Commit Graph
217 Commits
Author SHA1 Message Date
sam f20d226369 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 70f9b1b87c 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 b867275791 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 fa4566fb0d 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 4d6f49f7f3 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 5b1f46b7c3 fix(archied): report workflow settings watch outages 2026-09-26 20:38:48 +10:00
sam 5e8ab5cde9 docs(prds): de-date the org-enablement sentence in workflow-calls 2026-09-26 13:36:41 +10:00
sam 08deeb57a7 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 5c30e971f1 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 21e9e4a3b7 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 6eb5708914 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 2e07de667d docs(prds): approve PR review agent and store PRDs 2026-09-26 02:08:13 +10:00
sam 8df37c2bd0 docs(prds): store 2026-09-26 02:06:50 +10:00
sam f690db6fcf docs(prds): PR review agent 2026-09-26 02:05:52 +10:00
sam 8e9f212b87 docs(prds): approve execution-tree and external-harness PRDs 2026-09-26 01:58:29 +10:00
sam 882b650734 docs(prds): harnesses run as Kit v3 images behind a credential-injecting egress proxy 2026-09-26 01:54:35 +10:00
sam e6ca756d5b docs(prds): fold review findings into execution-tree and harness PRDs 2026-09-26 01:45:10 +10:00
sam 92a457e36b docs(prds): agents reach a harness only through a workflow stage 2026-09-26 01:41:12 +10:00
sam 20152f2da3 docs(prds): external agent harnesses 2026-09-26 01:38:14 +10:00
sam 0545df1451 docs(prds): execution tree and enforced state machine 2026-09-26 01:34:26 +10:00
sam 4ffebb855d feat(webui): five-place top bar with Settings, New task and one connection pill
Dashboard, Tasks, Workflows, Events and Settings replace the Work, Agent
and System menus. Configuration pages move under /settings/* with
redirects from their old paths; Logs and Appearance leave the bar and stay
reachable from Jump to, the Dashboard and the account menu. New task opens
the Start work form in a dialog and lands on the new task. One pill reports
the live stream's state.

Drops docs/prds/dashboard-navigation-groups.md: web UI design is not
tracked in PRDs.
2026-09-25 15:09:18 +10:00
sam 2a8ac397df docs(prds): reflow playbook-expression-syntax 2026-09-25 02:00:16 +10:00
sam 5f915931ef test: remove layout-pinned route-registry and task-meta fixture tests
TestDashboardPagesRegistryCoversEveryRoute parsed ui/src/router/index.ts as
text, and TestTaskMetaPayloadMatchesFixture plus ui/test/task-meta-snapshot
pinned a formatted JSON fixture. They failed on formatting, not behaviour.
2026-09-25 01:32:20 +10:00
sam 2e00777f07 refactor: format markdown files using prettier, fix spelling concerns, reduce Taskfile bloat 2026-09-25 01:10:28 +10:00
sam 335fb4bb22 Merge branch 'main' into pg/foundation 2026-09-24 22:21:24 +10:00
sam f3b8ddecb0 fix(eda): clear completed tasks; document the tool allowlist's reach and unchecked profile names
ClearTerminalTasks now deletes completed tasks, with a test that holds its
SQL list to taskstate.Terminal. The AllowTools comment says agentloop's
built-in file tools are outside the allowlist and why. The PRD model
diagram lists only what a profile holds (image, tools), and the profile
field and AgentProfile say a workflow's profile name is resolved at
dispatch, not when the workflow is saved.
2026-09-24 20:53:51 +10:00
sam 47fae672f1 feat(eda): workflow inputs, optional repository and agent profiles
Workflow definitions declare inputs, repository (none, optional or
required; default required) and profile. A binding assigns each input
from a mapped parameter or a constant and may take its repository from a
parameter, which must name a configured repo; both are checked when the
binding is saved and again at dispatch. Inputs travel as structured task
data (tasks.inputs, the task brief, and a JSON block in the agent's
mission), never as body text.

A task with no repository runs in a per-task scratch workspace with no
clone and no publication grant. The agent.run step runs one mission
without a repository and finishes the task in the new completed status.

Agent profiles live under [containers.profiles.<name>]: an image and an
allowlist over the tools archie adds (MCP, scripts, plugins).
[containers].image is the default profile; an unconfigured profile parks
the task. The workflow is now pinned before the container starts so the
profile can choose its image.

Also stop two archied tests writing embedded NATS state into the package
directory, refuse an empty state_dir for embedded NATS, and drop the NATS
store files an earlier lane commit tracked.
2026-09-24 20:29:33 +10:00
sam 35ebaa6ce4 docs: describe the PostgreSQL-only stores, state_dir and the import-only db_path
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.
2026-09-24 14:51:48 +10:00
sam cb518e6f6d feat(webui): serve change statuses and the config schema through /api/task-meta
Closes #865. The dashboard hand-copied the Change* file-status ids and events.ConfigCapturedSchema. /api/task-meta now serves both; the Vue dashboard renders ui/src/lib/task-meta-snapshot.ts until the served catalog lands. The Go handler is pinned to internal/webui/testdata/task_meta.json and the snapshot is pinned to that same fixture, so a one-sided rename fails a test.
2026-09-24 09:31:09 +10:00
sam 61f19a2807 docs(prds): orgs, workspaces and access control
Approved design for orgs and workspaces, people and agents as identities, the Cedar policy chain (instance with network rules, org, workspace, identity and workflow, object), server-derived credential scope, and one run credential per agent run. Secrets move from agent profiles to identities; event-automation.md is marked superseded where it said otherwise.
2026-09-24 00:34:14 +10:00
sam e878eb092c docs(prds): event automation — identified events, typed parameters, purpose-built agents 2026-09-23 23:50:27 +10:00
sam 068d89ebb4 feat(eda): playbook.Load findings name the offending action, when or args line 2026-09-23 22:42:14 +10:00
sam ee16b8a711 feat(playbooks): archie-playbooks serve, a language server publishing lint findings as diagnostics 2026-09-23 22:22:56 +10:00
sam 69e6d276e6 feat(playbooks): lint an EDA playbook directory with -eda-dir 2026-09-23 22:11:01 +10:00
sam d01f7b3d3a feat(eda): reject an args value whose checked CEL type cannot fill its Args field 2026-09-23 22:05:50 +10:00
sam e867760711 feat(eda): run action playbooks at pin time through the at-most-once dispatch ledger 2026-09-23 22:00:52 +10:00
sam b2dbcda697 docs(eda): playbook dispatch rows are retained until an explicit delete 2026-09-23 21:52:10 +10:00
sam 6bba6f8070 fix(eda): type-aware actions classifier, one stable-identifier grammar, loader tests that fail for the named reason 2026-09-23 21:48:52 +10:00
sam 75454d22c1 feat(workflow): routing and playbook findings carry the key's file:line 2026-09-23 21:41:56 +10:00
sam e9c2c09b4b fix(webui): move the live stream to /api/stream so reloading /events serves the page 2026-09-23 21:16:29 +10:00
sam aac31b69ad docs(agents): a bead never carries production instance detail
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.
2026-09-23 12:29:29 +10:00
sam cb8e4d0f13 docs(prds): approve the master-detail run page PRD
The maintainer approved task-run-master-detail.md after the
adversarial-review round; its status moves Draft -> Approved while the
work it describes is completed and verified.
2026-09-23 11:36:16 +10:00
sam 4573c27567 fix(webui): reset the stage filter on an attempt switch
A stage filter is a command scoped to the attempt it was made on: the
rail set it against that attempt's stage list. selectAttempt and
performRetry left filters untouched, so a stage selected on attempt 2
carried into attempt 1 -- a same-named stage there rendered as selected
without ever being commanded, or the log stayed narrowed to a stage the
new attempt does not have. The stage filter now resets when the selected
attempt changes; the level filter is attempt-agnostic and survives.

The master-detail PRD absorbs the adversarial review's verified findings:
the reload claim is narrowed to the URL contract (filters are not in the
URL), the unimplemented scroll and pinned claims are dropped, the
unnamed-stage and level-filter contracts are stated, the rail inventory
is corrected, and the acceptance list gains criteria for the
command-not-binding rule, attempt-switch reset, and keyboard selection.
2026-09-23 11:31:58 +10:00
sam 39ad75ac22 feat(webui): split the task run page into a master-detail pane
The five tabs gave the stage rail less than a third of the screen and
disconnected the log stream from the stage that produced it. The stage
rail is now the page's master pane, always visible; the four context
panels are the inspector and own the tab bar. Selecting a stage commands
the inspector to the log tab with that stage's filter set; clicking the
selected stage clears it. Selection is a command, not a binding -- the
operator can change the filter afterwards.

No endpoint, RPC or contract changed. tab=stages still resolves, to the
log tab; every inspector tab and attempt deep-link survives a reload.
Below the shell's 900px frame breakpoint the rail stacks above the
inspector. Design of record: docs/prds/task-run-master-detail.md (Draft,
per-run panel contracts unchanged from task-run-detail.md).
2026-09-23 11:20:45 +10:00
sam e231ef0786 merge(sams-cleanup): the PocketBase event-capture migration and its follow-ups
Moves event capture, mappings and bindings onto PocketBase-owned collections
in internal/infrastructure/edastore, and adds the read-only stateadmin
surface over the task database. Follow-ups included:

- the event feed cursor becomes a total order over a fixed-width timestamp
  with an opaque string cursor, so it no longer depends on rowid
  monotonicity;
- cron schedules get next-run arithmetic, so a cron job fires instead of
  returning ErrScheduleUnsupported;
- binding and mapping edits announce on the activity stream, so a dashboard
  edit is visible without a manual refresh;
- an unresolvable task identity fails closed rather than falling back to the
  root forge's credential;
- tool_call events project into the tool_calls collection, which had a
  schema and no writer.

Also: the branch is brought back to a passing task check, which it had not
been for the whole migration -- two pre-existing failures, an unrecorded
int64-to-string proto break and a stale generated docs artifact.
2026-09-23 03:33:49 +10:00
sam e0becd525c feat(artifacts): publish the completed PR review to the collaborative editor
Implements docs/prds/artifact-sender.md (Approved). archie-core now sends
generated artifacts to the offloaded.dev collaborative editor, whose
POST /api/artifacts route, bearer service token, PocketBase-backed
versions and idempotency semantics are the receiving contract.

- [artifacts] config section: base_url + token SecretRef with a
  token_env fallback naming WORKSPACE_INGEST_TOKEN. An empty base_url
  disables the sender entirely; a base_url with an unresolvable token
  disables it with a warning, because a missing credential disables a
  capability rather than stopping the daemon.
- internal/infrastructure/artifactsync: one-method Publish seam in the
  Courier posture, full source per publish (versions of record are
  snapshots), 503 retried three times with backoff, 401/400 surfaced
  immediately with the field reason, deterministic request ids
  (artifact:pr-review:<owner>/<repo>#<n>).
- ReviewReport gains a pure markdown renderer in internal/domain/workflow:
  summary, one subsection per finding with the failure scenario and
  disposition when present, verified properties as a checked-clean list.
- The daemon's PR reviewer publishes after a completed review when the
  sender is configured, records the editor deep link on the result, and
  degrades a failed publish to a log line -- publishing never fails the
  producing work.
2026-09-23 03:15:27 +10:00
sam 024dfbbe49 docs: delete ARCHITECTURE.md, move its normative content into docs/architecture
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.
2026-09-22 23:49:53 +10:00
sam 1d31ab71e3 docs(release): record the one-stream process, and stop process scopes inflating versions
RELEASING.md still described two independently versioned components, GATEWAY
and RUNTIME release inputs, and a `task release:prepare` invocation that no
longer exists. It is the file someone reads to cut a release, so a stale one is
worse than none.

The PRD's version computation carried a real flaw: a commit whose scope is the
repository's own machinery could still bump the product's version, so the first
improvement anyone made to the release process would inflate it -- which is
exactly what `feat(release)` would have done to this cut. Non-product scopes
(`release`, `ci`, `docs`, `build`, `test`) now contribute no bump.
2026-09-22 21:43:10 +10:00
sam cd2ab7f2cb feat(release): one release stream, one version, one page per version
CHANGELOG.archied.md and CHANGELOG.archie.md were two version streams that
drifted: a release that moved both components had two numbers, two pages and
two tags, and a reader had to visit two files to learn what shipped.

The merged history holds 65 versions from 64 archied and 34 archie sections --
33 that both components released, 31 only archied, one only archie -- so 98
published pages become 65. A version's date is the newest of its sections'
dates, and a component whose own date differs carries it on its label, because
the history has two dates and the merge must not invent one. `## [Unreleased]`
is not a release: it gets no page, and it stays at the top of the file.

A level-two heading is where the merge could silently drop a section, so the
merge is verified by content rather than by the generator: section counts per
source, the merged version set against the exact union, and every source `###`
title present both as a substring and, after stripping the component prefix, as
an identical heading. Counting `##` headings rather than releases overcounts by
one here, which is how the empty `[Unreleased]` block was caught.

- newsgen reads one file and writes `docs/news/<version>.md`, the index, the
  canonical `releases.json`, and `docs/news/redirects.json`. The redirect table
  is what keeps the retired `/news/<component>/<version>/` URLs alive; it is
  generated beside the pages so it cannot drift from them.
- release.sh takes one `--version`, keeps commit and tag (the Woodpecker
  pipeline that will own them does not exist yet), and exits 3 when the commit
  set justifies no release, so a pipeline can finish green without tagging.
- The consumers of the two files follow: the deploy workflow's tag gate and
  release-notes extraction, the zip contents, the update check's changelog
  links, the packaged-path note, the docs skill, and newsgen's tests.

The per-component detail survives as labelled sections inside each release, so
a reader still learns whether archied or the agent changed; what goes away is
the separate numbers and the separate pages.
2026-09-22 17:18:06 +10:00
sam 10b755468e docs(prds): decide how the merged history represents two dates per version
A version both components released carries one heading and one date: the newest among
its sections, because a version's date is when its last part shipped. Where a
component's own date differs, that component's section label carries its own, so the
per-component fact survives the merge instead of being collapsed into the heading.

The ambiguity is historical only -- one version stream with one tag gives a version
exactly one date -- so the rule represents the merged past rather than a design that
must hold.

The same section records how the merge is verified: by content, not by the generator
exiting zero. The section count per source, the merged version set equal to the union
of both, and every title still present; a generator agreeing with the file it just
wrote is evidence of nothing.
2026-09-22 17:09:04 +10:00