251 Commits
Author SHA1 Message Date
sam 83613d902a docs: format the docs 2026-11-17 17:53:58 +11:00
sam f92c5b4536 chore(runtime): delete Kit and external agent harness support (#1877)
ci/woodpecker/pr/quality Pipeline was successful
Quality / check (pull_request) Canceled after 7m39s
Archie runs its own agent loop only. Removes Kit resolution and launch,
the harness runner and adapters, the setup terminal and sandbox view,
harness secrets and OAuth capture (table dropped in migration 0075), the
task-tools contract that only Kit containers reached, and the
sandbox-kit-spec dependency. Agent profiles carry image and tools only.
The egress proxy keeps the model-session path; the sandbox relay code
stays for #1867.
2026-11-12 21:29:05 +11:00
sam e10bb161fe docs(prds): mark the self-development ADR as decided, not built (#1769) 2026-11-03 01:52:06 +11:00
sam 3b525b7482 docs(prds): mark the self-development ADR as record, not mechanism (#1769) 2026-11-03 01:50:54 +11:00
sam c2cc10ebfa docs(prds): record the self-development loop decision (#1769) 2026-11-03 01:36:31 +11:00
sam ec9bf5feb2 docs: track work in Gitea issues instead of beads
Every one of the 1709 tracker issues was created in Gitea and checked field by
field against its source record: title, body, state, label set, assignee,
comments, dependency edges and epic label. All 1729 beads are closed, citing the
issue that carries each one, and .beads is removed.

Three differences are deliberate: Gitea truncates titles at 253 characters, so
three long titles keep their full text in the issue body; Gitea refuses a mutual
dependency, so five symmetric relates-to links exist in one direction; issue 497
carries its fix from e3b1103f.
2026-10-29 23:22:35 +11:00
sam f2b8681611 refactor(workflow): stop assuming a human decides
An approval, ask or park can be resolved by an operator, a rule, a
classifier or automatically, so the vocabulary stops naming a person:

- step type human.approve -> workflow.approve
- park class needs_human -> needs_decision (ParkNeedsDecision)
- event kinds human_* -> operator_*
- alert kind task.needs_human -> task.needs_decision
- status grouping "needs you" -> "needs attention"

0061 rewrites the stored values, including the approval step type in the
workflow-definitions resource and each task's pinned definition, with the
digest recomputed so resumed tasks still match.
2026-10-25 17:31:16 +11:00
sam 5a55196572 docs: edit guides, PRDs and security notes, regenerate release news 2026-10-19 10:04:36 +11:00
sam aa1e2ca660 feat(kit): central tools for harnesses through the egress proxy and gateway task-tool RPCs 2026-10-17 23:42:37 +11:00
sam acec5d392d feat(archied): read-only run-scoped sandbox view over the harness contract (#1662)
* feat(archied): read-only run-scoped sandbox view over the harness contract

Serve RunTarget: the daemon resolves a running task and attempt to its Kit
container and follows its output, refusing a finished or unknown task with a
stated reason. The dashboard adds a Sandbox tab behind the task log's read
authority. Takeover stays out of scope until the sod1 authority is wired.

* fix(archied): scope and close sandbox views correctly

Forward harness activity into container output, bind containers and dashboard views to their attempt, enforce the asserted org, and report unavailable dependencies and interrupted streams accurately.

Refs: archie-core-qi91, archie-core-252tj
2026-10-14 02:57:32 +11:00
sam 7ef58293be feat(harness): serve a daemon-side setup session to the dashboard
The dashboard's setup terminal was a 503: it had a WebSocket route, an
authorizer and an xterm.js surface, but nothing owned a container. The
daemon owns containers, so the session contract lands there and the
dashboard consumes it over a new gRPC contract.

One session concept, two targets. A setup session is addressed by Kit
profile and is ephemeral; a run session (archie-core-qi91) is addressed by
task and attempt and is bounded by the task. This slice serves setup and
answers Unimplemented for run.

The contract, the authorisation, the lifetime and the egress phase are
settled in docs/prds/external-agent-harness.md, "Session contract". The
short version: the daemon serves harness.v1.HarnessService; the dashboard
authorizes the operator as an update on the secret and then dials the
daemon with the harness service token, required even on loopback because a
session is a shell holding an org's credential; the setup container runs
no worker, mounts no worktree, holds a keepalive, and carries an empty
container environment. Install hooks run at the install phase and the
session enters runtime before the shell, so a runtime-phase credential's
token endpoint is the one the proxy intercepts.

Capture is gated by the egress proxy on a granted service, and a setup
session has no task, so the daemon registers a session grant: the
session's proxy token resolves to the org's bindings for the Kit's
declared services. The real token never enters the container: the token
endpoint response is sentinelized and stored as the org's harness secret.

Every teardown path releases the pool slot, revokes the egress session and
the grant, removes the sandbox network, and removes the session's volumes.
The listener requires HARNESS_TOKEN and stops with a 10s grace before
Stop, so an open session cannot hold shutdown to the watchdog leash.
2026-10-09 01:38:41 +11:00
sam a8a118c1b8 chore: cut agent governance to a single constitution
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.
2026-10-03 21:47:46 +10:00
sam 703692ca7a feat(workflow): add the command.run step type
archie-core-ndm8 accepted the command-step trust decision, so a stored
workflow definition may run operator argv. The workflow engine has exactly one
call site -- agentworker, which is what the container agent serves -- so the
step runs on the container path by construction. A non-zero exit parks the run;
level: warn makes it advisory.

Settings mirror the repository gate's command shape (name, argv,
expect_failure) so a command means the same thing in both places. The settings
type is local rather than agentexec.Command because that struct carries JSON
wire tags only, and YAML decoding silently dropped expect_failure -- a command
declared to fail would have been reported as passing. A reflection test holds
the two shapes together.
2026-10-03 02:07:45 +10:00
sam aacec67c24 docs: delete the superseded adversarial review document family
The adversarial self-review system was removed in 625ead95, 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.
2026-10-03 00:01:42 +10:00
sam 7ca81dc85a feat(agentworker): answer MCP sampling from the task's model
A task hosts the same configured MCP servers as a chat turn, but the
worker's provider builder passed no sampling handler, so a task-scoped
server's sampling/createMessage request got a JSON-RPC method-not-found
while the identical request succeeded on the chat path. The worker runs
its own model runtime, so it can answer.

Thread a sampling handler built from the task's builder model into the
worker's MCP provider builder, beside the chat path's handler. Build the
task's model runtime once and share it with the stage runners instead of
creating a second client for sampling.

Move the sampling message mapping and max-token bound to agentexec, next
to the runtime both paths call models through, so a server gets the same
bound on either path. Carry the catalog's reasoning flag in
ModelLimits: a reasoning-class builder model must omit the max-token
bound its provider rejects, exactly as the chat path does.
2026-10-02 12:20:31 +10:00
sam bfb909a93a docs(prreview): the approval path keeps the task's workflow, it does not force implement
The PRD still described both approval surfaces requeueing under a hardcoded
implement workflow. The shipped path passes an empty workflow, which Requeue
reads as keep-the-task's, so the feasibility handoff has to name implement on
the task before the wait rather than relying on the handler.
2026-10-02 11:45:46 +10:00
sam 1f0cb9f318 docs(prds): name the registered step type and hold the vocabulary PRD to the provider set
docs/prds/workflow-step-vocabulary.md named the repository-rules step type
`workflow.diff-rules` while the vocabulary a deployment resolves carries
`gate.diff-rules` (workflow.DiffRulesStepName), so a definition written to
the document's word is refused at save and at run. The same decision's
sibling, docs/prds/runtime-control-plane.md, still claimed "Plugins can add
step types", which this document's closed-set rule contradicts: an
interpreted plugin contributes none, and a step type arrives as a provider
in the compiled-in set.

Correct both documents, and hold the vocabulary PRD to the provider set with
a guard test: every step-type-shaped name the document identifies must
resolve in workflowsteps.Providers(). The test fails on the pre-fix document
("workflow.diff-rules" is contributed by no provider) and passes after.

Refs: archie-core-vwqc, split from archie-core-gcoj (closed as invalidated by
re-verification: the provider set exists and cross-side agreement is already
pinned).
2026-10-02 11:05:08 +10:00
sam 721968eeff fix(workflow): derive a declared output's captures need for profile selection
A declared output is written through a capture tool, but the dispatch-time
harness check read only the workflow's needs.captures. A workflow that
declared outputs without also writing needs: {captures: true} could name a
Kit profile whose adapter serves no capture tools; a required output then
parked with "output %q is required" instead of the profile being refused.

WorkflowInterface.Needs now reports captures for a non-empty Outputs beside
the declared needs, and the profile check and Kit launcher read it. The
needs: block keeps its meaning for a workflow that captures without
declaring outputs.

- internal/domain/workflow/task: Needs() derives captures; DeclaredNeeds
  carries only the declared block.
- internal/daemon: pinTaskProfile and runKitTask read Needs().
- tests: parse-time derivation, and pinTaskProfile refusing an
  outputs-declaring workflow against a Kit adapter with no capture MCP.
2026-10-02 03:19:07 +10:00
sam a4abafe0ad docs(prds): decide the plugin live-reload open questions
Review of the plugin-settings reconcile PRD (F1-F8) returned REVISE: the doc
stated outcomes without making the decisions behind them. This revision makes
each one, so the PRD can carry the plugin live-reload work:

- ApplyMode is set to live and the gateway's version lag moves from the
  restart banner to the per-process applied-version rows.
- The skills_dir refusal gets a check site (a pre-layer comparison on the live
  path, not the value-agnostic validator), keeping #1143's validates-nothing
  intact.
- Records the four-directory coupling and why a whole-document refusal is
  acceptable.
- Justifies stop-then-start as a module's only check, and adds the refused
  dependent-replace outcome to the apply-status taxonomy.
- States that a reconcile tick re-runs layering and provider resolution, and
  what archie-gateway actually boots.
- Adds the Verification section.

Cited package paths re-checked against the tree; the control-plane
definitions now cite internal/app/controlplane/.
2026-10-02 03:10:18 +10:00
sam 24258e215f docs(prds): plugin settings reconcile live without a restart
Direction for GH #1154 (epic #998): reconcile the plugin, module and
secret-engine directories into the running registries, load new and
changed files, and surface only the removals through apply status.
Draft pending maintainer approval - not settled design, so no diff.
2026-09-30 11:41:11 +10:00
sam fcc6a7974e docs(prds): draft SOUL, the per-identity chat personality 2026-09-30 08:37:48 +10:00
sam bf1dc2e33e docs(prds): the step-type vocabulary PRD awaits the maintainer's approval 2026-09-30 07:56:52 +10:00
sam f34714ea07 merge: decide the workflow step-type vocabulary (m7oc, ze7y) 2026-09-30 07:56:10 +10:00
sam c2cfba1129 docs(prds): decide how step types are named, agreed, and refused 2026-09-30 07:55:34 +10:00
sam a67a142139 docs(prds): state the resource idempotency key and the approval gate's scope 2026-09-30 07:54:05 +10:00
sam d7f6f502a8 merge: decide the declared-outputs model for workflow.call (t2db.43) 2026-09-30 07:40:17 +10:00
sam 54e36ff8b7 merge: decide the operator-approval response channel and re-review cap (afbk.11) 2026-09-30 07:40:16 +10:00
sam 013fcd0919 docs(prds): decide the declared-outputs model for workflow.call 2026-09-30 07:38:50 +10:00
sam 00209ebe87 docs(prds): decide the operator-approval response channel and re-review cap 2026-09-30 07:38:03 +10:00
sam 761a1271a4 docs(prds): decide where per-workflow review settings live 2026-09-30 07:32:25 +10:00
sam cadbc6d1ca Merge origin/main (v1.44.1) into local main 2026-09-30 02:39:21 +10:00
sam 64128645c2 fix(eda): reject a result map missing a field or needing a conversion
DecodeResult accepted any value reflect could convert, so a number for a
string field silently became the rune string (42 became "*"), and a declared
field absent from the map read as its zero value. Both are now reported: a
value is accepted only at the field's declared type, and every declared field
must be present.

That is the boundary the typed CEL environment promises, and it is live now
that the action runner decodes every result into actions.<id>.result before a
later expression reads it. D5 in docs/prds/multi-action-playbooks.md records
the rule.
2026-09-30 02:38:20 +10:00
sam 8155cc915a docs(eda): ratify args evaluation-failure semantics (J6)
An args value that cannot be evaluated aborts its playbook run: the action and
every later action in that playbook do not run, other playbooks matching the
event still run, and the task is unaffected. J3's skip-and-continue rule stays
specific to `when`, because a predicate has a meaningful false and data does
not.

Ratified now that the action runner is the production consumer, and locked by a
call-site test that fails if the rule is weakened to a skip. Drop the stale
"unbuilt decisions" header line, since J1, J2 and the Result schema
declarations have shipped.
2026-09-30 02:31:21 +10:00
sam 67c5447ebc fix(controlplane): refresh a stale seeded resource and re-seed a removed one
A seed was consulted only for a resource kind the store did not hold, so a
document that changed in the build never reached a database an earlier
release had seeded. For workflow-definitions that is not a stale setting but
a total outage: the collection validates as one document, so a stored step
type this build no longer has fails every task's pin, whatever workflow the
task names. The seed's request ID was stable per kind and the store answers a
known request ID from resource_history, which outlives the resource, so the
documented recovery -- remove the resource and restart -- wrote nothing
either.

Seeds now carry one identity the reader can name, and a kind the store holds
is refreshed only when the seed itself wrote the newest revision: a
file-derived value stays the store's, and an operator's replacement is never
undone. The request ID is derived from the value, so an idempotent replay is
still one revision without making a second, changed document impossible. A
replay whose resource is gone re-creates it from the ledger's revision.

The shipped-vs-file-derived distinction is the seed's to make, so it is a
property of the definition (Defaults is set exactly for the kinds that ship a
document) rather than a check at each consumer.
2026-09-29 14:27:57 +10:00
sam d60f024e74 docs(prds): route intake's AI-score into lenses, split reviewer timeout from zero-findings, bound phase 9
Landing three PRD refinements found while studying prior reviewer art before
starting archie-core-afbk.3: dimension selection now sees intake's
machine-written score directly and adds a hallucination-check dimension for
it; a reviewer that exhausts its turn cap or deadline records a distinct
StepExecution status from one that completed and found nothing; phase 9
polish runs in a bounded pool of 8, matching phase 4.
2026-09-28 03:00:51 +10:00
sam 42a4e2465d feat(kitrun): mount the operator's skills store for agent-skills@1
A Kit's agent-skills@1 path now gets the shared skills store
(skills_dir/.agents/skills) bind-mounted read-only, whatever mode the Kit
asks for; with no skills_dir the host withholds the mount. skills_dir is
read live on every launch. skill.StoreDir exposes the store path so the
launcher does not copy the package's directory constant.

Part of archie-core-egkf.6.
2026-09-28 02:12:29 +10:00
sam 608403c1f9 feat(kit)!: a Kit profile names one Kit image, a workload or a published set
kitrun ran the first Kit of a profile's list as the container image, so
every mixin's layers (its tools, skills and staged context) were dropped
without a refusal. A profile's `kit` is now one digest-pinned reference:
a workload Kit, or a published Kit set, which the Kit spec's frontend
merges from a workload and its mixins into one image. archie composes no
Kits itself, and a bare mixin is refused with a pointer to publishing a
set. kit.Compose had no production caller left and is removed.

BREAKING CHANGE: `[containers.profiles.X] kit` and the agent-profiles
document's `kit` are a string, not a list. A stored list fails to decode
and must be rewritten as the one workload or set reference.

Part of archie-core-egkf.6.
2026-09-28 02:04:04 +10:00
sam 3f0071e27b feat(statestore): step_executions, StartStep/FinishStep under the run credential
Plan item 3 of docs/prds/execution-tree-state-machine.md (archie-core-1220), on
top of the transition tables and ErrIllegalTransition enforcement (1214/1215,
archie-core-qdbo.5):

- Migration 0017 adds step_executions -- id, org_id, workspace_id, execution_id,
  attempt, parent_id, depth, kind, name, called_execution_id, status, detail,
  tokens_used, started_at, finished_at, indexed on (execution_id, attempt, id).
  Ownership fields are stamped from the execution's row; depth is derived from
  the parent, never supplied by a caller. Existing rows gain no backfilled
  steps.
- task.Store (the workflow engine's mid-run facade) gains StartStep/FinishStep
  (5 methods, within the 8 cap), with storecontract.StepRecorder fronting them
  on the server; deadlineStore wraps both with its per-call timeout.
- The store enforces each write as one transaction: the guarded row write
  under the shared step transition table plus the transition's own
  stage_start/stage_finish event row. Staleness is decided before legality,
  the way guardTransition decides it, and the store returns the persisted
  event for the caller's post-commit publish -- the EmitDurable convention
  (the daemon's event sink skips already-persisted rows by assigned ID), which
  is why workflow.Run stops emitting stage events beside the store and no
  longer discards step-write errors: a failed start or finish parks the
  execution, and the stage does not run unrecorded. An interrupted stage
  records interrupted rather than failed; a recording failure on that
  shutdown path is logged and left to RecoverStale, which owns the
  interrupted-execution sweep in plan item 6.
- The run credential of docs/prds/orgs-and-access.md authorises StartStep and
  FinishStep on its own execution only: both requests carry the execution ID
  the grant check verifies (FinishStep carries it because the interceptor
  never reads the database), and FinishStep verifies handler-side that the
  step really is that execution's. authorizesTaskScopedCall's sanctioned
  widenings are now held as a lookup table so the next one stops growing a
  switch.
- The PRD's wire contract is StartStep(execution, attempt, parent, kind, name)
  -> step id; the responses also carry the persisted event (needed for the
  post-commit publish) and FinishStep's request carries execution_id (needed
  for the grant check) -- both noted here as deliberate additions to the PRD's
  shorthand. called_execution_id exists in the table but not yet on the wire:
  its named consumer is the workflow-call recording of plan item 4 (#1216).

Conformance drives both adapters; grant tests pin the own-execution scoping;
the wire sentinel set gains ErrInvalidStep (InvalidArgument, "step execution
invalid") for a step kind no consumer names.
2026-09-27 05:42:32 +10:00
sam 2604cd4cf4 docs(harness): pin per-stage profile override as workflow.call, not a mid-container switch
docs/prds/external-agent-harness.md's "Selection" says a stage may name a
different profile than its workflow's. Investigated before writing new
runtime code, per instruction not to build container-switching machinery:
a Kit task runs in one container provisioned for one profile (Container
layout), so a stage needing a different profile cannot be a mid-container
runner swap without inventing per-stage re-provisioning the PRD does not
ask for and Container layout argues against ("cost scales with the run,
not with how many agents it fans out to").

The requirement is already met by workflow.call plus per-task profile
resolution, both pre-existing: postgres.Store.StartCall stores the
callee's OWN Workflow name (not the caller's), and daemon.pinTaskProfile
resolves a task's profile purely from its own WorkflowDefinitionYAML.
Chaining these means a stage wanting a different profile is its own
callee workflow, started via workflow.call, exactly the way
event-automation.md already describes ("the callee runs as its own run
with its own agent profile").

No new production code, only a PRD clarification (dev-docs regenerated)
plus TestWorkflowCallGivesACalleeItsOwnProfile (daemon_test.go), which
closes the gap between two already-tested facts that nothing previously
stated together: TestWorkflowCallerConformance (staterpc) proves a
callee's Workflow field is independent of its caller's; this proves that
independence is what makes Kit-vs-image runner selection independent too,
composing a caller pinned to an image profile with a real StartCall-
created callee pinned to a Kit profile.
2026-09-27 05:25:39 +10:00
sam b6357c8fd4 fix(archied): report workflow settings watch outages 2026-09-26 20:38:48 +10:00
sam 4040e42d2b docs(prds): de-date the org-enablement sentence in workflow-calls 2026-09-26 13:36:41 +10:00
sam fb49ebd268 docs(prds): record the workflow-caller pair and grant widening in the State Store contract (archie-core-t2db.41) 2026-09-26 13:36:41 +10:00
sam 5ca398d0d9 docs(prds): decisive design for workflow.call runtime and save-time checks (archie-core-t2db.41) 2026-09-26 13:36:40 +10:00
sam 5b6572bcea feat(agentexec): run harness invocations as the Kit's user with no inherited environment
A Kit task runs worker and harness in one container, separated by user:
the worker keeps its credentials as root, and every harness invocation
runs as the Kit's user with only its declared environment. A nil env
would inherit the worker's, so the runner always passes an explicit one;
root is refused as a harness user, and a root worker refuses to start a
harness with no user. The PRD's container layout now says one container
per run, with the relay forwarding the proxy, NATS and the State Store.
2026-09-26 03:08:34 +10:00
sam 486d5574b3 docs(prds): fit harnesses, steps and the store inside the org boundary and profile model
A harness is an agent profile whose environment is a Kit composition, so
image profiles and existing workflows are unchanged and only Kit runs take
the egress path; the relay replaces the claim that containers reach the
proxy directly. Credentials, step records, store installs and reviews are
org-scoped under the run credential and the Authorizer, and workflow calls
are linked across executions rather than nested.
2026-09-26 02:41:02 +10:00
sam 1cf2742f54 docs(prds): approve PR review agent and store PRDs 2026-09-26 02:08:13 +10:00
sam 0f6cb5b8a6 docs(prds): store 2026-09-26 02:06:50 +10:00
sam fca30d6445 docs(prds): PR review agent 2026-09-26 02:05:52 +10:00
sam a98ca2c8e9 docs(prds): approve execution-tree and external-harness PRDs 2026-09-26 01:58:29 +10:00
sam 22d36fef75 docs(prds): harnesses run as Kit v3 images behind a credential-injecting egress proxy 2026-09-26 01:54:35 +10:00