkflowCallStatus` on its own task ID, `Update`/`Transition`/`InsertEvent`
|
||||
on its own row, and the step-execution pair on its own execution. It can read
|
||||
neither the callee's row nor the callee's steps. `WorkflowCallStatus` is
|
||||
therefore the only channel that exists, and it is already the sanctioned
|
||||
cross-run read — this model fills the placeholder it carries. The values live
|
||||
on the callee's row rather than on the caller's call step because the callee
|
||||
writes them and the caller only receives them.
|
||||
|
||||
The write order is part of the contract: a run persists its outputs before its
|
||||
outcome transition, so the status a caller sees when its wait ends already
|
||||
carries them. A set whose encoded form passes the bound the store applies to a
|
||||
structured payload (`clip`, as `ReviewPayload` is stored) is refused rather
|
||||
than clipped, because clipped JSON does not parse.
|
||||
|
||||
No sentinel moves: a missing required output is an engine park reason, and a
|
||||
caller asking about a task that is not its callee still gets `ErrCallNotYours`,
|
||||
so nothing new crosses `mapError`/`unmapError` and no canonical message string
|
||||
changes.
|
||||
|
||||
**Rejected:**
|
||||
- A new read RPC (`WorkflowCallOutputs`) — a second poll of a row the caller
|
||||
already polls, whose answer could disagree with the status beside it, and a
|
||||
second grant-widening row for the same parent-child check.
|
||||
- The step-execution record — `ListSteps` is granted by `read` on a run, so a
|
||||
caller cannot read the callee's steps at all, and making them readable would
|
||||
hand it the callee's whole step history, which the parent-child check exists
|
||||
to prevent. A step's `detail` is text clipped like every other detail.
|
||||
- The caller's call step as the store — the value originates in another
|
||||
process and must outlive the container that produced it.
|
||||
|
||||
## Out of scope
|
||||
|
||||
- A run started by a binding: it has no caller, and its outputs live on its
|
||||
own row only.
|
||||
- A stage reference to a previous stage's captured value.
|
||||
- Assigning outputs in a caller cancelled while it waits.
|
||||
|
||||
## Verification
|
||||
|
||||
- A definition whose output type is not in the vocabulary, and a call
|
||||
publishing an output neither side declares, are refused when saved.
|
||||
- A `wait: true` caller receives a value its callee wrote, returns it as its
|
||||
own output, and the caller's row carries it.
|
||||
- A run whose required output is never written parks, and its caller's stage
|
||||
fails naming the output.
|
||||
- A call step publishing an output over `wait: false` is refused when saved.
|
||||
- A retried attempt that writes no outputs leaves an empty set on the row.
|
||||
- An example under `examples/workflows/` carries an `outputs:` block and a
|
||||
call that publishes one, which `TestExampleWorkflowsParse` covers.
|
||||
@@ -0,0 +1,128 @@
|
||||
# Workflows calling workflows
|
||||
|
||||
**Status:** Draft
|
||||
**Date:** 2026-09-26
|
||||
**Bead:** `archie-core-t2db.41`
|
||||
**Extends:** `docs/prds/event-automation.md` (workflow/binding/profile model), `docs/prds/state-store-contract.md` (two new RPCs), `docs/prds/execution-tree-state-machine.md` (call kind)
|
||||
|
||||
## The call, end to end
|
||||
|
||||
```
|
||||
caller run (in agent container)
|
||||
workflow.call step ──StartCall──▶ State Store EnqueueCallTask(caller, workflow, inputs)
|
||||
│ callee task row: org/identity/owner/repo
|
||||
│ derived from the caller row server-side
|
||||
▼
|
||||
callee task (queued, org of the caller)
|
||||
│ daemon claims, pins the callee's OWN
|
||||
│ definition → its OWN agent profile
|
||||
▼
|
||||
callee run (its own container, own tree)
|
||||
wait: true ──poll──▶ State Store WorkflowCallStatus(caller, callee)
|
||||
wait: false ──continue
|
||||
```
|
||||
|
||||
A `workflow.call` step starts the callee as a first-class task and, with
|
||||
`wait: true`, waits for its terminal state. The callee is never run "inside"
|
||||
the caller: it gets its own task row, its own pinned definition, its own
|
||||
profile, its own container, and its own outcome on its own run
|
||||
(`execution-tree-state-machine.md`).
|
||||
|
||||
## Save-time checks (the collection is the authority)
|
||||
|
||||
All semantic checks run in `workflow.ValidateDefinitionCollection`, the gate
|
||||
every save and load of the `workflow-definitions` resource passes through.
|
||||
A single-definition parse cannot see callees, so it validates shape only.
|
||||
|
||||
- **Callee exists.** A call to a workflow outside the collection is refused.
|
||||
- **Inputs checked.** A call value is a literal or a reference
|
||||
(`inputs.<name>`) to the calling workflow's declared input. References must
|
||||
name a declared input; the resolved type must satisfy the callee's declared
|
||||
type; unknown callee inputs are refused; a required callee input must be
|
||||
assigned.
|
||||
- **Self-calls refused.** The call graph over the collection is walked from
|
||||
every workflow; a workflow that reaches itself, directly or through other
|
||||
workflows, is refused with the cycle path. (Cycles can otherwise deadlock:
|
||||
`wait: true` callers hold their containers.)
|
||||
- **Repository.** `workflow.call` needs no repository, so it is legal in a
|
||||
`repository: none` workflow: the callee inherits the caller's task record
|
||||
(owner/repo/identity/org), and the callee's own `repository` mode decides
|
||||
whether its run clones.
|
||||
- **Org enablement** (bead `archie-core-t2db.42`): the single
|
||||
instance-wide collection the current model serves is what "enabled for
|
||||
the caller's org" resolves against — an undefined callee parks. The
|
||||
callee's org is derived from the caller's row, so a callee is never
|
||||
visible outside its caller's org. The per-org enable/disable catalogue
|
||||
lands with `archie-core-t2db.42` and becomes the one source of this
|
||||
predicate.
|
||||
|
||||
## Runtime
|
||||
|
||||
**Depth limit.** `workflow.MaxCallDepth` (5). The calling stage refuses a call
|
||||
that would exceed it; the store re-checks on insert (callee depth = caller
|
||||
depth + 1), so no path can enqueue past the limit.
|
||||
|
||||
**Starting the callee.** The caller runs inside a container whose task-scoped
|
||||
State Store grant authorizes only `Update`/`Transition`/`InsertEvent` on its
|
||||
own task — it can neither enqueue a task nor read another one. One new
|
||||
contract RPC starts the callee:
|
||||
|
||||
- `EnqueueCallTask(caller_task_id, workflow, inputs_json) → task`
|
||||
— the store reads the caller row, refuses a caller that is not `running`,
|
||||
refuses past the depth limit, and inserts the callee row deriving org,
|
||||
workspace, identity, owner, repo and a fresh synthetic issue number from
|
||||
the caller (the same org COALESCE `EnqueueIssue`/`InsertChatTask` use). The
|
||||
callee row carries `call_parent_task_id` and `call_depth`.
|
||||
|
||||
**Waiting on the callee.** One new read RPC returns a call's callee:
|
||||
|
||||
- `WorkflowCallStatus(caller_task_id, call_task_id) → (status, detail)` — the
|
||||
handler verifies `call_parent_task_id` matches, so a caller reads only its
|
||||
own callees, and returns the callee's status plus its latest transition
|
||||
detail (the callee's summary — the wait:true "outputs" until a structured
|
||||
outputs model lands).
|
||||
|
||||
Both RPCs are admitted to task-scoped grants on `caller_task_id == granted
|
||||
task ID` (`authorizesTaskScopedCall` gains two request-shape cases). This is
|
||||
the one sanctioned widening of a task grant: the callee is the caller's child,
|
||||
and starting it is the mechanism by which one event becomes several runs. The
|
||||
widenings stay request-shape checks; the parent-child authorization is a
|
||||
handler-side row check, so the interceptor never reads the database.
|
||||
|
||||
**Schema.** `tasks` gains `call_parent_task_id` (bigint, default 0) and
|
||||
`call_depth` (int, default 0); both cross the wire on the `Task` message.
|
||||
Columns default so existing writers and rows read as depth-0 root runs.
|
||||
|
||||
**The engine capability.** The workflow domain owns a consumer facade,
|
||||
`task.Caller` (2 methods), carried by `*staterpc.Client` and wired into
|
||||
`TaskContext.Calls` by the agent worker's composition root — the same shape
|
||||
as `workflow.Store`. A runner with no `Calls` capability fails a
|
||||
`workflow.call` step with a named error rather than pretending.
|
||||
|
||||
**Semantics.**
|
||||
|
||||
- `wait: false` — start, record a durable `workflow_call_started` event, and
|
||||
continue. The callee's outcome is reported on its own run.
|
||||
- `wait: true` — start, then poll `WorkflowCallStatus` (2 s, bounded by the
|
||||
task's wall clock) until the callee is terminal. `completed`, `pr_open` and
|
||||
`merged` succeed the step; `parked`, `failed`, `rejected`, `dead` and
|
||||
`closed_wont_do` fail it with the callee's detail in the error. A durable
|
||||
`workflow_call_finished` event carries the terminal status and detail.
|
||||
- The caller's own stage/attempt accounting is unchanged: the call is one
|
||||
stage that took as long as its callee.
|
||||
- A callee inherits the caller's task record but is otherwise independent:
|
||||
retry, park and cancel of the callee never rewrite the caller. Cancelling a
|
||||
caller cancels its callees through the operator action on each
|
||||
(`execution-tree-state-machine.md` "Cancellation"); until the tree state
|
||||
machine lands, a caller cancelled while waiting fails its stage and leaves
|
||||
the callee running — the same semantics as `wait: false`.
|
||||
|
||||
## What is deliberately not here
|
||||
|
||||
- **Declared outputs.** `wait: true` receives the callee's terminal detail,
|
||||
not structured outputs; the outputs model is its own bead.
|
||||
- **The StepExecution tree.** The `call` kind is designed for in
|
||||
`execution-tree-state-machine.md`; this design lands the behaviour without
|
||||
the per-step records.
|
||||
- **Per-org enablement** — bead `archie-core-t2db.42`'s catalogue is the
|
||||
source once it exists.
|
||||
@@ -0,0 +1,85 @@
|
||||
# Workflow step vocabulary: what a step type is and how binaries agree on it
|
||||
|
||||
**Status:** Draft
|
||||
**Date:** 2026-09-29
|
||||
**Beads:** `archie-core-m7oc` (agreement between separately deployed binaries), `archie-core-ze7y` (the deleted `.archie/stages/*.go` equivalent)
|
||||
**Extends:** `docs/architecture/plugins-and-extensions.md` (plugin engine rule), `docs/prds/event-automation.md` (the workflow model step types serve)
|
||||
|
||||
**Authority:** `docs/architecture/plugins-and-extensions.md` — the workflow step vocabulary is a Workflow capability family, and its extension point follows the plugin engine rule.
|
||||
|
||||
## Decision
|
||||
|
||||
A workflow step type is a named Go factory: the word a YAML workflow writes in
|
||||
a step's `type` field, plus the factory that builds its stage. The name is a
|
||||
stable identifier; the identity also declares what plugin family claims it,
|
||||
so a contribution that shadows a shipped stage is refused instead of
|
||||
overriding it.
|
||||
|
||||
The Workflow domain owns the typed family contract — `StepTypeProvider` for a
|
||||
contribution and `Manager` as the owning registry. A provider contributes a
|
||||
whole set of step types under its own stable-identifier name; the manager
|
||||
validates the entire contribution before applying any of it (named provider,
|
||||
well-formed step-type names, non-nil factories, no step type claimed twice,
|
||||
no claim on a name another provider holds) and applies it atomically. The
|
||||
generic `plugin.Plugin` contract stays metadata-only.
|
||||
|
||||
The vocabulary is a compiled-in, closed set. `internal/infrastructure/workflowsteps`
|
||||
is the one place a step type is bundled into any binary that resolves one: the
|
||||
shipped workflow stages, the repository-hook replacements (`workflow.diff-rules`)
|
||||
and the repository-free event steps each arrive as one provider, and adding a
|
||||
step type means adding a provider to that set. Interpreted plugin sources
|
||||
cannot contribute step types: the Yaegi plugin host satisfies only the
|
||||
metadata contract, and no bridge to `StepFactory` exists.
|
||||
|
||||
Every binary that resolves a step type builds its manager from that same
|
||||
provider set at its composition root, before its first resolution, and
|
||||
injects the manager everywhere it resolves definitions. Agreement is per
|
||||
build: the State Store, the daemon's workflow-definitions client and the agent
|
||||
worker built from the same source register identical vocabularies by
|
||||
construction; binaries built from different sources can disagree, and only a
|
||||
matching deploy fixes that.
|
||||
|
||||
An unknown step type is refused twice, and never degraded. The validator
|
||||
`ParseDefinition` refuses a definition naming an unregistered type at save
|
||||
time, on the validating side the composition root built (the State Store's
|
||||
workflow-definitions resource validates there before anything is stored). The
|
||||
compiler refuses the same definition at run, so a binary handed a definition
|
||||
written against a vocabulary it does not have fails that run loudly instead of
|
||||
silently skipping steps. Both checks live in the Workflow domain against the
|
||||
injected manager, which is why no binary can opt out of the check by
|
||||
substituting its own registry.
|
||||
|
||||
## Relationship between the questions
|
||||
|
||||
`archie-core-ze7y` is the same question seen from the deleted
|
||||
repository-authored stages: those `.archie/stages/*.go` files held arbitrary
|
||||
stages, and their gate half landed as `workflow.diff-rules` settings rather
|
||||
than interpreted Go. Their stage half has no replacement and does not get one
|
||||
that approximates it: no interpreted-Go stage type is built, and no command
|
||||
step type is created by this decision to stand in for them. The refusal of
|
||||
`.archie/stages/*.go` stays until the maintainer's trust decision
|
||||
(`archie-core-ndm8`) says otherwise.
|
||||
|
||||
If that decision ever allows a command step type, it arrives as a provider in
|
||||
the compiled-in set under the rules above — a new contributor of exactly one
|
||||
step type at a named provider. It is not a plugin contribution mechanism, and
|
||||
it does not change any answer in this document.
|
||||
|
||||
## Rejected alternatives
|
||||
|
||||
- **A vocabulary version or hash on the wire.** The executing side already
|
||||
refuses an unknown step type at its first compile, which is the mismatch
|
||||
detector, and it fails closed. A wire field would only narrow the
|
||||
deploy-skew window that a matching deploy closes, at the cost of a new
|
||||
contract field.
|
||||
- **A Yaegi-plugin-to-`StepFactory` bridge.** It would run repository-supplied
|
||||
interpreted code inside the daemon's process with daemon privileges. The
|
||||
trust boundary invariant requires repository-authored code to run in the
|
||||
task container, not in an interpreter embeddable into any binary.
|
||||
- **A package-level process-global registrar.** Global mutable registry state
|
||||
is unreadable at the composition root, collides with itself when one
|
||||
process builds the vocabulary twice, and is what made the first attempt at
|
||||
this question worse instead of better.
|
||||
- **Degrading on an unknown step type.** A run that skips steps it cannot
|
||||
compile would finish green while silently dropping the behaviour the
|
||||
definition asked for; refusal at save and at run is the only honest option.
|
||||
@@ -57,8 +57,6 @@ require (
|
||||
github.com/nats-io/jwt/v2 v2.8.2 // indirect
|
||||
github.com/nats-io/nkeys v0.4.16 // indirect
|
||||
github.com/nats-io/nuid v1.0.1 // indirect
|
||||
github.com/opencontainers/go-digest v1.0.0 // indirect
|
||||
github.com/opencontainers/image-spec v1.1.1 // indirect
|
||||
github.com/pjbgf/sha1cd v0.6.0 // indirect
|
||||
github.com/pkg/browser v0.0.0-20240102092130-5ac0b6a4141c // indirect
|
||||
github.com/power-devops/perfstat v0.0.0-20260916203055-22a1a467d9f0 // indirect
|
||||
@@ -90,13 +88,13 @@ require (
|
||||
google.golang.org/genproto/googleapis/rpc v0.0.0-20260921155816-b14227669459 // indirect
|
||||
modernc.org/libc v1.77.1 // indirect
|
||||
modernc.org/sqlite v1.59.0 // indirect
|
||||
oras.land/oras-go/v2 v2.6.2 // indirect
|
||||
)
|
||||
|
||||
require (
|
||||
cel.dev/cel-go v0.32.0
|
||||
code.gitea.io/sdk/gitea v0.25.1
|
||||
github.com/BurntSushi/toml v1.6.0
|
||||
github.com/cedar-policy/cedar-go v1.8.0
|
||||
github.com/coreos/go-oidc/v3 v3.21.0
|
||||
github.com/docker/sandbox-kit-spec/v3 v3.0.0-m.6
|
||||
github.com/go-git/go-billy/v6 v6.0.0-alpha.2
|
||||
@@ -111,6 +109,8 @@ require (
|
||||
github.com/modelcontextprotocol/go-sdk v1.8.0
|
||||
github.com/nats-io/nats-server/v2 v2.15.0
|
||||
github.com/nats-io/nats.go v1.54.0
|
||||
github.com/opencontainers/go-digest v1.0.0
|
||||
github.com/opencontainers/image-spec v1.1.1
|
||||
github.com/pressly/goose/v3 v3.28.0
|
||||
github.com/samcharles93/ai-sdk v0.1.39
|
||||
github.com/testcontainers/testcontainers-go v0.44.0
|
||||
@@ -125,4 +125,5 @@ require (
|
||||
google.golang.org/grpc v1.85.0-dev.0.20260825072537-93e31b48545e
|
||||
google.golang.org/protobuf v1.36.12
|
||||
gopkg.in/yaml.v3 v3.0.1
|
||||
oras.land/oras-go/v2 v2.6.2
|
||||
)
|
||||
@@ -26,6 +26,8 @@ github.com/antlr4-go/antlr/v4 v4.13.1 h1:SqQKkuVZ+zWkMMNkjy5FZe5mr5WURWnlpmOuzYW
|
||||
github.com/antlr4-go/antlr/v4 v4.13.1/go.mod h1:GKmUxMtwp6ZgGwZSva4eWPC5mS6vUAmOABFgjdkM7Nw=
|
||||
github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5 h1:0CwZNZbxp69SHPdPJAN/hZIm0C4OItdklCFmMRWYpio=
|
||||
github.com/armon/go-socks5 v0.0.0-20160902184237-e75332964ef5/go.mod h1:wHh0iHkYZB8zMSxRWpUBQtwG5a7fFgvEO+odwuTv2gs=
|
||||
github.com/cedar-policy/cedar-go v1.8.0 h1:9gcU7EHXwHC2RMdpph68yTAkdB3behTTssC+kt4GoS8=
|
||||
github.com/cedar-policy/cedar-go v1.8.0/go.mod h1:h5+3CVW1oI5LXVskJG+my9TFCYI5yjh/+Ul3EJie6MI=
|
||||
github.com/cenkalti/backoff/v4 v4.3.0 h1:MyRJ/UdXutAwSAT+s3wNd7MfTIcy71VQueUuFK343L8=
|
||||
github.com/cenkalti/backoff/v4 v4.3.0/go.mod h1:Y3VNntkOUPxTVeUxJ/G5vcM//AlwfmyYozVcomhLiZE=
|
||||
github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
|
||||
|
||||
@@ -41,10 +41,11 @@ func runAsHarnessUser(cmd *exec.Cmd, name string) error {
|
||||
}
|
||||
|
||||
// harnessCredential resolves a user name or "uid[:gid]" to a credential.
|
||||
// Root is refused whichever way it is named.
|
||||
// Root is refused whichever way it is named. IDs are bounded to 31 bits so
|
||||
// they convert to int for os.Chown on every platform.
|
||||
func harnessCredential(name string) (*syscall.Credential, error) {
|
||||
uidText, gidText, hasGid := strings.Cut(name, ":")
|
||||
uid, uidErr := strconv.ParseUint(uidText, 10, 32)
|
||||
uid, uidErr := strconv.ParseUint(uidText, 10, 31)
|
||||
var cred syscall.Credential
|
||||
if uidErr == nil {
|
||||
cred.Uid, cred.Gid = uint32(uid), uint32(uid)
|
||||
@@ -53,18 +54,18 @@ func harnessCredential(name string) (*syscall.Credential, error) {
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("harness user %q: %w", uidText, err)
|
||||
}
|
||||
id, err := strconv.ParseUint(u.Uid, 10, 32)
|
||||
id, err := strconv.ParseUint(u.Uid, 10, 31)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("harness user %q has non-numeric uid %q", uidText, u.Uid)
|
||||
}
|
||||
group, err := strconv.ParseUint(u.Gid, 10, 32)
|
||||
group, err := strconv.ParseUint(u.Gid, 10, 31)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("harness user %q has non-numeric gid %q", uidText, u.Gid)
|
||||
}
|
||||
cred.Uid, cred.Gid = uint32(id), uint32(group)
|
||||
}
|
||||
if hasGid {
|
||||
gid, err := strconv.ParseUint(gidText, 10, 32)
|
||||
gid, err := strconv.ParseUint(gidText, 10, 31)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("harness group %q is not numeric", gidText)
|
||||
}
|
||||
|
||||
@@ -388,6 +388,8 @@ func TestHarnessUser(t *testing.T) {
|
||||
{"0", 0, 0, true},
|
||||
{"root", 0, 0, true},
|
||||
{"not-a-user-anywhere", 0, 0, true},
|
||||
{"2147483648", 0, 0, true},
|
||||
{"1000:2147483648", 0, 0, true},
|
||||
}
|
||||
for _, tt := range tests {
|
||||
cred, err := harnessCredential(tt.user)
|
||||
|
||||
@@ -6,7 +6,7 @@
|
||||
{"type": "system", "subtype": "hook_response", "hook_id": "04acf4c4-0c8d-4dd5-9d3a-a7a6df371224", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "ecbfdcf2-446c-4386-a89f-eeaf43e48b46", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
|
||||
{"type": "system", "subtype": "hook_response", "hook_id": "4c58406e-b5f0-49d7-af88-483c14212e0d", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "c10b3042-e990-49db-8937-954b6fe11570", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
|
||||
{"type": "system", "subtype": "hook_response", "hook_id": "a0cb320b-0bdd-45b5-90b5-451add28d1ed", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "3a3327f8-ad24-46d7-a194-e0ce68f9f871", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
|
||||
{"type": "system", "subtype": "init", "cwd": "/workspace", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "tools": ["Task", "Bash", "CronCreate", "CronDelete", "CronList", "DesignSync", "Edit", "EnterWorktree", "ExitWorktree", "ListAgents", "ListMcpResourcesTool", "LSP", "Monitor", "NotebookEdit", "PushNotification", "Read", "ReadMcpResourceDirTool", "ReadMcpResourceTool", "RemoteTrigger", "ReportFindings", "ScheduleWakeup", "SendMessage", "Skill", "TaskStop", "ToolSearch", "WebFetch", "WebSearch", "Workflow", "Write", "mcp__claude_ai_Claude_Docs__batch", "mcp__claude_ai_Claude_Docs__create", "mcp__claude_ai_Claude_Docs__delete", "mcp__claude_ai_Claude_Docs__export", "mcp__claude_ai_Claude_Docs__guide", "mcp__claude_ai_Claude_Docs__query", "mcp__claude_ai_Claude_Docs__read", "mcp__claude_ai_Claude_Docs__update", "mcp__claude_ai_Context7__query-docs", "mcp__claude_ai_Context7__resolve-library-id", "mcp__claude_ai_Excalidraw__create_view", "mcp__claude_ai_Excalidraw__read_me", "mcp__claude_ai_Gmail__apply_sensitive_message_label", "mcp__claude_ai_Gmail__apply_sensitive_thread_label", "mcp__claude_ai_Gmail__create_draft", "mcp__claude_ai_Gmail__create_label", "mcp__claude_ai_Gmail__delete_draft", "mcp__claude_ai_Gmail__delete_label", "mcp__claude_ai_Gmail__forward", "mcp__claude_ai_Gmail__get_draft", "mcp__claude_ai_Gmail__get_message", "mcp__claude_ai_Gmail__get_thread", "mcp__claude_ai_Gmail__label_message", "mcp__claude_ai_Gmail__label_thread", "mcp__claude_ai_Gmail__list_drafts", "mcp__claude_ai_Gmail__list_labels", "mcp__claude_ai_Gmail__mark_message_spam", "mcp__claude_ai_Gmail__mark_thread_spam", "mcp__claude_ai_Gmail__reply", "mcp__claude_ai_Gmail__search_threads", "mcp__claude_ai_Gmail__send_message", "mcp__claude_ai_Gmail__trash_message", "mcp__claude_ai_Gmail__trash_thread", "mcp__claude_ai_Gmail__unlabel_message", "mcp__claude_ai_Gmail__unlabel_thread", "mcp__claude_ai_Gmail__unmark_message_spam", "mcp__claude_ai_Gmail__unmark_thread_spam", "mcp__claude_ai_Gmail__untrash_message", "mcp__claude_ai_Gmail__untrash_thread", "mcp__claude_ai_Gmail__update_draft", "mcp__claude_ai_Gmail__update_label", "mcp__claude_ai_Gmail__update_message_labels", "mcp__claude_ai_Google_Calendar__create_event", "mcp__claude_ai_Google_Calendar__delete_event", "mcp__claude_ai_Google_Calendar__get_event", "mcp__claude_ai_Google_Calendar__list_calendars", "mcp__claude_ai_Google_Calendar__list_events", "mcp__claude_ai_Google_Calendar__respond_to_event", "mcp__claude_ai_Google_Calendar__search_events", "mcp__claude_ai_Google_Calendar__suggest_time", "mcp__claude_ai_Google_Calendar__update_event", "mcp__claude_ai_Microsoft_365__chat_message_search", "mcp__claude_ai_Microsoft_365__find_meeting_availability", "mcp__claude_ai_Microsoft_365__get_granted_scopes", "mcp__claude_ai_Microsoft_365__get_me", "mcp__claude_ai_Microsoft_365__outlook_batch_delete_messages", "mcp__claude_ai_Microsoft_365__outlook_batch_modify_labels", "mcp__claude_ai_Microsoft_365__outlook_calendar_search", "mcp__claude_ai_Microsoft_365__outlook_create_draft", "mcp__claude_ai_Microsoft_365__outlook_create_event", "mcp__claude_ai_Microsoft_365__outlook_create_filter", "mcp__claude_ai_Microsoft_365__outlook_create_label", "mcp__claude_ai_Microsoft_365__outlook_create_reply_all_draft", "mcp__claude_ai_Microsoft_365__outlook_create_reply_draft", "mcp__claude_ai_Microsoft_365__outlook_delete_draft", "mcp__claude_ai_Microsoft_365__outlook_delete_event", "mcp__claude_ai_Microsoft_365__outlook_delete_filter", "mcp__claude_ai_Microsoft_365__outlook_delete_label", "mcp__claude_ai_Microsoft_365__outlook_email_search", "mcp__claude_ai_Microsoft_365__outlook_find_available_time", "mcp__claude_ai_Microsoft_365__outlook_forward_mail", "mcp__claude_ai_Microsoft_365__outlook_modify_labels", "mcp__claude_ai_Microsoft_365__outlook_modify_thread_labels", "mcp__claude_ai_Microsoft_365__outlook_respond_to_event", "mcp__claude_ai_Microsoft_365__outlook_send_draft", "mcp__claude_ai_Microsoft_365__outlook_send_mail", "mcp__claude_ai_Microsoft_365__outlook_set_vacation", "mcp__claude_ai_Microsoft_365__outlook_trash_thread", "mcp__claude_ai_Microsoft_365__outlook_untrash_thread", "mcp__claude_ai_Microsoft_365__outlook_update_draft", "mcp__claude_ai_Microsoft_365__outlook_update_event", "mcp__claude_ai_Microsoft_365__outlook_update_label", "mcp__claude_ai_Microsoft_365__read_resource", "mcp__claude_ai_Microsoft_365__search_people", "mcp__claude_ai_Microsoft_365__sharepoint_copy_item", "mcp__claude_ai_Microsoft_365__sharepoint_create_folder", "mcp__claude_ai_Microsoft_365__sharepoint_delete_item", "mcp__claude_ai_Microsoft_365__sharepoint_folder_search", "mcp__claude_ai_Microsoft_365__sharepoint_move_item", "mcp__claude_ai_Microsoft_365__sharepoint_rename_item", "mcp__claude_ai_Microsoft_365__sharepoint_search", "mcp__claude_ai_Microsoft_365__sharepoint_update_file", "mcp__claude_ai_Microsoft_365__sharepoint_upload_file", "mcp__claude_ai_Microsoft_365__teams_create_chat", "mcp__claLine truncated
|
||||
{"type": "system", "subtype": "init", "cwd": "/workspace", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "tools": ["Task", "Bash", "Edit", "Read", "Write"], "mcp_servers": [], "model": "claude-opus-5-5", "permissionMode": "bypassPermissions", "slash_commands": [], "terminal_slash_commands": [], "apiKeySource": "none", "claude_code_version": "2.1.282", "output_style": "default", "agents": [], "skills": [], "plugins": [], "capabilities": ["interrupt_receipt_v1", "interrupt_cancel_queued_v1", "msg_lifecycle_v1", "mcp_read_resource_v1", "mcp_tool_ui_meta_v1"], "analytics_disabled": false, "product_feedback_disabled": false, "uuid": "0ad7c54e-a817-406b-af22-8f647b4e0021", "memory_paths": {}, "messaging_socket_path": "", "fast_mode_state": "off", "fast_mode_disabled_reason": "sdk_opt_in_required", "per_turn_effort_active": true, "view_mode": "default"}
|
||||
{"type": "assistant", "message": {"model": "claude-opus-5-5", "id": "msg_011CfQYZ2iQ3sZ59vJ9CCae9", "type": "message", "role": "assistant", "content": [{"type": "tool_use", "id": "toolu_01P8qrSZwqH1jjZXfrZETjKz", "name": "Bash", "input": {"command": "echo hello", "description": "Print hello"}, "caller": {"type": "direct"}}], "container": null, "stop_reason": null, "stop_sequence": null, "stop_details": null, "usage": {"input_tokens": 2, "cache_creation_input_tokens": 23584, "cache_read_input_tokens": 10119, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 23584}, "output_tokens": 16, "service_tier": "standard", "inference_geo": "not_available"}, "input_transformations": [], "diagnostics": null, "context_management": null}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "b4c3b51e-0a58-4b28-8c5a-20a2ff2aaadb", "timestamp": "2026-09-25T17:22:54.134Z", "request_id": "req_011CfQYZ2Ddp5YubZj8vB9Fb", "wire_tool_inputs": {"toolu_01P8qrSZwqH1jjZXfrZETjKz": {"command": "echo hello", "description": "Print hello"}}}
|
||||
{"type": "rate_limit_event", "rate_limit_info": {"status": "allowed_warning", "resetsAt": 1790377200, "rateLimitType": "seven_day", "utilization": 0.98, "isUsingOverage": false, "surpassedThreshold": 0.75, "unifiedWindows": {"five_hour": {"utilization": 0.76, "resetsAt": 1790366400}, "seven_day": {"utilization": 0.98, "resetsAt": 1790377200}}}, "uuid": "a91b2340-329e-4c73-8e1a-307860859743", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
|
||||
{"type": "user", "message": {"role": "user", "content": [{"tool_use_id": "toolu_01P8qrSZwqH1jjZXfrZETjKz", "type": "tool_result", "content": "hello", "is_error": false}]}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "6beae671-52a0-499a-b72b-f9321c1d9e14", "timestamp": "2026-09-25T17:22:54.460Z", "tool_use_result": {"stdout": "hello", "stderr": "", "interrupted": false, "isImage": false, "noOutputExpected": false}}
|
||||
|
||||
+1
-1
@@ -6,7 +6,7 @@
|
||||
{"type": "system", "subtype": "hook_response", "hook_id": "04acf4c4-0c8d-4dd5-9d3a-a7a6df371224", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "ecbfdcf2-446c-4386-a89f-eeaf43e48b46", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
|
||||
{"type": "system", "subtype": "hook_response", "hook_id": "4c58406e-b5f0-49d7-af88-483c14212e0d", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "c10b3042-e990-49db-8937-954b6fe11570", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
|
||||
{"type": "system", "subtype": "hook_response", "hook_id": "a0cb320b-0bdd-45b5-90b5-451add28d1ed", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "3a3327f8-ad24-46d7-a194-e0ce68f9f871", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
|
||||
{"type": "system", "subtype": "init", "cwd": "/workspace", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "tools": ["Task", "Bash", "CronCreate", "CronDelete", "CronList", "DesignSync", "Edit", "EnterWorktree", "ExitWorktree", "ListAgents", "ListMcpResourcesTool", "LSP", "Monitor", "NotebookEdit", "PushNotification", "Read", "ReadMcpResourceDirTool", "ReadMcpResourceTool", "RemoteTrigger", "ReportFindings", "ScheduleWakeup", "SendMessage", "Skill", "TaskStop", "ToolSearch", "WebFetch", "WebSearch", "Workflow", "Write", "mcp__claude_ai_Claude_Docs__batch", "mcp__claude_ai_Claude_Docs__create", "mcp__claude_ai_Claude_Docs__delete", "mcp__claude_ai_Claude_Docs__export", "mcp__claude_ai_Claude_Docs__guide", "mcp__claude_ai_Claude_Docs__query", "mcp__claude_ai_Claude_Docs__read", "mcp__claude_ai_Claude_Docs__update", "mcp__claude_ai_Context7__query-docs", "mcp__claude_ai_Context7__resolve-library-id", "mcp__claude_ai_Excalidraw__create_view", "mcp__claude_ai_Excalidraw__read_me", "mcp__claude_ai_Gmail__apply_sensitive_message_label", "mcp__claude_ai_Gmail__apply_sensitive_thread_label", "mcp__claude_ai_Gmail__create_draft", "mcp__claude_ai_Gmail__create_label", "mcp__claude_ai_Gmail__delete_draft", "mcp__claude_ai_Gmail__delete_label", "mcp__claude_ai_Gmail__forward", "mcp__claude_ai_Gmail__get_draft", "mcp__claude_ai_Gmail__get_message", "mcp__claude_ai_Gmail__get_thread", "mcp__claude_ai_Gmail__label_message", "mcp__claude_ai_Gmail__label_thread", "mcp__claude_ai_Gmail__list_drafts", "mcp__claude_ai_Gmail__list_labels", "mcp__claude_ai_Gmail__mark_message_spam", "mcp__claude_ai_Gmail__mark_thread_spam", "mcp__claude_ai_Gmail__reply", "mcp__claude_ai_Gmail__search_threads", "mcp__claude_ai_Gmail__send_message", "mcp__claude_ai_Gmail__trash_message", "mcp__claude_ai_Gmail__trash_thread", "mcp__claude_ai_Gmail__unlabel_message", "mcp__claude_ai_Gmail__unlabel_thread", "mcp__claude_ai_Gmail__unmark_message_spam", "mcp__claude_ai_Gmail__unmark_thread_spam", "mcp__claude_ai_Gmail__untrash_message", "mcp__claude_ai_Gmail__untrash_thread", "mcp__claude_ai_Gmail__update_draft", "mcp__claude_ai_Gmail__update_label", "mcp__claude_ai_Gmail__update_message_labels", "mcp__claude_ai_Google_Calendar__create_event", "mcp__claude_ai_Google_Calendar__delete_event", "mcp__claude_ai_Google_Calendar__get_event", "mcp__claude_ai_Google_Calendar__list_calendars", "mcp__claude_ai_Google_Calendar__list_events", "mcp__claude_ai_Google_Calendar__respond_to_event", "mcp__claude_ai_Google_Calendar__search_events", "mcp__claude_ai_Google_Calendar__suggest_time", "mcp__claude_ai_Google_Calendar__update_event", "mcp__claude_ai_Microsoft_365__chat_message_search", "mcp__claude_ai_Microsoft_365__find_meeting_availability", "mcp__claude_ai_Microsoft_365__get_granted_scopes", "mcp__claude_ai_Microsoft_365__get_me", "mcp__claude_ai_Microsoft_365__outlook_batch_delete_messages", "mcp__claude_ai_Microsoft_365__outlook_batch_modify_labels", "mcp__claude_ai_Microsoft_365__outlook_calendar_search", "mcp__claude_ai_Microsoft_365__outlook_create_draft", "mcp__claude_ai_Microsoft_365__outlook_create_event", "mcp__claude_ai_Microsoft_365__outlook_create_filter", "mcp__claude_ai_Microsoft_365__outlook_create_label", "mcp__claude_ai_Microsoft_365__outlook_create_reply_all_draft", "mcp__claude_ai_Microsoft_365__outlook_create_reply_draft", "mcp__claude_ai_Microsoft_365__outlook_delete_draft", "mcp__claude_ai_Microsoft_365__outlook_delete_event", "mcp__claude_ai_Microsoft_365__outlook_delete_filter", "mcp__claude_ai_Microsoft_365__outlook_delete_label", "mcp__claude_ai_Microsoft_365__outlook_email_search", "mcp__claude_ai_Microsoft_365__outlook_find_available_time", "mcp__claude_ai_Microsoft_365__outlook_forward_mail", "mcp__claude_ai_Microsoft_365__outlook_modify_labels", "mcp__claude_ai_Microsoft_365__outlook_modify_thread_labels", "mcp__claude_ai_Microsoft_365__outlook_respond_to_event", "mcp__claude_ai_Microsoft_365__outlook_send_draft", "mcp__claude_ai_Microsoft_365__outlook_send_mail", "mcp__claude_ai_Microsoft_365__outlook_set_vacation", "mcp__claude_ai_Microsoft_365__outlook_trash_thread", "mcp__claude_ai_Microsoft_365__outlook_untrash_thread", "mcp__claude_ai_Microsoft_365__outlook_update_draft", "mcp__claude_ai_Microsoft_365__outlook_update_event", "mcp__claude_ai_Microsoft_365__outlook_update_label", "mcp__claude_ai_Microsoft_365__read_resource", "mcp__claude_ai_Microsoft_365__search_people", "mcp__claude_ai_Microsoft_365__sharepoint_copy_item", "mcp__claude_ai_Microsoft_365__sharepoint_create_folder", "mcp__claude_ai_Microsoft_365__sharepoint_delete_item", "mcp__claude_ai_Microsoft_365__sharepoint_folder_search", "mcp__claude_ai_Microsoft_365__sharepoint_move_item", "mcp__claude_ai_Microsoft_365__sharepoint_rename_item", "mcp__claude_ai_Microsoft_365__sharepoint_search", "mcp__claude_ai_Microsoft_365__sharepoint_update_file", "mcp__claude_ai_Microsoft_365__sharepoint_upload_file", "mcp__claude_ai_Microsoft_365__teams_create_chat", "mcp__claLine truncated
|
||||
{"type": "system", "subtype": "init", "cwd": "/workspace", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "tools": ["Task", "Bash", "Edit", "Read", "Write"], "mcp_servers": [], "model": "claude-opus-5-5", "permissionMode": "bypassPermissions", "slash_commands": [], "terminal_slash_commands": [], "apiKeySource": "none", "claude_code_version": "2.1.282", "output_style": "default", "agents": [], "skills": [], "plugins": [], "capabilities": ["interrupt_receipt_v1", "interrupt_cancel_queued_v1", "msg_lifecycle_v1", "mcp_read_resource_v1", "mcp_tool_ui_meta_v1"], "analytics_disabled": false, "product_feedback_disabled": false, "uuid": "0ad7c54e-a817-406b-af22-8f647b4e0021", "memory_paths": {}, "messaging_socket_path": "", "fast_mode_state": "off", "fast_mode_disabled_reason": "sdk_opt_in_required", "per_turn_effort_active": true, "view_mode": "default"}
|
||||
{"type": "assistant", "message": {"model": "claude-opus-5-5", "id": "msg_011CfQYZ2iQ3sZ59vJ9CCae9", "type": "message", "role": "assistant", "content": [{"type": "tool_use", "id": "toolu_01P8qrSZwqH1jjZXfrZETjKz", "name": "Bash", "input": {"command": "echo hello", "description": "Print hello"}, "caller": {"type": "direct"}}], "container": null, "stop_reason": null, "stop_sequence": null, "stop_details": null, "usage": {"input_tokens": 2, "cache_creation_input_tokens": 23584, "cache_read_input_tokens": 10119, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 23584}, "output_tokens": 16, "service_tier": "standard", "inference_geo": "not_available"}, "input_transformations": [], "diagnostics": null, "context_management": null}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "b4c3b51e-0a58-4b28-8c5a-20a2ff2aaadb", "timestamp": "2026-09-25T17:22:54.134Z", "request_id": "req_011CfQYZ2Ddp5YubZj8vB9Fb", "wire_tool_inputs": {"toolu_01P8qrSZwqH1jjZXfrZETjKz": {"command": "echo hello", "description": "Print hello"}}}
|
||||
{"type":"assistant","message":{"content":[{"type":"tool_use"
|
||||
{"type": "rate_limit_event", "rate_limit_info": {"status": "allowed_warning", "resetsAt": 1790377200, "rateLimitType": "seven_day", "utilization": 0.98, "isUsingOverage": false, "surpassedThreshold": 0.75, "unifiedWindows": {"five_hour": {"utilization": 0.76, "resetsAt": 1790366400}, "seven_day": {"utilization": 0.98, "resetsAt": 1790377200}}}, "uuid": "a91b2340-329e-4c73-8e1a-307860859743", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
|
||||
|
||||
+1
-1
@@ -6,7 +6,7 @@
|
||||
{"type": "system", "subtype": "hook_response", "hook_id": "04acf4c4-0c8d-4dd5-9d3a-a7a6df371224", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "ecbfdcf2-446c-4386-a89f-eeaf43e48b46", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
|
||||
{"type": "system", "subtype": "hook_response", "hook_id": "4c58406e-b5f0-49d7-af88-483c14212e0d", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "c10b3042-e990-49db-8937-954b6fe11570", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
|
||||
{"type": "system", "subtype": "hook_response", "hook_id": "a0cb320b-0bdd-45b5-90b5-451add28d1ed", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "3a3327f8-ad24-46d7-a194-e0ce68f9f871", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
|
||||
{"type": "system", "subtype": "init", "cwd": "/workspace", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "tools": ["Task", "Bash", "CronCreate", "CronDelete", "CronList", "DesignSync", "Edit", "EnterWorktree", "ExitWorktree", "ListAgents", "ListMcpResourcesTool", "LSP", "Monitor", "NotebookEdit", "PushNotification", "Read", "ReadMcpResourceDirTool", "ReadMcpResourceTool", "RemoteTrigger", "ReportFindings", "ScheduleWakeup", "SendMessage", "Skill", "TaskStop", "ToolSearch", "WebFetch", "WebSearch", "Workflow", "Write", "mcp__claude_ai_Claude_Docs__batch", "mcp__claude_ai_Claude_Docs__create", "mcp__claude_ai_Claude_Docs__delete", "mcp__claude_ai_Claude_Docs__export", "mcp__claude_ai_Claude_Docs__guide", "mcp__claude_ai_Claude_Docs__query", "mcp__claude_ai_Claude_Docs__read", "mcp__claude_ai_Claude_Docs__update", "mcp__claude_ai_Context7__query-docs", "mcp__claude_ai_Context7__resolve-library-id", "mcp__claude_ai_Excalidraw__create_view", "mcp__claude_ai_Excalidraw__read_me", "mcp__claude_ai_Gmail__apply_sensitive_message_label", "mcp__claude_ai_Gmail__apply_sensitive_thread_label", "mcp__claude_ai_Gmail__create_draft", "mcp__claude_ai_Gmail__create_label", "mcp__claude_ai_Gmail__delete_draft", "mcp__claude_ai_Gmail__delete_label", "mcp__claude_ai_Gmail__forward", "mcp__claude_ai_Gmail__get_draft", "mcp__claude_ai_Gmail__get_message", "mcp__claude_ai_Gmail__get_thread", "mcp__claude_ai_Gmail__label_message", "mcp__claude_ai_Gmail__label_thread", "mcp__claude_ai_Gmail__list_drafts", "mcp__claude_ai_Gmail__list_labels", "mcp__claude_ai_Gmail__mark_message_spam", "mcp__claude_ai_Gmail__mark_thread_spam", "mcp__claude_ai_Gmail__reply", "mcp__claude_ai_Gmail__search_threads", "mcp__claude_ai_Gmail__send_message", "mcp__claude_ai_Gmail__trash_message", "mcp__claude_ai_Gmail__trash_thread", "mcp__claude_ai_Gmail__unlabel_message", "mcp__claude_ai_Gmail__unlabel_thread", "mcp__claude_ai_Gmail__unmark_message_spam", "mcp__claude_ai_Gmail__unmark_thread_spam", "mcp__claude_ai_Gmail__untrash_message", "mcp__claude_ai_Gmail__untrash_thread", "mcp__claude_ai_Gmail__update_draft", "mcp__claude_ai_Gmail__update_label", "mcp__claude_ai_Gmail__update_message_labels", "mcp__claude_ai_Google_Calendar__create_event", "mcp__claude_ai_Google_Calendar__delete_event", "mcp__claude_ai_Google_Calendar__get_event", "mcp__claude_ai_Google_Calendar__list_calendars", "mcp__claude_ai_Google_Calendar__list_events", "mcp__claude_ai_Google_Calendar__respond_to_event", "mcp__claude_ai_Google_Calendar__search_events", "mcp__claude_ai_Google_Calendar__suggest_time", "mcp__claude_ai_Google_Calendar__update_event", "mcp__claude_ai_Microsoft_365__chat_message_search", "mcp__claude_ai_Microsoft_365__find_meeting_availability", "mcp__claude_ai_Microsoft_365__get_granted_scopes", "mcp__claude_ai_Microsoft_365__get_me", "mcp__claude_ai_Microsoft_365__outlook_batch_delete_messages", "mcp__claude_ai_Microsoft_365__outlook_batch_modify_labels", "mcp__claude_ai_Microsoft_365__outlook_calendar_search", "mcp__claude_ai_Microsoft_365__outlook_create_draft", "mcp__claude_ai_Microsoft_365__outlook_create_event", "mcp__claude_ai_Microsoft_365__outlook_create_filter", "mcp__claude_ai_Microsoft_365__outlook_create_label", "mcp__claude_ai_Microsoft_365__outlook_create_reply_all_draft", "mcp__claude_ai_Microsoft_365__outlook_create_reply_draft", "mcp__claude_ai_Microsoft_365__outlook_delete_draft", "mcp__claude_ai_Microsoft_365__outlook_delete_event", "mcp__claude_ai_Microsoft_365__outlook_delete_filter", "mcp__claude_ai_Microsoft_365__outlook_delete_label", "mcp__claude_ai_Microsoft_365__outlook_email_search", "mcp__claude_ai_Microsoft_365__outlook_find_available_time", "mcp__claude_ai_Microsoft_365__outlook_forward_mail", "mcp__claude_ai_Microsoft_365__outlook_modify_labels", "mcp__claude_ai_Microsoft_365__outlook_modify_thread_labels", "mcp__claude_ai_Microsoft_365__outlook_respond_to_event", "mcp__claude_ai_Microsoft_365__outlook_send_draft", "mcp__claude_ai_Microsoft_365__outlook_send_mail", "mcp__claude_ai_Microsoft_365__outlook_set_vacation", "mcp__claude_ai_Microsoft_365__outlook_trash_thread", "mcp__claude_ai_Microsoft_365__outlook_untrash_thread", "mcp__claude_ai_Microsoft_365__outlook_update_draft", "mcp__claude_ai_Microsoft_365__outlook_update_event", "mcp__claude_ai_Microsoft_365__outlook_update_label", "mcp__claude_ai_Microsoft_365__read_resource", "mcp__claude_ai_Microsoft_365__search_people", "mcp__claude_ai_Microsoft_365__sharepoint_copy_item", "mcp__claude_ai_Microsoft_365__sharepoint_create_folder", "mcp__claude_ai_Microsoft_365__sharepoint_delete_item", "mcp__claude_ai_Microsoft_365__sharepoint_folder_search", "mcp__claude_ai_Microsoft_365__sharepoint_move_item", "mcp__claude_ai_Microsoft_365__sharepoint_rename_item", "mcp__claude_ai_Microsoft_365__sharepoint_search", "mcp__claude_ai_Microsoft_365__sharepoint_update_file", "mcp__claude_ai_Microsoft_365__sharepoint_upload_file", "mcp__claude_ai_Microsoft_365__teams_create_chat", "mcp__claLine truncated
|
||||
{"type": "system", "subtype": "init", "cwd": "/workspace", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "tools": ["Task", "Bash", "Edit", "Read", "Write"], "mcp_servers": [], "model": "claude-opus-5-5", "permissionMode": "bypassPermissions", "slash_commands": [], "terminal_slash_commands": [], "apiKeySource": "none", "claude_code_version": "2.1.282", "output_style": "default", "agents": [], "skills": [], "plugins": [], "capabilities": ["interrupt_receipt_v1", "interrupt_cancel_queued_v1", "msg_lifecycle_v1", "mcp_read_resource_v1", "mcp_tool_ui_meta_v1"], "analytics_disabled": false, "product_feedback_disabled": false, "uuid": "0ad7c54e-a817-406b-af22-8f647b4e0021", "memory_paths": {}, "messaging_socket_path": "", "fast_mode_state": "off", "fast_mode_disabled_reason": "sdk_opt_in_required", "per_turn_effort_active": true, "view_mode": "default"}
|
||||
{"type": "assistant", "message": {"model": "claude-opus-5-5", "id": "msg_011CfQYZ2iQ3sZ59vJ9CCae9", "type": "message", "role": "assistant", "content": [{"type": "tool_use", "id": "toolu_01P8qrSZwqH1jjZXfrZETjKz", "name": "Bash", "input": {"command": "echo hello", "description": "Print hello"}, "caller": {"type": "direct"}}], "container": null, "stop_reason": null, "stop_sequence": null, "stop_details": null, "usage": {"input_tokens": 2, "cache_creation_input_tokens": 23584, "cache_read_input_tokens": 10119, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 23584}, "output_tokens": 16, "service_tier": "standard", "inference_geo": "not_available"}, "input_transformations": [], "diagnostics": null, "context_management": null}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "b4c3b51e-0a58-4b28-8c5a-20a2ff2aaadb", "timestamp": "2026-09-25T17:22:54.134Z", "request_id": "req_011CfQYZ2Ddp5YubZj8vB9Fb", "wire_tool_inputs": {"toolu_01P8qrSZwqH1jjZXfrZETjKz": {"command": "echo hello", "description": "Print hello"}}}
|
||||
{"type": "rate_limit_event", "rate_limit_info": {"status": "allowed_warning", "resetsAt": 1790377200, "rateLimitType": "seven_day", "utilization": 0.98, "isUsingOverage": false, "surpassedThreshold": 0.75, "unifiedWindows": {"five_hour": {"utilization": 0.76, "resetsAt": 1790366400}, "seven_day": {"utilization": 0.98, "resetsAt": 1790377200}}}, "uuid": "a91b2340-329e-4c73-8e1a-307860859743", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
|
||||
{"type": "user", "message": {"role": "user", "content": [{"tool_use_id": "toolu_01P8qrSZwqH1jjZXfrZETjKz", "type": "tool_result", "content": "hello", "is_error": false}]}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "6beae671-52a0-499a-b72b-f9321c1d9e14", "timestamp": "2026-09-25T17:22:54.460Z", "tool_use_result": {"stdout": "hello", "stderr": "", "interrupted": false, "isImage": false, "noOutputExpected": false}}
|
||||
|
||||
@@ -1,272 +0,0 @@
|
||||
package agentworker
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"strings"
|
||||
|
||||
"github.com/samcharles93/ai-sdk/agent"
|
||||
"github.com/samcharles93/ai-sdk/core"
|
||||
"github.com/samcharles93/ai-sdk/runtime"
|
||||
"github.com/samcharles93/ai-sdk/toolkit"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/agentexec"
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow"
|
||||
"github.com/samcharles93/archie-core/internal/taskrun"
|
||||
)
|
||||
|
||||
// newReviewerFor builds the workflow.Reviewer for one task run, or nil
|
||||
// when the repo has not opted into review (Repo.ReviewEnabled == false)
|
||||
// or no providers are configured. Model resolution mirrors AgentStage's
|
||||
// own role->"builder" fallback (agent.go): Models["reviewer"], falling
|
||||
// back to Models["builder"].
|
||||
func newReviewerFor(req taskrun.Request) workflow.Reviewer {
|
||||
if !req.Repo.ReviewEnabled {
|
||||
return nil
|
||||
}
|
||||
return NewOperatorReviewer(req.Cfg.Models, req.Providers)
|
||||
}
|
||||
|
||||
// NewOperatorReviewer builds the workflow.Reviewer for an operator-triggered
|
||||
// review, resolved from daemon-level models and providers rather than a task
|
||||
// run. It shares newReviewerFor's role->"builder" model fallback but drops
|
||||
// the Repo.ReviewEnabled gate: the operator asked for the review explicitly,
|
||||
// so "not opted in" is not a reason to refuse. It returns nil when no model
|
||||
// resolves (no reviewer/builder model configured) or no provider runtime
|
||||
// builds, so the caller can report a clear "review not configured" result.
|
||||
func NewOperatorReviewer(models map[string]string, providers map[string]agentexec.Provider) workflow.Reviewer {
|
||||
modelRef := ReviewerModel(models)
|
||||
if modelRef == "" {
|
||||
return nil
|
||||
}
|
||||
rt := agentexec.NewRuntime(providers)
|
||||
if rt == nil {
|
||||
return nil
|
||||
}
|
||||
return newSubagentReviewer(rt, modelRef)
|
||||
}
|
||||
|
||||
// ReviewerModel resolves the reviewer role's model with the builder fallback.
|
||||
// It is the single source of truth for the role->"builder" rule, shared by
|
||||
// the workflow stage (via NewOperatorReviewer/newReviewerFor) and the
|
||||
// operator-triggered review's result reporting so the reported model and the
|
||||
// model actually run cannot diverge.
|
||||
func ReviewerModel(models map[string]string) string {
|
||||
if models["reviewer"] != "" {
|
||||
return models["reviewer"]
|
||||
}
|
||||
return models["builder"]
|
||||
}
|
||||
|
||||
// defaultReviewMaxSteps bounds the reviewer's tool loop when neither
|
||||
// ReviewRequest.MaxSteps nor the repo's configured budget set one.
|
||||
const defaultReviewMaxSteps = 10
|
||||
|
||||
// subagentReviewer implements workflow.Reviewer using ai-sdk's
|
||||
// agent.Subagent: a nested, synchronous generation in this same worker
|
||||
// process, with its own model, system prompt, toolset, and step budget.
|
||||
//
|
||||
// Isolation is two-fold. Conversation isolation is structural: Subagent.Run
|
||||
// only ever sends a prompt string, never the implementer's message
|
||||
// history. Workspace isolation is built by the caller (StageReview via
|
||||
// workflow.Trees.Snapshot): reviewerToolSet is rooted at that snapshot
|
||||
// directory and holds only read-only tools -- never the worker's own
|
||||
// toolset, which carries the worktreerpc publication grant a reviewer must
|
||||
// not be able to reach.
|
||||
type subagentReviewer struct {
|
||||
runtime *runtime.Runtime
|
||||
modelRef string
|
||||
}
|
||||
|
||||
// newSubagentReviewer constructs a Reviewer that runs on modelRef, resolved
|
||||
// through rt (the same provider runtime the worker's own agent runner
|
||||
// uses). rt must be non-nil.
|
||||
func newSubagentReviewer(rt *runtime.Runtime, modelRef string) *subagentReviewer {
|
||||
return &subagentReviewer{runtime: rt, modelRef: modelRef}
|
||||
}
|
||||
|
||||
var _ workflow.Reviewer = (*subagentReviewer)(nil)
|
||||
|
||||
// Review runs one adversarial review. It never returns a Go error: every
|
||||
// failure mode (unresolvable model, a Subagent.Run error, a truncated
|
||||
// run) folds into the returned ReviewReport, per
|
||||
// docs/prds/adversarial-self-review.md section 4's fail-closed contract.
|
||||
func (s *subagentReviewer) Review(ctx context.Context, req workflow.ReviewRequest) workflow.ReviewReport {
|
||||
if s.runtime == nil {
|
||||
return workflow.NewNotRunReviewReport("no provider runtime configured for the reviewer")
|
||||
}
|
||||
provider, model, err := s.runtime.ChatProvider(ctx, s.modelRef)
|
||||
if err != nil {
|
||||
return workflow.NewNotRunReviewReport(fmt.Sprintf("resolve reviewer model %q: %v", s.modelRef, err))
|
||||
}
|
||||
|
||||
var findings []workflow.ReviewFinding
|
||||
var checks []workflow.ReviewCheck
|
||||
tools := reviewerToolSet(req.SnapshotDir, &findings, &checks)
|
||||
|
||||
maxSteps := req.MaxSteps
|
||||
if maxSteps <= 0 {
|
||||
maxSteps = defaultReviewMaxSteps
|
||||
}
|
||||
|
||||
sub := agent.Subagent{
|
||||
Provider: provider,
|
||||
Model: model,
|
||||
System: reviewerSystemPrompt,
|
||||
Tools: tools,
|
||||
MaxSteps: maxSteps,
|
||||
}
|
||||
|
||||
summary, runErr := sub.Run(ctx, reviewerPrompt(req))
|
||||
if runErr != nil {
|
||||
// A truncated or errored run still yields whatever the reviewer
|
||||
// captured before it ran out of budget -- those findings are real
|
||||
// and must not be discarded just because the run's own
|
||||
// conclusion never arrived (docs/prds/adversarial-self-review.md
|
||||
// section 1, "findings return through a closure"). Zero captured
|
||||
// findings on error means the reviewer never got anywhere, which
|
||||
// fail-closed treats as not having run at all.
|
||||
if len(findings) == 0 {
|
||||
return workflow.NewNotRunReviewReport(runErr.Error())
|
||||
}
|
||||
return completedReview(findings, checks, "")
|
||||
}
|
||||
return completedReview(findings, checks, summary)
|
||||
}
|
||||
|
||||
// completedReview builds a completed report carrying the captured findings
|
||||
// and the properties the reviewer verified clean.
|
||||
func completedReview(findings []workflow.ReviewFinding, checks []workflow.ReviewCheck, summary string) workflow.ReviewReport {
|
||||
report := workflow.NewCompletedReviewReport(findings, summary)
|
||||
report.Checked = checks
|
||||
return report
|
||||
}
|
||||
|
||||
// reviewerSystemPrompt instructs the reviewer per CLAUDE.md's own
|
||||
// adversarial-review discipline: assume every line is wrong until proven
|
||||
// correct, work the checklist, report only what a fresh reader can verify
|
||||
// from what it was given.
|
||||
const reviewerSystemPrompt = `You are a fresh adversarial code reviewer. You did not write this change and have no access to how or why it was written -- only what is given to you below.
|
||||
|
||||
Assume every line is wrong until you have verified it is correct. Read whole files with your read tool, not just diff hunks, before concluding a call site or interface is satisfied. Use grep/find to check for other call sites a change affects.
|
||||
|
||||
Check for: dead code, unchecked errors, hardcoded values that should be parameters, interface-satisfaction defects, nil-pointer risk, goroutine leaks, races and unsynchronized shared state.
|
||||
|
||||
For every defect you find, call record_finding with: the file and line, a one-sentence defect statement, a concrete failure scenario (specific inputs or state that produce the wrong output or a crash -- not a hypothetical), a verdict, a level, and a category.
|
||||
|
||||
A finding must describe wrong behaviour or a crash. Style, formatting, naming, and preference nits are out of contract -- do not report them; they are exactly the padding that teaches an operator to skim past a findings list.
|
||||
|
||||
As you clear each checklist property, call record_checked with the property and how you verified it (which files or call sites you read). Record every property you actually checked and found correct, even when you also found defects; a review that reports no findings must still record what it checked, because "I checked and it is fine" and "I did not look" must not read the same.
|
||||
|
||||
Verdict is "confirmed" only when you have traced the actual failure -- read the code paths involved and can state exactly how it goes wrong. Verdict is "plausible" for a real worry you have not fully traced. Only a "confirmed" finding at level "error" blocks the pull request; do not inflate a plausible worry to confirmed/error to make it count -- an unjustified block is worse than a missed one, because it teaches the operator to stop trusting your reports.
|
||||
|
||||
Level is "error" for a defect that blocks; "warn" for something worth knowing but not blocking.
|
||||
|
||||
When a confirmed defect's fix is mechanical, and only then, pass suggestion: the exact text that should replace the anchored line, so the author can apply it in one click. It replaces that line exactly, so include the whole line (indentation included) and nothing else, and never guess -- a wrong one-click fix is worse than none. Do not pass a suggestion for a plausible finding, or for a fix you cannot state as a single line.
|
||||
|
||||
When you have finished checking, reply with a short summary of what you checked and what you found (or that you found nothing). If you find nothing, say so plainly -- reporting zero findings on properties you actually checked is a valid and expected outcome, not a failure to find something.`
|
||||
|
||||
// reviewerPrompt renders the reviewer's mission: the diff and issue text.
|
||||
// The snapshot itself is not embedded here -- it reaches the reviewer only
|
||||
// through its read-only toolset, rooted at SnapshotDir, never as prompt
|
||||
// text the reviewer could mistake for something it already checked.
|
||||
func reviewerPrompt(req workflow.ReviewRequest) string {
|
||||
var b strings.Builder
|
||||
b.WriteString("Review the following change. The full file tree at the reviewed commit is available through your tools; ")
|
||||
b.WriteString("start by reading the files the diff touches, not just the diff itself.\n\n")
|
||||
b.WriteString("<issue>\n")
|
||||
b.WriteString(req.IssueText)
|
||||
b.WriteString("\n</issue>\n\n<diff>\n")
|
||||
b.WriteString(req.Diff)
|
||||
b.WriteString("\n</diff>\n")
|
||||
return b.String()
|
||||
}
|
||||
|
||||
// reviewerToolSet builds the reviewer's read-only toolset, rooted at
|
||||
// snapshotDir, plus the structured capture tools that append directly to
|
||||
// findings and checks. This is a distinct toolset built fresh for each
|
||||
// review -- never the worker's own registry, which holds write/edit/shell
|
||||
// tools and the worktreerpc publication grant.
|
||||
func reviewerToolSet(snapshotDir string, findings *[]workflow.ReviewFinding, checks *[]workflow.ReviewCheck) core.ToolSet {
|
||||
reg := toolkit.NewRegistry()
|
||||
readOnly := []toolkit.Tool{
|
||||
toolkit.NewReadTool(snapshotDir, toolkit.NewReadTracker()),
|
||||
toolkit.NewGrepTool(snapshotDir),
|
||||
toolkit.NewFindTool(snapshotDir),
|
||||
}
|
||||
for _, tool := range readOnly {
|
||||
_ = reg.Register(tool) // names are fixed and distinct; Register cannot fail here
|
||||
}
|
||||
set := reg.CoreToolSet(toolkit.NonInteractiveBridge{})
|
||||
set["record_finding"] = recordFindingTool(findings)
|
||||
set["record_checked"] = recordCheckedTool(checks)
|
||||
return set
|
||||
}
|
||||
|
||||
// checkInput is the reviewer-facing shape of workflow.ReviewCheck.
|
||||
type checkInput struct {
|
||||
Property string `json:"property" jsonschema:"description=The property or code path you verified clean, e.g. 'nil-safety of Foo callers'."`
|
||||
Evidence string `json:"evidence" jsonschema:"description=How you verified it, e.g. 'read all 4 callers; each nil-checks before use'."`
|
||||
}
|
||||
|
||||
// recordCheckedTool builds the typed capture tool the reviewer calls once per
|
||||
// property it verified clean. Without it a zero-finding review reads the same
|
||||
// as a review that never looked; with it, "ran and found nothing" arrives
|
||||
// backed by what was actually checked.
|
||||
func recordCheckedTool(checks *[]workflow.ReviewCheck) *core.Tool {
|
||||
return core.NewTypedTool(
|
||||
"record_checked",
|
||||
"Record one property or code path you verified clean. Call this once per property you actually checked and found correct -- a review that reports no findings must still record what it checked.",
|
||||
func(_ context.Context, in checkInput) (string, error) {
|
||||
check := workflow.ReviewCheck{Property: in.Property, Evidence: in.Evidence}
|
||||
if err := check.Validate(); err != nil {
|
||||
return "record_checked rejected: " + err.Error(), nil //nolint:nilerr // rejection feedback lets the model retry with a valid check
|
||||
}
|
||||
*checks = append(*checks, check)
|
||||
return "check recorded", nil
|
||||
},
|
||||
)
|
||||
}
|
||||
|
||||
// findingInput is the reviewer-facing shape of workflow.ReviewFinding: the
|
||||
// model reports plain strings for Verdict/Level/Category, validated and
|
||||
// converted before being appended.
|
||||
type findingInput struct {
|
||||
File string `json:"file" jsonschema:"description=Repo-relative file path where the defect is located."`
|
||||
Line int `json:"line" jsonschema:"description=Line number where the defect is located."`
|
||||
Defect string `json:"defect" jsonschema:"description=One-sentence statement of the defect."`
|
||||
FailureScenario string `json:"failure_scenario" jsonschema:"description=Concrete inputs or state that produce the wrong output or a crash -- not a hypothetical."`
|
||||
Suggestion string `json:"suggestion,omitempty" jsonschema:"description=Optional. The exact replacement for the anchored line, when the fix is mechanical and you are certain of it -- it is offered as a one-click apply, so an approximate or partial line is worse than none. Only a confirmed finding may carry one; omit it for a plausible finding. Single line only."`
|
||||
Verdict string `json:"verdict" jsonschema:"description=Only 'confirmed' may block. Use 'plausible' for a real worry you have not fully traced.,enum=confirmed|plausible"`
|
||||
Level string `json:"level" jsonschema:"description=error blocks when confirmed; warn is advisory only.,enum=error|warn"`
|
||||
Category string `json:"category" jsonschema:"enum=dead-code|unchecked-error|hardcoded-value|interface-satisfaction|nil-risk|goroutine-leak|race|other"`
|
||||
}
|
||||
|
||||
// recordFindingTool builds the typed capture tool the reviewer must call
|
||||
// to report a defect. Rejecting an invalid finding with a plain-text
|
||||
// message (rather than a Go error) lets the model see what was wrong and
|
||||
// retry, the same environmental-enforcement pattern the rest of the
|
||||
// agent-loop tool contract uses.
|
||||
func recordFindingTool(findings *[]workflow.ReviewFinding) *core.Tool {
|
||||
return core.NewTypedTool(
|
||||
"record_finding",
|
||||
"Report one defect found during review. Call this once per defect; do not summarize multiple defects into one call.",
|
||||
func(_ context.Context, in findingInput) (string, error) {
|
||||
finding := workflow.ReviewFinding{
|
||||
File: in.File,
|
||||
Line: in.Line,
|
||||
Defect: in.Defect,
|
||||
FailureScenario: in.FailureScenario,
|
||||
Suggestion: in.Suggestion,
|
||||
Verdict: workflow.ReviewVerdict(in.Verdict),
|
||||
Level: workflow.ReviewLevel(in.Level),
|
||||
Category: workflow.ReviewCategory(in.Category),
|
||||
}
|
||||
if err := finding.Validate(); err != nil {
|
||||
return "record_finding rejected: " + err.Error(), nil //nolint:nilerr // rejection feedback lets the model retry with a valid finding
|
||||
}
|
||||
*findings = append(*findings, finding)
|
||||
return "finding recorded", nil
|
||||
},
|
||||
)
|
||||
}
|
||||
@@ -1,252 +0,0 @@
|
||||
package agentworker
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"slices"
|
||||
"testing"
|
||||
|
||||
"github.com/samcharles93/ai-sdk/agent"
|
||||
"github.com/samcharles93/ai-sdk/chat"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow"
|
||||
)
|
||||
|
||||
// TestReviewerToolSetIsReadOnlyAndHasNoMutationPath asserts, as a
|
||||
// construction fact rather than a prompt claim, that the reviewer's
|
||||
// toolset carries no tool capable of writing, editing, or running a
|
||||
// shell command -- the class of tool that could reach the worktreerpc
|
||||
// publication grant or otherwise mutate anything. Read/grep/find plus the
|
||||
// findings-capture tool are the entire surface.
|
||||
func TestReviewerToolSetIsReadOnlyAndHasNoMutationPath(t *testing.T) {
|
||||
var findings []workflow.ReviewFinding
|
||||
var checks []workflow.ReviewCheck
|
||||
set := reviewerToolSet(t.TempDir(), &findings, &checks)
|
||||
|
||||
names := make([]string, 0, len(set))
|
||||
for name := range set {
|
||||
names = append(names, name)
|
||||
}
|
||||
slices.Sort(names)
|
||||
|
||||
want := []string{"find", "grep", "read", "record_checked", "record_finding"}
|
||||
slices.Sort(want)
|
||||
if !slices.Equal(names, want) {
|
||||
t.Fatalf("reviewer toolset = %v, want exactly %v (no write/edit/shell)", names, want)
|
||||
}
|
||||
}
|
||||
|
||||
// TestReviewerToolSetIsRootedAtTheGivenSnapshot asserts the read tool
|
||||
// cannot read outside the snapshot directory it was constructed with --
|
||||
// it has no path back to the implementer's actual worktree.
|
||||
func TestReviewerToolSetIsRootedAtTheGivenSnapshot(t *testing.T) {
|
||||
snapshot := t.TempDir()
|
||||
if err := os.WriteFile(filepath.Join(snapshot, "in-snapshot.txt"), []byte("ok\n"), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
outside := t.TempDir()
|
||||
if err := os.WriteFile(filepath.Join(outside, "secret.txt"), []byte("nope\n"), 0o644); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
|
||||
var findings []workflow.ReviewFinding
|
||||
var checks []workflow.ReviewCheck
|
||||
set := reviewerToolSet(snapshot, &findings, &checks)
|
||||
readTool := set["read"]
|
||||
if readTool == nil {
|
||||
t.Fatal("reviewer toolset has no read tool")
|
||||
}
|
||||
|
||||
out, err := readTool.Execute(t.Context(), `{"path":"in-snapshot.txt"}`)
|
||||
if err != nil {
|
||||
t.Fatalf("read in-snapshot file: %v", err)
|
||||
}
|
||||
if !containsSubstr(out, "ok") {
|
||||
t.Errorf("read in-snapshot file = %q, want it to contain the file's content", out)
|
||||
}
|
||||
|
||||
// Tool failures are encoded in-band in the returned content, not as a
|
||||
// Go error (toolkit.Registry.CoreToolSet's own contract) -- an escape
|
||||
// attempt must reject there, not succeed.
|
||||
escapeOut, err := readTool.Execute(t.Context(), `{"path":"`+filepath.Join(outside, "secret.txt")+`"}`)
|
||||
if err != nil {
|
||||
t.Fatalf("read outside-snapshot path: %v", err)
|
||||
}
|
||||
if containsSubstr(escapeOut, "nope") {
|
||||
t.Errorf("read tool returned content from outside the snapshot: %q", escapeOut)
|
||||
}
|
||||
if !containsSubstr(escapeOut, "escapes") {
|
||||
t.Errorf("read tool output = %q, want a path-confinement rejection", escapeOut)
|
||||
}
|
||||
}
|
||||
|
||||
// TestRecordFindingToolAppendsToCapturedSlice asserts the capture-tool
|
||||
// contract: findings are recorded via the closure over the findings
|
||||
// slice, not returned from Subagent.Run's text.
|
||||
func TestRecordFindingToolAppendsToCapturedSlice(t *testing.T) {
|
||||
var findings []workflow.ReviewFinding
|
||||
tool := recordFindingTool(&findings)
|
||||
|
||||
input := `{"file":"main.go","line":10,"defect":"nil deref","failure_scenario":"calling Foo(nil) panics","verdict":"confirmed","level":"error","category":"nil-risk"}`
|
||||
if _, err := tool.Execute(t.Context(), input); err != nil {
|
||||
t.Fatalf("record_finding: %v", err)
|
||||
}
|
||||
if len(findings) != 1 {
|
||||
t.Fatalf("captured %d findings, want 1", len(findings))
|
||||
}
|
||||
if !findings[0].Blocking() {
|
||||
t.Error("captured finding is not blocking, want confirmed+error to block")
|
||||
}
|
||||
}
|
||||
|
||||
// TestRecordFindingToolRejectsInvalidVerdictWithoutError asserts an
|
||||
// invalid finding is rejected in-band (so the model can retry) rather
|
||||
// than surfacing as a hard tool error, and is not captured.
|
||||
func TestRecordFindingToolRejectsInvalidVerdictWithoutError(t *testing.T) {
|
||||
var findings []workflow.ReviewFinding
|
||||
tool := recordFindingTool(&findings)
|
||||
|
||||
input := `{"file":"main.go","line":1,"defect":"x","failure_scenario":"y","verdict":"maybe","level":"error","category":"other"}`
|
||||
out, err := tool.Execute(t.Context(), input)
|
||||
if err != nil {
|
||||
t.Fatalf("record_finding returned a Go error for invalid input: %v", err)
|
||||
}
|
||||
if !containsSubstr(out, "rejected") {
|
||||
t.Errorf("record_finding output = %q, want a rejection message", out)
|
||||
}
|
||||
if len(findings) != 0 {
|
||||
t.Errorf("captured %d findings, want 0 for an invalid finding", len(findings))
|
||||
}
|
||||
}
|
||||
|
||||
// TestRecordCheckedToolAppendsToCapturedSlice asserts the calibration capture
|
||||
// contract: a cleared property is recorded through the closure, so a
|
||||
// zero-finding review can report what it actually checked.
|
||||
func TestRecordCheckedToolAppendsToCapturedSlice(t *testing.T) {
|
||||
var checks []workflow.ReviewCheck
|
||||
tool := recordCheckedTool(&checks)
|
||||
|
||||
input := `{"property":"nil-safety of Foo callers","evidence":"read all 4 callers; each nil-checks"}`
|
||||
if _, err := tool.Execute(t.Context(), input); err != nil {
|
||||
t.Fatalf("record_checked: %v", err)
|
||||
}
|
||||
if len(checks) != 1 || checks[0].Property != "nil-safety of Foo callers" {
|
||||
t.Fatalf("captured checks = %+v, want one check for the recorded property", checks)
|
||||
}
|
||||
}
|
||||
|
||||
// TestRecordCheckedToolRejectsMissingEvidence asserts a check without evidence
|
||||
// is rejected in-band and not captured, so "verified clean" cannot be recorded
|
||||
// as a bare assertion.
|
||||
func TestRecordCheckedToolRejectsMissingEvidence(t *testing.T) {
|
||||
var checks []workflow.ReviewCheck
|
||||
tool := recordCheckedTool(&checks)
|
||||
|
||||
out, err := tool.Execute(t.Context(), `{"property":"looks fine","evidence":""}`)
|
||||
if err != nil {
|
||||
t.Fatalf("record_checked returned a Go error for invalid input: %v", err)
|
||||
}
|
||||
if !containsSubstr(out, "rejected") {
|
||||
t.Errorf("record_checked output = %q, want a rejection message", out)
|
||||
}
|
||||
if len(checks) != 0 {
|
||||
t.Errorf("captured %d checks, want 0 for a check with no evidence", len(checks))
|
||||
}
|
||||
}
|
||||
|
||||
// TestCompletedReviewCarriesChecks asserts the report the reviewer returns
|
||||
// carries the captured checks, not just the findings.
|
||||
func TestCompletedReviewCarriesChecks(t *testing.T) {
|
||||
checks := []workflow.ReviewCheck{{Property: "p", Evidence: "e"}}
|
||||
report := completedReview(nil, checks, "summary")
|
||||
if !report.Ran() {
|
||||
t.Fatal("completedReview report did not run")
|
||||
}
|
||||
if len(report.Checked) != 1 || report.Checked[0].Property != "p" {
|
||||
t.Fatalf("report.Checked = %+v, want the captured check", report.Checked)
|
||||
}
|
||||
}
|
||||
|
||||
// TestReviewSubagentConstructionNeverSendsConversationHistory asserts, at
|
||||
// the exact agent.Subagent construction Review performs, that only a
|
||||
// prompt string reaches the model. This exercises the same Subagent{}
|
||||
// shape subagentReviewer.Review builds (provider, model, system prompt,
|
||||
// reviewerToolSet, MaxSteps) directly against a fake chat.Provider, so it
|
||||
// proves the construction fact without needing a full *runtime.Runtime:
|
||||
// Subagent.Run populates GenerateOptions.Prompt and never Messages, so
|
||||
// there is no code path for the implementer's transcript to travel
|
||||
// through.
|
||||
func TestReviewSubagentConstructionNeverSendsConversationHistory(t *testing.T) {
|
||||
captured := &capturingChatProvider{}
|
||||
var findings []workflow.ReviewFinding
|
||||
var checks []workflow.ReviewCheck
|
||||
req := workflow.ReviewRequest{
|
||||
SnapshotDir: t.TempDir(),
|
||||
Diff: "diff --git a/x.go b/x.go\n",
|
||||
IssueText: "some issue text",
|
||||
}
|
||||
|
||||
sub := agent.Subagent{
|
||||
Provider: captured,
|
||||
Model: "fake-model",
|
||||
System: reviewerSystemPrompt,
|
||||
Tools: reviewerToolSet(req.SnapshotDir, &findings, &checks),
|
||||
MaxSteps: defaultReviewMaxSteps,
|
||||
}
|
||||
prompt := reviewerPrompt(req)
|
||||
if _, err := sub.Run(t.Context(), prompt); err != nil {
|
||||
t.Fatalf("Subagent.Run() error = %v", err)
|
||||
}
|
||||
|
||||
if captured.lastRequest == nil {
|
||||
t.Fatal("chat provider was never called")
|
||||
}
|
||||
// The only non-system message the model ever sees is the one
|
||||
// Subagent.Run derives from the prompt string -- there is no code
|
||||
// path here for a second, implementer-authored message to arrive
|
||||
// alongside it.
|
||||
var userMessages int
|
||||
for _, m := range captured.lastRequest.Messages {
|
||||
if m.Role == chat.RoleUser {
|
||||
userMessages++
|
||||
if m.Content != prompt {
|
||||
t.Errorf("user message content = %q, want the review prompt %q", m.Content, prompt)
|
||||
}
|
||||
}
|
||||
}
|
||||
if userMessages != 1 {
|
||||
t.Errorf("chat.Request carried %d user messages, want exactly 1 (the review prompt, no implementer history)", userMessages)
|
||||
}
|
||||
}
|
||||
|
||||
func containsSubstr(s, substr string) bool {
|
||||
return len(substr) == 0 ||
|
||||
(len(s) >= len(substr) && func() bool {
|
||||
for i := 0; i+len(substr) <= len(s); i++ {
|
||||
if s[i:i+len(substr)] == substr {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}())
|
||||
}
|
||||
|
||||
// capturingChatProvider is a minimal chat.Provider fake that records the
|
||||
// last chat.Request it received and returns a fixed, valid completion.
|
||||
type capturingChatProvider struct {
|
||||
lastRequest *chat.Request
|
||||
}
|
||||
|
||||
func (c *capturingChatProvider) Name() string { return "fake" }
|
||||
|
||||
func (c *capturingChatProvider) Chat(_ context.Context, req chat.Request) (chat.Response, error) {
|
||||
r := req
|
||||
c.lastRequest = &r
|
||||
return chat.Response{Content: "no findings", FinishReason: "stop"}, nil
|
||||
}
|
||||
|
||||
func (c *capturingChatProvider) ChatStream(_ context.Context, req chat.Request) (chat.Stream, error) {
|
||||
return nil, errors.New("not implemented")
|
||||
}
|
||||
@@ -15,6 +15,7 @@ import (
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow"
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow/task"
|
||||
"github.com/samcharles93/archie-core/internal/events"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/prsource"
|
||||
"github.com/samcharles93/archie-core/internal/installtype"
|
||||
"github.com/samcharles93/archie-core/internal/storage"
|
||||
"github.com/samcharles93/archie-core/internal/taskrun"
|
||||
@@ -183,6 +184,7 @@ func worktreeOwnerID(env string) int {
|
||||
type taskDependencies struct {
|
||||
forge workflow.Forger
|
||||
store workflow.Store
|
||||
calls task.Caller
|
||||
trees remoteTrees
|
||||
events agentexec.EventPublisher
|
||||
// steps is the workflow step vocabulary pinned definitions are compiled
|
||||
@@ -216,12 +218,11 @@ func applyToolLimits(agent agentexec.Runner, policy config.ToolPolicy, allow []s
|
||||
runner.AllowTools = allow
|
||||
}
|
||||
|
||||
// stageRunners builds the runner every agent stage uses, and the reviewer.
|
||||
func stageRunners(req taskrun.Request, mcpSet *mcpProviderSet, newRunner runnerFactory, log *slog.Logger) (agentexec.Runner, workflow.Reviewer, error) {
|
||||
// stageRunners builds the runner every agent stage uses.
|
||||
func stageRunners(req taskrun.Request, mcpSet *mcpProviderSet, newRunner runnerFactory, log *slog.Logger) (agentexec.Runner, error) {
|
||||
if req.Harness != nil {
|
||||
// The built-in loop has no route to a model from a Kit container, so
|
||||
// the review stage parks rather than running on it.
|
||||
return agentexec.HarnessStages{Runner: agentexec.NewHarnessRunner(nil), Spec: *req.Harness}, nil, nil
|
||||
// The built-in loop has no route to a model from a Kit container.
|
||||
return agentexec.HarnessStages{Runner: agentexec.NewHarnessRunner(nil), Spec: *req.Harness}, nil
|
||||
}
|
||||
var agent agentexec.Runner
|
||||
if mcpSet != nil && mcpSet.registry != nil {
|
||||
@@ -230,10 +231,10 @@ func stageRunners(req taskrun.Request, mcpSet *mcpProviderSet, newRunner runnerF
|
||||
agent = newRunner(req.Providers, log)
|
||||
}
|
||||
if agent == nil {
|
||||
return nil, nil, fmt.Errorf("no agent runner configured for task %d", req.Task.ID)
|
||||
return nil, fmt.Errorf("no agent runner configured for task %d", req.Task.ID)
|
||||
}
|
||||
applyToolLimits(agent, req.Cfg.ToolPolicy, req.Tools)
|
||||
return agent, newReviewerFor(req), nil
|
||||
return agent, nil
|
||||
}
|
||||
|
||||
// routeTask remains available for routing-only callers. Production execution
|
||||
@@ -285,7 +286,7 @@ func runTask(ctx context.Context, req taskrun.Request, dependencies taskDependen
|
||||
log.Warn("mcp providers had errors, continuing with available tools", "err", mcpErr)
|
||||
}
|
||||
|
||||
agent, reviewer, err := stageRunners(req, mcpSet, newRunner, log)
|
||||
agent, err := stageRunners(req, mcpSet, newRunner, log)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
@@ -309,17 +310,27 @@ func runTask(ctx context.Context, req taskrun.Request, dependencies taskDependen
|
||||
}
|
||||
|
||||
tc := &workflow.TaskContext{
|
||||
Task: req.Task,
|
||||
Repo: req.Repo,
|
||||
Cfg: req.Cfg.ToConfig(),
|
||||
Forge: dependencies.forge,
|
||||
Store: dependencies.store,
|
||||
Trees: trees,
|
||||
Agent: agent,
|
||||
Reviewer: reviewer,
|
||||
Bus: bus,
|
||||
Log: log,
|
||||
Task: req.Task,
|
||||
Repo: req.Repo,
|
||||
Cfg: req.Cfg.ToConfig(),
|
||||
Forge: dependencies.forge,
|
||||
Store: dependencies.store,
|
||||
Calls: dependencies.calls,
|
||||
Trees: trees,
|
||||
Agent: agent,
|
||||
Bus: bus,
|
||||
Log: log,
|
||||
}
|
||||
// pr-review reads an external pull request's data from workDir, which the
|
||||
// daemon already populated before this task started (daemon's
|
||||
// prefetchPRReview, writing under workDir/.archie-pr-review -- the same
|
||||
// host directory Docker bind-mounts at storage.WorktreeMountDir) -- never
|
||||
// over the network, and never with a forge credential in this process.
|
||||
// See docs/development/agent.md, "Giving the agent something new".
|
||||
if req.Task.Workflow == "pr-review" {
|
||||
tc.PRSource = prsource.NewFromMount(filepath.Join(workDir, prsource.PrefetchDirName))
|
||||
}
|
||||
|
||||
if req.Repo.PersistentStorage {
|
||||
memory, readErr := readProjectMemory(storage.MemoryPath)
|
||||
if readErr != nil {
|
||||
|
||||
@@ -382,7 +382,8 @@ func startStateStoreGRPC(t *testing.T, local *pgstore.TaskDB) string {
|
||||
eda := pgstore.EDA(t, nil)
|
||||
staterpc.RegisterServer(server, staterpc.Deps{
|
||||
Tasks: local, Captures: eda, Mappings: eda, Bindings: eda,
|
||||
BindingDispatcher: eda, BindingTaskCreator: local,
|
||||
BindingDispatcher: eda, BindingTaskCreator: local, WorkflowCalls: local,
|
||||
Steps: local, Canceller: local,
|
||||
})
|
||||
go func() { _ = server.Serve(listener) }()
|
||||
t.Cleanup(func() { server.Stop(); _ = listener.Close() })
|
||||
|
||||
@@ -0,0 +1,153 @@
|
||||
package agentworker
|
||||
|
||||
import (
|
||||
"context"
|
||||
"log/slog"
|
||||
"testing"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/agentexec"
|
||||
"github.com/samcharles93/archie-core/internal/config"
|
||||
"github.com/samcharles93/archie-core/internal/domain/org"
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow"
|
||||
workflowtask "github.com/samcharles93/archie-core/internal/domain/workflow/task"
|
||||
agentnats "github.com/samcharles93/archie-core/internal/infrastructure/agenttransport/nats"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/postgres/pgstore"
|
||||
"github.com/samcharles93/archie-core/internal/taskrun"
|
||||
)
|
||||
|
||||
// stubRunner is the agent runner that lets a test workflow end in an
|
||||
// agent.run tail without an LLM: the call step under test needs no agent,
|
||||
// but the workflow must still end with an outcome.
|
||||
type stubRunner struct{}
|
||||
|
||||
func (stubRunner) Run(_ context.Context, _ string, req agentexec.Request, _ agentexec.ToolCallReporter) (agentexec.Result, error) {
|
||||
return agentexec.Result{
|
||||
Version: agentexec.ProtocolVersion, TaskID: req.TaskID, Attempt: req.Attempt,
|
||||
Stage: req.Stage, Status: agentexec.StatusPassed, Summary: "reported",
|
||||
}, nil
|
||||
}
|
||||
|
||||
// fakeScratchTrees is the Trees for a scratch task: the workspace already
|
||||
// exists (the call step needs none, the agent.run tail works in it), and
|
||||
// nothing publishes.
|
||||
type fakeScratchTrees struct {
|
||||
dir string
|
||||
}
|
||||
|
||||
func (f *fakeScratchTrees) Prepare(context.Context, string, string, string, int, string, string, string) (string, string, error) {
|
||||
return f.dir, "", nil
|
||||
}
|
||||
|
||||
func (*fakeScratchTrees) CommitAll(context.Context, string, string) (bool, error) { return false, nil }
|
||||
func (*fakeScratchTrees) Push(context.Context) error { return nil }
|
||||
func (*fakeScratchTrees) Diff(context.Context, string, string) (string, error) { return "", nil }
|
||||
func (*fakeScratchTrees) ChangedFiles(context.Context, string, string) ([]string, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
func (*fakeScratchTrees) ChangedLines(context.Context, string, string) (int, error) { return 0, nil }
|
||||
func (*fakeScratchTrees) Snapshot(context.Context, string, string) error { return nil }
|
||||
|
||||
// TestExecuteTaskRequestStartsWorkflowCallCallee proves the engine's
|
||||
// task.Caller wiring end to end: a run of a repository-none workflow carrying
|
||||
// one workflow.call step starts a real callee task row through the same
|
||||
// State Store gRPC contract the production worker dials
|
||||
// (docs/prds/workflow-calls.md), and the caller carries on to its tail.
|
||||
func TestExecuteTaskRequestStartsWorkflowCallCallee(t *testing.T) {
|
||||
ctx := t.Context()
|
||||
st := pgstore.Open(t)
|
||||
|
||||
const callerYAML = "id: caller\nrepository: none\ninputs:\n src_ip: {type: string}\nsteps:\n - type: workflow.call\n settings:\n workflow: callee\n inputs: {src_ip: \"inputs.src_ip\"}\n wait: false\n - type: agent.run\n settings:\n mission: report\n"
|
||||
// A real caller row, claimed and running, so the store's enqueue reads
|
||||
// the same row shape production does.
|
||||
task, err := st.EnqueueChatTask(ctx, "", "", "workflow.call integration", "", "caller", "", nil)
|
||||
if err != nil {
|
||||
t.Fatalf("seed caller task: %v", err)
|
||||
}
|
||||
if err := st.Transition(ctx, task.ID, task.Status, workflow.StatusRunning, "started"); err != nil {
|
||||
t.Fatalf("claim caller: %v", err)
|
||||
}
|
||||
task.Status = workflow.StatusRunning
|
||||
task.Inputs = map[string]any{"src_ip": "10.0.0.9"}
|
||||
task.WorkflowDefinitionYAML = callerYAML
|
||||
task.WorkflowDefinitionDigest = workflow.DigestDefinition(callerYAML)
|
||||
if err := st.Update(ctx, task); err != nil {
|
||||
t.Fatalf("seed caller task: %v", err)
|
||||
}
|
||||
|
||||
natsSrv := startEmbeddedTaskRPCServer(t)
|
||||
transport, err := agentnats.Connect(ctx, agentnats.Config{
|
||||
URL: natsSrv.ClientURL(),
|
||||
StateStoreURL: startStateStoreGRPC(t, st),
|
||||
}, slog.New(slog.DiscardHandler))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
t.Cleanup(transport.Close)
|
||||
|
||||
workDir := t.TempDir()
|
||||
request := taskrun.Request{
|
||||
Task: task,
|
||||
Repo: config.Repo{},
|
||||
Cfg: config.Config{Models: map[string]string{"builder": "p/m"}}.ForTask(),
|
||||
WorkflowDefinition: callerYAML,
|
||||
}
|
||||
dependencies := taskDependencies{
|
||||
store: transport.Store(rpcTimeout),
|
||||
calls: transport.Calls(rpcTimeout),
|
||||
trees: &fakeScratchTrees{dir: workDir},
|
||||
steps: testSteps(t),
|
||||
}
|
||||
fakeRunner := runnerFactory(func(map[string]agentexec.Provider, *slog.Logger) agentexec.Runner { return stubRunner{} })
|
||||
response, err := runTask(ctx, request, dependencies, fakeRunner, workDir, slog.New(slog.DiscardHandler))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if response.Status != workflow.StatusCompleted {
|
||||
t.Fatalf("response status = %q (park reason %q), want completed", response.Status, response.Task.ParkReason)
|
||||
}
|
||||
|
||||
callee := calleeTaskOf(t, ctx, st, task.ID)
|
||||
if callee.Workflow != "callee" || callee.CallParentTaskID != task.ID || callee.CallDepth != 1 {
|
||||
t.Fatalf("callee = %+v, want workflow callee linked to task %d at depth 1", callee, task.ID)
|
||||
}
|
||||
if callee.Inputs["src_ip"] != "10.0.0.9" {
|
||||
t.Fatalf("callee inputs = %+v, want the call's resolved reference", callee.Inputs)
|
||||
}
|
||||
if callee.Org != org.OrgID("default") {
|
||||
t.Fatalf("callee org = %q, want the caller's %q", callee.Org, task.Org)
|
||||
}
|
||||
}
|
||||
|
||||
// calleeTaskOf reads the one callee task whose call_parent_task_id is
|
||||
// callerTaskID, straight off the pool the test owns.
|
||||
func calleeTaskOf(t *testing.T, ctx context.Context, st *pgstore.TaskDB, callerTaskID int64) *workflow.Task {
|
||||
t.Helper()
|
||||
rows, err := st.Pool.Query(ctx,
|
||||
`SELECT id, workflow, call_parent_task_id, call_depth, org_id, inputs
|
||||
FROM tasks WHERE call_parent_task_id = $1`, callerTaskID)
|
||||
if err != nil {
|
||||
t.Fatalf("callee query: %v", err)
|
||||
}
|
||||
defer rows.Close()
|
||||
var callees []*workflow.Task
|
||||
for rows.Next() {
|
||||
var id, parent, depth int64
|
||||
var wf, orgID, inputs string
|
||||
if err := rows.Scan(&id, &wf, &parent, &depth, &orgID, &inputs); err != nil {
|
||||
t.Fatalf("callee scan: %v", err)
|
||||
}
|
||||
decoded, _ := workflowtask.DecodeInputs(inputs)
|
||||
callees = append(callees, &workflow.Task{
|
||||
ID: id, Workflow: wf, CallParentTaskID: parent, CallDepth: int(depth),
|
||||
Org: org.OrgID(orgID), Inputs: decoded,
|
||||
})
|
||||
}
|
||||
if err := rows.Err(); err != nil {
|
||||
t.Fatalf("callee rows: %v", err)
|
||||
}
|
||||
if len(callees) != 1 {
|
||||
t.Fatalf("callee tasks of %d = %+v, want exactly one", callerTaskID, callees)
|
||||
}
|
||||
return callees[0]
|
||||
}
|
||||
@@ -8,6 +8,7 @@ import (
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/agentexec"
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow"
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow/task"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/agentboot"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/agentgit"
|
||||
agentnats "github.com/samcharles93/archie-core/internal/infrastructure/agenttransport/nats"
|
||||
@@ -50,6 +51,7 @@ type workerTransport interface {
|
||||
SubscribeTasks(context.Context, int64, agentnats.TaskHandler, *slog.Logger) (agentnats.Subscription, error)
|
||||
Forger(string, time.Duration) workflow.Forger
|
||||
Store(time.Duration) workflow.Store
|
||||
Calls(time.Duration) task.Caller
|
||||
Trees(string, string, time.Duration) agentnats.RemoteTrees
|
||||
}
|
||||
|
||||
@@ -152,6 +154,7 @@ func run(ctx context.Context, settings Settings, log *slog.Logger, dependencies
|
||||
type taskServiceTransport interface {
|
||||
Forger(string, time.Duration) workflow.Forger
|
||||
Store(time.Duration) workflow.Store
|
||||
Calls(time.Duration) task.Caller
|
||||
Trees(string, string, time.Duration) agentnats.RemoteTrees
|
||||
EventPublisher() agentexec.EventPublisher
|
||||
}
|
||||
@@ -161,6 +164,7 @@ func executeTaskRequest(ctx context.Context, request taskrun.Request, transport
|
||||
dependencies := taskDependencies{
|
||||
forge: transport.Forger(request.Task.Identity, rpcTimeout),
|
||||
store: transport.Store(rpcTimeout),
|
||||
calls: transport.Calls(rpcTimeout),
|
||||
trees: transport.Trees(request.Task.Identity, request.WorktreeGrant, rpcTimeout),
|
||||
events: transport.EventPublisher(),
|
||||
steps: steps,
|
||||
|
||||
@@ -11,6 +11,7 @@ import (
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/agentexec"
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow"
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow/task"
|
||||
agentnats "github.com/samcharles93/archie-core/internal/infrastructure/agenttransport/nats"
|
||||
)
|
||||
|
||||
@@ -75,6 +76,8 @@ func (*workerTransportStub) Forger(string, time.Duration) workflow.Forger { retu
|
||||
|
||||
func (*workerTransportStub) Store(time.Duration) workflow.Store { return nil }
|
||||
|
||||
func (*workerTransportStub) Calls(time.Duration) task.Caller { return nil }
|
||||
|
||||
func (*workerTransportStub) Trees(string, string, time.Duration) agentnats.RemoteTrees { return nil }
|
||||
|
||||
func TestRunPassesCompleteTransportConfiguration(t *testing.T) {
|
||||
|
||||
@@ -0,0 +1,110 @@
|
||||
// The `archied access reset` command: the locked-out-org and broken-instance
|
||||
// recovery surface (docs/prds/orgs-and-access.md, "Recovering from a
|
||||
// locked-out org"). It restores the shipped role policies for one org and
|
||||
// removes its other org-level policies, or removes the stored instance
|
||||
// policies; the cross-org forbid is engine-enforced and survives any reset.
|
||||
//
|
||||
// It runs only on the State Store host, never over the network, and is
|
||||
// recorded as an audit event. It claims the same store ownership the State
|
||||
// Store holds, so a running store refuses it: stop the store, reset, start
|
||||
// the store.
|
||||
package archied
|
||||
|
||||
import (
|
||||
"context"
|
||||
"flag"
|
||||
"fmt"
|
||||
"io"
|
||||
|
||||
"github.com/jackc/pgx/v5/pgxpool"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/domain/access"
|
||||
"github.com/samcharles93/archie-core/internal/domain/org"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/configuration"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/postgres"
|
||||
)
|
||||
|
||||
// accessResetCommand is the argv selector for the recovery command.
|
||||
const accessResetCommand = "access"
|
||||
|
||||
// IsAccessResetArgs reports whether args selects the access recovery command.
|
||||
func IsAccessResetArgs(args []string) bool {
|
||||
return len(args) > 2 && args[0] == accessResetCommand && args[1] == resetCommand
|
||||
}
|
||||
|
||||
const resetCommand = "reset"
|
||||
|
||||
// RunAccessReset performs the reset and returns the process exit code:
|
||||
// 0 reset, 1 failure, 2 usage.
|
||||
func RunAccessReset(ctx context.Context, args []string, stderr io.Writer) int {
|
||||
fs := flag.NewFlagSet(resetCommand, flag.ContinueOnError)
|
||||
fs.SetOutput(stderr)
|
||||
cfgPath := fs.String("config", configuration.DefaultConfigPath(), "path to a TOML/YAML config file or configuration directory")
|
||||
overlayPath := fs.String("config-overlay", "", "path to a TOML/YAML overlay file or configuration directory applied on top of -config")
|
||||
orgFlag := fs.String("org", "", "org whose access to reset; conflicts with --instance")
|
||||
instance := fs.Bool("instance", false, "reset the stored instance policies")
|
||||
if err := fs.Parse(args); err != nil {
|
||||
return 2
|
||||
}
|
||||
if fs.NArg() > 0 {
|
||||
fmt.Fprintf(stderr, "reset: unexpected argument %q\n", fs.Arg(0))
|
||||
return 2
|
||||
}
|
||||
if (*orgFlag != "" && *instance) || (*orgFlag == "" && !*instance) {
|
||||
fmt.Fprintln(stderr, "reset: give exactly one of --org <org> or --instance")
|
||||
return 2
|
||||
}
|
||||
|
||||
b := newBootstrap()
|
||||
defer b.cleanup()
|
||||
if err := b.loadConfig(ctx, *cfgPath, *overlayPath); err != nil {
|
||||
return 1
|
||||
}
|
||||
if err := b.openStateStorePool(ctx); err != nil {
|
||||
// A running State Store holds the ownership claim; the reset must not
|
||||
// race it. Stop the store, reset, start the store.
|
||||
fmt.Fprintln(stderr, "reset: open the State Store database (stop archie-state-store first)")
|
||||
return 1
|
||||
}
|
||||
resetter, ok := b.st.(access.Resetter)
|
||||
if !ok {
|
||||
fmt.Fprintln(stderr, "reset: the State Store does not support the access reset surface")
|
||||
return 1
|
||||
}
|
||||
var err error
|
||||
switch {
|
||||
case *instance:
|
||||
err = resetter.ResetInstancePolicies(ctx)
|
||||
default:
|
||||
err = resetter.ResetOrgPolicies(ctx, org.OrgID(*orgFlag))
|
||||
}
|
||||
if err != nil {
|
||||
fmt.Fprintf(stderr, "reset: %v\n", err)
|
||||
return 1
|
||||
}
|
||||
if err := recordResetAudit(ctx, b.pg, *orgFlag, *instance); err != nil {
|
||||
fmt.Fprintf(stderr, "reset: audit: %v\n", err)
|
||||
return 1
|
||||
}
|
||||
fmt.Fprintf(stderr, "reset: access policies for %s restored to the shipped set\n", resetTarget(*orgFlag, *instance))
|
||||
return 0
|
||||
}
|
||||
|
||||
// resetTarget names what the reset covered, for the operator's output.
|
||||
func resetTarget(orgID string, instance bool) string {
|
||||
if instance {
|
||||
return "the instance"
|
||||
}
|
||||
return fmt.Sprintf("org %q", orgID)
|
||||
}
|
||||
|
||||
// recordResetAudit writes the one audit row the reset is recorded as. The
|
||||
// policy changes themselves carry their own sys_audit rows; this names the
|
||||
// recovery.
|
||||
func recordResetAudit(ctx context.Context, pool *pgxpool.Pool, orgID string, instance bool) error {
|
||||
key := "reset/instance"
|
||||
if !instance {
|
||||
key = fmt.Sprintf("reset/org/%s", orgID)
|
||||
}
|
||||
return postgres.New(pool).RecordResetAudit(ctx, key)
|
||||
}
|
||||
@@ -0,0 +1,54 @@
|
||||
package archied
|
||||
|
||||
import (
|
||||
"strings"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestIsAccessResetArgs(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
args []string
|
||||
want bool
|
||||
}{
|
||||
{name: "org reset", args: []string{"access", "reset", "--org", "acme"}, want: true},
|
||||
{name: "instance reset", args: []string{"access", "reset", "--instance"}, want: true},
|
||||
{name: "config first", args: []string{"access", "reset", "-config", "/tmp/config.toml", "--org", "acme"}, want: true},
|
||||
{name: "setup is not a reset", args: []string{"setup"}, want: false},
|
||||
{name: "bare access", args: []string{"access"}, want: false},
|
||||
{name: "other subcommand", args: []string{"access", "grant"}, want: false},
|
||||
}
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
if got := IsAccessResetArgs(tt.args); got != tt.want {
|
||||
t.Fatalf("IsAccessResetArgs(%v) = %v, want %v", tt.args, got, tt.want)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestRunAccessResetUsage(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
args []string
|
||||
wantCode int
|
||||
wantText string
|
||||
}{
|
||||
{name: "no target", args: nil, wantCode: 2, wantText: "exactly one of --org"},
|
||||
{name: "both targets", args: []string{"--org", "acme", "--instance"}, wantCode: 2, wantText: "exactly one of --org"},
|
||||
{name: "unexpected argument", args: []string{"--instance", "extra"}, wantCode: 2, wantText: "unexpected argument"},
|
||||
{name: "unknown flag", args: []string{"--workspace", "net"}, wantCode: 2},
|
||||
}
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
var stderr strings.Builder
|
||||
code := RunAccessReset(t.Context(), tt.args, &stderr)
|
||||
if code != tt.wantCode {
|
||||
t.Fatalf("RunAccessReset(%v) = %d, want %d (stderr: %s)", tt.args, code, tt.wantCode, stderr.String())
|
||||
}
|
||||
if tt.wantText != "" && !strings.Contains(stderr.String(), tt.wantText) {
|
||||
t.Fatalf("stderr = %q, want it to name %q", stderr.String(), tt.wantText)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -30,6 +30,7 @@ import (
|
||||
"github.com/samcharles93/archie-core/internal/container"
|
||||
controlpb "github.com/samcharles93/archie-core/internal/contracts/controlplane/v1"
|
||||
"github.com/samcharles93/archie-core/internal/daemon"
|
||||
"github.com/samcharles93/archie-core/internal/domain/access"
|
||||
"github.com/samcharles93/archie-core/internal/domain/applystatus"
|
||||
"github.com/samcharles93/archie-core/internal/domain/curator"
|
||||
"github.com/samcharles93/archie-core/internal/domain/eda/module"
|
||||
@@ -46,6 +47,7 @@ import (
|
||||
"github.com/samcharles93/archie-core/internal/forge"
|
||||
forgewebhook "github.com/samcharles93/archie-core/internal/forge/webhook"
|
||||
"github.com/samcharles93/archie-core/internal/gateway"
|
||||
infraaccess "github.com/samcharles93/archie-core/internal/infrastructure/access"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/configuration"
|
||||
infraembedding "github.com/samcharles93/archie-core/internal/infrastructure/embedding"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/eventbus/nats"
|
||||
@@ -124,6 +126,11 @@ type boot struct {
|
||||
// set. The b.st field remains solely for the standalone archie-state-store
|
||||
// binary, which serves the task store from Postgres.
|
||||
stateStore storecontract.TaskStore
|
||||
// accessChain is the daemon's policy engine, built once from the stored
|
||||
// policies (openAccessChain); accessProblems is what the readiness
|
||||
// surface reports. Both are nil when no policy store is wired.
|
||||
accessChain access.Authorizer
|
||||
accessProblems []infraaccess.Problem
|
||||
// stateStoreGrants issues per-task, scoped State Store credentials for
|
||||
// agent containers (daemon.StateStoreGrantIssuer), wrapping the same
|
||||
// *staterpc.Client as stateStore. Nil when the State Store adapter isn't
|
||||
@@ -213,7 +220,16 @@ type boot struct {
|
||||
kitLauncher daemon.KitLauncher
|
||||
storeBackend storage.Backend
|
||||
|
||||
llm *runtime.Runtime
|
||||
// llm is the chat runtime's provider runtime, held in a pointer the chat
|
||||
// surfaces read through chatLLM at each use. A live provider-settings or
|
||||
// model-role-assignments update swaps it wholesale: ai-sdk's Runtime
|
||||
// caches the provider instances it built, so a changed provider set needs
|
||||
// a new Runtime rather than a mutated one.
|
||||
llm atomic.Pointer[runtime.Runtime]
|
||||
// runtimeVersions records the version of every control-plane kind boot's
|
||||
// layering applied. Set once at boot before the runtime-resource watches
|
||||
// start, which read it as their resume points.
|
||||
runtimeVersions map[string]int64
|
||||
|
||||
// embeddings is nil unless models["embedding"] and a working provider
|
||||
// credential are both configured -- see setupLLMAndChat's "Embeddings
|
||||
@@ -222,15 +238,11 @@ type boot struct {
|
||||
// unrelated call.
|
||||
embeddings domainembedding.Client
|
||||
|
||||
toolReg *tools.Registry
|
||||
chatModels gateway.ModelManager
|
||||
personas *gateway.PersonaRegistry
|
||||
chatTasks gateway.TaskCreator
|
||||
chatController *gateway.StoreTaskController
|
||||
// chatPRReviewer is the operator-triggered PR review capability, built
|
||||
// once and shared by every channel so a review in flight on one channel
|
||||
// is deduplicated against the same request on another (single-flight).
|
||||
chatPRReviewer gateway.ChatPRReviewer
|
||||
toolReg *tools.Registry
|
||||
chatModels *chatModelManager
|
||||
personas *gateway.PersonaRegistry
|
||||
chatTasks gateway.TaskCreator
|
||||
chatController *gateway.StoreTaskController
|
||||
defaultChatIdentity string
|
||||
updateService *releaseupdate.Service
|
||||
|
||||
@@ -279,6 +291,16 @@ func newBootstrap() *boot {
|
||||
return &boot{log: slog.New(slog.NewJSONHandler(os.Stderr, nil)), agentStatus: &daemon.AgentStatus{}}
|
||||
}
|
||||
|
||||
// chatLLM is the provider runtime the chat surfaces read at each use: a turn
|
||||
// resolves it when it starts, so a runtime swapped by a live model-settings
|
||||
// update is the one the turn after it runs on.
|
||||
func (b *boot) chatLLM() *runtime.Runtime { return b.llm.Load() }
|
||||
|
||||
// setLLM replaces the chat runtime. A nil runtime is a legal state: a
|
||||
// deployment whose every provider credential was disabled by a live update
|
||||
// leaves chat turns refused until another update restores one.
|
||||
func (b *boot) setLLM(rt *runtime.Runtime) { b.llm.Store(rt) }
|
||||
|
||||
func (b *boot) addCleanup(fn func()) {
|
||||
b.cleanups = append(b.cleanups, fn)
|
||||
}
|
||||
@@ -416,6 +438,47 @@ func (b *boot) openStateStoreAdapter() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// openStateStage opens the state-store adapter and its daemon-side surfaces
|
||||
// plus the policy chain, in one step of the composition sequence: the three
|
||||
// are ordered but not interleaved, and any failure fails the boot
|
||||
// (openStateStoreAdapter, openDaemonStateSurfaces, openAccessChain).
|
||||
func (b *boot) openStateStage(ctx context.Context) error {
|
||||
if err := b.openStores(ctx); err != nil {
|
||||
return err
|
||||
}
|
||||
if err := b.openDaemonStateSurfaces(); err != nil {
|
||||
return err
|
||||
}
|
||||
return b.openAccessChain(ctx)
|
||||
}
|
||||
|
||||
// openAccessChain builds the policy chain the daemon dispatches through
|
||||
// (docs/prds/orgs-and-access.md, "Where it lives"): the stored policies over
|
||||
// the wire, compiled once at boot. An invalid instance policy fails the boot;
|
||||
// an invalid org, workspace or object policy is retained as a health problem
|
||||
// and its level denies everything.
|
||||
func (b *boot) openAccessChain(ctx context.Context) error {
|
||||
source, ok := b.stateStore.(access.PolicySource)
|
||||
if !ok {
|
||||
return nil // no policy store wired: the chain is not built
|
||||
}
|
||||
stored, err := source.Policies(ctx)
|
||||
if err != nil {
|
||||
return fmt.Errorf("load stored policies: %w", err)
|
||||
}
|
||||
engine, err := infraaccess.New(stored)
|
||||
if err != nil {
|
||||
return fmt.Errorf("validate stored policies: %w", err)
|
||||
}
|
||||
b.accessChain = engine
|
||||
b.accessProblems = engine.Problems()
|
||||
for _, problem := range b.accessProblems {
|
||||
b.log.Error("stored access policy is invalid and denies its level",
|
||||
"policy", problem.Policy.ID, "level", problem.Policy.Level, "err", problem.Err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// openChatSessions opens the conversation store on its own pool from
|
||||
// database_url. The daemon reads it (session curator) and the Gateway serves
|
||||
// it; only the Gateway claims serve ownership (claimGatewayOwnership).
|
||||
@@ -863,10 +926,10 @@ func (b *boot) loadPlugins() error {
|
||||
|
||||
// buildWorktreeManager composes the process-wide worktree manager from the
|
||||
// resolved primary forge credential and the loaded config. Both process roots
|
||||
// own one: the daemon works tasks in it, and the Gateway materialises a pull
|
||||
// request head in it when an operator asks for a review (boot.prReviewer
|
||||
// refuses to build a reviewer without one, so a Gateway that skips this step
|
||||
// advertises no review_pr). It reads only, so it has nothing to report.
|
||||
// own one: the daemon works tasks in it, and the Gateway used it to
|
||||
// materialise a pull request head for the now-removed synchronous
|
||||
// operator-review path (archie-core-afbk.7). It reads only, so it has
|
||||
// nothing to report.
|
||||
//
|
||||
// Identity managers are not built here: buildTreesAndIdentities builds one per
|
||||
// identity, each in its own WorkDir, because the Gateway must not own daemon
|
||||
@@ -1087,7 +1150,7 @@ func (b *boot) setupCurators(ctx context.Context) {
|
||||
// (TurnRunnerConfig.BotUser), so a fact written here is a fact a later
|
||||
// turn reaches.
|
||||
Conversations: sessioncurator.NewAdapter(b.chatSessionStore, b.cfg.BotUser),
|
||||
LLM: curatorLLMRunner{rt: b.llm, outcomes: b.providerOutcomes},
|
||||
LLM: curatorLLMRunner{llm: b.chatLLM, outcomes: b.providerOutcomes},
|
||||
// b.chatModels.ActiveModel() is the same source sendChatTurn uses
|
||||
// for a real chat turn (telegram_setup.go) -- not
|
||||
// b.defaultChatIdentity, which names a task-routing identity, not
|
||||
@@ -1345,6 +1408,7 @@ func (b *boot) buildDaemon() {
|
||||
KindWorkflows: b.kindWorkflows,
|
||||
LabelWorkflows: b.labelWorkflows,
|
||||
WorkflowDefinitions: b.workflowDefinitions,
|
||||
WorkflowEnablement: b.controlPlane,
|
||||
Playbooks: b.playbooks,
|
||||
}
|
||||
if identities, ok := b.stateStore.(identity.Repository); ok {
|
||||
@@ -1368,6 +1432,18 @@ func (b *boot) buildDaemon() {
|
||||
if btc, ok := b.stateStore.(storecontract.BindingTaskCreator); ok {
|
||||
b.d.BindingTaskCreator = btc
|
||||
}
|
||||
// Dispatch is the second Authorizer call site: the chain built by
|
||||
// openAccessChain, the principal assembly over the wire, and the denial
|
||||
// record -- wired together or not at all (docs/prds/orgs-and-access.md).
|
||||
b.d.Access = b.accessChain
|
||||
if b.accessChain != nil {
|
||||
if principals, ok := b.stateStore.(access.PrincipalSource); ok {
|
||||
b.d.Principals = principals
|
||||
}
|
||||
if denials, ok := b.stateStore.(access.DenialStore); ok {
|
||||
b.d.Denials = denials
|
||||
}
|
||||
}
|
||||
b.d.PlaybookLedger = playbookLedger(b.stateStore, b.playbooks, b.log)
|
||||
b.setupForgeWebhook()
|
||||
}
|
||||
|
||||
@@ -15,14 +15,29 @@ import (
|
||||
// The configured role-to-model map supplies the available catalog; switching
|
||||
// chat models does not rewrite daemon configuration or affect workflow roles.
|
||||
type chatModelManager struct {
|
||||
mu sync.RWMutex
|
||||
models []string
|
||||
active string
|
||||
mu sync.RWMutex
|
||||
models []string
|
||||
active string
|
||||
// catalogs are the non-role sources the model set is derived from, kept
|
||||
// so SetConfigured can rebuild it after a live settings update without a
|
||||
// caller re-passing them.
|
||||
catalogs [][]string
|
||||
details map[string]gateway.ModelDetails
|
||||
providerNames map[string]string
|
||||
}
|
||||
|
||||
func newChatModelManager(configured map[string]string, catalogs ...[]string) *chatModelManager {
|
||||
// pickChatDefault is the model the manager starts on: the chat role's
|
||||
// assignment, falling back to the builder role's.
|
||||
func pickChatDefault(configured map[string]string) string {
|
||||
if active := strings.TrimSpace(configured["chat"]); active != "" {
|
||||
return active
|
||||
}
|
||||
return strings.TrimSpace(configured["builder"])
|
||||
}
|
||||
|
||||
// mergeModelRefs is the model set the manager offers: the configured role
|
||||
// assignments plus every catalog, unique and sorted.
|
||||
func mergeModelRefs(configured map[string]string, catalogs ...[]string) []string {
|
||||
unique := make(map[string]struct{}, len(configured))
|
||||
for _, ref := range configured {
|
||||
ref = strings.TrimSpace(ref)
|
||||
@@ -44,18 +59,35 @@ func newChatModelManager(configured map[string]string, catalogs ...[]string) *ch
|
||||
models = append(models, ref)
|
||||
}
|
||||
slices.Sort(models)
|
||||
return models
|
||||
}
|
||||
|
||||
active := strings.TrimSpace(configured["chat"])
|
||||
if active == "" {
|
||||
active = strings.TrimSpace(configured["builder"])
|
||||
}
|
||||
func newChatModelManager(configured map[string]string, catalogs ...[]string) *chatModelManager {
|
||||
return &chatModelManager{
|
||||
models: models, active: active,
|
||||
models: mergeModelRefs(configured, catalogs...),
|
||||
active: pickChatDefault(configured),
|
||||
catalogs: append([][]string(nil), catalogs...),
|
||||
details: make(map[string]gateway.ModelDetails),
|
||||
providerNames: make(map[string]string),
|
||||
}
|
||||
}
|
||||
|
||||
// SetConfigured re-derives the model set the manager offers after a live
|
||||
// change to model-role-assignments or provider-settings: the list is built
|
||||
// from the configured roles at construction, so a stored change would leave
|
||||
// the chat surfaces offering refs the runtime can no longer resolve. The
|
||||
// operator's active selection survives when the new roles still carry it; a
|
||||
// removed one falls back the way construction does.
|
||||
func (m *chatModelManager) SetConfigured(configured map[string]string) {
|
||||
m.mu.Lock()
|
||||
defer m.mu.Unlock()
|
||||
models := mergeModelRefs(configured, m.catalogs...)
|
||||
if !slices.Contains(models, m.active) {
|
||||
m.active = pickChatDefault(configured)
|
||||
}
|
||||
m.models = models
|
||||
}
|
||||
|
||||
func (m *chatModelManager) ApplyModelCatalog(snapshot modelcatalog.Snapshot) {
|
||||
m.mu.Lock()
|
||||
defer m.mu.Unlock()
|
||||
|
||||
@@ -28,8 +28,12 @@ type chatSetup struct {
|
||||
// Cfg is read once per setup function via Get(); the process is not
|
||||
// running yet at this point, so the reload-safe Holder is mostly a
|
||||
// formality, but matching the daemon's API keeps callers honest.
|
||||
Cfg *config.Holder
|
||||
LLM *runtime.Runtime
|
||||
Cfg *config.Holder
|
||||
// LLM resolves the provider runtime at each use: a live provider-settings
|
||||
// or model-role-assignments update swaps the runtime wholesale (ai-sdk's
|
||||
// Runtime caches the provider instances it built), so the pointer cannot
|
||||
// be captured at construction. nil means no model runtime is configured.
|
||||
LLM func() *runtime.Runtime
|
||||
ChatModels gateway.ModelManager
|
||||
ToolReg *tools.Registry
|
||||
Personas *gateway.PersonaRegistry
|
||||
@@ -37,7 +41,6 @@ type chatSetup struct {
|
||||
ChatTaskLister gateway.ChatTaskLister
|
||||
ChatTaskLogs gateway.ChatTaskLogReader
|
||||
ChatTaskActor gateway.ChatTaskActor
|
||||
ChatPRReviewer gateway.ChatPRReviewer
|
||||
DefaultChatIdentity string
|
||||
// Bus carries primary-input events (archie-core-035): a completed
|
||||
// chat turn is published here so input-driven curators can wake. Nil
|
||||
@@ -152,7 +155,7 @@ func makeChatLLMResponder(
|
||||
sessionStore gateway.SessionStore,
|
||||
router *gateway.Router,
|
||||
) (gateway.LLMResponder, gateway.LLMStreamResponder) {
|
||||
if s.LLM == nil {
|
||||
if s.LLM == nil || s.LLM() == nil {
|
||||
return nil, nil
|
||||
}
|
||||
runner := newChatTurnRunner(ctx, channel, s, sessionStore, router)
|
||||
@@ -178,7 +181,6 @@ func newChatTurnRunner(
|
||||
TaskLogs: s.ChatTaskLogs,
|
||||
TaskActor: s.ChatTaskActor,
|
||||
TaskIdentity: s.DefaultChatIdentity,
|
||||
PRReviewer: s.ChatPRReviewer,
|
||||
Bus: s.Bus,
|
||||
BotUser: cfg.BotUser,
|
||||
Channel: channel,
|
||||
@@ -365,7 +367,7 @@ func multimodalMediaRefs(output string) []tools.MediaRef {
|
||||
// untitled and are logged here.
|
||||
type chatTitleGenerator struct {
|
||||
log *slog.Logger
|
||||
llm *runtime.Runtime
|
||||
llm func() *runtime.Runtime
|
||||
chatModels gateway.ModelManager
|
||||
}
|
||||
|
||||
@@ -395,7 +397,11 @@ func (g *chatTitleGenerator) GenerateTitle(ctx context.Context, sessionID, first
|
||||
// broken provider on the strength of a call no user was waiting for.
|
||||
// No tool set and no stream, so no tool call can be reported: this turn
|
||||
// needs no icons.
|
||||
text, err := sendChatTurn(ctx, g.llm, g.chatModels.ActiveModel(),
|
||||
llm := g.llm()
|
||||
if llm == nil {
|
||||
return "", fmt.Errorf("no model runtime is configured")
|
||||
}
|
||||
text, err := sendChatTurn(ctx, llm, g.chatModels.ActiveModel(),
|
||||
core.GenerateOptions{Messages: messages, MaxSteps: 1}, nil, nil, nil)
|
||||
if err != nil {
|
||||
if g.log != nil {
|
||||
|
||||
@@ -3,6 +3,7 @@ package archied
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"fmt"
|
||||
|
||||
"github.com/samcharles93/ai-sdk/chat"
|
||||
"github.com/samcharles93/ai-sdk/core"
|
||||
@@ -17,7 +18,9 @@ import (
|
||||
// provider-neutral TurnModel seam. Tool construction remains here because it
|
||||
// depends on runtime registries and configured execution limits.
|
||||
type chatTurnModel struct {
|
||||
llm *runtime.Runtime
|
||||
// llm resolves the provider runtime at each turn, so a runtime swapped by
|
||||
// a live model-settings update is the one the turn after it runs on.
|
||||
llm func() *runtime.Runtime
|
||||
registry *tools.Registry
|
||||
maxSteps int
|
||||
limits agentexec.ToolLimits
|
||||
@@ -26,7 +29,7 @@ type chatTurnModel struct {
|
||||
}
|
||||
|
||||
func newChatTurnModel(
|
||||
llm *runtime.Runtime,
|
||||
llm func() *runtime.Runtime,
|
||||
registry *tools.Registry,
|
||||
maxSteps int,
|
||||
limits agentexec.ToolLimits,
|
||||
@@ -54,7 +57,7 @@ func (m *chatTurnModel) Prepare(
|
||||
return nil, err
|
||||
}
|
||||
return &preparedChatTurnModel{
|
||||
llm: m.llm,
|
||||
llm: m.llm(),
|
||||
model: req.Model,
|
||||
options: options,
|
||||
toolInfo: toolSummaries(options.Tools),
|
||||
@@ -97,6 +100,80 @@ func (m *preparedChatTurnModel) ToolSummaries() []gateway.ToolSummary {
|
||||
return append([]gateway.ToolSummary(nil), m.toolInfo...)
|
||||
}
|
||||
|
||||
// buildTurnMessages maps the gateway's compressed history onto ai-sdk chat
|
||||
// messages. The turn's inbound media is not part of stored history, so it
|
||||
// is merged here into the final user message as content parts: the model
|
||||
// sees the caption text plus each attachment's bytes (or URL), exactly for
|
||||
// the turn it arrived in.
|
||||
func buildTurnMessages(request gateway.TurnModelRequest) []chat.Message {
|
||||
messages := make([]chat.Message, len(request.Messages))
|
||||
for i, message := range request.Messages {
|
||||
role := chat.RoleUser
|
||||
switch message.Role {
|
||||
case "assistant":
|
||||
role = chat.RoleAssistant
|
||||
case "system":
|
||||
role = chat.RoleSystem
|
||||
}
|
||||
messages[i] = chat.Message{Role: role, Content: message.Content}
|
||||
}
|
||||
parts := mediaParts(request.Media)
|
||||
if len(parts) == 0 {
|
||||
return messages
|
||||
}
|
||||
last := len(messages) - 1
|
||||
// The media belongs to the inbound message, which is always the final
|
||||
// user entry; if the view ever ends differently, content stays intact
|
||||
// over silently attaching parts to an unrelated message.
|
||||
if last < 0 || messages[last].Role != chat.RoleUser {
|
||||
return messages
|
||||
}
|
||||
userMessages := messages[last]
|
||||
userMessages.Parts = append(chat.Parts{chat.TextPart{Text: userMessages.Content}}, parts...)
|
||||
userMessages.Content = ""
|
||||
messages[last] = userMessages
|
||||
return messages
|
||||
}
|
||||
|
||||
// mediaParts converts inbound media attachments into ai-sdk content
|
||||
// parts: images get ImagePart, everything else FilePart. An attachment
|
||||
// carrying neither bytes nor a URL names nothing consumable and is
|
||||
// dropped -- the turn's text still reaches the model.
|
||||
func mediaParts(media []gateway.MediaAttachment) []chat.Part {
|
||||
if len(media) == 0 {
|
||||
return nil
|
||||
}
|
||||
parts := make([]chat.Part, 0, len(media))
|
||||
for _, att := range media {
|
||||
if att.Type == "image" {
|
||||
switch {
|
||||
case len(att.Data) > 0 && att.MIMEType != "":
|
||||
parts = append(parts, chat.ImagePart{Data: att.Data, MediaType: att.MIMEType})
|
||||
case att.URL != "":
|
||||
parts = append(parts, chat.ImagePart{URL: att.URL})
|
||||
}
|
||||
continue
|
||||
}
|
||||
part := chat.FilePart{Name: att.FileName, MediaType: att.MIMEType}
|
||||
if len(att.Data) > 0 {
|
||||
part.Data = att.Data
|
||||
} else {
|
||||
part.URL = att.URL
|
||||
}
|
||||
if len(part.Data) == 0 && part.URL == "" {
|
||||
continue
|
||||
}
|
||||
if part.MediaType == "" {
|
||||
part.MediaType = "application/octet-stream"
|
||||
}
|
||||
parts = append(parts, part)
|
||||
}
|
||||
if len(parts) == 0 {
|
||||
return nil
|
||||
}
|
||||
return parts
|
||||
}
|
||||
|
||||
func (m *preparedChatTurnModel) ToolSchemaTokens() int {
|
||||
return m.toolTokens
|
||||
}
|
||||
@@ -107,19 +184,14 @@ func (m *preparedChatTurnModel) Generate(
|
||||
stream gateway.TurnStream,
|
||||
) (string, error) {
|
||||
options := m.options
|
||||
options.Messages = make([]chat.Message, len(request.Messages))
|
||||
for i, message := range request.Messages {
|
||||
role := chat.RoleUser
|
||||
switch message.Role {
|
||||
case "assistant":
|
||||
role = chat.RoleAssistant
|
||||
case "system":
|
||||
role = chat.RoleSystem
|
||||
}
|
||||
options.Messages[i] = chat.Message{Role: role, Content: message.Content}
|
||||
}
|
||||
options.Messages = buildTurnMessages(request)
|
||||
// This is one provider response's output allowance, not a turn-
|
||||
// continuation budget. Tool loops remain free to continue.
|
||||
options.MaxTokens = request.MaxOutputTokens
|
||||
// A runtime swapped to nil -- a live update that left no usable provider
|
||||
// configured -- is a refused turn, not a panic.
|
||||
if m.llm == nil {
|
||||
return "", fmt.Errorf("llm chat: no model runtime is configured")
|
||||
}
|
||||
return sendChatTurn(ctx, m.llm, m.model, options, stream, m.outcomes, m.icons)
|
||||
}
|
||||
@@ -0,0 +1,116 @@
|
||||
package archied
|
||||
|
||||
import (
|
||||
"testing"
|
||||
|
||||
"github.com/samcharles93/ai-sdk/chat"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/gateway"
|
||||
)
|
||||
|
||||
// TestBuildTurnMessagesAttachesMediaPartsToTheFinalUserMessage: inbound
|
||||
// media only reaches the model when the turn's request is turned into
|
||||
// message parts; the attachment belongs on the message the user just sent.
|
||||
func TestBuildTurnMessagesAttachesMediaPartsToTheFinalUserMessage(t *testing.T) {
|
||||
request := gateway.TurnModelRequest{
|
||||
Messages: []gateway.CompressedMessage{
|
||||
{Role: "system", Content: "sys"},
|
||||
{Role: "user", Content: "what is this?"},
|
||||
},
|
||||
Media: []gateway.MediaAttachment{
|
||||
{Type: "image", MIMEType: "image/png", Data: []byte("png-bytes")},
|
||||
{Type: "image", URL: "https://example.invalid/pic.jpg"},
|
||||
{Type: "document", MIMEType: "application/pdf", FileName: "report.pdf", Data: []byte("pdf-bytes")},
|
||||
},
|
||||
}
|
||||
|
||||
messages := buildTurnMessages(request)
|
||||
if len(messages) != 2 {
|
||||
t.Fatalf("messages = %d, want 2", len(messages))
|
||||
}
|
||||
if messages[0].Content != "sys" || len(messages[0].Parts) != 0 {
|
||||
t.Errorf("system message = %#v, want plain content and no parts", messages[0])
|
||||
}
|
||||
if messages[1].Content != "" {
|
||||
t.Errorf("user content = %q, want it moved into a text part", messages[1].Content)
|
||||
}
|
||||
parts := messages[1].Parts
|
||||
if len(parts) != 4 {
|
||||
t.Fatalf("user parts = %d, want text plus three media parts: %#v", len(parts), parts)
|
||||
}
|
||||
if text, ok := parts[0].(chat.TextPart); !ok || text.Text != "what is this?" {
|
||||
t.Errorf("part 0 = %#v, want the caption text", parts[0])
|
||||
}
|
||||
image, ok := parts[1].(chat.ImagePart)
|
||||
if !ok || string(image.Data) != "png-bytes" || image.MediaType != "image/png" {
|
||||
t.Errorf("part 1 = %#v, want an image part carrying the png bytes", parts[1])
|
||||
}
|
||||
linked, ok := parts[2].(chat.ImagePart)
|
||||
if !ok || linked.URL != "https://example.invalid/pic.jpg" {
|
||||
t.Errorf("part 2 = %#v, want an image part pointing at the URL", parts[2])
|
||||
}
|
||||
file, ok := parts[3].(chat.FilePart)
|
||||
if !ok {
|
||||
t.Fatalf("part 3 = %#v, want a file part", parts[3])
|
||||
}
|
||||
if string(file.Data) != "pdf-bytes" || file.MediaType != "application/pdf" || file.Name != "report.pdf" {
|
||||
t.Errorf("file part = %#v, want the pdf bytes with type and name", file)
|
||||
}
|
||||
}
|
||||
|
||||
// TestBuildTurnMessagesSkipsUndeliverableMedia: an attachment carrying
|
||||
// neither bytes nor a URL names nothing the model can consume, so it must
|
||||
// be dropped rather than sent as an empty part.
|
||||
func TestBuildTurnMessagesSkipsUndeliverableMedia(t *testing.T) {
|
||||
request := gateway.TurnModelRequest{
|
||||
Messages: []gateway.CompressedMessage{
|
||||
{Role: "user", Content: "look"},
|
||||
},
|
||||
Media: []gateway.MediaAttachment{
|
||||
{Type: "video"},
|
||||
{Type: "image", MIMEType: "image/png", Data: []byte("png")},
|
||||
},
|
||||
}
|
||||
messages := buildTurnMessages(request)
|
||||
fileSeen := false
|
||||
for _, p := range messages[0].Parts {
|
||||
if _, ok := p.(chat.FilePart); ok {
|
||||
fileSeen = true
|
||||
}
|
||||
}
|
||||
if fileSeen {
|
||||
t.Errorf("parts = %#v, want the empty attachment dropped", messages[0].Parts)
|
||||
}
|
||||
if len(messages[0].Parts) != 2 {
|
||||
t.Fatalf("user parts = %d, want text plus the one deliverable image", len(messages[0].Parts))
|
||||
}
|
||||
if text, ok := messages[0].Parts[0].(chat.TextPart); !ok || text.Text != "look" {
|
||||
t.Errorf("part 0 = %#v, want the text part", messages[0].Parts[0])
|
||||
}
|
||||
}
|
||||
|
||||
// TestBuildTurnMessagesWithoutMediaKeepsPlainContent is the regression
|
||||
// guard for the overwhelmingly common case: text-only turns stay exactly as
|
||||
// they were, with Content and no parts.
|
||||
func TestBuildTurnMessagesWithoutMediaKeepsPlainContent(t *testing.T) {
|
||||
request := gateway.TurnModelRequest{
|
||||
Messages: []gateway.CompressedMessage{
|
||||
{Role: "system", Content: "sys"},
|
||||
{Role: "user", Content: "plain"},
|
||||
{Role: "assistant", Content: "reply"},
|
||||
},
|
||||
}
|
||||
messages := buildTurnMessages(request)
|
||||
for i, want := range []struct {
|
||||
role chat.Role
|
||||
content string
|
||||
}{
|
||||
{chat.RoleSystem, "sys"},
|
||||
{chat.RoleUser, "plain"},
|
||||
{chat.RoleAssistant, "reply"},
|
||||
} {
|
||||
if messages[i].Content != want.content || messages[i].Parts != nil {
|
||||
t.Errorf("message %d = %#v, want content %q and no parts", i, messages[i], want.content)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -32,29 +32,3 @@ func TestStartGatewayRuntimeSetsUpMemoryBeforeGatewayChat(t *testing.T) {
|
||||
t.Fatal("startGatewayRuntime wires setupGatewayChat before setupMemoryEngine; the turn runner would capture a nil memory engine")
|
||||
}
|
||||
}
|
||||
|
||||
// TestStartGatewayRuntimeBuildsWorktreeManagerBeforeGatewayChat pins the
|
||||
// Gateway's own worktree-manager ordering. The Gateway owns PR review, so
|
||||
// startGatewayRuntime must compose the process-wide worktree manager before
|
||||
// setupGatewayChat resolves boot.prReviewer: prReviewer returns nil without a
|
||||
// manager, and a nil reviewer omits review_pr from every channel's tool set
|
||||
// (internal/gateway/review_tools.go). The Gateway deliberately does not call
|
||||
// buildTreesAndIdentities -- that also registers daemon identity runners it
|
||||
// must not own -- so nothing at runtime connects the manager to this
|
||||
// composition phase except the call this asserts on.
|
||||
func TestStartGatewayRuntimeBuildsWorktreeManagerBeforeGatewayChat(t *testing.T) {
|
||||
fileset := token.NewFileSet()
|
||||
file, err := parser.ParseFile(fileset, "gateway.go", nil, 0)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
run := methodBody(t, file, "startGatewayRuntime")
|
||||
trees := methodCallPosition(run, "buildWorktreeManager")
|
||||
chat := methodCallPosition(run, "setupGatewayChat")
|
||||
if trees == token.NoPos || chat == token.NoPos {
|
||||
t.Fatalf("startGatewayRuntime call positions: buildWorktreeManager=%v setupGatewayChat=%v, want both present", trees, chat)
|
||||
}
|
||||
if chat < trees {
|
||||
t.Fatal("startGatewayRuntime wires setupGatewayChat before buildWorktreeManager; the Gateway would resolve a nil reviewer and never advertise review_pr")
|
||||
}
|
||||
}
|
||||
@@ -5,8 +5,10 @@ import (
|
||||
"encoding/json"
|
||||
"log/slog"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/config"
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/configuration"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/postgres/pgstore"
|
||||
"github.com/samcharles93/archie-core/internal/webui"
|
||||
@@ -136,3 +138,30 @@ func TestPublishConfigSnapshotWithoutConfiguration(t *testing.T) {
|
||||
t.Fatalf("ConfigSnapshot = (found %v, %v), want nothing published", found, err)
|
||||
}
|
||||
}
|
||||
|
||||
// TestLiveSettingsApplyRepublishesTheConfigSnapshot: the dashboard renders the
|
||||
// published projection, not the daemon's Holder, so a live apply that changes
|
||||
// the running config must republish it or the page keeps showing the old
|
||||
// values until the next reload.
|
||||
func TestLiveSettingsApplyRepublishesTheConfigSnapshot(t *testing.T) {
|
||||
st := pgstore.Open(t)
|
||||
t.Cleanup(func() { _ = st.Close() })
|
||||
|
||||
b, _ := newLiveApplyBoot(t, fileConfig())
|
||||
b.stateStore = st
|
||||
if err := b.applyWorkflowExecutionSettings(t.Context(), workflow.ExecutionSettings{MaxModelToolSteps: 25, MaxRuntime: time.Hour, MaxConsecutiveGateFailures: 4}, 2); err != nil {
|
||||
t.Fatalf("live update: %v", err)
|
||||
}
|
||||
|
||||
snapshot, found, err := st.ConfigSnapshot(context.Background())
|
||||
if err != nil || !found {
|
||||
t.Fatalf("ConfigSnapshot = (found %v, %v), want the live apply to publish one", found, err)
|
||||
}
|
||||
var view webui.ConfigView
|
||||
if err := json.Unmarshal(snapshot.Document, &view); err != nil {
|
||||
t.Fatalf("decode published document: %v", err)
|
||||
}
|
||||
if view.Budgets.MaxSteps != 25 || view.Budgets.GateMaxFailures != 4 {
|
||||
t.Errorf("published budgets = %+v, want the live-applied limits", view.Budgets)
|
||||
}
|
||||
}
|
||||
@@ -5,6 +5,7 @@ import (
|
||||
"fmt"
|
||||
"time"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/agentexec"
|
||||
"github.com/samcharles93/archie-core/internal/app/controlplane"
|
||||
"github.com/samcharles93/archie-core/internal/config"
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow"
|
||||
@@ -16,10 +17,10 @@ import (
|
||||
// reload re-resolves the file document alone, so republishing that document
|
||||
// as it stands reverts each of these layers to its file value until the
|
||||
// process restarts (archie-core-ju85).
|
||||
func (b *boot) runtimeConfig(ctx context.Context, base config.Config) (config.Config, error) {
|
||||
func (b *boot) runtimeConfig(ctx context.Context, base config.Config) (config.Config, map[string]int64, error) {
|
||||
cfg, versions, err := b.controlPlane.RuntimeConfig(ctx, base)
|
||||
if err != nil {
|
||||
return config.Config{}, err
|
||||
return config.Config{}, nil, err
|
||||
}
|
||||
if settings := b.executionSettings.Load(); settings != nil {
|
||||
applyExecutionBudgets(&cfg, *settings)
|
||||
@@ -27,17 +28,17 @@ func (b *boot) runtimeConfig(ctx context.Context, base config.Config) (config.Co
|
||||
if err := configuration.Validate(&cfg); err != nil {
|
||||
wrapped := fmt.Errorf("validate database settings: %w", err)
|
||||
b.reportApplied(ctx, versions, wrapped)
|
||||
return config.Config{}, wrapped
|
||||
return config.Config{}, nil, wrapped
|
||||
}
|
||||
// The State Store persists source references, while openStores resolved
|
||||
// only the file snapshot. Layering provider-settings restores the source
|
||||
// references, so resolve the effective map before any runtime consumes it.
|
||||
if err := resolveProviderSecrets(&cfg, b.secrets, b.log); err != nil {
|
||||
b.reportApplied(ctx, versions, err)
|
||||
return config.Config{}, err
|
||||
return config.Config{}, nil, err
|
||||
}
|
||||
b.reportApplied(ctx, versions, nil)
|
||||
return cfg, nil
|
||||
return cfg, versions, nil
|
||||
}
|
||||
|
||||
// reportApplied publishes the version of each kind this process just layered
|
||||
@@ -50,12 +51,17 @@ func (b *boot) reportApplied(ctx context.Context, versions map[string]int64, app
|
||||
}
|
||||
|
||||
func (b *boot) loadRuntimeConfig(ctx context.Context) error {
|
||||
cfg, err := b.runtimeConfig(ctx, b.cfg)
|
||||
cfg, versions, err := b.runtimeConfig(ctx, b.cfg)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
b.cfg = cfg
|
||||
b.cfgHolder.Set(cfg)
|
||||
// The versions boot layered in are the resume points the runtime-resource
|
||||
// watches start from: a watch re-established after a version it already
|
||||
// applied neither replays a document this process handled nor skips one
|
||||
// it has not.
|
||||
b.runtimeVersions = versions
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -75,7 +81,7 @@ func (b *boot) reloadConfig(ctx context.Context, doc *configuration.Document) er
|
||||
// surface as a failed reload rather than a SIGHUP that never returns.
|
||||
queryCtx, cancel := context.WithTimeout(ctx, 10*time.Second)
|
||||
defer cancel()
|
||||
cfg, err := b.runtimeConfig(queryCtx, doc.Config)
|
||||
cfg, _, err := b.runtimeConfig(queryCtx, doc.Config)
|
||||
if err != nil {
|
||||
return fmt.Errorf("runtime settings unavailable: %w", err)
|
||||
}
|
||||
@@ -109,41 +115,45 @@ func (b *boot) startWorkflowExecutionSettings(ctx context.Context) error {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
var lastApplyErr, streamErr error
|
||||
open := func(ctx context.Context, after int64) (<-chan controlplane.AppliedSettings, error) {
|
||||
updates, err := b.controlPlane.WatchWorkflowExecutionSettings(ctx, after)
|
||||
if err == nil {
|
||||
b.applyStatus.Report(ctx, controlplane.WorkflowExecutionSettingsKind, after, lastApplyErr)
|
||||
}
|
||||
return updates, err
|
||||
}
|
||||
go keepWatch(ctx, b.log, controlplane.WorkflowExecutionSettingsKind, version, updates,
|
||||
b.controlPlane.WatchWorkflowExecutionSettings,
|
||||
open,
|
||||
waitFor,
|
||||
func(update controlplane.AppliedSettings) int64 { return update.Version },
|
||||
func(update controlplane.AppliedSettings) {
|
||||
if update.Err != nil {
|
||||
// A refused update arrives here, not through
|
||||
// applyWorkflowExecutionSettings: controlplane.Client decodes every
|
||||
// document it is handed, so a stored value this process cannot run
|
||||
// never reaches the apply call. Report it against the version it
|
||||
// came from -- the reporter keeps the version it last applied --
|
||||
// so the settings page shows the refusal instead of a version this
|
||||
// process never ran (docs/prds/control-plane-apply-status.md).
|
||||
//
|
||||
// A stream failure arrives the same way and must not be reported:
|
||||
// it carries no version at all, because a Recv error is the store
|
||||
// not answering rather than a document, and versions start at 1
|
||||
// (store.PutResource). The rule is
|
||||
// docs/prds/control-plane-apply-status.md, "What can be reported,
|
||||
// and what cannot": a process reaches its apply point only after
|
||||
// the State Store has answered it, and an unreachable store is
|
||||
// never reported as a failure by the process it affected. The
|
||||
// record would not stick of itself -- Report overwrites it on the
|
||||
// next applied version -- but a store that never changes again
|
||||
// leaves the one stamp standing, and the process must not write it
|
||||
// at all. Reporting it would also overwrite the text of a standing
|
||||
// refusal, which is the one message that says what to fix. The
|
||||
// reconnect is the loop's business, not the record's.
|
||||
// A refused document carries its version, while a stream failure
|
||||
// does not. Keep a refusal visible across a transport outage; when
|
||||
// there is no outstanding refusal, the end callback records the
|
||||
// outage until a watch is re-established.
|
||||
if update.Version > 0 {
|
||||
lastApplyErr = update.Err
|
||||
b.applyStatus.Report(ctx, controlplane.WorkflowExecutionSettingsKind, update.Version, update.Err)
|
||||
} else {
|
||||
streamErr = update.Err
|
||||
}
|
||||
b.log.Error("workflow execution settings watch failed", "err", update.Err)
|
||||
return
|
||||
}
|
||||
_ = b.applyWorkflowExecutionSettings(ctx, update.Settings, update.Version)
|
||||
lastApplyErr = b.applyWorkflowExecutionSettings(ctx, update.Settings, update.Version)
|
||||
},
|
||||
func() {
|
||||
if lastApplyErr != nil {
|
||||
return
|
||||
}
|
||||
if streamErr == nil {
|
||||
streamErr = fmt.Errorf("control-plane watch stream ended")
|
||||
}
|
||||
b.applyStatus.Report(ctx, controlplane.WorkflowExecutionSettingsKind, 0,
|
||||
fmt.Errorf("workflow execution settings watch unavailable: %w", streamErr))
|
||||
streamErr = nil
|
||||
})
|
||||
return nil
|
||||
}
|
||||
@@ -206,7 +216,7 @@ func (b *boot) applyWorkflowExecutionSettings(ctx context.Context, settings work
|
||||
return err
|
||||
}
|
||||
b.executionSettings.Store(&candidate.settings)
|
||||
b.cfgHolder.Set(candidate.cfg)
|
||||
b.publishConfig(ctx, candidate.cfg)
|
||||
b.applyStatus.Report(ctx, controlplane.WorkflowExecutionSettingsKind, version, nil)
|
||||
b.log.Info("workflow execution settings applied", "version", version)
|
||||
if limit, uptime := settings.MaxTaskRuntime, candidate.cfg.Containers.MaxUptime.Std(); uptime > 0 && (limit <= 0 || limit > uptime) {
|
||||
@@ -224,3 +234,122 @@ func applyExecutionBudgets(cfg *config.Config, settings workflow.ExecutionSettin
|
||||
cfg.Identities[i].Budgets = cfg.Budgets
|
||||
}
|
||||
}
|
||||
|
||||
// startLiveSettings starts everything a live control-plane update needs
|
||||
// established before Run continues: the workflow-execution-settings watch,
|
||||
// whose limits the layering applies, and one watch per runtime-resource kind
|
||||
// (control_plane.go, runtimeResourceKinds). Both first reads are synchronous,
|
||||
// so a control plane that cannot be watched at all fails the boot that asked
|
||||
// for it rather than leaving the process running settings it can no longer
|
||||
// update.
|
||||
func (b *boot) startLiveSettings(ctx context.Context) error {
|
||||
if err := b.startWorkflowExecutionSettings(ctx); err != nil {
|
||||
return fmt.Errorf("workflow execution settings: %w", err)
|
||||
}
|
||||
if err := b.startRuntimeResourceWatches(ctx, b.runtimeVersions); err != nil {
|
||||
return fmt.Errorf("runtime resource watches: %w", err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// runtimeResourceKinds are the control-plane kinds this process re-layers
|
||||
// live: on a new stored version the watch re-runs the layering a reload runs
|
||||
// (b.runtimeConfig, which applies the execution budgets the settings watch
|
||||
// published) and republishes through config.Holder, so the change takes
|
||||
// effect without a restart. Kinds stay out of this list while a
|
||||
// startup-built component still holds their value -- tool, plugin, container
|
||||
// and channel settings are frozen in components built at boot and remain
|
||||
// restart-required -- and a kind joins it only with a consumer that re-reads
|
||||
// it. Each kind is watched in its own goroutine, exactly the shape the
|
||||
// workflow-execution-settings watch established.
|
||||
var runtimeResourceKinds = []string{
|
||||
controlplane.ProviderSettingsKind,
|
||||
controlplane.ModelRoleAssignmentsKind,
|
||||
controlplane.RepositoryPoliciesKind,
|
||||
controlplane.SchedulingPolicyKind,
|
||||
}
|
||||
|
||||
// startRuntimeResourceWatches keeps a watch per live kind established for the
|
||||
// life of the process. versions carries the resume point each kind starts
|
||||
// from, the versions boot's layering recorded. The first stream per kind is
|
||||
// opened synchronously, so a control plane that cannot be watched at all
|
||||
// fails the boot that asked for it; after that the watch does not return, it
|
||||
// reconnects (see keepWatch, whose backoff rules these watches ride).
|
||||
func (b *boot) startRuntimeResourceWatches(ctx context.Context, versions map[string]int64) error {
|
||||
for _, kind := range runtimeResourceKinds {
|
||||
updates, err := b.controlPlane.WatchResource(ctx, kind, versions[kind])
|
||||
if err != nil {
|
||||
return fmt.Errorf("watch %s: %w", kind, err)
|
||||
}
|
||||
go keepWatch(ctx, b.log, kind, versions[kind], updates,
|
||||
func(ctx context.Context, afterVersion int64) (<-chan controlplane.AppliedResource, error) {
|
||||
return b.controlPlane.WatchResource(ctx, kind, afterVersion)
|
||||
},
|
||||
waitFor,
|
||||
func(update controlplane.AppliedResource) int64 { return update.Version },
|
||||
func(update controlplane.AppliedResource) { b.applyRuntimeResourceUpdate(ctx, kind, update) })
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// applyRuntimeResourceUpdate re-runs the layering a reload runs and
|
||||
// republishes the result through config.Holder. The base is the published
|
||||
// snapshot rather than the boot struct: reloadConfig publishes through the
|
||||
// same holder and does not update the boot config, so the holder is the one
|
||||
// view that is current in every path. The layering reads every kind from the
|
||||
// store over it, so a scheduling-policy document written during this
|
||||
// process's life and every other kind's last stored value land together, and
|
||||
// the merge is idempotent (every kind it reads replaces its fields).
|
||||
//
|
||||
// The published snapshot is replaced only after the same check the reload
|
||||
// and the boot layering pass: on a validation failure nothing is published,
|
||||
// the previous settings keep running (last-known-good), and the failure is
|
||||
// reported through apply status, which keeps the version still live on the
|
||||
// record. A refused update therefore reaches the settings page the way a
|
||||
// refused workflow-execution-settings update does
|
||||
// (docs/prds/control-plane-apply-status.md).
|
||||
func (b *boot) applyRuntimeResourceUpdate(ctx context.Context, kind string, update controlplane.AppliedResource) {
|
||||
if update.Err != nil {
|
||||
// A stream failure carries no version at all (versions start at 1,
|
||||
// store.PutResource), and a process must never report an unreachable
|
||||
// store as its own refusal; the reconnect is keepWatch's business.
|
||||
if update.Version > 0 {
|
||||
b.applyStatus.Report(ctx, kind, update.Version, update.Err)
|
||||
}
|
||||
b.log.Error("runtime settings watch failed", "kind", kind, "err", update.Err)
|
||||
return
|
||||
}
|
||||
base := b.cfgHolder.Get()
|
||||
// Boot publishes before the model catalog is merged in, so the snapshot
|
||||
// this read returns can lack the catalog's model limits and discovered
|
||||
// providers. The merge is idempotent, and reloadConfig re-applies it
|
||||
// before layering for the same reason.
|
||||
applyModelCatalog(&base, b.catalog)
|
||||
cfg, _, err := b.runtimeConfig(ctx, base)
|
||||
if err != nil {
|
||||
// runtimeConfig reported the refusal through apply status for every
|
||||
// kind it layers, keeping the version each of them last applied.
|
||||
b.log.Error("runtime settings update rejected; the running settings stay", "kind", kind, "version", update.Version, "err", err)
|
||||
return
|
||||
}
|
||||
b.publishConfig(ctx, cfg)
|
||||
b.log.Info("runtime settings applied", "kind", kind, "version", update.Version)
|
||||
switch kind {
|
||||
case controlplane.ProviderSettingsKind, controlplane.ModelRoleAssignmentsKind:
|
||||
b.rebuildChatModelRuntime(cfg)
|
||||
}
|
||||
}
|
||||
|
||||
// rebuildChatModelRuntime re-derives the gateway chat runtime's provider set
|
||||
// after a live change to provider-settings or model-role-assignments. The
|
||||
// turn runner reads the runtime through boot.chatLLM, so the swap reaches its
|
||||
// next turn without rebuilding the runner, and the model manager re-derives
|
||||
// the references it offers from the new role assignments.
|
||||
func (b *boot) rebuildChatModelRuntime(cfg config.Config) {
|
||||
if b.chatModels == nil {
|
||||
return // this process serves no chat turns
|
||||
}
|
||||
b.setLLM(agentexec.NewRuntime(executionProviders(cfg)))
|
||||
b.chatModels.SetConfigured(cfg.Models)
|
||||
b.log.Info("chat model runtime rebuilt", "providers", len(cfg.Providers), "models", len(cfg.Models))
|
||||
}
|
||||
@@ -132,7 +132,8 @@ func (*settingsWatchStub) Command(context.Context, *pb.CommandRequest, ...grpc.C
|
||||
panic("unexpected Command")
|
||||
}
|
||||
|
||||
func (s *settingsWatchStub) Watch(context.Context, *pb.WatchRequest, ...grpc.CallOption) (grpc.ServerStreamingClient[pb.WatchResponse], error) {
|
||||
func (s *settingsWatchStub) Watch(ctx context.Context, request *pb.WatchRequest, _ ...grpc.CallOption) (grpc.ServerStreamingClient[pb.WatchResponse], error) {
|
||||
_ = request
|
||||
responses := make([]*pb.WatchResponse, 0, len(s.documents))
|
||||
for i, document := range s.documents {
|
||||
responses = append(responses, &pb.WatchResponse{Resource: &pb.Resource{
|
||||
@@ -141,7 +142,7 @@ func (s *settingsWatchStub) Watch(context.Context, *pb.WatchRequest, ...grpc.Cal
|
||||
ValueJson: []byte(document),
|
||||
}})
|
||||
}
|
||||
return &watchStreamStub{responses: responses}, nil
|
||||
return &watchStreamStub{responses: responses, done: ctx.Done()}, nil
|
||||
}
|
||||
|
||||
// watchStreamStub is the client end of a Watch stream. Recv is the only method
|
||||
@@ -150,15 +151,26 @@ func (s *settingsWatchStub) Watch(context.Context, *pb.WatchRequest, ...grpc.Cal
|
||||
type watchStreamStub struct {
|
||||
grpc.ClientStream
|
||||
responses []*pb.WatchResponse
|
||||
done <-chan struct{}
|
||||
next int
|
||||
// onDeliver, when set, runs as the stream delivers each response, so a
|
||||
// stub standing in for the store can store what it just delivered.
|
||||
onDeliver func()
|
||||
}
|
||||
|
||||
func (s *watchStreamStub) Recv() (*pb.WatchResponse, error) {
|
||||
if s.next >= len(s.responses) {
|
||||
return nil, io.EOF
|
||||
if s.done == nil {
|
||||
return nil, io.EOF
|
||||
}
|
||||
<-s.done
|
||||
return nil, context.Canceled
|
||||
}
|
||||
response := s.responses[s.next]
|
||||
s.next++
|
||||
if s.onDeliver != nil {
|
||||
s.onDeliver()
|
||||
}
|
||||
return response, nil
|
||||
}
|
||||
|
||||
|
||||
@@ -5,6 +5,7 @@ import (
|
||||
"encoding/json"
|
||||
"log/slog"
|
||||
"os"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
@@ -113,22 +114,27 @@ func newReloadBoot(t *testing.T, stub *controlPlaneStub) *boot {
|
||||
return b
|
||||
}
|
||||
|
||||
func TestRuntimeConfigResolvesStoredProviderReference(t *testing.T) {
|
||||
t.Setenv("ARCHIE_TEST_STORED_PROVIDER", "provider-secret")
|
||||
resources := databaseOwnedResources()
|
||||
resources[controlplane.ProviderSettingsKind] = map[string]any{"main": map[string]any{
|
||||
"class": "openai", "api_key_ref": map[string]any{"engine": "env", "key": "ARCHIE_TEST_STORED_PROVIDER"},
|
||||
}}
|
||||
b := newReloadBoot(t, &controlPlaneStub{values: resources})
|
||||
b.secrets = secret.NewRegistry()
|
||||
if err := b.loadRuntimeConfig(t.Context()); err != nil {
|
||||
t.Fatal(err)
|
||||
func TestRuntimeConfigResolvesStoredProviderReferences(t *testing.T) {
|
||||
for _, providerID := range []string{"main", "secondary"} {
|
||||
t.Run(providerID, func(t *testing.T) {
|
||||
refKey := "ARCHIE_TEST_STORED_PROVIDER_" + strings.ToUpper(providerID)
|
||||
t.Setenv(refKey, "provider-secret")
|
||||
resources := databaseOwnedResources()
|
||||
resources[controlplane.ProviderSettingsKind] = map[string]any{providerID: map[string]any{
|
||||
"class": "openai", "api_key_ref": map[string]any{"engine": "env", "key": refKey},
|
||||
}}
|
||||
b := newReloadBoot(t, &controlPlaneStub{values: resources})
|
||||
b.secrets = secret.NewRegistry()
|
||||
if err := b.loadRuntimeConfig(t.Context()); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
got := b.cfgHolder.Get().Providers[providerID]
|
||||
if got.APIKey != (secret.SecretRef{}) || got.APIKeyEnv != providerSecretEnvName("root", providerID) {
|
||||
t.Fatalf("effective provider credential = %+v, want a resolved process-local env name", got)
|
||||
}
|
||||
t.Cleanup(func() { _ = os.Unsetenv(got.APIKeyEnv) })
|
||||
})
|
||||
}
|
||||
got := b.cfgHolder.Get().Providers["main"]
|
||||
if got.APIKey != (secret.SecretRef{}) || got.APIKeyEnv != providerSecretEnvName("root", "main") {
|
||||
t.Fatalf("effective provider credential = %+v, want a resolved process-local env name", got)
|
||||
}
|
||||
t.Cleanup(func() { _ = os.Unsetenv(got.APIKeyEnv) })
|
||||
}
|
||||
|
||||
// TestReloadConfigKeepsDatabaseOwnedSettings is archie-core-ju85. The SIGHUP
|
||||
|
||||
@@ -0,0 +1,242 @@
|
||||
package archied
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"slices"
|
||||
"strings"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"google.golang.org/grpc"
|
||||
"google.golang.org/grpc/codes"
|
||||
"google.golang.org/grpc/status"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/agentexec"
|
||||
"github.com/samcharles93/archie-core/internal/app/controlplane"
|
||||
pb "github.com/samcharles93/archie-core/internal/contracts/controlplane/v1"
|
||||
"github.com/samcharles93/archie-core/internal/secret"
|
||||
)
|
||||
|
||||
// resourceWatchStub answers Query with one stored version per kind and Watch
|
||||
// with the documents queued for the watched kind. It is the store end of the
|
||||
// seam the runtime-resource watch meets a live update through, and it is the
|
||||
// store: delivering a document stores it, so the layering the apply runs
|
||||
// reads the update back from Query the way production does. A kind the map
|
||||
// does not carry is answered codes.NotFound, the state a skipped seed leaves
|
||||
// behind.
|
||||
type resourceWatchStub struct {
|
||||
values map[string]any
|
||||
// version is the stored version until a watch delivers an update, which
|
||||
// is the version the store then answers Query with -- the apply the
|
||||
// delivery triggers layers and reports the version the store now holds.
|
||||
version int64
|
||||
// storedVersion, when present, is the version Query answers a kind with.
|
||||
storedVersion map[string]int64
|
||||
// watch queues, per kind, the documents a live write delivers after the
|
||||
// stored version, one per stream: the first open delivers the first
|
||||
// document, the second open the second, and so on.
|
||||
watch map[string][]string
|
||||
// opens counts how often each kind's stream was opened, so queued
|
||||
// documents are delivered in order across the reconnects keepWatch runs.
|
||||
opens map[string]int
|
||||
}
|
||||
|
||||
func (s *resourceWatchStub) versionOf(kind string) int64 {
|
||||
if stored, ok := s.storedVersion[kind]; ok {
|
||||
return stored
|
||||
}
|
||||
return s.version
|
||||
}
|
||||
|
||||
func (*resourceWatchStub) Catalog(context.Context, *pb.CatalogRequest, ...grpc.CallOption) (*pb.CatalogResponse, error) {
|
||||
return &pb.CatalogResponse{}, nil
|
||||
}
|
||||
|
||||
func (s *resourceWatchStub) Query(_ context.Context, request *pb.QueryRequest, _ ...grpc.CallOption) (*pb.QueryResponse, error) {
|
||||
value, ok := s.values[request.Kind]
|
||||
if !ok {
|
||||
return nil, status.Error(codes.NotFound, "resource not found")
|
||||
}
|
||||
encoded, err := json.Marshal(value)
|
||||
return &pb.QueryResponse{Resource: &pb.Resource{Kind: request.Kind, Version: s.versionOf(request.Kind), ValueJson: encoded}}, err
|
||||
}
|
||||
|
||||
func (s *resourceWatchStub) Watch(_ context.Context, request *pb.WatchRequest, _ ...grpc.CallOption) (grpc.ServerStreamingClient[pb.WatchResponse], error) {
|
||||
// One queued document per stream: a stream ends after the document it
|
||||
// carries, and the next one arrives on the reconnect -- the shape a store
|
||||
// whose writes are spaced apart produces, and the shape that keeps the
|
||||
// apply each delivery triggers reading the document back from Query
|
||||
// before the store has moved on to the next one.
|
||||
open := s.opens[request.Kind]
|
||||
s.opens[request.Kind] = open + 1
|
||||
if open >= len(s.watch[request.Kind]) {
|
||||
return &watchStreamStub{}, nil
|
||||
}
|
||||
document := s.watch[request.Kind][open]
|
||||
version := s.version + int64(open) + 1
|
||||
if version <= request.AfterVersion {
|
||||
return &watchStreamStub{}, nil
|
||||
}
|
||||
// The stub is the store: a document is stored when the stream delivers
|
||||
// it, so the apply that delivery triggers layers the document back from
|
||||
// Query.
|
||||
response := &pb.WatchResponse{Resource: &pb.Resource{
|
||||
Kind: request.Kind, Version: version, ValueJson: []byte(document),
|
||||
}}
|
||||
return &watchStreamStub{responses: []*pb.WatchResponse{response}, onDeliver: func() {
|
||||
s.values[request.Kind] = json.RawMessage(document)
|
||||
s.storedVersion[request.Kind] = version
|
||||
}}, nil
|
||||
}
|
||||
|
||||
func (*resourceWatchStub) History(context.Context, *pb.HistoryRequest, ...grpc.CallOption) (*pb.HistoryResponse, error) {
|
||||
panic("unexpected History")
|
||||
}
|
||||
|
||||
func (*resourceWatchStub) Audit(context.Context, *pb.AuditRequest, ...grpc.CallOption) (*pb.AuditResponse, error) {
|
||||
return &pb.AuditResponse{}, nil
|
||||
}
|
||||
|
||||
func (*resourceWatchStub) Command(context.Context, *pb.CommandRequest, ...grpc.CallOption) (*pb.CommandResponse, error) {
|
||||
panic("unexpected Command")
|
||||
}
|
||||
|
||||
// newResourceWatchBoot builds a boot whose apply status lands in a recorder,
|
||||
// with the chat model runtime a provider or role update must rebuild.
|
||||
func newResourceWatchBoot(t *testing.T, stub *resourceWatchStub) (*boot, *applyStatusRecorder) {
|
||||
t.Helper()
|
||||
b, recorder := newLiveApplyBoot(t, fileConfig())
|
||||
b.controlPlane = controlplane.NewRPCClient(stub)
|
||||
b.secrets = secret.NewRegistry()
|
||||
b.chatModels = newChatModelManager(fileConfig().Models)
|
||||
b.setLLM(agentexec.NewRuntime(executionProviders(fileConfig())))
|
||||
return b, recorder
|
||||
}
|
||||
|
||||
// schedulingDocument renders a scheduling-policy document the layering reads
|
||||
// back, so the applied and refused updates in these tests cannot disagree on
|
||||
// what "the stored scheduling policy" is.
|
||||
func schedulingDocument(interval string) string {
|
||||
return `{"poll_interval": "` + interval + `", "max_retries": 7, "dispatch": {"trigger": "assignee"}}`
|
||||
}
|
||||
|
||||
// TestRuntimeResourceWatchReLayersTheStoredChangeAndRepublishes is the live
|
||||
// apply for the four kinds the daemon watches (archie-core-zfb0.1): a new
|
||||
// stored version of scheduling-policy re-runs the layering a reload runs and
|
||||
// republishes through config.Holder, so the change takes effect without a
|
||||
// restart, the apply status records the version that was applied, and every
|
||||
// other database-owned setting the layering read is still in the running
|
||||
// config.
|
||||
func TestRuntimeResourceWatchReLayersTheStoredChangeAndRepublishes(t *testing.T) {
|
||||
values := databaseOwnedResources()
|
||||
stub := &resourceWatchStub{values: values, version: 3, storedVersion: map[string]int64{}, opens: map[string]int{}, watch: map[string][]string{
|
||||
controlplane.SchedulingPolicyKind: {schedulingDocument("5m")},
|
||||
}}
|
||||
b, status := newResourceWatchBoot(t, stub)
|
||||
if err := b.loadRuntimeConfig(t.Context()); err != nil {
|
||||
t.Fatalf("loadRuntimeConfig: %v", err)
|
||||
}
|
||||
|
||||
ctx, cancel := context.WithCancel(t.Context())
|
||||
defer cancel()
|
||||
if err := b.startRuntimeResourceWatches(ctx, b.runtimeVersions); err != nil {
|
||||
t.Fatalf("startRuntimeResourceWatches: %v", err)
|
||||
}
|
||||
// One record for boot's layering, one for the watched update.
|
||||
records := status.awaitCount(t, controlplane.SchedulingPolicyKind, 2)
|
||||
|
||||
cfg := b.cfgHolder.Get()
|
||||
if got := time.Duration(cfg.PollInterval); got != 5*time.Minute {
|
||||
t.Errorf("running PollInterval = %s, want the watched update (5m)", got)
|
||||
}
|
||||
if got := cfg.Repos[0].Name; got != "from-database" {
|
||||
t.Errorf("running Repos[0] = %q, want the other kinds' last values to survive the re-layering", got)
|
||||
}
|
||||
last := records[len(records)-1]
|
||||
if last.AppliedVersion != stub.version+1 {
|
||||
t.Errorf("apply status version = %d, want the delivered version %d", last.AppliedVersion, stub.version+1)
|
||||
}
|
||||
if last.Error != "" {
|
||||
t.Errorf("apply status error = %q, want none for an applied update", last.Error)
|
||||
}
|
||||
}
|
||||
|
||||
// TestRuntimeResourceWatchKeepsLastKnownGoodWhenTheUpdateIsRefused: an update
|
||||
// the layered document cannot run is refused before it is published, the
|
||||
// running config keeps the last version that was applied, and the refusal is
|
||||
// reported through apply status against the version still live.
|
||||
func TestRuntimeResourceWatchKeepsLastKnownGoodWhenTheUpdateIsRefused(t *testing.T) {
|
||||
stub := &resourceWatchStub{values: databaseOwnedResources(), version: 3, storedVersion: map[string]int64{}, opens: map[string]int{}, watch: map[string][]string{
|
||||
controlplane.SchedulingPolicyKind: {schedulingDocument("5m"), schedulingDocument("0s")},
|
||||
}}
|
||||
b, status := newResourceWatchBoot(t, stub)
|
||||
if err := b.loadRuntimeConfig(t.Context()); err != nil {
|
||||
t.Fatalf("loadRuntimeConfig: %v", err)
|
||||
}
|
||||
|
||||
ctx, cancel := context.WithCancel(t.Context())
|
||||
defer cancel()
|
||||
if err := b.startRuntimeResourceWatches(ctx, b.runtimeVersions); err != nil {
|
||||
t.Fatalf("startRuntimeResourceWatches: %v", err)
|
||||
}
|
||||
// One record for boot's layering, one for the applied update, one for the
|
||||
// refusal. The recorder keeps the version that is still live on a refusal,
|
||||
// so the third record carries the second update's version.
|
||||
records := status.awaitCount(t, controlplane.SchedulingPolicyKind, 3)
|
||||
|
||||
if got := time.Duration(b.cfgHolder.Get().PollInterval); got != 5*time.Minute {
|
||||
t.Errorf("running PollInterval = %s, want the last update that validated (5m)", got)
|
||||
}
|
||||
last := records[len(records)-1]
|
||||
if last.AppliedVersion != stub.version+1 {
|
||||
t.Errorf("apply status version = %d, want the version still live (%d)", last.AppliedVersion, stub.version+1)
|
||||
}
|
||||
if !strings.Contains(last.Error, "poll_interval must be positive") {
|
||||
t.Errorf("apply status error = %q, want it to carry the refusal", last.Error)
|
||||
}
|
||||
}
|
||||
|
||||
// TestLiveModelRoleUpdateRebuildsTheChatModelRuntime: providers and model
|
||||
// role assignments also feed the gateway chat runtime, so an update to either
|
||||
// kind swaps the runtime (ai-sdk's Runtime caches the provider instances it
|
||||
// built) and re-derives the model list the chat surfaces offer.
|
||||
func TestLiveModelRoleUpdateRebuildsTheChatModelRuntime(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
kind string
|
||||
}{
|
||||
{"a provider settings update", controlplane.ProviderSettingsKind},
|
||||
{"a model role assignments update", controlplane.ModelRoleAssignmentsKind},
|
||||
}
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
values := databaseOwnedResources()
|
||||
values[controlplane.ModelRoleAssignmentsKind] = map[string]string{
|
||||
"builder": "main/db-model", "chat": "main/db-model",
|
||||
}
|
||||
stub := &resourceWatchStub{values: values, version: 3, storedVersion: map[string]int64{}, opens: map[string]int{}}
|
||||
b, _ := newResourceWatchBoot(t, stub)
|
||||
if err := b.loadRuntimeConfig(t.Context()); err != nil {
|
||||
t.Fatalf("loadRuntimeConfig: %v", err)
|
||||
}
|
||||
before := b.chatLLM()
|
||||
|
||||
b.applyRuntimeResourceUpdate(t.Context(), tt.kind, controlplane.AppliedResource{Version: 4})
|
||||
|
||||
if after := b.chatLLM(); after == before {
|
||||
t.Error("the chat runtime was not rebuilt; the next turn keeps the previous provider set")
|
||||
}
|
||||
if !slices.Contains(b.chatModels.Models(), "main/db-model") {
|
||||
t.Errorf("chat models = %v, want the new role assignment's reference", b.chatModels.Models())
|
||||
}
|
||||
if got := b.chatModels.ActiveModel(); got != "main/db-model" {
|
||||
t.Errorf("chat active model = %q, want the chat role's model after the update", got)
|
||||
}
|
||||
// The running config carries the update, not just the chat runtime.
|
||||
if got := b.cfgHolder.Get().Models["chat"]; got != "main/db-model" {
|
||||
t.Errorf("running chat role = %q, want the applied assignment", got)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
@@ -52,12 +52,10 @@ const controlPlaneWatchHealthyMultiple = 2
|
||||
// re-establishes it in this same goroutine until ctx ends.
|
||||
//
|
||||
// A control-plane watch stream is not permanent. The State Store restarts, the
|
||||
// connection drops, the server closes the stream -- and nothing on the client
|
||||
// side reopens it. A watch that ends on its first end stops applying that kind
|
||||
// for the rest of the process's life: every later stored change is silently
|
||||
// never applied while the last apply-status record keeps re-stamping, so the
|
||||
// settings page reads the process as current, and the process recovers only by
|
||||
// restarting (archie-core-yrmr).
|
||||
// connection drops, or the server closes the stream. keepWatch reopens it in
|
||||
// place; workflow-execution-settings also reports the gap so apply status does
|
||||
// not keep re-stamping the previous successful version as current while no
|
||||
// live updates can arrive (archie-core-1050).
|
||||
//
|
||||
// One goroutine per kind, reconnecting in place: a long outage does not stack
|
||||
// watchers. Reopening resumes after the last version an update carried, so a
|
||||
@@ -129,6 +127,7 @@ func keepWatch[T any](
|
||||
wait func(ctx context.Context, d time.Duration) bool,
|
||||
versionOf func(update T) int64,
|
||||
deliver func(update T),
|
||||
onEnded ...func(),
|
||||
) {
|
||||
stream, backoff := first, controlPlaneWatchRetryMin
|
||||
for {
|
||||
@@ -146,6 +145,9 @@ func keepWatch[T any](
|
||||
if ctx.Err() != nil {
|
||||
return
|
||||
}
|
||||
if len(onEnded) > 0 {
|
||||
onEnded[0]()
|
||||
}
|
||||
backoff = retryDelay(backoff, attemptHealthy(progressed, time.Since(started), backoff))
|
||||
log.Warn("control plane watch stream ended; reconnecting",
|
||||
"kind", kind, "after_version", after, "retry_in", backoff)
|
||||
|
||||
@@ -47,7 +47,7 @@ func (s *outageStore) down(stall time.Duration) {
|
||||
s.failing, s.stall = true, stall
|
||||
}
|
||||
|
||||
func (s *outageStore) Resource(ctx context.Context, kind string) (storecontract.Resource, error) {
|
||||
func (s *outageStore) Resource(ctx context.Context, orgID, kind string) (storecontract.Resource, error) {
|
||||
s.mu.Lock()
|
||||
failing, stall := s.failing, s.stall
|
||||
s.mu.Unlock()
|
||||
@@ -55,7 +55,7 @@ func (s *outageStore) Resource(ctx context.Context, kind string) (storecontract.
|
||||
time.Sleep(stall)
|
||||
return storecontract.Resource{}, errors.New("state store unreachable")
|
||||
}
|
||||
return s.TaskDB.Resource(ctx, kind)
|
||||
return s.TaskDB.Resource(ctx, orgID, kind)
|
||||
}
|
||||
|
||||
// TestWatchRetryGrowsWhileTheStateStoreIsDown is the outage this reconnect
|
||||
|
||||
@@ -219,22 +219,22 @@ func TestWorkflowExecutionSettingsWatchIsReEstablishedAfterTheStreamEnds(t *test
|
||||
t.Errorf("watch resumed after %v, want the boot version then the last version handled", got)
|
||||
}
|
||||
|
||||
// Boot's own apply, then the update the re-established stream
|
||||
// delivered. Neither way the stream ends writes a record of its own:
|
||||
// a stream the server closed emits no update at all (controlplane
|
||||
// .Client sends one only for a Recv error), and a Recv failure
|
||||
// carries no version, which is the unreachable store the process must
|
||||
// never report as a failure of its own
|
||||
// (docs/prds/control-plane-apply-status.md, "What can be reported, and
|
||||
// what cannot").
|
||||
records := status.awaitCount(t, controlplane.WorkflowExecutionSettingsKind, 2)
|
||||
if len(records) != 2 {
|
||||
t.Fatalf("apply status = %+v, want the boot apply and the recovered one alone", records)
|
||||
// Boot applies version 1, the ended stream reports the outage, the
|
||||
// reopened watch clears it, and the delivered version 2 is applied.
|
||||
records := status.awaitCount(t, controlplane.WorkflowExecutionSettingsKind, 4)
|
||||
if len(records) != 4 {
|
||||
t.Fatalf("apply status = %+v, want boot, outage, reconnect, and update reports", records)
|
||||
}
|
||||
if records[0].AppliedVersion != 1 || records[0].Error != "" {
|
||||
t.Errorf("boot report = %+v, want a clean apply of version 1", records[0])
|
||||
}
|
||||
last := records[len(records)-1]
|
||||
if records[1].AppliedVersion != 1 || !strings.Contains(records[1].Error, "watch unavailable") {
|
||||
t.Errorf("outage report = %+v, want version 1 with a watch outage", records[1])
|
||||
}
|
||||
if records[2].AppliedVersion != 1 || records[2].Error != "" {
|
||||
t.Errorf("reconnect report = %+v, want the outage cleared at version 1", records[2])
|
||||
}
|
||||
last := records[3]
|
||||
if last.AppliedVersion != 2 || last.Error != "" {
|
||||
t.Errorf("last apply status = %+v, want the recovered apply of version 2 with the failure cleared", last)
|
||||
}
|
||||
@@ -256,7 +256,7 @@ func TestWorkflowExecutionSettingsWatchIsReEstablishedAfterTheStreamEnds(t *test
|
||||
// point), applystatus.Reporter keeps a standing error and re-stamps it forever,
|
||||
// and the dashboard renders any non-empty error as failed. The process reads as
|
||||
// failed for the rest of its life, after one blip.
|
||||
func TestWatchTransportFailureIsNotReportedAsAFailedApply(t *testing.T) {
|
||||
func TestWatchTransportFailureIsReportedUntilTheWatchRecovers(t *testing.T) {
|
||||
t.Parallel()
|
||||
b, recorder := newLiveApplyBoot(t, fileConfig())
|
||||
stub := &watchStub{
|
||||
@@ -285,23 +285,25 @@ func TestWatchTransportFailureIsNotReportedAsAFailedApply(t *testing.T) {
|
||||
// the loop delivers what ended the stream, then reopens.
|
||||
stub.awaitWatchCalls(t, controlplane.WorkflowExecutionSettingsKind, 2)
|
||||
|
||||
records := recorder.awaitCount(t, controlplane.WorkflowExecutionSettingsKind, 1)
|
||||
if len(records) != 1 {
|
||||
t.Fatalf("apply status = %+v, want the boot apply alone: an unreachable store writes no record", records)
|
||||
records := recorder.awaitCount(t, controlplane.WorkflowExecutionSettingsKind, 3)
|
||||
if len(records) != 3 {
|
||||
t.Fatalf("apply status = %+v, want boot, outage, and recovery reports", records)
|
||||
}
|
||||
if last := records[0]; last.AppliedVersion != 1 || last.Error != "" {
|
||||
t.Errorf("apply status = %+v, want the clean apply of version 1 still standing", last)
|
||||
if records[0].AppliedVersion != 1 || records[0].Error != "" {
|
||||
t.Errorf("boot apply status = %+v, want the clean apply of version 1", records[0])
|
||||
}
|
||||
if records[1].AppliedVersion != 1 || !strings.Contains(records[1].Error, "watch unavailable") {
|
||||
t.Errorf("outage apply status = %+v, want version 1 with a watch outage", records[1])
|
||||
}
|
||||
if records[2].AppliedVersion != 1 || records[2].Error != "" {
|
||||
t.Errorf("recovered apply status = %+v, want version 1 with the outage cleared", records[2])
|
||||
}
|
||||
}
|
||||
|
||||
// TestWatchTransportFailureDoesNotOverwriteARefusal is the other half of the
|
||||
// same rule, and the reason the branch is on the version rather than on the
|
||||
// error: a refused document arrives carrying the version it came from, so it is
|
||||
// the store answering and must be reported; a transport failure carries no
|
||||
// version and must not. Reporting the transport failure against the version
|
||||
// still live overwrites the refusal's text, so a validation error against
|
||||
// version 2 reads "control-plane unavailable: ..." after any blip, and the
|
||||
// operator loses the one message that says what to fix.
|
||||
// TestWatchTransportFailureDoesNotOverwriteARefusal keeps the more useful
|
||||
// versioned rejection visible when a stream drops afterward. Reconnection
|
||||
// restores that rejection instead of clearing it as though a valid update had
|
||||
// arrived.
|
||||
func TestWatchTransportFailureDoesNotOverwriteARefusal(t *testing.T) {
|
||||
t.Parallel()
|
||||
b, recorder := newLiveApplyBoot(t, fileConfig())
|
||||
@@ -332,18 +334,18 @@ func TestWatchTransportFailureDoesNotOverwriteARefusal(t *testing.T) {
|
||||
|
||||
stub.awaitWatchCalls(t, controlplane.WorkflowExecutionSettingsKind, 2)
|
||||
|
||||
records := recorder.awaitCount(t, controlplane.WorkflowExecutionSettingsKind, 2)
|
||||
if len(records) != 2 {
|
||||
t.Fatalf("apply status = %+v, want the boot apply and the refusal alone", records)
|
||||
records := recorder.awaitCount(t, controlplane.WorkflowExecutionSettingsKind, 3)
|
||||
if len(records) != 3 {
|
||||
t.Fatalf("apply status = %+v, want boot, refusal, and the preserved refusal after reconnect", records)
|
||||
}
|
||||
last := records[len(records)-1]
|
||||
last := records[2]
|
||||
if last.AppliedVersion != 1 {
|
||||
t.Errorf("refusal reported against version %d, want the version still live (1)", last.AppliedVersion)
|
||||
}
|
||||
if !strings.Contains(last.Error, "max model/tool steps must not be negative") {
|
||||
t.Errorf("apply status error = %q, want the refusal's own text", last.Error)
|
||||
}
|
||||
if strings.Contains(last.Error, "control-plane unavailable") {
|
||||
if strings.Contains(last.Error, "watch unavailable") {
|
||||
t.Errorf("apply status error = %q, want the transport blip not to have overwritten the refusal", last.Error)
|
||||
}
|
||||
// The refused version is unusable to this build, so the resume point moves
|
||||
@@ -394,13 +396,16 @@ func TestWatchReconnectDoesNotReplayWhatItAlreadyApplied(t *testing.T) {
|
||||
t.Errorf("watch resumed after %v, want the boot version then the last version handled", got)
|
||||
}
|
||||
|
||||
// One report for the boot apply and one for the update: a third would be
|
||||
// the re-served version 1 applied over itself.
|
||||
records := recorder.awaitCount(t, controlplane.WorkflowExecutionSettingsKind, 2)
|
||||
if len(records) != 2 {
|
||||
t.Fatalf("apply status = %+v, want the boot apply and the update alone", records)
|
||||
// The outage and reconnection records sit between boot and version 2; the
|
||||
// re-served version 1 is still filtered out.
|
||||
records := recorder.awaitCount(t, controlplane.WorkflowExecutionSettingsKind, 4)
|
||||
if len(records) != 4 {
|
||||
t.Fatalf("apply status = %+v, want boot, outage, reconnect, and version 2", records)
|
||||
}
|
||||
last := records[len(records)-1]
|
||||
if records[1].AppliedVersion != 1 || !strings.Contains(records[1].Error, "watch unavailable") {
|
||||
t.Errorf("outage report = %+v, want an outage against version 1", records[1])
|
||||
}
|
||||
last := records[3]
|
||||
if last.AppliedVersion != 2 || last.Error != "" {
|
||||
t.Errorf("last apply status = %+v, want the recovered apply of version 2", last)
|
||||
}
|
||||
|
||||
@@ -119,8 +119,21 @@ func RunGateway(ctx context.Context, options GatewayOptions) error {
|
||||
if err != nil {
|
||||
return fmt.Errorf("listen for gateway: %w", err)
|
||||
}
|
||||
return b.serveGatewayListener(ctx, listener, loopback, contract, opts)
|
||||
}
|
||||
|
||||
// serveGatewayListener is the serving tail of RunGateway: the listener is
|
||||
// bound, the process declares itself serving, and the chat contract answers
|
||||
// until ctx ends.
|
||||
func (b *boot) serveGatewayListener(ctx context.Context, listener net.Listener, loopback bool, contract gateway.ChatContract, opts []grpc.ServerOption) error {
|
||||
defer listener.Close()
|
||||
b.log.Info("archie-gateway running", "addr", listener.Addr().String(), "token_required", !loopback)
|
||||
// Boot is over and this listener is about to accept: the same fact
|
||||
// systemd's READY=1 asserts, so the announcement goes out here rather than
|
||||
// from a second notion of "started" (archie-core-1174). Not later: Serve
|
||||
// begins accepting the moment it is called, and a unit whose
|
||||
// TimeoutStartSec expires first would restart a healthy process.
|
||||
b.announceReady()
|
||||
return serveGateway(ctx, listener, contract, b.chatSessionStore, opts)
|
||||
}
|
||||
|
||||
@@ -143,13 +156,14 @@ func (b *boot) startGatewayRuntime(ctx context.Context, actor gateway.ChatTaskAc
|
||||
b.addCleanup(b.bus.Close)
|
||||
b.capabilityHost = plugin.NewHost()
|
||||
b.startRateLimiter(ctx, b.cfg.Chat.RateLimit)
|
||||
// The Gateway owns PR review (docs/prds/operator-pr-review.md §4), so it
|
||||
// composes the process-wide worktree manager before setupGatewayChat
|
||||
// resolves boot.prReviewer: prReviewer returns nil without a manager, and
|
||||
// a nil reviewer omits review_pr from every channel's tool set. The
|
||||
// manager is the only part of the daemon's tree composition the Gateway
|
||||
// takes -- it must not own identity runners, so it does not call
|
||||
// buildTreesAndIdentities.
|
||||
// The Gateway composes the process-wide worktree manager before
|
||||
// setupGatewayChat; nothing in this process reads it today (the old
|
||||
// synchronous operator-review path that did was removed with the
|
||||
// adversarial self-review system, archie-core-afbk.7 -- see that bead's
|
||||
// continuation for the operator trigger's replacement). Kept for the
|
||||
// manager's other consumers; it is the only part of the daemon's tree
|
||||
// composition the Gateway takes -- it must not own identity runners, so
|
||||
// it does not call buildTreesAndIdentities.
|
||||
b.buildWorktreeManager()
|
||||
// setupMemoryEngine must run before setupGatewayChat: setupGatewayChat
|
||||
// constructs the turn runner, which captures b.memEngines at
|
||||
|
||||
@@ -8,6 +8,7 @@ import (
|
||||
"github.com/samcharles93/archie-core/internal/app/controlplane"
|
||||
"github.com/samcharles93/archie-core/internal/config"
|
||||
"github.com/samcharles93/archie-core/internal/domain/agent"
|
||||
"github.com/samcharles93/archie-core/internal/domain/storecontract"
|
||||
"github.com/samcharles93/archie-core/internal/gateway"
|
||||
"github.com/samcharles93/archie-core/internal/tools"
|
||||
)
|
||||
@@ -21,7 +22,7 @@ func (b *boot) setupChatRuntime(ctx context.Context, cfg config.Config) error {
|
||||
// Created before the router so the LLMResponder can be wired in for
|
||||
// non-command message processing.
|
||||
providers := executionProviders(cfg)
|
||||
b.llm = agentexec.NewRuntime(providers)
|
||||
b.setLLM(agentexec.NewRuntime(providers))
|
||||
b.toolReg = tools.NewRegistry()
|
||||
chatModels := newChatModelManager(cfg.Models, cfg.Chat.Models, b.catalogModels)
|
||||
chatModels.ApplyModelCatalog(b.catalog)
|
||||
@@ -57,10 +58,14 @@ func (b *boot) setupChatRuntime(ctx context.Context, cfg config.Config) error {
|
||||
}
|
||||
b.chatTasks = chatTasks
|
||||
b.defaultChatIdentity = defaultChatIdentity
|
||||
var canceller storecontract.ExecutionCanceller
|
||||
if ec, ok := b.stateStore.(storecontract.ExecutionCanceller); ok {
|
||||
canceller = ec
|
||||
}
|
||||
b.chatController = gateway.NewStoreTaskController(chatTaskControllerAdapter{
|
||||
taskByID: b.stateStore.TaskByID,
|
||||
requeue: b.stateStore.Requeue,
|
||||
transition: b.stateStore.Transition,
|
||||
taskByID: b.stateStore.TaskByID,
|
||||
requeue: b.stateStore.Requeue,
|
||||
cancelExecution: canceller.CancelExecution,
|
||||
})
|
||||
b.updateService = makeUpdateService(chatSetup{Cfg: config.NewHolder(cfg)})
|
||||
return nil
|
||||
@@ -119,11 +124,11 @@ func (b *boot) setupGatewayChat(ctx context.Context, actor gateway.ChatTaskActor
|
||||
configureTaskCommands(router, b.chatTasks, b.chatController, chatTaskListerAdapter{tasks: b.stateStore.Tasks}, b.defaultChatIdentity)
|
||||
router.Health = b.statusHealth
|
||||
setup := chatSetup{
|
||||
Cfg: config.NewHolder(cfg), LLM: b.llm, ChatModels: b.chatModels, ToolReg: b.toolReg,
|
||||
Cfg: config.NewHolder(cfg), LLM: b.chatLLM, ChatModels: b.chatModels, ToolReg: b.toolReg,
|
||||
Personas: b.personas, ChatTasks: b.chatTasks,
|
||||
ChatTaskLister: chatTaskListerAdapter{tasks: b.stateStore.Tasks},
|
||||
ChatTaskLogs: chatTaskLogReaderAdapter{tasks: b.stateStore.TaskByID, taskLogs: b.taskLogs},
|
||||
ChatTaskActor: actor, ChatPRReviewer: b.prReviewer(),
|
||||
ChatTaskLister: chatTaskListerAdapter{tasks: b.stateStore.Tasks},
|
||||
ChatTaskLogs: chatTaskLogReaderAdapter{tasks: b.stateStore.TaskByID, taskLogs: b.taskLogs},
|
||||
ChatTaskActor: actor,
|
||||
DefaultChatIdentity: b.defaultChatIdentity,
|
||||
Bus: b.bus, Log: b.log,
|
||||
MemoryEngine: b.memoryStore(),
|
||||
|
||||
@@ -1,6 +1,21 @@
|
||||
package archied
|
||||
|
||||
import "testing"
|
||||
import (
|
||||
"context"
|
||||
"log/slog"
|
||||
"net"
|
||||
"testing"
|
||||
"time"
|
||||
|
||||
"google.golang.org/grpc"
|
||||
"google.golang.org/grpc/credentials/insecure"
|
||||
|
||||
pb "github.com/samcharles93/archie-core/internal/contracts/gateway/v1"
|
||||
"github.com/samcharles93/archie-core/internal/domain/messaging"
|
||||
"github.com/samcharles93/archie-core/internal/domain/taskactions"
|
||||
"github.com/samcharles93/archie-core/internal/sdnotify"
|
||||
"github.com/samcharles93/archie-core/internal/taskstate"
|
||||
)
|
||||
|
||||
func TestGatewayServerOptsLoopbackIsInsecure(t *testing.T) {
|
||||
opts, loopback, err := gatewayServerOpts("127.0.0.1:8585", "")
|
||||
@@ -36,3 +51,87 @@ func TestGatewayServerOptsMalformedListen(t *testing.T) {
|
||||
t.Fatal("malformed listen address should error")
|
||||
}
|
||||
}
|
||||
|
||||
// stubGatewayContract satisfies messaging.ChatContract with zero values: the
|
||||
// serve test exercises the listener, the READY announcement and one read RPC,
|
||||
// not the chat runtime.
|
||||
type stubGatewayContract struct{}
|
||||
|
||||
func (stubGatewayContract) Snapshot(context.Context) (messaging.ChatSnapshot, error) {
|
||||
return messaging.ChatSnapshot{}, nil
|
||||
}
|
||||
|
||||
func (stubGatewayContract) GetSession(context.Context, string) (messaging.SessionContext, bool, error) {
|
||||
return messaging.SessionContext{}, false, nil
|
||||
}
|
||||
|
||||
func (stubGatewayContract) RecentMessages(context.Context, string, int) ([]messaging.Message, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
func (stubGatewayContract) RecentTurns(context.Context, string, int) ([]messaging.TurnRecord, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
func (stubGatewayContract) Route(context.Context, messaging.Inbound) (messaging.ChatReply, error) {
|
||||
return messaging.ChatReply{}, nil
|
||||
}
|
||||
|
||||
func (stubGatewayContract) Stream(context.Context, messaging.Inbound) (<-chan messaging.ChatEvent, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
func (stubGatewayContract) Cancel(context.Context, string) (messaging.ChatCancellation, error) {
|
||||
return messaging.ChatCancellation{}, nil
|
||||
}
|
||||
|
||||
func (stubGatewayContract) SetPersona(context.Context, string, string) (bool, error) {
|
||||
return false, nil
|
||||
}
|
||||
|
||||
func (stubGatewayContract) ApplyTaskAction(context.Context, string, int64, taskstate.Action) (messaging.TaskActionResult, error) {
|
||||
return messaging.TaskActionResult{}, nil
|
||||
}
|
||||
|
||||
func (stubGatewayContract) ApplyOperatorTaskAction(context.Context, taskactions.Actor, int64, taskstate.Action) (messaging.TaskActionResult, error) {
|
||||
return messaging.TaskActionResult{}, nil
|
||||
}
|
||||
|
||||
// TestGatewayServingAnnouncesReady: archie-gateway run as a Type=notify unit
|
||||
// must send READY=1 at the moment it declares itself serving, or systemd kills
|
||||
// a healthy process once TimeoutStartSec expires (archie-core-1174). The
|
||||
// announcement is judged against the same evidence archied's run loop uses:
|
||||
// the contract answers over the bound listener, so READY asserts a serving
|
||||
// process rather than a bound socket.
|
||||
func TestGatewayServingAnnouncesReady(t *testing.T) {
|
||||
listener := newNotifyListener(t)
|
||||
b := &boot{log: slog.New(slog.DiscardHandler)}
|
||||
ctx, cancel := context.WithCancel(t.Context())
|
||||
defer cancel()
|
||||
|
||||
ln, err := (&net.ListenConfig{}).Listen(ctx, "tcp", "127.0.0.1:0")
|
||||
if err != nil {
|
||||
t.Fatalf("listen: %v", err)
|
||||
}
|
||||
|
||||
serveCh := make(chan error, 1)
|
||||
go func() { serveCh <- b.serveGatewayListener(ctx, ln, true, stubGatewayContract{}, nil) }()
|
||||
|
||||
if !listener.waitForState(t, 5*time.Second, sdnotify.ReadyState) {
|
||||
t.Fatal("no READY=1 datagram within 5s of the Gateway serving")
|
||||
}
|
||||
|
||||
conn, err := grpc.NewClient("passthrough:///"+ln.Addr().String(), grpc.WithTransportCredentials(insecure.NewCredentials()))
|
||||
if err != nil {
|
||||
t.Fatalf("dial: %v", err)
|
||||
}
|
||||
defer conn.Close()
|
||||
if _, err := pb.NewChatServiceClient(conn).Snapshot(t.Context(), &pb.SnapshotRequest{}); err != nil {
|
||||
t.Fatalf("Snapshot over gRPC: %v", err)
|
||||
}
|
||||
|
||||
cancel()
|
||||
if err := <-serveCh; err != nil {
|
||||
t.Fatalf("serveGatewayListener returned: %v", err)
|
||||
}
|
||||
}
|
||||
@@ -59,9 +59,14 @@ func (b *boot) setupKitLauncher(ctx context.Context) {
|
||||
log.Warn("kit harness runs disabled: egress relay", "err", err)
|
||||
return
|
||||
}
|
||||
// No credential resolver yet (archie-core-egkf.11): a Kit's required
|
||||
// credential is refused at the proxy until run credentials carry secrets.
|
||||
proxy := egress.NewProxy(ca, egress.ProxyOptions{})
|
||||
// grants is the production Resolver: Launch/Release Grant/RevokeGrant it
|
||||
// per run with exactly the declared-and-granted intersection
|
||||
// (docs/prds/external-agent-harness.md, Credentials; archie-core-egkf.11).
|
||||
grants := egress.NewGrantResolver()
|
||||
// Without a harness secret store, Register refuses a Kit with a
|
||||
// required OAuth credential.
|
||||
oauthStore, _ := b.stateStore.(egress.OAuthStore)
|
||||
proxy := egress.NewProxy(ca, egress.ProxyOptions{Resolver: grants, OAuthStore: oauthStore})
|
||||
srv := &http.Server{Handler: proxy, ReadHeaderTimeout: 30 * time.Second}
|
||||
go func() {
|
||||
if err := srv.Serve(ln); err != nil && !errors.Is(err, http.ErrServerClosed) {
|
||||
@@ -76,6 +81,7 @@ func (b *boot) setupKitLauncher(ctx context.Context) {
|
||||
b.kitLauncher = &kitrun.Launcher{
|
||||
Pool: pool, Fetch: fetcher, Proxy: proxy, Networks: networks,
|
||||
AgentBinary: agentBinary, CAFile: egress.CACertPath(caDir),
|
||||
Config: b.cfgHolder, Secrets: b.secrets, Grants: grants, OAuth: oauthStore,
|
||||
}
|
||||
log.Info("kit harness runs enabled", "proxy", ln.Addr().String())
|
||||
}
|
||||
|
||||
@@ -166,7 +166,6 @@ func (a chatTaskListerAdapter) ListChatTasks(ctx context.Context, identity strin
|
||||
Title: task.Title,
|
||||
Status: task.Status,
|
||||
Workflow: task.Workflow,
|
||||
Stage: task.Stage,
|
||||
PRNumber: task.PRNumber,
|
||||
Attempt: task.Attempt,
|
||||
ParkReason: task.ParkReason,
|
||||
@@ -358,29 +357,19 @@ func Run() int { //nolint:cyclop,funlen // the composition root's setup sequence
|
||||
return 1
|
||||
}
|
||||
|
||||
if err := b.openStores(ctx); err != nil {
|
||||
return 1
|
||||
}
|
||||
// Resolve the State Store surfaces before setupObservability wires the
|
||||
// dashboard's storage surfaces (§10): the shared contract adapter (the
|
||||
// remote *staterpc.Client dialed to [services.state].target; the daemon no
|
||||
// longer owns archie.db in-process, so an empty target is a composition
|
||||
// error, docs/prds/state-store-contract.md §12 step 7) and then, daemon
|
||||
// root only, the workflow-definitions client on this process's step
|
||||
// vocabulary. The daemon resolves step types through that client, so it is
|
||||
// built here -- after the adapter, whose transport it wraps -- and before
|
||||
// buildDaemon captures it. The gateway root shares only the adapter and
|
||||
// resolves no step type, so openDaemonStateSurfaces owns the order and
|
||||
// step_vocabulary_test.go pins the cut.
|
||||
if err := b.openDaemonStateSurfaces(); err != nil {
|
||||
// The state-store adapter, its daemon-side surfaces and the policy chain
|
||||
// dispatch evaluates: one ordered stage of the composition sequence
|
||||
// (openStateStage; docs/prds/state-store-contract.md §12 step 7 and
|
||||
// docs/prds/orgs-and-access.md).
|
||||
if err := b.openStateStage(ctx); err != nil {
|
||||
return 1
|
||||
}
|
||||
if err := b.loadRuntimeConfig(ctx); err != nil {
|
||||
b.log.Error("runtime settings unavailable", "err", err)
|
||||
return 1
|
||||
}
|
||||
if err := b.startWorkflowExecutionSettings(ctx); err != nil {
|
||||
b.log.Error("workflow execution settings unavailable", "err", err)
|
||||
if err := b.startLiveSettings(ctx); err != nil {
|
||||
b.log.Error("live settings unavailable", "err", err)
|
||||
return 1
|
||||
}
|
||||
go b.applyStatus.Run(ctx)
|
||||
@@ -494,7 +483,11 @@ func (s curatorEventSink) Emit(kind, detail string, data map[string]any) {
|
||||
// declared set is converted to a runnable core.ToolSet rather than a
|
||||
// parallel catalogue.
|
||||
type curatorLLMRunner struct {
|
||||
rt *runtime.Runtime
|
||||
// llm resolves the runtime at each call, so a live model-settings update
|
||||
// that swaps it wholesale is the one the next curator run reads; a
|
||||
// snapshot taken at construction would keep curators on the providers
|
||||
// boot started with.
|
||||
llm func() *runtime.Runtime
|
||||
// outcomes records this call for /status alongside sendChatTurn's. A
|
||||
// curator call is a model call this process made, and it does not pass
|
||||
// through sendChatTurn, so without this a daemon whose only recent model
|
||||
@@ -509,7 +502,11 @@ func (r curatorLLMRunner) Chat(ctx context.Context, req curator.ChatRequest) (cu
|
||||
// nil *runtime.Runtime panics on the first method call. A curator asking
|
||||
// for a completion on a daemon with no providers is a misconfiguration,
|
||||
// not a reason to take the process down.
|
||||
if r.rt == nil {
|
||||
if r.llm == nil {
|
||||
return curator.ChatResult{}, fmt.Errorf("curator chat: no model runtime is configured")
|
||||
}
|
||||
llm := r.llm()
|
||||
if llm == nil {
|
||||
return curator.ChatResult{}, fmt.Errorf("curator chat: no model runtime is configured")
|
||||
}
|
||||
msgs := make([]chat.Message, 0, len(req.Messages))
|
||||
@@ -521,7 +518,7 @@ func (r curatorLLMRunner) Chat(ctx context.Context, req curator.ChatRequest) (cu
|
||||
r.outcomes.record(req.Model, err)
|
||||
return curator.ChatResult{}, err
|
||||
}
|
||||
res, err := r.rt.Chat(ctx, req.Model, core.GenerateOptions{
|
||||
res, err := llm.Chat(ctx, req.Model, core.GenerateOptions{
|
||||
Messages: msgs,
|
||||
Tools: toolSet,
|
||||
MaxSteps: max(req.MaxSteps, 1),
|
||||
@@ -542,14 +539,16 @@ type chatTaskWriterAdapter struct {
|
||||
enqueue func(
|
||||
ctx context.Context,
|
||||
owner, repo, title, body, workflow, identity string,
|
||||
inputs map[string]any,
|
||||
) (*workflow.Task, error)
|
||||
}
|
||||
|
||||
func (a chatTaskWriterAdapter) EnqueueChatTask(
|
||||
ctx context.Context,
|
||||
owner, repo, title, body, workflow, identity string,
|
||||
inputs map[string]any,
|
||||
) (int64, error) {
|
||||
task, err := a.enqueue(ctx, owner, repo, title, body, workflow, identity)
|
||||
task, err := a.enqueue(ctx, owner, repo, title, body, workflow, identity, inputs)
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
@@ -560,9 +559,9 @@ func (a chatTaskWriterAdapter) EnqueueChatTask(
|
||||
}
|
||||
|
||||
type chatTaskControllerAdapter struct {
|
||||
taskByID func(context.Context, int64) (*workflow.Task, error)
|
||||
requeue func(context.Context, int64, string, string) error
|
||||
transition func(context.Context, int64, string, string, string) error
|
||||
taskByID func(context.Context, int64) (*workflow.Task, error)
|
||||
requeue func(context.Context, int64, string, string) error
|
||||
cancelExecution func(context.Context, int64, string, string) ([]int64, error)
|
||||
}
|
||||
|
||||
func (a chatTaskControllerAdapter) ChatTaskStatus(ctx context.Context, taskID int64) (gateway.ChatTaskStatus, bool, error) {
|
||||
@@ -595,12 +594,19 @@ func (a chatTaskControllerAdapter) CancelChatTask(ctx context.Context, taskID in
|
||||
return fmt.Errorf("task %d is not chat-originated", taskID)
|
||||
}
|
||||
// An operator declining work lands in the same state whichever surface
|
||||
// they used. This used to record StatusRejected while the dashboard
|
||||
// recorded StatusClosedWontDo, so the same decision showed up as two
|
||||
// different states -- and StatusRejected, which the PR reconciler uses
|
||||
// for "the pull request was closed without merging", stopped meaning one
|
||||
// thing.
|
||||
return a.transition(ctx, taskID, task.Status, workflow.StatusClosedWontDo, reason)
|
||||
// they used, through the one cancel path: the store records the
|
||||
// cancellation -- every non-terminal step of the current attempt plus the
|
||||
// execution's own move (docs/prds/execution-tree-state-machine.md) -- and
|
||||
// this write is what a late worker's next step write fails against. This
|
||||
// used to record StatusRejected while the dashboard recorded
|
||||
// StatusClosedWontDo, so the same decision showed up as two different
|
||||
// states -- and StatusRejected, which the PR reconciler uses for "the
|
||||
// pull request was closed without merging", stopped meaning one thing.
|
||||
if a.cancelExecution == nil {
|
||||
return fmt.Errorf("execution cancellation is unavailable")
|
||||
}
|
||||
_, err = a.cancelExecution(ctx, taskID, reason, workflow.StatusClosedWontDo)
|
||||
return err
|
||||
}
|
||||
|
||||
// chatTaskLogReaderAdapter gives the gateway a read view of a task's
|
||||
|
||||
@@ -567,7 +567,7 @@ func TestManualRequeueTaskRejectsOtherStatuses(t *testing.T) {
|
||||
func TestChatTaskListerAdapterReadsSQLiteIdentity(t *testing.T) {
|
||||
st := pgstore.Open(t)
|
||||
t.Cleanup(func() { _ = st.Close() })
|
||||
want, err := st.EnqueueChatTask(t.Context(), "acme", "widget", "identity task", "", "tdd", "reviewer")
|
||||
want, err := st.EnqueueChatTask(t.Context(), "acme", "widget", "identity task", "", "tdd", "reviewer", nil)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
@@ -610,13 +610,14 @@ func TestChatTaskWriterAdapter(t *testing.T) {
|
||||
enqueue: func(
|
||||
context.Context,
|
||||
string, string, string, string, string, string,
|
||||
map[string]any,
|
||||
) (*workflow.Task, error) {
|
||||
return tt.result, tt.err
|
||||
},
|
||||
}
|
||||
id, err := adapter.EnqueueChatTask(
|
||||
context.Background(),
|
||||
"owner", "repo", "title", "body", "workflow", "identity",
|
||||
"owner", "repo", "title", "body", "workflow", "identity", nil,
|
||||
)
|
||||
if (err != nil) != tt.wantErr {
|
||||
t.Fatalf("EnqueueChatTask() error = %v, wantErr %t", err, tt.wantErr)
|
||||
@@ -669,16 +670,16 @@ func TestChatTaskControllerAdapterRejectsForgeTask(t *testing.T) {
|
||||
|
||||
func TestChatTaskControllerAdapterTransitions(t *testing.T) {
|
||||
task := &workflow.Task{ID: 42, Source: workflow.SourceChat, Status: workflow.StatusWaitingHuman}
|
||||
var requeueFrom, requeueWorkflow, transitionFrom, transitionTo, transitionDetail string
|
||||
var requeueFrom, requeueWorkflow, cancelReason, cancelTo string
|
||||
adapter := chatTaskControllerAdapter{
|
||||
taskByID: func(context.Context, int64) (*workflow.Task, error) { return task, nil },
|
||||
requeue: func(_ context.Context, _ int64, from, workflow string) error {
|
||||
requeueFrom, requeueWorkflow = from, workflow
|
||||
return nil
|
||||
},
|
||||
transition: func(_ context.Context, _ int64, from, to, detail string) error {
|
||||
transitionFrom, transitionTo, transitionDetail = from, to, detail
|
||||
return nil
|
||||
cancelExecution: func(_ context.Context, _ int64, reason, to string) ([]int64, error) {
|
||||
cancelReason, cancelTo = reason, to
|
||||
return nil, nil
|
||||
},
|
||||
}
|
||||
|
||||
@@ -692,12 +693,12 @@ func TestChatTaskControllerAdapterTransitions(t *testing.T) {
|
||||
t.Fatalf("CancelChatTask(): %v", err)
|
||||
}
|
||||
// Declining from chat lands in the same state as declining from the
|
||||
// dashboard. It used to record StatusRejected, which the PR reconciler
|
||||
// also uses for "the pull request was closed without merging", so the
|
||||
// state could not tell an operator's decision from a forge outcome.
|
||||
if transitionFrom != workflow.StatusWaitingHuman || transitionTo != workflow.StatusClosedWontDo ||
|
||||
transitionDetail != "cancelled by test" {
|
||||
t.Errorf("transition = %q/%q/%q", transitionFrom, transitionTo, transitionDetail)
|
||||
// dashboard, through the one cancel path. It used to record
|
||||
// StatusRejected, which the PR reconciler also uses for "the pull
|
||||
// request was closed without merging", so the state could not tell an
|
||||
// operator's decision from a forge outcome.
|
||||
if cancelReason != "cancelled by test" || cancelTo != workflow.StatusClosedWontDo {
|
||||
t.Errorf("cancel = %q/%q", cancelReason, cancelTo)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -834,9 +835,9 @@ func TestChatTaskCommandsEndToEnd(t *testing.T) {
|
||||
profiles,
|
||||
)
|
||||
controller := gateway.NewStoreTaskController(chatTaskControllerAdapter{
|
||||
taskByID: st.TaskByID,
|
||||
requeue: st.Requeue,
|
||||
transition: st.Transition,
|
||||
taskByID: st.TaskByID,
|
||||
requeue: st.Requeue,
|
||||
cancelExecution: st.CancelExecution,
|
||||
})
|
||||
router := gateway.NewRouter(st, nil, "test")
|
||||
configureTaskCommands(router, creator, controller, chatTaskListerAdapter{tasks: st.Tasks}, defaultIdentity)
|
||||
|
||||
@@ -0,0 +1,155 @@
|
||||
package archied
|
||||
|
||||
import (
|
||||
"archive/tar"
|
||||
"bytes"
|
||||
"context"
|
||||
"go/ast"
|
||||
"go/parser"
|
||||
"go/token"
|
||||
"net"
|
||||
"testing"
|
||||
|
||||
"google.golang.org/grpc"
|
||||
"google.golang.org/grpc/credentials/insecure"
|
||||
"google.golang.org/grpc/test/bufconn"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/app/controlplane"
|
||||
"github.com/samcharles93/archie-core/internal/domain/storepkg"
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/postgres"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/postgres/pgstore"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/staterpc"
|
||||
)
|
||||
|
||||
// contributedLayer ships one workflow definition file's portable YAML.
|
||||
func contributedLayer(t *testing.T, path, yaml string) []byte {
|
||||
t.Helper()
|
||||
var raw bytes.Buffer
|
||||
writer := tar.NewWriter(&raw)
|
||||
if err := writer.WriteHeader(&tar.Header{Typeflag: tar.TypeReg, Name: path, Size: int64(len(yaml))}); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, err := writer.Write([]byte(yaml)); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if err := writer.Close(); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
return raw.Bytes()
|
||||
}
|
||||
|
||||
func packageDescriptor() storepkg.Descriptor {
|
||||
return storepkg.Descriptor{
|
||||
APIVersion: storepkg.APIVersion, DisplayName: "Review pack", Version: "1",
|
||||
Contributes: storepkg.Contributions{Workflows: []string{"workflows/review.yaml"}},
|
||||
Files: []storepkg.File{{Path: "workflows/review.yaml", Mode: 0o644}},
|
||||
}
|
||||
}
|
||||
|
||||
// TestPackageContributionsLiveRoundTrip drives the State Store's own
|
||||
// composition — the projections stateStoreDeps wires, the install and remove
|
||||
// RPCs the dashboard calls, and the workflow-definitions resource the daemon
|
||||
// reads per dispatch — over one real gRPC connection: installing a package
|
||||
// makes its workflow a usable org resource, and removing it stops being
|
||||
// usable, both without restarting anything.
|
||||
func TestPackageContributionsLiveRoundTrip(t *testing.T) {
|
||||
db := pgstore.Open(t)
|
||||
projections, err := newPackageProjections(db.Pool)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
const yaml = "id: review\nsteps:\n - type: bootstrap.apply\n"
|
||||
service := storepkg.Service{
|
||||
Registry: packageLayerRegistry{descriptor: packageDescriptor(), layer: contributedLayer(t, "workflows/review.yaml", yaml)},
|
||||
Store: postgres.NewInstalledPackages(db.Pool),
|
||||
Projections: projections,
|
||||
}
|
||||
listener := bufconn.Listen(1 << 20)
|
||||
server := grpc.NewServer()
|
||||
staterpc.RegisterServer(server, staterpc.Deps{Packages: service})
|
||||
go func() { _ = server.Serve(listener) }()
|
||||
t.Cleanup(func() { server.Stop(); _ = listener.Close() })
|
||||
conn, err := grpc.NewClient("passthrough:///state",
|
||||
grpc.WithTransportCredentials(insecure.NewCredentials()),
|
||||
grpc.WithContextDialer(func(ctx context.Context, _ string) (net.Conn, error) { return listener.DialContext(ctx) }))
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
t.Cleanup(func() { _ = conn.Close() })
|
||||
client := staterpc.NewClient(conn)
|
||||
const digest = "sha256:aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
|
||||
|
||||
if _, err := client.InstallPackage(t.Context(), "org-a", "review", "localhost:5000/review", digest); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
// The contribution is usable: the org resource the daemon's
|
||||
// WorkflowDefinitions client reads carries it now, no restart involved.
|
||||
resource, err := postgres.NewResources(db.Pool).Resource(t.Context(), "org-a", controlplane.WorkflowDefinitionsKind)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
collection, err := workflow.DecodeDefinitionCollection(resource.Value, workflow.BuiltinStepRegistry())
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, ok := collection.DefinitionByID("review"); !ok {
|
||||
t.Fatal("installed package's workflow is not an org workflow after install")
|
||||
}
|
||||
if err := client.RemoveInstalled(t.Context(), "org-a", "review"); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
resource, err = postgres.NewResources(db.Pool).Resource(t.Context(), "org-a", controlplane.WorkflowDefinitionsKind)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
collection, err = workflow.DecodeDefinitionCollection(resource.Value, workflow.BuiltinStepRegistry())
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
if _, ok := collection.DefinitionByID("review"); ok {
|
||||
t.Fatal("removed package's workflow still dispatches: the org resource kept it")
|
||||
}
|
||||
if entries, err := postgres.NewPackageContributions(db.Pool).Entries(t.Context(), "org-a", "review"); err != nil || len(entries) != 0 {
|
||||
t.Fatalf("contributions ledger after removal = %#v, %v", entries, err)
|
||||
}
|
||||
}
|
||||
|
||||
type packageLayerRegistry struct {
|
||||
descriptor storepkg.Descriptor
|
||||
layer []byte
|
||||
}
|
||||
|
||||
func (r packageLayerRegistry) Fetch(context.Context, string, string) (storepkg.Descriptor, []byte, error) {
|
||||
return r.descriptor, r.layer, nil
|
||||
}
|
||||
|
||||
// TestStateStoreDepsWiresPackageProjections pins the wiring the live round
|
||||
// trip drives: stateStoreDeps builds projections on the State Store's pool and
|
||||
// carries them into the packages service it composes.
|
||||
func TestStateStoreDepsWiresPackageProjections(t *testing.T) {
|
||||
file := "state_store.go"
|
||||
fset := token.NewFileSet()
|
||||
parsed, err := parser.ParseFile(fset, file, nil, 0)
|
||||
if err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
var calls []string
|
||||
ast.Inspect(parsed, func(node ast.Node) bool {
|
||||
if call, ok := node.(*ast.CallExpr); ok {
|
||||
if fn, ok := call.Fun.(*ast.Ident); ok {
|
||||
calls = append(calls, fn.Name)
|
||||
}
|
||||
}
|
||||
return true
|
||||
})
|
||||
found := false
|
||||
for _, call := range calls {
|
||||
if call == "newPackageProjections" {
|
||||
found = true
|
||||
}
|
||||
}
|
||||
if !found {
|
||||
t.Fatalf("stateStoreDeps (%s body) wires no package projections", file)
|
||||
}
|
||||
}
|
||||
@@ -1,364 +0,0 @@
|
||||
package archied
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"os"
|
||||
"strconv"
|
||||
"strings"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/agentexec"
|
||||
"github.com/samcharles93/archie-core/internal/app/agentworker"
|
||||
"github.com/samcharles93/archie-core/internal/config"
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow"
|
||||
"github.com/samcharles93/archie-core/internal/forge"
|
||||
"github.com/samcharles93/archie-core/internal/gateway"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/artifactsync"
|
||||
"github.com/samcharles93/archie-core/internal/worktree"
|
||||
)
|
||||
|
||||
// prReviewer implements gateway.ChatPRReviewer for the daemon. It fetches
|
||||
// an existing PR's metadata, materialises its head in a fresh clone, and runs
|
||||
// the same adversarial reviewer the workflow stage uses, all synchronously in
|
||||
// the requesting turn. Authorization is identity-scoped (the task_spawn
|
||||
// repository allow-list) and one review per PR runs at a time.
|
||||
type prReviewer struct {
|
||||
forge forge.PullRequestReader // nil = forge cannot read PRs
|
||||
trees *worktree.Manager
|
||||
models map[string]string
|
||||
providers map[string]agentexec.Provider
|
||||
maxSteps int
|
||||
// artifacts publishes the completed review to the collaborative editor.
|
||||
// nil = publishing is disabled (no [artifacts] base_url configured).
|
||||
artifacts artifactsync.Sender
|
||||
// currentMaxSteps lets the composition root apply live control-plane
|
||||
// versions to reviews that have not started yet. Tests and direct
|
||||
// constructions retain maxSteps as the fallback.
|
||||
currentMaxSteps func() int
|
||||
// allowed maps a chat identity to the "owner/name" repos it may review.
|
||||
// A nil identity is an authenticated dashboard operator, who may review
|
||||
// any configured repository.
|
||||
allowed map[string]map[string]bool
|
||||
log *slog.Logger
|
||||
|
||||
mu sync.Mutex
|
||||
inflight map[string]struct{}
|
||||
}
|
||||
|
||||
var _ gateway.ChatPRReviewer = (*prReviewer)(nil)
|
||||
|
||||
// ReviewPR fetches the PR, runs the isolated reviewer against its head, and
|
||||
// returns the structured findings. It never half-reviews: a missing forge
|
||||
// capability, an unresolvable head/base, or an absent reviewer model returns
|
||||
// an error rather than a fabricated result.
|
||||
func (r *prReviewer) ReviewPR(ctx context.Context, identity *string, repo string, number int) (gateway.PRReviewResult, error) {
|
||||
owner, name, err := splitOwnerRepo(repo)
|
||||
if err != nil {
|
||||
return gateway.PRReviewResult{}, err
|
||||
}
|
||||
if err := r.authorize(identity, owner, name); err != nil {
|
||||
return gateway.PRReviewResult{}, err
|
||||
}
|
||||
|
||||
key := owner + "/" + name + "#" + strconv.Itoa(number)
|
||||
if !r.begin(key) {
|
||||
return gateway.PRReviewResult{}, fmt.Errorf("review already in progress for %s", key)
|
||||
}
|
||||
defer r.end(key)
|
||||
|
||||
if r.forge == nil {
|
||||
return gateway.PRReviewResult{}, fmt.Errorf("forge does not support pull request review")
|
||||
}
|
||||
pr, err := r.forge.GetPullRequest(ctx, owner, name, number)
|
||||
if err != nil {
|
||||
return gateway.PRReviewResult{}, err
|
||||
}
|
||||
|
||||
model := agentworker.ReviewerModel(r.models)
|
||||
if model == "" {
|
||||
return gateway.PRReviewResult{}, fmt.Errorf("reviewer model is not configured (set models.reviewer, or models.builder as a fallback)")
|
||||
}
|
||||
reviewer := agentworker.NewOperatorReviewer(r.models, r.providers)
|
||||
if reviewer == nil {
|
||||
return gateway.PRReviewResult{}, fmt.Errorf("no provider runtime configured for the reviewer model %q", model)
|
||||
}
|
||||
if r.trees == nil {
|
||||
return gateway.PRReviewResult{}, fmt.Errorf("worktree manager is not configured")
|
||||
}
|
||||
|
||||
dir, cleanup, err := r.trees.CheckoutPR(ctx, owner, name, pr.HeadRef, pr.BaseRef)
|
||||
if err != nil {
|
||||
return gateway.PRReviewResult{}, err
|
||||
}
|
||||
defer cleanup()
|
||||
|
||||
diff, err := r.trees.Diff(ctx, dir, pr.BaseRef)
|
||||
if err != nil {
|
||||
return gateway.PRReviewResult{}, fmt.Errorf("compute PR diff: %w", err)
|
||||
}
|
||||
|
||||
snapshotDir, err := os.MkdirTemp("", "pr-review-snapshot-*")
|
||||
if err != nil {
|
||||
return gateway.PRReviewResult{}, fmt.Errorf("create review snapshot directory: %w", err)
|
||||
}
|
||||
defer os.RemoveAll(snapshotDir)
|
||||
if err := r.trees.Snapshot(ctx, dir, snapshotDir); err != nil {
|
||||
return gateway.PRReviewResult{}, fmt.Errorf("snapshot PR head: %w", err)
|
||||
}
|
||||
|
||||
maxSteps := r.maxSteps
|
||||
if r.currentMaxSteps != nil {
|
||||
maxSteps = r.currentMaxSteps()
|
||||
}
|
||||
report := reviewer.Review(ctx, workflow.ReviewRequest{
|
||||
SnapshotDir: snapshotDir,
|
||||
Diff: diff,
|
||||
IssueText: prIssueText(pr),
|
||||
MaxSteps: maxSteps,
|
||||
})
|
||||
r.logReview(key, model, report)
|
||||
|
||||
result := mapReviewResult(repo, number, model, report)
|
||||
return r.attachArtifact(ctx, result, identity, owner, name, number, report), nil
|
||||
}
|
||||
|
||||
// authorize enforces the identity-scoped repository allow-list. A nil
|
||||
// identity (dashboard operator) may review any configured repository.
|
||||
func (r *prReviewer) authorize(identity *string, owner, repo string) error {
|
||||
full := owner + "/" + repo
|
||||
if identity == nil {
|
||||
for _, set := range r.allowed {
|
||||
if set[full] {
|
||||
return nil
|
||||
}
|
||||
}
|
||||
return fmt.Errorf("repository %q is not configured", full)
|
||||
}
|
||||
set, ok := r.allowed[*identity]
|
||||
if !ok {
|
||||
return fmt.Errorf("identity %q is not configured for PR review", *identity)
|
||||
}
|
||||
if !set[full] {
|
||||
return fmt.Errorf("repository %q is not configured for this identity", full)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func (r *prReviewer) begin(key string) bool {
|
||||
r.mu.Lock()
|
||||
defer r.mu.Unlock()
|
||||
if r.inflight == nil {
|
||||
r.inflight = make(map[string]struct{})
|
||||
}
|
||||
if _, ok := r.inflight[key]; ok {
|
||||
return false
|
||||
}
|
||||
r.inflight[key] = struct{}{}
|
||||
return true
|
||||
}
|
||||
|
||||
func (r *prReviewer) end(key string) {
|
||||
r.mu.Lock()
|
||||
defer r.mu.Unlock()
|
||||
delete(r.inflight, key)
|
||||
}
|
||||
|
||||
func (r *prReviewer) logReview(key, model string, report workflow.ReviewReport) {
|
||||
if r.log == nil {
|
||||
return
|
||||
}
|
||||
blocking := 0
|
||||
for _, f := range report.Findings {
|
||||
if f.Blocking() {
|
||||
blocking++
|
||||
}
|
||||
}
|
||||
r.log.Info("operator PR review complete",
|
||||
"pr", key, "model", model, "status", string(report.Status),
|
||||
"findings", len(report.Findings), "blocking", blocking)
|
||||
}
|
||||
|
||||
// attachArtifact publishes the report when the sender is configured and
|
||||
// records the editor deep link on the result. Publishing never fails the
|
||||
// review: a failure degrades to an empty URL.
|
||||
func (r *prReviewer) attachArtifact(ctx context.Context, result gateway.PRReviewResult, identity *string, owner, name string, number int, report workflow.ReviewReport) gateway.PRReviewResult {
|
||||
result.ArtifactURL = r.publishArtifact(ctx, reviewActor(identity), owner, name, number, report)
|
||||
return result
|
||||
}
|
||||
|
||||
// reviewActor resolves the attribution: the requesting chat identity when one
|
||||
// exists, else the daemon's operator-reviewer actor.
|
||||
func reviewActor(identity *string) string {
|
||||
if identity != nil && *identity != "" {
|
||||
return *identity
|
||||
}
|
||||
return "system:pr-reviewer"
|
||||
}
|
||||
|
||||
// publishArtifact renders the report and hands it to the collaborative
|
||||
// editor when artifact publishing is configured. It returns the editor deep
|
||||
// link, or "" when publishing is disabled or failed: a publish failure is a
|
||||
// logged degradation, never an error that fails the producing review.
|
||||
func (r *prReviewer) publishArtifact(ctx context.Context, actor, owner, name string, number int, report workflow.ReviewReport) string {
|
||||
if r.artifacts == nil {
|
||||
return ""
|
||||
}
|
||||
title := fmt.Sprintf("Review of %s/%s#%d", owner, name, number)
|
||||
artifact := artifactsync.Artifact{
|
||||
Title: title,
|
||||
Source: report.RenderMarkdown(title),
|
||||
Meta: artifactsync.Meta{
|
||||
Format: "markdown",
|
||||
Category: "pr-review",
|
||||
Visibility: "account-only",
|
||||
Egress: "none",
|
||||
Actor: actor,
|
||||
Origin: "pr-review",
|
||||
RequestID: "artifact:pr-review:" + owner + "/" + name + "#" + strconv.Itoa(number),
|
||||
Version: "r1",
|
||||
SentAt: time.Now().UTC(),
|
||||
Task: &artifactsync.Task{Owner: owner, Repo: name, Number: number},
|
||||
},
|
||||
}
|
||||
url, err := r.artifacts.Publish(ctx, artifact)
|
||||
if err != nil {
|
||||
if r.log != nil {
|
||||
r.log.Warn("artifact publish failed; the review result is unaffected",
|
||||
"artifact", artifact.RequestID(), "err", err)
|
||||
}
|
||||
return ""
|
||||
}
|
||||
if r.log != nil {
|
||||
r.log.Info("artifact published", "artifact", artifact.RequestID(), "url", url)
|
||||
}
|
||||
return url
|
||||
}
|
||||
|
||||
// splitOwnerRepo splits "owner/name" with the same validation the gateway's
|
||||
// task_spawn allow-list uses.
|
||||
func splitOwnerRepo(s string) (owner, repo string, err error) {
|
||||
owner, repo, ok := strings.Cut(s, "/")
|
||||
if !ok || owner == "" || repo == "" {
|
||||
return "", "", fmt.Errorf("repository %q must be owner/name", s)
|
||||
}
|
||||
return owner, repo, nil
|
||||
}
|
||||
|
||||
// prIssueText renders the PR title/body as the review's issue text.
|
||||
func prIssueText(pr forge.PullRequest) string {
|
||||
if pr.Body == "" {
|
||||
return pr.Title
|
||||
}
|
||||
return pr.Title + "\n\n" + pr.Body
|
||||
}
|
||||
|
||||
// mapReviewResult adapts a workflow.ReviewReport into the gateway's
|
||||
// channel-neutral result shape.
|
||||
func mapReviewResult(repo string, number int, model string, report workflow.ReviewReport) gateway.PRReviewResult {
|
||||
out := gateway.PRReviewResult{
|
||||
Repo: repo,
|
||||
Number: number,
|
||||
Model: model,
|
||||
Status: string(report.Status),
|
||||
Summary: report.Summary,
|
||||
Reason: report.SkipReason,
|
||||
Findings: make([]gateway.PRReviewFinding, 0, len(report.Findings)),
|
||||
}
|
||||
for _, f := range report.Findings {
|
||||
out.Findings = append(out.Findings, gateway.PRReviewFinding{
|
||||
File: f.File,
|
||||
Line: f.Line,
|
||||
Defect: f.Defect,
|
||||
FailureScenario: f.FailureScenario,
|
||||
Verdict: string(f.Verdict),
|
||||
Level: string(f.Level),
|
||||
Category: string(f.Category),
|
||||
Blocking: f.Blocking(),
|
||||
})
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// buildReviewAllowlist derives the identity-scoped review allow-list from the
|
||||
// same profiles task_spawn uses, so a chat identity and the review command
|
||||
// agree on which repositories the identity may touch.
|
||||
func buildReviewAllowlist(cfg config.Config) map[string]map[string]bool {
|
||||
profiles, _ := chatTaskProfiles(cfg)
|
||||
out := make(map[string]map[string]bool, len(profiles))
|
||||
for _, p := range profiles {
|
||||
set := make(map[string]bool, len(p.Repos))
|
||||
for _, repo := range p.Repos {
|
||||
set[repo] = true
|
||||
}
|
||||
out[p.Identity] = set
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
// prReviewer assembles the operator-triggered review capability, or nil when
|
||||
// the forge cannot read PRs (the noop forge, or a forge with no PR read
|
||||
// support). A review tool that can never run must not be advertised, matching
|
||||
// the TaskTools nil-backend rule.
|
||||
//
|
||||
// The instance is built once and memoized on the boot struct so every channel
|
||||
// shares one in-flight set: a review of the same PR requested concurrently
|
||||
// from the Web UI and Telegram deduplicates instead of running twice.
|
||||
func (b *boot) prReviewer() gateway.ChatPRReviewer {
|
||||
if b.chatPRReviewer != nil {
|
||||
return b.chatPRReviewer
|
||||
}
|
||||
if b.trees == nil {
|
||||
return nil
|
||||
}
|
||||
forgeReader, _ := b.forgeClient.(forge.PullRequestReader)
|
||||
if forgeReader == nil {
|
||||
return nil
|
||||
}
|
||||
maxSteps := b.cfg.Budgets.MaxSteps
|
||||
if b.cfgHolder != nil {
|
||||
maxSteps = b.cfgHolder.Get().Budgets.MaxSteps
|
||||
}
|
||||
review := &prReviewer{
|
||||
forge: forgeReader,
|
||||
trees: b.trees,
|
||||
models: b.cfg.Models,
|
||||
providers: executionProviders(b.cfg),
|
||||
maxSteps: maxSteps,
|
||||
artifacts: b.artifactSender(),
|
||||
allowed: buildReviewAllowlist(b.cfg),
|
||||
log: b.log,
|
||||
}
|
||||
if b.cfgHolder != nil {
|
||||
review.currentMaxSteps = func() int { return b.cfgHolder.Get().Budgets.MaxSteps }
|
||||
}
|
||||
b.chatPRReviewer = review
|
||||
return b.chatPRReviewer
|
||||
}
|
||||
|
||||
// artifactSender builds the collaborative-editor sender when the [artifacts]
|
||||
// section configures one. An empty base_url disables publishing entirely; a
|
||||
// base_url with an unresolvable token is a missing credential, which disables
|
||||
// the capability with a loud warning rather than stopping the daemon
|
||||
// (docs/architecture/configuration.md, "A missing credential disables a
|
||||
// capability").
|
||||
func (b *boot) artifactSender() artifactsync.Sender {
|
||||
cfg := b.cfg.Artifacts
|
||||
if cfg.BaseURL == "" {
|
||||
return nil
|
||||
}
|
||||
token, err := b.secrets.Resolve(cfg.Token)
|
||||
if err != nil {
|
||||
b.log.Warn("artifact publishing disabled: the service credential could not be resolved",
|
||||
"base_url", cfg.BaseURL, "token_engine", cfg.Token.Engine, "err", err)
|
||||
return nil
|
||||
}
|
||||
if token == "" {
|
||||
b.log.Warn("artifact publishing disabled: the service token resolved empty",
|
||||
"base_url", cfg.BaseURL, "token_engine", cfg.Token.Engine)
|
||||
return nil
|
||||
}
|
||||
return artifactsync.NewClient(cfg.BaseURL, token)
|
||||
}
|
||||
@@ -1,317 +0,0 @@
|
||||
package archied
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"log/slog"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/config"
|
||||
"github.com/samcharles93/archie-core/internal/domain/workflow"
|
||||
"github.com/samcharles93/archie-core/internal/forge"
|
||||
"github.com/samcharles93/archie-core/internal/gateway"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/artifactsync"
|
||||
"github.com/samcharles93/archie-core/internal/tools"
|
||||
"github.com/samcharles93/archie-core/internal/worktree"
|
||||
)
|
||||
|
||||
func TestSplitOwnerRepo(t *testing.T) {
|
||||
tests := []struct {
|
||||
in string
|
||||
owner string
|
||||
repo string
|
||||
wantErr bool
|
||||
}{
|
||||
{"acme/widget", "acme", "widget", false},
|
||||
{"acme/widget/service", "acme", "widget/service", false},
|
||||
{"acme", "", "", true},
|
||||
{"/widget", "", "", true},
|
||||
{"acme/", "", "", true},
|
||||
{"", "", "", true},
|
||||
}
|
||||
for _, tt := range tests {
|
||||
owner, repo, err := splitOwnerRepo(tt.in)
|
||||
if tt.wantErr {
|
||||
if err == nil {
|
||||
t.Errorf("splitOwnerRepo(%q) error = nil, want error", tt.in)
|
||||
}
|
||||
continue
|
||||
}
|
||||
if err != nil {
|
||||
t.Errorf("splitOwnerRepo(%q) error = %v", tt.in, err)
|
||||
continue
|
||||
}
|
||||
if owner != tt.owner || repo != tt.repo {
|
||||
t.Errorf("splitOwnerRepo(%q) = (%q, %q), want (%q, %q)", tt.in, owner, repo, tt.owner, tt.repo)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestPRIssueText(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
pr forge.PullRequest
|
||||
want string
|
||||
}{
|
||||
{"title only", forge.PullRequest{Title: "Fix login"}, "Fix login"},
|
||||
{"title and body", forge.PullRequest{Title: "Fix login", Body: "The form 500s."}, "Fix login\n\nThe form 500s."},
|
||||
}
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
if got := prIssueText(tt.pr); got != tt.want {
|
||||
t.Errorf("prIssueText = %q, want %q", got, tt.want)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestMapReviewResult(t *testing.T) {
|
||||
report := workflow.ReviewReport{
|
||||
Status: workflow.ReviewStatusCompleted,
|
||||
Summary: "checked and cleared",
|
||||
Findings: []workflow.ReviewFinding{
|
||||
{File: "a.go", Line: 3, Defect: "nil deref", FailureScenario: "x", Verdict: workflow.ReviewVerdictConfirmed, Level: workflow.ReviewLevelError, Category: workflow.ReviewCategoryNilRisk},
|
||||
{File: "b.go", Line: 0, Defect: "style", FailureScenario: "y", Verdict: workflow.ReviewVerdictPlausible, Level: workflow.ReviewLevelWarn, Category: workflow.ReviewCategoryOther},
|
||||
},
|
||||
}
|
||||
got := mapReviewResult("acme/widget", 7, "openai/gpt-5", report)
|
||||
|
||||
if got.Repo != "acme/widget" || got.Number != 7 || got.Model != "openai/gpt-5" || got.Status != "completed" || got.Summary != "checked and cleared" {
|
||||
t.Fatalf("result meta = %+v", got)
|
||||
}
|
||||
if len(got.Findings) != 2 {
|
||||
t.Fatalf("findings = %d, want 2", len(got.Findings))
|
||||
}
|
||||
if !got.Findings[0].Blocking {
|
||||
t.Error("confirmed error finding should be blocking")
|
||||
}
|
||||
if got.Findings[1].Blocking {
|
||||
t.Error("plausible warn finding must not be blocking")
|
||||
}
|
||||
if got.Findings[0].Line != 3 {
|
||||
t.Errorf("line = %d, want 3", got.Findings[0].Line)
|
||||
}
|
||||
}
|
||||
|
||||
func TestMapReviewResultNotRunPreservesReason(t *testing.T) {
|
||||
report := workflow.NewNotRunReviewReport("no reviewer model configured")
|
||||
got := mapReviewResult("acme/widget", 7, "", report)
|
||||
if got.Status != "not_run" || got.Reason != "no reviewer model configured" {
|
||||
t.Fatalf("not_run result = %+v, want status not_run and reason preserved", got)
|
||||
}
|
||||
}
|
||||
|
||||
func TestPrReviewerAuthorize(t *testing.T) {
|
||||
r := &prReviewer{allowed: map[string]map[string]bool{
|
||||
"": {"acme/widget": true, "acme/core": true},
|
||||
"archie": {"acme/widget": true},
|
||||
}}
|
||||
archie := "archie"
|
||||
other := "other"
|
||||
|
||||
tests := []struct {
|
||||
name string
|
||||
identity *string
|
||||
owner string
|
||||
repo string
|
||||
wantErr bool
|
||||
}{
|
||||
{"identity own repo", &archie, "acme", "widget", false},
|
||||
{"identity foreign repo", &archie, "acme", "core", true},
|
||||
{"unknown identity", &other, "acme", "widget", true},
|
||||
{"operator any configured", nil, "acme", "core", false},
|
||||
{"operator unconfigured repo", nil, "acme", "other", true},
|
||||
}
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
err := r.authorize(tt.identity, tt.owner, tt.repo)
|
||||
if tt.wantErr && err == nil {
|
||||
t.Errorf("authorize(%v, %s/%s) error = nil, want error", tt.identity, tt.owner, tt.repo)
|
||||
}
|
||||
if !tt.wantErr && err != nil {
|
||||
t.Errorf("authorize(%v, %s/%s) error = %v, want nil", tt.identity, tt.owner, tt.repo, err)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestPrReviewerSingleflight(t *testing.T) {
|
||||
r := &prReviewer{}
|
||||
key := "acme/widget#7"
|
||||
if !r.begin(key) {
|
||||
t.Fatal("first begin = false, want true")
|
||||
}
|
||||
if r.begin(key) {
|
||||
t.Fatal("concurrent begin = true, want false (deterministic single-flight)")
|
||||
}
|
||||
r.end(key)
|
||||
if !r.begin(key) {
|
||||
t.Fatal("begin after end = false, want true")
|
||||
}
|
||||
}
|
||||
|
||||
func TestBuildReviewAllowlist(t *testing.T) {
|
||||
cfg := config.Config{
|
||||
Identities: []config.IdentityConfig{
|
||||
{Name: "archie", Repos: []config.Repo{{Owner: "acme", Name: "widget"}}},
|
||||
},
|
||||
}
|
||||
allowed := buildReviewAllowlist(cfg)
|
||||
|
||||
if !allowed["archie"]["acme/widget"] {
|
||||
t.Errorf("allowlist missing acme/widget for identity archie: %+v", allowed)
|
||||
}
|
||||
if allowed["archie"]["acme/core"] {
|
||||
t.Errorf("allowlist leaked acme/core to identity archie: %+v", allowed)
|
||||
}
|
||||
if _, ok := allowed["nobody"]; ok {
|
||||
t.Errorf("allowlist contains unknown identity nobody: %+v", allowed)
|
||||
}
|
||||
}
|
||||
|
||||
// reviewCapableForge satisfies both forge.Forge (via embedding) and
|
||||
// forge.PullRequestReader, so boot.prReviewer can be exercised in isolation.
|
||||
type reviewCapableForge struct {
|
||||
forge.Forge
|
||||
}
|
||||
|
||||
func (reviewCapableForge) GetPullRequest(context.Context, string, string, int) (forge.PullRequest, error) {
|
||||
return forge.PullRequest{}, nil
|
||||
}
|
||||
|
||||
// TestPrReviewerIsMemoized pins the cross-channel single-flight fix: every
|
||||
// gateway must share one prReviewer so a review of the same PR requested from
|
||||
// two channels at once deduplicates instead of running twice. The boot must
|
||||
// own a worktree manager: a reviewer without one can never run and must not be
|
||||
// produced (see TestPrReviewerNilWithoutTrees).
|
||||
func TestPrReviewerIsMemoized(t *testing.T) {
|
||||
b := &boot{
|
||||
forgeClient: reviewCapableForge{Forge: forge.NewNoop(slog.New(slog.DiscardHandler))},
|
||||
trees: &worktree.Manager{},
|
||||
}
|
||||
|
||||
first := b.prReviewer()
|
||||
if first == nil {
|
||||
t.Fatal("prReviewer() = nil, want a reviewer")
|
||||
}
|
||||
if second := b.prReviewer(); first != second {
|
||||
t.Fatal("prReviewer() returned distinct instances; channels would not share the in-flight set")
|
||||
}
|
||||
}
|
||||
|
||||
// TestPrReviewerNilWithoutTrees pins the producer-side invariant: a PR-capable
|
||||
// forge without a worktree manager must yield no reviewer. The standalone
|
||||
// Gateway never builds trees, and the daemon used to capture b.trees before it
|
||||
// was assigned, so both advertised a review_pr tool that always failed.
|
||||
func TestPrReviewerNilWithoutTrees(t *testing.T) {
|
||||
b := &boot{forgeClient: reviewCapableForge{Forge: forge.NewNoop(slog.New(slog.DiscardHandler))}}
|
||||
|
||||
if got := b.prReviewer(); got != nil {
|
||||
t.Fatalf("prReviewer() with no worktree manager = %T, want nil", got)
|
||||
}
|
||||
}
|
||||
|
||||
// TestReviewPRToolRegisteredOnlyWithWorkingReviewer composes the real boot
|
||||
// wiring (boot.prReviewer -> gateway.ReviewTools) and asserts review_pr is
|
||||
// advertised only when the reviewer can actually run.
|
||||
func TestReviewPRToolRegisteredOnlyWithWorkingReviewer(t *testing.T) {
|
||||
logger := slog.New(slog.DiscardHandler)
|
||||
b := &boot{
|
||||
forgeClient: reviewCapableForge{Forge: forge.NewNoop(logger)},
|
||||
log: logger,
|
||||
}
|
||||
|
||||
if hasReviewPRTool(gateway.ReviewTools(b.prReviewer(), "archie")) {
|
||||
t.Fatal("review_pr advertised with no worktree manager: a tool that cannot run must not be offered")
|
||||
}
|
||||
|
||||
b.trees = &worktree.Manager{}
|
||||
if !hasReviewPRTool(gateway.ReviewTools(b.prReviewer(), "archie")) {
|
||||
t.Fatal("review_pr not advertised with a worktree manager")
|
||||
}
|
||||
}
|
||||
|
||||
// hasReviewPRTool reports whether review_pr is offered. Presence is asserted by
|
||||
// name rather than by entry count: the contract is that this one capability is
|
||||
// offered only when it can run, so adding a sibling review tool must not turn
|
||||
// this red.
|
||||
func hasReviewPRTool(entries []tools.ToolEntry) bool {
|
||||
for _, e := range entries {
|
||||
if e.Name == "review_pr" {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
type fakeArtifactSender struct {
|
||||
calls int
|
||||
url string
|
||||
err error
|
||||
last artifactsync.Artifact
|
||||
}
|
||||
|
||||
func (f *fakeArtifactSender) Publish(_ context.Context, a artifactsync.Artifact) (string, error) {
|
||||
f.calls++
|
||||
f.last = a
|
||||
if f.err != nil {
|
||||
return "", f.err
|
||||
}
|
||||
return f.url, nil
|
||||
}
|
||||
|
||||
func TestPrReviewerPublishesTheCompletedReview(t *testing.T) {
|
||||
fake := &fakeArtifactSender{url: "https://offloaded.dev/collab?document=a_1"}
|
||||
r := &prReviewer{artifacts: fake, log: slog.New(slog.DiscardHandler)}
|
||||
report := workflow.NewCompletedReviewReport([]workflow.ReviewFinding{{
|
||||
File: "handler.go", Line: 42, Defect: "nil deref",
|
||||
FailureScenario: "empty payload crashes", Verdict: workflow.ReviewVerdictConfirmed,
|
||||
Level: workflow.ReviewLevelError,
|
||||
}}, "one finding")
|
||||
report.Checked = []workflow.ReviewCheck{{Property: "p", Evidence: "e"}}
|
||||
|
||||
url := r.publishArtifact(context.Background(), "system:pr-reviewer", "acme", "widget", 7, report)
|
||||
if url != fake.url {
|
||||
t.Fatalf("publishArtifact = %q, want the sender's url %q", url, fake.url)
|
||||
}
|
||||
if fake.calls != 1 {
|
||||
t.Fatalf("Publish called %d times, want 1", fake.calls)
|
||||
}
|
||||
got := fake.last
|
||||
if got.Meta.Format != "markdown" || got.Meta.Category != "pr-review" {
|
||||
t.Fatalf("format/category = %s/%s, want markdown/pr-review", got.Meta.Format, got.Meta.Category)
|
||||
}
|
||||
if got.Meta.Actor != "system:pr-reviewer" || got.Meta.Origin != "pr-review" {
|
||||
t.Fatalf("attribution = %s/%s", got.Meta.Actor, got.Meta.Origin)
|
||||
}
|
||||
if got.Meta.Visibility != "account-only" || got.Meta.Egress != "none" {
|
||||
t.Fatalf("visibility/egress = %s/%s", got.Meta.Visibility, got.Meta.Egress)
|
||||
}
|
||||
if got.Title != "Review of acme/widget#7" {
|
||||
t.Fatalf("title = %q", got.Title)
|
||||
}
|
||||
if got.Meta.RequestID != "artifact:pr-review:acme/widget#7" {
|
||||
t.Fatalf("requestId = %q, want the deterministic artifact key", got.Meta.RequestID)
|
||||
}
|
||||
if got.Meta.Task == nil || got.Meta.Task.Owner != "acme" || got.Meta.Task.Number != 7 {
|
||||
t.Fatalf("task coordinates = %+v", got.Meta.Task)
|
||||
}
|
||||
if !strings.Contains(got.Source, "## Findings") {
|
||||
t.Fatalf("source is not the rendered report:\n%s", got.Source)
|
||||
}
|
||||
}
|
||||
|
||||
func TestPrReviewerPublishDegradesOnSenderFailure(t *testing.T) {
|
||||
r := &prReviewer{artifacts: &fakeArtifactSender{err: errors.New("503 exhausted")}, log: slog.New(slog.DiscardHandler)}
|
||||
if url := r.publishArtifact(context.Background(), "system:pr-reviewer", "acme", "widget", 7, workflow.NewCompletedReviewReport(nil, "s")); url != "" {
|
||||
t.Fatalf("url = %q, want empty on a failed publish", url)
|
||||
}
|
||||
}
|
||||
|
||||
func TestPrReviewerPublishIsANoOpWithoutASender(t *testing.T) {
|
||||
r := &prReviewer{}
|
||||
if url := r.publishArtifact(context.Background(), "system:pr-reviewer", "acme", "widget", 7, workflow.NewCompletedReviewReport(nil, "s")); url != "" {
|
||||
t.Fatalf("url = %q, want empty when the sender is disabled", url)
|
||||
}
|
||||
}
|
||||
@@ -13,6 +13,7 @@ import (
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/app/controlplane"
|
||||
"github.com/samcharles93/archie-core/internal/config"
|
||||
"github.com/samcharles93/archie-core/internal/domain/storecontract"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/postgres/pgstore"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/postgres/pgtest"
|
||||
"github.com/samcharles93/archie-core/internal/secret"
|
||||
@@ -51,7 +52,7 @@ func TestStateStoreBootSeedsProviderSourceReference(t *testing.T) {
|
||||
go func() { errCh <- RunStateStore(ctx, StateStoreOptions{Config: path, Listen: "127.0.0.1:0"}) }()
|
||||
deadline := time.After(10 * time.Second)
|
||||
for {
|
||||
resource, err := store.Resource(t.Context(), controlplane.ProviderSettingsKind)
|
||||
resource, err := store.Resource(t.Context(), storecontract.DefaultOrgID, controlplane.ProviderSettingsKind)
|
||||
if err == nil {
|
||||
if strings.Contains(string(resource.Value), "ARCHIE_PROVIDER_") || !strings.Contains(string(resource.Value), ref.Key) {
|
||||
t.Fatalf("stored provider settings = %s, want source reference and no derived env name", resource.Value)
|
||||
|
||||
@@ -44,6 +44,9 @@ func (b *boot) setupReadinessProbes() {
|
||||
return pingChat(ctx, b.chat)
|
||||
}),
|
||||
}
|
||||
if b.accessProblems != nil {
|
||||
probes = append(probes, readiness.NewProblemProbe("access_policies", b.accessProblems))
|
||||
}
|
||||
b.healthRegistry = health.NewRegistry(probes...)
|
||||
}
|
||||
|
||||
|
||||
@@ -84,13 +84,13 @@ func TestSetupReadinessProbes_WiresEverySubsystem(t *testing.T) {
|
||||
}
|
||||
|
||||
report := b.healthRegistry.Run(context.Background())
|
||||
if len(report.Components) != 5 {
|
||||
t.Fatalf("components = %d, want 5: %+v", len(report.Components), report.Components)
|
||||
got := map[string]int{}
|
||||
for _, c := range report.Components {
|
||||
got[c.Name]++
|
||||
}
|
||||
want := []string{"state_db", "config", "disk", "model", "gateway"}
|
||||
for i, name := range want {
|
||||
if report.Components[i].Name != name {
|
||||
t.Fatalf("component[%d] = %q, want %q", i, report.Components[i].Name, name)
|
||||
for _, name := range []string{"state_db", "config", "disk", "model", "gateway"} {
|
||||
if got[name] != 1 {
|
||||
t.Errorf("component %q registered %d times, want 1: %+v", name, got[name], report.Components)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -117,6 +117,7 @@ var reloadableFields = map[string]bool{
|
||||
"Models": true,
|
||||
"ModelLimits": true,
|
||||
"Notify": true,
|
||||
"Review": true,
|
||||
// BotUser/BotEmail used to be poll-path only; ForTask now carries both
|
||||
// into the task snapshot as well, because the sandboxed worker builds
|
||||
// its own worktree.Manager and signs its own commits (agentworker
|
||||
@@ -148,16 +149,23 @@ var reloadableFields = map[string]bool{
|
||||
|
||||
// reloadableSubFields are sub-fields of structs that are otherwise
|
||||
// startup-built. VolumeTTL is re-read per cycle in cleanupExpiredStorage;
|
||||
// everything else in Containers (Image, MaxConcurrency,
|
||||
// MaxUptime, PullPolicy, Network) is frozen in the startup-built
|
||||
// container pool -- the dispatchers re-read MaxConcurrency but the pool
|
||||
// captures it at construction (container/pool.go:94,163), so a change
|
||||
// only partially applies and must warn requires-restart. Forge.Host is
|
||||
// carried into TaskContext by ForTask (display/link building only); the
|
||||
// forge client itself is startup-built, so Type/Token/TokenEnv stay
|
||||
// requires-restart.
|
||||
// Profiles is resolved fresh per dispatch (daemon.configFor ->
|
||||
// Containers.Profile, called from pinTaskProfile) and is also its own
|
||||
// live-applying control-plane resource (AgentProfileKind), never captured at
|
||||
// container-pool construction -- docs/prds/external-agent-harness.md
|
||||
// "Selection": a Kit profile applies without a restart. Credentials is the
|
||||
// same shape one layer down: kitrun.Launcher reads Config.Get().Containers.
|
||||
// Credentials fresh on every Launch (CredentialBindingsKind), never a slice
|
||||
// captured once when the launcher was built. Everything else in
|
||||
// Containers (Image, MaxConcurrency, MaxUptime, PullPolicy, Network) is
|
||||
// frozen in the startup-built container pool -- the dispatchers re-read
|
||||
// MaxConcurrency but the pool captures it at construction
|
||||
// (container/pool.go:94,163), so a change only partially applies and must
|
||||
// warn requires-restart. Forge.Host is carried into TaskContext by ForTask
|
||||
// (display/link building only); the forge client itself is startup-built, so
|
||||
// Type/Token/TokenEnv stay requires-restart.
|
||||
var reloadableSubFields = map[string]map[string]bool{
|
||||
"Containers": {"VolumeTTL": true},
|
||||
"Containers": {"VolumeTTL": true, "Profiles": true, "Credentials": true},
|
||||
"Forge": {"Host": true},
|
||||
// Policy is carried into TaskConfig by ForTask (config.go); MCPServers,
|
||||
// WebFetch and Minimax are not and stay requires-restart.
|
||||
|
||||
@@ -1,22 +1,18 @@
|
||||
// sd_notify.go implements systemd's sd_notify(3) protocol for archied: one
|
||||
// READY=1 when the run loop starts serving, and a WATCHDOG=1 heartbeat while
|
||||
// the run loop is demonstrably still making progress.
|
||||
// sd_notify.go wires the daemon into internal/sdnotify's implementation of
|
||||
// systemd's sd_notify(3) protocol: one READY=1 when the run loop starts
|
||||
// serving, and a WATCHDOG=1 heartbeat while the run loop is demonstrably still
|
||||
// making progress.
|
||||
//
|
||||
// The protocol is three environment variables and one datagram per state, so
|
||||
// this file speaks it directly instead of taking a module dependency: the whole
|
||||
// client is net.DialUnix plus a Write. Nothing here is fatal -- a process with
|
||||
// no NOTIFY_SOCKET (a plain terminal, Docker, a user unit without WatchdogSec)
|
||||
// sends nothing and serves exactly as before, and a socket that cannot be
|
||||
// written to is logged and ignored.
|
||||
// The protocol client and the heartbeat sampler live in internal/sdnotify
|
||||
// because archie-messaging, a separate process that cannot import this
|
||||
// package, is the next process that must be able to announce itself
|
||||
// (archie-core-g5g8). What stays here is what is the daemon's own: which
|
||||
// marker counts as progress (daemon.LastPollAt) and how long the loop may go
|
||||
// without beginning a poll pass.
|
||||
//
|
||||
// The heartbeat is deliberately not a bare ticker. A ticker fires whether or
|
||||
// not the loop it stands for is alive, so it would keep systemd satisfied while
|
||||
// the event loop was wedged -- the exact failure the watchdog exists to catch.
|
||||
// The sampler instead reads the daemon's own progress marker
|
||||
// (daemon.LastPollAt, stamped by the poll loop at the start of every pass) and
|
||||
// withholds the heartbeat once that marker is older than the loop's own poll
|
||||
// cadence. While passes keep beginning, beats flow at half of WatchdogSec; a
|
||||
// loop blocked inside a pass stops being reported as alive.
|
||||
// Nothing here is fatal -- a process with no NOTIFY_SOCKET (a plain terminal,
|
||||
// Docker, a user unit without WatchdogSec) sends nothing and serves exactly as
|
||||
// before, and a socket that cannot be written to is logged and ignored.
|
||||
//
|
||||
// Consuming the states is the unit's business: READY=1 needs Type=notify, and
|
||||
// the heartbeat needs WatchdogSec.
|
||||
@@ -25,109 +21,48 @@ package archied
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"fmt"
|
||||
"log/slog"
|
||||
"net"
|
||||
"os"
|
||||
"strconv"
|
||||
"time"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/sdnotify"
|
||||
)
|
||||
|
||||
const (
|
||||
// notifySocketEnv names the socket a manager passes to a Type=notify unit.
|
||||
notifySocketEnv = "NOTIFY_SOCKET"
|
||||
// watchdogUsecEnv carries WatchdogSec in microseconds.
|
||||
watchdogUsecEnv = "WATCHDOG_USEC"
|
||||
// watchdogPIDEnv names the process whose beats the watchdog counts.
|
||||
watchdogPIDEnv = "WATCHDOG_PID"
|
||||
|
||||
// readyState and watchdogState are the two sd_notify states archied sends.
|
||||
readyState = "READY=1"
|
||||
watchdogState = "WATCHDOG=1"
|
||||
|
||||
// watchdogHeartbeatDivisor is sd_notify(3)'s recommendation: beat at half
|
||||
// of WatchdogSec, so one missed beat is tolerated and two are not.
|
||||
watchdogHeartbeatDivisor = 2
|
||||
)
|
||||
|
||||
// notifier writes sd_notify states to the socket named in the environment. A
|
||||
// notifier with no address -- the normal case away from systemd -- sends
|
||||
// nothing and says nothing.
|
||||
type notifier struct {
|
||||
addr string
|
||||
log *slog.Logger
|
||||
}
|
||||
|
||||
// newNotifier resolves the notify socket. The address is read from the
|
||||
// environment systemd sets for the process, so systemd replaces the previous
|
||||
// unit's socket with the new one across a restart.
|
||||
func newNotifier(getenv func(string) string, log *slog.Logger) notifier {
|
||||
return notifier{addr: getenv(notifySocketEnv), log: log}
|
||||
}
|
||||
|
||||
// send delivers one state line. A failure is logged, never returned: a
|
||||
// notification is an observation about the daemon, and no observation is worth
|
||||
// refusing to serve over.
|
||||
func (n notifier) send(state string) {
|
||||
if n.addr == "" {
|
||||
return
|
||||
}
|
||||
if err := sendNotify(n.addr, state); err != nil {
|
||||
n.log.Warn("systemd notify failed", "state", state, "socket", n.addr, "err", err)
|
||||
}
|
||||
}
|
||||
|
||||
// sendNotify writes one state datagram to a unixgram socket. sd_notify(3) is
|
||||
// one datagram per state, so each send dials afresh: a manager restart recreates
|
||||
// its socket, and a connection cached across one would fail every send after it.
|
||||
// A leading '@' names the Linux abstract namespace, which user managers use;
|
||||
// net.UnixAddr takes that syntax verbatim.
|
||||
func sendNotify(addr, state string) error {
|
||||
conn, err := net.DialUnix("unixgram", nil, &net.UnixAddr{Name: addr, Net: "unixgram"})
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
defer func() { _ = conn.Close() }()
|
||||
if _, err := conn.Write([]byte(state)); err != nil {
|
||||
return fmt.Errorf("write %q: %w", state, err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// announceReady tells systemd the daemon has finished starting. It is called at
|
||||
// the moment the process declares itself serving (runLoop, next to
|
||||
// healthSurface.markServing), which is the same fact READY=1 asserts: boot is
|
||||
// over and the run loop is about to take over.
|
||||
// the moment a process declares itself serving: the daemon's run loop (next to
|
||||
// healthSurface.markServing), and the serve steps of archie-gateway and
|
||||
// archie-state-store (archie-core-1174), which have health surfaces of their
|
||||
// own and would otherwise hang a Type=notify unit until TimeoutStartSec while
|
||||
// perfectly healthy.
|
||||
func (b *boot) announceReady() {
|
||||
newNotifier(os.Getenv, b.log).send(readyState)
|
||||
sdnotify.Ready(b.log)
|
||||
}
|
||||
|
||||
// startWatchdog arms the heartbeat sampler for the daemon's run loop. It does
|
||||
// nothing unless a manager named a notify socket and asked for a watchdog
|
||||
// (WATCHDOG_USEC), so every deployment without systemd is unaffected.
|
||||
func (b *boot) startWatchdog(ctx context.Context) {
|
||||
n := newNotifier(os.Getenv, b.log)
|
||||
if n.addr == "" {
|
||||
n := sdnotify.New(os.Getenv, b.log)
|
||||
if !n.Enabled() {
|
||||
return
|
||||
}
|
||||
interval, ok := watchdogHeartbeat(os.Getenv, os.Getpid(), b.log)
|
||||
interval, ok := sdnotify.Heartbeat(os.Getenv, os.Getpid(), b.log)
|
||||
if !ok {
|
||||
return
|
||||
}
|
||||
|
||||
sampler := loopWatchdog{
|
||||
interval: interval,
|
||||
cadence: b.loopCadence,
|
||||
progress: b.d.LastPollAt,
|
||||
beat: func() { n.send(watchdogState) },
|
||||
log: b.log,
|
||||
sampler := sdnotify.Watchdog{
|
||||
Interval: interval,
|
||||
Cadence: b.loopCadence,
|
||||
Progress: b.d.LastPollAt,
|
||||
Beat: func() { n.Send(sdnotify.WatchdogState) },
|
||||
Log: b.log,
|
||||
}
|
||||
b.log.Info("systemd watchdog armed",
|
||||
"heartbeat", interval.String(),
|
||||
"loop_cadence", b.loopCadence().String())
|
||||
|
||||
go func() {
|
||||
if err := sampler.run(ctx); err != nil && !errors.Is(err, context.Canceled) {
|
||||
if err := sampler.Run(ctx); err != nil && !errors.Is(err, context.Canceled) {
|
||||
b.log.Error("systemd watchdog stopped", "err", err)
|
||||
}
|
||||
}()
|
||||
@@ -152,86 +87,3 @@ func (b *boot) loopCadence() time.Duration {
|
||||
}
|
||||
return cadence
|
||||
}
|
||||
|
||||
// watchdogHeartbeat reads systemd's watchdog contract and returns the heartbeat
|
||||
// cadence, which is half of WatchdogSec. ok is false when systemd asked for no
|
||||
// watchdog, and also when it asked for one from a different process:
|
||||
// WATCHDOG_PID names the process whose beats count, so a unit watching another
|
||||
// process must not have this one beating on its behalf.
|
||||
func watchdogHeartbeat(getenv func(string) string, pid int, log *slog.Logger) (time.Duration, bool) {
|
||||
raw := getenv(watchdogUsecEnv)
|
||||
if raw == "" {
|
||||
return 0, false
|
||||
}
|
||||
if rawPID := getenv(watchdogPIDEnv); rawPID != "" {
|
||||
wantPID, err := strconv.Atoi(rawPID)
|
||||
if err != nil || wantPID != pid {
|
||||
log.Warn("systemd watchdog disabled: WATCHDOG_PID is not this process",
|
||||
"watchdog_pid", rawPID, "pid", pid, "err", err)
|
||||
return 0, false
|
||||
}
|
||||
}
|
||||
watchdog, err := time.ParseDuration(raw + "us")
|
||||
if err != nil || watchdog <= 0 {
|
||||
log.Warn("systemd watchdog disabled: WATCHDOG_USEC unreadable", "value", raw, "err", err)
|
||||
return 0, false
|
||||
}
|
||||
return watchdog / watchdogHeartbeatDivisor, true
|
||||
}
|
||||
|
||||
// loopWatchdog samples the run loop's progress marker and emits the watchdog
|
||||
// heartbeat only while that marker is fresh. Sampling is periodic; the beat is
|
||||
// not, because it is licensed by the marker rather than by the clock.
|
||||
type loopWatchdog struct {
|
||||
// interval is the sampling cadence: half of systemd's WatchdogSec.
|
||||
interval time.Duration
|
||||
// cadence reports how long the loop may go between poll passes.
|
||||
cadence func() time.Duration
|
||||
// progress reports the start of the loop's most recent poll pass, or the
|
||||
// zero time when no pass has begun yet.
|
||||
progress func() time.Time
|
||||
// beat emits one WATCHDOG=1.
|
||||
beat func()
|
||||
log *slog.Logger
|
||||
}
|
||||
|
||||
// run samples until ctx ends. It returns ctx.Err() on shutdown, which is the
|
||||
// only way out: this sampler never gives up on its own, because a sampler that
|
||||
// stopped would leave systemd watching a process nothing reports for.
|
||||
func (w loopWatchdog) run(ctx context.Context) error {
|
||||
armedAt := time.Now()
|
||||
stalled := false
|
||||
ticker := time.NewTicker(w.interval)
|
||||
defer ticker.Stop()
|
||||
|
||||
for {
|
||||
select {
|
||||
case <-ctx.Done():
|
||||
return ctx.Err()
|
||||
case <-ticker.C:
|
||||
}
|
||||
|
||||
last := w.progress()
|
||||
if last.IsZero() {
|
||||
// No pass has begun at all. Measure staleness from arming, so a
|
||||
// loop that never starts polling is caught like one that stopped.
|
||||
last = armedAt
|
||||
}
|
||||
cadence := w.cadence()
|
||||
switch age := time.Since(last); {
|
||||
case age > cadence:
|
||||
if !stalled {
|
||||
w.log.Warn("systemd watchdog: run loop has not begun a poll pass within its interval; withholding the heartbeat until it does",
|
||||
"stale_for", age.String(), "loop_cadence", cadence.String())
|
||||
stalled = true
|
||||
}
|
||||
default:
|
||||
if stalled {
|
||||
w.log.Info("systemd watchdog: run loop resumed; heartbeats resumed",
|
||||
"last_pass_age", age.String())
|
||||
stalled = false
|
||||
}
|
||||
w.beat()
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -17,8 +17,17 @@ import (
|
||||
"github.com/samcharles93/archie-core/internal/config"
|
||||
"github.com/samcharles93/archie-core/internal/daemon"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/postgres/pgstore"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/postgres/pgtest"
|
||||
"github.com/samcharles93/archie-core/internal/sdnotify"
|
||||
)
|
||||
|
||||
// The protocol-level properties of the notify client -- the '@' address form,
|
||||
// the disabled and unusable socket contract, and the half-of-WatchdogSec
|
||||
// heartbeat -- are pinned in internal/sdnotify, where the client now lives.
|
||||
// These tests pin what is the daemon's: that its three serving entry points
|
||||
// announce, that the sampler samples daemon.LastPollAt, and that the whole
|
||||
// path stays silent and harmless without a NOTIFY_SOCKET.
|
||||
|
||||
// notifyRecorder captures every record at every level. The other recording
|
||||
// handler in this package keeps warnings only; these tests need "this path
|
||||
// logged nothing at all" as positive evidence that a disabled notifier stayed
|
||||
@@ -48,6 +57,7 @@ func (h *notifyRecorder) all() []slog.Record {
|
||||
return append([]slog.Record(nil), h.records...)
|
||||
}
|
||||
|
||||
// at returns the captured records at one level.
|
||||
func (h *notifyRecorder) at(level slog.Level) []slog.Record {
|
||||
h.mu.Lock()
|
||||
defer h.mu.Unlock()
|
||||
@@ -82,7 +92,7 @@ func listenNotify(t *testing.T, addr string) *notifyListener {
|
||||
t.Fatalf("listen for notify datagrams at %q: %v", addr, err)
|
||||
}
|
||||
t.Cleanup(func() { _ = conn.Close() })
|
||||
t.Setenv(notifySocketEnv, addr)
|
||||
t.Setenv(sdnotify.NotifySocketEnv, addr)
|
||||
return ¬ifyListener{conn: conn}
|
||||
}
|
||||
|
||||
@@ -119,6 +129,28 @@ func countState(states []string, want string) int {
|
||||
return n
|
||||
}
|
||||
|
||||
// waitForState reads datagrams until one carries want or the window closes.
|
||||
// The states drain above collects a window's worth; a boot-path test waiting
|
||||
// for one state returns as soon as it arrives.
|
||||
func (l *notifyListener) waitForState(t *testing.T, window time.Duration, want string) bool {
|
||||
t.Helper()
|
||||
deadline := time.Now().Add(window)
|
||||
buf := make([]byte, 1024)
|
||||
for time.Now().Before(deadline) {
|
||||
if err := l.conn.SetReadDeadline(time.Now().Add(50 * time.Millisecond)); err != nil {
|
||||
t.Fatalf("set notify read deadline: %v", err)
|
||||
}
|
||||
n, _, err := l.conn.ReadFromUnix(buf)
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
if string(buf[:n]) == want {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// newNotifyTestBoot builds the composition the notify path reads: a boot whose
|
||||
// config holder supplies the run loop's poll cadence, and a real daemon whose
|
||||
// own poll loop stamps the progress marker the heartbeat sampler samples.
|
||||
@@ -151,93 +183,12 @@ func pollPasses(ctx context.Context, d *daemon.Daemon, on *atomic.Bool, every ti
|
||||
}
|
||||
}
|
||||
|
||||
// TestNotifyReachesAbstractSocket pins the '@' address form. systemd is not
|
||||
// restricted to filesystem paths, and a client that stripped the prefix would
|
||||
// connect to a file that does not exist instead of the abstract namespace.
|
||||
func TestNotifyReachesAbstractSocket(t *testing.T) {
|
||||
listener := listenNotify(t, fmt.Sprintf("@archie-notify-test-%d", os.Getpid()))
|
||||
|
||||
(&boot{log: slog.New(slog.DiscardHandler)}).announceReady()
|
||||
|
||||
if states := listener.states(t, 300*time.Millisecond); !slices.Contains(states, readyState) {
|
||||
t.Errorf("states received = %v, want %q among them", states, readyState)
|
||||
}
|
||||
}
|
||||
|
||||
// TestNotifierDisabledIsSilentAndUnusableSocketWarns pins the two ends of the
|
||||
// delivery contract: no socket means nothing is attempted and nothing is said,
|
||||
// while a socket that cannot be written to is reported once and then ignored.
|
||||
// Neither may ever be fatal.
|
||||
func TestNotifierDisabledIsSilentAndUnusableSocketWarns(t *testing.T) {
|
||||
rec := ¬ifyRecorder{}
|
||||
log := slog.New(rec)
|
||||
|
||||
newNotifier(func(string) string { return "" }, log).send(readyState)
|
||||
if got := rec.all(); len(got) != 0 {
|
||||
t.Errorf("a notifier with no socket logged %d records, want none: %v", len(got), got)
|
||||
}
|
||||
|
||||
missing := filepath.Join(t.TempDir(), "absent", "n.sock")
|
||||
newNotifier(func(string) string { return missing }, log).send(readyState)
|
||||
warns := rec.at(slog.LevelWarn)
|
||||
if len(warns) != 1 {
|
||||
t.Fatalf("sends to an unusable socket logged %d warnings, want exactly 1", len(warns))
|
||||
}
|
||||
if errs := rec.at(slog.LevelError); len(errs) != 0 {
|
||||
t.Errorf("sends to an unusable socket logged %d errors, want none", len(errs))
|
||||
}
|
||||
}
|
||||
|
||||
// TestWatchdogHeartbeatInterval pins the interval convention: systemd passes
|
||||
// WatchdogSec as WATCHDOG_USEC and sd_notify(3) heartbeats at half of it, and
|
||||
// WATCHDOG_PID names the process whose beats count.
|
||||
func TestWatchdogHeartbeatInterval(t *testing.T) {
|
||||
const self = 42
|
||||
tests := []struct {
|
||||
name string
|
||||
usec string
|
||||
pidEnv string
|
||||
want time.Duration
|
||||
wantOK bool
|
||||
}{
|
||||
{name: "no watchdog requested", wantOK: false},
|
||||
{name: "half of a 30s watchdog", usec: "30000000", want: 15 * time.Second, wantOK: true},
|
||||
{name: "sub-second watchdog", usec: "20000", want: 10 * time.Millisecond, wantOK: true},
|
||||
{name: "unparseable", usec: "soon", wantOK: false},
|
||||
{name: "zero", usec: "0", wantOK: false},
|
||||
{name: "negative", usec: "-1", wantOK: false},
|
||||
{name: "watchdog pid is this process", usec: "20000", pidEnv: "42", want: 10 * time.Millisecond, wantOK: true},
|
||||
{name: "watchdog pid is another process", usec: "20000", pidEnv: "7", wantOK: false},
|
||||
{name: "watchdog pid is unreadable", usec: "20000", pidEnv: "seven", wantOK: false},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
getenv := func(key string) string {
|
||||
switch key {
|
||||
case watchdogUsecEnv:
|
||||
return tt.usec
|
||||
case watchdogPIDEnv:
|
||||
return tt.pidEnv
|
||||
default:
|
||||
return ""
|
||||
}
|
||||
}
|
||||
got, ok := watchdogHeartbeat(getenv, self, slog.New(slog.DiscardHandler))
|
||||
if ok != tt.wantOK || got != tt.want {
|
||||
t.Errorf("watchdogHeartbeat(usec=%q, pid=%q) = %v, %v; want %v, %v",
|
||||
tt.usec, tt.pidEnv, got, ok, tt.want, tt.wantOK)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
// TestNotifyReadyAndWatchdogHeartbeat is the run-loop path end to end: a real
|
||||
// NOTIFY_SOCKET, the daemon's own boot path announcing READY, and the run
|
||||
// loop's own progress marker producing WATCHDOG heartbeats.
|
||||
func TestNotifyReadyAndWatchdogHeartbeat(t *testing.T) {
|
||||
listener := newNotifyListener(t)
|
||||
t.Setenv(watchdogUsecEnv, "20000") // 20ms watchdog: heartbeat every 10ms
|
||||
t.Setenv(sdnotify.WatchdogUsecEnv, "20000") // 20ms watchdog: heartbeat every 10ms
|
||||
|
||||
b, d := newNotifyTestBoot(t, 50*time.Millisecond)
|
||||
ctx, cancel := context.WithCancel(t.Context())
|
||||
@@ -251,11 +202,11 @@ func TestNotifyReadyAndWatchdogHeartbeat(t *testing.T) {
|
||||
b.startWatchdog(ctx)
|
||||
|
||||
states := listener.states(t, 300*time.Millisecond)
|
||||
if !slices.Contains(states, readyState) {
|
||||
t.Errorf("states received = %v, want %q among them", states, readyState)
|
||||
if !slices.Contains(states, sdnotify.ReadyState) {
|
||||
t.Errorf("states received = %v, want %q among them", states, sdnotify.ReadyState)
|
||||
}
|
||||
if countState(states, watchdogState) == 0 {
|
||||
t.Errorf("states received = %v, want at least one %q among them", states, watchdogState)
|
||||
if countState(states, sdnotify.WatchdogState) == 0 {
|
||||
t.Errorf("states received = %v, want at least one %q among them", states, sdnotify.WatchdogState)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -265,7 +216,7 @@ func TestNotifyReadyAndWatchdogHeartbeat(t *testing.T) {
|
||||
// kept alive by an independent ticker.
|
||||
func TestWatchdogWithholdsHeartbeatWhenRunLoopStalls(t *testing.T) {
|
||||
listener := newNotifyListener(t)
|
||||
t.Setenv(watchdogUsecEnv, "20000") // 20ms watchdog: heartbeat every 10ms
|
||||
t.Setenv(sdnotify.WatchdogUsecEnv, "20000") // 20ms watchdog: heartbeat every 10ms
|
||||
|
||||
const cadence = 50 * time.Millisecond
|
||||
b, d := newNotifyTestBoot(t, cadence)
|
||||
@@ -277,7 +228,7 @@ func TestWatchdogWithholdsHeartbeatWhenRunLoopStalls(t *testing.T) {
|
||||
go pollPasses(ctx, d, &polling, 5*time.Millisecond)
|
||||
|
||||
b.startWatchdog(ctx)
|
||||
if beats := countState(listener.states(t, 200*time.Millisecond), watchdogState); beats == 0 {
|
||||
if beats := countState(listener.states(t, 200*time.Millisecond), sdnotify.WatchdogState); beats == 0 {
|
||||
t.Fatal("no WATCHDOG=1 within 200ms while the run loop was polling")
|
||||
}
|
||||
|
||||
@@ -300,12 +251,12 @@ func TestWatchdogWithholdsHeartbeatWhenRunLoopStalls(t *testing.T) {
|
||||
// terminal, and a systemd unit with no WatchdogSec all take this path, and none
|
||||
// of them may see a datagram, a warning, or a failed start.
|
||||
func TestNotifyUnsetIsNoOp(t *testing.T) {
|
||||
t.Setenv(watchdogUsecEnv, "20000")
|
||||
t.Setenv(sdnotify.WatchdogUsecEnv, "20000")
|
||||
// t.Setenv cannot unset a variable: register the restoration first, then
|
||||
// remove it for real so "unset" means unset.
|
||||
t.Setenv(notifySocketEnv, "")
|
||||
if err := os.Unsetenv(notifySocketEnv); err != nil {
|
||||
t.Fatalf("unset %s: %v", notifySocketEnv, err)
|
||||
t.Setenv(sdnotify.NotifySocketEnv, "")
|
||||
if err := os.Unsetenv(sdnotify.NotifySocketEnv); err != nil {
|
||||
t.Fatalf("unset %s: %v", sdnotify.NotifySocketEnv, err)
|
||||
}
|
||||
|
||||
rec := ¬ifyRecorder{}
|
||||
@@ -326,8 +277,8 @@ func TestNotifyUnsetIsNoOp(t *testing.T) {
|
||||
// would be a regression on every deployment that has no systemd at all.
|
||||
func TestNotifySocketFailureIsNotFatal(t *testing.T) {
|
||||
missing := filepath.Join(t.TempDir(), "absent", "n.sock")
|
||||
t.Setenv(notifySocketEnv, missing)
|
||||
t.Setenv(watchdogUsecEnv, "20000")
|
||||
t.Setenv(sdnotify.NotifySocketEnv, missing)
|
||||
t.Setenv(sdnotify.WatchdogUsecEnv, "20000")
|
||||
|
||||
rec := ¬ifyRecorder{}
|
||||
b, d := newNotifyTestBoot(t, 50*time.Millisecond)
|
||||
@@ -363,3 +314,36 @@ func TestNotifySocketFailureIsNotFatal(t *testing.T) {
|
||||
t.Errorf("an unusable notify socket logged %d errors, want none: %v", len(errs), errs)
|
||||
}
|
||||
}
|
||||
|
||||
// TestStateStoreBootAnnouncesReady: archie-state-store run as a Type=notify
|
||||
// unit must send READY=1 once its boot is over and it is serving the contract,
|
||||
// or systemd kills a healthy process once TimeoutStartSec expires
|
||||
// (archie-core-1174). The real RunStateStore composition drives it, over a
|
||||
// real State Store database, the way the provider-seeding boot test does.
|
||||
func TestStateStoreBootAnnouncesReady(t *testing.T) {
|
||||
listener := newNotifyListener(t)
|
||||
url := pgtest.URL(t)
|
||||
path := filepath.Join(t.TempDir(), "config.toml")
|
||||
body := fmt.Sprintf("bot_user = 'archie'\ndatabase_url = %q\n", url)
|
||||
if err := os.WriteFile(path, []byte(body), 0o600); err != nil {
|
||||
t.Fatal(err)
|
||||
}
|
||||
ctx, cancel := context.WithCancel(t.Context())
|
||||
defer cancel()
|
||||
errCh := make(chan error, 1)
|
||||
go func() { errCh <- RunStateStore(ctx, StateStoreOptions{Config: path, Listen: "127.0.0.1:0"}) }()
|
||||
|
||||
if !listener.waitForState(t, 15*time.Second, sdnotify.ReadyState) {
|
||||
select {
|
||||
case bootErr := <-errCh:
|
||||
t.Fatalf("RunStateStore exited before announcing ready: %v", bootErr)
|
||||
default:
|
||||
t.Fatal("no READY=1 datagram within 15s of boot")
|
||||
}
|
||||
}
|
||||
|
||||
cancel()
|
||||
if err := <-errCh; err != nil && !errors.Is(err, context.Canceled) {
|
||||
t.Fatalf("RunStateStore shutdown: %v", err)
|
||||
}
|
||||
}
|
||||
@@ -17,15 +17,22 @@ import (
|
||||
"net/http"
|
||||
"time"
|
||||
|
||||
"github.com/jackc/pgx/v5/pgxpool"
|
||||
"google.golang.org/grpc"
|
||||
|
||||
"github.com/samcharles93/archie-core/internal/app/controlplane"
|
||||
"github.com/samcharles93/archie-core/internal/config"
|
||||
"github.com/samcharles93/archie-core/internal/domain/access"
|
||||
"github.com/samcharles93/archie-core/internal/domain/health"
|
||||
"github.com/samcharles93/archie-core/internal/domain/identity"
|
||||
"github.com/samcharles93/archie-core/internal/domain/org"
|
||||
"github.com/samcharles93/archie-core/internal/domain/storecontract"
|
||||
"github.com/samcharles93/archie-core/internal/domain/storepkg"
|
||||
infraaccess "github.com/samcharles93/archie-core/internal/infrastructure/access"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/postgres"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/readiness"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/staterpc"
|
||||
registry "github.com/samcharles93/archie-core/internal/infrastructure/storepkg"
|
||||
)
|
||||
|
||||
func configuredIdentityNames(cfg config.Config) []string {
|
||||
@@ -66,7 +73,7 @@ type StateStoreOptions struct {
|
||||
// The conversation store belongs to the separate archie-gateway process. The
|
||||
// store service owns its own DB lifecycle, so
|
||||
// b.cleanup() is the sole owner closing b.st here (in-process owner).
|
||||
func RunStateStore(ctx context.Context, options StateStoreOptions) error {
|
||||
func RunStateStore(ctx context.Context, options StateStoreOptions) error { //nolint:cyclop // the composition root's setup sequence is deliberately flat and sequential
|
||||
b := newBootstrap()
|
||||
defer b.cleanup()
|
||||
if err := b.loadConfig(ctx, options.Config, options.Overlay); err != nil {
|
||||
@@ -90,12 +97,26 @@ func RunStateStore(ctx context.Context, options StateStoreOptions) error {
|
||||
if err := identityStore.BootstrapIdentities(ctx, legacyNames); err != nil {
|
||||
return fmt.Errorf("bootstrap identities: %w", err)
|
||||
}
|
||||
// The resumable default org/workspace upgrade runs before this process
|
||||
// serves anything: the State Store refuses scoped calls until its upgrade
|
||||
// has finished, rather than serving records with no org
|
||||
// (docs/prds/orgs-and-access.md, "Upgrading existing installs"). A store
|
||||
// without the upgrader is one that owns no tenant boundary yet, so the
|
||||
// absence degrades to "no upgrade" rather than aborting boot.
|
||||
if upgrader, ok := b.st.(org.Upgrader); ok {
|
||||
if err := upgrader.UpgradeDefaultOrg(ctx); err != nil {
|
||||
return fmt.Errorf("upgrade default org: %w", err)
|
||||
}
|
||||
}
|
||||
if err := b.seedAndValidatePolicies(ctx); err != nil {
|
||||
return err
|
||||
}
|
||||
// The validating side's control plane, built here at the composition root
|
||||
// before the first definition is read or replaced.
|
||||
resources, ok := b.st.(controlplane.ResourceStore)
|
||||
if !ok {
|
||||
return fmt.Errorf("state store does not support control-plane resources")
|
||||
}
|
||||
// The validating side's control plane, built here at the composition root
|
||||
// before the first definition is read or replaced.
|
||||
control, err := openStateStoreControlPlane(resources)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -126,12 +147,66 @@ func RunStateStore(ctx context.Context, options StateStoreOptions) error {
|
||||
if err := b.startOptionalSurfaces(ctx, options); err != nil {
|
||||
return err
|
||||
}
|
||||
// Boot is over and every listener this process serves is bound: the gRPC
|
||||
// contract below and, when -ready-addr asked for one, the readiness HTTP
|
||||
// surface. systemd's READY=1 asserts the same fact, so the announcement
|
||||
// goes out here rather than from a second notion of "started"
|
||||
// (archie-core-1174). Not earlier: a readiness surface that fails to bind
|
||||
// fails the boot, and READY must not precede it. Not later: Serve begins
|
||||
// accepting the moment it is called.
|
||||
b.announceReady()
|
||||
|
||||
deps := b.stateStoreDeps(grants)
|
||||
deps.ControlPlane = control
|
||||
return serveStateStore(ctx, listener, deps, opts)
|
||||
}
|
||||
|
||||
// seedAndValidatePolicies seeds the shipped role policies for every org
|
||||
// that lacks them, grants the agent identities their org's shipped developer
|
||||
// role, and re-validates every stored policy this process serves
|
||||
// (docs/prds/orgs-and-access.md, "Storing and changing policies" and
|
||||
// "Roles"). An invalid org, workspace or object policy is logged here and
|
||||
// named as a problem by the engines the consumers build; an invalid instance
|
||||
// policy fails this boot -- the store stops serving until it is fixed. A
|
||||
// store without the access surfaces degrades: there is no chain to seed.
|
||||
func (b *boot) seedAndValidatePolicies(ctx context.Context) error {
|
||||
policies, ok := b.st.(access.PolicyStore)
|
||||
if !ok {
|
||||
return nil
|
||||
}
|
||||
if agents, ok := b.st.(interface {
|
||||
EnsureAgentOrgMembership(context.Context) error
|
||||
}); ok {
|
||||
if err := agents.EnsureAgentOrgMembership(ctx); err != nil {
|
||||
return fmt.Errorf("grant agent org membership: %w", err)
|
||||
}
|
||||
}
|
||||
if orgs, ok := b.st.(org.Repository); ok {
|
||||
list, err := orgs.ListOrgs(ctx)
|
||||
if err != nil {
|
||||
return fmt.Errorf("list orgs for policy seeding: %w", err)
|
||||
}
|
||||
for _, o := range list {
|
||||
if err := policies.EnsureShippedOrgPolicies(ctx, o.ID); err != nil {
|
||||
return fmt.Errorf("seed shipped org policies for %s: %w", o.ID, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
stored, err := policies.ListPolicies(ctx)
|
||||
if err != nil {
|
||||
return fmt.Errorf("load stored policies: %w", err)
|
||||
}
|
||||
engine, err := infraaccess.New(stored)
|
||||
if err != nil {
|
||||
return fmt.Errorf("validate stored policies: %w", err)
|
||||
}
|
||||
for _, problem := range engine.Problems() {
|
||||
b.log.Error("stored access policy is invalid and denies its level",
|
||||
"policy", problem.Policy.ID, "level", problem.Policy.Level, "err", problem.Err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// reportUnseededResources logs every kind ImportConfig could not seed.
|
||||
//
|
||||
// Reported, not fatal: a stale TOML value in a setting the database owns must
|
||||
@@ -214,6 +289,22 @@ func (b *boot) openStateStore(ctx context.Context) error {
|
||||
// degrades that group rather than aborting boot.
|
||||
func (b *boot) stateStoreDeps(grants *staterpc.TaskGrants) staterpc.Deps {
|
||||
deps := staterpc.Deps{Tasks: b.st, Log: b.log, Grants: grants}
|
||||
if b.pg != nil {
|
||||
packages := storepkg.Service{
|
||||
Registry: registry.LocalRegistry{},
|
||||
Store: postgres.NewInstalledPackages(b.pg),
|
||||
}
|
||||
// A projection failure degrades the org resources a package would have
|
||||
// contributed to, the way a group above degrades: the State Store boots
|
||||
// and reports, rather than refusing to serve the task tables.
|
||||
projections, err := newPackageProjections(b.pg)
|
||||
if err != nil {
|
||||
b.log.Error("build package projections", "err", err)
|
||||
} else {
|
||||
packages.Projections = projections
|
||||
}
|
||||
deps.Packages = packages
|
||||
}
|
||||
if identities, ok := b.st.(identity.Repository); ok {
|
||||
deps.Identities = identities
|
||||
}
|
||||
@@ -250,6 +341,10 @@ func (b *boot) stateStoreDeps(grants *staterpc.TaskGrants) staterpc.Deps {
|
||||
deps.EventTypes = b.eda
|
||||
deps.Sources = b.eda
|
||||
deps.MappingMatches = b.eda
|
||||
// HarnessSecrets rides the same encrypted-at-rest store as source
|
||||
// webhook secrets (docs/prds/binding-secret-encryption.md), under its
|
||||
// own domain separator (bindingcipher.HarnessSecretDomain).
|
||||
deps.HarnessSecrets = b.eda
|
||||
}
|
||||
// tool_call events project into the tool_calls collection on the same
|
||||
// event-capture store: this process legitimately owns both, so the
|
||||
@@ -263,6 +358,8 @@ func (b *boot) stateStoreDeps(grants *staterpc.TaskGrants) staterpc.Deps {
|
||||
if btc, ok := b.st.(storecontract.BindingTaskCreator); ok {
|
||||
deps.BindingTaskCreator = btc
|
||||
}
|
||||
b.executionDeps(&deps)
|
||||
b.accessDeps(&deps)
|
||||
if css, ok := b.st.(storecontract.ConfigSnapshotStore); ok {
|
||||
deps.ConfigSnapshots = css
|
||||
}
|
||||
@@ -275,6 +372,40 @@ func (b *boot) stateStoreDeps(grants *staterpc.TaskGrants) staterpc.Deps {
|
||||
return deps
|
||||
}
|
||||
|
||||
// executionDeps wires the execution-tree surfaces (workflow calls, step
|
||||
// recording/reading, cancellation) from the same store, degrading each one
|
||||
// independently the store lacks it rather than failing the boot.
|
||||
func (b *boot) executionDeps(deps *staterpc.Deps) {
|
||||
if wc, ok := b.st.(storecontract.WorkflowCaller); ok {
|
||||
deps.WorkflowCalls = wc
|
||||
}
|
||||
if sr, ok := b.st.(storecontract.StepRecorder); ok {
|
||||
deps.Steps = sr
|
||||
}
|
||||
if ec, ok := b.st.(storecontract.ExecutionCanceller); ok {
|
||||
deps.Canceller = ec
|
||||
}
|
||||
if sr, ok := b.st.(storecontract.StepReader); ok {
|
||||
deps.StepReader = sr
|
||||
}
|
||||
}
|
||||
|
||||
// accessDeps wires the policy chain and its denial records from the same
|
||||
// store (docs/prds/orgs-and-access.md). A store without them -- one that owns
|
||||
// no tenant boundary yet -- degrades the access RPCs rather than failing the
|
||||
// boot, the same pattern the other optional surfaces use.
|
||||
func (b *boot) accessDeps(deps *staterpc.Deps) {
|
||||
if ps, ok := b.st.(access.PrincipalSource); ok {
|
||||
deps.Principals = ps
|
||||
}
|
||||
if ps, ok := b.st.(access.PolicyStore); ok {
|
||||
deps.Policies = ps
|
||||
}
|
||||
if ds, ok := b.st.(access.DenialStore); ok {
|
||||
deps.Denials = ds
|
||||
}
|
||||
}
|
||||
|
||||
// serveStateStore registers the StateStore gRPC service and serves it until
|
||||
// ctx ends, draining in-flight calls before returning (mirroring serveGateway
|
||||
// in gateway.go, minus the gateway's session-store argument).
|
||||
@@ -374,3 +505,22 @@ func stateStoreServerOpts(listen, token string, grants *staterpc.TaskGrants) (op
|
||||
grpc.ChainStreamInterceptor(grants.StreamInterceptor(token)),
|
||||
}, false, nil
|
||||
}
|
||||
|
||||
// newPackageProjections builds the family projectors an installed package's
|
||||
// contributions apply through: workflows become org workflow definitions, the
|
||||
// one resource kind the runtime reads live today. The step vocabulary
|
||||
// (stepVocabulary) is the same one this process's control plane validates
|
||||
// dashboard edits with, so a definition the projector admits is compilable
|
||||
// where it dispatches (openStateStoreControlPlane for the pairing).
|
||||
func newPackageProjections(pool *pgxpool.Pool) (map[string]storepkg.FamilyProjector, error) {
|
||||
steps, err := stepVocabulary()
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("register workflow step vocabulary: %w", err)
|
||||
}
|
||||
workflows, err := controlplane.NewWorkflowPackageProjector(
|
||||
postgres.NewResources(pool), postgres.NewPackageContributions(pool), steps)
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("build workflow package projector: %w", err)
|
||||
}
|
||||
return map[string]storepkg.FamilyProjector{storepkg.FamilyWorkflows: workflows}, nil
|
||||
}
|
||||
@@ -17,6 +17,7 @@ type eventCaptureStore interface { //nolint:interfacebloat // composite of the s
|
||||
storecontract.PlaybookDispatcher
|
||||
storecontract.EventTypeStore
|
||||
storecontract.SourceStore
|
||||
storecontract.HarnessSecretStore
|
||||
toolCallWriter
|
||||
}
|
||||
|
||||
|
||||
@@ -30,6 +30,7 @@ import (
|
||||
pb "github.com/samcharles93/archie-core/internal/contracts/controlplane/v1"
|
||||
"github.com/samcharles93/archie-core/internal/domain/storecontract"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/configuration"
|
||||
"github.com/samcharles93/archie-core/internal/infrastructure/controlplanerpc"
|
||||
)
|
||||
|
||||
// The audit identity every offline rollback records. A rollback is one more
|
||||
@@ -135,7 +136,7 @@ func replayRevision(ctx context.Context, resources controlplane.ResourceStore, o
|
||||
if !server.Owns(options.Kind) {
|
||||
return "", fmt.Errorf("unknown resource kind %q", options.Kind)
|
||||
}
|
||||
current, err := resources.Resource(ctx, options.Kind)
|
||||
current, err := resources.Resource(ctx, storecontract.DefaultOrgID, options.Kind)
|
||||
if errors.Is(err, storecontract.ErrResourceNotFound) {
|
||||
return "", fmt.Errorf("%s has no stored value to roll back", options.Kind)
|
||||
}
|
||||
@@ -146,7 +147,7 @@ func replayRevision(ctx context.Context, resources controlplane.ResourceStore, o
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
replaced, err := server.Command(ctx, &pb.CommandRequest{
|
||||
replaced, err := server.Command(ctx, controlplanerpc.CommandRequest(ctx, &pb.CommandRequest{
|
||||
Kind: options.Kind,
|
||||
Command: "replace",
|
||||
ValueJson: revision.Value,
|
||||
@@ -154,7 +155,7 @@ func replayRevision(ctx context.Context, resources controlplane.ResourceStore, o
|
||||
Actor: OfflineRollbackActor,
|
||||
Source: OfflineRollbackSource,
|
||||
RequestId: fmt.Sprintf("recovery-rollback-%s-%d", options.Kind, time.Now().UTC().UnixNano()),
|
||||
})
|
||||
}))
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("replay %s at revision %d: %w", options.Kind, revision.Version, err)
|
||||
}
|
||||
@@ -165,7 +166,7 @@ func replayRevision(ctx context.Context, resources controlplane.ResourceStore, o
|
||||
// revisionToReplay picks the value to put back: the revision the operator
|
||||
// named, or the newest one older than the value the resource carries now.
|
||||
func revisionToReplay(ctx context.Context, st controlplane.ResourceStore, kind string, current, requested int64) (storecontract.Resource, error) {
|
||||
history, err := st.ResourceHistory(ctx, kind, 0)
|
||||
history, err := st.ResourceHistory(ctx, storecontract.DefaultOrgID, kind, 0)
|
||||
if err != nil {
|
||||
return storecontract.Resource{}, fmt.Errorf("read %s history: %w", kind, err)
|
||||
}
|
||||
|
||||
Loaded 100 of 489 files, more files were not shown because too many files have changed in this diff.
Show more
Reference in new issue
Block a user