Compare commits

...
219 Commits
Author SHA1 Message Date
sam c3e64e5485 chore(release): v1.62.0
deploy / dist-zip (push) Successful in 5m9s
deploy / plan (push) Successful in 8s
deploy / agent-image (push) Successful in 3m15s
deploy / gate (push) Successful in 6m49s
deploy / archied-image (push) Successful in 2m36s
2026-11-10 09:48:01 +00:00
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 e3ffefdc7d fix(identity): use System as the one root identity and record who created every task (#1851)
deploy / plan (push) Successful in 25s
deploy / archied-image (push) Successful in 2m12s
deploy / gate (push) Successful in 7m57s
deploy / agent-image (push) Successful in 21s
deploy / dist-zip (push) Skipped
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 04798b990a docs(changelog): notes for the changes since 1.61.3
deploy / plan (push) Successful in 8s
deploy / agent-image (push) Successful in 24s
deploy / gate (push) Successful in 8m52s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 3m25s
2026-11-10 19:28:08 +11:00
sam 0e889977c0 fix(archied): resolve merge, close and issue tools through the repository's connection (#1847)
deploy / dist-zip (push) Canceled after 0s
deploy / plan (push) Successful in 6s
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / gate (push) Canceled after 2m50s
2026-11-10 19:25:15 +11:00
sam 47e3d8d837 Merge pull request 'Expose all task actions in the task detail header (archie)' (#1846) from feat/1000000000000000-expose-all-task-actions-in-the-task-detail-header into main
deploy / gate (push) Successful in 7m43s
deploy / agent-image (push) Successful in 14s
deploy / plan (push) Successful in 6s
deploy / archied-image (push) Successful in 2m27s
deploy / dist-zip (push) Skipped
Reviewed-on: #1846
2026-11-10 06:54:28 +00:00
archie 9a9629400e Expose all task actions in the task detail header (archie)
Quality / check (pull_request) Successful in 13m0s
ci/woodpecker/pr/quality Pipeline was successful
2026-11-10 16:54:00 +11:00
sam 0525edd3bb fix(postgres): blocker-changed marks only the org whose resource changed (#1839)
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 8m39s
deploy / archied-image (push) Failing after 13m38s
deploy / plan (push) Successful in 7s
deploy / agent-image (push) Canceled after 2s
2026-11-09 14:40:58 +11:00
sam 82313e4af5 feat(state-store): flag parked tasks when the resource their blocker names changes (#1839) 2026-11-09 14:40:58 +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 20ffe63367 fix(worktree): object-not-found match tolerates a successful push
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 8s
deploy / gate (push) Canceled after 1m47s
2026-11-09 14:40:19 +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 a3fdbddfc0 fix(worktree): match object-not-found by message too, as push transports may flatten it (#1843) 2026-11-09 14:37:18 +11:00
sam 70eef0ec99 fix(secretengine): report a full volume as an environment failure, not a bad credential (#1842) 2026-11-09 14:37:17 +11:00
sam 96236b6186 fix(worktree): rebuild the mirror and retry once when a push hits a missing object (#1843) 2026-11-09 14:37:17 +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 / agent-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / gate (push) Canceled after 4m4s
deploy / archied-image (push) Canceled after 0s
2026-11-09 14:36:08 +11:00
sam f44db54948 fix(archied): the watchdog heartbeat proves liveness and a stalled run loop reports degraded readiness (#1840)
State Store calls the daemon makes without a deadline now get one.
2026-11-09 14:36:08 +11:00
sam 44b52c54c0 build(agent): bake task into the agent image so the repository gate never fetches it per run
deploy / plan (push) Successful in 7s
deploy / dist-zip (push) Canceled after 0s
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / gate (push) Canceled after 8m56s
2026-11-09 14:27:18 +11:00
sam ec79c8123e fix(worktree): TestAwaitSpace recovery rows get a deadline a loaded host cannot run out 2026-11-09 14:27:18 +11:00
sam 4b0adac674 fix(daemon): open the task log before the workflow-identity check so its parks are logged
deploy / gate (push) Successful in 8m37s
deploy / plan (push) Successful in 6s
deploy / agent-image (push) Successful in 23s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 2m4s
2026-11-09 13:55:19 +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 e3dc7fc2e9 fix(issuerpc): list only issues opened by users with write access (#1830)
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / gate (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / plan (push) Canceled after 7s
Adds Issue.Author to the forge contract; the daemon drops issues from
authors without write access and fails the listing closed when the forge
cannot answer.
2026-11-09 12:43:44 +11:00
sam 2ae471398b test(gatewayrpc): an unreachable secret engine answers Unavailable
deploy / agent-image (push) Canceled after 0s
deploy / plan (push) Successful in 7s
deploy / archied-image (push) Canceled after 0s
deploy / gate (push) Canceled after 2m30s
deploy / dist-zip (push) Canceled after 0s
2026-11-09 12:39:32 +11:00
sam 6437c8009c fix(gatewayrpc): secret check reports an unreachable engine as unavailable, not as a missing key
deploy / plan (push) Successful in 13s
deploy / dist-zip (push) Canceled after 0s
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / gate (push) Canceled after 1m47s
2026-11-09 12:39:12 +11:00
sam f9b6077595 fix(ui): Dismiss all tooltip opens below so the unread badge stays visible (#1837)
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
deploy / plan (push) Successful in 9s
deploy / archied-image (push) Successful in 2m38s
deploy / gate (push) Successful in 8m1s
2026-11-09 09:41:50 +11:00
sam 00f62a5772 fix(configuration): startup setting descriptions in sentence case saying what a change needs (#1836) 2026-11-09 09:41:50 +11:00
sam 3db75f9e28 fix(postgres): drop the removed schedules kind's apply status so archied is not degraded (#1834) 2026-11-09 09:41:50 +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 fce5fab2a1 feat(ui): workflow row actions, throttled live reloads, toolbar and layout fixes (#1833) 2026-11-09 09:41:39 +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 8e5d4e8061 fix(worktree): rebuild the repo mirror when a refresh fails on a corrupt mirror (#1831) 2026-11-09 09:41:39 +11:00
sam c98666d6b7 fix(worktree): stale-clone reclaim keeps clones with uncommitted or unpushed work (#1829) 2026-11-09 09:41:33 +11:00
sam 055f2da9cd fix(daemon): reclaim stale task clones when the work volume is full; clean up dead tasks too (#1829) 2026-11-09 09:41:33 +11:00
sam fd14b8d358 fix(ui): toast on workflow enable/disable; editor toolbar wraps instead of crushing the run picker and Publish
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
deploy / gate (push) Skipped
deploy / dist-zip (push) Skipped
deploy / plan (push) Failing after 2s
2026-11-09 09:26:40 +11:00
sam 2365e5ede9 fix(archied): model catalog load no longer reverts control-plane execution budgets to the file's
deploy / agent-image (push) Canceled after 0s
deploy / archied-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / gate (push) Canceled after 1m46s
deploy / plan (push) Successful in 7s
2026-11-09 09:24:51 +11:00
sam c9248a251a fix(releaseupdate): label the daemon release row Services, not Gateway
deploy / dist-zip (push) Skipped
deploy / gate (push) Skipped
deploy / plan (push) Failing after 2s
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
2026-11-09 09:08:39 +11:00
sam eb4b2fab5a fix(ui): dashboard shows five tasks needing attention, not every one
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
deploy / gate (push) Failing after 1m14s
deploy / plan (push) Successful in 7s
deploy / dist-zip (push) Skipped
2026-11-09 09:05:47 +11:00
sam e0eb1dfdb7 fix(workflow): refuse an output named result beside an agent.run result capture at save time (#1384)
deploy / dist-zip (push) Canceled after 0s
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / gate (push) Canceled after 1m25s
deploy / plan (push) Successful in 7s
2026-11-09 09:04:17 +11:00
sam 031291a4bf fix(daemon): clone free-space floor is 1 GiB, not 5; clones share the mirror's objects
deploy / dist-zip (push) Canceled after 0s
deploy / plan (push) Successful in 7s
deploy / agent-image (push) Canceled after 0s
deploy / archied-image (push) Canceled after 0s
deploy / gate (push) Canceled after 3m17s
2026-11-09 09:00:46 +11:00
sam 618b22db15 fix(releaseupdate): canary ignores task alerts, which the park rate already judges
deploy / plan (push) Successful in 6s
deploy / agent-image (push) Canceled after 0s
deploy / gate (push) Canceled after 4m28s
deploy / archied-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
2026-11-09 08:56:22 +11:00
sam fc50b026cf docs(deployments): name the release pipeline, not one CI system's file
deploy / gate (push) Successful in 7m38s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 2m28s
deploy / agent-image (push) Successful in 22s
deploy / plan (push) Successful in 6s
2026-11-09 08:39:08 +11:00
sam e9f5d136b4 build(ui): drop the unused vue-sonner and vue-flow/controls dependencies
deploy / plan (push) Successful in 7s
deploy / archied-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / gate (push) Canceled after 3m21s
deploy / agent-image (push) Canceled after 0s
2026-11-09 08:35:44 +11:00
sam 403d5f8427 refactor: drop the unused access.PolicySource and the stale playbooks usage word 2026-11-09 08:35:44 +11:00
sam 5539835dd6 docs(deployments): agent image tags match the Woodpecker pipeline; drop the missing publish.sh
deploy / plan (push) Canceled after 8s
deploy / gate (push) Canceled after 0s
deploy / archied-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
2026-11-09 08:35:25 +11:00
sam b16dd6add4 refactor: delete unreferenced Go code (embedding contract, PolicySource, embedded changelog, ignored webui file) and the stale playbooks usage word 2026-11-09 08:35:25 +11:00
sam a053d98d7c refactor(kit): update capability types to use spec constants and add test for known capabilities
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 2m24s
2026-11-09 08:32:56 +11:00
sam f5a04ce8c5 refactor(archiegateway): own the chat task profiles; archied built a task creator it never read
deploy / agent-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / archied-image (push) Canceled after 0s
deploy / gate (push) Canceled after 22s
deploy / plan (push) Successful in 7s
2026-11-09 08:32:28 +11:00
sam 9616dd72ce refactor(playbook): drop the directory loader and docs left by the playbooks command
deploy / gate (push) Successful in 14m32s
deploy / plan (push) Successful in 7s
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Successful in 12s
deploy / archied-image (push) Successful in 3m2s
2026-11-09 07:53:02 +11:00
sam 6871abd7ee chore(lint): guard the messaging service's contract boundary with depguard instead of a test
deploy / plan (push) Successful in 6s
deploy / dist-zip (push) Canceled after 0s
deploy / gate (push) Canceled after 1m47s
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
2026-11-09 07:51:10 +11:00
sam 32fcbf1a2b chore(lint): guard the dashboard's daemon boundary with depguard instead of a test
deploy / archied-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / plan (push) Successful in 7s
deploy / agent-image (push) Canceled after 0s
deploy / gate (push) Canceled after 38s
2026-11-09 07:50:15 +11:00
sam 632ceb0f85 refactor: archieplaybooks is not required for some time now, webui is where playbooks are defined
deploy / agent-image (push) Canceled after 0s
deploy / plan (push) Successful in 7s
deploy / archied-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / gate (push) Canceled after 3m46s
2026-11-09 07:46:30 +11:00
sam 5414405ceb ci(woodpecker): add the Woodpecker pipelines that replace the Actions workflows
deploy / archied-image (push) Successful in 2m20s
deploy / gate (push) Successful in 8m56s
deploy / plan (push) Successful in 6s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
quality, deploy, release, canary and promote move to .woodpecker/. The
Gitea Actions files stay in place until the maintainer removes them, so
both paths are live for now.

deploy keeps its shape (plan -> gate -> images -> signed release) in one
workflow because Woodpecker shares nothing between workflows: the plan
env file, the built zip and the agent image digest pass through the
workspace. The gate drives the host daemon through the Go client with the
socket mounted, and the images are built with buildx so the digest the
release statement pins comes from --metadata-file.

Two behavioural changes: the userns preflight is gone (a docker-backend
step cannot create unprivileged user namespaces, and no test needs one),
and the zip is no longer published as a CI artifact (Woodpecker has none);
it ships through the OCI release, which is what install.sh reads.
2026-11-09 07:02:11 +11:00
sam cdbdbbc72d chore(release): v1.61.3
deploy / plan (push) Successful in 7s
deploy / agent-image (push) Successful in 2m44s
deploy / gate (push) Successful in 15m51s
deploy / archied-image (push) Successful in 3m32s
deploy / dist-zip (push) Successful in 3m17s
2026-11-08 15:47:31 +00:00
sam 2a04abb84e docs(ui): note the merged agent-profiles and harness settings page
deploy / dist-zip (push) Skipped
deploy / plan (push) Failing after 1s
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
deploy / gate (push) Skipped
2026-11-09 02:09:58 +11:00
sam 98f5af3eef refactor(ui): merge the harness settings page into agent profiles
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
deploy / gate (push) Skipped
deploy / dist-zip (push) Skipped
deploy / plan (push) Failing after 2s
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 d1b1bac4fb fix(presence): list only running agents; a finished task's agent is not stale
deploy / plan (push) Failing after 1s
deploy / agent-image (push) Skipped
deploy / gate (push) Skipped
deploy / archied-image (push) Skipped
deploy / dist-zip (push) Skipped
2026-11-09 01:53:42 +11:00
sam 45b368af2e docs(agentexec): drop history and refactoring narration from comments
deploy / plan (push) Failing after 2s
deploy / gate (push) Skipped
deploy / agent-image (push) Skipped
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Skipped
2026-11-09 01:45:07 +11:00
sam 0f6448c048 refactor(agentexec): delete unused runner injection seams, ServeCaptureMCP, an unreachable approval branch and orphan fixtures
deploy / agent-image (push) Skipped
deploy / plan (push) Failing after 1s
deploy / gate (push) Skipped
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Skipped
2026-11-09 01:43:53 +11:00
sam b15858adc9 fix(agentexec): clip tool detail on a rune boundary, stop resuming without a session, keep captures when the ready marker fails, log with context
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
deploy / dist-zip (push) Skipped
deploy / plan (push) Failing after 1s
deploy / gate (push) Skipped
2026-11-09 01:41:46 +11:00
sam 1ef576ca7b fix(agentexec): run gate commands as the harness user and reap the process group after each invocation
deploy / gate (push) Skipped
deploy / agent-image (push) Skipped
deploy / archied-image (push) Skipped
deploy / dist-zip (push) Skipped
deploy / plan (push) Failing after 7s
2026-11-09 01:40:10 +11:00
sam 50cb0b4276 fix(agent): point toolchains at their cache volumes so pnpm's store stays out of the worktree (#1815)
deploy / gate (push) Skipped
deploy / agent-image (push) Skipped
deploy / plan (push) Failing after 2s
deploy / archied-image (push) Skipped
deploy / dist-zip (push) Skipped
2026-11-09 01:35:18 +11:00
sam 472478cf83 refactor(state): delete the unused ArmedBindingsForSource RPC and query
deploy / plan (push) Failing after 2s
deploy / gate (push) Skipped
deploy / archied-image (push) Skipped
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Skipped
2026-11-09 01:22:02 +11:00
sam 90c7d137fb fix(ui): embed only the Latin IBM Plex subsets, woff2 only
deploy / plan (push) Failing after 1s
deploy / archied-image (push) Skipped
deploy / dist-zip (push) Skipped
deploy / gate (push) Skipped
deploy / agent-image (push) Skipped
2026-11-09 01:21:07 +11:00
sam 2d51cf5106 perf(daemon): dispatch captured events every second instead of every poll_interval; match bindings in memory
deploy / archied-image (push) Skipped
deploy / plan (push) Failing after 2s
deploy / dist-zip (push) Skipped
deploy / gate (push) Skipped
deploy / agent-image (push) Skipped
2026-11-09 01:19:50 +11:00
sam 1167f8a51e docs: add the Archie mark, wordmark, app icon and social card; show the wordmark in the README
deploy / gate (push) Skipped
deploy / plan (push) Failing after 1s
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
deploy / dist-zip (push) Skipped
2026-11-09 01:11:08 +11:00
sam 17e6e66e72 refactor(archied): delete the file-configured forge webhook receiver; forge webhooks arrive through event capture (#1817)
deploy / gate (push) Skipped
deploy / plan (push) Failing after 2s
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Skipped
deploy / archied-image (push) Skipped
2026-11-09 00:50:00 +11:00
sam fa76f4c994 fix(worktree): sign and attribute agent commits at push; forge git credentials (#1816, #1817)
deploy / agent-image (push) Skipped
deploy / plan (push) Failing after 7s
deploy / gate (push) Skipped
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Skipped
2026-11-09 00:11:54 +11:00
sam 21a523bd35 fix(gateway): report why curators are disabled instead of never reporting
deploy / archied-image (push) Skipped
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Skipped
deploy / gate (push) Skipped
deploy / plan (push) Failing after 2s
2026-11-09 00:11:03 +11:00
sam db377380a0 perf(ui): load route pages on demand
deploy / plan (push) Failing after 32s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Skipped
deploy / gate (push) Skipped
deploy / agent-image (push) Skipped
2026-11-09 00:05:39 +11:00
sam 81fcea7a03 fix(ui): keep blocked tasks out of pinned activity alerts 2026-11-09 00:05:39 +11:00
sam 011d22c24c fix(ui): read board and alerts once on load, not again on the first stream connect 2026-11-09 00:05:39 +11:00
sam 83c8614418 fix(statestore): start service health grace at boot, not at a peer's last report 2026-11-09 00:05:39 +11:00
sam ac98b68bda feat(archied): connection commit identity and SSH commit signing (#1816)
deploy / plan (push) Failing after 2s
deploy / archied-image (push) Skipped
deploy / dist-zip (push) Skipped
deploy / gate (push) Skipped
deploy / agent-image (push) Skipped
2026-11-09 00:05:32 +11:00
sam ad63692781 fix(archied): sign connection commits with the connection account (#1815)
deploy / plan (push) Failing after 12s
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
deploy / dist-zip (push) Skipped
deploy / gate (push) Skipped
2026-11-08 23:57:40 +11:00
sam 090b220d25 fix(ui): label resolved alerts in the activity feed
deploy / plan (push) Failing after 1s
deploy / archied-image (push) Skipped
deploy / dist-zip (push) Skipped
deploy / gate (push) Skipped
deploy / agent-image (push) Skipped
2026-11-08 23:56:41 +11:00
sam 514219b6a5 chore: ignore the pnpm store agents create in the worktree
deploy / archied-image (push) Skipped
deploy / dist-zip (push) Skipped
deploy / gate (push) Skipped
deploy / plan (push) Failing after 4s
deploy / agent-image (push) Skipped
2026-11-08 23:53:17 +11:00
sam 6a5ba67cf5 ci: keep the golangci-lint cache between quality runs
deploy / dist-zip (push) Skipped
deploy / gate (push) Skipped
deploy / plan (push) Failing after 10s
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
2026-11-08 23:34:33 +11:00
sam c09ece6064 fix(webui): hash, cache and gzip dashboard assets
deploy / plan (push) Failing after 8s
deploy / gate (push) Skipped
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
deploy / dist-zip (push) Skipped
2026-11-08 23:32:25 +11:00
sam 43ba64684e fix(webui): start a fresh event stream at recent activity, not the whole events table
deploy / plan (push) Successful in 25s
deploy / dist-zip (push) Canceled after 0s
deploy / gate (push) Canceled after 2m38s
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
2026-11-08 23:29:40 +11:00
sam 67fa57008e fix(ui): read alerts once per event burst, not once per replayed event
deploy / dist-zip (push) Skipped
deploy / plan (push) Failing after 1s
deploy / gate (push) Skipped
deploy / agent-image (push) Skipped
deploy / archied-image (push) Skipped
2026-11-08 23:21:06 +11:00
sam 074ebbd931 fix(chat): keep long turns alive, record and log why a turn failed (#1813)
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
deploy / gate (push) Skipped
deploy / dist-zip (push) Skipped
deploy / plan (push) Failing after 1s
2026-11-08 23:03:04 +11:00
sam 10d23e3e06 fix(ui): compare live reloads structurally instead of serialising them (#1812)
deploy / archied-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / gate (push) Canceled after 1m35s
deploy / agent-image (push) Canceled after 0s
deploy / plan (push) Successful in 26s
2026-11-08 23:01:10 +11:00
sam 6a4e1964f6 refactor(chat): one send path, drop POST /api/chat/message
deploy / plan (push) Successful in 8s
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
deploy / gate (push) Failing after 13m53s
deploy / dist-zip (push) Skipped
2026-11-08 18:34:26 +11:00
sam 5939ef6ff1 fix(postgres): write no audit row when retention prunes nothing (#1810)
deploy / archied-image (push) Successful in 2m55s
deploy / plan (push) Successful in 10s
deploy / agent-image (push) Successful in 12s
deploy / gate (push) Successful in 8m29s
deploy / dist-zip (push) Skipped
2026-11-08 17:27:30 +11:00
sam 1d9eff6529 fix(ops): log cancelled contexts at debug, one reconnect line per outage (#1809) 2026-11-08 17:27:30 +11:00
sam 6ae7f319cb fix(staterpc): log the cause of run credential lookup failures (#1808) 2026-11-08 17:27:30 +11:00
sam 260e9fc46e fix(agentworker): stop reporting task worker presence (#1807) 2026-11-08 17:27:30 +11:00
sam 52b5740c39 fix(daemon): cap tasks per issue poll and wait for disk before cloning (#1805)
deploy / plan (push) Successful in 1m6s
deploy / gate (push) Canceled after 11s
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
2026-11-08 17:26:00 +11:00
sam d11a0cd245 fix(workflow): one baseline fix per repository revision, drop download noise from gate output (#1806)
deploy / archied-image (push) Canceled after 0s
deploy / gate (push) Canceled after 1m2s
deploy / plan (push) Successful in 14s
deploy / agent-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
2026-11-08 17:23:21 +11:00
sam 860b2c85e0 fix(taskstate): retry transient parks with backoff, escalate when exhausted (#1804)
deploy / gate (push) Canceled after 2m21s
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 16s
2026-11-08 17:19:14 +11:00
sam af7577625f refactor(messaging): store Telegram's connection in extension-settings (#1802)
deploy / archied-image (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
deploy / gate (push) Canceled after 7m26s
deploy / plan (push) Successful in 11s
deploy / dist-zip (push) Canceled after 0s
2026-11-08 17:12:59 +11:00
sam 617a312ed5 ci(deploy): cancel superseded main deploys, never a release (#1801)
deploy / archied-image (push) Canceled after 0s
deploy / dist-zip (push) Canceled after 0s
deploy / gate (push) Canceled after 0s
deploy / plan (push) Canceled after 0s
deploy / agent-image (push) Canceled after 0s
2026-11-08 17:11:56 +11:00
sam a7d202fb04 ci: drop comments from workflow scripts 2026-11-08 17:11:56 +11:00
sam 2a52508a5d fix(build): install protoc-gen-go and protoc-gen-go-grpc in the agent image
deploy / archied-image (push) Skipped
deploy / gate (push) Failing after 14m30s
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Skipped
The in-container baseline task check failed at proto:check because buf
generate could not find either plugin on PATH, parking every task at
gate.repository.
2026-11-08 17:11:49 +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 / dist-zip (push) Skipped
deploy / agent-image (push) Successful in 22s
deploy / archied-image (push) Successful in 7m25s
2026-11-08 17:00:42 +11:00
sam 64bb195700 perf(ui): mount row action dialogs only while open and keep unchanged live reloads (#1798)
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Skipped
deploy / archied-image (push) Skipped
deploy / gate (push) Failing after 13m59s
2026-11-08 16:55:59 +11:00
sam c8a46fd9e7 ci: drop comments from workflow files
deploy / gate (push) Successful in 16m26s
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Successful in 12s
deploy / archied-image (push) Successful in 3m53s
2026-11-08 16:55:03 +11:00
sam 93db9a6395 feat(extensions): typed extension settings (number, boolean, duration, list, select)
deploy / agent-image (push) Successful in 12s
deploy / gate (push) Successful in 7m52s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 2m33s
2026-11-08 16:14:23 +11:00
sam 89808d0719 fix(extensions): list settings a version no longer declares and save only once they are removed
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Skipped
deploy / gate (push) Failing after 13m0s
deploy / agent-image (push) Skipped
2026-11-08 16:07:42 +11:00
sam ef99b7d74e fix(extensions): keep an extension's settings across removal and keys a version drops
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Skipped
deploy / archied-image (push) Skipped
deploy / gate (push) Failing after 3m39s
2026-11-08 16:05:19 +11:00
sam 62ddbea0c1 fix(messaging): show a configured Telegram whose extension is not installed
deploy / gate (push) Failing after 8m12s
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Skipped
deploy / archied-image (push) Skipped
2026-11-08 16:00:29 +11:00
sam b548cabcbf refactor(publicnet): one public-address dial guard for webhooks, attachments and web fetch (#1795)
deploy / agent-image (push) Skipped
deploy / archied-image (push) Skipped
deploy / gate (push) Failing after 8m13s
deploy / dist-zip (push) Skipped
2026-11-08 15:52:39 +11:00
sam 8f37cc79cd feat(channels): package-declared channel settings on an instance Channels page (#1796)
deploy / archied-image (push) Skipped
deploy / agent-image (push) Skipped
deploy / gate (push) Failing after 8m32s
deploy / dist-zip (push) Skipped
2026-11-08 15:48:43 +11:00
sam 031521550a fix(ui): keep unchanged rows across live reloads on the dashboard and workflows (#1798)
deploy / agent-image (push) Skipped
deploy / dist-zip (push) Skipped
deploy / gate (push) Failing after 8m11s
deploy / archied-image (push) Skipped
2026-11-08 15:09:06 +11:00
sam 3b67ef746f Merge pull request 'fix(daemon): claim and fetch tasks only while the dispatcher has room' (#1799) from fix/1797-claim-within-capacity into main
deploy / gate (push) Successful in 6m5s
deploy / agent-image (push) Successful in 15s
deploy / archied-image (push) Successful in 3m9s
deploy / dist-zip (push) Skipped
2026-11-08 03:53:07 +00:00
sam 18838105f0 ci(quality): run on pull requests only; deploy gates main
deploy / archied-image (push) Successful in 3m10s
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 4m50s
deploy / agent-image (push) Successful in 15s
2026-11-08 14:50:29 +11:00
sam d70596f4bf Merge branch 'main' into fix/1797-claim-within-capacity
Quality / check (pull_request) Successful in 7m24s
2026-11-08 03:45:21 +00:00
sam a9878c329d Merge pull request 'fix(ui/tasks): keep unchanged rows across live reloads' (#1800) from fix/1798-task-list-stable-rows into main
deploy / gate (push) Successful in 4m39s
deploy / agent-image (push) Successful in 11s
Quality / check (push) Successful in 6m40s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 3m27s
Reviewed-on: #1800
2026-11-08 03:45:13 +00:00
sam 558659bcf4 test(daemon): adopt go fix's promoted-field literal (#1797)
Quality / check (pull_request) Canceled after 2m32s
2026-11-08 03:37:54 +00:00
sam 00e7603932 fix(ui/tasks): keep unchanged rows across live reloads (#1798)
Quality / check (pull_request) Successful in 6m36s
2026-11-08 03:32:08 +00:00
sam 33f7323eb0 fix(daemon): claim and fetch tasks only while the dispatcher has room (#1797)
Quality / check (pull_request) Failing after 6m37s
2026-11-08 03:29:25 +00:00
sam 184038a918 fix(webui): link tasks to their repository connection's forge
deploy / archied-image (push) Successful in 3m2s
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Successful in 12s
Quality / check (push) Successful in 44m46s
deploy / gate (push) Successful in 4m52s
2026-11-08 06:42:38 +11:00
sam 8cb76092b6 chore(release): v1.61.2
Quality / check (push) Canceled after 12m5s
deploy / gate (push) Successful in 5m3s
deploy / agent-image (push) Successful in 3m23s
deploy / dist-zip (push) Successful in 1m51s
deploy / archied-image (push) Successful in 3m6s
2026-11-08 06:30:16 +11:00
sam 49d7619ba3 fix(daemon): claim a requeued backlog without a poll wait per task
deploy / gate (push) Successful in 4m56s
Quality / check (push) Canceled after 6m11s
deploy / archied-image (push) Successful in 3m1s
deploy / agent-image (push) Successful in 12s
deploy / dist-zip (push) Skipped
2026-11-08 06:24:54 +11:00
sam ae53e83ff3 chore(release): v1.61.1
Quality / check (push) Successful in 6m19s
deploy / archied-image (push) Successful in 3m0s
deploy / dist-zip (push) Successful in 2m41s
deploy / gate (push) Successful in 4m46s
deploy / agent-image (push) Successful in 3m16s
2026-11-08 06:04:33 +11:00
sam ef84e18f46 fix(ui): a new canvas workflow names the agent it runs as (#1622)
Quality / check (push) Successful in 6m53s
deploy / gate (push) Successful in 4m52s
deploy / agent-image (push) Successful in 11s
deploy / archied-image (push) Successful in 3m21s
deploy / dist-zip (push) Skipped
2026-11-08 05:49:40 +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 cc8428643a fix(gatewayrpc): sniff the head of URL-only attachments (#1672)
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Successful in 12s
deploy / gate (push) Successful in 4m41s
deploy / archied-image (push) Successful in 3m37s
Quality / check (push) Successful in 7m2s
2026-11-08 05:40:27 +11:00
sam 70251ff3ce chore(release): v1.61.0
deploy / gate (push) Successful in 4m44s
deploy / agent-image (push) Successful in 3m35s
deploy / dist-zip (push) Successful in 2m39s
Quality / check (push) Successful in 7m16s
deploy / archied-image (push) Successful in 3m0s
2026-11-08 04:59:28 +11:00
sam 76dc34a17c fix(distribution): trust the rotated catalogue signing key (#1790)
Quality / check (push) Canceled after 5m9s
deploy / archied-image (push) Successful in 2m58s
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 4m32s
deploy / agent-image (push) Successful in 12s
2026-11-08 04:54:32 +11:00
sam a6a0c7c11e fix(archied): say why the canary can't compare migrations
deploy / archied-image (push) Successful in 2m57s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 4m41s
Quality / check (push) Successful in 6m27s
2026-11-08 03:05:29 +11:00
sam f759387eb7 chore: ignore the fleet run directory 2026-11-08 02:48:29 +11:00
sam 21b3591da1 fix(e2e+ui): e2e checks for the audit's failure classes, and the gaps they caught (#1767)
deploy / gate (push) Successful in 4m48s
deploy / agent-image (push) Successful in 12s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 3m31s
Quality / check (push) Successful in 6m11s
loading-errors now forces each list API (/api/tasks, /api/captures,
/api/event-types, /api/tokens, /api/access/policies) to fail and asserts
the page shows its error surface, never its empty-state copy.
accessibility gains two static-route sweeps: every input/textarea/select/
button must have an accessible name, and every keyboard focus stop's
indicator (ring var, outline, shadow or focus border) must clear 3:1
against the background behind it. phone-overflow sweeps every static
route at 390x844 for horizontal scroll. The sweeps caught real gaps,
fixed here: the DurationInput amount input had no accessible name and
its unit select no focus indicator, and TabsContent and CodeBlockContent
were focusable with outline-none and no ring. The stale 'Sections' list
selector now matches the nav landmark.
2026-11-07 17:08:10 +11:00
sam e9937ded6b fix(ui): a failed answer keeps the question card and its filled-in answer (#1728)
deploy / archied-image (push) Successful in 3m25s
deploy / dist-zip (push) Skipped
Quality / check (push) Successful in 9m2s
deploy / gate (push) Successful in 4m49s
deploy / agent-image (push) Successful in 11s
answerAsk now clears the pending question only after api.chatAnswer
accepts it, and resolves whether it did. On failure the new askError ref
carries the message, shown on the card as a ReadError whose Retry resends
the last answer; ChatAskCard keeps the typed reply until acceptance and
routes every choice button through the same path, and the questionnaire
submits through the card so its answers are retryable too. askError resets
on turn start, on a new ask, and on conversation switch.
2026-11-07 01:23:10 +11:00
sam bd1acdd0cc fix(ui): switching conversation detaches the running turn (#1729)
deploy / archied-image (push) Successful in 3m24s
Quality / check (push) Canceled after 23s
deploy / gate (push) Successful in 4m47s
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Successful in 11s
selectSession now bumps a session epoch and aborts the in-flight stream
before switching, and the transcript read is applied only if the session is
still current. sendMessage captures the epoch at turn start: a detached turn
stops reading, cancels the reader, and writes no messages, streamingTurn or
session id; only the turn still owning the abort controller clears isSending,
so it cannot unlock the composer for a turn running in the new conversation.
2026-11-07 01:20:49 +11:00
sam a2c6341544 fix(ui): policy form opens blank on New, id read-only when editing, dirty draft asks first (#1730)
Quality / check (push) Canceled after 4m48s
deploy / archied-image (push) Successful in 3m26s
deploy / agent-image (push) Successful in 11s
deploy / gate (push) Successful in 4m52s
deploy / dist-zip (push) Skipped
New policy now resets the draft instead of reusing the open policy's, so
Save cannot overwrite the policy that happens to be open. The id input is
readonly while editing a persisted policy, so a rename can no longer write
a second policy. New/Edit/Cancel route through openForm, which asks for
confirmation before discarding a dirty draft.
2026-11-07 01:16:48 +11:00
sam cb3372ac76 fix(ui): terminal palette is theme tokens, switches live (#1739)
deploy / archied-image (push) Successful in 3m22s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
Quality / check (push) Canceled after 3m23s
deploy / gate (push) Successful in 4m51s
--terminal-bg/fg/cursor/selection are defined per theme in style.css
(dark keeps the deep well, light gets a paper inset) and exposed as
bg-terminal. Both xterm surfaces (SetupTerminal, SandboxView) read them
via lib/terminalTheme and re-apply on every data-theme flip, so the
theme switch is live; the raw #0b0f14/#e6edf3/#264f78 hex is gone.
2026-11-07 01:13:41 +11:00
sam 48e605a545 fix(ui): dead tokens replaced or deleted — text-ok, --radius-lg, real surface (#1740)
deploy / agent-image (push) Successful in 11s
Quality / check (push) Successful in 6m33s
deploy / gate (push) Successful in 4m49s
deploy / archied-image (push) Successful in 3m22s
deploy / dist-zip (push) Skipped
text-success was not a token (now text-ok) in ChatToolCall and BindEvent;
var(--radius) is undefined (now var(--radius-lg)) in input-group and Sonner;
Sonner's hsl(var(--popover) / 0.9) wrapped a hex (now a plain hex); the
undefined cn-font-heading class is deleted from the nine title components.
2026-11-07 01:06:42 +11:00
sam 9a4e59f0e0 fix(ui): tab, toggle, input and idle-text contrast meet their targets (#1741)
Quality / check (push) Canceled after 3m37s
deploy / archied-image (push) Successful in 3m24s
deploy / gate (push) Successful in 4m48s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
Inactive tab labels use text-fg-muted instead of foreground/60 (was
4.1:1). The selected toggle/toggle-group segment gains a sage-deep ring
(5.3:1 light, 3.9:1 dark) instead of the near-invisible muted fill.
--input rises to 3.6:1 (light) and 3.5:1 (dark) on the card; dark --idle
rises to 5.1:1 on --accent. Values computed against the style.css tokens.
2026-11-07 01:03:19 +11:00
sam 820beda72f fix(ui): empty states wait for the first read to settle (#1742)
deploy / gate (push) Successful in 4m49s
deploy / archied-image (push) Successful in 3m27s
deploy / dist-zip (push) Skipped
Quality / check (push) Successful in 6m42s
deploy / agent-image (push) Successful in 11s
Skills, curators, QuickTask's workflow list, the alerts bell and the
extensions catalogue now show a loading state until the first read
settles, then the data, the error, or the empty state. Draft-backed lists
(agent profiles, playbooks, credential bindings) show their empty state
only once the draft exists, not beside the load error.
2026-11-07 00:54:25 +11:00
sam c6f70de82d fix(ui): settings pages show a skeleton or the error until their draft loads (#1743)
Quality / check (push) Successful in 7m32s
deploy / archied-image (push) Successful in 3m27s
deploy / agent-image (push) Successful in 11s
deploy / gate (push) Successful in 4m59s
deploy / dist-zip (push) Skipped
New settings/KindGate renders the store's per-kind loading/error state
where the form would be: a skeleton while loading, ReadError with Retry
on a failed read. Wired into Tools, SystemModels, SystemRepos,
SchedulingPolicy, ContainerRuntime, OrgAlerts, Instructions, Plugins,
SystemTasks, UpdateSettings, IdentityGrants, OrgModels, Channels and
Authentication pages, which no longer render blank until the draft
exists.
2026-11-07 00:42:28 +11:00
sam f37f6e2453 fix(ui): one error presentation with Retry across the dashboard (#1744)
deploy / dist-zip (push) Skipped
Quality / check (push) Successful in 6m56s
deploy / agent-image (push) Successful in 11s
deploy / gate (push) Successful in 4m58s
deploy / archied-image (push) Successful in 3m28s
New components/ui ReadError (destructive Alert + message + optional Retry)
is now the single read-error presentation, used by Versions, Services,
Canary, OrgAccess, Denials, Tokens, Audit, Extensions, Harness and the
Status page (one page-level error instead of one per card). PanelError is
the same alert for task panels, and TasksState's error kind, the attempts
panel and the task-log pane all offer Retry. Org policy save errors sit
beside the Save button instead of at the page top.
2026-11-07 00:33:49 +11:00
sam f7a999e317 fix(ui): failed task pages keep rows with an inline error; refreshes don't flash (#1745)
deploy / archied-image (push) Successful in 3m28s
deploy / agent-image (push) Successful in 11s
Quality / check (push) Successful in 6m31s
deploy / gate (push) Successful in 4m49s
deploy / dist-zip (push) Skipped
A failed Load more or live refresh sets moreError beside the Load more
button instead of replacing the table; only a first-load failure takes
the table down. The no-match empty state says search covers loaded rows
when more pages exist. refreshAll keeps attempts/events (keep=true) and a
failed task-list read keeps the last known list, so panels no longer
flash to loading on every live update.
2026-11-07 00:25:36 +11:00
sam 45494d5b43 fix(ui): logs page error no longer flickers, live entries pruned, unavailable clears (#1746)
Quality / check (push) Canceled after 2m59s
deploy / gate (push) Successful in 4m51s
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Successful in 11s
deploy / archied-image (push) Successful in 3m28s
readError is cleared only by a successful read instead of at the start of
every 5 s refresh, so an outage shows a steady error beside the stale
lines. liveEntries is pruned past 1500 (the list shows 1000) so the map
cannot grow unbounded. streamState leaves "unavailable" as soon as live
entries flow again.
2026-11-07 00:22:40 +11:00
sam 9ca9545847 fix(ui): alert state is shared; a failed dismiss keeps the alert and says why (#1747)
deploy / archied-image (push) Successful in 3m30s
deploy / agent-image (push) Successful in 12s
Quality / check (push) Canceled after 3m8s
deploy / gate (push) Successful in 4m51s
deploy / dist-zip (push) Skipped
use-alerts.ts now holds the alerts/failed refs at module scope (wired once),
so the bell and the dashboard card see the same list. dismiss removes the
alert only after the server confirms; on failure it stays and the reason
shows in the bell. dismissAll reports any rejection and reloads.
2026-11-07 00:19:31 +11:00
sam fa14e7da80 fix(ui): chat failures are shown where they happen and leave the real state (#1748)
deploy / gate (push) Successful in 4m47s
deploy / agent-image (push) Successful in 11s
Quality / check (push) Canceled after 1m18s
deploy / archied-image (push) Successful in 3m27s
deploy / dist-zip (push) Skipped
Mic permission failure shows an inline alert; setModel only switches on
server confirmation and reverts + reports in the transcript on failure;
a failed session refresh after a turn no longer becomes a retryable turn
error; a voice clip during a turn queues instead of dropping; blocked
localStorage falls back to a per-load channel id; a failed install offers
Retry/Not now again; rename/branch use a labelled Dialog instead of
window.prompt; a failed cancel is reported; a stopped turn no longer
blocks transcript reloads.
2026-11-07 00:17:44 +11:00
sam 12eea5eee3 fix(ui): destructive actions confirm via AlertDialog, naming the item (#1749)
deploy / gate (push) Successful in 4m49s
deploy / agent-image (push) Successful in 12s
deploy / archied-image (push) Successful in 3m29s
deploy / dist-zip (push) Skipped
Quality / check (push) Canceled after 7m10s
Delete policy, remove member, revoke token, remove passkey and delete
source now open the shared AlertDialog confirmation that names the item,
matching the binding/mapping/event-type deletes that already confirmed.
2026-11-07 00:11:16 +11:00
sam ef623f6c68 fix(ui): rows keep table semantics; first-cell link/button is the focus target (#1750)
deploy / gate (push) Successful in 4m59s
deploy / archied-image (push) Successful in 3m29s
Quality / check (push) Successful in 6m40s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
DataTable, ActivityRow, LiveActivityCard's group row and CaptureRow no
longer put role=link/button, tabindex or aria-label on the <tr>. The row
keeps its mouse click handler; the first cell carries a real RouterLink
(DataTable rowLink) or button with the accessible name, so keyboard and
screen-reader users get a focus target and rows keep row/cell semantics.
The live-activity group row's disclosure button and open button are now
siblings, not nested.
2026-11-07 00:00:41 +11:00
sam ee2d19d011 fix(ui): real heading structure and a nav landmark for the sidebar (#1751)
deploy / agent-image (push) Successful in 11s
deploy / gate (push) Successful in 4m52s
deploy / dist-zip (push) Skipped
Quality / check (push) Canceled after 4m2s
deploy / archied-image (push) Successful in 3m30s
CardTitle and EmptyTitle take an as prop (default h2) and render through
component :is, so card and empty-state titles are headings; Section passes
as="h2" under the page's h1. The sidebar menu list now sits in
<nav aria-label="Sections">.
2026-11-06 23:56:34 +11:00
sam 53c6b3e413 fix(ui): disabled reasons and truncated values reachable without hover (#1752)
Quality / check (push) Canceled after 4m7s
deploy / archied-image (push) Successful in 3m32s
deploy / gate (push) Successful in 4m49s
deploy / agent-image (push) Successful in 12s
deploy / dist-zip (push) Skipped
Disabled New run and task-row buttons now carry their reason in a Tooltip
on a focusable wrapper (disabled buttons cannot take focus), and New run
says when the task list has not loaded. Truncated values (binding filter
and failure reason, activity rows, live alerts, event-type rule summaries,
source URLs, mapping field paths) are focusable spans whose full text is in
a Tooltip. The org switcher has distinct loading ('…' tile, 'Loading…')
and failed ('!' tile, 'Organisations unavailable') states.
2026-11-06 23:52:25 +11:00
sam d58125c0bc fix(ui): combobox pattern for the slash palette, named palette input, bound labels (#1753)
deploy / gate (push) Successful in 4m48s
Quality / check (push) Canceled after 4m45s
deploy / archied-image (push) Successful in 3m28s
deploy / agent-image (push) Successful in 12s
deploy / dist-zip (push) Skipped
The composer textarea is now role=combobox with aria-expanded,
aria-controls and aria-activedescendant wired to the slash palette's
listbox ids. CommandInput has an accessible name. FieldLabels without a
control beside them are bound: for/id on selects, inputs, switches and
duration inputs across channels, curators and schedules pages, and
role=group + aria-labelledby/aria-label on the TagsInput, secret-ref and
rule row groups.
2026-11-06 23:47:41 +11:00
sam 029198ff61 fix(ui): generation-guard the remaining async loads and polls (#1754)
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 4m51s
Quality / check (push) Canceled after 7m38s
deploy / archied-image (push) Successful in 3m26s
deploy / agent-image (push) Successful in 12s
Schedules, command palette, skills, repos, services, secret engines,
captures, event types, curators, sources, channels, mappings (list and
preview), dispatch links and workflow history now capture a generation
at request start and drop their writes unless still latest — the guard
logs/state.ts already used. A failed schedules poll keeps the last good
rows beside the inline error instead of replacing the table, and a
failed skills/secret-engines poll no longer clears the list.
2026-11-06 23:40:03 +11:00
sam 0b08fc5242 fix(ui): harness setup terminal reports the real failure and can be reopened (#1755)
Quality / check (push) Canceled after 5m18s
deploy / archied-image (push) Successful in 3m29s
deploy / gate (push) Successful in 4m48s
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Successful in 11s
A websocket that never opened stays "failed" — onclose no longer
overwrites it with "closed", so the terminal says "Could not open the
setup terminal." instead of "The terminal session ended.". The terminal
emits ended when its session closes, and HarnessPage resets terminalOpen
on it (plus a Close terminal button), so reopening starts a fresh session
instead of requiring a page reload. The harness load failure now has a
Retry button.
2026-11-06 23:34:38 +11:00
sam 93609c7ab3 fix(ui): eleven small dashboard state bugs from the audit (#1756)
deploy / agent-image (push) Successful in 11s
deploy / gate (push) Successful in 4m50s
Quality / check (push) Canceled after 3m13s
deploy / archied-image (push) Successful in 3m28s
deploy / dist-zip (push) Skipped
Install disables when no installable snapshot; retention hours is empty
until loaded instead of showing 0; the audit Action field carries all
comma-separated actions; saving a view over an existing name asks first;
"Password changed" is a notice, not a destructive alert; "Sign in
again" appears only on an expired session (classifyActionError) on
account, authentication and create-account; sign-out failure sets the
store error instead of an unhandled rejection; the workflow identity
select shows the seeded agent without writing it into the YAML;
unparseable durations show an inline error instead of snapping back;
CardAccordion keys items by id; curator add() explains a no-op.
2026-11-06 23:31:47 +11:00
sam 461d3dc1f7 fix(ui): phone-width overflows in the audit's flagged rows, with an e2e check (#1757)
deploy / agent-image (push) Successful in 11s
deploy / archied-image (push) Successful in 3m23s
Quality / check (push) Successful in 6m36s
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 4m54s
Grants rows and toggle groups wrap with a smaller phone label; the token
form wraps and its input flexes; the sources name column caps at full
width and its action buttons wrap; the rule-editor condition row wraps
with a full-width phone select; the payload tree indents less and breaks
long JSON leaves; the topbar instance badge truncates; org agent rows
keep Assign inline and move Rename/Suspend/Retire into a MoreMenu. New
e2e check phone-overflow.cjs visits these views at 390x844 with seeded
data and asserts no horizontal scroll.
2026-11-06 23:23:16 +11:00
sam 94f79177a2 fix(ui): adopt the type scale across components/ui and pages (#1758)
deploy / archied-image (push) Successful in 3m20s
deploy / agent-image (push) Successful in 11s
deploy / gate (push) Successful in 4m53s
Quality / check (push) Successful in 6m42s
deploy / dist-zip (push) Skipped
components/ui and the pages now use only the style.css scale:
text-[0.8rem]→text-label, text-[0.625rem]→text-micro, text-base/text-sm→
text-label (rows and controls), text-xs→text-caption (captions and
secondary text), text-lg/text-xl/text-2xl→text-title (panel and page
titles). Rendered markdown (ChatMarkdown/ChatInline/markdown.ts) keeps
Tailwind steps as the issue allows. 196 files, class-token swaps only.
2026-11-06 23:07:46 +11:00
sam 9169e9db09 fix(ui): hand-rolled cards, headings, captions and empties use components/ui (#1759)
deploy / archied-image (push) Successful in 3m24s
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 4m50s
Quality / check (push) Canceled after 4m48s
deploy / agent-image (push) Successful in 11s
Captions move from text-xs to the text-caption type-scale token across
the workflow/bind/schedule editors and curator card. The task page title
uses PageHeader's h1 classes. Hand-rolled boxes become Card (token
reveal, recovery code, pending extension update) or CodeView (install
progress); the startup-settings key/value table becomes MetadataList;
the harness empty row becomes TableEmpty; 'No tokens/dispatches/inputs/
removed' states become Empty; the step-editor problem line becomes a
destructive Alert. The risky-row danger tint in ToolsPage and
SystemReposPage now uses SettingRow tone="danger" instead of a
hand-written before: overlay (DANGER_ROW deleted).
2026-11-06 23:03:10 +11:00
sam 0d0cd09124 fix(ui): known lists use Select/TagsInput fed by the server catalogue (#1760)
deploy / gate (push) Successful in 4m36s
deploy / agent-image (push) Successful in 12s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 3m17s
Quality / check (push) Successful in 8m37s
Token lifetimes use Select instead of NativeSelect. Credential bindings
pick service from the store's credentialServices and organisation from
the org list (empty = default, via a sentinel). Curator and agent-profile
tools are TagsInput instead of comma text; curator model is a Select of
the configured providers' models from /api/config's catalog. Org and
system model pages pick provider class from the catalog's classes, and
SystemModelsPage's local CLASSES list is deleted. Chat model choice is a
Select of the server-served model list instead of a button row.

Left as free text because no server source exists: policy object kind,
curator memory engine, update channel labels, connection type default,
container default, step titles (x-step-types carries no titles).
2026-11-06 22:51:21 +11:00
sam 0dc5bf9a9b fix(ui): times honour the Appearance zone, one duration formatter everywhere (#1761)
deploy / dist-zip (push) Skipped
Quality / check (push) Successful in 6m44s
deploy / agent-image (push) Successful in 11s
deploy / archied-image (push) Successful in 3m44s
deploy / gate (push) Successful in 4m54s
lib/format.ts gains shortTime(value, zone) and becomes the home of the
single duration() formatter (moved from timeline-event.ts, which
re-exports it so the stage rail and duration.test.ts are unchanged).
LogTable's time column, audit's From/To chips and chat session titles now
format in the zone chosen under Appearance instead of the browser's.
StepNode, schedule runDuration, labels formatMs and ChatToolCall all
delegate to duration(), removing the "12ms" vs "12 ms" vs "under 1 s"
split.
2026-11-06 22:21:45 +11:00
sam ca107f6977 fix(ui): failed draft save is retried, then shown — never dropped silently (#1731)
persistDraft retried only while draftState.saving was true, but
settings.replace clears saving in its finally before resolving false, so
the retry branch could never run and a failed putDraft vanished. It now
retries on a bounded schedule (5 attempts, 500ms apart) regardless of the
saving flag, and on final failure sets localError so the editor's alert
says the draft was not saved while the edit stays in the editor. The
alert also reads the draft store's own error (workflows.draftState.error)
instead of only the definitions store's.
2026-11-06 22:09:56 +11:00
sam 4dad1415e6 fix(ui): workflow reads keep their error instead of showing empty (#1732)
Triggers: a failed bindings/schedules read surfaces as an error with
Retry in TriggerSettings instead of "Manual runs only." Run stages: a
failed attempts read sets stagesError, shown with Retry above the canvas
instead of a bare canvas. Bind form: failed reads show an error with
Retry rather than empty pickers, and save refuses to mappingUpdate an
existing mapping unless the bindings list actually loaded. History: a
failed revisions read shows the error with Retry in the revision list,
and "No recorded changes" appears only after a successful read.
2026-11-06 22:06:25 +11:00
sam 5bf0a696c6 fix(ui): failed reads show an error with Retry, not an empty view (#1733)
Chat: a failed conversation load sets sessionError, shown in the
transcript with Retry instead of the empty invitation (it no longer goes
to statusText in the settings popover). Command palette: failed task or
workflow reads render a "Couldn't load … — Retry" item in that group.
Denials: the table no longer shows "No denials recorded" under an
error. Mapping form: failed captures/event-types reads show an error row
with Retry instead of "No captured events yet." or a silently empty
select. Channels: a failed status read keeps the last badges and shows
an error with Retry. Sources: read failures are separate from write
failures, shown with Retry, and a loaded-but-empty list gets an empty
state.
2026-11-06 22:01:03 +11:00
sam 7a8d948fcb fix(ui): drop stale async responses with a generation guard (#1734)
TasksPage load/loadMore, use-task-run keyedLoad, TaskLogs loadOlder and
EventsPage loadCounts now each capture a generation at request start and
drop their writes unless they are still the latest request, the same
guard logs/state.ts already uses. dropCaches also stales every in-flight
keyed read, so a 30s timeout's null can no longer overwrite a newer
successful response, and the task-log pager no longer writes a page
fetched under the old attempt or filter.
2026-11-06 21:52:55 +11:00
sam d90f7d48d0 fix(ui): step card header is a keyboard-operable button, Edit in its menu (#1735)
The step header in StepNode.vue was a div with @click and no role, so a
step could not be opened from the keyboard, and Edit existed only in the
right-click canvas menu. The header now renders as a real <button> (with
aria-expanded) whenever the step can toggle, so Tab/Enter/Space open it;
while renaming it stays a div so the rename input is not nested inside a
button. The actions menu trigger moved to an absolute overlay at the
card's top-right (same spot as before, with a matching spacer in the
header row) and gained an Edit item that toggles the step, matching the
canvas context menu.
2026-11-06 21:48:55 +11:00
sam c5a43f21aa fix(ui): accessible names on fields that had only placeholders (#1736)
Step editor fields (lead, compact rows, long/YAML textareas and the
compact boolean switch), the org policy editor (policy id, level,
workspace id, object kind/id, Cedar textarea), the binding constant
value input, the log search and the channel tags inputs now each carry
an aria-label. On TagsInput the aria-label moved from the root div,
where screen readers never reach it, onto the actual TagsInputInput.
2026-11-06 21:43:23 +11:00
sam d3fbb0842f fix(ui): focus rings at full strength for 3:1 contrast (#1737)
The shared components used focus-visible:ring-ring/50 (and the base
outline-ring/50), which measured 2.1:1 on light and 2.4:1 on dark --
under the 3:1 WCAG 2.4.11/1.4.11 requires. All ring-ring and outline-ring
tokens in ui/src now render at full strength (5.3:1 light, 5.7:1 dark),
matching the :focus-visible outline floor in style.css.
2026-11-06 21:39:37 +11:00
sam dafd426316 fix(ui): startup failure is a centred panel that retries on its own (#1738)
When /api/auth/status fails, App.vue now shows a centred card with the
logo, a plain 'Can't reach Archie' statement and the detail in a
destructive Alert (role=alert), and retries the read every 5s until it
succeeds instead of offering only a manual Retry link. errorMessage in
api.ts only reads text/plain bodies, so a proxy's HTML error page no
longer passes through as the detail; other content types fall back to
the status line.
2026-11-06 21:36:17 +11:00
sam bec374aa92 ci(quality): stop installing ripgrep and setting sysctl from the gate (#1710)
The check job now runs on the archie-quality self-hosted runner under an
unprivileged user, so the sudo apt-get install and sudo sysctl steps fail,
exactly as the deploy gate did before 3b372b4a. Both are host provisioning:
ripgrep is installed on the runner host and the userns restriction belongs in
sysctl.d. The namespace check stays, without sudo.
2026-11-06 21:30:33 +11:00
sam 85b21578d8 ci(release): name the missing DEPLOY_TOKEN before checkout, and list what a mirror needs
Quality / check (push) Successful in 3m46s
deploy / gate (push) Successful in 4m29s
deploy / agent-image (push) Successful in 12s
deploy / archied-image (push) Successful in 2m53s
deploy / dist-zip (push) Skipped
Refs #1788
2026-11-05 00:33:18 +11:00
sam 03c25e7214 docs(workflow): say repo.commit never runs the checkout's git hooks
deploy / gate (push) Successful in 4m45s
deploy / agent-image (push) Successful in 12s
deploy / archied-image (push) Successful in 3m0s
Quality / check (push) Successful in 3m44s
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 / agent-image (push) Successful in 11s
deploy / archied-image (push) Successful in 3m13s
deploy / dist-zip (push) Skipped
2026-11-03 20:56:03 +11:00
sam 3cf025fb4a fix(worktree): mirror fetch follows moved tags and rewritten branches
deploy / gate (push) Successful in 4m35s
Quality / check (push) Successful in 6m46s
deploy / archied-image (push) Successful in 2m55s
deploy / agent-image (push) Successful in 12s
deploy / dist-zip (push) Skipped
2026-11-03 10:00:04 +11:00
sam 81b784876b fix(ui): live task updates refresh in place instead of flashing the loading state
Quality / check (push) Successful in 3m52s
deploy / archied-image (push) Successful in 3m14s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 4m33s
2026-11-03 09:51:43 +11:00
sam 6c42f64bfa chore(release): v1.60.0
deploy / archied-image (push) Successful in 2m52s
Quality / check (push) Canceled after 18s
deploy / gate (push) Successful in 4m39s
deploy / agent-image (push) Successful in 3m21s
deploy / dist-zip (push) Successful in 1m47s
2026-11-03 09:51:30 +11:00
sam d74216c6b7 docs(changelog): curator issue tools (#1770)
Quality / check (push) Successful in 4m3s
deploy / archied-image (push) Successful in 2m49s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 4m42s
2026-11-03 09:43:45 +11:00
sam 0b7ce448ab fix(e2e): checks follow the sidebar navigation; trim stray button and caption whitespace (#1789)
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
Quality / check (push) Successful in 3m52s
deploy / gate (push) Successful in 4m36s
deploy / archied-image (push) Successful in 3m16s
2026-11-03 09:35:19 +11:00
sam 2fb8c09a00 refactor(webui): extract the workflows module (#1778)
deploy / gate (push) Successful in 4m37s
deploy / archied-image (push) Successful in 2m51s
Quality / check (push) Successful in 4m23s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
2026-11-03 08:39:40 +11:00
sam 0442f1849f refactor(webui): extract the audit module and its export guards (#1778)
deploy / gate (push) Successful in 4m33s
deploy / archied-image (push) Successful in 2m52s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
Quality / check (push) Canceled after 1m17s
2026-11-03 08:38:22 +11:00
sam cf049797b0 refactor(webui): extract the schedules and alerts modules (#1778)
deploy / agent-image (push) Successful in 12s
deploy / dist-zip (push) Skipped
Quality / check (push) Canceled after 1m5s
deploy / gate (push) Successful in 4m33s
deploy / archied-image (push) Successful in 2m48s
2026-11-03 08:37:15 +11:00
sam 18e6fe6af6 refactor(webui): extract the chat module and its ask/file state (#1778)
deploy / gate (push) Successful in 4m35s
Quality / check (push) Canceled after 1m5s
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Successful in 11s
deploy / archied-image (push) Successful in 2m48s
2026-11-03 08:36:09 +11:00
sam e8a84d3e41 refactor(webui): extract the control-plane and logs modules (#1778)
deploy / gate (push) Successful in 4m31s
deploy / dist-zip (push) Skipped
deploy / agent-image (push) Successful in 11s
Quality / check (push) Canceled after 1m17s
deploy / archied-image (push) Successful in 2m49s
2026-11-03 08:34:51 +11:00
sam c5f4541cbf refactor(webui): extract the access policies and denials module (#1778)
Quality / check (push) Canceled after 1m5s
deploy / gate (push) Successful in 4m35s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 2m49s
deploy / agent-image (push) Successful in 12s
2026-11-03 08:33:46 +11:00
sam 369e5038ca refactor(webui): extract the identities and tokens module (#1778)
deploy / archied-image (push) Successful in 2m52s
deploy / agent-image (push) Successful in 10s
deploy / dist-zip (push) Skipped
Quality / check (push) Canceled after 1m9s
deploy / gate (push) Successful in 4m34s
2026-11-03 08:32:44 +11:00
sam 66862a1bab refactor(webui): extract the orgs resource module (#1778)
deploy / dist-zip (push) Skipped
Quality / check (push) Successful in 4m2s
deploy / gate (push) Successful in 4m39s
deploy / agent-image (push) Successful in 11s
deploy / archied-image (push) Successful in 2m51s
2026-11-03 08:28:36 +11:00
sam 25dcdb2d19 refactor(webui): extract the extensions resource module (#1778)
Quality / check (push) Successful in 5m1s
deploy / archied-image (push) Successful in 2m46s
deploy / agent-image (push) Successful in 10s
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 4m35s
2026-11-03 08:22:02 +11:00
sam 1830a89898 refactor(webui): extract the harness resource module (#1778)
deploy / agent-image (push) Successful in 12s
Quality / check (push) Successful in 3m56s
deploy / gate (push) Successful in 4m34s
deploy / archied-image (push) Successful in 2m55s
deploy / dist-zip (push) Skipped
2026-11-03 08:17:12 +11:00
sam 6e718e165a feat(curator): issue_list and issue_create tools via the daemon (#1770)
deploy / agent-image (push) Successful in 12s
deploy / gate (push) Successful in 4m30s
Quality / check (push) Successful in 4m6s
deploy / archied-image (push) Successful in 2m50s
deploy / dist-zip (push) Skipped
2026-11-03 08:12:05 +11:00
sam 0a37b551f5 refactor(webui): extract the tasks resource module (#1778)
Quality / check (push) Successful in 3m47s
deploy / agent-image (push) Successful in 10s
deploy / gate (push) Successful in 4m32s
deploy / archied-image (push) Successful in 2m51s
deploy / dist-zip (push) Skipped
2026-11-03 08:06:56 +11:00
sam 864b87faa6 refactor(webui): extract event-types, mappings and sources modules (#1778)
deploy / gate (push) Successful in 4m29s
Quality / check (push) Successful in 3m52s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 2m48s
deploy / agent-image (push) Successful in 11s
Same pattern as the bindings pilot: eventTypesAPI (registers unconditionally,
list answers enabled:false without a store), mappingsAPI and sourcesAPI
(constructed only when their store is configured, 503 stub otherwise).
Shared helpers unsignedSources/recentRefusals/listedIn stay on Server; the
dispatch-ledger handler stays shared for captures/tasks. task check green.
2026-11-03 07:42:50 +11:00
sam d55d8580cf refactor(webui): extract the bindings resource module (#1778)
Pilot for one-module-per-resource: bindingsAPI owns the /api/bindings*
routes and their handlers, constructed only when the binding store is
configured; a 503 stub mounts the same routes otherwise, preserving the
old not-configured answers. Handlers move off *Server unchanged in
behavior; the shared dispatch-ledger handler stays on Server for the
captures/tasks routes. task check green.
2026-11-03 07:01:12 +11:00
sam 63229d1711 refactor(storecontract): assert every store interface at its implementation (#1781)
Complete the var _ storecontract.X = (*T)(nil) sweep so each of the 31
contract interfaces is compiler-checked against at least one adapter:
postgres.Store (19), postgres.EDA (11, consolidated into edastore.go),
staterpc.Client (29). Removes the scattered single-line assertions from
harness_secrets.go, edastore_eventtypes.go, sources.go, run_credentials.go.
task check green.
2026-11-03 06:24:09 +11:00
sam 56044476fc chore(release): v1.59.0
deploy / dist-zip (push) Successful in 2m35s
deploy / archied-image (push) Successful in 2m45s
deploy / gate (push) Successful in 4m21s
deploy / agent-image (push) Successful in 3m15s
Quality / check (push) Successful in 3m53s
2026-11-03 06:15:09 +11:00
sam 796bfd0045 docs(changelog): forge extensions gain CreateIssue
deploy / gate (push) Successful in 5m16s
deploy / archied-image (push) Successful in 3m2s
deploy / dist-zip (push) Skipped
Quality / check (push) Successful in 7m12s
deploy / agent-image (push) Successful in 11s
2026-11-03 02:43:25 +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 443a7a501b refactor(storecontract): split the store contract into topical files (#1781)
Pure move: one 624-line storecontract.go becomes storecontract.go
(package doc + composed TaskStore), task.go, capture.go, binding.go,
mapping.go, source.go, status.go, resource.go, credentials.go and
errors.go. The package remains the single seam; no declaration changed
(verified line-identical against HEAD). task check green.
2026-11-03 02:27:57 +11:00
sam 88e86776e8 feat(forge): add CreateIssue to the forge contract (#1770)
deploy / archied-image (push) Successful in 2m54s
deploy / gate (push) Successful in 4m43s
deploy / agent-image (push) Successful in 11s
Quality / check (push) Successful in 4m10s
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 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 2f8076d7f8 fix(access): forbid clause scopes the canary grant against its developer role (#1727)
deploy / archied-image (push) Successful in 2m53s
deploy / agent-image (push) Successful in 10s
deploy / gate (push) Successful in 4m45s
deploy / dist-zip (push) Skipped
Quality / check (push) Successful in 3m37s
Service accounts created through the identities API are assigned the
developer role in the request's org, whose shipped policy permits read and
write across the org -- the permit alone did not scope the canary. Install a
matching org-canary-grant-forbid policy (access.CanaryGrantForbidPolicy) that
negates exactly the permit's surface for the canary identity; a forbid wins
within the level, so the role can no longer widen access. Engine tests pin
the surface with the principal carrying the developer role, and the
rehearsal now proves it live: the scoped token gets 403 on /api/access/policies
and 200 on /api/chat/update, and the full canary loop runs on it.

task check passes; task canary:rehearse green (REHEARSE_EXIT=0).
2026-11-02 06:23:38 +11:00
sam c180a2debb feat(access): scoped canary grant replaces instance-admin CANARY_TOKEN (#1727)
deploy / gate (push) Successful in 4m48s
deploy / dist-zip (push) Skipped
Quality / check (push) Successful in 3m49s
deploy / archied-image (push) Successful in 2m55s
deploy / agent-image (push) Successful in 11s
The canary now authenticates as a dedicated service-account identity in the
system org whose only grant is access.CalaryGrantPolicy: read the signal
endpoints (chat update, alerts, logs, tasks), read and write the
update-settings resource, and trigger an update install. CANARY_TOKEN no
longer carries instance admin; DEPLOY_TOKEN stays CI-only.

- authorize: POST /api/chat/update/install and /defer map to
  update on Object::"update" (dashboard) instead of run on any workflow,
  so the grant can cover installs without granting workflow runs
- accounts: active service-account identities may authenticate with bearer
  tokens (CanAct), not just users
- new POST /api/identities/{id}/tokens (behind manage_identities) mints a
  token for a named non-user identity; new AccountService RPC
  BindIdentityPersonalToken backs it remotely, refusing user-kind targets,
  with the caller recorded as audit actor
- engine tests pin the grant's exact allow/deny surface

RELEASING.md documents the one-time setup. task check passes on this tree.
2026-11-02 06:03:41 +11:00
sam 5356745968 fix(releaseupdate): address review findings on the #1725 canary change
deploy / archied-image (push) Successful in 3m11s
Quality / check (push) Successful in 3m39s
deploy / gate (push) Successful in 4m28s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
- one shared UpdateStateDir() resolver for daemon and dashboard, instead of
  two copies that could drift
- the recovery path for a committed/rolled-back journal writes
  installed.json too, so a crash after the outcome phase cannot lose the
  install record
- JudgeCanaryNow is the explicit signals-only entry point for promoting
  without the window, replacing the zero-install-time sentinel
- canary version comparisons use IssuedAt, matching Promote's replay rule,
  so semver/issued-at divergence cannot wedge check red; queuedBehind
  reuses the judgeable predicate instead of a looser check
- promote prints the channel/pin; promote.yml cancels superseded runs
- canary card: no duplicated elapsed rendering, channel row waits for the
  settings resource instead of showing a default, agent fallback '?'
- rehearsal script bounds its docker build/push/run calls

task check passes on this tree.
2026-11-02 02:45:26 +11:00
sam 5b5059615b feat(releaseupdate): judge the installed release, window from install (#1725)
deploy / archied-image (push) Successful in 3m14s
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 4m31s
Quality / check (push) Successful in 4m2s
deploy / agent-image (push) Successful in 11s
The canary window now counts from when a release is installed on the host
(installed.json / installed_at in the update snapshot), not from the
statement's issued_at, and 'release canary check' judges the release the
canary actually runs via its exact-pin tag instead of the moving next tag.
A newer release on next queues behind the one being judged instead of
restarting the clock, so stable moves once per release.

New subcommands: canary status (read-only state, signals, verdict), canary
promote (promote now when hard checks pass), canary unpin (back to next),
and start -force. A held/pinned canary is verified installable every check
and a stranded pin fails the run red instead of looking green. Rollback
pre-flight checks stable's zip and agent image digests before pinning.
Relative signals are judged whenever both windows carry minimum data, so a
breach rolls back mid-window; promote still needs the full window unless
the operator promotes early (new promote.yml workflow_dispatch). The window
is configurable via -window / CANARY_WINDOW.

Also: dashboard canary status card (ui), and task canary:rehearse, a local
end-to-end rehearsal of publish -> canary start -> status -> check ->
promote against a throwaway registry and host.

task check passes; rehearsal run green (REHEARSE_EXIT=0).
2026-11-02 01:15:29 +11:00
sam bca1f3b412 chore(release): v1.58.1
deploy / agent-image (push) Successful in 3m18s
Quality / check (push) Successful in 3m43s
deploy / dist-zip (push) Successful in 2m37s
deploy / gate (push) Successful in 4m36s
deploy / archied-image (push) Successful in 2m52s
2026-11-02 00:27:14 +11:00
sam 3af96fd818 fix(daemon): watch the task intake loop too and name the stalled loop
deploy / agent-image (push) Successful in 12s
deploy / gate (push) Successful in 4m30s
Quality / check (push) Canceled after 26s
deploy / archied-image (push) Successful in 2m50s
deploy / dist-zip (push) Skipped
2026-11-02 00:26:50 +11:00
sam 1043982529 fix(daemon): stamp each run-loop cycle so the systemd watchdog keeps beating
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 2m54s
Quality / check (push) Successful in 3m37s
deploy / gate (push) Successful in 4m27s
2026-11-02 00:22:24 +11:00
sam 6abfe32540 chore(release): v1.58.0
Quality / check (push) Successful in 3m39s
deploy / archied-image (push) Successful in 2m49s
deploy / gate (push) Successful in 4m19s
deploy / agent-image (push) Successful in 3m9s
deploy / dist-zip (push) Successful in 4m52s
2026-11-01 23:55:55 +11:00
sam 1f9807a99c fix(ui/chat): give the collapsed composer its own card and reserve its height (#1719)
deploy / gate (push) Successful in 4m33s
deploy / archied-image (push) Successful in 3m16s
Quality / check (push) Successful in 3m39s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
2026-11-01 23:11:01 +11:00
sam b2edf1fa8b build(ui): reinstall Trace and Collapsible with the shadcn-vue CLI
Quality / check (push) Successful in 3m34s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 4m32s
deploy / archied-image (push) Successful in 3m26s
2026-11-01 23:05:18 +11:00
sam bb897e76b8 Merge pull request 'feat(agentexec): record each agent run's transcript and show it per step (#1718)' (#1724) from claude/intelligent-tereshkova-5422da into main
deploy / gate (push) Successful in 4m37s
deploy / archied-image (push) Successful in 3m13s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
Quality / check (push) Successful in 3m41s
Reviewed-on: #1724
2026-11-01 11:43:32 +00:00
sam 07062352b4 Merge branch 'main' into claude/intelligent-tereshkova-5422da
Quality / check (pull_request) Successful in 3m35s
2026-11-01 11:43:20 +00:00
sam 856c15858b feat(ui): replace the top bar navigation with the sidebar-07 block (#1723)
deploy / agent-image (push) Successful in 11s
Quality / check (push) Successful in 3m24s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 3m18s
deploy / gate (push) Successful in 4m32s
2026-11-01 22:09:54 +11:00
sam 69a46249cc feat(webui): draw each transcript entry with its Trace pattern (#1718)
Quality / check (pull_request) Successful in 3m38s
Record the model's reasoning parts. The step run view shows reasoning as a
Thought row, shell calls as a terminal, the gate as a test run, web_fetch as a
source, finish as the verdict, and each fan-out branch as a subagent.
2026-11-01 22:09:53 +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 d6ca6a72a5 build(ui): build the dashboard in CI and the Taskfile instead of committing ui/dist
deploy / gate (push) Successful in 4m28s
deploy / archied-image (push) Successful in 3m29s
Quality / check (push) Canceled after 1m27s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
2026-11-01 22:07:36 +11:00
sam 243832fee6 docs(ui): add components with the shadcn-vue CLI, not by hand
deploy / archied-image (push) Successful in 2m47s
deploy / dist-zip (push) Skipped
Quality / check (push) Successful in 3m7s
deploy / gate (push) Successful in 3m51s
deploy / agent-image (push) Successful in 11s
2026-11-01 21:47:54 +11:00
sam e8c2c844a8 ci: skip setup-go caching on the self-hosted runner (#1716)
Quality / check (push) Successful in 3m1s
deploy / archied-image (push) Successful in 2m54s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 4m6s
2026-11-01 21:21:09 +11:00
sam 6220387ed6 fix(install): restart running services on reinstall (#1716)
Quality / check (push) Successful in 3m32s
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 7m18s
deploy / agent-image (push) Successful in 11s
deploy / archied-image (push) Successful in 3m4s
2026-11-01 17:59:05 +11:00
sam efd3eb2854 fix(releaseupdate): wait for the canary to offer a release before installing (#1716)
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 3m3s
Quality / check (push) Successful in 3m14s
deploy / gate (push) Successful in 6m48s
2026-11-01 02:55:31 +11:00
sam c78063eba0 chore(release): v1.57.0
Quality / check (push) Successful in 3m20s
deploy / archied-image (push) Successful in 2m51s
deploy / dist-zip (push) Failing after 1m56s
deploy / gate (push) Successful in 6m29s
deploy / agent-image (push) Successful in 3m25s
2026-11-01 02:26:01 +11:00
sam 0e931485a0 docs(releaseupdate): use contractions in the release and canary text (#1716)
deploy / agent-image (push) Successful in 12s
deploy / dist-zip (push) Skipped
deploy / gate (push) Successful in 6m27s
deploy / archied-image (push) Successful in 2m57s
Quality / check (push) Successful in 7m33s
2026-10-31 22:18:57 +11:00
sam 1bf536d4ab docs(releaseupdate): rewrite the canary comments in plain English (#1716)
deploy / agent-image (push) Successful in 11s
Quality / check (push) Canceled after 8m7s
deploy / archied-image (push) Successful in 2m57s
deploy / gate (push) Successful in 6m20s
deploy / dist-zip (push) Skipped
2026-10-31 22:11:04 +11:00
sam 2181b5fd08 ci(deploy): move the images' :latest only when a release is promoted (#1716)
deploy / gate (push) Successful in 6m29s
deploy / agent-image (push) Successful in 10s
deploy / archied-image (push) Successful in 2m59s
Quality / check (push) Successful in 3m47s
deploy / dist-zip (push) Skipped
2026-10-31 21:48:10 +11:00
sam a4a7c96da6 feat(releaseupdate): publish to next and promote to stable only after a canary evaluation (#1716)
deploy / agent-image (push) Skipped
deploy / dist-zip (push) Skipped
deploy / gate (push) Failing after 16m14s
deploy / archied-image (push) Skipped
Quality / check (push) Successful in 3m49s
2026-10-31 21:39:32 +11:00
sam a7f6e517ad ci(release): cut releases from [Unreleased] by workflow dispatch (#1716)
Quality / check (push) Canceled after 9m13s
deploy / gate (push) Successful in 7m17s
deploy / agent-image (push) Successful in 11s
deploy / dist-zip (push) Skipped
deploy / archied-image (push) Successful in 2m56s
2026-10-31 21:30:33 +11:00
sam 812d9004a7 feat(webui): keep the Model setup step open until the provider credential resolves (#1045)
deploy / agent-image (push) Successful in 11s
Quality / check (push) Successful in 4m40s
deploy / gate (push) Successful in 6m15s
deploy / archied-image (push) Successful in 2m57s
deploy / dist-zip (push) Skipped
2026-10-31 20:04:06 +11:00
sam ebc6dd67e6 fix(setup): offer the bundled database as an explicit choice on a re-run (#1388)
With an existing database_url, setup prefilled the URL, so a blank answer
kept it and the bundled socket database was unreachable without typing its
URL. The re-run database step now presents a choice menu: keep the existing
URL (still the default), switch to the bundled database (socket URL plus a
generated PGPASSWORD written to the env file), or enter a different URL.
Fresh installs and -database-url are unchanged; a blank answer anywhere
still keeps the existing URL. Pinned at the setup API level with fake
prompter/sink: TestRunParamsDatabaseChoice.
2026-10-31 20:03:33 +11:00
807 changed files with 21462 additions and 9804 deletions

No files matched your search

+49
View File
@@ -0,0 +1,49 @@
name: canary
on:
schedule:
- cron: "*/15 * * * *"
workflow_dispatch:
concurrency:
group: canary
permissions:
contents: read
packages: write
jobs:
judge:
if: vars.CANARY_URL != ''
runs-on: self-hosted
steps:
- name: Checkout
uses: actions/checkout@v4
with:
ref: main
fetch-depth: 0
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: false
- name: Build archied
run: go build -tags no_ui -o "$RUNNER_TEMP/archied" ./cmd/archied
- name: Log in to the Gitea registry
run: echo "${{ secrets.DEPLOY_TOKEN }}" | docker login git.catlow.cloud -u "${{ github.actor }}" --password-stdin
- name: Judge the canary
env:
ARCHIE_CANARY_TOKEN: ${{ secrets.CANARY_TOKEN }}
CANARY_WINDOW: ${{ vars.CANARY_WINDOW }}
run: |
window_args=()
if [ -n "$CANARY_WINDOW" ]; then
window_args=(-window "$CANARY_WINDOW")
fi
"$RUNNER_TEMP/archied" release canary check -dashboard "${{ vars.CANARY_URL }}" \
"${window_args[@]}" \
-latest git.catlow.cloud/sam/archied,git.catlow.cloud/sam/archie-agent
+54 -107
View File
@@ -1,7 +1,3 @@
# Builds and pushes the archied and archie-agent images to the Gitea
# registry on every merge to main, and publishes the distribution zip as a
# release on this repository. Gitea Actions reads this .github/workflows/
# directory.
name: deploy
on:
@@ -9,20 +5,8 @@ on:
branches: [main]
tags: ["v*"]
# Rapid successive pushes to main (a release commit right after its
# preceding fix, say) previously queued a full gate+build for each one,
# several minutes apiece, with no caching -- so a burst of pushes left
# three deploys racing in parallel for the same runner capacity. Only the
# last one's images matter (each job pushes its image tags), so cancel a
# superseded run rather than let it fight for resources it can't use.
#
# Keyed on the commit, not github.ref: a release push lands main and its
# tag in one go, both pointing at the same commit -- on.push matches
# branches and tags both, so a single release push otherwise fires
# redundant builds of identical content that a ref-keyed group can't see
# as the same work.
concurrency:
group: deploy-${{ github.sha }}
group: ${{ startsWith(github.ref, 'refs/tags/') && format('deploy-release-{0}', github.sha) || format('deploy-{0}', github.ref) }}
cancel-in-progress: true
permissions:
@@ -30,20 +14,17 @@ permissions:
packages: write
jobs:
gate:
plan:
runs-on: self-hosted
outputs:
archied_version: ${{ steps.release_tag.outputs.archied_version }}
run: ${{ steps.release_tag.outputs.run }}
steps:
- name: Checkout
uses: actions/checkout@v4
with:
fetch-depth: 0
# Read the release from the commit, not from github.ref. One release
# push carries main and both tags at the same SHA, and only one of
# those refs survives the concurrency group, so a ref-derived version
# is whatever won the race. The tag at HEAD is the same either way.
- name: Resolve archied tag at HEAD
id: release_tag
run: |
@@ -54,11 +35,33 @@ jobs:
else
echo "no release tag at HEAD; distribution zip will be skipped"
fi
run=true
case "$GITHUB_REF" in
refs/tags/*) ;;
*)
if [ -n "$version" ]; then
run=false
echo "the v$version tag push runs this commit; skipping the branch run"
fi
;;
esac
echo "run=$run" >> "$GITHUB_OUTPUT"
gate:
needs: plan
if: needs.plan.outputs.run == 'true'
runs-on: self-hosted
steps:
- name: Checkout
uses: actions/checkout@v4
with:
fetch-depth: 0
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: false
- uses: pnpm/action-setup@v4
with:
@@ -84,27 +87,12 @@ jobs:
git branch main origin/main
fi
# ripgrep and the unprivileged-userns sysctl are provisioned on the host.
# A self-hosted runner should not need sudo, and installing a package on
# every run is not the gate's job.
- name: Verify unprivileged user namespaces
run: unshare --user --map-root-user --net true
# The gate's uncached `go test ./...` runs the Docker-backed tests that
# -short skips, and those start a container from alpine:3. A fresh runner
# has no such image, so the suite failed on "No such image: alpine:3".
- name: Pull test container images
run: docker pull alpine:3
# One definition of the gate, in the Taskfile. This step used to inline
# its own list, which drifted weaker than `task check`: it ran no
# db:check, news:check or ui:check, so a release could ship stale
# generated SQL, a stale ui/dist, or release notes that disagree with
# CHANGELOG.md. It also ran the dashboard suite here rather than in the
# gate, where test:ui runs it with the type check. TEST_FLAGS is the one
# difference -- the release runs the whole suite, uncached and including
# the Docker-backed tests -short skips. The diff after it asserts
# `task fmt` changed nothing.
- name: Quality gate
run: |
task check TEST_FLAGS=-count=1
@@ -134,12 +122,11 @@ jobs:
if [ $fail -ne 0 ]; then
echo
echo "A release tag points at this commit but its changelog does not"
echo "describe that version. Run: task release:prepare VERSION=<ver>"
echo "edit the generated notes, then: task release VERSION=<ver>"
echo "describe that version. Cut releases with the release workflow."
exit 1
fi
if ! git tag --points-at HEAD | grep -qE '^v[0-9]' ; then
echo "This commit is not a release, so the images are published as :edge and sha-<sha>; :latest keeps naming the newest release."
echo "This commit isn't a release, so the images are published as :edge and sha-<sha>; :latest keeps naming the newest promoted release."
fi
archied-image:
@@ -151,9 +138,6 @@ jobs:
with:
fetch-depth: 0
# Deliberately NOT `github.sha`. On a tag push that is the ref's OBJECT id,
# and every release tag in this repo is annotated, so it names a tag object
# that cannot be checked out. Dereference it to the commit.
- name: Resolve the commit this ref points at
id: commit
run: |
@@ -170,35 +154,18 @@ jobs:
- name: Resolve component versions
id: versions
run: |
# One release stream: a `v*` tag names both components' versions.
RELEASE_TAG="$(git tag --points-at HEAD --list 'v*' | sort -V | tail -1)"
GATEWAY_VERSION="${RELEASE_TAG#v}"
RUNTIME_VERSION="${RELEASE_TAG#v}"
# `dev+<sha>` is what a build that is NOT a release reports, and it is
# honest now that such a build no longer publishes :latest: the version
# names the commit it came from, and the sha-<sha> tag makes it
# restorable. Before, this same string reached :latest minutes after a
# release and made the release's own stamping read as dev
# (archie-core-i5nb). (On an untagged push GITHUB_SHA IS the commit —
# the tag case is handled by the dereference above.)
[ -n "$GATEWAY_VERSION" ] || GATEWAY_VERSION="dev+${GITHUB_SHA:0:12}"
[ -n "$RUNTIME_VERSION" ] || RUNTIME_VERSION="dev+${GITHUB_SHA:0:12}"
echo "release_tag=$RELEASE_TAG" >> "$GITHUB_OUTPUT"
echo "gateway=$GATEWAY_VERSION" >> "$GITHUB_OUTPUT"
echo "runtime=$RUNTIME_VERSION" >> "$GITHUB_OUTPUT"
# :latest names the newest RELEASE, so only a commit that IS one
# publishes it. A push to main publishes :edge (mutable, newest main)
# and sha-<sha> (immutable) instead. That is what stops a release's
# :latest stamping from being overwritten minutes later by the next
# ordinary commit, which left a host reporting dev and made the update
# path unable to tell current from stale (archie-core-i5nb).
#
# `if` blocks rather than `[ -n "$X" ] && echo`: the latter returns
# non-zero when the test fails, and these steps run under `set -e`.
{
echo "archied_tags<<EOF"
if [ -n "$RELEASE_TAG" ]; then
echo "git.catlow.cloud/sam/archied:latest"
echo "git.catlow.cloud/sam/archied:$RELEASE_TAG"
fi
echo "git.catlow.cloud/sam/archied:edge"
echo "git.catlow.cloud/sam/archied:sha-${{ steps.commit.outputs.sha }}"
@@ -218,7 +185,6 @@ jobs:
cache-from: type=gha,scope=archied
cache-to: type=gha,mode=max,scope=archied
agent-image:
outputs:
agent_digest: ${{ steps.agent.outputs.digest }}
@@ -230,7 +196,6 @@ jobs:
with:
fetch-depth: 0
# Annotated tags: dereference to the commit, as archied-image does.
- name: Resolve the commit this ref points at
id: commit
run: |
@@ -261,30 +226,16 @@ jobs:
file: Dockerfile
push: true
tags: |
git.catlow.cloud/sam/archie-agent:latest
git.catlow.cloud/sam/archie-agent:${{ steps.versions.outputs.release_tag }}
git.catlow.cloud/sam/archie-agent:sha-${{ steps.commit.outputs.sha }}
build-args: |
RUNTIME_VERSION=${{ steps.versions.outputs.runtime }}
cache-from: type=gha,scope=archie-agent
cache-to: type=gha,mode=max,scope=archie-agent
# Packages every host-run binary (archied, archie-gateway,
# archie-state-store, archie-ui, archie-messaging) as a
# linux/amd64 zip for a
# non-Docker install, plus archie-agent: it has no unit, but a Kit run
# mounts it from archied's directory, so a host without it parks them.
# It waits only for the agent image, whose digest
# release.json pins.
dist-zip:
needs: [gate, agent-image]
# Not gated on github.ref. A release is pushed as main plus both tags at
# one SHA, the concurrency group below collapses those into a single run,
# and the survivor is whichever ref happened to start last -- for
# v1.23.0 that was refs/heads/main, so this job was skipped and no zip
# was ever produced. Resolve the tag from the commit instead of trusting
# the ref that won the race, and skip only when there is genuinely no
# archied tag at HEAD.
if: needs.gate.outputs.archied_version != ''
needs: [plan, gate, agent-image]
if: needs.plan.outputs.archied_version != ''
runs-on: self-hosted
steps:
- name: Checkout
@@ -294,10 +245,26 @@ jobs:
uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: false
- uses: pnpm/action-setup@v4
with:
package_json_file: ui/package.json
- name: Set up Node
uses: actions/setup-node@v4
with:
node-version: "24"
- name: Build the dashboard
working-directory: ui
run: |
pnpm install --frozen-lockfile
pnpm run build
- name: Resolve archied version
id: version
run: echo "version=${{ needs.gate.outputs.archied_version }}" >> "$GITHUB_OUTPUT"
run: echo "version=${{ needs.plan.outputs.archied_version }}" >> "$GITHUB_OUTPUT"
- name: Build linux/amd64 binaries
env:
@@ -306,22 +273,8 @@ jobs:
CGO_ENABLED: "0"
run: |
set -e
# Every process in the documented deployment ships in the zip, and
# every one of them carries the archied version it was cut from:
# they are one release, and an operator matching binaries by eye
# needs each to say so.
#
# That claim is load-bearing and this list is the whole of it: the
# v1.30.0 messaging extraction moved Telegram/email/webhook out of
# archied and nothing added archie-messaging here, so a host install
# ran on with a dead Telegram bot and no error anywhere
# (archie-core-1c01). TestDistZipShipsEveryHostCommand fails if this
# list and the copy list below stop matching the commands in cmd/.
ldflags="-X github.com/samcharles93/archie-core/internal/installtype.buildType=binary -X github.com/samcharles93/archie-core/internal/buildinfo.Version=${{ steps.version.outputs.version }} -X github.com/samcharles93/archie-core/internal/buildinfo.Runtime=${{ steps.version.outputs.version }} -X github.com/samcharles93/archie-core/internal/app/agentworker.version=${{ steps.version.outputs.version }}"
mkdir -p dist
# Units first, then the binaries that run beside them without one.
# The agentworker stamp only lands in archie-agent; the linker
# ignores -X for a symbol a binary does not import.
for cmd in $(jq -r '.required_topology.units[], .required_topology.binaries[]?' release.json); do
go build -ldflags "$ldflags" -o "dist/$cmd" "./cmd/$cmd"
done
@@ -339,8 +292,6 @@ jobs:
digest='${{ needs.agent-image.outputs.agent_digest }}'
test -n "$digest"
jq --arg image "git.catlow.cloud/sam/archie-agent@$digest" '. + {agent_image: $image}' release.json > "$name/release.json"
# README.md doesn't exist yet in this repo; include it once it does
# rather than fail the release on its absence.
[ -f README.md ] && cp README.md "$name/"
zip -r "$name.zip" "$name"
echo "name=$name" >> "$GITHUB_OUTPUT"
@@ -352,10 +303,6 @@ jobs:
path: ${{ steps.zip.outputs.name }}.zip
retention-days: 90
# Installs and updates take a release from the signed artifact in the
# registry, so this is what publishes it: the statement signed with
# RELEASE_SIGNING_KEY and the zip, tagged v<version>, next, and stable
# unless it is a prerelease.
- name: Log in to the Gitea registry
run: echo "${{ secrets.DEPLOY_TOKEN }}" | docker login git.catlow.cloud -u "${{ github.actor }}" --password-stdin
@@ -373,8 +320,6 @@ jobs:
-agent-image "git.catlow.cloud/sam/archie-agent@${{ needs.agent-image.outputs.agent_digest }}" \
-changelog "https://git.catlow.cloud/sam/archie/releases/tag/v$version"
# The release page carries this version's changelog section, the
# release's own reviewed prose; the signed statement links to it.
- name: Publish the Gitea release notes
env:
DEPLOY_TOKEN: ${{ secrets.DEPLOY_TOKEN }}
@@ -395,7 +340,6 @@ jobs:
api="https://git.catlow.cloud/api/v1"
repo="sam/archie"
auth="Authorization: token $DEPLOY_TOKEN"
# Idempotent: a re-run replaces the release on the tag.
curl -sf -X DELETE -H "$auth" "$api/repos/$repo/releases/tags/$tag" >/dev/null || true
curl -sf -X POST -H "$auth" -H "Content-Type: application/json" \
-d "$(jq -n --arg tag "$tag" --arg name "Archie v$version" --arg body "$(cat "$notes")" \
@@ -403,9 +347,12 @@ jobs:
"$api/repos/$repo/releases" >/dev/null
echo "published release notes for $tag"
# A Gitea package belongs to its owner, not a repository, so the ones this
# workflow publishes are linked here. Linking is per package and a no-op
# once done, so an already linked package is not an error.
- name: Install the release on the canary
if: vars.CANARY_URL != ''
env:
ARCHIE_CANARY_TOKEN: ${{ secrets.CANARY_TOKEN }}
run: ./dist/archied release canary start -dashboard "${{ vars.CANARY_URL }}" -version "${{ steps.version.outputs.version }}"
- name: Link the packages to this repository
env:
DEPLOY_TOKEN: ${{ secrets.DEPLOY_TOKEN }}
+47
View File
@@ -0,0 +1,47 @@
name: promote
on:
workflow_dispatch:
inputs:
version:
description: "release the canary is expected to run; must match what it runs"
required: true
type: string
concurrency:
group: promote
cancel-in-progress: true
permissions:
contents: read
packages: write
jobs:
promote:
if: vars.CANARY_URL != ''
runs-on: self-hosted
steps:
- name: Checkout
uses: actions/checkout@v4
with:
ref: main
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: false
- name: Build archied
run: go build -tags no_ui -o "$RUNNER_TEMP/archied" ./cmd/archied
- name: Log in to the Gitea registry
run: echo "${{ secrets.DEPLOY_TOKEN }}" | docker login git.catlow.cloud -u "${{ github.actor }}" --password-stdin
- name: Promote the canary's release
env:
ARCHIE_CANARY_TOKEN: ${{ secrets.CANARY_TOKEN }}
run: |
"$RUNNER_TEMP/archied" release canary promote -dashboard "${{ vars.CANARY_URL }}" \
-version "${{ inputs.version }}" \
-latest git.catlow.cloud/sam/archied,git.catlow.cloud/sam/archie-agent
+9 -10
View File
@@ -2,8 +2,6 @@ name: Quality
on:
pull_request:
push:
branches: [main]
permissions:
contents: read
@@ -20,12 +18,8 @@ jobs:
with:
fetch-depth: 0
- name: Verify extension namespace support
run: |
if [ -e /proc/sys/kernel/apparmor_restrict_unprivileged_userns ]; then
sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0
fi
unshare --user --map-root-user --net true
- name: Verify unprivileged user namespaces
run: unshare --user --map-root-user --net true
- uses: actions/setup-go@v5
with:
@@ -46,8 +40,13 @@ jobs:
go install mvdan.cc/gofumpt@v0.11.0
bash tools/proto.sh install
sudo apt-get update
sudo apt-get install -y --no-install-recommends ripgrep
- uses: actions/cache@v4
with:
path: ~/.cache/golangci-lint
key: golangci-lint-${{ hashFiles('.golangci-version', '.golangci.yml', 'go.sum') }}-${{ github.sha }}
restore-keys: |
golangci-lint-${{ hashFiles('.golangci-version', '.golangci.yml', 'go.sum') }}-
golangci-lint-
- name: Ensure contract baseline ref
run: |
+55
View File
@@ -0,0 +1,55 @@
name: release
on:
workflow_dispatch:
inputs:
release:
description: "major, minor, patch, or an exact version such as 1.57.0"
required: true
default: minor
concurrency:
group: release
permissions:
contents: write
jobs:
cut:
runs-on: self-hosted
steps:
- name: Check DEPLOY_TOKEN is configured
env:
DEPLOY_TOKEN: ${{ secrets.DEPLOY_TOKEN }}
run: |
if [ -z "$DEPLOY_TOKEN" ]; then
echo "::error::DEPLOY_TOKEN is not set for this repository, so the release cannot push its commit and tag. Set the secret here, or dispatch the release from the Gitea primary."
exit 1
fi
- name: Checkout
uses: actions/checkout@v4
with:
ref: main
fetch-depth: 0
token: ${{ secrets.DEPLOY_TOKEN }}
- name: Set up Go
uses: actions/setup-go@v5
with:
go-version-file: go.mod
cache: false
- name: Install Task
run: go install github.com/go-task/task/v3/cmd/task@v3.48.0
- name: Cut the release
env:
RELEASE: ${{ inputs.release }}
run: |
git config user.name "Sam Catlow"
git config user.email "sam@catlow.tech"
task release RELEASE="$RELEASE"
- name: Push the release
run: git push --atomic origin main "$(git describe --exact-match --match 'v*' HEAD)"
+3 -1
View File
@@ -25,7 +25,7 @@ config.production.toml
/ui/node_modules/
/ui/.vite/
/ui/*.tsbuildinfo
# ui/dist IS committed: the Go build must not need a Node toolchain.
/ui/dist/
# air live-reload
/.air/
@@ -47,3 +47,5 @@ __pycache__/
# Local symlink to the archipelago marketplace repo
/archipelago
.agents-run/
/.pnpm-store/
+15 -1
View File
@@ -82,8 +82,22 @@ linters:
- {pkg: "github.com/samcharles93/archie-core/internal/app/archied", desc: "the daemon is another service"}
- {pkg: "github.com/samcharles93/archie-core/internal/app/archiegateway", desc: "the Gateway is another service"}
- {pkg: "github.com/nats-io", desc: "the State Store serves gRPC only"}
dashboard-service:
files: ["**/internal/webui/**", "**/internal/app/archieui/**", "**/cmd/archie-ui/**"]
deny:
- {pkg: "github.com/samcharles93/archie-core/internal/container", desc: "only the daemon owns containers"}
- {pkg: "github.com/samcharles93/archie-core/internal/agentexec", desc: "only the daemon owns containers"}
- {pkg: "github.com/samcharles93/archie-core/internal/app/archied", desc: "the daemon is another service"}
messaging-service:
files: ["**/internal/app/archiemessaging/**", "**/cmd/archie-messaging/**"]
deny:
- {pkg: "github.com/jackc/pgx", desc: "reach the State Store through its contract"}
- {pkg: "github.com/samcharles93/archie-core/internal/infrastructure/postgres", desc: "reach the State Store through its contract"}
- {pkg: "github.com/samcharles93/archie-core/internal/infrastructure/controlplanestore", desc: "reach the State Store through its contract"}
- {pkg: "github.com/samcharles93/archie-core/internal/domain/workflow", desc: "the workflow engine is the daemon's"}
- {pkg: "github.com/samcharles93/archie-core/internal/agentexec", desc: "agent execution is the daemon's"}
shared:
files: ["**/internal/app/servicekit/**", "**/internal/app/chattask/**"]
files: ["**/internal/app/servicekit/**"]
deny:
- {pkg: "github.com/samcharles93/archie-core/internal/daemon", desc: "shared code must not pull in a service"}
- {pkg: "github.com/samcharles93/archie-core/internal/webui", desc: "shared code must not pull in a service"}
-4
View File
@@ -1,4 +0,0 @@
# Generated output: only its generator writes it, and the gate byte-checks it.
docs/data/generated/
internal/contracts/
ui/dist/
+51
View File
@@ -0,0 +1,51 @@
# Canary judge: check the release the canary is running, then promote it, pick
# up a newer `next`, or roll it back. Every fifteen minutes, and on demand.
#
# Requires repo secrets canary_url, canary_token and deploy_token (the registry
# credentials the `-latest` re-tagging needs). canary_window is optional.
# Shell-side references are written $$name (see the note in deploy.yaml).
#
# Written to fail loudly when canary_url is missing: the schedule only exists
# because the maintainer asked for one, so a canary nobody configured is a
# misconfiguration, not a quiet skip.
when:
- event: [cron]
- event: [manual]
# A judging run takes longer than the interval when the canary is unhealthy;
# overlapping runs would judge the same release twice.
concurrency: 1
steps:
- name: judge
image: golang:1.27.3-bookworm
environment:
CANARY_URL:
from_secret: canary_url
CANARY_WINDOW:
from_secret: canary_window
ARCHIE_CANARY_TOKEN:
from_secret: canary_token
DEPLOY_TOKEN:
from_secret: deploy_token
commands:
- '[ -n "$$CANARY_URL" ] || { echo "repo secret canary_url is not set, so there is no canary to judge"; exit 1; }'
- '[ -n "$$ARCHIE_CANARY_TOKEN" ] || { echo "repo secret canary_token is not set, so the canary cannot be reached"; exit 1; }'
- '[ -n "$$DEPLOY_TOKEN" ] || { echo "repo secret deploy_token is not set, so the registry cannot be tagged"; exit 1; }'
- go build -tags no_ui -o /tmp/archied ./cmd/archied
# archied reads the registry credentials a docker login would have
# written; this step has no docker CLI, so the file is written directly.
- |
set -eu
mkdir -p "$$HOME/.docker"
auth=$(printf '%s:%s' "$$CI_REPO_OWNER" "$$DEPLOY_TOKEN" | base64 -w0)
printf '{"auths":{"git.catlow.cloud":{"auth":"%s"}}}\n' "$$auth" > "$$HOME/.docker/config.json"
- |
set -eu
set --
if [ -n "$$CANARY_WINDOW" ]; then
set -- -window "$$CANARY_WINDOW"
fi
/tmp/archied release canary check -dashboard "$$CANARY_URL" "$$@" \
-latest git.catlow.cloud/sam/archied,git.catlow.cloud/sam/archie-agent
+333
View File
@@ -0,0 +1,333 @@
# Publish pipeline: a push to main builds the edge images, a v* tag also cuts a
# signed release. The release workflow pushes main and the tag in one command,
# so both events are delivered for the same commit; `plan` decides which
# pipeline does the work and the other one skips.
#
# Requires repo secrets: deploy_token (pushes images, publishes the Gitea
# release, links the packages) and release_signing_key (the ed25519 seed the
# release statement is signed with). canary_url and canary_token are optional;
# without them the canary install is skipped.
#
# Every shell-side reference is written $$name, which arrives at the shell as
# $name. Woodpecker rewrites only the braced form: ${name} is substituted before
# the shell runs, and an operator inside it is dropped, so ${version:-none}
# becomes empty instead of defaulting. The escaped form is used everywhere so the
# rule is mechanical rather than a judgement per line.
when:
- event: push
branch: [main]
- event: tag
ref: refs/tags/v*
# Two deployments at once would race on the released tags and on `latest`.
concurrency: 1
variables:
# The gate and the distribution step both build the dashboard. Anchored here
# rather than written twice, so the digest and the pnpm version can only
# change in one place.
- &node-setup |
set -eu
apt-get update -qq
apt-get install -y -qq --no-install-recommends xz-utils
curl -fsSL -o /tmp/node.tar.xz https://nodejs.org/dist/v24.22.2/node-v24.22.2-linux-x64.tar.xz
echo "48cc0e21e048790e54c0cf5749c2725005313d652651c40b7a21feb9697aaf75 /tmp/node.tar.xz" | sha256sum -c -
tar -xJf /tmp/node.tar.xz -C /usr/local --strip-components=1
# pnpm's version belongs to the lockfile; installing any other one makes
# `pnpm install --frozen-lockfile` reject the tree.
npm install -g "pnpm@$(node -p 'require("./ui/package.json").packageManager.split("@")[1]')"
clone:
git:
image: woodpeckerci/plugin-git:2.8.0
settings:
# A tag pipeline must see the tag it is building, and a branch pipeline
# must see a tag pointing at HEAD to know the tag pipeline owns it.
tags: true
fetch_target_branch: true
steps:
- name: plan
image: alpine:3
commands:
- apk add --no-cache git
- |
set -eu
# An annotated tag makes CI_COMMIT_SHA the tag object, so the commit is
# resolved from the ref: image tags and the release statement pin it.
sha=$(git rev-parse "$$CI_COMMIT_REF^{commit}")
version=$(git tag --points-at HEAD --list 'v*' | sed -e 's|^v||' | sort -V | tail -1)
run=true
case "$$CI_PIPELINE_EVENT" in
tag) ;;
*) [ -z "$$version" ] || run=false ;;
esac
{
echo "COMMIT_SHA=$$sha"
echo "RELEASE_VERSION=$$version"
echo "RUN=$$run"
} > "$$CI_WORKSPACE/.git/ci-plan.env"
echo "commit $$sha, release $${version:-none}, run $$run"
- name: gate
image: golang:1.27.3-bookworm
depends_on: [plan]
# The full test suite starts containers. It drives the host daemon through
# the Go client, so the socket is enough - this step needs no docker CLI.
# The one test that needs the daemon binds a temporary directory into the
# container it starts, so that directory has to exist at the same path on
# the host; TMPDIR points the test at it.
volumes:
- /var/run/docker.sock:/var/run/docker.sock
- /var/tmp/woodpecker-archie-gate:/var/tmp/woodpecker-archie-gate
environment:
DOCKER_HOST: unix:///var/run/docker.sock
TMPDIR: /var/tmp/woodpecker-archie-gate
commands:
- '. "$$CI_WORKSPACE/.git/ci-plan.env"'
- '[ "$$RUN" = true ] || { echo "a release tag owns this commit; the tag pipeline publishes it"; exit 0; }'
- go install github.com/go-task/task/v3/cmd/task@v3.48.0
- go install github.com/golangci/golangci-lint/v2/cmd/golangci-lint@$(cat .golangci-version)
- go install mvdan.cc/gofumpt@v0.11.0
- bash tools/proto.sh install
- *node-setup
- |
set -eu
if ! git show-ref --verify --quiet refs/heads/main; then
if git rev-parse --verify --quiet origin/main >/dev/null; then
git branch main origin/main
else
# A tag pipeline clones the tag alone. HEAD is the released commit,
# which was on main, so the contract baseline is that same tree.
echo "no origin/main in this clone; using the released commit as the contract baseline"
git branch main HEAD
fi
fi
- task check TEST_FLAGS=-count=1
- git diff --exit-code
- go install golang.org/x/vuln/cmd/govulncheck@latest
- govulncheck ./...
- |
set -eu
fail=0
for tag in $(git tag --points-at HEAD); do
case "$$tag" in
v*)
ver=$(echo "$$tag" | sed -e 's|^v||')
echo " release tag $$tag -> looking for [$$ver] in CHANGELOG.md"
grep -q "^## \[$$ver\]" CHANGELOG.md || {
echo " FAIL: CHANGELOG.md has no [$$ver] section"
fail=1
}
;;
esac
done
if [ $$fail -ne 0 ]; then
echo
echo "A release tag points at this commit but its changelog does not"
echo "describe that version. Cut releases with the release workflow."
exit 1
fi
if ! git tag --points-at HEAD | grep -qE '^v[0-9]'; then
echo "This commit isn't a release, so the images are published as :edge and sha-<sha>; :latest keeps naming the newest promoted release."
fi
- name: archied-image
image: docker:29-cli
depends_on: [gate]
volumes:
- /var/run/docker.sock:/var/run/docker.sock
environment:
DOCKER_HOST: unix:///var/run/docker.sock
DEPLOY_TOKEN:
from_secret: deploy_token
commands:
- '. "$$CI_WORKSPACE/.git/ci-plan.env"'
- '[ "$$RUN" = true ] || { echo "skipped: the tag pipeline publishes this commit"; exit 0; }'
- '[ -n "$$DEPLOY_TOKEN" ] || { echo "repo secret deploy_token is not set"; exit 1; }'
- printf '%s' "$$DEPLOY_TOKEN" | docker login git.catlow.cloud -u "$$CI_REPO_OWNER" --password-stdin
- |
set -eu
# A release reports its version; anything else is a build of main and
# says so, so a running binary can always name its commit.
if [ -n "$$RELEASE_VERSION" ]; then
component=$$RELEASE_VERSION
else
component="dev+$(echo "$$COMMIT_SHA" | cut -c1-12)"
fi
set -- \
--tag "git.catlow.cloud/sam/archied:edge" \
--tag "git.catlow.cloud/sam/archied:sha-$$COMMIT_SHA"
if [ -n "$$RELEASE_VERSION" ]; then
set -- "$$@" --tag "git.catlow.cloud/sam/archied:v$$RELEASE_VERSION"
fi
# No cache flags: the agent's daemon keeps its layer cache between
# pipelines, which is what type=gha bought on ephemeral runners.
docker buildx build --push --file Dockerfile.archied \
--build-arg GATEWAY_VERSION="$$component" \
--build-arg RUNTIME_VERSION="$$component" \
--provenance=false \
"$$@" .
- name: agent-image
image: docker:29-cli
depends_on: [gate]
volumes:
- /var/run/docker.sock:/var/run/docker.sock
environment:
DOCKER_HOST: unix:///var/run/docker.sock
DEPLOY_TOKEN:
from_secret: deploy_token
commands:
- '. "$$CI_WORKSPACE/.git/ci-plan.env"'
- '[ "$$RUN" = true ] || { echo "skipped: the tag pipeline publishes this commit"; exit 0; }'
- '[ -n "$$RELEASE_VERSION" ] || { echo "not a release; the agent image is only published with a release"; exit 0; }'
- '[ -n "$$DEPLOY_TOKEN" ] || { echo "repo secret deploy_token is not set"; exit 1; }'
- printf '%s' "$$DEPLOY_TOKEN" | docker login git.catlow.cloud -u "$$CI_REPO_OWNER" --password-stdin
- |
set -eu
apk add --no-cache jq
docker buildx build --push --file Dockerfile \
--build-arg RUNTIME_VERSION="$$RELEASE_VERSION" \
--tag "git.catlow.cloud/sam/archie-agent:v$$RELEASE_VERSION" \
--tag "git.catlow.cloud/sam/archie-agent:sha-$$COMMIT_SHA" \
--provenance=false \
--metadata-file "$$CI_WORKSPACE/.git/agent-image.json" \
.
# The release statement pins the agent image by digest, so the digest is
# what the distribution records, not the tag.
jq -er '."containerimage.digest"' "$$CI_WORKSPACE/.git/agent-image.json" \
> "$$CI_WORKSPACE/.git/agent-image.digest"
echo "agent image $(cat "$$CI_WORKSPACE/.git/agent-image.digest")"
- name: dist
image: golang:1.27.3-bookworm
depends_on: [archied-image, agent-image]
commands:
- '. "$$CI_WORKSPACE/.git/ci-plan.env"'
- '[ "$$RUN" = true ] || { echo "skipped: the tag pipeline publishes this commit"; exit 0; }'
- '[ -n "$$RELEASE_VERSION" ] || { echo "not a release; no distribution to build"; exit 0; }'
- apt-get update -qq
- apt-get install -y -qq --no-install-recommends jq zip
- *node-setup
# A subshell: a bare `cd ui` here would leave every later command in this
# step building from the dashboard directory.
- |
set -eu
(
cd ui
pnpm install --frozen-lockfile
pnpm run build
)
- |
set -eu
base=github.com/samcharles93/archie-core
ldflags="-X $${base}/internal/installtype.buildType=binary -X $${base}/internal/buildinfo.Version=$$RELEASE_VERSION -X $${base}/internal/buildinfo.Runtime=$$RELEASE_VERSION -X $${base}/internal/app/agentworker.version=$$RELEASE_VERSION"
cmds=$(jq -r '.required_topology.units[], .required_topology.binaries[]?' release.json)
mkdir -p dist
for cmd in $$cmds; do
GOOS=linux GOARCH=amd64 CGO_ENABLED=0 go build -ldflags "$$ldflags" -o "dist/$$cmd" "./cmd/$$cmd"
done
name="archie-core-archied-v$$RELEASE_VERSION-linux-amd64"
mkdir -p "$$name"
for cmd in $$cmds; do
cp "dist/$$cmd" "$$name/"
done
cp deployments/INSTRUCTIONS.md CHANGELOG.md "$$name/"
if [ -f README.md ]; then cp README.md "$$name/"; fi
digest=$(cat "$$CI_WORKSPACE/.git/agent-image.digest")
test -n "$$digest"
jq --arg image "git.catlow.cloud/sam/archie-agent@$$digest" '. + {agent_image: $$image}' \
release.json > "$$name/release.json"
zip -qr "$$name.zip" "$$name"
echo "RELEASE_ZIP=$$name.zip" >> "$$CI_WORKSPACE/.git/ci-plan.env"
echo "built $$name.zip"
- name: publish
image: golang:1.27.3-bookworm
depends_on: [dist]
environment:
DEPLOY_TOKEN:
from_secret: deploy_token
ARCHIE_RELEASE_SEED:
from_secret: release_signing_key
commands:
- '. "$$CI_WORKSPACE/.git/ci-plan.env"'
- '[ "$$RUN" = true ] || { echo "skipped: the tag pipeline publishes this commit"; exit 0; }'
- '[ -n "$$RELEASE_VERSION" ] || { echo "not a release; nothing to publish"; exit 0; }'
- '[ -n "$$ARCHIE_RELEASE_SEED" ] || { echo "repo secret release_signing_key is not set"; exit 1; }'
# archied pushes the release artifact with oras, which reads the registry
# credentials a docker login would have written.
- |
set -eu
mkdir -p "$$HOME/.docker"
auth=$(printf '%s:%s' "$$CI_REPO_OWNER" "$$DEPLOY_TOKEN" | base64 -w0)
printf '{"auths":{"git.catlow.cloud":{"auth":"%s"}}}\n' "$$auth" > "$$HOME/.docker/config.json"
- |
set -eu
prerelease=false
case "$$RELEASE_VERSION" in *-*) prerelease=true ;; esac
digest=$(cat "$$CI_WORKSPACE/.git/agent-image.digest")
./dist/archied release publish -source git.catlow.cloud/sam/archie \
-version "$$RELEASE_VERSION" -prerelease="$$prerelease" \
-zip "$$RELEASE_ZIP" \
-agent-image "git.catlow.cloud/sam/archie-agent@$$digest" \
-changelog "https://git.catlow.cloud/sam/archie/releases/tag/v$$RELEASE_VERSION"
- name: notes
image: golang:1.27.3-bookworm
depends_on: [dist]
environment:
DEPLOY_TOKEN:
from_secret: deploy_token
commands:
- '. "$$CI_WORKSPACE/.git/ci-plan.env"'
- '[ "$$RUN" = true ] || { echo "skipped: the tag pipeline publishes this commit"; exit 0; }'
- '[ -n "$$RELEASE_VERSION" ] || { echo "not a release; no notes to publish"; exit 0; }'
- '[ -n "$$DEPLOY_TOKEN" ] || { echo "repo secret deploy_token is not set"; exit 1; }'
- apt-get update -qq
- apt-get install -y -qq --no-install-recommends jq
- |
set -eu
tag="v$$RELEASE_VERSION"
notes=$(mktemp)
awk -v hdr="## [$$RELEASE_VERSION]" '
index($$0, hdr) == 1 { printing = 1 }
printing && /^## \[/ && index($$0, hdr) != 1 { exit }
printing { print }
' CHANGELOG.md > "$$notes"
if ! [ -s "$$notes" ]; then
echo "no [$$RELEASE_VERSION] section extracted from CHANGELOG.md" >&2
exit 1
fi
api=https://git.catlow.cloud/api/v1
repo=sam/archie
auth="Authorization: token $$DEPLOY_TOKEN"
curl -sf -X DELETE -H "$$auth" "$$api/repos/$$repo/releases/tags/$$tag" >/dev/null || true
curl -sf -X POST -H "$$auth" -H "Content-Type: application/json" \
-d "$(jq -n --arg tag "$$tag" --arg name "Archie v$$RELEASE_VERSION" --arg body "$(cat "$$notes")" \
'{tag_name: $$tag, name: $$name, body: $$body, draft: false, prerelease: false}')" \
"$$api/repos/$$repo/releases" >/dev/null
echo "published release notes for $$tag"
# The packages exist under this repository's namespace but are not
# linked to it, so the package pages stay empty until this runs.
for name in archied archie-agent archie; do
curl -sS -o /dev/null -X POST -H "$$auth" \
"$$api/packages/sam/container/$$name/-/link/archie" || true
done
- name: canary
image: golang:1.27.3-bookworm
depends_on: [publish]
environment:
CANARY_URL:
from_secret: canary_url
ARCHIE_CANARY_TOKEN:
from_secret: canary_token
commands:
- '. "$$CI_WORKSPACE/.git/ci-plan.env"'
- '[ "$$RUN" = true ] || { echo "skipped: the tag pipeline publishes this commit"; exit 0; }'
- '[ -n "$$RELEASE_VERSION" ] || { echo "not a release; nothing to install on the canary"; exit 0; }'
- '[ -n "$$CANARY_URL" ] || { echo "canary_url is not set; skipping the canary install"; exit 0; }'
- ./dist/archied release canary start -dashboard "$$CANARY_URL" -version "$$RELEASE_VERSION"
+41
View File
@@ -0,0 +1,41 @@
# Manual promotion: move stable to the release the canary is running, without
# waiting for its verdict. Same rules as the canary's own promotion, minus the
# window.
#
# Start it with the pipeline variable VERSION set to the release the canary
# runs (woodpecker-cli pipeline create --branch main --var VERSION=1.57.0).
#
# Requires repo secrets canary_url, canary_token and deploy_token.
when:
- event: [manual]
concurrency: 1
steps:
- name: promote
image: golang:1.27.3-bookworm
environment:
CANARY_URL:
from_secret: canary_url
ARCHIE_CANARY_TOKEN:
from_secret: canary_token
DEPLOY_TOKEN:
from_secret: deploy_token
commands:
- '[ -n "$$VERSION" ] || { echo "VERSION is empty: start this workflow with the pipeline variable VERSION=<release the canary runs>"; exit 1; }'
- '[ -n "$$CANARY_URL" ] || { echo "repo secret canary_url is not set, so there is no canary to read"; exit 1; }'
- '[ -n "$$ARCHIE_CANARY_TOKEN" ] || { echo "repo secret canary_token is not set, so the canary cannot be reached"; exit 1; }'
- '[ -n "$$DEPLOY_TOKEN" ] || { echo "repo secret deploy_token is not set, so the registry cannot be tagged"; exit 1; }'
- go build -tags no_ui -o /tmp/archied ./cmd/archied
# archied reads the registry credentials a docker login would have
# written; this step has no docker CLI, so the file is written directly.
- |
set -eu
mkdir -p "$$HOME/.docker"
auth=$(printf '%s:%s' "$$CI_REPO_OWNER" "$$DEPLOY_TOKEN" | base64 -w0)
printf '{"auths":{"git.catlow.cloud":{"auth":"%s"}}}\n' "$$auth" > "$$HOME/.docker/config.json"
- >-
/tmp/archied release canary promote -dashboard "$$CANARY_URL"
-version "$$VERSION"
-latest git.catlow.cloud/sam/archied,git.catlow.cloud/sam/archie-agent
+60
View File
@@ -0,0 +1,60 @@
# Pull-request gate: the same `task check` the maintainer runs locally.
#
# One step, not one step per check: `task check` installs task, golangci-lint,
# gofumpt, buf and sqlc into the container it runs in, and a second step starts
# from an empty container and pays for that again.
when:
- event: [pull_request]
clone:
git:
image: woodpeckerci/plugin-git:2.8.0
settings:
# The gate compares the contracts against main and reads the release tags
# for the version a build reports, so a partial clone will not do.
tags: true
# A pull-request pipeline otherwise clones only the pull request's own
# ref, leaving no main for the contract baseline to compare against.
fetch_target_branch: true
steps:
- name: check
image: golang:1.27.3-bookworm
commands:
- go install github.com/go-task/task/v3/cmd/task@v3.48.0
- go install github.com/golangci/golangci-lint/v2/cmd/golangci-lint@$(cat .golangci-version)
- go install mvdan.cc/gofumpt@v0.11.0
- bash tools/proto.sh install
# The gate builds and tests the dashboard, so Node and pnpm sit next to
# Go. Pinned tarball verified by digest, not a third-party setup script:
# the gate must not change under the repository.
- |
set -eu
apt-get update -qq
apt-get install -y -qq --no-install-recommends xz-utils
curl -fsSL -o /tmp/node.tar.xz https://nodejs.org/dist/v24.22.2/node-v24.22.2-linux-x64.tar.xz
echo "48cc0e21e048790e54c0cf5749c2725005313d652651c40b7a21feb9697aaf75 /tmp/node.tar.xz" | sha256sum -c -
tar -xJf /tmp/node.tar.xz -C /usr/local --strip-components=1
# pnpm's version belongs to the lockfile; installing any other one makes
# `pnpm install --frozen-lockfile` reject the tree.
npm install -g "pnpm@$(node -p 'require("./ui/package.json").packageManager.split("@")[1]')"
node --version
pnpm --version
- |
set -eu
# The contract baseline is a local main. plugin-git fetches with an explicit
# refspec, so it creates no remote-tracking branch itself; only the target
# branch fetch above does, which is why this fails rather than comparing
# the pull request against its own tree.
if ! git show-ref --verify --quiet refs/heads/main; then
if ! git rev-parse --verify --quiet origin/main >/dev/null; then
echo "no main in this clone, so the contracts cannot be compared against a baseline" >&2
exit 1
fi
git branch main origin/main
fi
- task --concurrency 1 check
# The gate rewrites the tree (fmt, generated contracts and queries); a
# rewrite the author did not commit is a failure, not a side effect.
- git diff --exit-code
+50
View File
@@ -0,0 +1,50 @@
# Manual release: turn [Unreleased] in CHANGELOG.md into a release commit, tag
# it, and push main and the tag in one command. The deploy pipeline publishes
# what this pushes, so this workflow commits and tags but never builds.
#
# Start it with the pipeline variable RELEASE=minor (or major, patch, or an
# exact 1.2.3): woodpecker-cli pipeline create --branch main --var RELEASE=minor
# sam/archie, or the same variable in the web UI's pipeline dialog.
#
# Shell-side references are written $$name (see the note in deploy.yaml).
#
# Requires repo secret deploy_token, a token that may push to main and to tags.
when:
- event: [manual]
# Two releases at once would read the same last tag and try to write it twice.
concurrency: 1
clone:
git:
image: woodpeckerci/plugin-git:2.8.0
settings:
# `task release` derives the next version from the release tags.
tags: true
fetch_target_branch: true
steps:
- name: cut
image: golang:1.27.3-bookworm
environment:
DEPLOY_TOKEN:
from_secret: deploy_token
commands:
- '[ -n "$$RELEASE" ] || { echo "RELEASE is empty: start this workflow with the pipeline variable RELEASE=major|minor|patch|x.y.z"; exit 1; }'
- '[ -n "$$DEPLOY_TOKEN" ] || { echo "repo secret deploy_token is not set, so the release cannot push its commit and tag"; exit 1; }'
- go install github.com/go-task/task/v3/cmd/task@v3.48.0
- git config user.name "Sam Catlow"
- git config user.email "sam@catlow.tech"
- task release RELEASE="$$RELEASE"
- |
set -eu
tag=$(git describe --exact-match --match 'v*' HEAD)
# HEAD, not a local main: the clone checks out the fetched ref detached,
# so there is no branch to name. The release commit is a child of main,
# so this is the fast-forward an atomic push needs.
#
# Gitea authenticates a token in the password position and ignores the
# user name, so the token never has to be a real login.
git push --atomic "https://x-access-token:$$DEPLOY_TOKEN@git.catlow.cloud/sam/archie.git" HEAD:refs/heads/main "$$tag"
echo "released $$tag"
+106
View File
@@ -5,6 +5,112 @@ release's per-component sections are labelled beneath its heading.
## [Unreleased]
## [1.62.0] - 2026-11-10
### archied
- When an agent step reaches its step budget, the task asks to continue instead of parking. Approving resumes the stopped step with its conversation, including inside a parallel branch.
- A parked task is flagged when the credential, connection or setting its blocker names changes, so you can see which parks are worth retrying.
- Merging, closing and issue tools use the repository's own forge connection. A repository on Gitea no longer gets a GitHub 404 when its pull request is merged from archie.
- A restart re-queues a running task at the step it was interrupted in, and parks it after three restarts instead of looping.
- Issues and pull request review activity from authors without write access are ignored.
- A baseline repair made by the repository gate is opened as its own pull request before the task continues.
- Closing an issue that still has open dependencies is recorded as refused, rather than parking the task.
- When the work volume fills, stale task clones are reclaimed; clones with uncommitted or unpushed work are kept. Clones need 1 GiB free, not 5.
- A corrupt repository mirror is rebuilt, and a push that hits a missing object rebuilds the mirror and retries once.
- Readiness reports degraded when the run loop stalls.
- Execution budgets set in the dashboard are no longer reverted when the model catalogue loads.
- A full volume is reported as an environment failure, and an unreachable secret engine as unavailable, rather than as a bad or missing credential.
- A park from the workflow identity check now appears in the task log.
- Every task records the identity that created it, and its queued event names the task, actor and principal. System is the one instance identity: it polls forge connections and owns the root grants and connection permits the bot-named identity used to hold, which existing tasks, grants and permits move to on upgrade.
### archie-ui
- A chat reply is no longer lost when you switch conversation or reload mid-answer: the turn finishes and its reply is in the conversation when you come back. Stop is the only way to cancel it.
- The task page offers every action the task list does.
- Workflows have row actions, enabling or disabling one confirms with a toast, and the editor toolbar wraps on narrow screens.
- The dashboard lists five tasks needing attention, not every one.
- Dismiss all no longer covers the unread badge.
### archie-agent
- The agent image includes Task, so the repository gate no longer downloads it on every run.
## [1.61.3] - 2026-11-08
### archie-ui
- Issue, pull request and repository links on tasks open on the forge the repository's connection points at, instead of GitHub.
- Settings: the Harness page is now part of Agent profiles. The setup terminal and the credential sign-in status sit on the same page as the Kit profiles they target, so a profile with a Kit can be signed in from the page that defines it.
## [1.61.2] - 2026-11-07
### archied
- archied no longer gets killed by the systemd watchdog when a restart or update leaves many tasks to resume. Each resumed task used to cost a full queue poll before the next was picked up, so a dozen of them outlasted the 30-second watchdog; an update that hit this was rolled back.
## [1.61.1] - 2026-11-07
### archie-gateway
- An image or voice attachment that arrives as a link is now checked against what the link serves, the same as an uploaded one. A link whose content is not the declared type, or that cannot be read, is refused.
### archie-ui
- A workflow created on the canvas now saves the agent it runs as, so it runs instead of parking with "declares no identity to run as".
### archie-state-store
- A workflow that no longer validates after an upgrade (for example it names a step type that was removed) is repaired at startup instead of breaking every workflow. A shipped workflow is restored from this release's copy; a workflow you created is removed and logged, and its earlier revision stays in the resource history. Valid workflows you created or edited are kept.
## [1.61.0] - 2026-11-07
### archied
- A `workflow.handoff` now finishes its run and starts a separate, linked run of the next workflow on the same issue, instead of continuing as another attempt. The task page links each run to the one before and after it; attempts count only retries of one run.
- A task no longer fails to prepare its worktree with "some refs were not updated" after a tag or branch moves on the forge.
### archie-ui
- The task page no longer flashes its loading state on every live update while a task runs.
### archie-state-store
- The extension catalogue lists and installs again. Its default signing key has changed; an instance that set its own catalogue signing key in Extension settings keeps using that key.
## [1.60.0] - 2026-11-02
### archied
- Curators can list a repository's open issues and file new ones with the `issue_list` and `issue_create` tools, which reach the forge through the daemon. A curator files only when its definition declares `issue_create`; the shipped self-intake example runs in dry run with `issue_list` for deduplication. Listing every open issue needs the forge extensions from the archipelago release after 1.2.0.
## [1.59.0] - 2026-11-02
### archied
- Forge extensions can open issues: the forge surface gains `CreateIssue` alongside list, comment and close, and the bundled Gitea and GitHub extensions implement it.
## [1.58.1] - 2026-11-01
### archied
- The systemd watchdog now also watches the task intake loop, and its warning names the loop that stalled.
- archied no longer restarts about a minute after it starts. Under systemd, the watchdog never saw a poll pass and killed it on every start since 1.56.0.
## [1.58.0] - 2026-11-01
### archied
- Running `install.sh` over an install whose services are already running now restarts them, so they run the new binaries.
## [1.57.0] - 2026-10-31
### archied
- A release reaches `stable` only after it has run on a canary for a day and passed: `archied release publish` now publishes to `next` alone, `archied release canary start|check` installs a release on a canary and judges it from the canary's dashboard, promoting it or rolling the canary back, and `archied release promote` moves `stable` by hand. Promotion refuses a prerelease and a release older than the one `stable` names. The `archied` and `archie-agent` images are published as `:v<version>`, and `:latest` moves only when a release is promoted.
## [1.56.0] - 2026-10-31
### archied
+1 -1
View File
@@ -105,7 +105,7 @@ When sources disagree, the higher one wins:
- If a fix fails twice, throw the block away and rewrite it simply.
- Comments say why, briefly. No migration history, phase names or issue
narration in code.
- Generated files (`ui/dist/`, protobuf, sqlc) are regenerated and committed
- Generated files (protobuf, sqlc) are regenerated and committed
with the change that caused them, never hand-edited.
## Tests
+24 -1
View File
@@ -58,6 +58,12 @@ ENV PATH="/usr/local/go/bin:/go/bin:${PATH}"
ARG GOLANGCI_LINT_VERSION=2.14.0
ARG GOFUMPT_VERSION=0.11.0
ARG BUF_VERSION=1.72.0
# Pinned to the versions tools/proto.sh installs; buf generate shells out to them.
ARG PROTOC_GEN_GO_VERSION=1.36.11
ARG PROTOC_GEN_GO_GRPC_VERSION=1.6.2
# Repository gates run `task`; fetching it per run parks the task when the
# download fails.
ARG TASK_VERSION=3.54.0
RUN curl -fsSL "https://github.com/golangci/golangci-lint/releases/download/v${GOLANGCI_LINT_VERSION}/golangci-lint-${GOLANGCI_LINT_VERSION}-linux-amd64.tar.gz" \
| tar -xz -C /usr/local/bin --strip-components=1 \
@@ -66,7 +72,12 @@ RUN curl -fsSL "https://github.com/golangci/golangci-lint/releases/download/v${G
"https://github.com/mvdan/gofumpt/releases/download/v${GOFUMPT_VERSION}/gofumpt_v${GOFUMPT_VERSION}_linux_amd64" && \
curl -fsSL -o /usr/local/bin/buf \
"https://github.com/bufbuild/buf/releases/download/v${BUF_VERSION}/buf-Linux-x86_64" && \
chmod +x /usr/local/bin/gofumpt /usr/local/bin/buf
curl -fsSL "https://github.com/go-task/task/releases/download/v${TASK_VERSION}/task_linux_amd64.tar.gz" \
| tar -xz -C /usr/local/bin task && \
chmod +x /usr/local/bin/gofumpt /usr/local/bin/buf && \
GOBIN=/usr/local/bin go install "google.golang.org/protobuf/cmd/protoc-gen-go@v${PROTOC_GEN_GO_VERSION}" && \
GOBIN=/usr/local/bin go install "google.golang.org/grpc/cmd/protoc-gen-go-grpc@v${PROTOC_GEN_GO_GRPC_VERSION}" && \
go clean -cache -modcache
# ── Python via uv ─────────────────────────────────────────────────────
ARG PYTHON_VERSION=3.14
@@ -74,6 +85,18 @@ RUN curl -fsSL https://astral.sh/uv/install.sh | sh
ENV PATH="/root/.local/bin:${PATH}"
RUN uv python install --default "${PYTHON_VERSION}" && rm -rf /root/.cache/uv
# Point each toolchain at its cache volume (internal/storage). Unset, pnpm puts
# its store on the worktree's filesystem, inside the repository the agent commits.
ENV GOMODCACHE=/data/cache/go/mod \
GOCACHE=/data/cache/go/build \
npm_config_cache=/data/cache/node \
npm_config_store_dir=/data/cache/pnpm \
DENO_DIR=/data/cache/deno \
BUN_INSTALL_CACHE_DIR=/data/cache/bun \
PIP_CACHE_DIR=/data/cache/pip \
UV_CACHE_DIR=/data/cache/pip \
CARGO_HOME=/data/cache/cargo
COPY --from=builder /usr/local/bin/archie-agent /usr/local/bin/archie-agent
# The daemon injects NATS_URL and, when configured, NATS_TOKEN.
+9
View File
@@ -1,11 +1,20 @@
# archied — the archie daemon
# Run via docker compose alongside NATS.
FROM node:24-trixie-slim AS dashboard
WORKDIR /src/ui
RUN corepack enable
COPY ui/package.json ui/pnpm-lock.yaml ui/pnpm-workspace.yaml ./
RUN pnpm install --frozen-lockfile
COPY ui/ ./
RUN pnpm run build
FROM golang:1.27-trixie AS builder
WORKDIR /src
COPY go.mod go.sum ./
RUN go mod download
COPY . .
COPY --from=dashboard /src/ui/dist ./ui/dist
ARG GATEWAY_VERSION=dev
ARG RUNTIME_VERSION=dev
RUN CGO_ENABLED=0 go build \
+6 -1
View File
@@ -1,4 +1,9 @@
# Archie
<h1>
<picture>
<source media="(prefers-color-scheme: dark)" srcset="assets/brand/archie-wordmark-dark.svg">
<img alt="Archie" src="assets/brand/archie-wordmark.svg" height="56">
</picture>
</h1>
**Event-driven Agentic Automation**
+227 -110
View File
@@ -1,141 +1,258 @@
# Releasing
One release stream. `CHANGELOG.md` carries every release section, one generated
page per version describes it, and one tag names the release. A release is one
version covering whatever changed; the components' entries are labelled sections
inside it (`### archied`, `### archie-agent`), not separate numbers or separate
pages.
page per version describes it, and one `v*` tag names the release. One version
covers every process in the host bundle (`archied`, `archie-gateway`,
`archie-state-store`, `archie-ui`, `archie-messaging`) and the `archie-agent`
image; per-component detail is a labelled section inside the version
(`### archied`, `### archie-agent`).
The host bundle ships five processes (`archied`, `archie-gateway`,
`archie-state-store`, `archie-ui`, `archie-messaging`), and
one version covers all of them. `archie-agent`, the per-task sandboxed runtime,
ships as a container image and its changes are the `## [version]` release's
`### archie-agent` section.
A release is cut by CI, published to `next`, run on the canary for a day, and
promoted to `stable` only if the canary's signals pass. Nothing is run locally.
`tools/release.sh` decides which commits a release carries from the package
closure of **every shipped binary**, not from commit-message guessing: a change
to a package only the messaging service, state store, playbook runner or UI
links still lands in the changelog. Read its header comment for how it
partitions commits and enforces `main`-only, clean-tree releases.
## Notes are written with the change
## What justifies a version
`task release:preview VERSION=X.Y.Z` shows exactly what would land, before
anything is written. A commit set that justifies no version produces no version:
`release.sh` exits **3** with "nothing to release" rather than inventing one, so
a pipeline can finish green without tagging.
Most sessions touch the gateway side (daemon, gateway, web UI, chat, messaging)
and leave the agent runtime alone. That is no longer a per-component `skip`
decision — one version covers the release — but a runtime code change being
merged to `main` is still not the same as it being in production: the
`archie-agent` image is rebuilt by the release, and a host that runs the agent
must pull the new image (`docker compose pull agent`) to get it.
## What the notes are for
A commit that changes what a reader experiences adds its bullet under
`## [Unreleased]` in `CHANGELOG.md`, in the same commit. The release takes that
section as it stands, so write the bullet as the release note, not as a commit
subject.
**Release notes describe the reader's experience of what shipped.** The test is
the reader, not whether a sentence is negative:
- A capability that **never existed** leaves no expectation to correct, so a
note about it reads as a feature to someone who never had the thing — out.
- **The implementation's journey** — what was rebuilt, what a guard finally
covers, what a browser API refuses to surface — is not the reader's experience
either — out.
- A capability that **shipped but is not yet wired** _is_ the reader's
note about it reads as a feature to someone who never had the thing: out.
- **The implementation's journey** (what was rebuilt, what a guard finally
covers, what a browser API refuses to surface) isn't the reader's experience
either: out.
- A capability that **shipped but isn't yet wired** _is_ the reader's
experience, so it belongs, worded as a caveat on the capability and paired
with the behaviour that compensates for it.
Design constraints and withheld capabilities are not release news.
Do not apply this mechanically: deleting a caveat a reader needs misleads them,
which is the failure this rule exists to prevent.
Design constraints and withheld capabilities are not release news. Deleting a
caveat a reader needs misleads them, which is the failure this rule exists to
prevent.
## Cutting a release
```bash
task release:preview VERSION=1.3.0 # preview what would land
task release:prepare VERSION=1.3.0 # write the section into CHANGELOG.md, uncommitted
# edit CHANGELOG.md -- generated notes are a starting point, not the release
task release VERSION=1.3.0 # commit + annotated tag
git push --atomic origin main v1.3.0 # both refs or neither
```
Dispatch the **release** workflow (`.github/workflows/release.yml`) with
`major`, `minor`, `patch` or an exact version. It runs `task release` on `main`:
Pushing the tag is the release. The deploy workflow builds the images and the
zip, then `archied release publish` signs the release with the
`RELEASE_SIGNING_KEY` Actions secret and pushes it to
`git.catlow.cloud/sam/archie` as `v1.3.0`, `next`, and `stable` unless the
version is a prerelease. `install.sh` and the updater install only what that
key signed.
1. refuses a dirty tree, an existing tag, or an `[Unreleased]` with no entries;
2. turns `[Unreleased]` into `## [x.y.z] - date` under a new empty
`[Unreleased]`, and runs `task news`;
3. commits `chore(release): vx.y.z` and tags `vx.y.z`;
`release:prepare` emits bare commit subjects; they are a starting point. Rewrite
them to say what a reader gets, per "What the notes are for" above.
then pushes `main` and the tag atomically with `DEPLOY_TOKEN`. A push made with
the job token wouldn't start other workflows, so the user token is what lets
the tag start the deploy.
Pushing is a separate, explicit step — never push without confirming first (see
the repo's general "check before doing anything hard to reverse" rule). The
deploy workflow reads tags pointing at `HEAD`; pushing the commit without its
tag gets images stamped `dev`, which is why the push names the tag and is
`--atomic`.
Every workflow that reaches the registry or the canary reads its credentials
from Actions secrets, so a mirror of this repository carries its own set:
### After a release, `main` and the working branch have diverged
| Name | Kind | Used by |
|---|---|---|
| `DEPLOY_TOKEN` | secret | release, deploy, canary, promote — the registry push, the tag push, and the package links |
| `RELEASE_SIGNING_KEY` | secret | deploy — signs the release statement |
| `CANARY_TOKEN` | secret | deploy, canary, promote — the canary's dashboard API |
| `CANARY_URL` | variable | deploy, canary, promote — where that dashboard is |
| `CANARY_WINDOW` | variable | canary — the judged window; empty means the default |
The release commit lands on `main` — `tools/release.sh` refuses to run anywhere
else — while the working branch keeps advancing. So after every release, `main`
is ahead by exactly that commit and the branch is ahead by however far it has
moved: **neither tip is an ancestor of the other**, and `--ff-only` fails in
both directions. That refusal reads as "the tree is not ready" when in fact the
tree is fine.
A mirror missing them fails at its first login or push; `release.yml` names the
missing `DEPLOY_TOKEN` before it checks out, so the run doesn't read as a broken
release.
Merge the release commit into the branch first, so any conflict is resolved on
the branch, where it is reversible and nobody is reading the tip:
```bash
git merge main # on the branch
git merge --ff-only <branch> # then, in whichever worktree holds main
```
Confirm which worktree holds `main` with `git worktree list` before the
`--ff-only`. A detached worktree sitting at the same commit will accept it and
move nothing, which looks like success.
After a release, pull `main` before committing on it again: CI has added the
release commit.
## What a release publishes
Tagging one version produces, from a single `deploy` run:
The tag push runs `deploy.yml`:
- **Container images** — `git.catlow.cloud/sam/archied:latest` and, on a
release tag, `git.catlow.cloud/sam/archie-agent:latest`. The runtime image is
rebuilt by the release, so runtime commits merged to `main` do not reach a
running sandbox until the host pulls the new image. The hand-run
`tools/publish.sh` publishes the same two images to
`git.catlow.cloud/sam` instead, which is the registry the binary's default
`[containers].image` names.
- **`:latest` names the newest release, not the newest commit.** A push to
`main` that is not a release publishes `archied:edge` (mutable, tracking
`main`) and `archied:sha-<commit>` (immutable) instead, so a release's
`:latest` stamping is not overwritten minutes later by the next ordinary
commit. A host that runs releases follows `:latest`; a host that tracks `main`
follows `:edge`.
- **A GitHub Release with a distribution zip** — `dist-zip` builds every process
the reference deployment runs (`archied`, `archie-gateway`,
`archie-state-store`, `archie-ui`, `archie-messaging`) for
linux/amd64, packs them with `deployments/INSTRUCTIONS.md` and `CHANGELOG.md`,
and attaches the zip to the Release. The Release body is that version's
`## [version]` section of `CHANGELOG.md`.
- **Gate.** `task check TEST_FLAGS=-count=1` (uncached, including the
Docker-backed tests `-short` skips) and `govulncheck`, then a check that the
tag has a `[version]` section in `CHANGELOG.md`.
- **Images.** `archied:v<version>` and `archie-agent:v<version>` on a release
tag; `archied:edge` and `archied:sha-<commit>` on any other push to `main`.
`:latest` moves only on promotion, so it names the newest promoted release.
- **The signed release.** `archied release publish` signs a statement
(version, issued_at, zip digest, agent image by digest) with
`RELEASE_SIGNING_KEY` and pushes it with the distribution zip to
`git.catlow.cloud/sam/archie` as `v<version>` and `next`. It never moves
`stable`.
- **The release-notes page** on Gitea, from that version's `CHANGELOG.md`
section, which the statement links to.
- **The canary install**: `archied release canary start` points the canary at
`next` and installs the release through its dashboard.
The zip is also uploaded as an Actions artifact, but that is a backup copy:
artifacts expire after 90 days and need an Actions login to download. The
Release asset is the durable, operator-reachable one.
GitHub-style Actions run the workflow from the tagged commit, so a fix to
`deploy.yml` reaches a release only if it is an ancestor of the tag. Re-cut the
release rather than committing the fix on top of a tagged one.
## Gate
## The canary
CI (`deploy.yml`) runs `task check TEST_FLAGS=-count=1` before building images,
then verifies any release tag at `HEAD` has a matching `[version]` section in
`CHANGELOG.md`. The gate has one definition, in the Taskfile: the release runs
it with the uncached suite, including the Docker-backed tests `-short` skips.
A tag with no changelog entry is a hard failure. No tags at `HEAD` is a
warning, not a failure -- images get stamped `dev`.
The canary is the production host, following `next`. Every quarter hour
`canary.yml` runs `archied release canary check`, which reads the canary
through its dashboard API and judges **the release the canary actually runs**,
not the moving `next` tag:
One consequence worth knowing when a release commit needs amending: GitHub
Actions runs the workflow **from the commit that triggered it**, so a fix to
`deploy.yml` only takes effect for a release if it is an ancestor of the tagged
commit. Delete and re-cut the tag (`git tag -d`, `task release`) rather than
committing the fix on top of an already-tagged release.
| Signal | Source | Fails when |
| --- | --- | --- |
| Install outcome | `GET /api/chat/update` | the canary doesn't run the judged release (the watchdog rolled it back) |
| Readiness | `GET /health/detailed` | the rollup isn't `ok` |
| Alerts | `GET /api/alerts` | an open `action` alert was first raised after the release was installed |
| Error log | `GET /api/logs?level=error` | error lines per window exceed `2 × baseline + 10` |
| Task outcomes | `GET /api/tasks` | the share of finished tasks that parked or died rose more than 10 points |
- **Control.** The canary's own window before the release was installed. With
one production host there's no simultaneous control.
- **Window.** 24 hours counted from the **install** on the canary, not from
the release's issue time: the host records it in `installed.json`
(`committed_at`) and reports it as `installed_at` in `GET /api/chat/update`.
One cycle of schedules and traffic. The first 30 minutes are for the install
and restart. `canary.yml` passes `-window` when the `CANARY_WINDOW` Actions
variable is set; the flag defaults to 24h. A host that doesn't report an
install time degrades to the release statement's issue time.
- **Hard signals** (install, readiness, alerts) roll back at any check after
that. **Relative signals** (errors, tasks) are judged against the baseline
whenever both windows carry enough data, so a breach rolls the release back
even mid-window; a full window with no failure promotes it.
- **Too little data skips a signal** rather than failing it: fewer than 5
finished tasks in the window, or an error log that reaches back less than an
hour into the baseline. A log read that stops short of a window is scaled to
a full window from what it covers.
### Queueing
`deploy.yml` installs each new release on the canary with
`archied release canary start -version V`, which first points the canary back
at `next` (clearing any rollback pin) and then installs `V` — unless the
canary is already judging a release newer than stable that isn't `V`, in which
case `V` is **queued** behind it and the canary keeps running what it judges.
`-force` installs regardless. A `check` that promotes (or finds nothing to
judge) installs the newer `next` in the same run, so a queue drains one
release per promotion.
### Subcommands
```
archied release canary status read-only: channel/pin, installed release and
installed_at, stable/next, window progress, and
the verdict the current signals would give
archied release canary start point the canary at next and install -version,
queued behind a release being judged (-force to
override)
archied release canary check judge the installed release over -window
(default 24h): promote, pick up a newer next,
or roll back; a held canary is reported, and a
held pin that is no longer installable fails
the run red
archied release canary promote promote the installed release now if its
signals pass; refuses with exit 1 otherwise
archied release canary unpin return the canary to next from any pin
```
### Promote
A release that passes the window is promoted: `stable` is retagged to the
`v<version>` manifest. The signature covers the statement, not the tag, so the
retag needs no signing key. The `archied` and `archie-agent` images' `:latest`
move to their `:v<version>` first, and the agent image must be the digest the
statement pins. Promotion refuses a prerelease and a release issued before the
one `stable` names, the same replay rule hosts enforce. The decision and its
reasons are in the `canary` run log.
Early promotion is a dispatch away: the **promote** workflow
(`.github/workflows/promote.yml`) takes a `version` input and runs
`archied release canary promote -version V` on the canary. It judges the
release the canary runs — the window doesn't matter for the decision — and
refuses (red run) on any hard failure or relative breach with enough data.
### Roll back
`stable` stays put, and the run turns red. Before the canary is pinned to
`stable`, `check` verifies `stable` is actually installable — its statement's
zip blob must still be in the release repository and its pinned agent image
must still resolve (`releaseupdate.Installable`). If it isn't, the run fails
loudly and the canary stays on `next` rather than being stranded on a pin.
Otherwise the canary is pinned to the `stable` version through its update
settings and reinstalled through its dashboard.
A release whose migrations differ from `stable`'s can't go back without
restoring the pre-update database snapshot, which loses every write since. The
canary is held on the failed release instead (pinned to it) and the fix goes
forward in the next release. The next release's deploy points the canary back
at `next`.
A pinned canary isn't judged, so a rollback is decided once — but `check`
verifies the pin is still installable every run, so a stranded pin shows red
instead of green. `archied release canary unpin` returns the canary to `next`
by hand.
### Configuration
| Name | Kind | Holds |
| --- | --- | --- |
| `CANARY_URL` | Actions variable | the canary's dashboard URL; unset disables the canary steps |
| `CANARY_TOKEN` | Actions secret | an API token bound to a dedicated `service_account` identity on the canary, carrying only the canary grant policy (see below) — never instance admin |
| `CANARY_WINDOW` | Actions variable | optional `-window` override for `canary check`; unset is 24h |
| `DEPLOY_TOKEN` | Actions secret | registry and repository write, for publishing, promoting and the release push; stays CI-only, promotion runs in CI and never on the host |
| `RELEASE_SIGNING_KEY` | Actions secret | the release signing seed |
#### Setting up `CANARY_TOKEN` once
`CANARY_TOKEN` is a bearer token for a dedicated service-account identity in
the system org whose only grant is the canary policy
(`access.CanaryGrantPolicy`): read the signal endpoints (`GET /api/chat/update`,
`GET /api/alerts`, `GET /api/logs`, `GET /api/tasks`), read and write the
`update-settings` resource, and trigger an update install
(`POST /api/chat/update/install`). It carries no other rights, and instance
admin is never needed. With an instance-admin token (for example the operator
session), run against the canary host:
```bash
# 1. Create the service-account identity in the system org.
curl -X POST "$CANARY_URL/api/identities" -H "Authorization: Bearer $ADMIN" \
-H 'Content-Type: application/json' \
-d '{"kind":"service_account","display_name":"ci-canary"}'
# -> {"id":"<canary-identity-id>", ...}
# 2. Issue its token (shown exactly once).
curl -X POST "$CANARY_URL/api/identities/<canary-identity-id>/tokens" \
-H "Authorization: Bearer $ADMIN" -H 'Content-Type: application/json' \
-d '{"name":"ci-canary","days":90}'
# -> {"id":"<token-hash>","token":"archie_pat_..."} -- store the token value as the CANARY_TOKEN secret
# 3. Install the grant pair, scoped to that identity. The policies' org is
# pinned to the caller's org (org-sys for the instance admin), so the
# bodies need no org field. The permit alone is not enough: service
# accounts created through the API are assigned the developer role, so a
# matching forbid (installed second) negates everything outside the
# permit's surface for that identity.
curl -X PUT "$CANARY_URL/api/access/policies" -H "Authorization: Bearer $ADMIN" \
-H 'Content-Type: application/json' \
-d '{"id":"org-canary-grant","level":"org","text":"permit(principal, action, resource) when {\n resource.org == principal.org &&\n principal == Archie::Identity::\"<canary-identity-id>\" &&\n (\n (action == Archie::Action::\"read\" && [\"dashboard\", \"task\"].contains(resource.kind)) ||\n (action == Archie::Action::\"read\" && resource == Archie::Object::\"update-settings\") ||\n (action == Archie::Action::\"update\" && resource == Archie::Object::\"update\") ||\n (action == Archie::Action::\"manage_identities\" && resource == Archie::Object::\"update-settings\")\n )\n};"}'
```
The second policy forbids the canary identity from everything the permit does
not name, so its developer role cannot widen the grant:
```bash
curl -X PUT "$CANARY_URL/api/access/policies" -H "Authorization: Bearer $ADMIN" \
-H 'Content-Type: application/json' \
-d '{"id":"org-canary-grant-forbid","level":"org","text":"forbid(principal, action, resource) when {\\n resource.org == principal.org &&\\n principal == Archie::Identity::\\\"<canary-identity-id>\\\" &&\\n !(\\n (action == Archie::Action::\\\"read\\\" && [\\\"dashboard\\\", \\\"task\\\"].contains(resource.kind)) ||\\n (action == Archie::Action::\\\"read\\\" && resource == Archie::Object::\\\"update-settings\\\") ||\\n (action == Archie::Action::\\\"update\\\" && resource == Archie::Object::\\\"update\\\") ||\\n (action == Archie::Action::\\\"manage_identities\\\" && resource == Archie::Object::\\\"update-settings\\\")\\n )\\n};"}'
```
The policy texts are exactly `access.CanaryGrantPolicy` and
`access.CanaryGrantForbidPolicy` from `internal/domain/access/canary.go` with
the identity id filled in. The canary needs no other rights: `GET
/health/detailed` is unauthenticated, and every other call it makes is covered
by the grant pair.
The runner must reach `CANARY_URL`. Without a canary a release stays on `next`
until promoted by hand, under the same refusals:
```bash
archied release promote -version 1.57.0 \
-latest git.catlow.cloud/sam/archied,git.catlow.cloud/sam/archie-agent
```
+41 -30
View File
@@ -100,18 +100,12 @@ tasks:
- pnpm install --frozen-lockfile
ui:
desc: Build the dashboard into ui/dist (committed; the Go build embeds it)
desc: Build the dashboard into ui/dist, which the Go build embeds
dir: ui
deps: [ui:deps]
cmds:
- pnpm run build
ui:check:
desc: Rebuild the dashboard into a temporary directory and reject a stale ui/dist
deps: [ui:deps]
cmds:
- bash tools/uidist.sh check
test:ui:
desc: Test and type-check the dashboard
dir: ui
@@ -227,8 +221,16 @@ tasks:
cmds:
- node e2e/run.cjs {{.CLI_ARGS}}
canary:rehearse:
# Local rehearsal only: spins up its own registry, database and host, and
# is deliberately absent from check and CI.
desc: Rehearse the release-canary loop on a throwaway local host (needs docker; never part of the gate)
cmds:
- sh tools/canary-rehearse.sh
build:
desc: Build archie services and agent binaries
deps: [ui]
vars:
GATEWAY_VERSION: '{{.GATEWAY_VERSION | default .VERSION}}'
RUNTIME_VERSION: '{{.RUNTIME_VERSION | default .VERSION}}'
@@ -278,13 +280,14 @@ tasks:
desc: Run the full quality gate
# Finish mutations before starting parallel checks.
cmds:
# Node packages land under ui/, which `go test ./...` walks: installing
# them while the parallel checks scan the tree makes a lockfile update
# delete Go sources mid-walk. Install first, then fan out. Every Go step
# embeds ui/dist, so the dashboard is built before any of them.
- task: ui
- task: fmt
- task: proto:check
- task: db:check
# Node packages land under ui/, which `go test ./...` walks: installing
# them while the parallel checks scan the tree makes a lockfile update
# delete Go sources mid-walk. Install first, then fan out.
- task: ui:deps
- task: check:readonly
check:readonly:
@@ -297,25 +300,33 @@ tasks:
- task: build
- task: test
- task: test:ui
- task: ui:check
release:preview:
desc: "Show the release notes that would be generated (VERSION=1.2.0)"
cmds:
- tools/release.sh --version {{.VERSION}} --dry-run
requires:
vars: [VERSION]
release:prepare:
desc: Prepare changelog notes for editing (VERSION=1.2.0)
cmds:
- tools/release.sh --version {{.VERSION}} --prepare
requires:
vars: [VERSION]
release:
desc: Commit and tag the prepared release (VERSION=1.2.0)
cmds:
- tools/release.sh --version {{.VERSION}} --tag
desc: "Turn [Unreleased] into a release, then commit and tag it (RELEASE=major|minor|patch|1.2.3)"
requires:
vars: [VERSION]
vars: [RELEASE]
cmds:
- |
set -euo pipefail
die() { echo "release: $*" >&2; exit 1; }
[ "$(git rev-parse --abbrev-ref HEAD)" = main ] || die "releases are cut from main"
[ -z "$(git status --porcelain)" ] || die "the working tree is dirty"
last="$(git tag --list 'v*' --sort=-v:refname | grep -E '^v[0-9]+\.[0-9]+\.[0-9]+$' | head -1 || true)"
IFS=. read -r major minor patch <<<"${last#v}"
case "{{.RELEASE}}" in
major) version="$((major + 1)).0.0" ;;
minor) version="$major.$((minor + 1)).0" ;;
patch) version="$major.$minor.$((patch + 1))" ;;
*) version="$(echo "{{.RELEASE}}" | sed 's/^v//')" ;;
esac
echo "$version" | grep -Eq '^[0-9]+\.[0-9]+\.[0-9]+(-[0-9A-Za-z.]+)?$' || die "$version is not a version"
! git rev-parse -q --verify "refs/tags/v$version" >/dev/null || die "v$version already exists"
awk '/^## \[Unreleased\]/ { u = 1; next } u && /^## \[/ { exit } u && /^- / { found = 1 } END { exit !found }' CHANGELOG.md ||
die "[Unreleased] in CHANGELOG.md has no entries"
awk -v hdr="## [$version] - $(date -u +%F)" '{ print } /^## \[Unreleased\]/ { print ""; print hdr }' CHANGELOG.md >CHANGELOG.md.tmp
mv CHANGELOG.md.tmp CHANGELOG.md
go -C tools run -mod=readonly ./newsgen --repo-root ..
git add CHANGELOG.md docs/news
git commit -q -m "chore(release): v$version"
git tag -a "v$version" -m "v$version"
echo "tagged v$version"
+9
View File
@@ -156,6 +156,15 @@ _needs a repository._
| `push` | bool | Push the branch after committing. |
| `reference` | `Fixes` \| `Implements` \| `Refs` | How the commit links to the task issue. |
Hooks never run. The commit is created by go-git, which ignores `.git/hooks`
and `core.hooksPath`, and the agent never runs git, so `pre-commit`,
`commit-msg` and `prepare-commit-msg` in the checkout are inert files. A
repository whose rules live only in a hook — a formatter, a secret scanner,
commitlint, a DCO trailer — gets a commit that does not satisfy them: the run
reports success and the pull request fails the check afterwards. Put the same
commands in `command.run` or the repository gate, which both run in the task
container before this step.
### `repo.open-pr`
_needs a repository._
+1
View File
@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 512 512"><rect width="512" height="512" rx="112" fill="#0e0f10"/><g fill="#51a580" transform="translate(96 96) scale(13.333) translate(-0 -0)"><path d="M2 21h4l8-18h-4z"/><path d="M14.9 5.03 22 21h-4l-5.1-11.47z"/><path d="M10.47 15h3.06l1.11 2.5H9.36z"/></g></svg>

After

Width:  |  Height:  |  Size: 319 B

+1
View File
@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24" fill="#51a580"><path d="M2 21h4l8-18h-4z"/><path d="M14.9 5.03 22 21h-4l-5.1-11.47z"/><path d="M10.47 15h3.06l1.11 2.5H9.36z"/></svg>

After

Width:  |  Height:  |  Size: 194 B

+1
View File
@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 1200 630"><rect width="1200" height="630" fill="#0e0f10"/><svg x="320" y="209.6153846153846" width="560" height="150.76923076923077" viewBox="-4 21.4 312 84"><g fill="#51a580" transform="translate(-7.7555555555555555 18.56666666666667) scale(3.8777777777777778)"><path d="M2 21h4l8-18h-4z"/><path d="M14.9 5.03 22 21h-4l-5.1-11.47z"/><path d="M10.47 15h3.06l1.11 2.5H9.36z"/></g><path fill="#e8e6e1" d="M99.76 68L99.76 100L86.96 100L86.96 47.80L99.76 47.80L99.76 58.60L100.26 58.60Q100.96 55.80 102.61 53.35Q104.26 50.90 107.11 49.35Q109.96 47.80 114.06 47.80L116.86 47.80L116.86 59.90L112.86 59.90Q108.56 59.90 105.61 60.75Q102.66 61.60 101.21 63.35Q99.76 65.10 99.76 68M145.86 101.20Q134.26 101.20 128.01 93.80Q121.76 86.40 121.76 73.80Q121.76 61.30 128.01 53.95Q134.26 46.60 145.86 46.60Q153.76 46.60 158.91 50.10Q164.06 53.60 166.36 59.80L155.86 64.50Q154.96 61.20 152.46 59.05Q149.96 56.90 145.86 56.90Q140.56 56.90 137.86 60.25Q135.16 63.60 135.16 69.20L135.16 78.70Q135.16 84.10 137.86 87.50Q140.56 90.90 145.86 90.90Q150.36 90.90 152.91 88.55Q155.46 86.20 156.86 82.70L166.66 87.40Q164.16 94.30 158.81 97.75Q153.46 101.20 145.86 101.20M188.36 100L175.56 100L175.56 26L188.36 26L188.36 56.50L188.86 56.50Q190.46 52.30 193.91 49.45Q197.36 46.60 203.46 46.60Q211.46 46.60 215.81 51.95Q220.16 57.30 220.16 67L220.16 100L207.36 100L207.36 68.30Q207.36 62.80 205.36 59.95Q203.36 57.10 198.76 57.10Q196.16 57.10 193.76 58.05Q191.36 59 189.86 60.85Q188.36 62.70 188.36 65.50M239.76 40.20Q235.86 40.20 234.06 38.35Q232.26 36.50 232.26 33.80L232.26 31.80Q232.26 29 234.06 27.20Q235.86 25.40 239.76 25.40Q243.66 25.40 245.46 27.20Q247.26 29 247.26 31.80L247.26 33.80Q247.26 36.50 245.46 38.35Q243.66 40.20 239.76 40.20M246.16 100L233.36 100L233.36 47.80L246.16 47.80M280.96 101.20Q273.26 101.20 267.76 97.85Q262.26 94.50 259.31 88.35Q256.36 82.20 256.36 73.80Q256.36 65.60 259.26 59.45Q262.16 53.30 267.56 49.95Q272.96 46.60 280.56 46.60Q288.76 46.60 294.01 50.20Q299.26 53.80 301.81 59.75Q304.36 65.70 304.36 72.90L304.36 77.10L269.66 77.10L269.66 78.40Q269.66 84 272.86 87.50Q276.06 91 282.36 91Q287.06 91 290.16 88.95Q293.26 86.90 295.66 83.90L302.56 91.60Q299.36 95.90 293.81 98.55Q288.26 101.20 280.96 101.20M280.76 56.20Q277.36 56.20 274.86 57.75Q272.36 59.30 271.01 62.05Q269.66 64.80 269.66 68.40L269.66 69.20L291.06 69.20L291.06 68.30Q291.06 64.60 289.86 61.95Q288.66 59.30 286.36 57.75Q284.06 56.20 280.76 56.20"/></svg><g fill="#a8a59f" transform="translate(224.91199999999998 460.38461538461536)"><path transform="translate(0.00 0)" d="M18.70-23.73L18.70-21.22L11.15-21.22L11.15 0L8.30 0L8.30-21.22L0.75-21.22L0.75-23.73"/><path transform="translate(19.45 0)" d="M5.61 0L2.89 0L2.89-25.16L5.61-25.16L5.61-14.69L5.75-14.69Q6.39-16.18 7.57-17.07Q8.74-17.95 10.71-17.95Q13.43-17.95 15.01-16.20Q16.59-14.45 16.59-11.25L16.59 0L13.87 0L13.87-10.78Q13.87-13.12 12.87-14.31Q11.87-15.50 9.89-15.50Q8.81-15.50 7.82-15.15Q6.83-14.79 6.22-14.04Q5.61-13.29 5.61-12.17"/><path transform="translate(38.76 0)" d="M9.49 0.41Q7.11 0.41 5.34-0.73Q3.57-1.87 2.58-3.93Q1.60-5.98 1.60-8.77Q1.60-11.56 2.58-13.62Q3.57-15.67 5.34-16.81Q7.11-17.95 9.49-17.95Q11.83-17.95 13.53-16.85Q15.23-15.74 16.15-13.80Q17.07-11.87 17.07-9.38L17.07-8.09L4.45-8.09L4.45-7.28Q4.45-5 5.83-3.49Q7.21-1.97 9.66-1.97Q11.32-1.97 12.56-2.75Q13.80-3.54 14.48-5L16.42-3.60Q15.57-1.84 13.77-0.71Q11.97 0.41 9.49 0.41M9.49-15.67Q8.02-15.67 6.89-14.99Q5.75-14.31 5.10-13.11Q4.45-11.90 4.45-10.37L4.45-10.13L14.14-10.13L14.14-10.51Q14.14-12.07 13.57-13.23Q12.99-14.38 11.93-15.03Q10.88-15.67 9.49-15.67"/><path transform="translate(57.43 0)" d=""/><path transform="translate(65.45 0)" d="M17.17-2.38L17.17 0L15.64 0Q14.55 0 13.87-0.46Q13.19-0.92 12.89-1.73Q12.68-2.24 12.61-2.86L12.44-2.86Q11.90-1.26 10.56-0.42Q9.21 0.41 7.38 0.41Q4.59 0.41 3.04-1.02Q1.50-2.45 1.50-4.90Q1.50-6.56 2.31-7.70Q3.13-8.84 4.78-9.44Q6.43-10.03 8.98-10.03L12.44-10.03L12.44-11.76Q12.44-13.63 11.42-14.62Q10.40-15.61 8.30-15.61Q6.73-15.61 5.64-14.89Q4.56-14.18 3.84-12.99L2.21-14.52Q2.92-15.91 4.49-16.93Q6.05-17.95 8.43-17.95Q11.59-17.95 13.38-16.39Q15.16-14.82 15.16-12.04L15.16-2.38L17.17-2.38M12.44-5.10L12.44-7.99L8.84-7.99Q6.53-7.99 5.44-7.31Q4.35-6.63 4.35-5.34L4.35-4.62Q4.35-3.33 5.30-2.62Q6.26-1.90 7.82-1.90Q9.18-1.90 10.22-2.33Q11.25-2.75 11.85-3.49Q12.44-4.22 12.44-5.10"/><path transform="translate(83.61 0)" d="M17.68 1.94Q17.68 3.74 16.73 4.91Q15.78 6.09 13.89 6.65Q12 7.21 9.18 7.21Q6.46 7.21 4.74 6.70Q3.03 6.19 2.24 5.22Q1.46 4.25 1.46 2.89Q1.46 1.46 2.21 0.65Q2.96-0.17 4.25-0.51L4.25-0.88Q3.50-1.26 3.09-1.85Q2.69-2.45 2.69-3.33Q2.69-4.66 3.54-5.36Q4.39-6.05 5.71-6.39L5.71-6.53Q4.15-7.28 3.28-8.67Q2.41-10.06 2.41-11.90Q2.41-13.70 3.23-15.06Q4.05-16.42 5.54-17.19Q7.04-17.95 9.01-17.95Q9.96-17.95 10.79-17.78Q11.63-17.61 12.34-17.27L12.34-17.58Q12.34-18.60 12.82-19.26Q13.29-19.92 14.38-19.92L17-19.92L17-17.54L13.67-17.54L13.67-16.42Q14.62-15.61 15.15-14.45Q15.67-13.29 15.67-11.90Q15.67-Line truncated

After

Width:  |  Height:  |  Size: 20 KiB

+1
View File
@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="-4 21.40 312 84" role="img" aria-label="Archie"><title>Archie</title><g fill="#51a580" transform="translate(-7.7555555555555555 18.56666666666667) scale(3.8777777777777778)"><path d="M2 21h4l8-18h-4z"/><path d="M14.9 5.03 22 21h-4l-5.1-11.47z"/><path d="M10.47 15h3.06l1.11 2.5H9.36z"/></g><path fill="#e8e6e1" d="M99.76 68L99.76 100L86.96 100L86.96 47.80L99.76 47.80L99.76 58.60L100.26 58.60Q100.96 55.80 102.61 53.35Q104.26 50.90 107.11 49.35Q109.96 47.80 114.06 47.80L116.86 47.80L116.86 59.90L112.86 59.90Q108.56 59.90 105.61 60.75Q102.66 61.60 101.21 63.35Q99.76 65.10 99.76 68M145.86 101.20Q134.26 101.20 128.01 93.80Q121.76 86.40 121.76 73.80Q121.76 61.30 128.01 53.95Q134.26 46.60 145.86 46.60Q153.76 46.60 158.91 50.10Q164.06 53.60 166.36 59.80L155.86 64.50Q154.96 61.20 152.46 59.05Q149.96 56.90 145.86 56.90Q140.56 56.90 137.86 60.25Q135.16 63.60 135.16 69.20L135.16 78.70Q135.16 84.10 137.86 87.50Q140.56 90.90 145.86 90.90Q150.36 90.90 152.91 88.55Q155.46 86.20 156.86 82.70L166.66 87.40Q164.16 94.30 158.81 97.75Q153.46 101.20 145.86 101.20M188.36 100L175.56 100L175.56 26L188.36 26L188.36 56.50L188.86 56.50Q190.46 52.30 193.91 49.45Q197.36 46.60 203.46 46.60Q211.46 46.60 215.81 51.95Q220.16 57.30 220.16 67L220.16 100L207.36 100L207.36 68.30Q207.36 62.80 205.36 59.95Q203.36 57.10 198.76 57.10Q196.16 57.10 193.76 58.05Q191.36 59 189.86 60.85Q188.36 62.70 188.36 65.50M239.76 40.20Q235.86 40.20 234.06 38.35Q232.26 36.50 232.26 33.80L232.26 31.80Q232.26 29 234.06 27.20Q235.86 25.40 239.76 25.40Q243.66 25.40 245.46 27.20Q247.26 29 247.26 31.80L247.26 33.80Q247.26 36.50 245.46 38.35Q243.66 40.20 239.76 40.20M246.16 100L233.36 100L233.36 47.80L246.16 47.80M280.96 101.20Q273.26 101.20 267.76 97.85Q262.26 94.50 259.31 88.35Q256.36 82.20 256.36 73.80Q256.36 65.60 259.26 59.45Q262.16 53.30 267.56 49.95Q272.96 46.60 280.56 46.60Q288.76 46.60 294.01 50.20Q299.26 53.80 301.81 59.75Q304.36 65.70 304.36 72.90L304.36 77.10L269.66 77.10L269.66 78.40Q269.66 84 272.86 87.50Q276.06 91 282.36 91Q287.06 91 290.16 88.95Q293.26 86.90 295.66 83.90L302.56 91.60Q299.36 95.90 293.81 98.55Q288.26 101.20 280.96 101.20M280.76 56.20Q277.36 56.20 274.86 57.75Q272.36 59.30 271.01 62.05Q269.66 64.80 269.66 68.40L269.66 69.20L291.06 69.20L291.06 68.30Q291.06 64.60 289.86 61.95Q288.66 59.30 286.36 57.75Q284.06 56.20 280.76 56.20"/></svg>

After

Width:  |  Height:  |  Size: 2.3 KiB

+1
View File
@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="-4 21.40 312 84" role="img" aria-label="Archie"><title>Archie</title><g fill="currentColor" transform="translate(-7.7555555555555555 18.56666666666667) scale(3.8777777777777778)"><path d="M2 21h4l8-18h-4z"/><path d="M14.9 5.03 22 21h-4l-5.1-11.47z"/><path d="M10.47 15h3.06l1.11 2.5H9.36z"/></g><path fill="currentColor" d="M99.76 68L99.76 100L86.96 100L86.96 47.80L99.76 47.80L99.76 58.60L100.26 58.60Q100.96 55.80 102.61 53.35Q104.26 50.90 107.11 49.35Q109.96 47.80 114.06 47.80L116.86 47.80L116.86 59.90L112.86 59.90Q108.56 59.90 105.61 60.75Q102.66 61.60 101.21 63.35Q99.76 65.10 99.76 68M145.86 101.20Q134.26 101.20 128.01 93.80Q121.76 86.40 121.76 73.80Q121.76 61.30 128.01 53.95Q134.26 46.60 145.86 46.60Q153.76 46.60 158.91 50.10Q164.06 53.60 166.36 59.80L155.86 64.50Q154.96 61.20 152.46 59.05Q149.96 56.90 145.86 56.90Q140.56 56.90 137.86 60.25Q135.16 63.60 135.16 69.20L135.16 78.70Q135.16 84.10 137.86 87.50Q140.56 90.90 145.86 90.90Q150.36 90.90 152.91 88.55Q155.46 86.20 156.86 82.70L166.66 87.40Q164.16 94.30 158.81 97.75Q153.46 101.20 145.86 101.20M188.36 100L175.56 100L175.56 26L188.36 26L188.36 56.50L188.86 56.50Q190.46 52.30 193.91 49.45Q197.36 46.60 203.46 46.60Q211.46 46.60 215.81 51.95Q220.16 57.30 220.16 67L220.16 100L207.36 100L207.36 68.30Q207.36 62.80 205.36 59.95Q203.36 57.10 198.76 57.10Q196.16 57.10 193.76 58.05Q191.36 59 189.86 60.85Q188.36 62.70 188.36 65.50M239.76 40.20Q235.86 40.20 234.06 38.35Q232.26 36.50 232.26 33.80L232.26 31.80Q232.26 29 234.06 27.20Q235.86 25.40 239.76 25.40Q243.66 25.40 245.46 27.20Q247.26 29 247.26 31.80L247.26 33.80Q247.26 36.50 245.46 38.35Q243.66 40.20 239.76 40.20M246.16 100L233.36 100L233.36 47.80L246.16 47.80M280.96 101.20Q273.26 101.20 267.76 97.85Q262.26 94.50 259.31 88.35Q256.36 82.20 256.36 73.80Q256.36 65.60 259.26 59.45Q262.16 53.30 267.56 49.95Q272.96 46.60 280.56 46.60Q288.76 46.60 294.01 50.20Q299.26 53.80 301.81 59.75Q304.36 65.70 304.36 72.90L304.36 77.10L269.66 77.10L269.66 78.40Q269.66 84 272.86 87.50Q276.06 91 282.36 91Q287.06 91 290.16 88.95Q293.26 86.90 295.66 83.90L302.56 91.60Q299.36 95.90 293.81 98.55Q288.26 101.20 280.96 101.20M280.76 56.20Q277.36 56.20 274.86 57.75Q272.36 59.30 271.01 62.05Q269.66 64.80 269.66 68.40L269.66 69.20L291.06 69.20L291.06 68.30Q291.06 64.60 289.86 61.95Q288.66 59.30 286.36 57.75Q284.06 56.20 280.76 56.20"/></svg>

After

Width:  |  Height:  |  Size: 2.3 KiB

+1
View File
@@ -0,0 +1 @@
<svg xmlns="http://www.w3.org/2000/svg" viewBox="-4 21.40 312 84" role="img" aria-label="Archie"><title>Archie</title><g fill="#51a580" transform="translate(-7.7555555555555555 18.56666666666667) scale(3.8777777777777778)"><path d="M2 21h4l8-18h-4z"/><path d="M14.9 5.03 22 21h-4l-5.1-11.47z"/><path d="M10.47 15h3.06l1.11 2.5H9.36z"/></g><path fill="#1f1f1d" d="M99.76 68L99.76 100L86.96 100L86.96 47.80L99.76 47.80L99.76 58.60L100.26 58.60Q100.96 55.80 102.61 53.35Q104.26 50.90 107.11 49.35Q109.96 47.80 114.06 47.80L116.86 47.80L116.86 59.90L112.86 59.90Q108.56 59.90 105.61 60.75Q102.66 61.60 101.21 63.35Q99.76 65.10 99.76 68M145.86 101.20Q134.26 101.20 128.01 93.80Q121.76 86.40 121.76 73.80Q121.76 61.30 128.01 53.95Q134.26 46.60 145.86 46.60Q153.76 46.60 158.91 50.10Q164.06 53.60 166.36 59.80L155.86 64.50Q154.96 61.20 152.46 59.05Q149.96 56.90 145.86 56.90Q140.56 56.90 137.86 60.25Q135.16 63.60 135.16 69.20L135.16 78.70Q135.16 84.10 137.86 87.50Q140.56 90.90 145.86 90.90Q150.36 90.90 152.91 88.55Q155.46 86.20 156.86 82.70L166.66 87.40Q164.16 94.30 158.81 97.75Q153.46 101.20 145.86 101.20M188.36 100L175.56 100L175.56 26L188.36 26L188.36 56.50L188.86 56.50Q190.46 52.30 193.91 49.45Q197.36 46.60 203.46 46.60Q211.46 46.60 215.81 51.95Q220.16 57.30 220.16 67L220.16 100L207.36 100L207.36 68.30Q207.36 62.80 205.36 59.95Q203.36 57.10 198.76 57.10Q196.16 57.10 193.76 58.05Q191.36 59 189.86 60.85Q188.36 62.70 188.36 65.50M239.76 40.20Q235.86 40.20 234.06 38.35Q232.26 36.50 232.26 33.80L232.26 31.80Q232.26 29 234.06 27.20Q235.86 25.40 239.76 25.40Q243.66 25.40 245.46 27.20Q247.26 29 247.26 31.80L247.26 33.80Q247.26 36.50 245.46 38.35Q243.66 40.20 239.76 40.20M246.16 100L233.36 100L233.36 47.80L246.16 47.80M280.96 101.20Q273.26 101.20 267.76 97.85Q262.26 94.50 259.31 88.35Q256.36 82.20 256.36 73.80Q256.36 65.60 259.26 59.45Q262.16 53.30 267.56 49.95Q272.96 46.60 280.56 46.60Q288.76 46.60 294.01 50.20Q299.26 53.80 301.81 59.75Q304.36 65.70 304.36 72.90L304.36 77.10L269.66 77.10L269.66 78.40Q269.66 84 272.86 87.50Q276.06 91 282.36 91Q287.06 91 290.16 88.95Q293.26 86.90 295.66 83.90L302.56 91.60Q299.36 95.90 293.81 98.55Q288.26 101.20 280.96 101.20M280.76 56.20Q277.36 56.20 274.86 57.75Q272.36 59.30 271.01 62.05Q269.66 64.80 269.66 68.40L269.66 69.20L291.06 69.20L291.06 68.30Q291.06 64.60 289.86 61.95Q288.66 59.30 286.36 57.75Q284.06 56.20 280.76 56.20"/></svg>

After

Width:  |  Height:  |  Size: 2.3 KiB

-9
View File
@@ -1,9 +0,0 @@
package configtemplate
import _ "embed"
// Changelog is the verbatim contents of CHANGELOG.md, so a binary carries the
// release notes for the version it was built as.
//
//go:embed CHANGELOG.md
var Changelog string
-39
View File
@@ -1,39 +0,0 @@
// The Messaging Service reaches the State Store and the workflow engine only
// through their contracts. Go imports are atomic, so one reference relinks a
// runtime, and the boundary holds only while something re-measures it.
package main
import (
"context"
"os/exec"
"strings"
"testing"
"time"
)
func TestMessagingDoesNotLinkStoreOrWorkflowRuntime(t *testing.T) {
ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
defer cancel()
out, err := exec.CommandContext(ctx, "go", "list", "-deps", ".").Output()
if err != nil {
t.Fatalf("go list -deps .: %v", err)
}
linked := map[string]bool{}
for line := range strings.SplitSeq(strings.TrimSpace(string(out)), "\n") {
linked[line] = true
}
for _, pkg := range []string{
"github.com/jackc/pgx/v5/pgxpool",
"github.com/samcharles93/archie-core/internal/infrastructure/postgres",
"github.com/samcharles93/archie-core/internal/infrastructure/controlplanestore",
"github.com/samcharles93/archie-core/internal/domain/workflow",
"github.com/samcharles93/archie-core/internal/agentexec",
} {
t.Run(pkg, func(t *testing.T) {
if linked[pkg] {
t.Errorf("cmd/archie-messaging links %s: services reach each other only through contracts", pkg)
}
})
}
}
-41
View File
@@ -1,41 +0,0 @@
// This file enforces the dashboard's process boundary
// (docs/prds/external-agent-harness.md, "Session contract", Transport): the
// dashboard must not link the container or daemon internals, because only the
// daemon owns containers. Go imports are atomic, so a single reference
// relinks a runtime, and the boundary holds only while something re-measures
// it. archie-core-h3s0 names this check; it was purged with the test suite and
// is restored here.
package main
import (
"context"
"os/exec"
"strings"
"testing"
"time"
)
func TestDashboardDoesNotLinkContainerRuntime(t *testing.T) {
ctx, cancel := context.WithTimeout(context.Background(), 30*time.Second)
defer cancel()
out, err := exec.CommandContext(ctx, "go", "list", "-deps", ".").Output()
if err != nil {
t.Fatalf("go list -deps .: %v", err)
}
linked := map[string]bool{}
for line := range strings.SplitSeq(strings.TrimSpace(string(out)), "\n") {
linked[line] = true
}
for _, pkg := range []string{
"github.com/samcharles93/archie-core/internal/container",
"github.com/samcharles93/archie-core/internal/app/archied",
"github.com/samcharles93/archie-core/internal/agentexec",
} {
t.Run(pkg, func(t *testing.T) {
if linked[pkg] {
t.Errorf("cmd/archie-ui links %s: only the daemon owns containers", pkg)
}
})
}
}
+1 -4
View File
@@ -7,12 +7,11 @@ import (
"strings"
"github.com/samcharles93/archie-core/internal/app/archied"
"github.com/samcharles93/archie-core/internal/app/archieplaybooks"
"github.com/samcharles93/archie-core/internal/app/prbench"
)
const commandUsage = "usage: archied [flags] # run the daemon; archied -h lists the flags\n" +
"subcommands: setup, update, release, status, prbench, playbooks"
"subcommands: setup, update, release, status, prbench"
func main() {
os.Exit(run(os.Args[1:]))
@@ -35,8 +34,6 @@ func run(args []string) int {
return archied.RunStatus(args[1:], os.Stdout, os.Stderr)
case "prbench":
return prbench.Main(args[1:], os.Stdout, os.Stderr)
case "playbooks":
return archieplaybooks.Run(args[1:], os.Stderr)
}
// A word that is not a subcommand is refused rather than ignored: a
// stale `archied update-topology` would otherwise start a second
+17 -3
View File
@@ -19,9 +19,6 @@ bot_user = "vectis-labs-archie"
type = "github"
host = "https://github.com"
token = { engine = "env", key = "ARCHIE_GITHUB_TOKEN" }
# intake = "poll" # "poll", "webhook" or "both"
# webhook_secret = { engine = "env", key = "ARCHIE_WEBHOOK_SECRET" }
# webhook_addr = "0.0.0.0:8645"
[dispatch]
trigger = "assignee" # "assignee", "label" or "either"
@@ -94,3 +91,20 @@ target = "127.0.0.1:9090"
# releases_key = "base64 public key"
# catalogue = "registry.example/owner/archipelago/catalogue"
# catalogue_key = "base64 public key"
# Long-running agent loops that maintain memory, skills and — in dry run —
# file follow-up issues from recent runs. Definitions are data: the server
# validates them and the gateway applies them live.
# [[curators]]
# name = "self-intake"
# interval = "1h"
# tools = ["run_list", "run_events", "issue_list"]
# instructions = """
# You are archie's self-intake curator, in dry run. Each pass: list recent
# task runs with run_list, inspect anything parked or failed with run_events,
# check issue_list for each repo so nothing already open is repeated, then
# report candidate follow-up issues, each tied to the run that produced it.
# Do not create issues.
# """
# To let it file: add "issue_create" to tools and tell it to file each
# candidate (citing the run) instead of only reporting it.
+1 -12
View File
@@ -1,8 +1,6 @@
# Running this distribution
This archive contains five linux/amd64 binaries:
Each service owns its data and reaches the others only through their gRPC
This archive holds the linux/amd64 binary for each service. Each service owns its data and reaches the others only through their gRPC
contracts (or NATS, for task actions):
| Service | Owns | Reaches |
@@ -13,9 +11,6 @@ contracts (or NATS, for task actions):
| `archie-messaging` | the Telegram, email and webhook channel connections | Gateway; State Store for channel settings |
| `archie-ui` | the dashboard and the webhook capture receiver | Gateway; State Store |
`archied playbooks lint` checks playbook binding YAML before it reaches the
daemon, and `archied playbooks serve` is its language server for editors.
Without `archie-messaging` the channels are simply absent, so it needs a unit
of its own (`deployments/systemd-user-service.md`).
@@ -67,12 +62,6 @@ that reference is on a registry that needs a login -- see
systemd user-unit runbook:
<https://offloaded.dev>.
## Verifying an install
`archied playbooks lint -dir <playbooks-dir>` validates playbook binding YAML
against the same schema `archied` loads at startup — run it against your
playbooks directory before pointing `archied` at it.
## Version
This archive's binaries are built from the `archied` release tag in its
+11
View File
@@ -45,3 +45,14 @@ listen = "127.0.0.1:8585"
[services.daemon]
target = "127.0.0.1:8587"
listen = "127.0.0.1:8587"
# Dry-run self-intake curator (#1770): surveys recent runs and reports
# candidate follow-up issues as pass summaries; declares no issue-creating
# tool, so it cannot file. Needs a chat model configured to run at all.
[[curators]]
name = "self-intake"
interval = "1h"
tools = ["run_list", "run_events", "issue_list"]
instructions = """
You are archie's self-intake curator, in dry run. Each pass: list recent task runs with run_list, inspect anything parked or failed with run_events, check issue_list for each repo so nothing already open is repeated, then report candidate follow-up issues — concrete, each tied to the run that produced it. Do not create issues; this pass reports only (no issue-creating tool is declared, so it cannot). End your reply with the report.
"""
+11 -34
View File
@@ -169,47 +169,24 @@ fall back to a host model loop.
## 6. Pinning the archie-agent Image
`archie-agent:latest` is a moving target: every release re-publishes it, so it
can change under a running deployment with no warning and no way to reproduce a
prior build. Two paths publish it, to different references:
The release pipeline publishes
`git.catlow.cloud/sam/archie-agent` as `:v<version>` and `:sha-<commit>` when
the commit carries a release tag; an ordinary push to `main` publishes nothing
for the agent image, and `:latest` moves only when a release is promoted. A
distribution zip pins the image its own release
published, by digest, in `release.json`, and `archied update install` pulls
exactly that.
- `.github/workflows/deploy.yml` publishes `git.catlow.cloud/sam/archie-agent`
as `:latest` and `:sha-<commit>` when the commit carries a release tag; an
ordinary push to `main` publishes nothing for the agent image.
- `tools/publish.sh`, run by hand for a release, publishes
`git.catlow.cloud/sam/archie-agent` as `:latest` and `:sha-<commit>`, which is
the registry the shipped default above names.
A distribution zip pins whichever one its own release published, by digest, in
`release.json`; `archied update install` then pulls exactly that.
As of this writing, `archie-agent` has **no published semantic-version tag** --
both paths publish only `:latest` and an immutable `:sha-<commit>` (`archied`
is versioned independently per `RELEASING.md`, but that versioning is not yet
reflected as a registry tag for the agent image). Until one publishes it, the
only reproducible reference is a content digest, resolved once and pinned
explicitly:
To pin by hand, prefer the version tag for readability, or a digest where you
need byte-for-byte reproducibility (a tag can be overwritten, a digest cannot):
```toml
[containers]
image = "git.catlow.cloud/sam/archie-agent:v<version>"
# or
image = "git.catlow.cloud/sam/archie-agent@sha256:<digest>"
```
This is the digest `latest` resolved to on 2026-09-05. Digest pinning is the
strongest option for production: it is immutable and independently
verifiable (`docker manifest inspect git.catlow.cloud/sam/archie-agent@sha256:...`),
at the cost of being opaque in a config file a human is meant to edit --
resolve a fresh digest deliberately (`docker pull ...:latest` followed by
`docker inspect --format '{{index .RepoDigests 0}}'`) rather than editing this
one in place expecting it to track new releases.
If/when CI starts publishing a semantic-version tag for `archie-agent`
(e.g. `git.catlow.cloud/sam/archie-agent:v1.21.0`), prefer that tag for
day-to-day config readability, and reserve digest pinning for deployments
that need byte-for-byte reproducibility guarantees a tag alone cannot give
(tags are mutable pointers; a compromised or accidentally-overwritten tag
still resolves, a digest cannot).
A reference on a registry that needs a login needs the credential in
`[containers].registry_auth` -- the release's own
`git.catlow.cloud/sam/archie-agent` digest is one, since an anonymous pull
+20
View File
@@ -85,7 +85,17 @@
"/news/archie/1.54.3/": "/news/1.54.3/",
"/news/archie/1.55.0/": "/news/1.55.0/",
"/news/archie/1.56.0/": "/news/1.56.0/",
"/news/archie/1.57.0/": "/news/1.57.0/",
"/news/archie/1.58.0/": "/news/1.58.0/",
"/news/archie/1.58.1/": "/news/1.58.1/",
"/news/archie/1.59.0/": "/news/1.59.0/",
"/news/archie/1.6.0/": "/news/1.6.0/",
"/news/archie/1.60.0/": "/news/1.60.0/",
"/news/archie/1.61.0/": "/news/1.61.0/",
"/news/archie/1.61.1/": "/news/1.61.1/",
"/news/archie/1.61.2/": "/news/1.61.2/",
"/news/archie/1.61.3/": "/news/1.61.3/",
"/news/archie/1.62.0/": "/news/1.62.0/",
"/news/archie/1.7.0/": "/news/1.7.0/",
"/news/archie/1.8.0/": "/news/1.8.0/",
"/news/archie/1.9.0/": "/news/1.9.0/",
@@ -186,7 +196,17 @@
"/news/archied/1.54.3/": "/news/1.54.3/",
"/news/archied/1.55.0/": "/news/1.55.0/",
"/news/archied/1.56.0/": "/news/1.56.0/",
"/news/archied/1.57.0/": "/news/1.57.0/",
"/news/archied/1.58.0/": "/news/1.58.0/",
"/news/archied/1.58.1/": "/news/1.58.1/",
"/news/archied/1.59.0/": "/news/1.59.0/",
"/news/archied/1.6.0/": "/news/1.6.0/",
"/news/archied/1.60.0/": "/news/1.60.0/",
"/news/archied/1.61.0/": "/news/1.61.0/",
"/news/archied/1.61.1/": "/news/1.61.1/",
"/news/archied/1.61.2/": "/news/1.61.2/",
"/news/archied/1.61.3/": "/news/1.61.3/",
"/news/archied/1.62.0/": "/news/1.62.0/",
"/news/archied/1.7.0/": "/news/1.7.0/",
"/news/archied/1.8.0/": "/news/1.8.0/",
"/news/archied/1.9.0/": "/news/1.9.0/",
+50
View File
@@ -1,4 +1,54 @@
[
{
"version": "1.62.0",
"date": "2026-11-10",
"body": "### archied\n\n- When an agent step reaches its step budget, the task asks to continue instead of parking. Approving resumes the stopped step with its conversation, including inside a parallel branch.\n- A parked task is flagged when the credential, connection or setting its blocker names changes, so you can see which parks are worth retrying.\n- Merging, closing and issue tools use the repository's own forge connection. A repository on Gitea no longer gets a GitHub 404 when its pull request is merged from archie.\n- A restart re-queues a running task at the step it was interrupted in, and parks it after three restarts instead of looping.\n- Issues and pull request review activity from authors without write access are ignored.\n- A baseline repair made by the repository gate is opened as its own pull request before the task continues.\n- Closing an issue that still has open dependencies is recorded as refused, rather than parking the task.\n- When the work volume fills, stale task clones are reclaimed; clones with uncommitted or unpushed work are kept. Clones need 1 GiB free, not 5.\n- A corrupt repository mirror is rebuilt, and a push that hits a missing object rebuilds the mirror and retries once.\n- Readiness reports degraded when the run loop stalls.\n- Execution budgets set in the dashboard are no longer reverted when the model catalogue loads.\n- A full volume is reported as an environment failure, and an unreachable secret engine as unavailable, rather than as a bad or missing credential.\n- A park from the workflow identity check now appears in the task log.\n- Every task records the identity that created it, and its queued event names the task, actor and principal. System is the one instance identity: it polls forge connections and owns the root grants and connection permits the bot-named identity used to hold, which existing tasks, grants and permits move to on upgrade.\n\n### archie-ui\n\n- A chat reply is no longer lost when you switch conversation or reload mid-answer: the turn finishes and its reply is in the conversation when you come back. Stop is the only way to cancel it.\n- The task page offers every action the task list does.\n- Workflows have row actions, enabling or disabling one confirms with a toast, and the editor toolbar wraps on narrow screens.\n- The dashboard lists five tasks needing attention, not every one.\n- Dismiss all no longer covers the unread badge.\n\n### archie-agent\n\n- The agent image includes Task, so the repository gate no longer downloads it on every run."
},
{
"version": "1.61.3",
"date": "2026-11-08",
"body": "### archie-ui\n\n- Issue, pull request and repository links on tasks open on the forge the repository's connection points at, instead of GitHub.\n\n- Settings: the Harness page is now part of Agent profiles. The setup terminal and the credential sign-in status sit on the same page as the Kit profiles they target, so a profile with a Kit can be signed in from the page that defines it."
},
{
"version": "1.61.2",
"date": "2026-11-07",
"body": "### archied\n\n- archied no longer gets killed by the systemd watchdog when a restart or update leaves many tasks to resume. Each resumed task used to cost a full queue poll before the next was picked up, so a dozen of them outlasted the 30-second watchdog; an update that hit this was rolled back."
},
{
"version": "1.61.1",
"date": "2026-11-07",
"body": "### archie-gateway\n\n- An image or voice attachment that arrives as a link is now checked against what the link serves, the same as an uploaded one. A link whose content is not the declared type, or that cannot be read, is refused.\n\n### archie-ui\n\n- A workflow created on the canvas now saves the agent it runs as, so it runs instead of parking with \"declares no identity to run as\".\n\n### archie-state-store\n\n- A workflow that no longer validates after an upgrade (for example it names a step type that was removed) is repaired at startup instead of breaking every workflow. A shipped workflow is restored from this release's copy; a workflow you created is removed and logged, and its earlier revision stays in the resource history. Valid workflows you created or edited are kept."
},
{
"version": "1.61.0",
"date": "2026-11-07",
"body": "### archied\n\n- A `workflow.handoff` now finishes its run and starts a separate, linked run of the next workflow on the same issue, instead of continuing as another attempt. The task page links each run to the one before and after it; attempts count only retries of one run.\n\n- A task no longer fails to prepare its worktree with \"some refs were not updated\" after a tag or branch moves on the forge.\n\n### archie-ui\n\n- The task page no longer flashes its loading state on every live update while a task runs.\n\n### archie-state-store\n\n- The extension catalogue lists and installs again. Its default signing key has changed; an instance that set its own catalogue signing key in Extension settings keeps using that key."
},
{
"version": "1.60.0",
"date": "2026-11-02",
"body": "### archied\n\n- Curators can list a repository's open issues and file new ones with the `issue_list` and `issue_create` tools, which reach the forge through the daemon. A curator files only when its definition declares `issue_create`; the shipped self-intake example runs in dry run with `issue_list` for deduplication. Listing every open issue needs the forge extensions from the archipelago release after 1.2.0."
},
{
"version": "1.59.0",
"date": "2026-11-02",
"body": "### archied\n\n- Forge extensions can open issues: the forge surface gains `CreateIssue` alongside list, comment and close, and the bundled Gitea and GitHub extensions implement it."
},
{
"version": "1.58.1",
"date": "2026-11-01",
"body": "### archied\n\n- The systemd watchdog now also watches the task intake loop, and its warning names the loop that stalled.\n- archied no longer restarts about a minute after it starts. Under systemd, the watchdog never saw a poll pass and killed it on every start since 1.56.0."
},
{
"version": "1.58.0",
"date": "2026-11-01",
"body": "### archied\n\n- Running `install.sh` over an install whose services are already running now restarts them, so they run the new binaries."
},
{
"version": "1.57.0",
"date": "2026-10-31",
"body": "### archied\n\n- A release reaches `stable` only after it has run on a canary for a day and passed: `archied release publish` now publishes to `next` alone, `archied release canary start|check` installs a release on a canary and judges it from the canary's dashboard, promoting it or rolling the canary back, and `archied release promote` moves `stable` by hand. Promotion refuses a prerelease and a release older than the one `stable` names. The `archied` and `archie-agent` images are published as `:v<version>`, and `:latest` moves only when a release is promoted."
},
{
"version": "1.56.0",
"date": "2026-10-31",
+68
View File
@@ -0,0 +1,68 @@
# Self-development loop: archie develops its own codebase
**Status:** Decided, not yet built (2026-11-03, sam) **Scope:** how archie
persistently takes on development of archie-core itself. This file records a
desired state, not an implementation or a product: nothing below exists unless
the "Built today" section says so. The plan is tracked as epic #1769 with child
issues #1770–#1775. This file is a record, not a mechanism: agents only see
what is in their context, so verify every claim here against the code before
acting on it — where they disagree, the code wins. The boundary below is
load-bearing only where it is enforced (the gate, access control, the daemon's
git monopoly) and stated in `AGENTS.md`; everywhere else this file is a pointer.
## Built today
The machinery the loop will reuse exists: shipped triage/implement/pr-review
workflows, the adversarial self-review stage before a PR opens (epic #1348,
closed), the prbench judge for review quality with its acceptance bar, canary
releases judged on the installed release (releaseupdate), and the curator
engine. What does not exist is the loop itself: no self-intake curator, no
approved-issue auto-run, no judge for diffs, no outcome distillation, no
canary routing specific to self-directed changes.
## Decision
Archie improves its own codebase through a closed loop, built in stages:
1. **Self-intake** (#1770): a curator pass reads run outcomes, step transcripts,
gate failures and alerts, dedupes against open issues, and files new issues.
Archie files its own work; the maintainer approves priority.
2. **Approved-issue loop** (#1771): an approved issue runs the shipped
triage/implement workflows end to end — read-only plan, gated build,
adversarial self-review, daemon commits and opens a green PR. The maintainer
still merges at this stage.
3. **Implementation judge** (#1772): the prbench judge pattern scores diffs,
calibrated against the maintainer's merge decisions; auto-merge applies only
when the gate is green, the review stage is clean, and the judge is above the
calibrated bar.
4. **Outcome distillation** (#1773): a curator turns merged-run postmortems into
proposals for the repo's agent instructions, each added only because it
changes a decision; rules that stop changing decisions are removed.
5. **Canary** (#1774): self-directed changes ship through the canary release
window and are judged on the installed release before promotion. Rollback is
a plain revert, because every self-directed change is one gated commit.
## Boundary
Enforcement lives in the harness, never in the prompt (#1775). Changes to the
commit gate, the invariants in `AGENTS.md`, access control and grant scoping,
the daemon-only git path, and webhook HMAC verification may be proposed by
archie but are never merged by archie — they require a maintainer merge.
Everything else (workflows, curators, memory, docs, the dashboard) is fair game
for the loop.
## Why
Self-improvement degrades when it relies on the model choosing to follow rules.
Gates, scoped grants and the daemon's monopoly on git cannot be argued with; a
prompt can. Keeping quality measurable — a judge bar and a canary verdict as
numbers, tests guarding the protected seams — is what lets the loop widen
without turning the codebase to garbage.
## Consequences
- One issue → one small PR applies doubly to self-directed work: past about 100
lines or any new mechanism, the change stops and reassesses.
- Every self-directed commit cites the issue that authorized it.
- Rule proposals from the distillation curator must name the run that triggered
them, and `AGENTS.md` stays short enough to read in full every session.
+1 -1
View File
@@ -78,7 +78,7 @@ accounts by unverified email, or create an administrator.
| Chat downloads: `webui/api_chat_files.go` | Offered file token expires and is bound to the initiating person; requests cannot supply a filesystem path. | `TestChatFileDownload` |
| Per-person memory: `archiegateway/chat_identity.go`, gateway memory tools, `sessioncurator` | Verified web sender identity scopes reads/writes. Curator refuses unidentified or mixed participants instead of guessing a person. | Gateway memory and session-curator tests |
| Workflow/task actions: `webui/api_tasks.go`, `domain/taskactions`, `staterpc` | Policy and stored workspace before action; domain transition, authority and durable dispatch guards remain in force. | HTTP deny matrix, task action/domain tests, task grant tests |
| Incoming webhooks: `forge/webhook`, `captureintake`, access delivery engine | Verify HMAC before parsing; derive source/org from stored source; evaluate source delivery policies and egress rules. No browser-user credential is inferred. | Webhook/capture tests, `TestAuthorizeDelivery` |
| Incoming webhooks: `captureintake`, access delivery engine | Verify HMAC before parsing; derive source/org from stored source; evaluate source delivery policies and egress rules. No browser-user credential is inferred. | Capture tests, `TestAuthorizeDelivery` |
| Control-plane configuration, secrets, harness and extensions | Browser policy and instance-only restrictions where registered; service contracts carry principal/org; task grants cannot invoke administrative RPCs. | HTTP deny matrix, `TestAdministrationRoutes`, `TestChannelReloadRoute`, `TestConfineHarnessOrg` |
| Audit feed: `webui/api_audit.go`, `domain/audit` | `read_audit` on the `audit` resource; org scope and the instance-wide exception come from the authenticated principal, never the query string. Export carries the same grant, needs an explicit range of at most a year, and is rate-limited per identity, one at a time. Redaction runs in the State Store adapter before an entry crosses gRPC. | `TestReadAuditRoleBoundary`, `TestAuditRoutesFollowTheReadAuditRole`, `TestHTTPPolicyCannotBeBypassed`, `TestAuditErrorMapping`, `TestAuditCSVCellNeutralisesFormulas` |
| Live HTTP/SSE and diagnostics | Authenticated policy gate applies before stream creation; org-scoped event reads; instance logs require administrative visibility. | HTTP deny matrix, instance-only tests, `TestServiceLogsRequireInstanceCredential` |
+126 -3
View File
@@ -1,9 +1,14 @@
// Keyboard and phone access: the task dialog fits and tabs in order, pages
// title correctly, the skip link and palette focus main content, and
// query-only tab switches keep focus where it is.
// query-only tab switches keep focus where it is. Then the audit's two
// static sweeps (#1767): no unnamed controls on any route, and every keyboard
// focus stop's indicator clears 3:1 against the background behind it.
const assert = require('node:assert/strict');
const { staticRoutes } = require('./helpers/routes.cjs');
module.exports = async ({ page, go, shot, settled }) => {
module.exports = async ({ page, go, shot, fail, settled, tolerate }) => {
// The extension catalogue 502 is a stack-environment issue, not this check.
tolerate(/extensions\/catalogue/);
await page.setViewportSize({ width: 390, height: 844 });
await go('/tasks');
await page.getByRole('button', { name: 'Jump to', exact: true }).click();
@@ -35,7 +40,7 @@ module.exports = async ({ page, go, shot, settled }) => {
assert.ok(await skip.evaluate(el => el === document.activeElement), 'Skip link is not the first keyboard stop');
await page.keyboard.press('Enter');
assert.equal(await page.evaluate(() => document.activeElement?.id), 'main-content');
await page.getByRole('button', { name: 'Sections', exact: true }).click();
await page.getByRole('button', { name: 'Toggle Sidebar', exact: true }).click();
await page.getByRole('navigation', { name: 'Sections', exact: true }).getByRole('link', { name: 'Tasks', exact: true }).click();
await page.waitForFunction(() => document.activeElement?.id === 'main-content', null, { timeout: 5000 }).catch(() => {});
assert.equal(await page.evaluate(() => document.activeElement?.id), 'main-content', 'route navigation did not focus main');
@@ -50,4 +55,122 @@ module.exports = async ({ page, go, shot, settled }) => {
const tab = page.getByRole('tab', { name: /^Map/ });
await tab.click();
assert.ok(await tab.evaluate(el => el === document.activeElement), 'query-only navigation stole focus');
await page.setViewportSize({ width: 1440, height: 900 });
// Unnamed controls: every visible input, textarea, select, button or
// widget role on each static route needs an accessible name (accname
// order: labelledby, label, content, value, placeholder, title).
for (const r of staticRoutes()) {
await go(r);
const unnamed = await page.evaluate(() => {
const name = (el) => {
const by = el.getAttribute('aria-labelledby');
if (by) {
const t = by.split(/\s+/).map((id) => (document.getElementById(id)?.textContent || '')).join(' ').trim();
if (t) return t;
}
const al = el.getAttribute('aria-label');
if (al && al.trim()) return al.trim();
if (el.id) {
const l = document.querySelector(`label[for="${CSS.escape(el.id)}"]`);
if (l && l.textContent.trim()) return l.textContent.trim();
}
const wrap = el.closest('label');
if (wrap && wrap.textContent.trim()) return wrap.textContent.trim();
if (el.tagName === 'BUTTON' || el.getAttribute('role') === 'button' || el.getAttribute('role') === 'tab' || el.getAttribute('role') === 'switch') return el.textContent.trim();
if (el.tagName === 'INPUT') {
const t = (el.getAttribute('type') || 'text').toLowerCase();
if (t === 'submit' || t === 'button' || t === 'reset') return el.value.trim();
if (t === 'image') return (el.getAttribute('alt') || '').trim();
}
return (el.getAttribute('placeholder') || el.getAttribute('title') || '').trim();
};
return [...document.querySelectorAll('button, input, textarea, select, [role="button"], [role="tab"], [role="switch"], [role="checkbox"]')]
.filter((el) => el.type !== 'hidden' && el.getClientRects().length)
.filter((el) => !name(el))
.map((el) => `${el.tagName.toLowerCase()}${el.id ? '#' + el.id : ''}: ${el.outerHTML.slice(0, 120)}`);
});
for (const u of unnamed) fail(`unnamed control on ${r}: ${u}`);
}
// Focus contrast: Tab through each static route; the focused element's
// outline or ring must clear 3:1 against the effective background behind it.
const focusProbe = () => page.evaluate(() => {
const el = document.activeElement;
if (!el || el === document.body || el === document.documentElement) return null;
const cs = getComputedStyle(el);
const parse = (c) => {
c = String(c).trim();
let m = c.match(/rgba?\(([^)]+)\)/);
if (m) {
const p = m[1].split(',').map(Number);
return { r: p[0], g: p[1], b: p[2], a: p.length > 3 ? p[3] : 1 };
}
m = c.match(/^#([0-9a-f]{3,8})$/i);
if (m) {
let h = m[1];
if (h.length === 3 || h.length === 4) h = [...h].map((x) => x + x).join('');
const n = parseInt(h.slice(0, 6), 16);
return { r: (n >> 16) & 255, g: (n >> 8) & 255, b: n & 255, a: h.length === 8 ? parseInt(h.slice(6, 8), 16) / 255 : 1 };
}
return null;
};
const bgBehind = (start) => {
for (let n = start; n; n = n.parentElement) {
const c = parse(getComputedStyle(n).backgroundColor);
if (c && c.a > 0) return c;
}
return { r: 255, g: 255, b: 255, a: 1 };
};
// An outer ring or outline is painted over the parent's background; an
// inset one over the element's own. Score against whichever is higher.
const bgSelf = bgBehind(el);
const bgParent = bgBehind(el.parentElement);
const over = (fg, bg) => {
const a = fg.a + bg.a * (1 - fg.a);
if (a === 0) return { r: 0, g: 0, b: 0 };
return { r: (fg.r * fg.a + bg.r * bg.a * (1 - fg.a)) / a, g: (fg.g * fg.a + bg.g * bg.a * (1 - fg.a)) / a, b: (fg.b * fg.a + bg.b * bg.a * (1 - fg.a)) / a };
};
const lum = (c) => {
const f = (v) => { v /= 255; return v <= 0.03928 ? v / 12.92 : Math.pow((v + 0.055) / 1.055, 2.4); };
return 0.2126 * f(c.r) + 0.7152 * f(c.g) + 0.0722 * f(c.b);
};
const ratio = (c1, c2) => {
const l1 = lum(c1), l2 = lum(c2);
return (Math.max(l1, l2) + 0.05) / (Math.min(l1, l2) + 0.05);
};
let fg = null;
// The ring lives in --tw-ring-shadow on :focus-visible; read the var
// directly, then fall back to outline, any shadow layer, focus border.
if (el.matches(':focus-visible')) {
const m = cs.getPropertyValue('--tw-ring-shadow').match(/rgba?\([^)]+\)|#[0-9a-f]{3,8}\b/i);
if (m) { const c = parse(m[0]); if (c && c.a > 0) fg = c; }
}
if (!fg && cs.outlineStyle !== 'none' && parseFloat(cs.outlineWidth) > 0) fg = parse(cs.outlineColor === 'currentcolor' ? cs.color : cs.outlineColor);
if (!fg && cs.boxShadow && cs.boxShadow !== 'none') {
for (const m of cs.boxShadow.matchAll(/rgba?\([^)]+\)|#[0-9a-f]{3,8}\b/gi)) {
const c = parse(m[0]);
if (c && c.a > 0) { fg = c; break; }
}
}
if (!fg && el.matches(':focus-visible') && parseFloat(cs.borderTopWidth) > 0) {
const c = parse(cs.borderTopColor);
if (c && c.a > 0) fg = c;
}
const sig = `${el.tagName}#${el.id}:${(el.textContent || '').trim().slice(0, 30)}`;
if (!fg) return { sig, ratio: 0 };
return { sig, ratio: Math.max(ratio(over(fg, bgSelf), bgSelf), ratio(over(fg, bgParent), bgParent)) };
});
for (const r of staticRoutes()) {
await go(r);
let prev = '';
for (let i = 0; i < 40; i++) {
await page.keyboard.press('Tab');
const info = await focusProbe();
if (!info || info.sig === prev) break;
prev = info.sig;
if (info.ratio < 3) fail(`focus indicator under 3:1 on ${r} at ${info.sig} (ratio ${info.ratio.toFixed(2)})`);
}
}
};
+19
View File
@@ -0,0 +1,19 @@
// The dashboard's static routes, read from the router source so a new page is
// swept automatically. Parameterised and redirect routes are skipped.
const fs = require('fs');
const path = require('path');
function staticRoutes() {
const src = fs.readFileSync(path.join(__dirname, '../../../ui/src/router/index.ts'), 'utf8');
const out = [];
for (const line of src.split('\n')) {
if (/redirect:/.test(line)) continue;
const m = line.match(/path: "([^"]*)"/);
if (!m || m[1].includes(':')) continue;
if (m[1].startsWith('/')) out.push(m[1]);
else if (m[1]) out.push('/org/' + m[1]);
}
return [...new Set(out)];
}
module.exports = { staticRoutes };
+18 -1
View File
@@ -1,5 +1,7 @@
const assert=require('node:assert/strict');
module.exports=async({page,go,shot})=>{
module.exports=async({page,go,shot,tolerate})=>{
// The extension catalogue 502 is a stack-environment issue, not this check.
tolerate(/extensions\/catalogue/);
await page.route('**/api/access/policies',async route=>{await new Promise(r=>setTimeout(r,2200));await route.continue()});
await go('/access/policies');
assert.equal(await page.getByText('No policies yet.',{exact:true}).count(),0);
@@ -16,4 +18,19 @@ module.exports=async({page,go,shot})=>{
await page.getByRole('button',{name:'Retry runs',exact:true}).click();
await page.getByRole('alert').filter({hasText:'Could not load recent runs'}).waitFor({state:'hidden'});
await shot('recovered');
// A failed list read is an error, never the empty state (#1767): force each
// page's list API to 500 and check its empty-state copy stays hidden.
const failList = async (pattern,path,emptyTexts,errorSel='[role=alert]')=>{
await page.route(pattern,route=>route.fulfill({status:200,contentType:'application/json',body:'unreadable response'}));
await go(path);
await page.locator(errorSel).first().waitFor();
for(const text of emptyTexts) assert.equal(await page.getByText(text,{exact:true}).count(),0,`${path} shows its empty state ("${text}") while the list read fails`);
await page.unroute(pattern);
};
await failList('**/api/tasks*','/tasks',['No tasks yet'],'text=Archie is not responding');
await failList('**/api/captures*','/events',['No captures yet']);
await failList('**/api/event-types*','/events',['No event types yet']);
await failList('**/api/tokens*','/account',['No tokens yet']);
await failList('**/api/access/policies*','/org/policies',['No policies yet']);
await shot('failed-reads-show-errors');
};
+6 -5
View File
@@ -1,4 +1,4 @@
// The topbar org selector: choosing a member org reloads the dashboard into it,
// The sidebar org switcher: choosing a member org reloads the dashboard into it,
// Tasks and Workflows then show only that org's work, and the API refuses an
// org the caller is not a member of.
const assert = require('node:assert/strict');
@@ -8,11 +8,12 @@ module.exports = async ({ page, go, shot, settled, tolerate }) => {
tolerate(ABSENT);
await go('/tasks');
await page.getByText('Fix flaky login test').first().waitFor();
const picker = page.getByRole('combobox', { name: 'Organisation' });
const picker = page.getByRole('button', { name: /^Organisation: / });
await picker.waitFor();
const offered = await (async () => {
await picker.click();
const names = await page.getByRole('option').allInnerTexts();
await page.getByRole('menuitem').first().waitFor();
const names = (await page.getByRole('menuitem').allInnerTexts()).map(t => t.trim().split('\n').pop().trim());
await page.keyboard.press('Escape');
return names;
})();
@@ -22,9 +23,9 @@ module.exports = async ({ page, go, shot, settled, tolerate }) => {
await shot('home-org-workflows');
await picker.click();
await Promise.all([page.waitForEvent('load'), page.getByRole('option', { name: 'Beta', exact: true }).click()]);
await Promise.all([page.waitForEvent('load'), page.getByRole('menuitem', { name: 'Beta' }).click()]);
await settled('/workflows');
await page.getByRole('combobox', { name: 'Organisation' }).waitFor();
await page.getByRole('button', { name: /^Organisation: / }).waitFor();
assert.equal(await page.getByText('Parked', { exact: true }).count(), 0, 'workflow run counts leaked across orgs');
await shot('beta-workflows');
await go('/tasks');
+69
View File
@@ -0,0 +1,69 @@
// Phone-width sweep of the views the November audit flagged (#1757): at
// 390x844 each must fit without horizontal scroll or clipped controls. The
// topbar (with its instance badge) is on every page; /account holds the
// token form, /org/agents the agent rows and the grants card, /events the
// sources table, the event-type rule editor and the mapping editor dialog.
const assert = require('node:assert/strict');
const { staticRoutes } = require('./helpers/routes.cjs');
module.exports = async ({ page, go, shot, fail, settled, tolerate }) => {
// The extension catalogue 502 is a stack-environment issue, not this check.
tolerate(/extensions\/catalogue/);
await page.setViewportSize({ width: 390, height: 844 });
const assertNoOverflow = async (label) => {
const { scrollWidth, innerWidth } = await page.evaluate(() => ({
scrollWidth: document.documentElement.scrollWidth,
innerWidth: window.innerWidth,
}));
if (scrollWidth > innerWidth) {
fail(`${label} overflows 390px: scrollWidth=${scrollWidth} > innerWidth=${innerWidth}`);
}
};
const visit = async (path, label, waitFor) => {
await go(path);
if (waitFor) await settled(waitFor);
await assertNoOverflow(label);
await shot(label);
};
await visit('/account', 'account-tokens', 'text=API tokens');
await visit('/org/agents', 'org-agents', 'text=Credential grants');
await go('/events');
await settled('[role=tab]');
await assertNoOverflow('events');
await shot('events');
// The seeded event type's rule editor (RuleEditor's condition row) opens
// from the Edit button on its row.
const editType = page.locator('button[aria-label^="Edit "]').first();
if (await editType.count()) {
await editType.click();
await page.getByRole('dialog').first().waitFor();
await settled();
await assertNoOverflow('event-type rule editor');
await shot('rule-editor');
await page.keyboard.press('Escape');
await settled();
}
// The mappings tab's editor dialog carries the payload tree.
await page.getByRole('tab', { name: 'Map' }).click();
await settled('text=New mapping');
await assertNoOverflow('mappings list');
const editMapping = page.locator('button', { hasText: 'Edit' }).first();
if (await editMapping.count()) {
await editMapping.click();
await page.getByRole('dialog').first().waitFor();
await settled();
await assertNoOverflow('mapping editor dialog');
await shot('mapping-editor');
}
// Every static route fits 390px (#1767): horizontal scroll fails.
for (const r of staticRoutes()) {
await visit(r, `route ${r}`, null);
}
};
+2 -16
View File
@@ -1,24 +1,10 @@
// Every static route loads without errors, renders, and shows no text with
// stray leading, trailing or doubled spaces.
const fs = require('fs');
const path = require('path');
function routes() {
const src = fs.readFileSync(path.join(__dirname, '../../ui/src/router/index.ts'), 'utf8');
const out = [];
for (const line of src.split('\n')) {
if (/redirect:/.test(line)) continue;
const m = line.match(/path: "([^"]*)"/);
if (!m || m[1].includes(':')) continue;
if (m[1].startsWith('/')) out.push(m[1]);
else if (m[1]) out.push('/org/' + m[1]);
}
return [...new Set(out)];
}
const { staticRoutes } = require('./helpers/routes.cjs');
module.exports = async ({ page, go, shot, fail }) => {
const stray = new Map();
for (const r of routes()) {
for (const r of staticRoutes()) {
await go(r);
await shot(r);
// Log lines are data, not copy.
+17 -20
View File
@@ -20,7 +20,7 @@ require (
github.com/emirpasic/gods v1.18.1 // indirect
github.com/fatih/color v1.19.0 // indirect
github.com/felixge/httpsnoop v1.1.0 // indirect
github.com/fxamacker/cbor/v2 v2.9.6 // indirect
github.com/fxamacker/cbor/v2 v2.10.0 // indirect
github.com/go-git/gcfg/v2 v2.0.2 // indirect
github.com/go-json-experiment/json v0.0.0-20260820222146-c27c302e5fc3 // indirect
github.com/go-logr/logr v1.4.4 // indirect
@@ -29,20 +29,19 @@ require (
github.com/go-webauthn/x v0.3.1 // indirect
github.com/golang/protobuf v1.5.4 // indirect
github.com/google/go-tpm v0.9.8 // indirect
github.com/grpc-ecosystem/grpc-gateway/v2 v2.32.0 // indirect
github.com/grpc-ecosystem/grpc-gateway/v2 v2.33.0 // indirect
github.com/hashicorp/yamux v0.1.2 // indirect
github.com/jackc/pgpassfile v1.0.0 // indirect
github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 // indirect
github.com/jackc/puddle/v2 v2.2.3 // indirect
github.com/kevinburke/ssh_config v1.6.0 // indirect
github.com/klauspost/compress v1.20.3 // indirect
github.com/mattn/go-colorable v0.1.16 // indirect
github.com/mattn/go-isatty v0.0.24 // indirect
github.com/mfridman/interpolate v0.0.2 // indirect
github.com/minio/highwayhash v1.0.4 // indirect
github.com/moby/docker-image-spec v1.3.1 // indirect
github.com/nats-io/jwt/v2 v2.8.2 // indirect
github.com/nats-io/nkeys v0.4.16 // indirect
github.com/nats-io/jwt/v2 v2.8.3 // indirect
github.com/nats-io/nkeys v0.4.17 // indirect
github.com/nats-io/nuid v1.0.1 // indirect
github.com/oklog/run v1.2.0 // indirect
github.com/philhofer/fwd v1.2.1 // indirect
@@ -60,45 +59,43 @@ require (
go.opentelemetry.io/otel/log v1.47.0 // indirect
go.opentelemetry.io/otel/metric v1.47.0 // indirect
go.uber.org/multierr v1.11.0 // indirect
go.yaml.in/yaml/v3 v3.0.5 // indirect
golang.org/x/exp v0.0.0-20261014143641-f0251eb4aa3e // indirect
go.yaml.in/yaml/v3 v3.0.6 // indirect
golang.org/x/exp v0.0.0-20261106192419-47ce03d25ef0 // indirect
golang.org/x/sync v0.24.0 // indirect
golang.org/x/text v0.43.0 // indirect
golang.org/x/time v0.16.0 // indirect
google.golang.org/genproto/googleapis/api v0.0.0-20261019180522-ce908d29299b // indirect
google.golang.org/genproto/googleapis/rpc v0.0.0-20261019180522-ce908d29299b // indirect
google.golang.org/genproto/googleapis/api v0.0.0-20261104224025-d1e00e9f33ab // indirect
google.golang.org/genproto/googleapis/rpc v0.0.0-20261104224025-d1e00e9f33ab // indirect
)
require (
cel.dev/cel-go v0.32.0
cel.dev/cel-go v0.33.2
github.com/BurntSushi/toml v1.6.0
github.com/cedar-policy/cedar-go v1.8.0
github.com/cedar-policy/cedar-go v1.9.0
github.com/containerd/errdefs v1.0.0
github.com/coreos/go-oidc/v3 v3.21.0
github.com/docker/sandbox-kit-spec/v3 v3.0.0-m.8
github.com/docker/sandbox-kit-spec/v3 v3.0.0-m.12
github.com/go-git/go-billy/v6 v6.0.0-beta.1
github.com/go-git/go-git/v6 v6.0.0-beta.1
github.com/go-jose/go-jose/v4 v4.1.6
github.com/go-telegram/bot v1.27.0
github.com/go-jose/go-jose/v4 v4.1.9
github.com/go-webauthn/webauthn v0.18.2
github.com/golang-jwt/jwt/v5 v5.3.1
github.com/google/jsonschema-go v0.4.3
github.com/google/uuid v1.6.0
github.com/hashicorp/go-hclog v1.6.3
github.com/hashicorp/go-plugin v1.8.0
github.com/jackc/pgx/v5 v5.11.0
github.com/hiddeco/sshsig v0.2.0
github.com/jackc/pgx/v5 v5.12.0
github.com/klauspost/compress v1.20.3
github.com/moby/moby/api v1.56.1
github.com/moby/moby/client v0.6.2
github.com/modelcontextprotocol/go-sdk v1.8.0
github.com/nats-io/nats-server/v2 v2.15.1
github.com/nats-io/nats-server/v2 v2.15.2
github.com/nats-io/nats.go v1.55.0
github.com/opencontainers/go-digest v1.0.0
github.com/opencontainers/image-spec v1.1.1
github.com/pressly/goose/v3 v3.29.0
github.com/samcharles93/ai-sdk v0.6.0
go.lsp.dev/jsonrpc2 v1.0.1
go.lsp.dev/protocol v1.0.1
go.lsp.dev/uri v1.0.1
go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.72.0
go.opentelemetry.io/contrib/instrumentation/net/http/otelhttp v0.72.0
go.opentelemetry.io/otel v1.47.0
@@ -107,7 +104,7 @@ require (
go.opentelemetry.io/otel/sdk v1.47.0
go.opentelemetry.io/otel/trace v1.47.0
go.opentelemetry.io/proto/otlp v1.11.1
golang.org/x/crypto v0.58.0
golang.org/x/crypto v0.58.1-0.20261009181718-2f1f834330b2
golang.org/x/mod v0.42.0
golang.org/x/net v0.62.0
golang.org/x/oauth2 v0.37.0
+35 -8
View File
@@ -1,5 +1,7 @@
cel.dev/cel-go v0.32.0 h1:irvpFKr5EuGPyxeME03ERh0rii1TX+BDAnB9eL3IvNk=
cel.dev/cel-go v0.32.0/go.mod h1:DnVip7tpJSsgZymwfT+m1tnEVy3ivAjSMXPx12YrMkU=
cel.dev/cel-go v0.33.2 h1:eAcEdBguc6AFrGbPOyE0g168Uey4kKFW9J6qsBLSeMU=
cel.dev/cel-go v0.33.2/go.mod h1:DnVip7tpJSsgZymwfT+m1tnEVy3ivAjSMXPx12YrMkU=
cel.dev/expr v0.25.3 h1:A2jO8jwOugrrovveCWfj0KEZOfqiLgAcwjpHPhzIGw0=
cel.dev/expr v0.25.3/go.mod h1:hrXvqGP6G6gyx8UAHSHJ5RGk//1Oj5nXQ2NI02Nrsg4=
github.com/BurntSushi/toml v1.6.0 h1:dRaEfpa2VI55EwlIW72hMRHdWouJeRF7TPYhI+AUQjk=
@@ -20,6 +22,8 @@ github.com/bufbuild/protocompile v0.14.1 h1:iA73zAf/fyljNjQKwYzUHD6AD4R8KMasmwa/
github.com/bufbuild/protocompile v0.14.1/go.mod h1:ppVdAIhbr2H8asPk6k4pY7t9zB1OU5DoEw9xY/FUi1c=
github.com/cedar-policy/cedar-go v1.8.0 h1:9gcU7EHXwHC2RMdpph68yTAkdB3behTTssC+kt4GoS8=
github.com/cedar-policy/cedar-go v1.8.0/go.mod h1:h5+3CVW1oI5LXVskJG+my9TFCYI5yjh/+Ul3EJie6MI=
github.com/cedar-policy/cedar-go v1.9.0 h1:p6KSbPT0E79gO5mXNdwAqbDPn4ypz7gX5WV0ScLWmFc=
github.com/cedar-policy/cedar-go v1.9.0/go.mod h1:+pmZnfwQkIUKO9qHzoL2wg8Q6xn7c9le15sexhinvVw=
github.com/cenkalti/backoff/v5 v5.0.3 h1:ZN+IMa753KfX5hd8vVaMixjnqRZ3y8CuJKRKj1xcsSM=
github.com/cenkalti/backoff/v5 v5.0.3/go.mod h1:rkhZdG3JZukswDf7f0cwqPNk4K0sa+F97BxZthm/crw=
github.com/cespare/xxhash/v2 v2.3.0 h1:UL815xU9SqsFlibzuggzjXhog7bL6oX9BbNZnL2UFvs=
@@ -46,6 +50,8 @@ github.com/docker/go-units v0.5.0 h1:69rxXcBk27SvSaaxTtLh/8llcHD8vYHT7WSdRZ/jvr4
github.com/docker/go-units v0.5.0/go.mod h1:fgPhTUdO+D/Jk86RDLlptpiXQzgHJF7gydDDbaIK4Dk=
github.com/docker/sandbox-kit-spec/v3 v3.0.0-m.8 h1:ay2XEj0yW3uzsNwN3KXS/c4nlneHONFKaHlrVhu2WCQ=
github.com/docker/sandbox-kit-spec/v3 v3.0.0-m.8/go.mod h1:4G6VgFAp9eaQkwy7DbZbOfWRD/Mjvc/TnEtQBRRMEsA=
github.com/docker/sandbox-kit-spec/v3 v3.0.0-m.12 h1:ZPkgVmmfBTEYUdVpEHVFF8BxTXFrYONQ3cDTgAc/JXc=
github.com/docker/sandbox-kit-spec/v3 v3.0.0-m.12/go.mod h1:s/lMVROKewN90s0OQ4WrOi6v3+IBDtRI75Hmol8rG4Y=
github.com/dustin/go-humanize v1.1.0 h1:dbKTrvD0klcbBV/h4AWJdMuZogJACoMlvWIWZ5b2xWg=
github.com/dustin/go-humanize v1.1.0/go.mod h1:hc1CvRkJMsgxqjmjMQF3QNRAZBwY8AXBAzKYoSX9sFI=
github.com/emirpasic/gods v1.18.1 h1:FXtiHYKDGKCW2KzwZKx0iC0PQmdlorYgdFG9jPXJ1Bc=
@@ -57,6 +63,8 @@ github.com/felixge/httpsnoop v1.1.0 h1:3YtUj32ZZkqZtt3sZZsClsymw/QDuVfpNhoA31zeO
github.com/felixge/httpsnoop v1.1.0/go.mod h1:Zqxgdd+1Rkcz8euOqdr7lqgCRJztwr5hp9vDSi5UZCE=
github.com/fxamacker/cbor/v2 v2.9.6 h1:NHZPxuUjJXQjX9itA785y/5NKSlI4HQ+S7noZsmI7hs=
github.com/fxamacker/cbor/v2 v2.9.6/go.mod h1:4EaZp6ClVunETjQ4GHmGNzysDK91Lr+r6Yz6tJqzVCw=
github.com/fxamacker/cbor/v2 v2.10.0 h1:HVF3T5vYwLqO81ebPirWEPNv2SMrUMD3HLnKgEr6uWE=
github.com/fxamacker/cbor/v2 v2.10.0/go.mod h1:uSwlToFuT9BZAKRxxVm3qQC8DR4tlWl7D6pf20iRYH4=
github.com/gliderlabs/ssh v0.3.8 h1:a4YXD1V7xMF9g5nTkdfnja3Sxy1PVDCj1Zg4Wb8vY6c=
github.com/gliderlabs/ssh v0.3.8/go.mod h1:xYoytBv1sV0aL3CavoDuJIQNURXkkfPA/wxQ1pL1fAU=
github.com/go-git/gcfg/v2 v2.0.2 h1:MY5SIIfTGGEMhdA7d7JePuVVxtKL7Hp+ApGDJAJ7dpo=
@@ -69,6 +77,8 @@ github.com/go-git/go-git/v6 v6.0.0-beta.1 h1:1t+vJYGDBN6f9GRWskgWx5UjXPFUa7wfffZ
github.com/go-git/go-git/v6 v6.0.0-beta.1/go.mod h1:ugDlr38Wwc+fOw85J+Oluh5TNXQtJgYMcriOljg3l4s=
github.com/go-jose/go-jose/v4 v4.1.6 h1:sNRkftxFJxwsILiQukqp5z83QBSmntVwmgRY7AqBDO4=
github.com/go-jose/go-jose/v4 v4.1.6/go.mod h1:x4oUasVrzR7071A4TnHLGSPpNOm2a21K9Kf04k1rs08=
github.com/go-jose/go-jose/v4 v4.1.9 h1:pKfeQkig1NmgK4hJrZYXLEYURXfoJB61Larw0uIW4gY=
github.com/go-jose/go-jose/v4 v4.1.9/go.mod h1:x4oUasVrzR7071A4TnHLGSPpNOm2a21K9Kf04k1rs08=
github.com/go-json-experiment/json v0.0.0-20260820222146-c27c302e5fc3 h1:UADEEmDKgfXbtnGJZ97beY5XLo9ZechG1nlU4KnRrkE=
github.com/go-json-experiment/json v0.0.0-20260820222146-c27c302e5fc3/go.mod h1:tphK2c80bpPhMOI4v6bIc2xWywPfbqi1Z06+RcrMkDg=
github.com/go-logr/logr v1.2.2/go.mod h1:jdQByPbusPIv2/zmleS9BjJVeZ6kBagPoEUsqbVz/1A=
@@ -76,8 +86,6 @@ github.com/go-logr/logr v1.4.4 h1:tG4xh9yMsRCAiodLVTxyrkzSZ9+o0L1Kg/+cPVcbP/8=
github.com/go-logr/logr v1.4.4/go.mod h1:9T104GzyrTigFIr8wt5mBrctHMim0Nb2HLGrmQ40KvY=
github.com/go-logr/stdr v1.2.2 h1:hSWxHoqTgW2S2qGc0LTAI563KZ5YKYRhT3MFKZMbjag=
github.com/go-logr/stdr v1.2.2/go.mod h1:mMo/vtBO5dYbehREoey6XUKy/eSumjCCveDpRre4VKE=
github.com/go-telegram/bot v1.27.0 h1:PG9yBDzM8O26oUerE9SZwWlHon4RpH8WcNslZ7CEZmE=
github.com/go-telegram/bot v1.27.0/go.mod h1:i2TRs7fXWIeaceF3z7KzsMt/he0TwkVC680mvdTFYeM=
github.com/go-viper/mapstructure/v2 v2.5.0 h1:vM5IJoUAy3d7zRSVtIwQgBj7BiWtMPfmPEgAXnvj1Ro=
github.com/go-viper/mapstructure/v2 v2.5.0/go.mod h1:oJDH3BJKyqBA2TXFhDsKDGDTlndYOZ6rGS0BRZIxGhM=
github.com/go-webauthn/webauthn v0.18.2 h1:0BeftmEHU7i3Dv0VFwBtidy/ba37Vcdjvqst9EYu8Sk=
@@ -100,18 +108,24 @@ github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
github.com/grpc-ecosystem/grpc-gateway/v2 v2.32.0 h1:QMILzF8BA7xftE4zVORkRrlv08m12St3csK4RsyRgRs=
github.com/grpc-ecosystem/grpc-gateway/v2 v2.32.0/go.mod h1:+ZQ6iUL8+ATyxGDQNuRKpNwJFdGDUi0e7E1QL9MvI7U=
github.com/grpc-ecosystem/grpc-gateway/v2 v2.33.0 h1:5T5Ns3kMpWr+z3s5ZA0e7ljVyWNVNxK76sHPAxi5D1k=
github.com/grpc-ecosystem/grpc-gateway/v2 v2.33.0/go.mod h1:oWNYw09cH8wl8fFgC5hKlBLxR4XfKy2KQpP8MJjeCcc=
github.com/hashicorp/go-hclog v1.6.3 h1:Qr2kF+eVWjTiYmU7Y31tYlP1h0q/X3Nl3tPGdaB11/k=
github.com/hashicorp/go-hclog v1.6.3/go.mod h1:W4Qnvbt70Wk/zYJryRzDRU/4r0kIg0PVHBcfoyhpF5M=
github.com/hashicorp/go-plugin v1.8.0 h1:ie8S6RRY8RvB2usYZv+AAZ/wBvx2AU5p5QeP5j/FORs=
github.com/hashicorp/go-plugin v1.8.0/go.mod h1:BExt6KEaIYx804z8k4gRzRLEvxKVb+kn0NMcihqOqb8=
github.com/hashicorp/yamux v0.1.2 h1:XtB8kyFOyHXYVFnwT5C3+Bdo8gArse7j2AQ0DA0Uey8=
github.com/hashicorp/yamux v0.1.2/go.mod h1:C+zze2n6e/7wshOZep2A70/aQU6QBRWJO/G6FT1wIns=
github.com/hiddeco/sshsig v0.2.0 h1:gMWllgKCITXdydVkDL+Zro0PU96QI55LwUwebSwNTSw=
github.com/hiddeco/sshsig v0.2.0/go.mod h1:nJc98aGgiH6Yql2doqH4CTBVHexQA40Q+hMMLHP4EqE=
github.com/jackc/pgpassfile v1.0.0 h1:/6Hmqy13Ss2zCq62VdNG8tM1wchn8zjSGOBJ6icpsIM=
github.com/jackc/pgpassfile v1.0.0/go.mod h1:CEx0iS5ambNFdcRtxPj5JhEz+xB6uRky5eyVu/W2HEg=
github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761 h1:iCEnooe7UlwOQYpKFhBabPMi4aNAfoODPEFNiAnClxo=
github.com/jackc/pgservicefile v0.0.0-20240606120523-5a60cdf6a761/go.mod h1:5TJZWKEWniPve33vlWYSoGYefn3gLQRzjfDlhSJ9ZKM=
github.com/jackc/pgx/v5 v5.11.0 h1:IzBBtyK9AHqf98cctWFifYSci2hgQR/cd56wB4p+ogg=
github.com/jackc/pgx/v5 v5.11.0/go.mod h1:mal1tBGAFfLHvZzaYh77YS/eC6IX9OWbRV1QIIM0Jn4=
github.com/jackc/pgx/v5 v5.12.0 h1:hWwax8YiGT0YiN50U1oIDn5kgR7KC2tG3rmavwpPkxY=
github.com/jackc/pgx/v5 v5.12.0/go.mod h1:u2Fi6no03HCSBYE+ZVdLxbwdu3xyi2vU+K/YNJioSds=
github.com/jackc/puddle/v2 v2.2.3 h1:f8HoREISb3l5eO9coPgK7U3hKLhWGokOFVcThl5jrao=
github.com/jackc/puddle/v2 v2.2.3/go.mod h1:vriiEXHvEE654aYKXXjOvZM39qJ0q+azkZFrfEOc3H4=
github.com/jhump/protoreflect v1.17.0 h1:qOEr613fac2lOuTgWN4tPAtLL7fUSbuJL5X5XumQh94=
@@ -149,12 +163,18 @@ github.com/modelcontextprotocol/go-sdk v1.8.0 h1:KIvahhYqwtbeniWVPs3TcXEA7b8jEtw
github.com/modelcontextprotocol/go-sdk v1.8.0/go.mod h1:dL7u98E/zjJTGzEq+j30jQ8K2k1mb6LeAH4inEcSGts=
github.com/nats-io/jwt/v2 v2.8.2 h1:XXRgB60MSTnqsRwejQurVDs/hcv2dkt+86GjI+I/bMc=
github.com/nats-io/jwt/v2 v2.8.2/go.mod h1:Ag/56sq9OblL4JgdYufDd16Egb17Kr/8WwwuO/forVc=
github.com/nats-io/jwt/v2 v2.8.3 h1:pqImTmlqH2zPHKNdRXO0YRyWif2diGRlrtLFJ2RxM2I=
github.com/nats-io/jwt/v2 v2.8.3/go.mod h1:OOY2rP/UU8tcfoqhbHmBKcNdpFMKvmxIkmFFa16M4wI=
github.com/nats-io/nats-server/v2 v2.15.1 h1:fK3AeYFIji1Smng60jB0hVoAPZezA/UzsaI3BqXFNEI=
github.com/nats-io/nats-server/v2 v2.15.1/go.mod h1:yeuYRtKVKIFtmMz2/YPk+6hvmNBnk+WwTUzErBdH6IE=
github.com/nats-io/nats-server/v2 v2.15.2 h1:yLsgt2kslgymvxvjFq1WGWck5hkat2YYfbXvQ145tzU=
github.com/nats-io/nats-server/v2 v2.15.2/go.mod h1:VXHCZgDglV5wO2B8ZE58yG2HzqxQxYUbQqibUh5Xcr8=
github.com/nats-io/nats.go v1.55.0 h1:Ng8QKHdvdHIWoaiq0+d/aH1BWkxvcJxWJ0Y/9BPKx3M=
github.com/nats-io/nats.go v1.55.0/go.mod h1:y+DZoD1oBOYfZTU681eTUiUjI0vbqYGixNVFHcjHJ0k=
github.com/nats-io/nkeys v0.4.16 h1:rd5oAuLOb8mnAycB0xleuEBNS1pVVnN0fv/FF34Eypg=
github.com/nats-io/nkeys v0.4.16/go.mod h1:llLgWoI0o4z/Q57q2R1kHfmocyhGV6VG/U18Glg1Afs=
github.com/nats-io/nkeys v0.4.17 h1:JAJrlDhOyQqOt0a1eg4cbIZ1Kc7+vmkCigAltpwQpVA=
github.com/nats-io/nkeys v0.4.17/go.mod h1:llLgWoI0o4z/Q57q2R1kHfmocyhGV6VG/U18Glg1Afs=
github.com/nats-io/nuid v1.0.1 h1:5iA8DT8V7q8WK2EScv2padNa/rTESc1KdnPw4TC2paw=
github.com/nats-io/nuid v1.0.1/go.mod h1:19wcPz3Ph3q0Jbyiqsd0kePYG7A95tJPxeL+1OSON2c=
github.com/ncruces/go-strftime v1.1.0 h1:vtPmPWMkb539RGV9WpWT9EwJGvrOCKvMNI4obWL47Hk=
@@ -203,12 +223,6 @@ github.com/x448/float16 v0.8.4 h1:qLwI1I70+NjRFUR3zs1JPUCgaCXSh3SW62uAKT1mSBM=
github.com/x448/float16 v0.8.4/go.mod h1:14CWIYCyZA/cWjXOioeEpHeN/83MdbZDRQHoFcYsOfg=
github.com/yosida95/uritemplate/v3 v3.0.2 h1:Ed3Oyj9yrmi9087+NczuL5BwkIc4wvTb5zIM+UJPGz4=
github.com/yosida95/uritemplate/v3 v3.0.2/go.mod h1:ILOh0sOhIJR3+L/8afwt/kE++YT040gmv5BQTMR2HP4=
go.lsp.dev/jsonrpc2 v1.0.1 h1:JZAchpm6RcOuwEOnZ7kF3kA1EpEjdJZ/6rMSfOF3+F4=
go.lsp.dev/jsonrpc2 v1.0.1/go.mod h1:WN+TesqrPumBmUdsuWyn9DHq3zl4i85L/qG0NLdj8qg=
go.lsp.dev/protocol v1.0.1 h1:kLWUIk1v/deXxo1D0VO4avjZnfeuZ82mouJgJd/NbdU=
go.lsp.dev/protocol v1.0.1/go.mod h1:e//i41aEqc9ml32xiNuneUwbjOjuvTA4+uv+AkssJgk=
go.lsp.dev/uri v1.0.1 h1:ywxJN1UXoQ+v0I9lkoQNMmsm7lub5G9ZG7KXT8YTx30=
go.lsp.dev/uri v1.0.1/go.mod h1:06a0ghafs4PuqkLsJGUmlgPHw6+kH79edRXjOT/rA8s=
go.opentelemetry.io/auto/sdk v1.2.1 h1:jXsnJ4Lmnqd11kwkBV2LgLoFMZKizbCi5fNZ/ipaZ64=
go.opentelemetry.io/auto/sdk v1.2.1/go.mod h1:KRTj+aOaElaLi+wW1kO/DZRXwkF4C5xPbEe3ZiIhN7Y=
go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.72.0 h1:Tq+E65HaNbZTeqcLw6QUhsV+/EIWdkfUH2CQzcrlE5M=
@@ -241,10 +255,16 @@ go.uber.org/multierr v1.11.0 h1:blXXJkSxSSfBVBlC76pxqeO+LN3aDfLQo+309xJstO0=
go.uber.org/multierr v1.11.0/go.mod h1:20+QtiLqy0Nd6FdQB9TLXag12DsQkrbs3htMFfDN80Y=
go.yaml.in/yaml/v3 v3.0.5 h1:N6y/pJk8buWs9NY5ERU2HSMfm+IuD/OtfdAnq6kESPw=
go.yaml.in/yaml/v3 v3.0.5/go.mod h1:HVTZu1O7/Vkt2N+BFy8Zza+lnLsABggaTM2ZpNIGuKg=
go.yaml.in/yaml/v3 v3.0.6 h1:zcDfvjXEqTQmpjniUBLc91xYJMB2c4QOFxEF/LCEckM=
go.yaml.in/yaml/v3 v3.0.6/go.mod h1:HVTZu1O7/Vkt2N+BFy8Zza+lnLsABggaTM2ZpNIGuKg=
golang.org/x/crypto v0.58.0 h1:COkYLr4k7nDI4r6QtMML2AfzeIswWHAJthLS6K/M/54=
golang.org/x/crypto v0.58.0/go.mod h1:Xh+kl5A+M0gMiWDytH2Hhr5Z7WbNCpv/eB/EFgfSk+w=
golang.org/x/crypto v0.58.1-0.20261009181718-2f1f834330b2 h1:zGDaB+/Mus2mScKvZ23k+W9NAUbP56sNM9SptgvWI5A=
golang.org/x/crypto v0.58.1-0.20261009181718-2f1f834330b2/go.mod h1:Xh+kl5A+M0gMiWDytH2Hhr5Z7WbNCpv/eB/EFgfSk+w=
golang.org/x/exp v0.0.0-20261014143641-f0251eb4aa3e h1:HgI6W1OolKK6tcV74is+rl9SMT0njsHlp0TbQiGXI/A=
golang.org/x/exp v0.0.0-20261014143641-f0251eb4aa3e/go.mod h1:DBoxwWhjaW8DJJw/YeM4zpeOKMC1FMXSblsYy+1mFSw=
golang.org/x/exp v0.0.0-20261106192419-47ce03d25ef0 h1:1GO4fJiyGakz0Liu2Ve1qPAwQYPkKlG1Q8iO2CYjtFA=
golang.org/x/exp v0.0.0-20261106192419-47ce03d25ef0/go.mod h1:J3U+E8RzytcGvwz+uJuAP4zULJ2TkAQBnmPZMexpdXs=
golang.org/x/mod v0.42.0 h1:ICeL3t2L30ljSPHHxDnR4fqVcBt/zR2zJAb9juavmQg=
golang.org/x/mod v0.42.0/go.mod h1:u5fzIrRInkL8MaO1cbRkUHT64v303YIT5KEqpNr7jRs=
golang.org/x/net v0.62.0 h1:18ELalfM5+XNRwzM2nYqXsZQ9ByS1uhj2O/U7+5jqRY=
@@ -270,12 +290,19 @@ golang.org/x/time v0.16.0 h1:vMb6ptszcQMkcwiRTAuNNU50gom6++Q/6gY2hDM6VDE=
golang.org/x/time v0.16.0/go.mod h1:rVKOqvZeKvrDKTQiAHJ7wmwP0RzleSphoEA9RcdLA0s=
golang.org/x/tools v0.52.0 h1:ryxg4U63oaUYk7uOLTF37n43f4qgtGvqV4Ioit1BaEs=
golang.org/x/tools v0.52.0/go.mod h1:ItcP5UNaVGG+Yc4eIYmaFLNJ4soEopkx5Y2d4lcEurs=
golang.org/x/tools v0.52.1-0.20261106145633-d407941a339a h1:Yqozs0FNPRoPGS4hNGlrNwRENWr5H5nVG9sN/f+5640=
gonum.org/v1/gonum v0.17.0 h1:VbpOemQlsSMrYmn7T2OUvQ4dqxQXU+ouZFQsZOx50z4=
gonum.org/v1/gonum v0.17.0/go.mod h1:El3tOrEuMpv2UdMrbNlKEh9vd86bmQ6vqIcDwxEOc1E=
google.golang.org/genproto/googleapis/api v0.0.0-20261019180522-ce908d29299b h1:nB3spRIaSPtxJpxb0k41yljROvm2Jrwfs2pSNdKS5y8=
google.golang.org/genproto/googleapis/api v0.0.0-20261019180522-ce908d29299b/go.mod h1:9N4vtjEwvgQKEdlFVQO0M44ErhecQ9DCSQfGoZ51M6w=
google.golang.org/genproto/googleapis/api v0.0.0-20261026165753-2ffab32bce7e h1:e789sLZjeTdc02ZCQGTSzHOu0fR73+dwPQVKUp67Z88=
google.golang.org/genproto/googleapis/api v0.0.0-20261026165753-2ffab32bce7e/go.mod h1:vHV3wJM9WZyfV7GyB+OQGq5dWVrFwCDxapPK4WlRD88=
google.golang.org/genproto/googleapis/api v0.0.0-20261104224025-d1e00e9f33ab h1:n6IDWZ1RzI/NberLoLLFNrjl1H45uhc4+WYsUf5lPPc=
google.golang.org/genproto/googleapis/api v0.0.0-20261104224025-d1e00e9f33ab/go.mod h1:vHV3wJM9WZyfV7GyB+OQGq5dWVrFwCDxapPK4WlRD88=
google.golang.org/genproto/googleapis/rpc v0.0.0-20261019180522-ce908d29299b h1:6WNWHZk91dp4gZ25642OALkuG1UVNZbwENJD19DnB8k=
google.golang.org/genproto/googleapis/rpc v0.0.0-20261019180522-ce908d29299b/go.mod h1:OaIUM3+LpYcK2GXM4FTmhWoIq371Owdr+Cc7/BsYHHc=
google.golang.org/genproto/googleapis/rpc v0.0.0-20261104224025-d1e00e9f33ab h1:8sYjjefPfQ+FZEh1ZwBAqK/NifJVhOxut8nRh3SJzZM=
google.golang.org/genproto/googleapis/rpc v0.0.0-20261104224025-d1e00e9f33ab/go.mod h1:OaIUM3+LpYcK2GXM4FTmhWoIq371Owdr+Cc7/BsYHHc=
google.golang.org/grpc v1.86.0-dev h1:FLq7hcApuJeJ70J9+k0FvmXsNCwS8B2/MeAfYdy3GHY=
google.golang.org/grpc v1.86.0-dev/go.mod h1:Ovl0ECo4xx5r4kn/6d4BPSNB7OIFuu6EAjOzjtVAKaM=
google.golang.org/protobuf v1.36.12 h1:pJOKDDOyeXErUroCihFAd5LQuwXBSpVnKGrj5o/fwxc=
+4 -2
View File
@@ -475,10 +475,12 @@ EOF
fi
# Auto-enable and start the services, the store first so a fresh boot does
# not race a dial it depends on.
# not race a dial it depends on. Restart rather than start, because a
# reinstall over running services would otherwise leave the old binaries
# running.
if [ "${AUTO_START}" = true ]; then
echo "==> Enabling and starting Archie services..."
systemctl --user enable --now $INSTANCE_UNITS ||
{ systemctl --user enable $INSTANCE_UNITS && systemctl --user restart $INSTANCE_UNITS; } ||
echo " Notice: Could not start every service automatically. Check: systemctl --user status ${INSTANCE_UNITS}"
fi
fi
+7 -11
View File
@@ -10,6 +10,7 @@ import (
"io"
"os"
"sync"
"sync/atomic"
"github.com/modelcontextprotocol/go-sdk/mcp"
@@ -41,14 +42,6 @@ func AcceptCapture(spec agentrun.CaptureTool, accepted int, value json.RawMessag
return spec.Name + " recorded", true
}
// ServeCaptureMCP serves a stage's capture tools over MCP and appends each
// accepted call to sink as one JSON line. A rejected call is answered with
// its rejection, so the agent can correct it, and is not recorded.
func ServeCaptureMCP(ctx context.Context, specs []agentrun.CaptureTool, sink io.Writer, t mcp.Transport) error {
server := mcp.NewServer(&mcp.Implementation{Name: "archie", Version: "1"}, nil)
return serveHarnessMCP(ctx, specs, sink, t, server, false)
}
func serveHarnessMCP(ctx context.Context, specs []agentrun.CaptureTool, sink io.Writer, t mcp.Transport, server *mcp.Server, central bool) error {
if central {
cleanup, err := addCentralTools(ctx, server, specs)
@@ -142,12 +135,15 @@ func ServeCaptureFiles(ctx context.Context, specPath, capturesPath string, t mcp
}
defer sink.Close()
server := mcp.NewServer(&mcp.Implementation{Name: "archie", Version: "1"}, nil)
var ready atomic.Bool
server.AddReceivingMiddleware(func(next mcp.MethodHandler) mcp.MethodHandler {
return func(ctx context.Context, method string, req mcp.Request) (mcp.Result, error) {
result, err := next(ctx, method, req)
if err == nil && (method == "tools/list" || method == "tools/call") {
if err := os.WriteFile(capturesPath+".ready", nil, 0o600); err != nil {
return nil, fmt.Errorf("record MCP initialization: %w", err)
if err == nil && (method == "tools/list" || method == "tools/call") && !ready.Load() {
// A call is already recorded by now, so a failed marker must not
// turn it into a tool error; the runner reports the missing marker.
if os.WriteFile(capturesPath+".ready", nil, 0o600) == nil {
ready.Store(true)
}
}
return result, err
+1 -1
View File
@@ -52,7 +52,7 @@ type HarnessStages struct {
Spec agentrun.HarnessSpec
}
func (r HarnessStages) Run(ctx context.Context, workspace string, req agentrun.Request, report agentrun.ToolCallReporter) (agentrun.Result, error) {
func (r HarnessStages) Run(ctx context.Context, workspace string, req agentrun.Request, report agentrun.Reporter) (agentrun.Result, error) {
spec := r.Spec
req.Harness = &spec
return r.Runner.Run(ctx, workspace, req, report)
+1 -1
View File
@@ -34,7 +34,7 @@ func TestHarnessRequiresMCPInitialization(t *testing.T) {
if !central {
req.CaptureTools = []agentrun.CaptureTool{{Name: "capture_result", Parameters: json.RawMessage(`{"type":"object"}`)}}
}
result, err := NewHarnessRunner(nil).Run(t.Context(), workspace, req, nil)
result, err := NewHarnessRunner().Run(t.Context(), workspace, req, agentrun.Reporter{})
if err != nil {
t.Fatal(err)
}
+8 -10
View File
@@ -28,7 +28,7 @@ func newClaudeCodeHarnessOutput() *claudeCodeHarnessOutput {
}
}
func (o *claudeCodeHarnessOutput) Line(line []byte, report agentrun.ToolCallReporter) {
func (o *claudeCodeHarnessOutput) Line(line []byte, report agentrun.Reporter) {
var event struct {
Type string `json:"type"`
SessionID string `json:"session_id"`
@@ -44,7 +44,7 @@ func (o *claudeCodeHarnessOutput) Line(line []byte, report agentrun.ToolCallRepo
switch event.Type {
case "assistant":
o.assistant(event.Message, report)
o.assistant(event.Message)
case "user":
o.user(event.Message, report)
case "result":
@@ -55,7 +55,7 @@ func (o *claudeCodeHarnessOutput) Line(line []byte, report agentrun.ToolCallRepo
}
}
func (o *claudeCodeHarnessOutput) assistant(raw json.RawMessage, _ agentrun.ToolCallReporter) {
func (o *claudeCodeHarnessOutput) assistant(raw json.RawMessage) {
var message struct {
ID string `json:"id"`
Usage json.RawMessage `json:"usage"`
@@ -79,7 +79,7 @@ func (o *claudeCodeHarnessOutput) assistant(raw json.RawMessage, _ agentrun.Tool
}
}
func (o *claudeCodeHarnessOutput) user(raw json.RawMessage, report agentrun.ToolCallReporter) {
func (o *claudeCodeHarnessOutput) user(raw json.RawMessage, report agentrun.Reporter) {
var message struct {
Content []struct {
Type string `json:"type"`
@@ -100,12 +100,10 @@ func (o *claudeCodeHarnessOutput) user(raw json.RawMessage, report agentrun.Tool
continue
}
delete(o.pending, block.ToolUseID)
if report != nil {
report(agentrun.ToolCallReport{
Tool: tool, Detail: ClipToolCallDetail(claudeResultContent(block.Content)),
Failed: block.IsError,
})
}
report.ReportToolCall(agentrun.ToolCallReport{
Tool: tool, Detail: ClipToolCallDetail(claudeResultContent(block.Content)),
Failed: block.IsError,
})
}
}
+3 -3
View File
@@ -15,7 +15,7 @@ type codexHarnessOutput struct {
usage agentrun.Usage
}
func (o *codexHarnessOutput) Line(line []byte, report agentrun.ToolCallReporter) {
func (o *codexHarnessOutput) Line(line []byte, report agentrun.Reporter) {
var event struct {
Type string `json:"type"`
ThreadID string `json:"thread_id"`
@@ -43,8 +43,8 @@ func (o *codexHarnessOutput) Line(line []byte, report agentrun.ToolCallReporter)
})
}
case "item.completed":
if call, ok := event.Item.report(); ok && report != nil {
report(call)
if call, ok := event.Item.report(); ok {
report.ReportToolCall(call)
}
}
}
+2 -4
View File
@@ -18,7 +18,7 @@ func newCopilotHarnessOutput() *copilotHarnessOutput {
return &copilotHarnessOutput{pending: make(map[string]string)}
}
func (o *copilotHarnessOutput) Line(line []byte, report agentrun.ToolCallReporter) {
func (o *copilotHarnessOutput) Line(line []byte, report agentrun.Reporter) {
var event struct {
Type string `json:"type"`
SessionID string `json:"sessionId"`
@@ -52,9 +52,7 @@ func (o *copilotHarnessOutput) Line(line []byte, report agentrun.ToolCallReporte
return
}
delete(o.pending, event.Data.ToolCallID)
if report != nil {
report(agentrun.ToolCallReport{Tool: tool, Detail: ClipToolCallDetail(event.Data.Result.Content), Failed: !event.Data.Success})
}
report.ReportToolCall(agentrun.ToolCallReport{Tool: tool, Detail: ClipToolCallDetail(event.Data.Result.Content), Failed: !event.Data.Success})
}
}
+3 -3
View File
@@ -15,7 +15,7 @@ type piHarnessOutput struct {
usage agentrun.Usage
}
func (o *piHarnessOutput) Line(line []byte, report agentrun.ToolCallReporter) {
func (o *piHarnessOutput) Line(line []byte, report agentrun.Reporter) {
var event struct {
Type string `json:"type"`
ID string `json:"id"`
@@ -49,7 +49,7 @@ func (o *piHarnessOutput) Line(line []byte, report agentrun.ToolCallReporter) {
o.usage = addUsage(o.usage, usageFromFields(u.Input, u.Output, u.CacheRead, u.CacheWrite))
}
case "tool_execution_end":
if event.ToolName == "" || report == nil {
if event.ToolName == "" {
return
}
texts := make([]string, 0, len(event.Result.Content))
@@ -58,7 +58,7 @@ func (o *piHarnessOutput) Line(line []byte, report agentrun.ToolCallReporter) {
texts = append(texts, block.Text)
}
}
report(agentrun.ToolCallReport{Tool: event.ToolName, Detail: ClipToolCallDetail(strings.Join(texts, "\n")), Failed: event.IsError})
report.ReportToolCall(agentrun.ToolCallReport{Tool: event.ToolName, Detail: ClipToolCallDetail(strings.Join(texts, "\n")), Failed: event.IsError})
}
}
+3
View File
@@ -11,6 +11,9 @@ import (
// process groups are unavailable.
func setProcessGroup(*exec.Cmd) {}
// reapGroup has nothing to do where process groups are unavailable.
func reapGroup(*exec.Cmd) {}
// runAsHarnessUser refuses a named harness user where user switching is
// unavailable, rather than running the harness as the worker.
func runAsHarnessUser(_ *exec.Cmd, name string) error {
+8
View File
@@ -22,6 +22,14 @@ func setProcessGroup(cmd *exec.Cmd) {
cmd.Cancel = func() error { return syscall.Kill(-cmd.Process.Pid, syscall.SIGKILL) }
}
// reapGroup kills whatever the command left running in its process group, so a
// daemonised child cannot outlive the invocation that started it.
func reapGroup(cmd *exec.Cmd) {
if cmd.Process != nil {
_ = syscall.Kill(-cmd.Process.Pid, syscall.SIGKILL)
}
}
// runAsHarnessUser drops the invocation to the Kit's user. A worker running
// as root refuses to start a harness with no user, because the harness would
// then share the worker's user and could read its credentials.
+47 -37
View File
@@ -45,7 +45,7 @@ const (
// knows its CLI's stream format; it reports tool calls as they complete and
// the session to resume.
type HarnessOutput interface {
Line(line []byte, report agentrun.ToolCallReporter)
Line(line []byte, report agentrun.Reporter)
SessionID() string
Usage() agentrun.Usage
}
@@ -54,20 +54,13 @@ type HarnessOutput interface {
// guarantees do not depend on the CLI obeying its prompt: the runner checks
// the worktree and the repository's refs and configuration after every
// invocation, runs the gate itself, and owns the process's lifetime.
type HarnessRunner struct {
newOutput func() HarnessOutput
// mcpCommand starts archie's MCP server; it defaults to this binary's
// own "mcp" subcommand.
mcpCommand []string
}
type HarnessRunner struct{}
// NewHarnessRunner returns a runner using newOutput to read each
// invocation. A nil newOutput reads with the adapter the request names.
func NewHarnessRunner(newOutput func() HarnessOutput) *HarnessRunner {
return &HarnessRunner{newOutput: newOutput}
}
// NewHarnessRunner returns a runner that reads each invocation with the
// adapter the request names.
func NewHarnessRunner() *HarnessRunner { return &HarnessRunner{} }
func (r *HarnessRunner) Run(ctx context.Context, workspace string, req agentrun.Request, report agentrun.ToolCallReporter) (agentrun.Result, error) {
func (r *HarnessRunner) Run(ctx context.Context, workspace string, req agentrun.Request, report agentrun.Reporter) (agentrun.Result, error) {
if err := validateHarness(req); err != nil {
return agentrun.Result{}, err
}
@@ -95,7 +88,7 @@ func (r *HarnessRunner) Run(ctx context.Context, workspace string, req agentrun.
return res, err
}
func (r *HarnessRunner) run(ctx context.Context, workspace string, req agentrun.Request, mcpConfig string, report agentrun.ToolCallReporter) (agentrun.Result, error) {
func (r *HarnessRunner) run(ctx context.Context, workspace string, req agentrun.Request, mcpConfig string, report agentrun.Reporter) (agentrun.Result, error) {
res := agentrun.Result{Version: agentrun.ProtocolVersion, TaskID: req.TaskID, Attempt: req.Attempt, Stage: req.Stage}
before, err := snapshotRepo(workspace)
if err != nil {
@@ -133,7 +126,7 @@ func (r *HarnessRunner) run(ctx context.Context, workspace string, req agentrun.
return res, err
}
gateOutput, gateErr := runHarnessGate(runCtx, req.Gate.Commands, workspace)
gateOutput, gateErr := runHarnessGate(runCtx, req.Harness, req.Gate.Commands, workspace)
if gateErr == nil {
res.Status = agentrun.StatusPassed
return res, nil
@@ -144,7 +137,11 @@ func (r *HarnessRunner) run(ctx context.Context, workspace string, req agentrun.
if res.Iterations >= maxIterations {
return park(res, StopGate, gateOutput), nil
}
verb, prompt = resumeVerb(req.Harness, session), "The quality gate failed. Fix the cause, then stop.\n\n"+gateOutput
verb = resumeVerb(req.Harness, session)
if len(verb) == 0 {
return park(res, StopGate, gateOutput), nil
}
prompt = "The quality gate failed. Fix the cause, then stop.\n\n" + gateOutput
}
}
@@ -171,9 +168,6 @@ func settle(runCtx context.Context, workspace string, before repoState, req agen
}
func (r *HarnessRunner) output(adapter string) HarnessOutput {
if r.newOutput != nil {
return r.newOutput()
}
if a, ok := LookupHarnessAdapter(adapter); ok {
return a.NewOutput()
}
@@ -230,7 +224,9 @@ func harnessArgv(h *agentrun.HarnessSpec, verb []string, prompt, session, mcpCon
}
// resumeVerb continues the session the last invocation reported, falling
// back to the most recent session when the CLI reported none.
// back to the most recent session when the CLI reported none. It returns nil
// when neither is possible: resuming with an empty session ID would start a
// broken command.
func resumeVerb(h *agentrun.HarnessSpec, sessionID string) []string {
if len(h.Resume) > 0 && sessionID != "" {
return slices.Clone(h.Resume)
@@ -238,13 +234,13 @@ func resumeVerb(h *agentrun.HarnessSpec, sessionID string) []string {
if len(h.Continue) > 0 {
return slices.Clone(h.Continue)
}
return slices.Clone(h.Resume)
return nil
}
// invoke runs one harness invocation in its own process group, feeding
// stdout to out line by line. Cancelling ctx kills the whole group, so a
// CLI's children cannot outlive the step.
func invoke(ctx context.Context, workspace string, h *agentrun.HarnessSpec, argv []string, out HarnessOutput, report agentrun.ToolCallReporter) error {
func invoke(ctx context.Context, workspace string, h *agentrun.HarnessSpec, argv []string, out HarnessOutput, report agentrun.Reporter) error {
cmd := exec.CommandContext(ctx, argv[0], argv[1:]...)
cmd.Dir = workspace
cmd.WaitDelay = killGrace
@@ -270,8 +266,16 @@ func invoke(ctx context.Context, workspace string, h *agentrun.HarnessSpec, argv
for scanner.Scan() {
out.Line(scanner.Bytes(), report)
}
_, _ = io.Copy(io.Discard, output)
if err := cmd.Wait(); err != nil {
if err := scanner.Err(); err != nil {
// Stop the CLI rather than leave it writing into a pipe nobody parses.
_ = cmd.Cancel()
_, _ = io.Copy(io.Discard, output)
_ = cmd.Wait()
return fmt.Errorf("read harness output: %w", err)
}
waitErr := cmd.Wait()
reapGroup(cmd)
if err := waitErr; err != nil {
if ctx.Err() != nil {
return ctx.Err()
}
@@ -304,14 +308,24 @@ func harnessPrompt(workspace string, req agentrun.Request) string {
return b.String()
}
func runHarnessGate(ctx context.Context, commands []agentrun.Command, workspace string) (string, error) {
// runHarnessGate runs the gate commands confined like the harness: they
// execute code the harness just wrote, so they get its user, its environment
// and its process group rather than the worker's.
func runHarnessGate(ctx context.Context, h *agentrun.HarnessSpec, commands []agentrun.Command, workspace string) (string, error) {
for _, c := range commands {
if len(c.Argv) == 0 {
continue
}
cmd := exec.CommandContext(ctx, c.Argv[0], c.Argv[1:]...)
cmd.Dir = workspace
cmd.WaitDelay = killGrace
cmd.Env = append([]string{}, h.Env...)
setProcessGroup(cmd)
if err := runAsHarnessUser(cmd, h.User); err != nil {
return "", err
}
output, err := cmd.CombinedOutput()
reapGroup(cmd)
switch {
case c.ExpectFailure && err == nil:
return fmt.Sprintf("[%s] expected this command to fail, but it passed:\n%s", c.Name, clipGate(output)),
@@ -467,9 +481,9 @@ func policyViolation(before, after repoState, changes []string, req agentrun.Req
type silentOutput struct{}
func (silentOutput) Line([]byte, agentrun.ToolCallReporter) {}
func (silentOutput) SessionID() string { return "" }
func (silentOutput) Usage() agentrun.Usage { return agentrun.Usage{} }
func (silentOutput) Line([]byte, agentrun.Reporter) {}
func (silentOutput) SessionID() string { return "" }
func (silentOutput) Usage() agentrun.Usage { return agentrun.Usage{} }
// tailBuffer keeps the last stderrTailBytes written to it.
type tailBuffer struct{ buf bytes.Buffer }
@@ -507,18 +521,14 @@ func (r *HarnessRunner) prepareCaptures(req agentrun.Request) (config, captures
return fail(err)
}
specPath, capturesPath, configPath := filepath.Join(dir, "tools.json"), filepath.Join(dir, "captures.jsonl"), filepath.Join(dir, "mcp.json")
command := r.mcpCommand
if len(command) == 0 {
self, err := os.Executable()
if err != nil {
return fail(err)
}
command = []string{self}
self, err := os.Executable()
if err != nil {
return fail(err)
}
server := map[string]any{
"env": harnessMCPEnvironment(req.Harness.Env),
"command": command[0],
"args": slices.Concat(command[1:], []string{"mcp", "-spec", specPath, "-captures", capturesPath}),
"command": self,
"args": []string{"mcp", "-spec", specPath, "-captures", capturesPath},
}
cfg, err := json.Marshal(map[string]any{"mcpServers": map[string]any{"archie": server}})
if err != nil {
+1 -1
View File
@@ -18,7 +18,7 @@ func TestHarnessLiveOutput(t *testing.T) {
if os.Geteuid() == 0 {
user = "65534"
}
err := invoke(t.Context(), "/tmp", &agentrun.HarnessSpec{User: user}, []string{"sh", "-c", `printf '%s\n' '{"type":"thread.started","thread_id":"live-thread"}'; printf '%s\n' 'live diagnostic' >&2`}, adapter, nil)
err := invoke(t.Context(), "/tmp", &agentrun.HarnessSpec{User: user}, []string{"sh", "-c", `printf '%s\n' '{"type":"thread.started","thread_id":"live-thread"}'; printf '%s\n' 'live diagnostic' >&2`}, adapter, agentrun.Reporter{})
if err != nil {
t.Fatal(err)
}
+7 -3
View File
@@ -7,6 +7,7 @@ import (
"path/filepath"
"slices"
"strings"
"unicode/utf8"
"github.com/google/jsonschema-go/jsonschema"
@@ -15,15 +16,18 @@ import (
// toolCallDetailBytes caps the summary ToolCallReport.Detail carries. This
// rides on every task's observability event stream, so one large file read
// must not dominate it the way baselineMissionBytes-sized content is allowed
// to dominate a builder's own context.
// must not dominate it.
const toolCallDetailBytes = 300
func ClipToolCallDetail(s string) string {
if len(s) <= toolCallDetailBytes {
return s
}
return s[:toolCallDetailBytes] + "…"
cut := toolCallDetailBytes
for cut > 0 && !utf8.RuneStart(s[cut]) {
cut--
}
return s[:cut] + "…"
}
func ProjectScopedRules(workspace, extra string) string {
+45
View File
@@ -0,0 +1,45 @@
package modelloop
import (
"fmt"
"strings"
"github.com/samcharles93/archie-core/internal/domain/agentrun"
)
// missionWithHistory puts the conversation of an earlier run of the stage
// ahead of the mission, cut to fit the model's context window. agentloop has no
// field for prior messages, so the conversation goes in the first user message
// as text.
func missionWithHistory(req agentrun.Request) string {
entries := agentrun.BoundHistory(req.History, agentrun.HistoryBytes(req.ContextWindow))
if len(entries) == 0 {
return req.Mission
}
var b strings.Builder
b.WriteString("<previous_run>\nAn earlier run of this stage stopped at its step budget and was approved to continue. " +
"Its conversation follows and its edits are already in the worktree. Continue from where it stopped; do not start over.\n\n")
for _, e := range entries {
switch e.Kind {
case agentrun.TranscriptModel:
if e.Text != "" {
fmt.Fprintf(&b, "[you] %s\n", e.Text)
}
for _, call := range e.ToolCalls {
fmt.Fprintf(&b, "[you called %s] %s\n", call.Name, call.Args)
}
case agentrun.TranscriptTool:
if e.Error != "" {
fmt.Fprintf(&b, "[%s failed] %s\n", e.Tool, e.Error)
} else {
fmt.Fprintf(&b, "[%s returned] %s\n", e.Tool, e.Output)
}
case agentrun.TranscriptUser:
fmt.Fprintf(&b, "[feedback] %s\n", e.Text)
case agentrun.TranscriptCompaction:
fmt.Fprintf(&b, "[summary of earlier steps] %s\n", e.Text)
}
}
b.WriteString("</previous_run>\n\n")
return b.String() + req.Mission
}
+12 -4
View File
@@ -53,7 +53,7 @@ func NewLoopRunner(
// work on the chat workspace and bypass ReadOnly and ProtectPaths.
const workspaceToolset = "workspace"
func (r *LoopRunner) Run(ctx context.Context, workspace string, req agentrun.Request, report agentrun.ToolCallReporter) (agentrun.Result, error) {
func (r *LoopRunner) Run(ctx context.Context, workspace string, req agentrun.Request, report agentrun.Reporter) (agentrun.Result, error) {
if err := req.Validate(); err != nil {
return agentrun.Result{}, err
}
@@ -67,19 +67,25 @@ func (r *LoopRunner) Run(ctx context.Context, workspace string, req agentrun.Req
notes := &memoryNotes{initial: req.Notes}
captures := make(map[string][]json.RawMessage)
toolOpts := r.Limits.Options(workspaceToolset)
toolOpts.OnToolCall = report
toolOpts.OnToolCall = report.ToolCall
centralTools, err := BuildToolSet(r.tools, toolOpts)
if err != nil {
return agentrun.Result{}, fmt.Errorf("build central tool set: %w", err)
}
captureTools := captureToolSet(req.CaptureTools, captures)
var modelHooks []core.ModelHook
var toolHooks []core.ToolHook
if report.Transcript != nil {
recorder := newTranscript(report.Transcript)
modelHooks, toolHooks = []core.ModelHook{recorder}, []core.ToolHook{recorder}
}
res, err := r.run(ctx, agentloop.Config{
Runtime: r.runtime,
ModelRef: req.Model,
WorkDir: workspace,
MaxParallelToolCalls: MaxParallelToolCalls,
Mission: req.Mission,
Mission: missionWithHistory(req),
ExtraRules: agentexec.ProjectScopedRules(workspace, req.ExtraRules),
Notes: notes,
Gate: toAgentGate(req.Gate),
@@ -101,7 +107,9 @@ func (r *LoopRunner) Run(ctx context.Context, workspace string, req agentrun.Req
allowedTools(centralTools, r.AllowTools),
captureTools,
),
Logger: r.logger(req),
ModelHooks: modelHooks,
ToolHooks: toolHooks,
Logger: r.logger(req),
})
result := resultFromRun(req, res, notes.appended, captures)
if cause := context.Cause(ctx); cause != nil {
+7 -13
View File
@@ -36,24 +36,22 @@ func (l ToolLimits) EnsureSpillDir() error {
return nil
}
// Options builds the tool-set options for a single turn or stage.
// There is no aggregate turn output budget; only per-result caps apply.
// Options builds the tool-set options for a single turn or stage. Only
// per-result caps apply; there is no aggregate turn output budget.
func (l ToolLimits) Options(excludeToolsets ...string) ToolSetOptions {
opts := ToolSetOptions{
return ToolSetOptions{
MaxResultChars: l.MaxResultChars,
ExcludeToolsets: excludeToolsets,
SpillDir: l.SpillDir,
}
return opts
}
// ToolSetOptions bounds what a built tool set may do and return.
//
// The zero value builds every available tool with no result limits, which is
// the behaviour this package had before the options existed.
// The zero value builds every available tool with no result limits.
type ToolSetOptions struct {
// SpillDir receives complete results displaced by the per-tool cap. Empty
// selects inline truncation. There is deliberately no aggregate turn cap.
// selects inline truncation.
SpillDir string
// MaxResultChars caps a single tool result. Entries setting
@@ -74,12 +72,11 @@ type ToolSetOptions struct {
// OnToolCall, when non-nil, is notified once per completed tool call.
// LoopRunner populates it so a workflow stage can surface tool activity on
// the task timeline. Nil means no one is listening.
OnToolCall agentrun.ToolCallReporter
OnToolCall func(agentrun.ToolCallReport)
}
// reportToolCallCompletion notifies opts.OnToolCall, if set, of one
// completed call. Factored out of toolExecute's closure so the branching
// here doesn't add to that function's own cognitive-complexity budget.
// completed call.
func reportToolCallCompletion(opts ToolSetOptions, entry tools.ToolEntry, result string, err error) {
if opts.OnToolCall == nil {
return
@@ -241,9 +238,6 @@ func toolExecute(entry tools.ToolEntry, opts ToolSetOptions) func(context.Contex
// requireApproval blocks until entry's approval is granted, returning an
// error if it is denied, times out, or the approver misbehaves.
func requireApproval(ctx context.Context, entry tools.ToolEntry, opts ToolSetOptions, args map[string]any) error {
if opts.Approval == nil {
return fmt.Errorf("tool %s requires approval but no approver is configured", entry.Name)
}
approveCtx, cancel := context.WithTimeout(ctx, tools.ToolApprovalTimeout)
defer cancel()
desc := entry.Description
+187
View File
@@ -0,0 +1,187 @@
package modelloop
import (
"context"
"encoding/json"
"strings"
"sync"
"time"
"unicode/utf8"
"github.com/samcharles93/ai-sdk/chat"
"github.com/samcharles93/ai-sdk/core"
"github.com/samcharles93/archie-core/internal/domain/agentrun"
"github.com/samcharles93/archie-core/internal/webhookguard"
)
// transcriptFieldLimit caps each recorded text field, in bytes.
const transcriptFieldLimit = 32 << 10
// compactionPrefix starts the instruction agentloop sends to summarise the
// history, which marks a model call as a compaction rather than a step.
const compactionPrefix = "Compact the conversation history above"
// transcript records one agent run's conversation through agentloop's model
// and tool hooks. Tool hooks run concurrently, so entries are numbered and
// reported under one lock to keep their order.
type transcript struct {
report func(agentrun.TranscriptEntry)
mu sync.Mutex
seq int
prompted bool
lastUser string
started map[string]time.Time
}
func newTranscript(report func(agentrun.TranscriptEntry)) *transcript {
return &transcript{report: report, started: map[string]time.Time{}}
}
func (t *transcript) add(entry agentrun.TranscriptEntry) {
t.seq++
entry.Seq = t.seq
t.report(entry)
}
func (t *transcript) ModelCallStarted(context.Context, chat.Request) {}
func (t *transcript) ModelCallFinished(_ context.Context, req chat.Request, resp *chat.Response, err error, latency time.Duration, usage *chat.Usage) {
t.mu.Lock()
defer t.mu.Unlock()
entry := agentrun.TranscriptEntry{Kind: agentrun.TranscriptModel, LatencyMS: latency.Milliseconds(), Usage: transcriptUsage(usage)}
if isCompaction(req) {
entry.Kind = agentrun.TranscriptCompaction
} else {
t.recordInput(req.Messages)
}
if err != nil {
entry.Error = clip(err.Error(), nil)
}
if resp != nil {
entry.Text = clip(resp.Content, &entry.TextBytes)
entry.Reasoning = clip(reasoning(resp.Parts), &entry.ReasoningBytes)
entry.FinishReason = resp.FinishReason
for _, call := range resp.ToolCalls {
recorded := agentrun.TranscriptToolCall{ID: call.ID, Name: call.Name}
recorded.Args = clipArgs(call.Arguments, &recorded.ArgsBytes)
entry.ToolCalls = append(entry.ToolCalls, recorded)
}
}
t.add(entry)
}
// recordInput records the prompt on the first call, and after that each user
// message the loop appended since the model last answered: gate feedback,
// recovery nudges. Assistant and tool messages are recorded from the response
// and the tool hooks instead.
func (t *transcript) recordInput(messages []chat.Message) {
if !t.prompted {
t.prompted = true
for _, message := range messages {
t.recordMessage(message)
}
return
}
start := len(messages)
for start > 0 && messages[start-1].Role == chat.RoleUser {
start--
}
for _, message := range messages[start:] {
if message.Content != t.lastUser {
t.recordMessage(message)
}
}
}
func (t *transcript) recordMessage(message chat.Message) {
kind := agentrun.TranscriptUser
switch message.Role {
case chat.RoleSystem:
kind = agentrun.TranscriptSystem
case chat.RoleUser:
t.lastUser = message.Content
default:
return
}
entry := agentrun.TranscriptEntry{Kind: kind}
entry.Text = clip(message.Content, &entry.TextBytes)
t.add(entry)
}
func (t *transcript) BeforeToolExecute(_ context.Context, call *core.ToolCall) (*core.Skip, error) {
t.mu.Lock()
t.started[call.ToolCallID] = time.Now()
t.mu.Unlock()
return nil, nil
}
func (t *transcript) AfterToolExecute(_ context.Context, call core.ToolCall, result *core.ToolResult) {
t.mu.Lock()
defer t.mu.Unlock()
entry := agentrun.TranscriptEntry{Kind: agentrun.TranscriptTool, CallID: call.ToolCallID, Tool: call.ToolName}
if started, ok := t.started[call.ToolCallID]; ok {
entry.LatencyMS = time.Since(started).Milliseconds()
delete(t.started, call.ToolCallID)
}
entry.Args = clipArgs(call.Input, &entry.ArgsBytes)
entry.Output = clip(result.Output, &entry.OutputBytes)
entry.Error = clip(result.Error, nil)
t.add(entry)
}
func reasoning(parts chat.Parts) string {
var texts []string
for _, part := range parts {
if thought, ok := part.(chat.ReasoningPart); ok && thought.Text != "" {
texts = append(texts, thought.Text)
}
}
return strings.Join(texts, "\n\n")
}
func isCompaction(req chat.Request) bool {
n := len(req.Messages)
return n > 0 && req.Messages[n-1].Role == chat.RoleUser && strings.HasPrefix(req.Messages[n-1].Content, compactionPrefix)
}
func transcriptUsage(usage *chat.Usage) *agentrun.Usage {
if usage == nil {
return nil
}
return &agentrun.Usage{
PromptTokens: usage.PromptTokens,
CompletionTokens: usage.CompletionTokens,
TotalTokens: usage.TotalTokens,
CachedTokens: usage.CachedTokens,
CacheCreationTokens: usage.CacheCreationTokens,
}
}
// clipArgs redacts tool arguments by key when they are JSON, then clips them.
func clipArgs(args string, full *int) string {
if json.Valid([]byte(args)) {
if redacted, err := webhookguard.RedactPayload([]byte(args)); err == nil {
args = string(redacted)
}
}
return clip(args, full)
}
// clip redacts secret-shaped spans and cuts text to transcriptFieldLimit on a
// rune boundary, storing the original size in full when it cuts.
func clip(text string, full *int) string {
text = webhookguard.RedactText(text)
if len(text) <= transcriptFieldLimit {
return text
}
if full != nil {
*full = len(text)
}
cut := transcriptFieldLimit
for cut > 0 && !utf8.RuneStart(text[cut]) {
cut--
}
return text[:cut]
}
@@ -0,0 +1,71 @@
package modelloop
import (
"strings"
"testing"
"github.com/samcharles93/ai-sdk/core"
"github.com/samcharles93/archie-core/internal/domain/agentrun"
)
func TestTranscriptToolEntryRedactsAndClips(t *testing.T) {
const jwt = "eyJhbGciOiJIUzI1NiJ9.eyJzdWIiOiJhcmNoaWUifQ.c2lnbmF0dXJlc2lnbmF0dXJl"
const pem = "-----BEGIN RSA PRIVATE KEY-----\nMIIEow\n-----END RSA PRIVATE KEY-----"
long := strings.Repeat("x", transcriptFieldLimit+10)
tests := []struct {
name string
input string
output string
wantArgs string
wantOutput string
wantBytes int
}{
{
name: "secret key in arguments, token inside output",
input: `{"path":"a.txt","api_key":"plain-value"}`,
output: "curl -H 'Authorization: Bearer " + jwt + "' done",
wantArgs: `{"api_key":"[redacted]","path":"a.txt"}`,
wantOutput: "curl -H 'Authorization: Bearer [redacted]' done",
},
{
name: "private key block inside output",
input: `{}`,
output: "before\n" + pem + "\nafter",
wantArgs: `{}`,
wantOutput: "before\n[redacted]\nafter",
},
{
name: "oversized output keeps its full size",
input: `{}`,
output: long,
wantArgs: `{}`,
wantOutput: long[:transcriptFieldLimit],
wantBytes: len(long),
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
var got []agentrun.TranscriptEntry
recorder := newTranscript(func(entry agentrun.TranscriptEntry) { got = append(got, entry) })
call := core.ToolCall{ToolCallID: "c1", ToolName: "shell", Input: tt.input}
if _, err := recorder.BeforeToolExecute(t.Context(), &call); err != nil {
t.Fatal(err)
}
recorder.AfterToolExecute(t.Context(), call, &core.ToolResult{Output: tt.output})
if len(got) != 1 {
t.Fatalf("entries = %d, want 1", len(got))
}
entry := got[0]
if entry.Args != tt.wantArgs {
t.Errorf("args = %q, want %q", entry.Args, tt.wantArgs)
}
if entry.Output != tt.wantOutput {
t.Errorf("output = %q, want %q", entry.Output, tt.wantOutput)
}
if entry.OutputBytes != tt.wantBytes {
t.Errorf("output bytes = %d, want %d", entry.OutputBytes, tt.wantBytes)
}
})
}
}
+4 -3
View File
@@ -1,6 +1,7 @@
package agentexec
import (
"context"
"encoding/json"
"log/slog"
@@ -14,16 +15,16 @@ type EventPublisher interface {
// ForwardTaskEvents publishes every event from sub to SubjectForEvents(taskID)
// until sub closes. Failures are logged.
func ForwardTaskEvents(sub *events.Sub, pub EventPublisher, taskID int64, log *slog.Logger) {
func ForwardTaskEvents(ctx context.Context, sub *events.Sub, pub EventPublisher, taskID int64, log *slog.Logger) {
subject := SubjectForEvents(taskID)
for e := range sub.C {
data, err := json.Marshal(e)
if err != nil {
log.Warn("task event marshal failed", "task", taskID, "kind", e.Kind, "err", err)
log.WarnContext(ctx, "task event marshal failed", "task", taskID, "kind", e.Kind, "err", err)
continue
}
if err := pub.Publish(subject, data); err != nil {
log.Warn("task event publish failed", "task", taskID, "kind", e.Kind, "err", err)
log.WarnContext(ctx, "task event publish failed", "task", taskID, "kind", e.Kind, "err", err)
}
}
}
@@ -1,15 +0,0 @@
{"type": "system", "subtype": "hook_started", "hook_id": "3364ed13-2659-4abb-bda4-58243f1eb065", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "uuid": "959d5b3d-d376-4416-9abb-71e0b8a36047", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_started", "hook_id": "4c58406e-b5f0-49d7-af88-483c14212e0d", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "uuid": "1f5ed274-0baa-4558-b00f-36ef98d28ebc", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_started", "hook_id": "04acf4c4-0c8d-4dd5-9d3a-a7a6df371224", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "uuid": "5aa154a9-9315-4a6c-8de0-750cb35139cf", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_started", "hook_id": "a0cb320b-0bdd-45b5-90b5-451add28d1ed", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "uuid": "ef74547a-736e-4bb9-bd68-16cc1592b2a3", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_response", "hook_id": "3364ed13-2659-4abb-bda4-58243f1eb065", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "398b087e-942b-4d67-904c-1778d3b20063", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_response", "hook_id": "04acf4c4-0c8d-4dd5-9d3a-a7a6df371224", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "ecbfdcf2-446c-4386-a89f-eeaf43e48b46", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_response", "hook_id": "4c58406e-b5f0-49d7-af88-483c14212e0d", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "c10b3042-e990-49db-8937-954b6fe11570", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_response", "hook_id": "a0cb320b-0bdd-45b5-90b5-451add28d1ed", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "3a3327f8-ad24-46d7-a194-e0ce68f9f871", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "init", "cwd": "/workspace", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "tools": ["Task", "Bash", "Edit", "Read", "Write"], "mcp_servers": [], "model": "claude-opus-5-5", "permissionMode": "bypassPermissions", "slash_commands": [], "terminal_slash_commands": [], "apiKeySource": "none", "claude_code_version": "2.1.282", "output_style": "default", "agents": [], "skills": [], "plugins": [], "capabilities": ["interrupt_receipt_v1", "interrupt_cancel_queued_v1", "msg_lifecycle_v1", "mcp_read_resource_v1", "mcp_tool_ui_meta_v1"], "analytics_disabled": false, "product_feedback_disabled": false, "uuid": "0ad7c54e-a817-406b-af22-8f647b4e0021", "memory_paths": {}, "messaging_socket_path": "", "fast_mode_state": "off", "fast_mode_disabled_reason": "sdk_opt_in_required", "per_turn_effort_active": true, "view_mode": "default"}
{"type": "assistant", "message": {"model": "claude-opus-5-5", "id": "msg_011CfQYZ2iQ3sZ59vJ9CCae9", "type": "message", "role": "assistant", "content": [{"type": "tool_use", "id": "toolu_01P8qrSZwqH1jjZXfrZETjKz", "name": "Bash", "input": {"command": "echo hello", "description": "Print hello"}, "caller": {"type": "direct"}}], "container": null, "stop_reason": null, "stop_sequence": null, "stop_details": null, "usage": {"input_tokens": 2, "cache_creation_input_tokens": 23584, "cache_read_input_tokens": 10119, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 23584}, "output_tokens": 16, "service_tier": "standard", "inference_geo": "not_available"}, "input_transformations": [], "diagnostics": null, "context_management": null}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "b4c3b51e-0a58-4b28-8c5a-20a2ff2aaadb", "timestamp": "2026-09-25T17:22:54.134Z", "request_id": "req_011CfQYZ2Ddp5YubZj8vB9Fb", "wire_tool_inputs": {"toolu_01P8qrSZwqH1jjZXfrZETjKz": {"command": "echo hello", "description": "Print hello"}}}
{"type": "rate_limit_event", "rate_limit_info": {"status": "allowed_warning", "resetsAt": 1790377200, "rateLimitType": "seven_day", "utilization": 0.98, "isUsingOverage": false, "surpassedThreshold": 0.75, "unifiedWindows": {"five_hour": {"utilization": 0.76, "resetsAt": 1790366400}, "seven_day": {"utilization": 0.98, "resetsAt": 1790377200}}}, "uuid": "a91b2340-329e-4c73-8e1a-307860859743", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "user", "message": {"role": "user", "content": [{"tool_use_id": "toolu_01P8qrSZwqH1jjZXfrZETjKz", "type": "tool_result", "content": "hello", "is_error": false}]}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "6beae671-52a0-499a-b72b-f9321c1d9e14", "timestamp": "2026-09-25T17:22:54.460Z", "tool_use_result": {"stdout": "hello", "stderr": "", "interrupted": false, "isImage": false, "noOutputExpected": false}}
{"type": "assistant", "message": {"model": "claude-opus-5-5", "id": "msg_011CfQYZHW9AJ164FSYj39uG", "type": "message", "role": "assistant", "content": [{"type": "tool_use", "id": "toolu_01YNNETbc61jN44ATXrmHdEC", "name": "Bash", "input": {"command": "cat /nonexistent-file", "description": "Read a nonexistent file"}, "caller": {"type": "direct"}}], "container": null, "stop_reason": null, "stop_sequence": null, "stop_details": null, "usage": {"input_tokens": 2, "cache_creation_input_tokens": 580, "cache_read_input_tokens": 33703, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 580}, "output_tokens": 16, "service_tier": "standard", "inference_geo": "not_available"}, "input_transformations": [], "diagnostics": null, "context_management": null}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "3b14941d-c8eb-45f4-b555-829e06119f19", "timestamp": "2026-09-25T17:22:56.420Z", "request_id": "req_011CfQYZH18nwJgBYNZs8XGq", "wire_tool_inputs": {"toolu_01YNNETbc61jN44ATXrmHdEC": {"command": "cat /nonexistent-file", "description": "Read a nonexistent file"}}}
{"type": "user", "message": {"role": "user", "content": [{"type": "tool_result", "content": "Exit code 1\ncat: /nonexistent-file: No such file or directory", "is_error": true, "tool_use_id": "toolu_01YNNETbc61jN44ATXrmHdEC"}]}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "395dc93d-0e4f-40b5-854b-77a128aa0990", "timestamp": "2026-09-25T17:22:56.442Z", "tool_use_result": "Error: Exit code 1\ncat: /nonexistent-file: No such file or directory"}
{"type": "assistant", "message": {"model": "claude-opus-5-5", "id": "msg_011CfQYZRy8qPUaVcnVs9CQD", "type": "message", "role": "assistant", "content": [{"type": "text", "text": "done\n\nThe first command printed `hello`. The second failed with \"No such file or directory\".\n\nGoogle Drive, exa and intercom still need authorizing. Google Drive is set up in its claude.ai connector settings. For exa and intercom, run `/mcp` in an interactive session."}], "container": null, "stop_reason": null, "stop_sequence": null, "stop_details": null, "usage": {"input_tokens": 2, "cache_creation_input_tokens": 145, "cache_read_input_tokens": 34283, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 145}, "output_tokens": 89, "service_tier": "standard", "inference_geo": "not_available"}, "input_transformations": [], "diagnostics": null, "context_management": null}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "8f97a329-c76c-4b90-b154-bda9468b969d", "timestamp": "2026-09-25T17:22:58.580Z", "request_id": "req_011CfQYZRSdq9mNMbE7n8okT"}
-17
View File
@@ -1,17 +0,0 @@
{"type": "system", "subtype": "hook_started", "hook_id": "3364ed13-2659-4abb-bda4-58243f1eb065", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "uuid": "959d5b3d-d376-4416-9abb-71e0b8a36047", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_started", "hook_id": "4c58406e-b5f0-49d7-af88-483c14212e0d", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "uuid": "1f5ed274-0baa-4558-b00f-36ef98d28ebc", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_started", "hook_id": "04acf4c4-0c8d-4dd5-9d3a-a7a6df371224", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "uuid": "5aa154a9-9315-4a6c-8de0-750cb35139cf", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_started", "hook_id": "a0cb320b-0bdd-45b5-90b5-451add28d1ed", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "uuid": "ef74547a-736e-4bb9-bd68-16cc1592b2a3", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_response", "hook_id": "3364ed13-2659-4abb-bda4-58243f1eb065", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "398b087e-942b-4d67-904c-1778d3b20063", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_response", "hook_id": "04acf4c4-0c8d-4dd5-9d3a-a7a6df371224", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "ecbfdcf2-446c-4386-a89f-eeaf43e48b46", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_response", "hook_id": "4c58406e-b5f0-49d7-af88-483c14212e0d", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "c10b3042-e990-49db-8937-954b6fe11570", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_response", "hook_id": "a0cb320b-0bdd-45b5-90b5-451add28d1ed", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "3a3327f8-ad24-46d7-a194-e0ce68f9f871", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "init", "cwd": "/workspace", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "tools": ["Task", "Bash", "Edit", "Read", "Write"], "mcp_servers": [], "model": "claude-opus-5-5", "permissionMode": "bypassPermissions", "slash_commands": [], "terminal_slash_commands": [], "apiKeySource": "none", "claude_code_version": "2.1.282", "output_style": "default", "agents": [], "skills": [], "plugins": [], "capabilities": ["interrupt_receipt_v1", "interrupt_cancel_queued_v1", "msg_lifecycle_v1", "mcp_read_resource_v1", "mcp_tool_ui_meta_v1"], "analytics_disabled": false, "product_feedback_disabled": false, "uuid": "0ad7c54e-a817-406b-af22-8f647b4e0021", "memory_paths": {}, "messaging_socket_path": "", "fast_mode_state": "off", "fast_mode_disabled_reason": "sdk_opt_in_required", "per_turn_effort_active": true, "view_mode": "default"}
{"type": "assistant", "message": {"model": "claude-opus-5-5", "id": "msg_011CfQYZ2iQ3sZ59vJ9CCae9", "type": "message", "role": "assistant", "content": [{"type": "tool_use", "id": "toolu_01P8qrSZwqH1jjZXfrZETjKz", "name": "Bash", "input": {"command": "echo hello", "description": "Print hello"}, "caller": {"type": "direct"}}], "container": null, "stop_reason": null, "stop_sequence": null, "stop_details": null, "usage": {"input_tokens": 2, "cache_creation_input_tokens": 23584, "cache_read_input_tokens": 10119, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 23584}, "output_tokens": 16, "service_tier": "standard", "inference_geo": "not_available"}, "input_transformations": [], "diagnostics": null, "context_management": null}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "b4c3b51e-0a58-4b28-8c5a-20a2ff2aaadb", "timestamp": "2026-09-25T17:22:54.134Z", "request_id": "req_011CfQYZ2Ddp5YubZj8vB9Fb", "wire_tool_inputs": {"toolu_01P8qrSZwqH1jjZXfrZETjKz": {"command": "echo hello", "description": "Print hello"}}}
{"type":"assistant","message":{"content":[{"type":"tool_use"
{"type": "rate_limit_event", "rate_limit_info": {"status": "allowed_warning", "resetsAt": 1790377200, "rateLimitType": "seven_day", "utilization": 0.98, "isUsingOverage": false, "surpassedThreshold": 0.75, "unifiedWindows": {"five_hour": {"utilization": 0.76, "resetsAt": 1790366400}, "seven_day": {"utilization": 0.98, "resetsAt": 1790377200}}}, "uuid": "a91b2340-329e-4c73-8e1a-307860859743", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "user", "message": {"role": "user", "content": [{"tool_use_id": "toolu_01P8qrSZwqH1jjZXfrZETjKz", "type": "tool_result", "content": "hello", "is_error": false}]}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "6beae671-52a0-499a-b72b-f9321c1d9e14", "timestamp": "2026-09-25T17:22:54.460Z", "tool_use_result": {"stdout": "hello", "stderr": "", "interrupted": false, "isImage": false, "noOutputExpected": false}}
{"type": "assistant", "message": {"model": "claude-opus-5-5", "id": "msg_011CfQYZHW9AJ164FSYj39uG", "type": "message", "role": "assistant", "content": [{"type": "tool_use", "id": "toolu_01YNNETbc61jN44ATXrmHdEC", "name": "Bash", "input": {"command": "cat /nonexistent-file", "description": "Read a nonexistent file"}, "caller": {"type": "direct"}}], "container": null, "stop_reason": null, "stop_sequence": null, "stop_details": null, "usage": {"input_tokens": 2, "cache_creation_input_tokens": 580, "cache_read_input_tokens": 33703, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 580}, "output_tokens": 16, "service_tier": "standard", "inference_geo": "not_available"}, "input_transformations": [], "diagnostics": null, "context_management": null}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "3b14941d-c8eb-45f4-b555-829e06119f19", "timestamp": "2026-09-25T17:22:56.420Z", "request_id": "req_011CfQYZH18nwJgBYNZs8XGq", "wire_tool_inputs": {"toolu_01YNNETbc61jN44ATXrmHdEC": {"command": "cat /nonexistent-file", "description": "Read a nonexistent file"}}}
{"type": "user", "message": {"role": "user", "content": [{"type": "tool_result", "content": "Exit code 1\ncat: /nonexistent-file: No such file or directory", "is_error": true, "tool_use_id": "toolu_01YNNETbc61jN44ATXrmHdEC"}]}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "395dc93d-0e4f-40b5-854b-77a128aa0990", "timestamp": "2026-09-25T17:22:56.442Z", "tool_use_result": "Error: Exit code 1\ncat: /nonexistent-file: No such file or directory"}
{"type": "assistant", "message": {"model": "claude-opus-5-5", "id": "msg_011CfQYZRy8qPUaVcnVs9CQD", "type": "message", "role": "assistant", "content": [{"type": "text", "text": "done\n\nThe first command printed `hello`. The second failed with \"No such file or directory\".\n\nGoogle Drive, exa and intercom still need authorizing. Google Drive is set up in its claude.ai connector settings. For exa and intercom, run `/mcp` in an interactive session."}], "container": null, "stop_reason": null, "stop_sequence": null, "stop_details": null, "usage": {"input_tokens": 2, "cache_creation_input_tokens": 145, "cache_read_input_tokens": 34283, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 145}, "output_tokens": 89, "service_tier": "standard", "inference_geo": "not_available"}, "input_transformations": [], "diagnostics": null, "context_management": null}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "8f97a329-c76c-4b90-b154-bda9468b969d", "timestamp": "2026-09-25T17:22:58.580Z", "request_id": "req_011CfQYZRSdq9mNMbE7n8okT"}
{"duration_api_ms": 7263, "stop_reason": "end_turn", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "total_cost_usd": 0.21507700000000002, "usage": {"input_tokens": 6, "cache_creation_input_tokens": 24309, "cache_read_input_tokens": 78105, "output_tokens": 248, "output_tokens_details": {"thinking_tokens": 0}, "server_tool_use": {"web_search_requests": 0, "web_fetch_requests": 0}, "service_tier": "standard", "cache_creation": {"ephemeral_1h_input_tokens": 24309, "ephemeral_5m_input_tokens": 0}, "inference_geo": "not_available", "iterations": [{"input_tokens": 2, "output_tokens": 89, "cache_read_input_tokens": 34283, "cache_creation_input_tokens": 145, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 145}, "type": "message"}], "speed": "standard"}, "modelUsage": {"claude-opus-5-5": {"inputTokens": 6, "outputTokens": 248, "cacheReadInputTokens": 78105, "cacheCreationInputTokens": 24309, "webSearchRequests": 0, "costUSD": 0.21507700000000002, "contextWindow": 1000000, "maxOutputTokens": 128000, "thinkingTokens": 0, "canonicalModel": "claude-opus-5-5", "provider": "firstParty", "costBasis": "list"}}, "permission_denials": [], "terminal_reason": "completed", "fast_mode_state": "off", "fast_mode_disabled_reason": "sdk_opt_in_required", "subagent_stats": {"spawned": 0, "requested": {"background": 0, "foreground": 0, "unset": 0}, "started_in_background": 0, "max_depth": 0, "spawned_by_subagents": 0, "completed": 0, "failed": 0, "killed": {"parent": 0, "user": 0, "system": 0}, "refused": {"depth_limit": 0, "concurrency_limit": 0, "budget": 0}, "by_type": {}}, "is_error": false, "num_turns": 3, "subtype": "success", "api_error_status": null, "result": "done\n\nThe first command printed `hello`. The second failed with \"No such file or directory\".\n\nGoogle Drive, exa and intercom still need authorizing. Google Drive is set up in its claude.ai connector settings. For exa and intercom, run `/mcp` in an interactive session.", "ttft_ms": 3229, "type": "result", "duration_ms": 7717, "uuid": "d0b46ba2-f8ff-49eb-b35e-b4eb6b9b272b", "ttft_stream_ms": 2833, "time_to_request_ms": 102, "first_content_frame_ms": 2834, "queued_turn_count": 0, "result_index": 0}
-16
View File
@@ -1,16 +0,0 @@
{"type": "system", "subtype": "hook_started", "hook_id": "3364ed13-2659-4abb-bda4-58243f1eb065", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "uuid": "959d5b3d-d376-4416-9abb-71e0b8a36047", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_started", "hook_id": "4c58406e-b5f0-49d7-af88-483c14212e0d", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "uuid": "1f5ed274-0baa-4558-b00f-36ef98d28ebc", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_started", "hook_id": "04acf4c4-0c8d-4dd5-9d3a-a7a6df371224", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "uuid": "5aa154a9-9315-4a6c-8de0-750cb35139cf", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_started", "hook_id": "a0cb320b-0bdd-45b5-90b5-451add28d1ed", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "uuid": "ef74547a-736e-4bb9-bd68-16cc1592b2a3", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_response", "hook_id": "3364ed13-2659-4abb-bda4-58243f1eb065", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "398b087e-942b-4d67-904c-1778d3b20063", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_response", "hook_id": "04acf4c4-0c8d-4dd5-9d3a-a7a6df371224", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "ecbfdcf2-446c-4386-a89f-eeaf43e48b46", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_response", "hook_id": "4c58406e-b5f0-49d7-af88-483c14212e0d", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "c10b3042-e990-49db-8937-954b6fe11570", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "hook_response", "hook_id": "a0cb320b-0bdd-45b5-90b5-451add28d1ed", "hook_name": "SessionStart:startup", "hook_event": "SessionStart", "output": "", "stdout": "", "stderr": "", "exit_code": 0, "outcome": "success", "uuid": "3a3327f8-ad24-46d7-a194-e0ce68f9f871", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "system", "subtype": "init", "cwd": "/workspace", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "tools": ["Task", "Bash", "Edit", "Read", "Write"], "mcp_servers": [], "model": "claude-opus-5-5", "permissionMode": "bypassPermissions", "slash_commands": [], "terminal_slash_commands": [], "apiKeySource": "none", "claude_code_version": "2.1.282", "output_style": "default", "agents": [], "skills": [], "plugins": [], "capabilities": ["interrupt_receipt_v1", "interrupt_cancel_queued_v1", "msg_lifecycle_v1", "mcp_read_resource_v1", "mcp_tool_ui_meta_v1"], "analytics_disabled": false, "product_feedback_disabled": false, "uuid": "0ad7c54e-a817-406b-af22-8f647b4e0021", "memory_paths": {}, "messaging_socket_path": "", "fast_mode_state": "off", "fast_mode_disabled_reason": "sdk_opt_in_required", "per_turn_effort_active": true, "view_mode": "default"}
{"type": "assistant", "message": {"model": "claude-opus-5-5", "id": "msg_011CfQYZ2iQ3sZ59vJ9CCae9", "type": "message", "role": "assistant", "content": [{"type": "tool_use", "id": "toolu_01P8qrSZwqH1jjZXfrZETjKz", "name": "Bash", "input": {"command": "echo hello", "description": "Print hello"}, "caller": {"type": "direct"}}], "container": null, "stop_reason": null, "stop_sequence": null, "stop_details": null, "usage": {"input_tokens": 2, "cache_creation_input_tokens": 23584, "cache_read_input_tokens": 10119, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 23584}, "output_tokens": 16, "service_tier": "standard", "inference_geo": "not_available"}, "input_transformations": [], "diagnostics": null, "context_management": null}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "b4c3b51e-0a58-4b28-8c5a-20a2ff2aaadb", "timestamp": "2026-09-25T17:22:54.134Z", "request_id": "req_011CfQYZ2Ddp5YubZj8vB9Fb", "wire_tool_inputs": {"toolu_01P8qrSZwqH1jjZXfrZETjKz": {"command": "echo hello", "description": "Print hello"}}}
{"type": "rate_limit_event", "rate_limit_info": {"status": "allowed_warning", "resetsAt": 1790377200, "rateLimitType": "seven_day", "utilization": 0.98, "isUsingOverage": false, "surpassedThreshold": 0.75, "unifiedWindows": {"five_hour": {"utilization": 0.76, "resetsAt": 1790366400}, "seven_day": {"utilization": 0.98, "resetsAt": 1790377200}}}, "uuid": "a91b2340-329e-4c73-8e1a-307860859743", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92"}
{"type": "user", "message": {"role": "user", "content": [{"tool_use_id": "toolu_01P8qrSZwqH1jjZXfrZETjKz", "type": "tool_result", "content": "hello", "is_error": false}]}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "6beae671-52a0-499a-b72b-f9321c1d9e14", "timestamp": "2026-09-25T17:22:54.460Z", "tool_use_result": {"stdout": "hello", "stderr": "", "interrupted": false, "isImage": false, "noOutputExpected": false}}
{"type": "assistant", "message": {"model": "claude-opus-5-5", "id": "msg_011CfQYZHW9AJ164FSYj39uG", "type": "message", "role": "assistant", "content": [{"type": "tool_use", "id": "toolu_01YNNETbc61jN44ATXrmHdEC", "name": "Bash", "input": {"command": "cat /nonexistent-file", "description": "Read a nonexistent file"}, "caller": {"type": "direct"}}], "container": null, "stop_reason": null, "stop_sequence": null, "stop_details": null, "usage": {"input_tokens": 2, "cache_creation_input_tokens": 580, "cache_read_input_tokens": 33703, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 580}, "output_tokens": 16, "service_tier": "standard", "inference_geo": "not_available"}, "input_transformations": [], "diagnostics": null, "context_management": null}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "3b14941d-c8eb-45f4-b555-829e06119f19", "timestamp": "2026-09-25T17:22:56.420Z", "request_id": "req_011CfQYZH18nwJgBYNZs8XGq", "wire_tool_inputs": {"toolu_01YNNETbc61jN44ATXrmHdEC": {"command": "cat /nonexistent-file", "description": "Read a nonexistent file"}}}
{"type": "user", "message": {"role": "user", "content": [{"type": "tool_result", "content": "Exit code 1\ncat: /nonexistent-file: No such file or directory", "is_error": true, "tool_use_id": "toolu_01YNNETbc61jN44ATXrmHdEC"}]}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "395dc93d-0e4f-40b5-854b-77a128aa0990", "timestamp": "2026-09-25T17:22:56.442Z", "tool_use_result": "Error: Exit code 1\ncat: /nonexistent-file: No such file or directory"}
{"type": "assistant", "message": {"model": "claude-opus-5-5", "id": "msg_011CfQYZRy8qPUaVcnVs9CQD", "type": "message", "role": "assistant", "content": [{"type": "text", "text": "done\n\nThe first command printed `hello`. The second failed with \"No such file or directory\".\n\nGoogle Drive, exa and intercom still need authorizing. Google Drive is set up in its claude.ai connector settings. For exa and intercom, run `/mcp` in an interactive session."}], "container": null, "stop_reason": null, "stop_sequence": null, "stop_details": null, "usage": {"input_tokens": 2, "cache_creation_input_tokens": 145, "cache_read_input_tokens": 34283, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 145}, "output_tokens": 89, "service_tier": "standard", "inference_geo": "not_available"}, "input_transformations": [], "diagnostics": null, "context_management": null}, "parent_tool_use_id": null, "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "uuid": "8f97a329-c76c-4b90-b154-bda9468b969d", "timestamp": "2026-09-25T17:22:58.580Z", "request_id": "req_011CfQYZRSdq9mNMbE7n8okT"}
{"duration_api_ms": 7263, "stop_reason": "end_turn", "session_id": "9c22c15c-80ef-42c6-a503-8d087ec47d92", "total_cost_usd": 0.21507700000000002, "usage": {"input_tokens": 6, "cache_creation_input_tokens": 24309, "cache_read_input_tokens": 78105, "output_tokens": 248, "output_tokens_details": {"thinking_tokens": 0}, "server_tool_use": {"web_search_requests": 0, "web_fetch_requests": 0}, "service_tier": "standard", "cache_creation": {"ephemeral_1h_input_tokens": 24309, "ephemeral_5m_input_tokens": 0}, "inference_geo": "not_available", "iterations": [{"input_tokens": 2, "output_tokens": 89, "cache_read_input_tokens": 34283, "cache_creation_input_tokens": 145, "cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 145}, "type": "message"}], "speed": "standard"}, "modelUsage": {"claude-opus-5-5": {"inputTokens": 6, "outputTokens": 248, "cacheReadInputTokens": 78105, "cacheCreationInputTokens": 24309, "webSearchRequests": 0, "costUSD": 0.21507700000000002, "contextWindow": 1000000, "maxOutputTokens": 128000, "thinkingTokens": 0, "canonicalModel": "claude-opus-5-5", "provider": "firstParty", "costBasis": "list"}}, "permission_denials": [], "terminal_reason": "completed", "fast_mode_state": "off", "fast_mode_disabled_reason": "sdk_opt_in_required", "subagent_stats": {"spawned": 0, "requested": {"background": 0, "foreground": 0, "unset": 0}, "started_in_background": 0, "max_depth": 0, "spawned_by_subagents": 0, "completed": 0, "failed": 0, "killed": {"parent": 0, "user": 0, "system": 0}, "refused": {"depth_limit": 0, "concurrency_limit": 0, "budget": 0}, "by_type": {}}, "is_error": false, "num_turns": 3, "subtype": "success", "api_error_status": null, "result": "done\n\nThe first command printed `hello`. The second failed with \"No such file or directory\".\n\nGoogle Drive, exa and intercom still need authorizing. Google Drive is set up in its claude.ai connector settings. For exa and intercom, run `/mcp` in an interactive session.", "ttft_ms": 3229, "type": "result", "duration_ms": 7717, "uuid": "d0b46ba2-f8ff-49eb-b35e-b4eb6b9b272b", "ttft_stream_ms": 2833, "time_to_request_ms": 102, "first_content_frame_ms": 2834, "queued_turn_count": 0, "result_index": 0}
-8
View File
@@ -1,8 +0,0 @@
{"type":"thread.started","thread_id":"01a0db19-f9d6-7ad2-870c-c29b7fd8ab0a"}
{"type":"turn.started"}
{"type":"item.started","item":{"id":"item_0","type":"mcp_tool_call","server":"archie","tool":"record_verdict","arguments":{"verdict":"ok"},"result":null,"error":null,"status":"in_progress"}}
{"type":"item.completed","item":{"id":"item_0","type":"mcp_tool_call","server":"archie","tool":"record_verdict","arguments":{"verdict":"ok"},"result":{"content":[{"type":"text","text":"record_verdict recorded"}],"structured_content":null},"error":null,"status":"completed"}}
{"type":"item.started","item":{"id":"item_1","type":"file_change","changes":[{"path":"/tmp/hfx/note.txt","kind":"add"}],"status":"in_progress"}}
{"type":"item.completed","item":{"id":"item_1","type":"file_change","changes":[{"path":"/tmp/hfx/note.txt","kind":"add"}],"status":"completed"}}
{"type":"item.completed","item":{"id":"item_2","type":"agent_message","text":"done"}}
{"type":"turn.completed","usage":{"input_tokens":96397,"cached_input_tokens":80896,"cache_write_input_tokens":0,"output_tokens":203,"reasoning_output_tokens":87}}
-9
View File
@@ -1,9 +0,0 @@
{"type":"thread.started","thread_id":"01a0db18-e119-7872-bf13-3644369044fb"}
{"type":"turn.started"}
{"type":"item.completed","item":{"id":"item_0","type":"agent_message","text":"I’ll run the two requested shell commands in order, exactly as written."}}
{"type":"item.started","item":{"id":"item_1","type":"command_execution","command":"/usr/bin/bash -lc 'echo hello'","aggregated_output":"","exit_code":null,"status":"in_progress"}}
{"type":"item.completed","item":{"id":"item_1","type":"command_execution","command":"/usr/bin/bash -lc 'echo hello'","aggregated_output":"hello\n","exit_code":0,"status":"completed"}}
{"type":"item.started","item":{"id":"item_2","type":"command_execution","command":"/usr/bin/bash -lc 'cat /nonexistent-file'","aggregated_output":"","exit_code":null,"status":"in_progress"}}
{"type":"item.completed","item":{"id":"item_2","type":"command_execution","command":"/usr/bin/bash -lc 'cat /nonexistent-file'","aggregated_output":"cat: /nonexistent-file: No such file or directory\n","exit_code":1,"status":"failed"}}
{"type":"item.completed","item":{"id":"item_3","type":"agent_message","text":"done"}}
{"type":"turn.completed","usage":{"input_tokens":72082,"cached_input_tokens":57600,"cache_write_input_tokens":0,"output_tokens":118,"reasoning_output_tokens":0}}
-12
View File
@@ -1,12 +0,0 @@
{"type":"user.message","data":{"content":"Call the archie record_verdict tool with verdict \"ok\", then reply done.","transformedContent":"<current_datetime>2026-09-26T10:24:51.899+10:00</current_datetime>\n\nCall the archie record_verdict tool with verdict \"ok\", then reply done.","messageId":"6edfda87-baa7-43ae-9085-b35df7730a5b","supportedNativeDocumentMimeTypes":[],"delivery":"idle","interactionId":"ffa78343-e6f5-42aa-aea1-867cf22d8c62","turnId":"0","parentAgentTaskId":"695a0eb0-7c9f-403f-bf8a-11b359bbd6ef"},"id":"e6d6b78e-25a8-4718-9ab5-21730e4c1930","timestamp":"2026-09-26T00:24:51.899Z","parentId":"cf961d42-16aa-496f-81d2-f205e525c341"}
{"type":"assistant.turn_start","data":{"turnId":"0","interactionId":"ffa78343-e6f5-42aa-aea1-867cf22d8c62"},"id":"43c30d9f-a78d-49ab-a73d-a5059d6a8f33","timestamp":"2026-09-26T00:24:51.951Z","parentId":"d0f5807a-db5a-4bf5-bfca-0a0df80eb3e1"}
{"type":"assistant.message","data":{"messageId":"10378468-f2b3-4f1f-bbca-876991380095","originatingMessageId":"6edfda87-baa7-43ae-9085-b35df7730a5b","model":"mai-code-1.1-flash","content":"","toolRequests":[{"toolCallId":"call_SCpBb7giULn1ses3WUvaZ646","name":"archie-record_verdict","arguments":{"verdict":"ok"},"type":"function","toolTitle":"record_verdict","mcpServerName":"archie","mcpToolName":"record_verdict"}],"interactionId":"ffa78343-e6f5-42aa-aea1-867cf22d8c62","turnId":"0","rte":true,"apiCallId":"o4IeQmLtNQWeaj+YWo08mszPXOF1AP702ynApqaRloJ8MNMmCNuUlmqMMdwDx27Tz5AVPoX1PWYGPBcL7y+TQE22HWxuzkAPH8S8LdvfGV+ancUM6NM1SeWCj3Q3JzZNPxQUkRqNJ7D2vvMLcAVYOMHfOU9+Bu1dTI/+opLLn4L85IaRKa20wJ3cN5Lh0kRIoBYWrYQwImIBAkjaPlIOJRUNku2BLwFcBeNciBkvwBW6v0dUAE3GOvt8Wi8u2ierGofUYTmv4PNRZJnEjE69og/rOlP+b7x8Zf6amoEaZoFBET1Kw8Or57gcsdumstObCF+2MI8oFfnMg3igVm8/ZHMmTlUebjfNsc2PlzVyFWZfT5SwY+LjyzE22QTggIQwZ1kNUI7baA3JMqo5PQuoztdTWtJuz/u42q43kOLKhnj+P2YGP/I5FBvLbDcghIsS","serverTools":{"provider":"openai-responses"}},"id":"9adeb15a-b245-4b11-948e-9e688e7b1dad","timestamp":"2026-09-26T00:24:55.924Z","parentId":"43c30d9f-a78d-49ab-a73d-a5059d6a8f33"}
{"type":"tool.execution_start","data":{"toolCallId":"call_SCpBb7giULn1ses3WUvaZ646","toolName":"archie-record_verdict","arguments":{"verdict":"ok"},"turnId":"0","model":"mai-code-1.1-flash","toolTitle":"record_verdict","mcpServerName":"archie","mcpConfigServerName":"archie","mcpTransport":"stdio","mcpConfigSource":"user","mcpToolName":"record_verdict"},"id":"fffc906a-39af-4eb1-91ba-80fa0f8cb7f7","timestamp":"2026-09-26T00:24:55.927Z","parentId":"9adeb15a-b245-4b11-948e-9e688e7b1dad"}
{"type":"tool.execution_complete","data":{"toolCallId":"call_SCpBb7giULn1ses3WUvaZ646","model":"mai-code-1.1-flash","interactionId":"ffa78343-e6f5-42aa-aea1-867cf22d8c62","turnId":"0","rte":true,"success":true,"result":{"content":"record_verdict recorded","detailedContent":"record_verdict recorded","contents":[{"type":"text","text":"record_verdict recorded"}]},"toolTelemetry":{"metrics":{"mcp_result_content_bytes":23}}},"id":"97d661ef-f75b-4734-b358-c843a3e5543d","timestamp":"2026-09-26T00:24:55.931Z","parentId":"fffc906a-39af-4eb1-91ba-80fa0f8cb7f7"}
{"type":"assistant.turn_end","data":{"turnId":"0"},"id":"6a3adff0-7017-4c44-8d8d-b32d94442b7b","timestamp":"2026-09-26T00:24:55.936Z","parentId":"97d661ef-f75b-4734-b358-c843a3e5543d"}
{"type":"assistant.turn_start","data":{"turnId":"1","interactionId":"ffa78343-e6f5-42aa-aea1-867cf22d8c62"},"id":"20538fbe-354e-4c37-a66d-dd169baaae6c","timestamp":"2026-09-26T00:24:55.937Z","parentId":"6a3adff0-7017-4c44-8d8d-b32d94442b7b"}
{"type":"assistant.message_start","data":{"messageId":"fd2cd067-22f8-45a3-996e-5b5170455259","phase":"final_answer"},"ephemeral":true,"id":"0aa849db-670e-4d8c-bf28-4b67fedbfefd","timestamp":"2026-09-26T00:24:58.682Z","parentId":"20538fbe-354e-4c37-a66d-dd169baaae6c"}
{"type":"assistant.message","data":{"messageId":"fd2cd067-22f8-45a3-996e-5b5170455259","originatingMessageId":"6edfda87-baa7-43ae-9085-b35df7730a5b","model":"mai-code-1.1-flash","content":"done","toolRequests":[],"interactionId":"ffa78343-e6f5-42aa-aea1-867cf22d8c62","turnId":"1","phase":"final_answer","rte":true,"apiCallId":"rQ30ntxRLGIEBrvhcd/a8wMwoTOBA1A5DiGkpF5vfM/MXyIvo81P2W19LNGRYtko/DuDhi1S2NbJp2REVkOsV7QiReoS59ABuGoME9Jp5ccwWfjR4dtfrwZY7ARBkDjoE79/dt0e+73SvAIoP6Vc5DoJ1aBOlDb1Uo7sGxyPDUPNfnjFc0ZSSr1YHviwGcVOoSkB66IrY+zzdz+s43b+Kn9sDiFD/28bvxdH3o6tqmuuVYL35qGuyhoDUlRKk4JXTB8aAjw1IS+lXYVYHfoGhv6F+ZEIf9H/KOVioWCfW3wPEyNOiPyA0qH9gy8g6V1rminPG+6JgwPdZ3QVEuOddFQjj8OjpTLHYKyKVDRxwNq7p0WEH1Wgb8wPpSZpHtAHoHL5rlsSCWcZcoAKFU/Eh+pi9ms073CsMyjhwu+x93O5x8z/pv8CD8BRkJuT0lH6","serverTools":{"provider":"openai-responses"}},"id":"c1b6cb34-b547-4b09-a057-042129d8e8e6","timestamp":"2026-09-26T00:24:59.033Z","parentId":"20538fbe-354e-4c37-a66d-dd169baaae6c"}
{"type":"assistant.turn_end","data":{"turnId":"1"},"id":"ac711ef0-98c9-4903-8605-d0a075038156","timestamp":"2026-09-26T00:24:59.037Z","parentId":"c1b6cb34-b547-4b09-a057-042129d8e8e6"}
{"type":"assistant.idle","data":{},"ephemeral":true,"id":"3cdd0759-c01f-4670-bd89-1d7d265057c5","timestamp":"2026-09-26T00:24:59.042Z","parentId":"dde7674c-f216-47d1-99dc-b1a42340e3ab"}
{"type":"result","timestamp":"2026-09-26T00:24:59.048Z","sessionId":"46ce5d05-adf6-45ac-82bc-167a3c48a146","exitCode":0,"usage":{"premiumRequests":1,"totalApiDurationMs":7028,"sessionDurationMs":10510,"codeChanges":{"linesAdded":0,"linesRemoved":0,"filesModified":[]}}}
-21
View File
@@ -1,21 +0,0 @@
{"type":"user.message","data":{"content":"Run exactly these two shell commands, one at a time, then reply \"done\": 1) echo hello 2) cat /nonexistent-file","transformedContent":"<current_datetime>2026-09-26T10:24:05.291+10:00</current_datetime>\n\nRun exactly these two shell commands, one at a time, then reply \"done\": 1) echo hello 2) cat /nonexistent-file","messageId":"592e4a25-4edd-4138-8428-04377528629d","supportedNativeDocumentMimeTypes":[],"delivery":"idle","interactionId":"6bd23866-01a9-4330-a002-3630c4c1fe7a","turnId":"0","parentAgentTaskId":"a7334356-386f-4883-a45b-c0202257c75e"},"id":"30170ef7-73c3-4ddc-b68a-420fa53126c5","timestamp":"2026-09-26T00:24:05.291Z","parentId":"c5779a53-653b-4d88-9a5d-5d04392191bc"}
{"type":"assistant.turn_start","data":{"turnId":"0","interactionId":"6bd23866-01a9-4330-a002-3630c4c1fe7a"},"id":"7eaf3f4d-f167-4458-87ee-3d5590b00c18","timestamp":"2026-09-26T00:24:05.334Z","parentId":"14d0190b-e039-42f9-a4b9-0a75ae807f1f"}
{"type":"assistant.message","data":{"messageId":"6b6bea7c-2344-47a1-95db-1f8d6e682666","originatingMessageId":"592e4a25-4edd-4138-8428-04377528629d","model":"mai-code-1.1-flash","content":"","toolRequests":[{"toolCallId":"call_B7mfLIxqUZJ0U7TPuq7AICf6","name":"bash","arguments":{"command":"echo hello","description":"Run the first required shell command","mode":"sync","initial_wait":10},"type":"function","intentionSummary":"Run the first required shell command"}],"interactionId":"6bd23866-01a9-4330-a002-3630c4c1fe7a","turnId":"0","rte":true,"apiCallId":"f62pmo58wYEiXCowGq2scylnq7Sl72p0HPwz/uzwyAxSnDimAMaUhplE5ob+c/7UI4GlY/FKov+OuTgP6cZYK7vKyWfmHE9irEusbHzDNwaNyfjyJzDuyko5LEHYhPYh4tVFCdob6X764KL1JPVls66S+KZU6pxGyqW5Z9SuYNl1pw/T/mtRZamdmejkxNtprl6c6SZjn//mGF8QAUE5TTHGCUf4ZVynuCu8OplI6+WU4ecM86bUgFHRxHdAml3UpXrLnhhqGf/24sMtIaZdm5XhxNYtpTn1HD5ZDHsyS0pJBAstHCT3zpdjkkg+oy+9I7cfZ8D/aE8tLJjRO36rY69+r2QhLB7gko41WnZhgeTlxtgIaUpEbA5RT325gzH2y70ryklfEwUfM3vecHLbSmBPBVo/2Si5tAMzaX9/fePrelVxJZmogzX2zFEM7oZH","serverTools":{"provider":"openai-responses"}},"id":"18daf5a9-28ad-4e32-a964-c7a7b2fa3561","timestamp":"2026-09-26T00:24:07.616Z","parentId":"7eaf3f4d-f167-4458-87ee-3d5590b00c18"}
{"type":"tool.execution_start","data":{"toolCallId":"call_B7mfLIxqUZJ0U7TPuq7AICf6","toolName":"bash","arguments":{"command":"echo hello","description":"Run the first required shell command","mode":"sync","initial_wait":10},"turnId":"0","model":"mai-code-1.1-flash","shellToolInfo":{"possiblePaths":[],"hasWriteFileRedirection":false}},"id":"495b5003-1cae-48ab-a3cf-299aebdbcd57","timestamp":"2026-09-26T00:24:07.617Z","parentId":"18daf5a9-28ad-4e32-a964-c7a7b2fa3561"}
{"type":"tool.execution_partial_result","data":{"toolCallId":"call_B7mfLIxqUZJ0U7TPuq7AICf6","partialOutput":"hello\n"},"ephemeral":true,"id":"bfa8c93e-8702-4405-9f34-fcf2e488a5f7","timestamp":"2026-09-26T00:24:07.671Z","parentId":"495b5003-1cae-48ab-a3cf-299aebdbcd57"}
{"type":"tool.execution_partial_result","data":{"toolCallId":"call_B7mfLIxqUZJ0U7TPuq7AICf6","partialOutput":"hello\n"},"ephemeral":true,"id":"f2a7773b-fc90-4dec-90a2-7f59a9703002","timestamp":"2026-09-26T00:24:07.671Z","parentId":"495b5003-1cae-48ab-a3cf-299aebdbcd57"}
{"type":"tool.execution_complete","data":{"toolCallId":"call_B7mfLIxqUZJ0U7TPuq7AICf6","model":"mai-code-1.1-flash","interactionId":"6bd23866-01a9-4330-a002-3630c4c1fe7a","turnId":"0","rte":true,"shellExecution":{"exitCode":0},"success":true,"result":{"content":"hello\n<shellId: 0 completed with exit code 0>","detailedContent":"hello\n<shellId: 0 completed with exit code 0>"},"toolTelemetry":{"properties":{"customTimeout":"true","executionMode":"sync","detached":"false","sandboxApplied":"false","sandboxOptOutRequested":"false"},"metrics":{"commandTimeout":30000}}},"id":"1998c4e2-5bc7-48ec-b25a-22e09e0b8c94","timestamp":"2026-09-26T00:24:07.676Z","parentId":"495b5003-1cae-48ab-a3cf-299aebdbcd57"}
{"type":"assistant.turn_end","data":{"turnId":"0"},"id":"5f5a4959-c817-4e68-b29b-393bc2489708","timestamp":"2026-09-26T00:24:07.681Z","parentId":"1998c4e2-5bc7-48ec-b25a-22e09e0b8c94"}
{"type":"assistant.turn_start","data":{"turnId":"1","interactionId":"6bd23866-01a9-4330-a002-3630c4c1fe7a"},"id":"e637d527-fe9a-40a3-b686-7d351233ac5e","timestamp":"2026-09-26T00:24:07.682Z","parentId":"5f5a4959-c817-4e68-b29b-393bc2489708"}
{"type":"assistant.message","data":{"messageId":"ee78bdc4-8346-4970-95ed-de15d5b92dbb","originatingMessageId":"592e4a25-4edd-4138-8428-04377528629d","model":"mai-code-1.1-flash","content":"","toolRequests":[{"toolCallId":"call_KOZ6Yo6H2tFaGF8JSeHhROJ1","name":"bash","arguments":{"command":"cat /nonexistent-file","description":"Run the second required shell command to trigger the expected error","mode":"sync","initial_wait":10},"type":"function","intentionSummary":"Run the second required shell command to trigger the expected error"}],"interactionId":"6bd23866-01a9-4330-a002-3630c4c1fe7a","turnId":"1","rte":true,"apiCallId":"KG3rWA5KnDXtL/Ftwooj+JjuuS+L+ah1aYHMcnKw9dFSwz3o2iOv3slDRYSqE5e2KrWgrIFsDtMAgiXlXahwtf8vnIpJgcRQrv2dJqpiPx955GxFNfsv0y+LitYKH69Iv+707wPPOfekR97bhzfXA2QGjna6+0FzEW/ZHT8LfAIfiyqai9XiXiOhZOTKVxAJ5xmJSZqDTtt8V+Ut2EL/3LCl19/wYTTF0YAHEjSovoQP19hx3RAqXCMhnJd1Uy4q4mlsNNvbGIPbcZwLrfNVTnVa9BV4mECvecH9IeJ9axMUZS/lA/jU3Da5VNCEtsXOYnhk6DX8tSNQLB+NYumqzmk2X+dUq2Wb3Y8W/MoL7c0//NSYqYDbRjLkEpaaKZYiibA/KFE5XVp48Gdd+cnzODhH1K4O39xTwAHjQlflj1s39qRqMRw6CL6tDf/frGwU","serverTools":{"provider":"openai-responses"}},"id":"64c89fe7-be35-41f2-9127-034874b52d95","timestamp":"2026-09-26T00:24:09.954Z","parentId":"e637d527-fe9a-40a3-b686-7d351233ac5e"}
{"type":"tool.execution_start","data":{"toolCallId":"call_KOZ6Yo6H2tFaGF8JSeHhROJ1","toolName":"bash","arguments":{"command":"cat /nonexistent-file","description":"Run the second required shell command to trigger the expected error","mode":"sync","initial_wait":10},"turnId":"1","model":"mai-code-1.1-flash","shellToolInfo":{"possiblePaths":[],"hasWriteFileRedirection":false}},"id":"a240e698-9aaa-43d3-bdb8-517399bb9c2a","timestamp":"2026-09-26T00:24:09.956Z","parentId":"64c89fe7-be35-41f2-9127-034874b52d95"}
{"type":"tool.execution_partial_result","data":{"toolCallId":"call_KOZ6Yo6H2tFaGF8JSeHhROJ1","partialOutput":"cat: /nonexistent-file: No such file or directory\n"},"ephemeral":true,"id":"554fa3fb-6bb0-4b8d-b2ec-723131f48064","timestamp":"2026-09-26T00:24:09.966Z","parentId":"a240e698-9aaa-43d3-bdb8-517399bb9c2a"}
{"type":"tool.execution_partial_result","data":{"toolCallId":"call_KOZ6Yo6H2tFaGF8JSeHhROJ1","partialOutput":"cat: /nonexistent-file: No such file or directory\n"},"ephemeral":true,"id":"94dae986-d597-40a5-831c-388182db7301","timestamp":"2026-09-26T00:24:09.966Z","parentId":"a240e698-9aaa-43d3-bdb8-517399bb9c2a"}
{"type":"tool.execution_complete","data":{"toolCallId":"call_KOZ6Yo6H2tFaGF8JSeHhROJ1","model":"mai-code-1.1-flash","interactionId":"6bd23866-01a9-4330-a002-3630c4c1fe7a","turnId":"1","rte":true,"shellExecution":{"exitCode":1},"success":true,"result":{"content":"cat: /nonexistent-file: No such file or directory\n<shellId: 1 completed with exit code 1>","detailedContent":"cat: /nonexistent-file: No such file or directory\n<shellId: 1 completed with exit code 1>"},"toolTelemetry":{"properties":{"customTimeout":"true","executionMode":"sync","detached":"false","sandboxApplied":"false","sandboxOptOutRequested":"false","shell_error_category":"command_nonzero_exit"},"metrics":{"commandTimeout":30000,"exit_code":1}}},"id":"f22d0b04-9056-4d5c-b798-6a3eb26cc2b1","timestamp":"2026-09-26T00:24:09.971Z","parentId":"a240e698-9aaa-43d3-bdb8-517399bb9c2a"}
{"type":"assistant.turn_end","data":{"turnId":"1"},"id":"f823f0b3-33d8-4ca5-a111-733fa58c66e9","timestamp":"2026-09-26T00:24:09.975Z","parentId":"f22d0b04-9056-4d5c-b798-6a3eb26cc2b1"}
{"type":"assistant.turn_start","data":{"turnId":"2","interactionId":"6bd23866-01a9-4330-a002-3630c4c1fe7a"},"id":"361e7d6b-7832-4137-9d71-b2ca66d90526","timestamp":"2026-09-26T00:24:09.975Z","parentId":"f823f0b3-33d8-4ca5-a111-733fa58c66e9"}
{"type":"assistant.message_start","data":{"messageId":"d92c3a5f-329a-4b84-8548-76a9f6acf6a9","phase":"final_answer"},"ephemeral":true,"id":"09bcf00a-0f8e-44c7-9539-98ac6b25f150","timestamp":"2026-09-26T00:24:11.613Z","parentId":"361e7d6b-7832-4137-9d71-b2ca66d90526"}
{"type":"assistant.message","data":{"messageId":"d92c3a5f-329a-4b84-8548-76a9f6acf6a9","originatingMessageId":"592e4a25-4edd-4138-8428-04377528629d","model":"mai-code-1.1-flash","content":"done","toolRequests":[],"interactionId":"6bd23866-01a9-4330-a002-3630c4c1fe7a","turnId":"2","phase":"final_answer","rte":true,"apiCallId":"HnNPE0K4S9Sfzu3aBEKNBu0bN71YXywM7Iou7HJYeGMBSegpo3BPJcfUERt8oGnSgEpfS5aEntUzNMfpuS91+3QbHxfDkApmOYcWeU/YXFlpQkgeT8bhYmNQ0g+Lpo7Zf45jMikQQ23xdX7r4zQHEXBud6cWLde+ujXNZ4Tc3mq1fPTvsa2Z4qD9gCRKwFksOqOQR4UeRuRRxIr2qWEXs61qj4xfH7BM0IAbm07zCyv6arLfHHhtbe/wXkv7fBWCbtQufB+KRW8Z5Wo+6peGgEi4x9ayQETTUG3K/q6nUY3wbHVquOI/UYHZewJFwPDfleQq2l6Okim8ftIIvoNfyvIy1GRDS/n/UnrUpDG1NNmgJDDcDIManTx9wpywEGR/K8gzfl98ddcd5N+6RC4G678wPu9AQef65ztQyKJB5jFLzkhI1LPc5+yTY0V8gZMA","serverTools":{"provider":"openai-responses"}},"id":"4657559f-58ec-4922-bed9-7fc89cdc7de9","timestamp":"2026-09-26T00:24:11.832Z","parentId":"361e7d6b-7832-4137-9d71-b2ca66d90526"}
{"type":"assistant.turn_end","data":{"turnId":"2"},"id":"b5ad8a1e-47f2-460b-ac09-0fe63f266271","timestamp":"2026-09-26T00:24:11.833Z","parentId":"4657559f-58ec-4922-bed9-7fc89cdc7de9"}
{"type":"assistant.idle","data":{},"ephemeral":true,"id":"1bcbd91f-9903-4b9a-8c22-cfea0d567a80","timestamp":"2026-09-26T00:24:11.838Z","parentId":"e800bf25-1659-4023-8e1c-55270f374526"}
{"type":"result","timestamp":"2026-09-26T00:24:11.847Z","sessionId":"bdf5531e-b8a4-4baf-bed2-d914242fa387","exitCode":0,"usage":{"premiumRequests":1,"totalApiDurationMs":6371,"sessionDurationMs":14653,"codeChanges":{"linesAdded":0,"linesRemoved":0,"filesModified":[]}}}
-29
View File
@@ -1,29 +0,0 @@
{"type":"session","version":3,"id":"01a0db18-e4a1-7000-9cbe-7467b0385e65","timestamp":"2026-09-26T00:23:56.833Z","cwd":"/tmp/hfx"}
{"type":"agent_start"}
{"type":"turn_start"}
{"type":"message_start","message":{"role":"user","content":[{"type":"text","text":"Run exactly these two shell commands, one at a time, then reply \"done\": 1) echo hello 2) cat /nonexistent-file"}],"attribution":"user","timestamp":1790382237281}}
{"type":"message_end","message":{"role":"user","content":[{"type":"text","text":"Run exactly these two shell commands, one at a time, then reply \"done\": 1) echo hello 2) cat /nonexistent-file"}],"attribution":"user","timestamp":1790382237281}}
{"type":"message_start","message":{"role":"assistant","content":[{"type":"thinking","thinking":"Simple","thinkingSignature":"reasoning_content"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-flash","usage":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"totalTokens":0,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1790382237472,"responseId":"065106e6-b09d-48f7-b6c6-e4e85fde221b"}}
{"type":"message_end","message":{"role":"assistant","content":[{"type":"thinking","thinking":"Simple: run echo hello, then cat /nonexistent-file. One at a time.","thinkingSignature":"reasoning_content"},{"type":"toolCall","id":"call_00_nr3UPjdQx9tkGIlERsCP4300","name":"bash","arguments":{"command":"echo hello","i":"Running echo hello"},"partialArgs":"{\"command\": \"echo hello\", \"i\": \"Running echo hello\"}","streamIndex":0,"intent":"Running echo hello"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-flash","usage":{"input":25222,"output":75,"cacheRead":0,"cacheWrite":0,"totalTokens":25297,"reasoningTokens":19,"cost":{"input":0.0037833,"output":0.000044999999999999996,"cacheRead":0,"cacheWrite":0,"total":0.0038282999999999998}},"stopReason":"toolUse","timestamp":1790382237472,"responseId":"065106e6-b09d-48f7-b6c6-e4e85fde221b","duration":1472.9358650000001,"ttft":1164.486779,"completedAt":1790382238970}}
{"type":"tool_execution_start","toolCallId":"call_00_nr3UPjdQx9tkGIlERsCP4300","toolName":"bash","args":{"command":"echo hello"},"intent":"Running echo hello"}
{"type":"tool_execution_update","toolCallId":"call_00_nr3UPjdQx9tkGIlERsCP4300","toolName":"bash","args":{"command":"echo hello"},"partialResult":{"content":[{"type":"text","text":"hello\n"}],"details":{}}}
{"type":"tool_execution_update","toolCallId":"call_00_nr3UPjdQx9tkGIlERsCP4300","toolName":"bash","args":{"command":"echo hello"},"partialResult":{"content":[{"type":"text","text":"hello\n\n\nWall time: 0.03 seconds"}],"details":{"timeoutSeconds":300,"wallTimeMs":28.820365000000038}}}
{"type":"tool_execution_end","toolCallId":"call_00_nr3UPjdQx9tkGIlERsCP4300","toolName":"bash","result":{"content":[{"type":"text","text":"hello\n\n\nWall time: 0.03 seconds"}],"details":{"timeoutSeconds":300,"wallTimeMs":28.820365000000038}},"isError":false}
{"type":"message_start","message":{"role":"toolResult","toolCallId":"call_00_nr3UPjdQx9tkGIlERsCP4300","toolName":"bash","content":[{"type":"text","text":"hello\n\n\nWall time: 0.03 seconds"}],"details":{"timeoutSeconds":300,"wallTimeMs":28.820365000000038},"isError":false,"timestamp":1790382239011}}
{"type":"message_end","message":{"role":"toolResult","toolCallId":"call_00_nr3UPjdQx9tkGIlERsCP4300","toolName":"bash","content":[{"type":"text","text":"hello\n\n\nWall time: 0.03 seconds"}],"details":{"timeoutSeconds":300,"wallTimeMs":28.820365000000038},"isError":false,"timestamp":1790382239011}}
{"type":"turn_end","message":{"role":"assistant","content":[{"type":"thinking","thinking":"Simple: run echo hello, then cat /nonexistent-file. One at a time.","thinkingSignature":"reasoning_content"},{"type":"toolCall","id":"call_00_nr3UPjdQx9tkGIlERsCP4300","name":"bash","arguments":{"command":"echo hello","i":"Running echo hello"},"partialArgs":"{\"command\": \"echo hello\", \"i\": \"Running echo hello\"}","streamIndex":0,"intent":"Running echo hello"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-flash","usage":{"input":25222,"output":75,"cacheRead":0,"cacheWrite":0,"totalTokens":25297,"reasoningTokens":19,"cost":{"input":0.0037833,"output":0.000044999999999999996,"cacheRead":0,"cacheWrite":0,"total":0.0038282999999999998}},"stopReason":"toolUse","timestamp":1790382237472,"responseId":"065106e6-b09d-48f7-b6c6-e4e85fde221b","duration":1472.9358650000001,"ttft":1164.486779},"toolResults":[{"role":"toolResult","toolCallId":"call_00_nr3UPjdQx9tkGIlERsCP4300","toolName":"bash","content":[{"type":"text","text":"hello\n\n\nWall time: 0.03 seconds"}],"details":{"timeoutSeconds":300,"wallTimeMs":28.820365000000038},"isError":false,"timestamp":1790382239011}]}
{"type":"turn_start"}
{"type":"message_start","message":{"role":"assistant","content":[{"type":"toolCall","id":"call_00_ET_2IFtDySsuHmiOftiTqJg7979","name":"bash","arguments":{"command":"cat /nonexistent-file","i":"Reading nonexistent file"},"partialArgs":"{\"command\": \"cat /nonexistent-file\", \"i\": \"Reading nonexistent file\"}","streamIndex":0}],"api":"openai-completions","provider":"deepseek","model":"deepseek-flash","usage":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"totalTokens":0,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1790382239018,"responseId":"d232767b-4ac0-4264-b166-1234dd27e949"}}
{"type":"message_end","message":{"role":"assistant","content":[{"type":"toolCall","id":"call_00_ET_2IFtDySsuHmiOftiTqJg7979","name":"bash","arguments":{"command":"cat /nonexistent-file","i":"Reading nonexistent file"},"partialArgs":"{\"command\": \"cat /nonexistent-file\", \"i\": \"Reading nonexistent file\"}","streamIndex":0,"intent":"Reading nonexistent file"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-flash","usage":{"input":231,"output":61,"cacheRead":25088,"cacheWrite":0,"totalTokens":25380,"cost":{"input":0.000034649999999999995,"output":0.000036599999999999995,"cacheRead":0.000075264,"cacheWrite":0,"total":0.000146514}},"stopReason":"toolUse","timestamp":1790382239018,"responseId":"d232767b-4ac0-4264-b166-1234dd27e949","duration":1915.5203490000004,"completedAt":1790382240956}}
{"type":"tool_execution_start","toolCallId":"call_00_ET_2IFtDySsuHmiOftiTqJg7979","toolName":"bash","args":{"command":"cat /nonexistent-file"},"intent":"Reading nonexistent file"}
{"type":"tool_execution_update","toolCallId":"call_00_ET_2IFtDySsuHmiOftiTqJg7979","toolName":"bash","args":{"command":"cat /nonexistent-file"},"partialResult":{"content":[{"type":"text","text":"cat: /nonexistent-file: No such file or directory\n"}],"details":{}}}
{"type":"tool_execution_update","toolCallId":"call_00_ET_2IFtDySsuHmiOftiTqJg7979","toolName":"bash","args":{"command":"cat /nonexistent-file"},"partialResult":{"content":[{"type":"text","text":"cat: /nonexistent-file: No such file or directory\n\n\nWall time: 0.00 seconds\n\nCommand exited with code 1"}],"details":{"timeoutSeconds":300,"wallTimeMs":2.267550999999912,"exitCode":1}}}
{"type":"tool_execution_end","toolCallId":"call_00_ET_2IFtDySsuHmiOftiTqJg7979","toolName":"bash","result":{"content":[{"type":"text","text":"cat: /nonexistent-file: No such file or directory\n\n\nWall time: 0.00 seconds\n\nCommand exited with code 1"}],"details":{"timeoutSeconds":300,"wallTimeMs":2.267550999999912,"exitCode":1},"isError":true},"isError":true}
{"type":"message_start","message":{"role":"toolResult","toolCallId":"call_00_ET_2IFtDySsuHmiOftiTqJg7979","toolName":"bash","content":[{"type":"text","text":"cat: /nonexistent-file: No such file or directory\n\n\nWall time: 0.00 seconds\n\nCommand exited with code 1"}],"details":{"timeoutSeconds":300,"wallTimeMs":2.267550999999912,"exitCode":1},"isError":true,"timestamp":1790382240960}}
{"type":"message_end","message":{"role":"toolResult","toolCallId":"call_00_ET_2IFtDySsuHmiOftiTqJg7979","toolName":"bash","content":[{"type":"text","text":"cat: /nonexistent-file: No such file or directory\n\n\nWall time: 0.00 seconds\n\nCommand exited with code 1"}],"details":{"timeoutSeconds":300,"wallTimeMs":2.267550999999912,"exitCode":1},"isError":true,"timestamp":1790382240960}}
{"type":"turn_end","message":{"role":"assistant","content":[{"type":"toolCall","id":"call_00_ET_2IFtDySsuHmiOftiTqJg7979","name":"bash","arguments":{"command":"cat /nonexistent-file","i":"Reading nonexistent file"},"partialArgs":"{\"command\": \"cat /nonexistent-file\", \"i\": \"Reading nonexistent file\"}","streamIndex":0,"intent":"Reading nonexistent file"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-flash","usage":{"input":231,"output":61,"cacheRead":25088,"cacheWrite":0,"totalTokens":25380,"cost":{"input":0.000034649999999999995,"output":0.000036599999999999995,"cacheRead":0.000075264,"cacheWrite":0,"total":0.000146514}},"stopReason":"toolUse","timestamp":1790382239018,"responseId":"d232767b-4ac0-4264-b166-1234dd27e949","duration":1915.5203490000004},"toolResults":[{"role":"toolResult","toolCallId":"call_00_ET_2IFtDySsuHmiOftiTqJg7979","toolName":"bash","content":[{"type":"text","text":"cat: /nonexistent-file: No such file or directory\n\n\nWall time: 0.00 seconds\n\nCommand exited with code 1"}],"details":{"timeoutSeconds":300,"wallTimeMs":2.267550999999912,"exitCode":1},"isError":true,"timestamp":1790382240960}]}
{"type":"turn_start"}
{"type":"message_start","message":{"role":"assistant","content":[{"type":"text","text":"done\n\n("}],"api":"openai-completions","provider":"deepseek","model":"deepseek-flash","usage":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"totalTokens":0,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"stop","timestamp":1790382240964,"responseId":"5183f0c3-4531-44b6-b80a-61b6290dfb22"}}
{"type":"message_end","message":{"role":"assistant","content":[{"type":"text","text":"done\n\n(2) exited 1: `cat: /nonexistent-file: No such file or directory`"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-flash","usage":{"input":205,"output":25,"cacheRead":25216,"cacheWrite":0,"totalTokens":25446,"cost":{"input":0.000030749999999999995,"output":0.000014999999999999999,"cacheRead":0.000075648,"cacheWrite":0,"total":0.00012139799999999999}},"stopReason":"stop","timestamp":1790382240964,"responseId":"5183f0c3-4531-44b6-b80a-61b6290dfb22","duration":1189.6723079999992,"ttft":1106.6433019999995,"completedAt":1790382242178}}
{"type":"turn_end","message":{"role":"assistant","content":[{"type":"text","text":"done\n\n(2) exited 1: `cat: /nonexistent-file: No such file or directory`"}],"api":"openai-completions","provider":"deepseek","model":"deepseek-flash","usage":{"input":205,"output":25,"cacheRead":25216,"cacheWrite":0,"totalTokens":25446,"cost":{"input":0.000030749999999999995,"output":0.000014999999999999999,"cacheRead":0.000075648,"cacheWrite":0,"total":0.00012139799999999999}},"stopReason":"stop","timestamp":1790382240964,"responseId":"5183f0c3-4531-44b6-b80a-61b6290dfb22","duration":1189.6723079999992,"ttft":1106.6433019999995},"toolResults":[]}
{"type":"agent_end","messages":[],"isTerminal":true}
-30
View File
@@ -1,30 +0,0 @@
{"type":"session","version":3,"id":"01a0db18-e183-7432-9e4b-4b16bfc83856","timestamp":"2026-09-26T00:23:56.037Z","cwd":"/tmp/hfx"}
{"type":"agent_start"}
{"type":"turn_start"}
{"type":"message_start","message":{"role":"user","content":[{"type":"text","text":"Run exactly these two shell commands, one at a time, then reply \"done\": 1) echo hello 2) cat /nonexistent-file"}],"timestamp":1790382237711}}
{"type":"message_end","message":{"role":"user","content":[{"type":"text","text":"Run exactly these two shell commands, one at a time, then reply \"done\": 1) echo hello 2) cat /nonexistent-file"}],"timestamp":1790382237711}}
{"type":"message_start","message":{"role":"assistant","content":[{"type":"toolCall","id":"call_4w3gr4ma","name":"bash","arguments":{"command":"echo hello"},"partialArgs":"{\"command\":\"echo hello\"}","streamIndex":0}],"api":"openai-completions","provider":"ollama-cloud","model":"glm-5.3-flash","usage":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"totalTokens":0,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"pending","timestamp":1790382237724,"responseId":"chatcmpl-176"}}
{"type":"message_end","message":{"role":"assistant","content":[{"type":"toolCall","id":"call_4w3gr4ma","name":"bash","arguments":{"command":"echo hello"}}],"api":"openai-completions","provider":"ollama-cloud","model":"glm-5.3-flash","usage":{"input":36426,"output":12,"cacheRead":0,"cacheWrite":0,"reasoning":0,"totalTokens":36438,"cost":{"input":0.0054639,"output":0.000006,"cacheRead":0,"cacheWrite":0,"total":0.0054699}},"stopReason":"toolUse","timestamp":1790382237724,"responseId":"chatcmpl-176","rawStopReason":"tool_calls"}}
{"type":"tool_execution_start","toolCallId":"call_4w3gr4ma","toolName":"bash","args":{"command":"echo hello"}}
{"type":"tool_execution_update","toolCallId":"call_4w3gr4ma","toolName":"bash","args":{"command":"echo hello"},"partialResult":{"content":[]}}
{"type":"tool_execution_update","toolCallId":"call_4w3gr4ma","toolName":"bash","args":{"command":"echo hello"},"partialResult":{"content":[{"type":"text","text":"hello\n"}],"details":{}}}
{"type":"tool_execution_end","toolCallId":"call_4w3gr4ma","toolName":"bash","result":{"content":[{"type":"text","text":"hello\n"}]},"isError":false}
{"type":"message_start","message":{"role":"toolResult","toolCallId":"call_4w3gr4ma","toolName":"bash","content":[{"type":"text","text":"hello\n"}],"isError":false,"timestamp":1790382240554}}
{"type":"message_end","message":{"role":"toolResult","toolCallId":"call_4w3gr4ma","toolName":"bash","content":[{"type":"text","text":"hello\n"}],"isError":false,"timestamp":1790382240554}}
{"type":"turn_end","message":{"role":"assistant","content":[{"type":"toolCall","id":"call_4w3gr4ma","name":"bash","arguments":{"command":"echo hello"}}],"api":"openai-completions","provider":"ollama-cloud","model":"glm-5.3-flash","usage":{"input":36426,"output":12,"cacheRead":0,"cacheWrite":0,"reasoning":0,"totalTokens":36438,"cost":{"input":0.0054639,"output":0.000006,"cacheRead":0,"cacheWrite":0,"total":0.0054699}},"stopReason":"toolUse","timestamp":1790382237724,"responseId":"chatcmpl-176","rawStopReason":"tool_calls"},"toolResults":[{"role":"toolResult","toolCallId":"call_4w3gr4ma","toolName":"bash","content":[{"type":"text","text":"hello\n"}],"isError":false,"timestamp":1790382240554}]}
{"type":"turn_start"}
{"type":"message_start","message":{"role":"assistant","content":[{"type":"toolCall","id":"call_cta082t7","name":"bash","arguments":{"command":"cat /nonexistent-file"},"partialArgs":"{\"command\":\"cat /nonexistent-file\"}","streamIndex":0}],"api":"openai-completions","provider":"ollama-cloud","model":"glm-5.3-flash","usage":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"totalTokens":0,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"pending","timestamp":1790382240561,"responseId":"chatcmpl-207"}}
{"type":"message_end","message":{"role":"assistant","content":[{"type":"toolCall","id":"call_cta082t7","name":"bash","arguments":{"command":"cat /nonexistent-file"}}],"api":"openai-completions","provider":"ollama-cloud","model":"glm-5.3-flash","usage":{"input":5007,"output":15,"cacheRead":31360,"cacheWrite":0,"reasoning":0,"totalTokens":36382,"cost":{"input":0.00075105,"output":0.000007499999999999999,"cacheRead":0,"cacheWrite":0,"total":0.00075855}},"stopReason":"toolUse","timestamp":1790382240561,"responseId":"chatcmpl-207","rawStopReason":"tool_calls"}}
{"type":"tool_execution_start","toolCallId":"call_cta082t7","toolName":"bash","args":{"command":"cat /nonexistent-file"}}
{"type":"tool_execution_update","toolCallId":"call_cta082t7","toolName":"bash","args":{"command":"cat /nonexistent-file"},"partialResult":{"content":[]}}
{"type":"tool_execution_update","toolCallId":"call_cta082t7","toolName":"bash","args":{"command":"cat /nonexistent-file"},"partialResult":{"content":[{"type":"text","text":"cat: /nonexistent-file: No such file or directory\n"}],"details":{}}}
{"type":"tool_execution_end","toolCallId":"call_cta082t7","toolName":"bash","result":{"content":[{"type":"text","text":"cat: /nonexistent-file: No such file or directory\n\n\nCommand exited with code 1"}],"details":{}},"isError":true}
{"type":"message_start","message":{"role":"toolResult","toolCallId":"call_cta082t7","toolName":"bash","content":[{"type":"text","text":"cat: /nonexistent-file: No such file or directory\n\n\nCommand exited with code 1"}],"details":{},"isError":true,"timestamp":1790382242598}}
{"type":"message_end","message":{"role":"toolResult","toolCallId":"call_cta082t7","toolName":"bash","content":[{"type":"text","text":"cat: /nonexistent-file: No such file or directory\n\n\nCommand exited with code 1"}],"details":{},"isError":true,"timestamp":1790382242598}}
{"type":"turn_end","message":{"role":"assistant","content":[{"type":"toolCall","id":"call_cta082t7","name":"bash","arguments":{"command":"cat /nonexistent-file"}}],"api":"openai-completions","provider":"ollama-cloud","model":"glm-5.3-flash","usage":{"input":5007,"output":15,"cacheRead":31360,"cacheWrite":0,"reasoning":0,"totalTokens":36382,"cost":{"input":0.00075105,"output":0.000007499999999999999,"cacheRead":0,"cacheWrite":0,"total":0.00075855}},"stopReason":"toolUse","timestamp":1790382240561,"responseId":"chatcmpl-207","rawStopReason":"tool_calls"},"toolResults":[{"role":"toolResult","toolCallId":"call_cta082t7","toolName":"bash","content":[{"type":"text","text":"cat: /nonexistent-file: No such file or directory\n\n\nCommand exited with code 1"}],"details":{},"isError":true,"timestamp":1790382242598}]}
{"type":"turn_start"}
{"type":"message_start","message":{"role":"assistant","content":[{"type":"thinking","thinking":"Both","thinkingSignature":"reasoning"}],"api":"openai-completions","provider":"ollama-cloud","model":"glm-5.3-flash","usage":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"totalTokens":0,"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0,"total":0}},"stopReason":"pending","timestamp":1790382242606,"responseId":"chatcmpl-491"}}
{"type":"message_end","message":{"role":"assistant","content":[{"type":"thinking","thinking":"Both commands run. Reply \"done\".","thinkingSignature":"reasoning"},{"type":"text","text":"done"}],"api":"openai-completions","provider":"ollama-cloud","model":"glm-5.3-flash","usage":{"input":5045,"output":11,"cacheRead":31360,"cacheWrite":0,"reasoning":0,"totalTokens":36416,"cost":{"input":0.0007567499999999999,"output":0.0000055,"cacheRead":0,"cacheWrite":0,"total":0.0007622499999999999}},"stopReason":"stop","timestamp":1790382242606,"responseId":"chatcmpl-491","rawStopReason":"stop"}}
{"type":"turn_end","message":{"role":"assistant","content":[{"type":"thinking","thinking":"Both commands run. Reply \"done\".","thinkingSignature":"reasoning"},{"type":"text","text":"done"}],"api":"openai-completions","provider":"ollama-cloud","model":"glm-5.3-flash","usage":{"input":5045,"output":11,"cacheRead":31360,"cacheWrite":0,"reasoning":0,"totalTokens":36416,"cost":{"input":0.0007567499999999999,"output":0.0000055,"cacheRead":0,"cacheWrite":0,"total":0.0007622499999999999}},"stopReason":"stop","timestamp":1790382242606,"responseId":"chatcmpl-491","rawStopReason":"stop"},"toolResults":[]}
{"type":"agent_end","messages":[],"willRetry":false}
{"type":"agent_settled"}
@@ -44,7 +44,7 @@ func readProjectMemory(path string) (string, error) {
return "Project memory from earlier sessions:\n" + strings.Join(entries, "\n"), nil
}
func (r persistentRunner) Run(ctx context.Context, workspace string, request agentrun.Request, report agentrun.ToolCallReporter) (agentrun.Result, error) {
func (r persistentRunner) Run(ctx context.Context, workspace string, request agentrun.Request, report agentrun.Reporter) (agentrun.Result, error) {
if !r.enabled {
return r.Runner.Run(ctx, workspace, request, report)
}
+6 -2
View File
@@ -33,6 +33,7 @@ import (
// worktreerpc; local git operations run on the bind-mounted worktree.
type remoteTrees interface {
Push(ctx context.Context) error
workflow.BaselineLedger
}
type hybridTrees struct {
@@ -185,7 +186,7 @@ func applyToolLimits(agent agentrun.Runner, policy config.ToolPolicy, allow []st
func stageRunners(req taskrun.Request, mcpSet *taskmcp.Set, newRunner runnerFactory, llm *runtime.Runtime, log *slog.Logger) (agentrun.Runner, error) {
if req.Harness != nil {
// The built-in loop has no route to a model from a Kit container.
return agentexec.HarnessStages{Runner: agentexec.NewHarnessRunner(nil), Spec: *req.Harness}, nil
return agentexec.HarnessStages{Runner: agentexec.NewHarnessRunner(), Spec: *req.Harness}, nil
}
var agent agentrun.Runner
if mcpSet != nil && mcpSet.Registry != nil {
@@ -246,7 +247,7 @@ func runTask(ctx context.Context, req taskrun.Request, dependencies taskDependen
bus = events.NewBus()
sub := bus.Subscribe(64)
defer sub.Close()
go agentexec.ForwardTaskEvents(sub, dependencies.events, req.Task.ID, log)
go agentexec.ForwardTaskEvents(ctx, sub, dependencies.events, req.Task.ID, log)
}
tc := &workflow.TaskContext{
@@ -263,6 +264,9 @@ func runTask(ctx context.Context, req taskrun.Request, dependencies taskDependen
Log: log,
Guardrails: dependencies.guardrails,
}
if dependencies.trees != nil {
tc.Baseline = dependencies.trees
}
tc.Instructions = req.Instructions
configureTaskContext(tc, workDir)
-16
View File
@@ -3,25 +3,18 @@ package agentworker
import (
"context"
"errors"
"log/slog"
"net/http"
"strconv"
"time"
"github.com/samcharles93/archie-core/internal/agentexec"
"github.com/samcharles93/archie-core/internal/domain/health"
"github.com/samcharles93/archie-core/internal/domain/presence"
"github.com/samcharles93/archie-core/internal/domain/storecontract"
"github.com/samcharles93/archie-core/internal/domain/workflow"
"github.com/samcharles93/archie-core/internal/domain/workflow/task"
"github.com/samcharles93/archie-core/internal/infrastructure/agentboot"
"github.com/samcharles93/archie-core/internal/infrastructure/agentgit"
agentnats "github.com/samcharles93/archie-core/internal/infrastructure/agenttransport/nats"
"github.com/samcharles93/archie-core/internal/infrastructure/egress"
"github.com/samcharles93/archie-core/internal/infrastructure/readiness"
"github.com/samcharles93/archie-core/internal/infrastructure/workflowsteps"
"github.com/samcharles93/archie-core/internal/installtype"
"github.com/samcharles93/archie-core/internal/logging"
"github.com/samcharles93/archie-core/internal/storage"
"github.com/samcharles93/archie-core/internal/taskrun"
@@ -67,8 +60,6 @@ type workerTransport interface {
Close()
LogPublisher() agentexec.LogPublisher
SubscribeTasks(context.Context, int64, agentnats.TaskHandler, *slog.Logger) (agentnats.Subscription, error)
PutPresence(context.Context, storecontract.Presence) error
BrokerReady() bool
}
type workerDependencies struct {
@@ -174,13 +165,6 @@ func run(ctx context.Context, settings Settings, log *slog.Logger, dependencies
}
}()
registry := health.NewRegistry(readiness.NewContractProbe("nats", 0, func(context.Context) error {
if !transport.BrokerReady() {
return errors.New("broker disconnected")
}
return nil
}))
go presence.Run(ctx, presence.Agent, presence.Build{InstanceID: strconv.FormatInt(taskID, 10), Version: Version(), InstallType: installtype.Type()}, transport, registry, log)
log.InfoContext(ctx, "archie-agent ready", "nats", settings.NATSURL)
dependencies.wait(ctx, log)
return nil
+5 -3
View File
@@ -12,11 +12,13 @@ import (
"github.com/samcharles93/archie-core/internal/config"
"github.com/samcharles93/archie-core/internal/domain/alert"
"github.com/samcharles93/archie-core/internal/domain/identity"
"github.com/samcharles93/archie-core/internal/domain/org"
"github.com/samcharles93/archie-core/internal/infrastructure/alertwebhook"
"github.com/samcharles93/archie-core/internal/infrastructure/controlplanerpc"
"github.com/samcharles93/archie-core/internal/infrastructure/controlplanestore"
"github.com/samcharles93/archie-core/internal/infrastructure/modelcatalog"
"github.com/samcharles93/archie-core/internal/infrastructure/publicnet"
"github.com/samcharles93/archie-core/internal/releaseupdate"
)
@@ -172,7 +174,7 @@ func providerAlerts(providers map[string]config.Provider) []alert.Input {
// instance org always among them.
func credentialOrgs(cfg config.Config) []org.OrgID {
orgs := []org.OrgID{org.DefaultOrgID}
for _, name := range append([]string{""}, identityNames(cfg)...) {
for _, name := range append([]string{string(identity.SystemID)}, identityNames(cfg)...) {
orgName, _ := cfg.CredentialAccess(name)
if id := org.OrgID(credentialOrg(orgName)); !slices.Contains(orgs, id) {
orgs = append(orgs, id)
@@ -202,7 +204,7 @@ func credentialOrg(name string) string {
func unboundAlerts(cfg config.Config) map[org.OrgID][]alert.Input {
out := map[org.OrgID][]alert.Input{}
seen := map[alert.Key]bool{}
for _, name := range append([]string{""}, identityNames(cfg)...) {
for _, name := range append([]string{string(identity.SystemID)}, identityNames(cfg)...) {
orgName, granted := cfg.CredentialAccess(name)
orgID := org.OrgID(credentialOrg(orgName))
bound := cfg.Containers.BoundCredentials(orgName, granted, granted)
@@ -301,7 +303,7 @@ func (b *boot) recheckAlerts(ctx context.Context) {
// as skipped; one that fails is retried by the store on its schedule.
func (b *boot) deliverAlerts(store alert.Deliverer) func(context.Context) {
client := &http.Client{Timeout: 15 * time.Second}
public := alertwebhook.PublicClient()
public := publicnet.Client(10*time.Second, 15*time.Second)
// The system org's webhook may sit on the instance's own network; another
// org's reaches the public internet only.
clientFor := func(owner org.OrgID) *http.Client {
+21 -62
View File
@@ -11,7 +11,6 @@ import (
"errors"
"fmt"
"log/slog"
"net/http"
"net/url"
"os"
"os/signal"
@@ -23,7 +22,6 @@ import (
"syscall"
"time"
"github.com/samcharles93/archie-core/internal/app/chattask"
"github.com/samcharles93/archie-core/internal/app/servicekit"
"github.com/samcharles93/archie-core/internal/config"
"github.com/samcharles93/archie-core/internal/container"
@@ -43,13 +41,12 @@ import (
"github.com/samcharles93/archie-core/internal/domain/workintake"
"github.com/samcharles93/archie-core/internal/events"
"github.com/samcharles93/archie-core/internal/forge"
forgewebhook "github.com/samcharles93/archie-core/internal/forge/webhook"
"github.com/samcharles93/archie-core/internal/gateway"
infraaccess "github.com/samcharles93/archie-core/internal/infrastructure/access"
"github.com/samcharles93/archie-core/internal/infrastructure/configuration"
"github.com/samcharles93/archie-core/internal/infrastructure/controlplanestore"
"github.com/samcharles93/archie-core/internal/infrastructure/eventbus/nats"
"github.com/samcharles93/archie-core/internal/infrastructure/extension"
"github.com/samcharles93/archie-core/internal/infrastructure/issuerpc"
"github.com/samcharles93/archie-core/internal/infrastructure/kitrun"
"github.com/samcharles93/archie-core/internal/infrastructure/logrpc"
"github.com/samcharles93/archie-core/internal/infrastructure/messagingrpc"
@@ -178,8 +175,6 @@ type boot struct {
// start, which read it as their resume points.
runtimeVersions map[string]int64
chatTasks gateway.TaskCreator
defaultChatIdentity string
// messaging delivers outbound chat messages through the Messaging Service.
messaging *messagingrpc.Client
@@ -294,7 +289,7 @@ func (b *boot) openStateStoreAdapter(ctx context.Context) error {
if target == "" {
return fmt.Errorf("services.state.target is required: archied/archie-gateway no longer own archie.db; the standalone archie-state-store process owns it (docs/prds/state-store-contract.md §12 step 7)")
}
client, cleanup, err := servicekit.StateStoreClient(presence.Daemon, b.cfg)
client, cleanup, err := servicekit.StateStoreClient(presence.Daemon, b.cfg, staterpc.WithCallDeadline(stateCallDeadline))
if err != nil {
b.log.ErrorContext(ctx, "state store adapter", "err", err)
return err
@@ -500,10 +495,8 @@ func (b *boot) setupContainers(ctx context.Context) func() {
return closeDocker
}
// setupGatewayClient dials the Gateway, which owns every model call. The daemon
// only enqueues the chat tasks scheduled workflows create.
// setupGatewayClient dials the Gateway, which owns every model call.
func (b *boot) setupGatewayClient(ctx context.Context) error {
b.setupChatTasks(b.cfg)
contract, cleanup, err := composeChatContract(b.cfg)
if err != nil {
return err
@@ -587,9 +580,21 @@ func (b *boot) registerNATSRPC() error {
return err
}
b.addCleanup(unsubscribeTaskActions)
unsubscribeIssues, err := (&issuerpc.Server{Forge: b.issueForge, Log: log}).Register(coreConn)
if err != nil {
log.Error("issue RPC register failed", "err", err)
return err
}
b.addCleanup(unsubscribeIssues)
return nil
}
// issueForge is the forge of owner/repo's own connection.
func (b *boot) issueForge(ctx context.Context, owner, repo string) (forge.IssueForge, error) {
return b.repositoryForge(ctx, owner, repo)
}
func (b *boot) buildDaemon() {
log := b.log
b.d = &daemon.Daemon{
@@ -614,7 +619,6 @@ func (b *boot) buildDaemon() {
TaskInstructions: b.taskInstructions,
IssueSources: b.issueSources,
OrgPrincipals: b.orgPrincipals,
RootIdentityID: identity.StableID(servicekit.IdentityNames(b.cfg)[0]),
TaskLogs: b.taskLogs,
AgentStatus: b.agentStatus,
WorkflowDefinitions: b.workflowDefinitions,
@@ -658,7 +662,6 @@ func (b *boot) buildDaemon() {
b.d.Denials = denials
}
b.d.PlaybookLedger = playbookLedger(b.stateStore, b.log)
b.setupForgeWebhook()
}
func playbookLedger(source any, log *slog.Logger) storecontract.PlaybookDispatcher {
@@ -669,43 +672,6 @@ func playbookLedger(source any, log *slog.Logger) storecontract.PlaybookDispatch
return nil
}
func (b *boot) setupForgeWebhook() {
cfg, log := b.cfg, b.log
if cfg.Forge.Intake != config.ForgeIntakeWebhook && cfg.Forge.Intake != config.ForgeIntakeBoth {
return
}
parser, ok := b.forgeClient.(forge.WebhookParser)
if !ok {
log.Error("forge webhook disabled: the forge cannot parse webhooks", "forge_type", cfg.Forge.Type)
return
}
secretValue, err := b.secrets.Resolve(cfg.Forge.WebhookSecret)
if err != nil || secretValue == "" {
log.Error("forge webhook disabled: secret unavailable",
"engine", cfg.Forge.WebhookSecret.Engine, "key", cfg.Forge.WebhookSecret.Key, "err", err)
return
}
receiver := forgewebhook.New(secretValue, parser, cfg.Dispatch.Trigger, cfg.Label, cfg.BotUser, b.d.PublishTask, b.d.PublishReaction, b.withdrawIssue, log)
host, port := parseListenAddr(cfg.Forge.WebhookAddr, "0.0.0.0", 8645)
addr := fmt.Sprintf("%s:%d", host, port)
srv := &http.Server{Addr: addr, Handler: receiver, ReadHeaderTimeout: 5 * time.Second}
b.startGateways = append(b.startGateways, func() {
go func() {
if err := srv.ListenAndServe(); err != nil && err != http.ErrServerClosed {
log.Error("forge webhook server stopped", "err", err)
}
}()
log.Info("forge webhook listening", "addr", addr)
})
b.addCleanup(func() {
shutdownCtx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
defer cancel()
_ = srv.Shutdown(shutdownCtx)
})
}
func (b *boot) publishConfig(ctx context.Context, cfg config.Config) {
b.cfgHolder.Set(cfg)
// The daemon owns the published configuration view.
@@ -822,18 +788,6 @@ func (b *boot) runLoop(ctx context.Context, once bool) error {
return nil
}
// setupChatTasks wires the task creator scheduled workflows enqueue through.
func (b *boot) setupChatTasks(cfg config.Config) {
profiles, defaultChatIdentity := chattask.Profiles(cfg)
if len(profiles) > 0 {
b.chatTasks = gateway.NewStoreTaskCreatorForProfiles(
chattask.Writer{Enqueue: b.stateStore.EnqueueChatTask},
profiles,
)
}
b.defaultChatIdentity = defaultChatIdentity
}
func (b *boot) addCleanup(fn func()) {
b.cleanups = append(b.cleanups, fn)
}
@@ -849,7 +803,12 @@ func (b *boot) loadCatalog(ctx context.Context) {
return
}
models := modelcatalog.Apply(&b.cfg, snapshot)
b.cfgHolder.Set(b.cfg.Clone())
// Layer the catalog over the live config, not b.cfg: b.cfg predates the
// execution-settings watch, so publishing it would put the file's budgets
// back over the control plane's.
live := b.cfgHolder.Get().Clone()
modelcatalog.Apply(&live, snapshot)
b.cfgHolder.Set(live)
b.catalog.Set(snapshot)
b.log.InfoContext(ctx, "model catalog loaded", "providers", len(snapshot.Providers), "models", len(models))
}
+2 -4
View File
@@ -4,7 +4,6 @@ import (
"context"
"encoding/json"
"github.com/samcharles93/archie-core/internal/app/servicekit"
"github.com/samcharles93/archie-core/internal/config"
"github.com/samcharles93/archie-core/internal/daemon"
"github.com/samcharles93/archie-core/internal/domain/access"
@@ -14,7 +13,7 @@ import (
)
// orgAgents is every organisation with the principals that may act in it,
// system org first. The system org's own root identity leads its list.
// system org first. System leads the system org's list.
type orgAgents struct {
owner org.OrgID
principals []access.Principal
@@ -63,8 +62,7 @@ func (b *boot) organisations(ctx context.Context) []orgAgents {
for _, owner := range b.owners(ctx, directory) {
entry := orgAgents{owner: owner}
if owner == org.DefaultOrgID && directory != nil {
root := identity.StableID(servicekit.IdentityNames(b.cfgHolder.Get())[0])
if principal, err := directory.PrincipalFor(ctx, root); err == nil {
if principal, err := directory.PrincipalFor(ctx, identity.SystemID); err == nil {
entry.principals = append(entry.principals, principal)
}
}
+3 -34
View File
@@ -12,11 +12,9 @@ import (
"flag"
"fmt"
"log/slog"
"net"
"os"
"os/signal"
"path/filepath"
"strconv"
"strings"
"syscall"
"time"
@@ -253,23 +251,6 @@ func persistEvents(ctx context.Context, sink *events.Sub, st storecontract.TaskS
}
}
// parseListenAddr splits "host:port" into components, using defaults
// when the input is empty or missing a part.
func parseListenAddr(addr, defaultHost string, defaultPort int) (string, int) {
if addr == "" {
return defaultHost, defaultPort
}
host, portStr, err := net.SplitHostPort(addr)
if err != nil {
return defaultHost, defaultPort
}
port, err := strconv.Atoi(portStr)
if err != nil || port < 0 {
return host, defaultPort
}
return host, port
}
// subscribeSystemLogs subscribes to every task's system log subject at once.
// archie-agent's own log lines ship here (agentexec.SubjectForSystem) rather
// than staying on its stderr, and this is where they land: one wildcard
@@ -362,25 +343,13 @@ func registerTaskRPCServers(nc *natsio.Conn, resolve func(context.Context, *work
resolved, err := resolve(ctx, t, config.OperationPR)
return resolved.Forge, err
}}
trees := &worktreerpc.Server{Runs: runs, Log: log, Resolve: func(ctx context.Context, t *workflow.Task) (*worktree.Manager, error) {
trees := &worktreerpc.Server{Runs: runs, Log: log, Baselines: worktreerpc.NewBaselineClaims(), Resolve: func(ctx context.Context, t *workflow.Task) (*worktree.Manager, error) {
resolved, err := resolve(ctx, t, config.OperationPush)
return resolved.Trees, err
}}
messages := &messagerpc.Server{Runs: runs, Deliver: deliver, Log: log}
for _, identity := range []string{"", "*"} {
stop, err := messages.RegisterFor(nc, identity)
if err != nil {
unsubscribe()
return nil, err
}
unsubs = append(unsubs, stop)
stop, err = fg.RegisterFor(nc, identity)
if err != nil {
unsubscribe()
return nil, err
}
unsubs = append(unsubs, stop)
stop, err = trees.RegisterFor(nc, identity)
for _, register := range []func(*natsio.Conn, string) (func(), error){messages.RegisterFor, fg.RegisterFor, trees.RegisterFor} {
stop, err := register(nc, "*")
if err != nil {
unsubscribe()
return nil, err
+2 -1
View File
@@ -104,7 +104,7 @@ func validOrigin(origin string) bool {
func outcomeText(t *task.Task) string {
title := notificationTitle(t.Title)
if kind := taskstate.ApprovalKind(t.Status, t.ReviewGate); kind != "" {
if kind := taskstate.ApprovalKind(t.Status, t.ReviewGate, t.RetryMode); kind != "" {
return fmt.Sprintf("Task %d (%s) needs your approval of its %s. Approve or reject it on the task page.", t.ID, title, approvalNoun[kind])
}
if t.Status == task.StatusPROpen {
@@ -141,4 +141,5 @@ func notificationTitle(title string) string {
var approvalNoun = map[string]string{
taskstate.ApprovalPlan: "plan",
taskstate.ApprovalReview: "review findings",
taskstate.ApprovalBudget: "request to continue past its step budget",
}
+35
View File
@@ -34,6 +34,12 @@ func (b *boot) setupReadinessProbes() {
_, err := b.stateStore.StatusCounts(ctx)
return err
}),
runLoopProbe{stalest: func() (string, time.Time) {
if b.d == nil {
return "", time.Time{}
}
return b.d.StalestLoop()
}, cadence: b.loopCadence},
readiness.NewConfigProbe(b.cfgHolder.Get, configuration.Validate),
readiness.NewDiskProbeTargets(diskProbeTargets(cfg)),
// The daemon no longer runs a chat channel, so it cannot observe one's
@@ -100,3 +106,32 @@ func (unscopedBroker) Name() string { return "nats_credential_scope" }
func (unscopedBroker) Check(context.Context) health.Result {
return health.Result{Status: health.StatusDegraded, Detail: "external NATS: containers get a broker token that reaches every subject; use the embedded broker"}
}
// stateCallDeadline bounds each State Store call the daemon makes without a
// deadline of its own.
const stateCallDeadline = 20 * time.Second
// runLoopStallFactor is how many poll intervals a loop may go without
// beginning a pass before it is reported degraded.
const runLoopStallFactor = 3
// runLoopProbe reports a run loop that has stopped beginning passes, for
// instance blocked on a slow State Store.
type runLoopProbe struct {
stalest func() (string, time.Time)
cadence func() time.Duration
}
func (runLoopProbe) Name() string { return "run_loop" }
func (p runLoopProbe) Check(context.Context) health.Result {
loop, last := p.stalest()
if last.IsZero() {
return health.Result{Status: health.StatusOK}
}
limit := max(p.cadence()*runLoopStallFactor, time.Minute)
if age := time.Since(last); age > limit {
return health.Result{Status: health.StatusDegraded, Detail: loop + " loop has not begun a pass for " + age.Round(time.Second).String()}
}
return health.Result{Status: health.StatusOK}
}
+49 -5
View File
@@ -17,7 +17,13 @@ import (
const releaseUsage = `usage: archied release <command>
keygen -seed FILE write a new signing key's seed to FILE and print its public key
publish sign a release and push it to a release source`
publish sign a release and push it to a release source's next channel
promote -version V point stable at a published release by hand
canary status show the canary's channel, installed release, window and verdict (read-only)
canary start point the canary at next and install a release on it, queued behind one being judged
canary check judge the release the canary runs: promote it, pick up a newer next, or roll back
canary promote promote the release the canary runs now, if its signals pass
canary unpin return the canary to the next channel from any pin`
// RunRelease is the publisher's side of a release source: it makes the key
// a source signs with and pushes signed releases to it.
@@ -31,6 +37,10 @@ func RunRelease(args []string, out, stderr io.Writer) int {
return runReleaseKeygen(args[1:], out, stderr)
case "publish":
return runReleasePublish(args[1:], out, stderr)
case "promote":
return runReleasePromote(args[1:], out, stderr)
case "canary":
return runReleaseCanary(args[1:], out, stderr)
default:
fmt.Fprintln(stderr, releaseUsage)
return 2
@@ -79,7 +89,7 @@ func runReleasePublish(args []string, out, stderr io.Writer) int {
flags.StringVar(&req.Repository, "source", "", "OCI repository to publish to")
seedEnv := flags.String("seed-env", "ARCHIE_RELEASE_SEED", "environment variable holding the base64 private key seed")
flags.StringVar(&req.Version, "version", "", "release version")
flags.BoolVar(&req.Prerelease, "prerelease", false, "publish to next only")
flags.BoolVar(&req.Prerelease, "prerelease", false, "mark the release a prerelease, which never reaches stable")
flags.StringVar(&req.ZipPath, "zip", "", "distribution zip")
flags.StringVar(&req.AgentImage, "agent-image", "", "agent image pinned by digest")
flags.StringVar(&req.Changelog, "changelog", "", "URL of the release notes")
@@ -97,10 +107,8 @@ func runReleasePublish(args []string, out, stderr io.Writer) int {
}
req.Signer = ed25519.NewKeyFromSeed(seed)
public := distribution.EncodeKey(ed25519.PublicKey(req.Signer[ed25519.SeedSize:]))
// stable moves only when the canary promotes the release.
req.Channels = []string{"next"}
if !req.Prerelease {
req.Channels = append(req.Channels, "stable")
}
statement, err := releaseupdate.Publish(context.Background(), req)
if err != nil {
fmt.Fprintln(stderr, err)
@@ -110,3 +118,39 @@ func runReleasePublish(args []string, out, stderr io.Writer) int {
strings.Join(req.Channels, ", "), public)
return 0
}
// runReleasePromote moves stable without a canary verdict, under the same
// rules the canary promotes by.
func runReleasePromote(args []string, out, stderr io.Writer) int {
flags := flag.NewFlagSet("release promote", flag.ContinueOnError)
flags.SetOutput(stderr)
reference := flags.String("source", "", "OCI repository releases are published to; blank is the official releases")
key := flags.String("key", "", "base64 ed25519 public key the source signs with")
version := flags.String("version", "", "release to promote")
latest := flags.String("latest", "", "comma-separated image repositories whose v<version> tag becomes latest")
if err := flags.Parse(args); err != nil {
return 2
}
source, err := distribution.Parse(*reference, *key, distribution.DefaultReleases())
if err != nil || *version == "" {
fmt.Fprintln(stderr, "release promote: -version is required, and -source with -key name another source")
return 2
}
statement, err := releaseupdate.Promote(context.Background(), source.Reference, source.Key, *version, splitList(*latest))
if err != nil {
fmt.Fprintln(stderr, err)
return 1
}
fmt.Fprintf(out, "stable is %s\n", statement.Version)
return 0
}
func splitList(value string) []string {
var items []string
for item := range strings.SplitSeq(value, ",") {
if item = strings.TrimSpace(item); item != "" {
items = append(items, item)
}
}
return items
}
+656
View File
@@ -0,0 +1,656 @@
package archied
import (
"bytes"
"context"
"errors"
"flag"
"fmt"
"io"
"os"
"os/exec"
"strings"
"time"
"oras.land/oras-go/v2/errdef"
"github.com/samcharles93/archie-core/internal/domain/distribution"
"github.com/samcharles93/archie-core/internal/releaseupdate"
)
// canaryInstallWait bounds how long an install on the canary may take,
// including the watchdog's health wait and a rollback.
const canaryInstallWait = 20 * time.Minute
// migrationsDir holds the schema migrations; a release that changes it can't
// be rolled back without restoring the database snapshot.
const migrationsDir = "internal/infrastructure/postgres/migrations"
func runReleaseCanary(args []string, out, stderr io.Writer) int {
if len(args) == 0 {
fmt.Fprintln(stderr, releaseUsage)
return 2
}
switch args[0] {
case "status":
return runCanaryStatus(args[1:], out, stderr)
case "start":
return runCanaryStart(args[1:], out, stderr)
case "check":
return runCanaryCheck(args[1:], out, stderr)
case "promote":
return runCanaryPromote(args[1:], out, stderr)
case "unpin":
return runCanaryUnpin(args[1:], out, stderr)
default:
fmt.Fprintln(stderr, releaseUsage)
return 2
}
}
// addCanaryFlags registers the flags every canary subcommand takes.
func addCanaryFlags(flags *flag.FlagSet) (dashboardURL, tokenEnv *string) {
dashboardURL = flags.String("dashboard", "", "canary dashboard URL")
tokenEnv = flags.String("token-env", "ARCHIE_CANARY_TOKEN", "environment variable holding a dashboard API token for the canary")
return dashboardURL, tokenEnv
}
// addSourceFlags registers the flags naming the release source.
func addSourceFlags(flags *flag.FlagSet) (reference, key *string) {
reference = flags.String("source", "", "OCI repository releases are published to; blank is the official releases")
key = flags.String("key", "", "base64 ed25519 public key the source signs with")
return reference, key
}
func canaryDashboard(url, tokenEnv string) (releaseupdate.CanaryDashboard, error) {
if url == "" {
return releaseupdate.CanaryDashboard{}, errors.New("-dashboard is required")
}
return releaseupdate.CanaryDashboard{URL: url, Token: os.Getenv(tokenEnv)}, nil
}
func canarySource(reference, key string) (distribution.Source, error) {
return distribution.Parse(reference, key, distribution.DefaultReleases())
}
// fetchChannel fetches a channel tag; found is false when the channel has no
// release yet.
func fetchChannel(ctx context.Context, source distribution.Source, tag string) (release releaseupdate.Release, found bool, err error) {
release, err = releaseupdate.Fetch(ctx, source, tag)
if errors.Is(err, errdef.ErrNotFound) {
return releaseupdate.Release{}, false, nil
}
return release, err == nil, err
}
// publishedChannels are the releases the source currently publishes.
type publishedChannels struct {
next, stable releaseupdate.Release
hasNext, hasStable bool
}
func fetchChannels(ctx context.Context, source distribution.Source) (publishedChannels, error) {
var channels publishedChannels
var err error
if channels.next, channels.hasNext, err = fetchChannel(ctx, source, "next"); err != nil {
return channels, err
}
if channels.stable, channels.hasStable, err = fetchChannel(ctx, source, "stable"); err != nil {
return channels, err
}
return channels, nil
}
// canaryRun is the release the canary actually runs: its version, when it was
// installed and its fetched release statement.
type canaryRun struct {
version string
installedAt time.Time
release releaseupdate.Release
found bool
}
// readCanaryRun reads what the canary runs. A host that doesn't record install
// times (it updated before they were tracked) degrades to the release
// statement's issue time.
func readCanaryRun(ctx context.Context, dashboard releaseupdate.CanaryDashboard, source distribution.Source) (canaryRun, error) {
var run canaryRun
version, installedAt, _, err := dashboard.Installed(ctx)
if err != nil {
return run, err
}
run.version, run.installedAt = version, installedAt
release, found, err := fetchChannel(ctx, source, releaseupdate.Tag("exact-pin", version))
if err != nil {
return run, err
}
run.release, run.found = release, found
if run.installedAt.IsZero() && found {
run.installedAt = release.Statement.IssuedAt
}
return run, nil
}
// newerIssued reports whether release a was issued after b. IssuedAt, not
// semver order: Promote refuses a release issued before the one stable names,
// so the judge must agree with that replay rule.
func newerIssued(a, b releaseupdate.Release) bool {
return a.Statement.IssuedAt.After(b.Statement.IssuedAt)
}
func displayVersion(version string) string {
if version == "" {
return "unknown"
}
return version
}
func displayRelease(release releaseupdate.Release, found bool) string {
if !found {
return "none"
}
return release.Statement.Version
}
func printVerdict(out io.Writer, version string, verdict releaseupdate.CanaryVerdict) {
fmt.Fprintf(out, "%s: %s\n", displayVersion(version), verdict.Decision)
for _, reason := range verdict.Reasons {
fmt.Fprintf(out, " %s\n", reason)
}
}
func runCanaryStatus(args []string, out, stderr io.Writer) int {
flags := flag.NewFlagSet("release canary status", flag.ContinueOnError)
flags.SetOutput(stderr)
dashboardURL, tokenEnv := addCanaryFlags(flags)
reference, key := addSourceFlags(flags)
window := flags.Duration("window", releaseupdate.CanaryWindow, "window a release is judged over, counted from its install")
if err := flags.Parse(args); err != nil {
return 2
}
dashboard, err := canaryDashboard(*dashboardURL, *tokenEnv)
if err != nil {
fmt.Fprintln(stderr, "release canary status:", err)
return 2
}
source, err := canarySource(*reference, *key)
if err != nil {
fmt.Fprintln(stderr, "release canary status:", err)
return 2
}
if err := printCanaryStatus(context.Background(), dashboard, source, *window, out); err != nil {
fmt.Fprintln(stderr, "release canary status:", err)
return 1
}
return 0
}
// printCanaryStatus reports the canary's channel, installed release, the
// published channels, window progress and the verdict the current signals
// would give, without acting on anything.
func printCanaryStatus(ctx context.Context, dashboard releaseupdate.CanaryDashboard, source distribution.Source, window time.Duration, out io.Writer) error {
channel, pin, err := dashboard.Channel(ctx)
if err != nil {
return err
}
channels, err := fetchChannels(ctx, source)
if err != nil {
return err
}
run, err := readCanaryRun(ctx, dashboard, source)
if err != nil {
return err
}
printCanaryState(out, channel, pin, run, channels, window)
return printCanaryVerdict(ctx, dashboard, run, window, out)
}
func printCanaryState(out io.Writer, channel, pin string, run canaryRun, channels publishedChannels, window time.Duration) {
fmt.Fprintf(out, "channel: %s\n", channelDisplay(channel, pin))
fmt.Fprintf(out, "installed: %s", displayVersion(run.version))
if run.installedAt.IsZero() {
fmt.Fprintln(out, " (installed_at not reported)")
} else {
fmt.Fprintf(out, " since %s\n", run.installedAt.Format(time.RFC3339))
}
fmt.Fprintf(out, "stable: %s\n", displayRelease(channels.stable, channels.hasStable))
fmt.Fprintf(out, "next: %s\n", displayRelease(channels.next, channels.hasNext))
if run.installedAt.IsZero() {
fmt.Fprintln(out, "window: unknown, no install time to count from")
} else {
elapsed := time.Since(run.installedAt)
fmt.Fprintf(out, "window: %s of %s elapsed since the install\n", elapsed.Round(time.Minute), window)
}
}
func printCanaryVerdict(ctx context.Context, dashboard releaseupdate.CanaryDashboard, run canaryRun, window time.Duration, out io.Writer) error {
if run.installedAt.IsZero() {
fmt.Fprintln(out, "verdict: unknown, no install time to judge from")
return nil
}
now := time.Now().UTC()
signals, err := dashboard.Signals(ctx, run.installedAt, now, window)
if err != nil {
return fmt.Errorf("read canary signals: %w", err)
}
printSignals(out, signals)
verdict := releaseupdate.JudgeCanary(run.version, run.installedAt, now, window, signals)
fmt.Fprintf(out, "verdict on %s: %s (read-only)\n", displayVersion(run.version), verdict.Decision)
for _, reason := range verdict.Reasons {
fmt.Fprintf(out, " %s\n", reason)
}
return nil
}
func printSignals(out io.Writer, s releaseupdate.CanarySignals) {
fmt.Fprintf(out, "signals: runs %q, ready=%t, new action alerts=%d\n", s.Installed, s.Ready, len(s.NewActionAlerts))
fmt.Fprintf(out, " tasks finished %d, parked or died %d (baseline %d, %d)\n",
s.Canary.Finished, s.Canary.Bad, s.Baseline.Finished, s.Baseline.Bad)
fmt.Fprintf(out, " error lines %d, log covers %s (baseline %d, covers %s)\n",
s.Canary.Errors, s.Canary.Covered.Round(time.Minute), s.Baseline.Errors, s.Baseline.Covered.Round(time.Minute))
}
func channelDisplay(channel, pin string) string {
if pin != "" {
return channel + " (pinned to " + pin + ")"
}
return channel
}
func runCanaryStart(args []string, out, stderr io.Writer) int {
flags := flag.NewFlagSet("release canary start", flag.ContinueOnError)
flags.SetOutput(stderr)
dashboardURL, tokenEnv := addCanaryFlags(flags)
reference, key := addSourceFlags(flags)
version := flags.String("version", "", "release to install on the canary")
force := flags.Bool("force", false, "install even when the canary is still judging a newer release")
if err := flags.Parse(args); err != nil {
return 2
}
dashboard, err := canaryDashboard(*dashboardURL, *tokenEnv)
if err != nil {
fmt.Fprintln(stderr, "release canary start:", err)
return 2
}
if *version == "" {
fmt.Fprintln(stderr, "release canary start: -version is required")
return 2
}
source, err := canarySource(*reference, *key)
if err != nil {
fmt.Fprintln(stderr, "release canary start:", err)
return 2
}
if err := startCanary(context.Background(), dashboard, source, *version, *force, out); err != nil {
fmt.Fprintln(stderr, "release canary start:", err)
return 1
}
return 0
}
// startCanary points the canary at next — clearing any rollback pin — and
// installs version on it. A release published while the canary still judges a
// newer one queues behind it, so the running window isn't restarted under a
// different release.
func startCanary(ctx context.Context, dashboard releaseupdate.CanaryDashboard, source distribution.Source, version string, force bool, out io.Writer) error {
// The channel is read before following next: a canary already on next is
// judging the release it runs, and a new release queues behind that one.
channel, _, err := dashboard.Channel(ctx)
if err != nil {
return err
}
if err := dashboard.Follow(ctx, "next", ""); err != nil {
return fmt.Errorf("point the canary at next: %w", err)
}
if !force {
queued, err := queuedBehind(ctx, dashboard, source, channel, version, out)
if err != nil {
return err
}
if queued {
return nil
}
}
if err := dashboard.Install(ctx, version, canaryInstallWait); err != nil {
return err
}
fmt.Fprintf(out, "the canary follows next and runs %s\n", version)
return nil
}
// queuedBehind reports whether version must wait: the canary already follows
// next and is still judging the release it runs (a judgeable one), which is a
// different release from version.
func queuedBehind(ctx context.Context, dashboard releaseupdate.CanaryDashboard, source distribution.Source, channel, version string, out io.Writer) (bool, error) {
if channel != "next" {
return false, nil
}
run, err := readCanaryRun(ctx, dashboard, source)
if err != nil {
return false, err
}
if run.version == version {
return false, nil
}
channels, err := fetchChannels(ctx, source)
if err != nil {
return false, err
}
if judgeable(run, channels) {
fmt.Fprintf(out, "%s is queued behind %s, which the canary is still judging\n", version, run.version)
return true, nil
}
return false, nil
}
func runCanaryCheck(args []string, out, stderr io.Writer) int {
flags := flag.NewFlagSet("release canary check", flag.ContinueOnError)
flags.SetOutput(stderr)
dashboardURL, tokenEnv := addCanaryFlags(flags)
reference, key := addSourceFlags(flags)
latest := flags.String("latest", "", "comma-separated image repositories whose v<version> tag becomes latest on promotion")
checkout := flags.String("checkout", ".", "repository checkout with release tags, to see whether a release migrated the database")
window := flags.Duration("window", releaseupdate.CanaryWindow, "window the installed release is judged over, counted from its install")
if err := flags.Parse(args); err != nil {
return 2
}
dashboard, err := canaryDashboard(*dashboardURL, *tokenEnv)
if err != nil {
fmt.Fprintln(stderr, "release canary check:", err)
return 2
}
source, err := canarySource(*reference, *key)
if err != nil {
fmt.Fprintln(stderr, "release canary check:", err)
return 2
}
code, err := checkCanary(context.Background(), dashboard, source, splitList(*latest), *checkout, *window, out)
if err != nil {
fmt.Fprintln(stderr, "release canary check:", err)
return 1
}
return code
}
// checkCanary judges the release the canary actually runs — not the moving
// next tag — and acts on the verdict. The exit code is 1 when the run should
// show red: a rollback happened, or the canary is held on a pin that can no
// longer be installed.
func checkCanary(ctx context.Context, dashboard releaseupdate.CanaryDashboard, source distribution.Source, latest []string, checkout string, window time.Duration, out io.Writer) (int, error) {
channels, err := fetchChannels(ctx, source)
if err != nil {
return 1, err
}
channel, pin, err := dashboard.Channel(ctx)
if err != nil {
return 1, err
}
if channel != "next" {
return heldCanary(ctx, source, channel, pin, out)
}
run, err := readCanaryRun(ctx, dashboard, source)
if err != nil {
return 1, err
}
if !judgeable(run, channels) {
fmt.Fprintf(out, "nothing to judge: the canary runs %s\n", displayVersion(run.version))
return pickupNext(ctx, dashboard, channels, run.version, out)
}
return judgeInstalled(ctx, dashboard, source, run, channels, latest, checkout, window, out)
}
// judgeable reports whether the installed release is one the canary judges: a
// published, non-prerelease release issued after stable's.
func judgeable(run canaryRun, channels publishedChannels) bool {
if !run.found || run.release.Statement.Prerelease {
return false
}
return !channels.hasStable || newerIssued(run.release, channels.stable)
}
func judgeInstalled(ctx context.Context, dashboard releaseupdate.CanaryDashboard, source distribution.Source, run canaryRun, channels publishedChannels, latest []string, checkout string, window time.Duration, out io.Writer) (int, error) {
now := time.Now().UTC()
signals, err := dashboard.Signals(ctx, run.installedAt, now, window)
if err != nil {
return 1, fmt.Errorf("read canary signals: %w", err)
}
verdict := releaseupdate.JudgeCanary(run.version, run.installedAt, now, window, signals)
printVerdict(out, run.version, verdict)
switch verdict.Decision {
case releaseupdate.CanaryPromote:
return 0, promoteJudged(ctx, dashboard, source, run, channels, latest, out)
case releaseupdate.CanaryRollBack:
return 1, rollBackCanary(ctx, dashboard, source, run, channels, checkout, out)
default:
return 0, nil
}
}
// promoteJudged moves stable to the judged release, then picks up a newer next
// queued behind it.
func promoteJudged(ctx context.Context, dashboard releaseupdate.CanaryDashboard, source distribution.Source, run canaryRun, channels publishedChannels, latest []string, out io.Writer) error {
if _, err := releaseupdate.Promote(ctx, source.Reference, source.Key, run.version, latest); err != nil {
return fmt.Errorf("promote %s: %w", run.version, err)
}
fmt.Fprintf(out, "stable is %s\n", run.version)
fresh := channels
fresh.stable, fresh.hasStable = run.release, true
_, err := pickupNext(ctx, dashboard, fresh, run.version, out)
return err
}
// pickupNext installs the next release when it is newer than stable and the
// canary doesn't already run it.
func pickupNext(ctx context.Context, dashboard releaseupdate.CanaryDashboard, channels publishedChannels, installed string, out io.Writer) (int, error) {
if !channels.hasNext || channels.next.Statement.Version == installed {
return 0, nil
}
if channels.hasStable && !newerIssued(channels.next, channels.stable) {
return 0, nil
}
if err := dashboard.Install(ctx, channels.next.Statement.Version, canaryInstallWait); err != nil {
return 1, err
}
fmt.Fprintf(out, "the canary picks up %s from next\n", channels.next.Statement.Version)
return 0, nil
}
// heldCanary reports a canary that isn't following next. Its pin must still be
// installable: a stranded pin fails the run instead of looking green.
func heldCanary(ctx context.Context, source distribution.Source, channel, pin string, out io.Writer) (int, error) {
if pin != "" {
err := checkPin(ctx, source, pin)
if errors.Is(err, errStrandedPin) {
fmt.Fprintf(out, "ERROR: the canary is held on %s %s, which is stranded: %v; unpin it or republish the release\n", channel, pin, err)
return 1, nil
}
if err != nil {
return 1, err
}
fmt.Fprintf(out, "held on %s %s, nothing to judge\n", channel, pin)
return 0, nil
}
fmt.Fprintf(out, "held on %s, nothing to judge\n", channel)
return 0, nil
}
// errStrandedPin marks a held pin that can no longer be installed.
var errStrandedPin = errors.New("pin is stranded")
// checkPin fails when a held pin can no longer be installed: the release is
// gone from the source, or its artifacts are.
func checkPin(ctx context.Context, source distribution.Source, pin string) error {
release, found, err := fetchChannel(ctx, source, releaseupdate.Tag("exact-pin", pin))
if err != nil {
return err
}
if !found {
return fmt.Errorf("%w: no release %s in the source", errStrandedPin, releaseupdate.Tag("exact-pin", pin))
}
if err := releaseupdate.Installable(ctx, source, release); err != nil {
return fmt.Errorf("%w: %w", errStrandedPin, err)
}
return nil
}
// rollBackCanary returns the canary to stable after a failed verdict. stable
// is checked installable before the canary is pinned to it: a pin whose
// artifacts are gone would strand the canary, so the run fails loudly and the
// canary stays on next. A release that changed the migrations is held on the
// failed version instead, because going back past a migration needs the
// pre-update database snapshot.
func rollBackCanary(ctx context.Context, dashboard releaseupdate.CanaryDashboard, source distribution.Source, run canaryRun, channels publishedChannels, checkout string, out io.Writer) error {
failed := run.version
if !channels.hasStable {
return holdCanary(ctx, dashboard, failed, "there's no stable release to return to", out)
}
stable := channels.stable
if err := releaseupdate.Installable(ctx, source, stable); err != nil {
return fmt.Errorf("stable %s is not installable, the canary stays on next: %w", stable.Statement.Version, err)
}
changed, err := migrated(ctx, checkout, stable.Statement.Version, failed)
if err != nil {
return holdCanary(ctx, dashboard, failed, err.Error(), out)
}
if changed {
return holdCanary(ctx, dashboard, failed, failed+" changed the database schema", out)
}
if err := dashboard.Follow(ctx, "exact-pin", stable.Statement.Version); err != nil {
return fmt.Errorf("pin the canary to %s: %w", stable.Statement.Version, err)
}
if err := dashboard.Install(ctx, stable.Statement.Version, canaryInstallWait); err != nil {
return fmt.Errorf("return the canary to %s: %w", stable.Statement.Version, err)
}
fmt.Fprintf(out, "the canary is back on %s and stable is unchanged\n", stable.Statement.Version)
return nil
}
func holdCanary(ctx context.Context, dashboard releaseupdate.CanaryDashboard, version, why string, out io.Writer) error {
if err := dashboard.Follow(ctx, "exact-pin", version); err != nil {
return fmt.Errorf("hold the canary on %s: %w", version, err)
}
fmt.Fprintf(out, "%s: the canary is held on %s and stable is unchanged; fix forward\n", why, version)
return nil
}
// runGitDiff runs git diff --quiet between two release tags and reports its
// exit code and stderr. It is a variable so tests can drive the three
// outcomes without a repository.
var runGitDiff = func(ctx context.Context, checkout, from, to string) (int, string, error) {
cmd := exec.CommandContext(ctx, "git", "-C", checkout, "diff", "--quiet", "v"+from, "v"+to, "--", migrationsDir)
var buf bytes.Buffer
cmd.Stderr = &buf
err := cmd.Run()
if err == nil {
return 0, "", nil
}
if exitErr, ok := errors.AsType[*exec.ExitError](err); ok {
return exitErr.ExitCode(), buf.String(), err
}
return -1, buf.String(), err
}
// migrated reports whether the migrations differ between two release tags.
// It returns true, nil when they differ, false, nil when they are identical,
// and true, err when git could not answer, with the reason in err. Every
// non-identical outcome holds the canary rather than rolls it back.
func migrated(ctx context.Context, checkout, from, to string) (bool, error) {
code, stderr, runErr := runGitDiff(ctx, checkout, from, to)
switch code {
case 0:
return false, nil
case 1:
return true, nil
}
reason := strings.TrimSpace(stderr)
if reason == "" && runErr != nil {
reason = runErr.Error()
}
return true, fmt.Errorf("could not tell whether %s changed the database schema: %s", to, reason)
}
func runCanaryPromote(args []string, out, stderr io.Writer) int {
flags := flag.NewFlagSet("release canary promote", flag.ContinueOnError)
flags.SetOutput(stderr)
dashboardURL, tokenEnv := addCanaryFlags(flags)
reference, key := addSourceFlags(flags)
latest := flags.String("latest", "", "comma-separated image repositories whose v<version> tag becomes latest on promotion")
version := flags.String("version", "", "release expected on the canary; must match what it runs")
window := flags.Duration("window", releaseupdate.CanaryWindow, "window the signals are read over, counted from the install")
if err := flags.Parse(args); err != nil {
return 2
}
dashboard, err := canaryDashboard(*dashboardURL, *tokenEnv)
if err != nil {
fmt.Fprintln(stderr, "release canary promote:", err)
return 2
}
source, err := canarySource(*reference, *key)
if err != nil {
fmt.Fprintln(stderr, "release canary promote:", err)
return 2
}
code, err := promoteCanaryNow(context.Background(), dashboard, source, *version, splitList(*latest), *window, out)
if err != nil {
fmt.Fprintln(stderr, "release canary promote:", err)
return 1
}
return code
}
// promoteCanaryNow promotes the release the canary runs right now, without
// waiting out the window: the signals must show no hard failure and no
// relative breach. It refuses, with exit 1, when anything fails.
func promoteCanaryNow(ctx context.Context, dashboard releaseupdate.CanaryDashboard, source distribution.Source, expectVersion string, latest []string, window time.Duration, out io.Writer) (int, error) {
run, err := readCanaryRun(ctx, dashboard, source)
if err != nil {
return 1, err
}
channel, pin, err := dashboard.Channel(ctx)
if err != nil {
return 1, err
}
fmt.Fprintf(out, "channel: %s\n", channelDisplay(channel, pin))
if expectVersion != "" && expectVersion != run.version {
return 1, fmt.Errorf("the canary runs %s, not %s", displayVersion(run.version), expectVersion)
}
if !run.found {
return 1, fmt.Errorf("no release %s in the source to promote", displayVersion(run.version))
}
now := time.Now().UTC()
signals, err := dashboard.Signals(ctx, run.installedAt, now, window)
if err != nil {
return 1, fmt.Errorf("read canary signals: %w", err)
}
verdict := releaseupdate.JudgeCanaryNow(run.version, now, window, signals)
printVerdict(out, run.version, verdict)
if verdict.Decision == releaseupdate.CanaryRollBack {
fmt.Fprintln(out, "refusing to promote: the canary's signals fail")
return 1, nil
}
if _, err := releaseupdate.Promote(ctx, source.Reference, source.Key, run.version, latest); err != nil {
return 1, fmt.Errorf("promote %s: %w", run.version, err)
}
fmt.Fprintf(out, "stable is %s\n", run.version)
return 0, nil
}
func runCanaryUnpin(args []string, out, stderr io.Writer) int {
flags := flag.NewFlagSet("release canary unpin", flag.ContinueOnError)
flags.SetOutput(stderr)
dashboardURL, tokenEnv := addCanaryFlags(flags)
if err := flags.Parse(args); err != nil {
return 2
}
dashboard, err := canaryDashboard(*dashboardURL, *tokenEnv)
if err != nil {
fmt.Fprintln(stderr, "release canary unpin:", err)
return 2
}
if err := dashboard.Follow(context.Background(), "next", ""); err != nil {
fmt.Fprintln(stderr, "release canary unpin:", err)
return 1
}
fmt.Fprintln(out, "the canary follows next again, with no pin")
return 0
}
@@ -0,0 +1,57 @@
package archied
import (
"context"
"strings"
"testing"
)
func TestMigrated(t *testing.T) {
tests := []struct {
name string
code int
stderr string
wantChanged bool
wantErr bool
wantSubstr string
}{
{
name: "identical migrations",
code: 0,
wantChanged: false,
},
{
name: "migrations differ",
code: 1,
wantChanged: true,
},
{
name: "git cannot answer",
code: 128,
stderr: "fatal: bad revision 'v1.0.0'\n",
wantChanged: true,
wantErr: true,
wantSubstr: "fatal: bad revision 'v1.0.0'",
},
}
for _, tt := range tests {
t.Run(tt.name, func(t *testing.T) {
old := runGitDiff
runGitDiff = func(context.Context, string, string, string) (int, string, error) {
return tt.code, tt.stderr, nil
}
t.Cleanup(func() { runGitDiff = old })
changed, err := migrated(context.Background(), ".", "1.0.0", "1.1.0")
if changed != tt.wantChanged {
t.Fatalf("changed = %v, want %v", changed, tt.wantChanged)
}
if (err != nil) != tt.wantErr {
t.Fatalf("err = %v, want err %v", err, tt.wantErr)
}
if tt.wantErr && !strings.Contains(err.Error(), tt.wantSubstr) {
t.Fatalf("err = %q, want substring %q", err, tt.wantSubstr)
}
})
}
}
+130 -6
View File
@@ -3,8 +3,14 @@ package archied
import (
"context"
"encoding/json"
"errors"
"fmt"
"io/fs"
"path/filepath"
"strings"
"syscall"
"github.com/go-git/go-git/v6"
"github.com/samcharles93/archie-core/internal/config"
"github.com/samcharles93/archie-core/internal/daemon"
@@ -12,6 +18,7 @@ import (
"github.com/samcharles93/archie-core/internal/domain/org"
"github.com/samcharles93/archie-core/internal/domain/workflow"
"github.com/samcharles93/archie-core/internal/forge"
"github.com/samcharles93/archie-core/internal/infrastructure/configuration"
"github.com/samcharles93/archie-core/internal/infrastructure/controlplanestore"
"github.com/samcharles93/archie-core/internal/worktree"
)
@@ -52,6 +59,38 @@ func (b *boot) repositoryAccess(ctx context.Context, task *workflow.Task, operat
return failure("connection_missing", "The selected connection no longer exists. Choose another connection.")
}
// repositoryForge is the forge client of owner/repo's own connection, for
// operator and chat actions, in the org ctx carries. The instance's default
// forge may be a different host entirely.
func (b *boot) repositoryForge(ctx context.Context, owner, repo string) (forge.Forge, error) {
repository, err := b.repositoryBinding(ctx, owner, repo)
if err != nil {
return nil, err
}
if repository.Connection == "" {
return nil, &forge.AccessError{Code: "connection_required", Message: "Choose a connection for this repository."}
}
connections, err := b.repositoryConnections(ctx)
if err != nil {
return nil, err
}
for _, connection := range connections {
if connection.ID != repository.Connection {
continue
}
token, code, message := b.connectionToken(ctx, connection)
if code != "" {
return nil, &forge.AccessError{Code: code, Connection: connection.ID, Message: message}
}
client := b.connectionForge(ctx, connection, org.OrgFromContext(ctx), token)
if _, disabled := client.(*forge.NoopForge); disabled {
return nil, &forge.AccessError{Code: "forge_unavailable", Connection: connection.ID, Message: "Enable the forge extension for this connection."}
}
return client, nil
}
return nil, &forge.AccessError{Code: "connection_missing", Connection: repository.Connection, Message: "The selected connection no longer exists. Choose another connection."}
}
func (b *boot) repositoryBinding(ctx context.Context, owner, name string) (config.Repo, error) {
var repos []config.Repo
_, found, err := b.controlPlane.Query(ctx, controlplanestore.RepositoryPoliciesKind, func(value []byte) error { return json.Unmarshal(value, &repos) })
@@ -90,24 +129,45 @@ func (b *boot) openRepositoryConnection(ctx context.Context, principal access.Pr
if !connection.Permitted(string(principal.IdentityID), operation) {
return failure("operation_denied", fmt.Sprintf("Allow this agent to %s through %s before continuing.", operation, connection.Name))
}
token, err := b.secrets.Resolve(connection.Token)
if err != nil || token == "" {
return failure("credential_unavailable", fmt.Sprintf("The credential for %s is unavailable. Check its secret reference.", connection.Name))
token, code, message := b.connectionToken(ctx, connection)
if code != "" {
return failure(code, message)
}
host := strings.TrimRight(connection.Host, "/")
if !strings.Contains(host, "://") {
host = "https://" + host
}
out.Forge = b.connectionForge(ctx, connection, principal.Org, token)
cfg := b.cfgHolder.Get()
username := connection.Account
gitToken := token
var (
minted forge.GitCredential
err error
)
if issuer, ok := out.Forge.(forge.GitCredentialIssuer); ok {
minted, err = issuer.GitCredential(ctx, repository.Owner, repository.Name)
switch {
case errors.Is(err, errors.ErrUnsupported):
case err != nil:
b.log.WarnContext(ctx, "git credential unavailable", "connection", connection.ID, "error", err)
return failure("credential_unavailable", fmt.Sprintf("%s could not issue a credential for %s/%s. Check the app is installed on it.", connection.Name, repository.Owner, repository.Name))
default:
username, gitToken = minted.Username, minted.Token
}
}
if username == "" && connection.Type == "gitea" {
username, err = connectionAccount(ctx, connection.Type, host, token)
if err != nil {
return failure("account_unverified", "The forge account could not be verified. Check the credential and its permissions.")
}
}
cfg := b.cfgHolder.Get()
out.Trees = &worktree.Manager{WorkDir: worktree.OrgWorkDir(cfg.WorkDir, string(principal.Org)), Token: token, AuthUser: username, BaseURL: host, BotUser: cfg.BotUser, BotEmail: cfg.BotEmail, Log: b.log}
out.Forge = b.connectionForge(ctx, connection, principal.Org, token)
botUser, botEmail := commitIdentity(cfg, connection, minted, username)
signer, code, message := b.connectionSigner(connection)
if code != "" {
return failure(code, message)
}
out.Trees = &worktree.Manager{WorkDir: worktree.OrgWorkDir(cfg.WorkDir, string(principal.Org)), Token: gitToken, AuthUser: username, BaseURL: host, BotUser: botUser, BotEmail: botEmail, Signer: signer, Log: b.log}
if operation == config.OperationPR {
if _, disabled := out.Forge.(*forge.NoopForge); disabled {
return failure("forge_unavailable", "Enable the forge extension for this connection.")
@@ -115,3 +175,67 @@ func (b *boot) openRepositoryConnection(ctx context.Context, principal access.Pr
}
return out, nil
}
// connectionToken resolves the connection's credential, or returns a failure
// code and message. A full volume is reported as such, not as a bad reference.
func (b *boot) connectionToken(ctx context.Context, connection config.ForgeConnection) (string, string, string) {
token, err := b.secrets.Resolve(connection.Token)
if volume, full := exhaustedVolume(err); full {
b.log.ErrorContext(ctx, "secret resolution failed: host resource exhausted", "connection", connection.ID, "volume", volume, "error", err)
return "", "environment_exhausted", fmt.Sprintf("The host has run out of space on %s, so the credential for %s cannot be read. Free space there.", volume, connection.Name)
}
if err != nil || token == "" {
return "", "credential_unavailable", fmt.Sprintf("The credential for %s is unavailable. Check its secret reference.", connection.Name)
}
return token, "", ""
}
// exhaustedVolume reports whether err is a full volume or quota and names the
// volume, so the failure reads as an environment problem rather than a
// misconfigured secret.
func exhaustedVolume(err error) (string, bool) {
if !errors.Is(err, syscall.ENOSPC) && !errors.Is(err, syscall.EDQUOT) {
return "", false
}
if pathErr, ok := errors.AsType[*fs.PathError](err); ok {
return filepath.Dir(pathErr.Path), true
}
return "the host volume", true
}
// commitIdentity is the author of commits made through a connection: its
// configured commit identity, else the identity the forge minted with the
// credential, else the root bot fields, else its account.
func commitIdentity(cfg config.Config, connection config.ForgeConnection, minted forge.GitCredential, account string) (string, string) {
if connection.CommitName != "" {
return connection.CommitName, configuration.DefaultBotEmail(connection.Type, connection.CommitName, connection.CommitEmail)
}
if minted.CommitName != "" {
return minted.CommitName, minted.CommitEmail
}
if cfg.BotUser != "" {
return cfg.BotUser, cfg.BotEmail
}
user := account
if user == "" {
user = "archie"
}
return user, configuration.DefaultBotEmail(connection.Type, user, connection.CommitEmail)
}
// connectionSigner resolves the connection's SSH signing key. It returns nil
// when none is configured, or a failure code and message.
func (b *boot) connectionSigner(connection config.ForgeConnection) (git.Signer, string, string) {
if connection.SigningKey.Key == "" {
return nil, "", ""
}
key, err := b.secrets.Resolve(connection.SigningKey)
if err != nil || key == "" {
return nil, "signing_key_unavailable", fmt.Sprintf("The signing key for %s is unavailable. Check its secret reference.", connection.Name)
}
signer, err := worktree.NewSSHSigner([]byte(key))
if err != nil {
return nil, "signing_key_invalid", fmt.Sprintf("The signing key for %s is not an OpenSSH private key.", connection.Name)
}
return signer, "", ""
}
@@ -3,6 +3,7 @@ package archied
import (
"context"
"encoding/json"
"errors"
"log/slog"
"net/http"
"net/http/cgi"
@@ -28,6 +29,7 @@ import (
"github.com/samcharles93/archie-core/internal/domain/identity"
"github.com/samcharles93/archie-core/internal/domain/org"
"github.com/samcharles93/archie-core/internal/domain/workflow"
"github.com/samcharles93/archie-core/internal/forge"
infraaccess "github.com/samcharles93/archie-core/internal/infrastructure/access"
"github.com/samcharles93/archie-core/internal/infrastructure/controlplanestore"
"github.com/samcharles93/archie-core/internal/secret"
@@ -299,3 +301,40 @@ func TestConnectionAccountRefusesRedirects(t *testing.T) {
})
}
}
type recordingForge struct {
forge.Forge
merged bool
}
func (f *recordingForge) MergePR(context.Context, string, string, int) error {
f.merged = true
return nil
}
// An operator merge goes through the repository's own connection: the
// instance's default forge may be another host that does not have the repo.
func TestMergeUsesRepositoryConnection(t *testing.T) {
t.Setenv("ARCHIE_TEST_CONNECTION_TOKEN", "token")
docs := &repositoryDocuments{
repos: map[org.OrgID][]config.Repo{"org-a": {{Owner: "acme", Name: "app", Connection: "gitea"}}},
connections: map[org.OrgID][]config.ForgeConnection{"org-a": {{ID: "gitea", Name: "Gitea", Type: "gitea", Host: "git.example.test", Token: config.SecretRef{Engine: "env", Key: "ARCHIE_TEST_CONNECTION_TOKEN"}}}},
}
instance := &recordingForge{}
b := &boot{controlPlane: controlplanestore.NewRPCClient(docs), forgeClient: instance, cfgHolder: config.NewHolder(config.Config{}), secrets: secret.NewRegistry(), log: slog.New(slog.DiscardHandler)}
for _, tt := range []struct{ name, owner, repo, code string }{
{"bound repository", "acme", "app", "forge_unavailable"},
{"unmanaged repository", "acme", "other", "repository_not_configured"},
} {
t.Run(tt.name, func(t *testing.T) {
err := b.mergePR(org.WithOrg(t.Context(), "org-a"), tt.owner, tt.repo, 1)
accessErr, ok := errors.AsType[*forge.AccessError](err)
if !ok || accessErr.Code != tt.code {
t.Fatalf("error = %v, want code %s", err, tt.code)
}
if instance.merged {
t.Fatal("merged through the instance forge")
}
})
}
}
@@ -6,6 +6,7 @@ import (
"testing"
"github.com/samcharles93/archie-core/internal/config"
"github.com/samcharles93/archie-core/internal/domain/identity"
"github.com/samcharles93/archie-core/internal/domain/workflow"
"github.com/samcharles93/archie-core/internal/infrastructure/egress"
)
@@ -41,7 +42,7 @@ func TestEgressResolvesOnlyGrantedCredentials(t *testing.T) {
}},
}
r := runCredentialResolver{
runs: runsByToken{"dashboard-run": {ID: 9, Identity: "new-agent"}, "root-run": {ID: 1}, "acme-run": {ID: 2, Identity: "acme-bot", Org: "acme"}, "acme-row-run": {ID: 3, Org: "acme"}},
runs: runsByToken{"dashboard-run": {ID: 9, Identity: "new-agent"}, "root-run": {ID: 1, Identity: string(identity.SystemID)}, "acme-run": {ID: 2, Identity: "acme-bot", Org: "acme"}, "acme-row-run": {ID: 3, Org: "acme"}},
config: config.NewHolder(cfg),
secrets: secretValues{"GH": "gh-secret", "ROOT_AI": "root-ai", "ACME_AI": "acme-ai", "ROOT_OPENAI": "root-openai", "ACME_OPENAI": "acme-openai", "ROOT_DEEPSEEK": "root-deepseek"},
}
+7 -16
View File
@@ -1,14 +1,12 @@
// sd_notify.go wires the daemon into internal/sdnotify's implementation of
// systemd's sd_notify(3) protocol: one READY=1 when the run loop starts
// serving, and a WATCHDOG=1 heartbeat while the run loop is demonstrably still
// making progress.
// serving, and a WATCHDOG=1 heartbeat while the process is alive.
//
// The protocol client and the heartbeat sampler live in internal/sdnotify
// because archie-messaging, a separate process that cannot import this
// package, is the next process that must be able to announce itself.
// What stays here is what is the daemon's own: which
// marker counts as progress (daemon.LastPollAt) and how long the loop may go
// without beginning a poll pass.
// A run loop that stalls on a slow peer is reported by the run_loop readiness
// probe, never by withholding the heartbeat.
//
// Nothing here is fatal -- a process with no NOTIFY_SOCKET (a plain terminal,
// Docker, a user unit without WatchdogSec) sends nothing and serves exactly as
@@ -37,7 +35,7 @@ func (b *boot) announceReady() {
sdnotify.Ready(b.log)
}
// startWatchdog arms the heartbeat sampler for the daemon's run loop. It does
// startWatchdog arms the heartbeat. It does
// nothing unless a manager named a notify socket and asked for a watchdog
// (WATCHDOG_USEC), so every deployment without systemd is unaffected.
func (b *boot) startWatchdog(ctx context.Context) {
@@ -52,14 +50,10 @@ func (b *boot) startWatchdog(ctx context.Context) {
sampler := sdnotify.Watchdog{
Interval: interval,
Cadence: b.loopCadence,
Progress: b.d.LastPollAt,
Beat: func() { n.Send(sdnotify.WatchdogState) },
Log: b.log,
}
b.log.InfoContext(ctx, "systemd watchdog armed",
"heartbeat", interval.String(),
"loop_cadence", b.loopCadence().String())
"heartbeat", interval.String())
go func() {
if err := sampler.Run(ctx); err != nil && !errors.Is(err, context.Canceled) {
@@ -68,11 +62,8 @@ func (b *boot) startWatchdog(ctx context.Context) {
}()
}
// loopCadence is the longest interval at which the run loop may go without
// beginning a fresh poll pass, and therefore how stale the progress marker may
// be before the loop counts as stalled.
//
// The shared interval is re-read so live polling changes are honoured.
// loopCadence is the interval at which the run loop begins a poll pass. The
// shared interval is re-read so live polling changes are honoured.
func (b *boot) loopCadence() time.Duration {
return b.cfgHolder.Get().PollInterval.Std()
}
+19 -19
View File
@@ -2,7 +2,6 @@ package archied
import (
"context"
"fmt"
"github.com/samcharles93/archie-core/internal/domain/taskactions"
"github.com/samcharles93/archie-core/internal/domain/workflow"
@@ -29,15 +28,6 @@ func (b *boot) taskActions() taskactions.Service {
)
}
// withdrawIssue declines the task an issue queued, if it has one.
func (b *boot) withdrawIssue(ctx context.Context, owner, repo string, number int, reason string) error {
task, err := b.stateStore.TaskByIssue(ctx, owner, repo, number)
if err != nil || task == nil {
return err
}
return b.taskActions().Withdraw(ctx, task.ID, reason)
}
func (b *boot) cancelTask(id int64) bool {
if b.d == nil {
return false
@@ -46,24 +36,27 @@ func (b *boot) cancelTask(id int64) bool {
}
func (b *boot) closeIssue(ctx context.Context, owner, repo string, number int, comment string) error {
if b.forgeClient == nil {
return fmt.Errorf("forge is not configured")
f, err := b.repositoryForge(ctx, owner, repo)
if err != nil {
return err
}
return b.forgeClient.CloseIssue(ctx, owner, repo, number, comment)
return f.CloseIssue(ctx, owner, repo, number, comment)
}
func (b *boot) closePR(ctx context.Context, owner, repo string, number int, comment string) error {
if b.forgeClient == nil {
return fmt.Errorf("forge is not configured")
f, err := b.repositoryForge(ctx, owner, repo)
if err != nil {
return err
}
return b.forgeClient.ClosePR(ctx, owner, repo, number, comment)
return f.ClosePR(ctx, owner, repo, number, comment)
}
func (b *boot) mergePR(ctx context.Context, owner, repo string, number int) error {
if b.forgeClient == nil {
return fmt.Errorf("forge is not configured")
f, err := b.repositoryForge(ctx, owner, repo)
if err != nil {
return err
}
return b.forgeClient.MergePR(ctx, owner, repo, number)
return f.MergePR(ctx, owner, repo, number)
}
func (b *boot) removeTaskLogs(id int64) error {
@@ -77,6 +70,13 @@ func (b *boot) removeTaskWorktree(task *taskactions.Task) error {
if b.d == nil {
return nil
}
// A run that handed off shares the work item's worktree with its
// successor; archiving the old run must not remove it.
if current, err := b.stateStore.TaskByIssue(context.Background(), task.Owner, task.Repo, task.IssueNumber); err != nil {
return err
} else if current != nil && current.ID != task.ID {
return nil
}
return b.d.RemoveWorktree(&workflow.Task{Owner: task.Owner, Repo: task.Repo, Identity: task.Identity, IssueNumber: task.IssueNumber, Org: task.Org})
}
+1
View File
@@ -35,6 +35,7 @@ func (b taskBroker) TaskSubjects(ctx context.Context, taskID int64, credential s
agentexec.SubjectForEvents(taskID),
spanrelay.Subject(taskID),
worktreerpc.SubjectFor(task.Identity, worktreerpc.SubjectPush),
worktreerpc.SubjectFor(task.Identity, worktreerpc.SubjectBaseline),
messagerpc.SubjectFor(task.Identity),
}, forgerpc.Subjects(task.Identity)...)
return nats.TaskSubjects{Publish: publish, Subscribe: []string{agentnats.SubjectForTask(taskID)}}, nil
+1 -4
View File
@@ -295,10 +295,7 @@ func hasConfigSection(document map[string]any, section string) bool {
}
func updateStateDir() string {
if dir := os.Getenv("ARCHIE_UPDATE_STATE_DIR"); dir != "" {
return dir
}
return configuration.DefaultUpdateStateDir()
return configuration.UpdateStateDir()
}
// resumeUpdate hands an interrupted transaction to the frozen watchdog and
+10 -4
View File
@@ -26,10 +26,16 @@ func (b *server) setSkillList(entries []skill.CatalogEntry) {
// channels, so channel reload is left unset and answers Unavailable.
func (b *server) chatCatalog() gatewayrpc.Catalog {
return gatewayrpc.Catalog{
CheckSecret: func(ref secret.SecretRef) bool { _, err := b.secrets.Resolve(ref); return err == nil },
Logs: b.recentLogs,
Skills: b.skillEntries,
Curators: b.curatorStates,
CheckSecret: func(ref secret.SecretRef) (bool, error) {
if _, ok := b.secrets.Get(ref.Engine); !ok {
return false, fmt.Errorf("secret engine %q is not reachable", ref.Engine)
}
_, err := b.secrets.Resolve(ref)
return err == nil, nil
},
Logs: b.recentLogs,
Skills: b.skillEntries,
Curators: b.curatorStates,
}
}
@@ -1,6 +1,4 @@
// Package chattask derives the chat task profiles a config allows and adapts
// the State Store's enqueue call to the gateway's task writer.
package chattask
package archiegateway
import (
"context"
@@ -12,8 +10,8 @@ import (
"github.com/samcharles93/archie-core/internal/gateway"
)
// Writer adapts an enqueue call returning the task to gateway.TaskWriter.
type Writer struct {
// chatTaskWriter adapts an enqueue call returning the task to gateway.TaskWriter.
type chatTaskWriter struct {
Enqueue func(
ctx context.Context,
owner, repo, title, body, workflow, identity, origin, draft string,
@@ -21,7 +19,7 @@ type Writer struct {
) (*workflow.Task, error)
}
func (a Writer) EnqueueChatTask(
func (a chatTaskWriter) EnqueueChatTask(
ctx context.Context,
owner, repo, title, body, workflow, identity, origin string,
inputs map[string]any,
@@ -36,15 +34,15 @@ func (a Writer) EnqueueChatTask(
return task.ID, nil
}
// Profiles returns the task profiles cfg allows and the default identity.
func Profiles(cfg config.Config) ([]gateway.TaskProfile, string) {
// chatTaskProfiles returns the task profiles cfg allows and the default identity.
func chatTaskProfiles(cfg config.Config) ([]gateway.TaskProfile, string) {
if len(cfg.Identities) > 0 {
profiles := make([]gateway.TaskProfile, 0, len(cfg.Identities))
for _, identity := range cfg.Identities {
if len(identity.Repos) == 0 {
continue
}
profiles = append(profiles, newProfile(identity.Name, identity.Repos))
profiles = append(profiles, newChatTaskProfile(identity.Name, identity.Repos))
}
if len(profiles) == 0 {
return nil, ""
@@ -57,10 +55,10 @@ func Profiles(cfg config.Config) ([]gateway.TaskProfile, string) {
// Chat acts as the control-plane operator, the identity the dashboard
// stamps on the tasks it creates.
operator := string(identity.OperatorID())
return []gateway.TaskProfile{newProfile(operator, cfg.Repos)}, operator
return []gateway.TaskProfile{newChatTaskProfile(operator, cfg.Repos)}, operator
}
func newProfile(identity string, repos []config.Repo) gateway.TaskProfile {
func newChatTaskProfile(identity string, repos []config.Repo) gateway.TaskProfile {
allowed := make([]string, 0, len(repos))
for _, repo := range repos {
allowed = append(allowed, repo.Owner+"/"+repo.Name)
+1 -1
View File
@@ -107,7 +107,7 @@ func (a chatTaskListerAdapter) ListChatTasks(ctx context.Context, identity strin
// started -- so the pinned definition answers there instead. A review wait and
// every other status name the workflow the task is on or will run next.
func (a chatTaskListerAdapter) chatWorkflow(ctx context.Context, task workflow.Task) string {
if a.task == nil || taskstate.ApprovalKind(task.Status, task.ReviewGate) != taskstate.ApprovalPlan {
if a.task == nil || taskstate.ApprovalKind(task.Status, task.ReviewGate, task.RetryMode) != taskstate.ApprovalPlan {
return task.Workflow
}
full, err := a.task(ctx, task.ID)
+46 -5
View File
@@ -12,7 +12,9 @@ import (
"github.com/samcharles93/archie-core/internal/agentexec/modelloop"
"github.com/samcharles93/archie-core/internal/config"
"github.com/samcharles93/archie-core/internal/domain/access"
"github.com/samcharles93/archie-core/internal/domain/curator"
"github.com/samcharles93/archie-core/internal/domain/org"
"github.com/samcharles93/archie-core/internal/domain/usage"
"github.com/samcharles93/archie-core/internal/events"
"github.com/samcharles93/archie-core/internal/infrastructure/controlplanestore"
@@ -22,12 +24,12 @@ import (
"github.com/samcharles93/archie-core/internal/infrastructure/toolbuilder"
)
func (b *server) setupCurators(ctx context.Context) bool {
func (b *server) setupCurators(ctx context.Context) error {
log := b.log.With("component", "curator")
model, err := b.chatModels.ModelFor(ctx)
if err != nil {
log.WarnContext(ctx, "curators disabled: chat model unavailable; configure a chat model and restart the gateway", "err", err)
return false
return fmt.Errorf("curators disabled until the gateway restarts with a chat model: %w", err)
}
skillsRoot := b.cfg.SkillsDir
if skillsRoot == "" {
@@ -40,7 +42,7 @@ func (b *server) setupCurators(ctx context.Context) bool {
MemoryEngines: b.memEngines,
Skills: skillcurator.NewStore(skillsRoot),
Conversations: sessioncurator.NewAdapter(b.chatSessionStore, b.cfg.BotUser),
LLM: curatorLLMRunner{llm: b.chatLLM, outcomes: b.providerOutcomes, usage: b.usage},
LLM: actingPrincipalRunner{inner: curatorLLMRunner{llm: b.chatLLM, outcomes: b.providerOutcomes, usage: b.usage}, resolve: b.actingPrincipal},
Model: model,
})
@@ -58,7 +60,7 @@ func (b *server) setupCurators(ctx context.Context) bool {
b.addCleanup(shutdownCuratorRuntime(rt, log))
reg := b.curatorRegistry
b.addCleanup(shutdownCuratorRegistry(reg, log))
return true
return nil
}
//nolint:contextcheck // shutdown runs after the parent context is cancelled
@@ -95,6 +97,42 @@ func (s curatorEventSink) Emit(kind, detail string, data map[string]any) {
s.b.Publish(context.Background(), events.Event{Kind: kind, Detail: detail, Data: data})
}
// actingPrincipal resolves the identity the instance acts as for automated
// work (the default chat identity, falling back to the bot user), so curator
// passes authorize guarded tools exactly as that identity would.
func (b *server) actingPrincipal(ctx context.Context) (access.Principal, error) {
name := b.defaultChatIdentity
if name == "" {
name = b.cfg.BotUser
}
if name == "" {
return access.Principal{}, fmt.Errorf("no acting identity configured (chat identity or bot user)")
}
idn, err := b.stateStore.ResolveLegacyName(ctx, name)
if err != nil {
return access.Principal{}, fmt.Errorf("resolve acting identity %q: %w", name, err)
}
return b.stateStore.PrincipalFor(ctx, idn.ID)
}
// actingPrincipalRunner attaches the acting principal to every curator model
// call. Tool handlers run in the call's context, so guarded tools see the
// curator as the instance's identity, never as an anonymous or caller-supplied
// one; a pass that cannot resolve the principal fails closed.
type actingPrincipalRunner struct {
inner curator.LLMRunner
resolve func(context.Context) (access.Principal, error)
}
func (r actingPrincipalRunner) Chat(ctx context.Context, req curator.ChatRequest) (curator.ChatResult, error) {
p, err := r.resolve(ctx)
if err != nil {
return curator.ChatResult{}, fmt.Errorf("curator pass: %w", err)
}
ctx = org.WithScope(org.WithOrg(access.WithPrincipal(ctx, p), p.Org), p.Org)
return r.inner.Chat(ctx, req)
}
// curatorLLMRunner adapts the shared ai-sdk runtime to the curator
// family's narrow LLMRunner contract: one model reference, plain
// messages, and the declared tool set -- no streaming. Tools are built
@@ -180,7 +218,10 @@ func (b *server) watchCurators(ctx context.Context, version int64) error {
func (b *server) startCurators(ctx context.Context) error {
// Curators wake on this process's turns and read its conversations.
if !b.setupCurators(ctx) {
// A disabled runtime is reported, so the dashboard shows why curators do
// not apply rather than a process that never reported.
if err := b.setupCurators(ctx); err != nil {
b.applyStatus.Report(ctx, controlplanestore.CuratorsKind, 0, err)
return nil
}
if err := b.curatorRuntime.Start(ctx); err != nil {
@@ -6,7 +6,6 @@ import (
"log/slog"
"github.com/samcharles93/archie-core/internal/agentexec/modelloop"
"github.com/samcharles93/archie-core/internal/app/chattask"
"github.com/samcharles93/archie-core/internal/app/servicekit"
"github.com/samcharles93/archie-core/internal/buildinfo"
"github.com/samcharles93/archie-core/internal/config"
@@ -88,10 +87,10 @@ func (b *server) setupChatRuntime(ctx context.Context, cfg config.Config, actor
// setupChatTasks wires the task creator chat commands and scheduled workflows
// enqueue through.
func (b *server) setupChatTasks(cfg config.Config) {
profiles, defaultChatIdentity := chattask.Profiles(cfg)
profiles, defaultChatIdentity := chatTaskProfiles(cfg)
if len(profiles) > 0 {
b.chatTasks = gateway.NewStoreTaskCreatorForProfiles(
chattask.Writer{Enqueue: b.stateStore.EnqueueChatTask},
chatTaskWriter{Enqueue: b.stateStore.EnqueueChatTask},
profiles,
)
}
+9
View File
@@ -18,6 +18,7 @@ import (
"github.com/samcharles93/archie-core/internal/gateway"
infraaccess "github.com/samcharles93/archie-core/internal/infrastructure/access"
"github.com/samcharles93/archie-core/internal/infrastructure/controlplanerpc"
"github.com/samcharles93/archie-core/internal/infrastructure/issuerpc"
"github.com/samcharles93/archie-core/internal/infrastructure/staterpc"
"github.com/samcharles93/archie-core/internal/infrastructure/taskmcp"
"github.com/samcharles93/archie-core/internal/plugin"
@@ -109,6 +110,14 @@ func (b *server) registerWorkflowTools(ctx context.Context) {
authz := infraaccess.StartLive(ctx, b.stateStore.ListPolicies, b.stateStore.PoliciesVersion, b.log)
workflows := controlplanerpc.NewWorkflows(b.stateStore.ControlPlane())
entries := append(gateway.WorkflowTools(workflows, authz), gateway.IntegrationTools(integrationSource{Workflows: workflows, store: b.stateStore}, authz)...)
// Run-inspection tools back long-running curators (self-intake first);
// the State Store client satisfies the source directly.
entries = append(entries, gateway.RunTools(b.stateStore, authz)...)
// Issue tools reach the forge through the daemon, which alone holds its
// credentials; without the broker connection they are not registered.
if b.taskActionsConn != nil {
entries = append(entries, gateway.IssueTools(issuerpc.Client{Conn: b.taskActionsConn, Timeout: 30 * time.Second}, authz)...)
}
for _, entry := range entries {
if err := b.toolReg.Register(entry); err != nil {
b.log.WarnContext(ctx, "workflow tool registration failed", "tool", entry.Name, "err", err)
Loaded 100 of 807 files, more files were not shown because too many files have changed in this diff. Show more