Replace CLAUDE.md with a short decision-rule constitution; move PRDs,
architecture, development and design docs and repo skills out of the tree;
delete the docs tooling (docsgen, prdlint, docdrift, docsite, contractaudit,
reachaudit) and its gate steps; stop install.sh copying repo skills into
runtime skills.
docs/architecture is declared authoritative for settled design, so a page that
cites code which has moved actively misleads every session and every subagent
brief that reads it. Nothing in the gate compared a prose citation against the
tree: docsgen checks the contract schema against Go types, docsite checks
generated artifacts against their Markdown sources, prdlint checks PRD writing
style. All three verify internal consistency, so a page can describe a package
deleted months ago and every check stays green -- which is how a page describing
a removed system survives behind a hand-written "removed" banner.
Add tools/docdrift. It resolves every internal/... citation under docs/ against
the tree and fails on one that dangles, handling the shapes prose actually uses:
a package with a symbol (internal/config.Config), a test with its package
(internal/app/archieui/TestFoo), a file-shape template
(internal/webui/api_<concern>.go), and a Go package pattern (internal/...).
Generated artifacts are skipped so embedded page bodies are not double-counted.
The baseline is a burn-down list of the 48 citations already broken -- packages
that moved (internal/store, internal/memory, internal/nats) and ones never built
(internal/policy, the image and research capability docs). It is not a licence:
the check also fails when an allowlisted citation starts resolving again, so an
exemption cannot outlive its reason. Regenerate with `docdrift list`.
Wire it into `task check` as docs:drift.
Also correct AGENTS.md, which listed `policy` among the cross-cutting packages
sitting under internal/. No such package has ever existed in this tree; the
design is approved and unbuilt (docs/architecture/policy.md). That is exactly
the class of stale claim this check now catches.
The adversarial self-review system was removed in d73e0748, but four pages
describing it survived: the architecture page, its design-decision PRD, and the
two superseded calibration/operator PRDs. The architecture page carried a
hand-written "removed, not shipped" banner and was kept only because live PRDs
linked to it, so every reader paid for a system the tree no longer has.
Delete all four and repoint the live referrers at the authority that replaced
them (docs/prds/pr-review-agent.md): inline-review.md's Builds-on line,
pr-review-remediation.md's isolation-contract citation, pr-review-agent.md's
supersede clause, CLAUDE.md's contributor rule, and three Go comments that cited
the deleted paths. Regenerate docs/data/generated/dev-docs.json.
History stays in git; the tree stops describing a system it does not have.
ImagePull was called with empty options, so a private registry answered 401
on every pull regardless of containers.pull_policy. docker login did not help
either: it writes ~/.docker/config.json, which only the CLI reads.
Add containers.registry_auth, a SecretRef reusing the credential shape the
rest of the file uses, whose resolved value is a Docker registry.AuthConfig
JSON document. archied resolves it at boot and the pool base64url-encodes it
into the X-Registry-Auth header ImagePullOptions carries.
A missing or unresolvable credential degrades to the anonymous pull that
existed before the field (with a warning), so a deployment with no private
registry is unaffected; a half-named reference is refused by
configuration.Validate. The field is file-owned and json:"-", so the
container-runtime-policies layering has to preserve it explicitly, the way it
preserves Profiles.
docs/prds/pr-review-agent.md's own header already declared this
superseded (docs/architecture/adversarial-review.md, docs/prds/
operator-pr-review.md, docs/prds/review-calibration.md); this executes
that removal per the maintainer's explicit decision, so no reference
to the old path remains:
- internal/domain/workflow/review.go, review_findings.go,
review_report_md.go and their tests: Reviewer, ReviewRequest,
StageReview, StagePostReviewComments, ReviewReport/ReviewFinding and
friends. ReviewComment relocated into workflow.go (still used by
Forger.CreateReviewComments and the new pr-review pipeline).
- internal/app/agentworker/review.go: the ai-sdk-backed subagentReviewer.
- internal/app/archied/pr_review.go: the synchronous operator-review
path (prReviewer, gateway.ChatPRReviewer wiring). The review_pr chat
tool now self-omits (nil reviewer) until the operator trigger is
rebuilt to enqueue an async pr-review task instead of reviewing
synchronously in the chat turn.
- config.Repo.ReviewEnabled and its dashboard exposure.
- Two composition-order tests and one dashboard test that existed only
to pin the deleted path.
Also splits PRReview()'s Stage list into prReviewDecisionStages()
(phases 1-8) and stagePROutput() (phase 9), so a future caller can
splice the decision phases before a PR exists and defer posting until
after -- needed for the "archie's own PRs" trigger, not wired here: it
needs the same stage-loop-around-StageOpenPR semantics this pass
couldn't fully verify in the time available (does an Outcome-setting
stage like StageOpenPR end the compiled-workflow-definition engine the
same way it ends workflow.Run's literal loop?). Carries ScoredFinding.
Adversary through synthesis so that trigger's blocking-finding check
doesn't need to cross-reference back into the pre-synthesis slice.
Not built in this pass, left as a precise continuation (see the bead
comment): the watched-repositories and operator triggers, both blocked
on the same real question -- how a forge-reading credential reaches
PRSource's real implementation when the pr-review pipeline's Stage.Run
bodies execute inside the sandboxed archie-agent process, which holds
none today.
ListCaptures and ListUndispatchedCaptures had no callers once the client
moved to the streaming RPCs; they were kept only for mixed-version rollouts.
Binding.secret was unused since signing moved to Source; its number and
name are reserved.
One page per area: frontend UI, agent, workflows, daemon (task lifecycle and
event automation together), State Store, control plane and settings, and
processes and wiring, with merging work kept separate.
docs/development/ holds one page per kind of change (settings, State Store
and persistence, task lifecycle, workflows and steps, event automation,
dashboard, agent execution and containers, processes and wiring, merging
work), each naming every layer the change must reach and pointing at the
document that owns the design. The docs build puts them in the development
set; docs/index.md and CLAUDE.md link them.
Also adds the container-profile case to the validator agreement test, the
check the profiles work skipped.
Architecture, deployment, installer, skill and PRD text now name the Postgres
State Store, the offline recovery commands on database_url, state_dir for host
state, and db_path as the legacy-file locator for archie-state-store import.
Finalised PRDs, CHANGELOG, docs/news and docs/archive are unchanged records.
internal/infrastructure/postgres opens a pgx pool, checks server_version_num >= 180000, and applies goose migrations with a Postgres session advisory lock so processes starting together apply each migration once. internal/infrastructure/postgres/pgtest starts postgres:18 through testcontainers per test binary and gives each test its own database. Adds jackc/pgx/v5 v5.11.0, pressly/goose/v3 v3.28.0 and testcontainers-go v0.44.0. The database URL config, sqlc, the Compose service and the ownership lock move to archie-core-7r0x.2, where they have consumers.
task test runs -short with the test cache on; task test:full keeps the
uncached run. The 50s keepalive proof skips under -short (the deploy
workflow's full go test still runs it). Sleep-bound archied watch tests
run in parallel, and the read-only gate steps run concurrently after fmt
and proto:check. ui:deps is run: once so the parallel UI steps install once.
Beads sync to a Dolt remote, so anything written into one is published.
Two beads filed earlier today named an operator host, its internal
address and its filesystem paths -- the tracker was treated as a private
store, which it is not.
The rule is stated where the tracker is described, next to the existing
one about .beads/ never reaching a commit, because it is the same class:
the tracker is not a private store. Host-specific facts belong in the
operator's memos instance, which a bead may point at.
ARCHITECTURE.md duplicated the docs/architecture tree and had drifted badly
against it: "internal/ holds ~36" against 112 packages, two of the seven
binaries listed, a Forge table listing `RepliesAfter` (deleted from the tree),
and a stated invariant ("No daemon-internal cron") contradicted by the
scheduling engine that internal/app/archied/scheduling.go composes and
main.go starts.
It was also the sole home of three pieces of still-authoritative content, so
those move rather than disappear:
- plugin engine rule (strict), the memory engine family, and the
internal/plugin/architecture_test.go enforcement note ->
docs/architecture/plugins-and-extensions.md
- intake provenance: forge poll/webhook dedup through
TaskEnvelope.IdempotencyKey, binding-stamped chat/playbook enqueue, and the
single-identity webhook-intake rejection ->
docs/architecture/messaging-and-work-intake.md
Live references are repointed from CLAUDE.md (AGENTS.md is a symlink to it),
docs/architecture, docs/guides, seven PRDs, and four .agents skills. The
heading "## Plugin engine rule (strict)" is preserved in its new home so the
existing #plugin-engine-rule-strict citations keep resolving. Generated docs
artifacts regenerated.
Two rules added to the quality-gate step, both learned by getting them wrong
tonight.
The gate must gate the commit: one conditional chain, so its exit status is what
decides whether the commit runs. Written as separate statements on one command
line it is decorative, because nothing reads its status but the operator -- the
failure is discovered after it has already been pushed.
And never assert a gate result that was not just produced on that exact tree. A
commit message outlives the tree it describes and is read by people who were not
there; if the tree has moved, describe the change and let the run speak.
AGENTS.md is a symlink to this file, so the edit belongs here.
The rule belongs in CLAUDE.md, the inventory belongs in the config skill. The
skill already carried a decoded-but-unwired ledger and defines its status terms
exactly, so the entry now points at it instead of duplicating it, and the ledger
gains the live instance from 2026-09-22 (per-identity forge intake) plus the
three shapes an unwired field can take - not-consumed, not-projected, and
deliberately-not-projected, the last being UpdateCheckCommand/UpdateInstallCommand
read from base by design.
Three defects in one session landed the same way: a map field the file overlay
dropped (xrux), a field missing from the control-plane projection
(parallel_tool_calls), and per-identity forge.intake - accepted TOML that no
consumer reads, and which is not even validated. The entry names the shape,
gives the live example with file:line, and points at
docs/architecture/configuration.md as the config authority.
Red-green stays the default, but a test that cannot fail for an interesting
reason is noise in the gate rather than evidence. Tests that restate an
assignment or a constant were being written to satisfy the protocol literally.
An empty handed-over export cost a whole autonomous run this session: the tree
was reconstructed from instead, on a 131-file change with no context. An
unreadable input is a blocking fact, not a gap to fill by inference.
The Web UI and messaging channels now read and write Archie's runtime
settings through one versioned, audited control-plane API hosted on the
State Store's existing gRPC server: catalog, query, command, watch. Each
feature owns its resource, validation and commands; storage only writes
versions and audit records.
Workflows move with it. Definitions become portable YAML compiled through
a closed, typed step registry and stored as a control-plane resource, so
the yaegi interpretation paths (internal/gate, wfeval, wfextract,
gateeval, gateextract, skillbuild) are deleted rather than carried.
The UI process reads definitions as data: the JSON projection lives in
internal/domain/workflow/task so a dashboard decodes the stored
collection without linking the workflow engine, which cmd/archie-ui's
deletion gate forbids. Shipped definitions ride the catalog descriptor
rather than a bespoke REST route, keeping the API to its four operations.
archie-messaging gains -state-store-target/-state-store-token and reads
channel settings from the database, failing closed when the State Store
is unreachable: the database is authoritative for those settings.
The attempt selector becomes an icon-ended pager from the registry
pagination primitive: chevrons walk run history, numbers land on an
attempt, and the active page is the attempt on screen. It sits top-right
above the tab card, and the meta line loses the attempt text fact since
the control now carries it.
`task fmt` formats with the standalone gofumpt and `task lint` re-checks that
formatting with the gofumpt golangci-lint vendors. `task check` runs `fmt`
then `lint` without diffing the tree, so `lint` is the only hard failure for
formatting -- and when the two versions differ, any construct they disagree on
makes the gate unsatisfiable: the standalone formatter rewrites a file one way
and lint rejects it, with nothing a contributor can run to satisfy both.
The surfaces had drifted onto three different pairs. This machine ran gofumpt
v0.7.0 against golangci-lint 2.13.2 (vendors v0.11.0), the image pinned
golangci-lint 2.12.2 (vendors v0.9.2) next to gofumpt v0.11.0, and CI
installed gofumpt@latest. `any((Trees)(nil))` in changes_test.go is the
construct that surfaced it: gofumpt <= v0.9.2 keeps the redundant parens,
>= v0.10.0 removes them.
- Dockerfile: golangci-lint 2.13.2, whose vendored gofumpt v0.11.0 now equals
the pinned GOFUMPT_VERSION, so the image's two formatters agree.
- Dockerfile: fail the build if the pins ever diverge, rather than ship an
image whose gate cannot pass.
- deploy.yml: gofumpt@v0.11.0 instead of @latest, which drifts ahead of
whatever golangci-lint vendors.
- Record the invariant where an agent will meet it: AGENTS.md (CLAUDE.md) and
the build-and-env skill, whose snapshots now name the pinned pair instead of
calling both unpinned.
Two of the three findings from review. The third had already been fixed by the
version of the service-registry PRD that landed on main.
1. docs/prds/state-store-contract.md §10 still prescribed the topology that was
deleted when the State Store was extracted. It said an empty `Target` opens a
local `*store.Store` adapter, and that the daemon's base path is that local
store "already opened by openProductionTaskStore". Neither holds: the
standalone archie-state-store process exclusively owns archie.db, and both
archied and archie-gateway reject an empty target (bootstrap.go,
state_store_client.go: "services.state.target is required").
openProductionTaskStore still exists, but only inside that standalone process.
Following the ratified section would have reinstated the deleted in-process
ownership path. The config.example.toml bullet (which still advised adding the
section with a COMMENTED target -- impossible to boot) and the "opposite
default (local, not remote)" blockquote are corrected with it; the section is
already present with the target uncommented and marked REQUIRED.
2. CLAUDE.md named the State Store authority rev. 2c while the contract itself is
ratified at rev. 2d. AGENTS.md is a symlink to CLAUDE.md, so one edit covers
both guides.
Not changed: the typo-visibility finding is already addressed by the PRD on main.
Its tracking name, unregisteredServiceKeys, is unimplemented in Go, so the runtime
diagnostic is still missing -- filed as archie-core-jp4g.
Closes#855 (archie-core-5gzx).
The check mode added in the preceding commit had no caller, so it prevented nothing: a
stale contracts.json still passed every gate. This wires it in and makes
drift fail the build.
- `task docs:generate` writes the committed artifact.
- `task docs:check` verifies it, non-destructively.
- `task check` runs `docs:check`, right after `proto:check`, so both
generated-artifact surfaces are judged the same way in the same place.
The check cannot be satisfied by rewriting: it generates into a temporary
directory, so a failing gate leaves the artifact exactly as it found it and
the author applies the regenerated bytes. That keeps the regenerated diff
reviewable in the same commit as the code change that caused it, which is
what Step 9 of the architecture document requires and what a CI auto-update
would quietly bypass.
Documents that called this gap open are updated rather than left to
contradict the code:
- `generated-documentation.md` Step 8 (no `docs:*` task exists -> both exist),
Step 9 (drift is gated locally, not in CI), and the hook/CI policy (rule 3
is now enforced by the gate; rules 1, 2, and 4 still rely on the author,
since nothing observes a commit).
- `contract-conformance-audit.md` gap 1, now closed.
- `config-example-drift.md` item 3, which asked for exactly this wiring.
- `CLAUDE.md`, whose `task check` description listed neither `docs:check`
nor `test:tools`.
- The build, docs, and diagnostics skills, plus a re-baselined diagnostics
snapshot: the `task_docs` delivery surface went 0 -> 6 and the `tools`
module 4 -> 7 now that the tasks exist.
Verified with `task check` (green), including the new `docs:check` step.
Closes archie-core-h019.7. Three parts:
- Promote docs/prds/adversarial-self-review.md into
docs/architecture/adversarial-review.md, describing the stage as shipped
(subagent executor, .git-free snapshot, ReviewReport contract, fail-closed
park, models.reviewer budget, operator-triggered review_pr) and mark the PRD
as promoted.
- Add the review stage to ARCHITECTURE.md's task lifecycle.
- Reconcile CLAUDE.md's Development Protocol: distinguish the contributor's
opt-in manual pass from archied's automatic pre-PR review.
Note: the h019.7 text said the review diverts to waiting_human, but the
shipped stage (h019.1/h019.4) parks to StatusParked, not waiting_human. This
change documents the shipped behaviour (parked), not the stale wording.
archie-core-ymut decided the configuration page reads a projection the daemon
publishes rather than reaching into a shared config.Holder. This is the
carrier: a single-row store surface plus PutConfigSnapshot/GetConfigSnapshot,
taking the contract to 42 RPCs.
The document is opaque here. Its shape belongs to the daemon that builds it
and the page that renders it, so the store neither parses nor validates it,
and schema names the projection so a reader can refuse one it does not
understand. It is secret-free where it is built: the projection carries an API
key's environment variable name and whether it resolved, never a value.
Both RPCs are administrative. authorizesTaskScopedCall is deny-by-default, so
a container's task-scoped grant can neither rewrite what an operator reads nor
read a projection of the deployment it runs inside; a test pins both.
Nothing publishes or reads it yet -- the daemon's publisher and the UI's
read path land with the rest of the cutover.
The gate also runs proto:lint, proto:check and lint (Taskfile.yml:187-200);
the summary line omitted all three. A session that reads this line and
assembles go vet + go build + go test + gofumpt as an equivalent stand-in
misses golangci-lint entirely, which is how main last went red.
The in-process-multiplexed-server and daemon.StateStoreTokens bullets
described the pre-.4.6 design; neither boot.startStateStoreServer nor
daemon.StateStoreTokens exist in the codebase anymore. Replaced with
what's actually true: the standalone archie-state-store process,
staterpc.GrantIssuer/TaskGrants task-scoped credentials, and
archie-agent's single (no longer dual-path) gRPC Store.
Surfaced while reconciling beads .4.2-.4.6 against main -- all five
verified against the code and closed as genuinely done.
* feat(state-store): generalize storerpc as the State Store gRPC contract
Implements archie-core-8cda.4.2 against docs/prds/state-store-contract.md
rev. 2c: generate protobuf/gRPC client and server adapters for every
ratified store contract (proto/state/v1/state.proto, 40 RPCs, one
StateStoreService), add internal/infrastructure/staterpc with a bufconn
conformance suite exercising both local and remote adapters, serve the
service in-process (bridge address + mandatory per-task bearer token when
agent containers exist, loopback-only otherwise), and flip archie-agent's
workflow.Store to a long-lived gRPC client when the daemon injects
STATE_STORE_URL/STATE_STORE_TOKEN (falling back to the legacy NATS
storerpc path otherwise -- one agent process is never both).
Also drops the *sql.Tx parameter from store.BindingDispatcher.RecordDispatch
(a required wire-blocker fix: a transaction cannot cross a gRPC boundary,
and production always passed nil).
fix(store): drop RecordDispatch's unusable *sql.Tx parameter
feat(config): add services.state contract-adapter selector
* fix(state-store): apply no-mistakes review decisions
- Drop StreamTokenInterceptor (unused; the State Store service has no
streaming RPCs and nothing calls it).
- Make StateStoreTokens.Validate compare tokens in constant time
(crypto/subtle) per the auto-fix hardening.ing finding.
- Amend config.example.toml / config.Services.State doc text so it frames
[services.state].target as the ratified surface consumed by the upcoming
standalone archie-state-store binary (.4.3), not active today.
* feat(curator): add embedding client and sampler wave-1 prerequisites
Bead archie-core-1786637500752-415-434e5bb9 (GitHub #436) was closed with
no linked PR/commits, and the surprisal-sampling bead
archie-core-1786637500776-416-600a66e5 (GitHub #437) found none of its
stated prerequisites -- an embedding client, a Sampler interface, or the
four wave-1 cheap sampling strategies -- actually exist. This builds them:
- internal/domain/embedding + internal/infrastructure/embedding: a narrow
typed embedding client, config-driven via a providers table + a role in
[models], mirroring the existing chat model role convention. Degrades to
capability-unavailable (never fails startup or a call) for a missing
role, unknown provider, unsupported class, or unresolved credential.
Wired as an optional capability in bootstrap.go's setupEmbeddings.
- internal/domain/sampling: the Sampler interface plus recency, random,
all, and staleness-proxy strategies, per docs/prds/curator-sampler-wave1.md.
Deterministic given fixed inputs, matching GitHub #437's stated
acceptance criterion for the embedding-backed strategy it will add
behind this same interface (not part of this change).
Table-driven tests throughout; httptest for the embedding client, no live
service. No curator wiring yet -- nothing consumes either capability in
this change.
* no-mistakes(document): docs(architecture): mark curator sampling prereqs as landed
Dolt is the source of truth and already syncs via its own git+ remote
(bd dolt push/pull). Committing the JSONL export separately produced a
steady stream of no-op "chore(beads)" commits that skewed commit counts
without adding information. Untrack the export files, disable
export.auto/git-add, and drop the beads-commit step from CLAUDE.md's
Session Completion Protocol.
ARCHITECTURE.md described forge intake as polling-only and listed Gitea
as still "planned" despite internal/forge/gitea.go fully implementing
it -- both stale since 7d5u.4/.2/.3 shipped forge webhook intake.
Corrected the opening description, package map, Provenance-by-origin
paragraph, [forge] config bullet, and Implemented/Planned lists; added
a "Webhook intake" subsection documenting internal/forge/webhook as a
separate HTTP receiver reusing the poller's TaskEnvelope/PublishTask
path.
CLAUDE.md gains the internal/forge/webhook/ trap: HMAC verification
must precede payload parsing, and the webhook-built TaskEnvelope must
keep its poll-compatible owner/repo/number idempotency key or
poll/webhook double-dispatch returns.
plugins-and-extensions.md gains a section cross-referencing 7d5u.1's
decision (in-process typed families, no amendment needed) and naming
the Module action position as the shipped instance -- Channel/Forge
positions are correctly left as open investigation (t2db.19), not
claimed as shipped.
Closes archie-core-7d5u.6.