237 Commits
Author SHA1 Message Date
sam ee66e4f0f3 refactor(prompts): the last three instructions written in Go are files (#2051)
AGENTS.md sends every instruction to a file in internal/prompts, and the
workspace scoping rule, the PR-review adversary mission and the model probe
were the three that still read as Go string literals. The text is unchanged:
the templates render the same bytes the concatenations built.
2026-11-21 03:48:42 +11:00
samandCopilot 64dfad6d53 feat(runs): add typed results and model aliases (#2043)
Also fix repository-free message.send validation (#2046) and add a single-binary development smoke path (#1977).

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
2026-11-18 23:47:35 +11:00
sam ce70d4f3ee feat(runs): workflow documents take today's step shape, references and when (#2039)
A step is id/type/settings with when and on_failure; the five kinds become
the types agent.run (inline mission), connector.action, approval.wait,
run.notify and workflow.sleep. Documents declare inputs, repository,
instructions, identity and profile; references are {{ task|inputs|steps }}
checked at save. Any number of approval steps, each asking only about what
was held since; actions still held at the end are put to people before the
run finishes. Triggers are refused for a workflow they can't start, and the
workflows API lists, reads and saves documents beside a step-type catalog.

Copied from internal/domain/workflow: definition.go, step_refs.go,
step_flow.go's checks, control_steps.go's when parser, vocabulary.go and
task/interface.go. stableid moves to internal/platform.
2026-11-17 18:43:45 +11:00
sam a8d1de8b5e fix(prompts): mark forge-authored text as untrusted data (#1976) 2026-11-14 20:09:19 +11:00
sam 6c287b48e6 fix: return write-side close errors; the gate checks unhandled errors 2026-11-14 03:31:46 +11:00
sam 41f44c43a1 feat(workflow): issue routing is a control-plane setting edited in the dashboard (#1959)
Label to workflow rules and a default workflow are the intake-routes
resource: ordered, case-insensitive, first rule wins, seeded with bug to
tdd, feature to feasibility, default triage. A write naming an undefined
workflow or an empty label is refused. The daemon reads it through the
workflow definitions client when pinning a task and at intake.

The kind indirection only carried this routing, so it is removed: the
per-kind NATS subjects (every consumer already bound archie.task.>) are
one subject, the envelope and playbook triggers lose their kind, and
x-intake-routes is dropped. The dashboard gets an Issue routing page
under Automation; the trigger card reads the same setting.
2026-11-13 20:28:52 +11:00
sam ca4b039cb4 feat(workflow): serve step type titles with the step vocabulary (#1961)
Each step type declares its title beside its factory and settings; the
control plane serves it in x-step-types, and the dashboard reads it instead
of a hand-written TYPE_TITLES table. Parallel and switch are YAML shapes, not
registered types, so their titles stay with the graph.
2026-11-13 20:26:27 +11:00
sam 841c6aea16 feat(workflow): serve which workflows start each one; the trigger card stops re-deriving it (#1960) 2026-11-13 18:01:33 +11:00
sam f4c304cfba refactor: log through the injected logger with context; NATS handlers root in the registering context (#1927) 2026-11-13 03:56:12 +11:00
sam 60c0f19e63 fix(forge): a close refused for open dependencies is a typed error across the boundary (#1922) 2026-11-13 03:47:34 +11:00
sam 606da1aee5 chore(workflow): remove the needs block (#1888)
ci/woodpecker/pr/quality Pipeline was successful
Quality / check (pull_request) Successful in 3m8s
2026-11-13 02:11:22 +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 4728c8c253 feat(usage): report model usage per org with identity and cost (#1855)
Model usage was recorded per call and never read, so an org could not see
what it spent. Add the read side:

- model_usage carries identity_id. Task calls take it from the task row,
  chat and curator calls from the calling principal carried in the usage
  record, so an outbox replay keeps its attribution. Existing task rows are
  backfilled from tasks.
- StatsService.UsageTotals sums the caller org's rows by UTC day, source,
  provider, model and identity. The org comes from the principal, with no
  org parameter, so cross-org reads do not exist.
- GET /api/usage prices tokens at the catalog's list rate, netting cache
  hits, and reports calls to unpriced models as tokens only. The published
  catalog view now carries each model's cost.
- A new org Usage page behind a read_usage grant: admin and owner only,
  with a 7, 30 or 90 day range, totals, the daily series, and model, source
  and identity breakdowns. The org shell keeps it on the caller's own org.
2026-11-11 02:15:29 +11:00
sam bc16b74c93 fix(prompts): correct the product guide, and make chat replies scannable and honest about their own history
deploy / plan (push) Successful in 8s
ci/woodpecker/push/deploy Pipeline was successful
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / gate (push) Canceled after 5m8s
2026-11-11 00:04:43 +11:00
sam 44237b448b refactor(prompts): every model prompt is a file in internal/prompts
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / plan (push) Successful in 6s
ci/woodpecker/push/deploy Pipeline was canceled
deploy / gate (push) Canceled after 2m58s
2026-11-11 00:01:43 +11:00
sam 5ea115746c fix(dashboard): blocked tasks say what they need, and a provider refusal names its fix
deploy / plan (push) Successful in 6s
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / gate (push) Canceled after 5m37s
ci/woodpecker/push/deploy Pipeline was canceled
2026-11-10 23:19:29 +11:00
sam e3ffefdc7d fix(identity): use System as the one root identity and record who created every task (#1851)
deploy / plan (push) Successful in 25s
deploy / gate (push) Successful in 7m57s
deploy / agent-image (push) Successful in 21s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 2m12s
Drop the bot_user-derived root identity and the empty-identity sentinel. System
polls forge connections and owns instance-level work; a polled task stores the
polling identity, task_queued and work_request_submitted carry task id, actor
and principal, and an empty task identity is refused. Migration 0072 moves
empty tasks.identity, the identity-grants root key and the old root's
connection permits to System so a re-poll dedups.
2026-11-10 20:01:16 +11:00
sam e34941b1eb fix(workflow): record a close refused for open dependencies instead of parking (#1845) 2026-11-09 14:40:58 +11:00
sam 67c9b7a00a fix(workflow): publish a baseline repair as a PR before the task continues (#1844)
Dependents now wait for the baseline gate to pass on the base branch
instead of a specific branch merging.
2026-11-09 14:40:58 +11:00
sam bcbd09fc08 fix(workflow): a budget stop in a parallel branch asks to continue and resumes the branch (#1838) 2026-11-09 14:37:22 +11:00
sam e75d5c8ade fix(store): a restart re-queues a running task at its interrupted step and parks it after 3 restarts (#1841)
deploy / plan (push) Successful in 7s
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / gate (push) Canceled after 4m4s
2026-11-09 14:36:08 +11:00
sam dc2c3b983f feat(workflow): a budget continuation resumes at the stopped step with its conversation (#1832)
deploy / plan (push) Successful in 7s
deploy / gate (push) Successful in 8m12s
deploy / agent-image (push) Successful in 28s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 2m11s
2026-11-09 12:44:01 +11:00
sam f27e9853cc test(workflow): budget stop asks to continue and resumes on approval (#1832) 2026-11-09 09:41:46 +11:00
sam 561863613f feat(workflow): agent.run asks to continue when it reaches its step budget (#1832) 2026-11-09 09:41:46 +11:00
sam e0eb1dfdb7 fix(workflow): refuse an output named result beside an agent.run result capture at save time (#1384)
deploy / plan (push) Successful in 7s
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / gate (push) Canceled after 1m25s
2026-11-09 09:04:17 +11:00
sam d11a0cd245 fix(workflow): one baseline fix per repository revision, drop download noise from gate output (#1806)
deploy / plan (push) Successful in 14s
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / gate (push) Canceled after 1m2s
2026-11-08 17:23:21 +11:00
sam 98fb9dfddf feat(workflow): task, workflow, step and model attributes on run, step and agent spans (#1803)
deploy / gate (push) Successful in 16m25s
deploy / agent-image (push) Successful in 22s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 7m25s
2026-11-08 17:00:42 +11:00
sam cf1be16763 fix(controlplane): repair a stored workflow collection that no longer validates (#1622) 2026-11-08 05:49:40 +11:00
sam 03c25e7214 docs(workflow): say repo.commit never runs the checkout's git hooks
Quality / check (push) Successful in 3m44s
deploy / gate (push) Successful in 4m45s
deploy / archied-image (push) Successful in 3m0s
deploy / agent-image (push) Successful in 12s
deploy / dist-zip (push) Skipped
Refs #1792
2026-11-05 00:26:20 +11:00
sam c30624a59e feat(workflow): a handoff starts a separate linked run of the next workflow (#1791)
Quality / check (push) Successful in 4m12s
deploy / gate (push) Successful in 4m42s
deploy / archied-image (push) Successful in 3m13s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
2026-11-03 20:56:03 +11:00
sam 88e86776e8 feat(forge): add CreateIssue to the forge contract (#1770)
Quality / check (push) Successful in 4m10s
deploy / gate (push) Successful in 4m43s
deploy / archied-image (push) Successful in 2m54s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
Issue-level writes could comment and close but not open an issue, so no
curator or workflow stage can file its own work yet. Adds the rpc to
proto/forge/v1, regenerates the contracts, and threads it through the
domain interface, forgerpc client/server (comment permission, like
CloseIssue), forgeext, and the archipelago SDK + gitea/github plugins.
2026-11-03 02:04:56 +11:00
sam 6f10ecc04f feat(agentexec): record each agent run's transcript and show it per step (#1718)
The loop runner hooks every model call and tool call and reports ordered,
redacted, clipped entries. Each is persisted as an agent_transcript task
event through InsertEvent, left out of the timeline read, and served per
attempt at /api/tasks/{id}/transcript. The step run view shows it with Trace.
2026-11-01 22:09:53 +11:00
sam 3977eaad68 fix(workflow): make the repository optional for the triage workflow (#1578) 2026-10-31 00:36:10 +11:00
sam 5485dc4690 chore(workflow): finish dropping the unread step-type catalogue accessors (#1014)
Manager.StepTypes and Providers had no reader; the catalogue they were meant
to feed is not missing -- Registry/Settings serve it as x-step-types in the
workflow-definitions schema, read by the dashboard workflow editor and the
gateway's workflow_step_types tool. Remove the write-only providers field
the accessor deletion left behind, and pin that production reader in
controlplanerpc so a dropped schema extension fails the gate.
2026-10-30 01:31:36 +11:00
sam 0a1aa8b3c2 fix(prreview): classify comment lines against the diff before posting 2026-10-30 00:35:36 +11:00
sam 8aa65bc7b4 fix(workflow): close a budget-stopped stage with its findings as the outcome 2026-10-30 00:06:38 +11:00
sam 3c4b7b5877 fix(workflow): keep a stopped stage's notes in the parked detail 2026-10-27 15:22:42 +11:00
sam be0f6f5ab7 fix(gateway): name a plan wait's workflow from its run, not the next one
workflow.approve pre-writes the task's workflow column with the workflow
that runs once approved, so task_list named a workflow that had not
started while the task's own log named the one that produced the plan.
Chat now names the compiled workflow through the pinned definition for a
plan wait, matching the log.
2026-10-26 18:32:25 +11:00
sam c00a90c9ca fix(workflow): report a parked run's outcome as the task's status
A run that parked left tc.Outcome empty, so the taskrun response carried an
empty status and the daemon logged 'taskrun run recorded no outcome' for a run
that had recorded one, then retried the park it could not apply.

Record the outcome once the parked transition lands, so a budget stop and every
other park surface with the reason the run parked.
2026-10-26 18:28:32 +11:00
sam d7d1bd4556 fix(workflow): record the own-PR flag after the review stages that allocate it
StagePRReviewAndOpenPR set tc.prReview.ownPR before the decision stages ran,
but intake allocates tc.prReview, so every implement run dereferenced a nil
state at repo.open-pr and the agent container panicked with exit code 2
before opening the pull request.
2026-10-26 18:07:01 +11:00
sam 6f8371a7bf feat(workflow): message.send step delivers text through archied's messaging client 2026-10-26 00:56:07 +11:00
sam 656feab2a4 refactor(logging): log with the caller's context so records carry trace ids 2026-10-25 23:30:01 +11:00
sam 0880e6a01c feat(natsrpc): propagate trace context across NATS and into task runs 2026-10-25 23:03:55 +11:00
sam 7d9c40d79d fix(workflow): review a task's own pull request as a comment
GitHub refuses REQUEST_CHANGES from a pull request's author, so a blocking
finding on the PR a task opened lost every finding. The retry's identical
refusal is now reported once, and forge errors drop the gRPC framing.
2026-10-25 17:57:20 +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 fc609171ca docs: clarify reviewer in implement finish summary 2026-10-25 17:20:13 +11:00
sam 2399da1f8d docs(workflow): name no human approver in the plan document 2026-10-25 17:19:06 +11:00
sam d699b9afba feat(workflow): approve a PRD as one structured document
The prd step returns the PRD as structured fields and human.approve takes
them as its document. The plan text every surface reads and the approval
card's layout are both rendered from that one document, so what the human
approves is what the implement workflow is handed. Replaces the separately
generated OpenUI view, which could drift from the plan.
2026-10-25 16:53:17 +11:00
sam 54a78175b4 feat(workflow): render a PRD's generated view on the plan approval card
agent.run gains views: the agent may return an OpenUI Lang view of its
answer through an optional view tool, read as steps.<id>.view. human.approve
stores it as the task's plan_view, and the approval card renders it with
the dashboard's own components, falling back to the plan text when there
is no view or it does not parse. The feasibility prd step uses it.
2026-10-25 16:33:04 +11:00
sam 958561d255 feat(egress): record a test run's deliveries instead of sending them
A test run used to suppress only forge and push writes, which named one
destination among many. Deliveries now have one seam: TaskContext.Deliveries
records each as "would ..." and performs none, and a recording egress
session does the same for a Kit run's HTTP writes and central tool calls,
answering them synthetically. Provider hosts stay live, since model traffic
is how a test run reads. Native containers have no proxy (archie-core-n8d3).
2026-10-25 16:01:06 +11:00