271 Commits
Author SHA1 Message Date
sam 32fbf8b69c refactor(gateway,ui): the page catalogue is generated from the router (#2050)
The assistant's catalogue was a 33-entry literal in Go, hand-maintained beside
the dashboard's routes: eight real pages were missing from it, so page_index
could not name them, and descriptions had drifted where both copies existed.

The routes move to ui/src/router/routes.ts, free of component imports, and
ui/scripts/pages.ts writes the catalogue from them. The nav and page_index now
read the same generated file, and task pages:check fails when it is stale, the
way the proto, sqlc and OpenAPI outputs do.
2026-11-21 03:53:10 +11:00
sam a8d1de8b5e fix(prompts): mark forge-authored text as untrusted data (#1976) 2026-11-14 20:09:19 +11:00
sam 48c28b36ba fix(gateway): bound task titles in the /tasks and /agents listings (#1076) 2026-11-14 15:29:36 +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 851cb78b04 fix(chat): a failed turn reads as a plain sentence, shown as an error 2026-11-13 13:16:11 +11:00
sam d0118756d7 refactor(gateway): the turn owner ID is made once by the composition root (#1928) 2026-11-13 03:57:05 +11:00
sam afaea346ee refactor(access): authorization takes the caller's context instead of a stored one (#1925) 2026-11-13 03:54:05 +11:00
sam c5f24ec914 chore: delete code no binary reaches
Removes the Kit task-tool result shim (and with it the MCP go-sdk
dependency), the messaging enable/disable/restart helpers and channel
rebuild closures nothing calls since channels became extensions, the
unused messaging capability, ephemeral and text-fallback types, and
single stragglers in telemetry, releaseupdate, skill, storepkg and
webui. The egress sandbox relay stays for #1867.
2026-11-13 03:33:32 +11:00
sam ff8615b090 feat(gateway): stream model reasoning as reasoning chat events (#1907)
The ai-sdk FullStream drain moves from the archiegateway composition into
internal/gateway (DrainStreamParts), next to the TurnStream it feeds, and
gains a StreamPartReasoningDelta case: each reasoning delta is forwarded on
the new optional ReasoningStream method, which localChatStream turns into a
ChatEvent{Kind: "reasoning", Text: delta} on the same stream. done/error
semantics are unchanged, and the FullStream is still drained to close when no
stream is attached.
2026-11-13 00:21:23 +11:00
sam fe8afb18d0 fix(gateway): a failed chat turn shows plain wording, not the provider's error (#1902)
deploy / plan (push) Canceled after 0s
deploy / gate (push) Canceled after 0s
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
ci/woodpecker/push/deploy Pipeline was canceled
2026-11-12 23:11:07 +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 255e0c7ee0 feat(chat): titles read the reply too, and session memory sees what it already holds
deploy / plan (push) Successful in 7s
deploy / archied-image (push) Successful in 30s
ci/woodpecker/push/deploy Pipeline was successful
deploy / gate (push) Successful in 7m39s
deploy / agent-image (push) Skipped
deploy / dist-zip (push) Skipped
2026-11-11 00:10:00 +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 e5e968780f fix(chat): the conversation picker reads as the panel's title, and titles name the subject, not the mood
ci/woodpecker/push/deploy Pipeline was successful
deploy / gate (push) Successful in 7m24s
deploy / agent-image (push) Skipped
deploy / archied-image (push) Canceled after 38s
deploy / plan (push) Successful in 9s
deploy / dist-zip (push) Canceled after 0s
2026-11-10 23:53:24 +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 13ec693726 fix(gateway): let a streamed chat turn finish after its stream closes (#1848)
deploy / plan (push) Successful in 7s
deploy / gate (push) Successful in 7m49s
deploy / agent-image (push) Successful in 12s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 2m24s
2026-11-10 20:14:04 +11:00
sam 3b840d7847 fix(daemon): drop PR review activity from authors without write access (#1830)
Adds a forge HasWriteAccess call; the review scan publishes only
collaborators' reviews and comments, and issue_list marks forge text
as untrusted.
2026-11-09 09:41:39 +11:00
sam 98f5af3eef refactor(ui): merge the harness settings page into agent profiles
deploy / plan (push) Failing after 2s
deploy / gate (push) Skipped
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
deploy / dist-zip (push) Skipped
The harness page's setup terminal targets the Kit agent profiles, so the
two pages were two halves of one flow split across routes: with no Kit
profile the harness page dead-ended in a disabled 'No profiles
configured' select while the place to create one sat on another page.

/settings/agent-profiles now carries the profiles editor and a 'Harness
sign-in' section (setup terminal plus the credential-bindings sign-in
table), and /settings/harness redirects to it. The bindings re-read when
a terminal session ends so a fresh capture shows immediately, and a
null-seeded agent-profiles document now renders the empty state instead
of a bare add form. The gateway page registry names the merged page.
2026-11-09 02:03:20 +11:00
sam 074ebbd931 fix(chat): keep long turns alive, record and log why a turn failed (#1813)
deploy / plan (push) Failing after 1s
deploy / gate (push) Skipped
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
deploy / dist-zip (push) Skipped
2026-11-08 23:03:04 +11:00
sam 6e718e165a feat(curator): issue_list and issue_create tools via the daemon (#1770)
Quality / check (push) Successful in 4m6s
deploy / gate (push) Successful in 4m30s
deploy / archied-image (push) Successful in 2m50s
deploy / agent-image (push) Successful in 12s
deploy / dist-zip (push) Skipped
2026-11-03 08:12:05 +11:00
sam abcb72a76a feat(curator): dry-run self-intake pass with run inspection tools (#1770)
Curators could only reach the workflow/integration tools; there was no way
to survey task runs. Adds run_list/run_events to the shared registry
(guarded as read on task kind), attaches the instance's acting principal
to curator model calls so guarded tools authorize, and records a pass's
final text as a pass.summary action so the report is inspectable. Ships a
dry-run self-intake definition in dev.toml/config.example.toml declaring
only those two tools, so it cannot file issues yet.
2026-11-03 02:35:06 +11:00
sam 003771ca48 feat(access): denial retention knob, State Store sweep and dashboard denials page (#1842)
Add [access].denial_retention (default 90 days, matching the audit-retention
seed) wired through config defaults and validation; the State Store sweeps
denial records older than the configured age hourly via the new
access.DenialPruner / PruneDenials store query. The dashboard gains
GET /api/access/denials (read_audit-gated, so org admins/owners see their
org's records; the store scopes by the credential's org) and an
/org/denials page backed by a Pinia store.
2026-10-31 14:23:31 +11:00
sam c3d49cbc6c feat(webui): park model credential failures with a recovery link, add Model setup step, readiness badges, and move audit to the organisation 2026-10-27 11:06:18 +11:00
sam 6f57d38669 feat(webui): offer each organisation page only to callers its API write allows, and move appearance to the account menu 2026-10-27 10:47:14 +11:00
sam d60995af43 fix(orgs): layer only the fields an org document sets, retry alerts on a failed lookup, and key chat sessions by org 2026-10-27 10:38:00 +11:00
sam 472d9d8b10 feat(messaging): run a channel per organisation and deliver only through the owner's 2026-10-27 10:38:00 +11:00
sam 8150df8d81 feat(scheduling): resolve the issue discovery rule per organisation 2026-10-27 10:38:00 +11:00
sam 90deba8472 fix(gateway): chat /cancel declines through the task-action service so the run stops 2026-10-27 10:00:54 +11:00
sam 4de8882ef5 fix(gateway): require a remote check before claiming branch or PR state
The chat agent read only its local checkout, so an unfetched workspace made it report that no task branch or PR existed and that shipped UI code did not exist. Add a core rule: refresh from the remote or check the forge before describing branches, commits, pull requests or the default branch, and say the answer is local-only when it cannot.
2026-10-26 18:28:32 +11:00
sam c4c50ea70d fix(gateway): cap task_spawn titles and carry instructions into the body 2026-10-26 18:24:47 +11:00
sam e85719f2d2 fix(controlplanerpc): attribute chat workflow drafts so saves succeed 2026-10-26 18:24:46 +11:00
sam b701f60a99 feat(scheduling): schedules and runs in the State Store with grid timing and run history
Schedules leave the schedules control-plane resource for State Store tables
behind a ScheduleService contract. A run is claimed per schedule slot, missed
slots fire once, the next run stays on the schedule's grid, cron is read in the
schedule-settings time zone, and failed runs are recorded and advance. Three
failures in a row raise a schedule.failing alert. A fired run records a
schedule-fired capture. Run history is pruned by age and count.

Removes the chat and spawn-task runners, the dangerous-payload guard and the
old schedules settings page.
2026-10-26 00:49:24 +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 2d2ca156d8 feat(ui): unified audit page with server filters and live tail 2026-10-25 22:09:25 +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 340223de2e feat(modelloop): run a step's tool calls in parallel as each tool's classification allows 2026-10-25 16:45:34 +11:00
sam 75c1dbf83c fix(access): check the policy version before each decision
archied, archie-ui and the tool gateway re-read the stored policies on a 30s
ticker, so a forbid written seconds earlier did not stop a run. One
instance-wide revision now moves inside the transaction of every policy write,
and a decision reads it first and rebuilds the engine only when it moved.

A version read that fails, or a policy list that fails after a bump, refuses
with ErrChainUnavailable instead of standing on the last chain, so three call
sites now treat unavailable as availability rather than denial: dispatch leaves
the capture for the next cycle, a task start parks transient, and the tool
gateway reports the tool as unavailable.
2026-10-25 16:21:01 +11:00
sam e8a60c4abd refactor!: waiting_human becomes waiting_approval, with the approval kind on each task 2026-10-24 23:45:20 +11:00
sam 974c93498a fix(gateway): save a messaging session instead of requiring web visibility 2026-10-20 03:12:40 +11:00
sam 1b2a8eec7c feat(chat): ask several questions in one interaction with ask_questions
A turn can pose a questionnaire (single and multiple choice, free text,
skippable) and read the answers back, rendered in the chat with the
shadcn-vue questionnaire. The gateway contract gains a questionnaire ask and a
can_question capability; answers travel as a JSON object keyed by question name
and are checked against the questions that were asked.
2026-10-19 03:30:47 +11:00
sam 889856aa81 feat(ui): Build with Archie runs on the chat system, floats over the canvas and keeps its conversation
Each workflow has its own persisted conversation, rendered like the chat panel.
The canvas and YAML go read-only while Archie works instead of inert. The code
block highlighter loads Go and TOML and drops jsx, tsx and vue.
2026-10-19 02:43:54 +11:00
sam 991b40047a fix(ui): Instructions replaces SOUL in routes and agent pages; terse alerts; missing-key hint 2026-10-18 19:27:11 +11:00
sam 846626fabf feat(gateway): read instructions and access policies from the workflow tools
settings_get now reads three more kinds:
- soul, the instruction text layered into a workflow run;
- task-policy, the diff cap and alert delivery settings;
- org-model-policy, which models an org may use.

None of them holds a secret value: task-policy's notify_secret and the
secrets elsewhere in the readable kinds are SecretRef references (engine and
key), never the resolved value.

access_policies_list is new: the caller org's Cedar policies (id, level,
scope, text), and the instance policies when the caller owns the instance,
which is what the dashboard lists for the same read. It is guarded as
access.ActionRead on access.KindPolicy, the check the dashboard makes.
IntegrationSource gained Policies, implemented over the State Store's
ListPolicies.

workflow_get now says how its instructions field layers: after the
instance's and the organisation's, before the repository's.
2026-10-18 02:39:25 +11:00
sam 7768fa808d fix(gateway): workflow and integration tools ask the access policies as their caller 2026-10-18 02:35:59 +11:00
sam 39c3c47ea2 feat(gateway): workflow and integration tools for chat and Kit harnesses alike 2026-10-18 02:32:30 +11:00
sam b4595bf8bb feat(workflows): iterate on a workflow's draft with Archie from the canvas 2026-10-18 02:27:41 +11:00
sam 1cd0ed22f5 refactor(curator): rename SessionSummary to SessionRef 2026-10-17 17:12:52 +11:00
sam f45ea9e0aa feat(workflow): configure review precision and approval on the review.pr step 2026-10-17 17:00:55 +11:00