mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
f8b4a6755cac61db86e3908c2c6518b3c5e9ca59
79
Commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
 Renn F
|
d8841279a8 | Updated uv.lock | ||
|
RoboCo Release Manager
|
31418c9a32 | chore(release): 0.26.0 | ||
|
Renn F
|
67485213d7 | uv.lock upgrade | ||
|
Renn F
|
c33a03f2aa | Updated uv.lock | ||
|
RoboCo Release Manager
|
3e8b3d82e6 | chore(release): 0.25.0 | ||
|
Renn F
|
3c1064e7d1 | Updated uv.lock | ||
|
Renn F
|
3338f88e1b | chore(release): 0.24.0 | ||
|
Renn F
|
179467943c | chore(release): 0.23.0 | ||
|
Renn F
|
76a396b152 | chore(release): 0.22.0 | ||
|
Renn F
|
a322dc8f9f | chore(release): 0.21.0 | ||
|
Renn F
|
80e54390dc | + uv.lock | ||
|
|
2a9d9e25d9 |
feat(tasks): task-content guardrails — structured plans + constraints split (#328)
* feat(tasks): task-content guardrails — structured plans + constraints split Bound task PLANNING content the way journals/notes already are, fixing the poor task quality flagged 2026-07-07 (degenerate roots, over-decomposed leaves, descriptions bloated by an auto-attached conventions dump). Phase A — plan/AC guardrails (no migration): - _pm_sub_tasks_gate: cap sub_tasks at 7; per-subtask ceilings (title <=200, description <=600) enforced at both the Pydantic boundary and the gate. Dropped the min-2-roots and no-subtasks-on-code rules: both contradict the 2026-05-08 rule (test_cell_pm_can_plan_code_typed_parent_via_i_will_plan) and break legitimate single-cell roots. Long comment in the gate explains. - IWillPlanRequest: plan <=2000, approach <=800 (floor 150 kept), typed SubTaskCreate/RiskCreate/OpenQuestionCreate replacing loose list[dict]. - DelegateRequest + task_completeness: acceptance_criteria capped at 7 items, each <=200 chars. New FieldRule.MAX_LENGTH_LIST + _post_rule_reject helper (extracted to keep the gate under xenon B). - Routes dump typed models to dicts for the existing rich_plan shaper. Phase B — conventions split (migration 068): - New nullable tasks.constraints Text column; _attach_baseline_constraints now writes the ## Constraints block there instead of appending to description, so description is the human-authored instruction only. The conventions still reach the agent independently at spawn via the ambient block, so agent correctness is unaffected. - TaskResponse / Task model / panel Task type carry constraints; panel shows a read-only Constraints card. Field is optional on the TS type (backend returns null for flag-off / pre-migration rows). Tests: 5 new gate unit tests, 7 schema tests, 3 AC policy tests, 3 e2e smoke scenarios; 4 baseline-constraints integration tests updated. ruff/mypy/xenon clean; 10026 unit+foundation+e2e green; panel typecheck clean. Refs: plan breezy-imagining-kahn * test(tasks): use typed SubTaskCreate instead of dict literals in plan tests make quality runs mypy over tests/ (1079 files), not just roboco/ — the four sites passing dict literals to the now-typed sub_tasks: list[SubTaskCreate] field failed mypy. Construct SubTaskCreate directly; the typed model raising ValidationError IS the boundary the rejection tests assert. * fix(deps): drop unused python-jose — clears PYSEC-2026-1325 (ecdsa, no fix) CI's pip-audit went red on a freshly-published advisory PYSEC-2026-1325 against ecdsa 0.19.2 (no fix published — 0.19.2 is the latest). ecdsa is a transitive dep of python-jose, which is a DIRECT dep of roboco but is NOT imported anywhere in roboco/ or tests/ (grep-verified). The actual JWT path uses PyJWT (import jwt) + fastapi_users.jwt, not python-jose. So python-jose is a dead dependency. Removing it (deletion over an --ignore-vuln waiver) drops ecdsa + rsa + pyasn1 + their type stubs from the lockfile, eliminating the CVE at the source. deptry roboco/ stays clean (no missing-dep), mypy clean, auth + schema tests pass. Master CI was green 9h before this PR's run, so the advisory published in that window would red any run including master — this fix unblocks both. * chore(prompts): regenerate verb tables for typed plan sub_tasks Phase A's IWillPlanRequest schema change (sub_tasks/risks/open_questions from loose list[dict] to typed SubTaskCreate/RiskCreate/OpenQuestionCreate) made the auto-generated verb tables stale. Regenerated via scripts/regenerate_verb_tables.py — the diff is purely the signature reflection (list[str|str] -> list[SubTaskCreate], etc.). Required by the foundation-check gate (Makefile:559). --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com> |
||
|
|
4923ee3ff3 |
MinIO video storage (chunk 1: config+deps+compose) + event-loop perf fix (#308)
* feat(video): Phase A — VideoEngine origination spine + held-source gates
New default-off engine skeleton: opens a UX/UI authoring task (source=video, assigned to a ux-dev, LOW complexity to clear the dev-needs-subtasks guard) and materializes a held CEO-approval draft (source=video_post). Excludes video_post from all three held-source skip sites; adds the video_draft marker, six config flags, and the feature-flag entries. Origination + gate behavior unit-tested.
* refactor(orchestrator): fold _dispatch_dev_work skip chain into a helper
The per-source if/continue chain grew past xenon's --max-absolute B when the video_post held source joined it. Extract _is_non_dev_dispatch_source (every held-CEO source plus the two Board exploration sources) so the dev loop's skip is one flat call. Behavior-identical.
* feat(video): Phase B — propose_video do-tool (metadata-only, team-gated)
UX/UI dev records a video's composition ref + per-platform captions onto the authoring task's video_draft marker. Team-gated at runtime via _caller_team (Role.DEVELOPER can't tell a ux-dev from a be-dev). Resolves the caller's ACTIVE task via get_active_task_for_agent, not an oldest-first scan that would clobber a second open video task. Metadata only, no render. Wired through do_server + route + schema; added to _DEV_DO.
* feat(video): Phase D — render loop + RemotionRenderer client
Orchestrator-async _video_render_loop renders a completed authoring task's merged composition to MP4 (vertical + square) via the remotion-renderer sidecar and materializes the held video_post draft. RemotionRenderer tars the read-clone's motion/ source, POSTs it, and saves the returned MP4 bytes to a TASK-scoped local path (no shared volume; a composition is reused across videos so a composition-scoped path would clobber an earlier draft). Render failures bounded-retry (read-clone catch-up window, transient sidecar) up to a cap, then terminal-fail. Client tested vs a mock transport; loop vs a mock renderer + real DB.
* feat(video): Phase C — release / spotlight / on-demand video triggers
Three entry points open a UX/UI video-authoring task via VideoEngine.open_video_task: (1) a published release drafts a companion video — best-effort in ReleaseProposalService.approve, never fails the publish; script from the CHANGELOG via the local model with a template fallback. (2) propose_feature_spotlight gains optional wants_video/video_script — best-effort, gated on video_on_spotlight, default-off leaves the spotlight flow byte-for-byte unchanged. (3) POST /video/request (CEO-only) for an on-demand brief, with clean disabled/not_opened responses. All gated on video_engine_enabled.
* fix(video): savepoint-isolate video-task inserts (F042 poisoned session)
The best-effort try/except around open_video_task (release-publish + spotlight hooks) swallowed the Python exception, but a DBAPI error at the insert flush left the shared session must-rollback — so the caller's next commit (release finalize / request boundary) threw PendingRollbackError: the release stuck 'pending' after actually publishing, or the spotlight draft + HTTP response were lost. Wrap both inserts (open_video_task, _originate_video_post) in a begin_nested savepoint (the repo's established F042 pattern) so a DB error rolls back only the insert. open_video_task returns None (every caller already handles it); _originate_video_post propagates to the render loop's handler. Regression test: an insert FK error returns None with the session left usable. Dormant while the flags were off; armed on the NAS.
* feat(video): Phase G — motion/ package + remotion-renderer sidecar + compose
In-repo Remotion v4 motion/ package (ReleaseAnnouncement composition; calculateMetadata returns 1080x1920 vertical / 1080x1080 square from inputProps.orientation) + a credential-free remotion-renderer sidecar: untar the POSTed motion/ source, bundle (LRU-cached per source sha), selectComposition + renderMedia h264, stream the MP4 bytes back — matching the RemotionRenderer client contract. docker/remotion.Dockerfile on Debian (Chrome apt deps, build-time Chrome pre-warm, ffmpeg bundled in @remotion/renderer). Wired into both compose files (roboco_default only, shm_size 1gb, /health check) + the release publish matrix. Verified via a real local render of both cuts; the Debian docker build is the CEO's to run.
* chore(video): D-hardening — video_post source_task_id + render-loop docstring
Add a source_task_id back-reference to the video_post held-draft marker (traceability from a draft to its authoring task; also makes the render loop's two-key idempotency check wireable later). Fix the render-loop test's stale docstring ('never retried' -> bounded-retry). Both from the Phase D critic's non-blocking follow-ups.
* feat(video): Phase E1 — VideoPostService + heartbeat mutex (approve->post)
CEO-approve->post service: heartbeat-renewed Redis mutex (fail-closed, grace=ttl-2*heartbeat), re-read-in-lock double-post guard, per-platform durable commits (asyncio.shield-ed, settle-before-rollback on lock-loss), all writes inside the lock (captions validated pre-lock, applied in-lock — no stale whole-column clobber), idempotent, per-platform retry-skip. Poster interfaces (X/TikTok, mocked here). Reject + list-held-drafts. Survived 3 adversarial rounds; residual = a crash in the poster->commit window (CEO-gated low-freq, documented).
* fix(video): G-hardening — renderer leaks + Share Tech Mono brand font
Sidecar: give bundle() an explicit outDir tracked + deleted on LRU eviction (was leaking ~19MB remotion-webpack-bundle-* per source); res.on('close') cleanup so an aborted/retried download no longer leaks its remotion-out-* MP4 dir. Fonts: vendor Share Tech Mono (roboco-website brand font) as the display face (self-hosted woff2, 400-weight, headline fontWeight 700->400 to avoid faux-bold) + self-hosted Inter body — no gstatic fetch at render time (lsof-verified). Extras: composition_id whitelist (400) + Multer error middleware (400/413).
* feat(video): Phase E2 — X v2 + TikTok posters, tiktok_credentials, routes
LiveXVideoPoster (X v2 chunked media upload: init/append/finalize/STATUS-poll -> tweet w/ media_ids, OAuth1 signer reused). LiveTikTokPoster (OAuth2 inbox: init -> chunked PUT with asymmetric final chunk -> status-fetch; 401 -> refresh_token grant, rotated token persisted). tiktok_credentials Fernet singleton + migration 062 (single head). Routes: CEO approve/reject + list held drafts + write-only tiktok creds, wiring real posters into VideoPostService. Residual: a lock-loss right after a token-refresh flush can discard the rotated token (same rare CEO-gated class as the documented post->commit window).
* feat(video): Phase F — panel video-post queue + TikTok creds card + flags
video-post-queue.tsx: <video> MP4 preview with 9:16/1:1 cut switch, per-platform editable captions (280/2200 counters, over-limit disables approve), approve/reject, Request-a-video dialog. tiktok-credentials-card.tsx (4 write-only OAuth2 fields). feature-flags-card inlines TikTokCredentialsForm under video_engine_enabled. Mounted in command-center. tsc/eslint clean, 273 panel tests green. NOTE: needs the GET /video/posts/{id}/media route + mp4_paths on VideoPostResponse (folded into H) for the preview source.
* feat(video): Phase H — media route + e2e smoke + NAS arming + docs
GET /video/posts/{id}/media?cut= (CEO-gated FileResponse of the rendered MP4; closes the panel preview gap) + mp4_paths on VideoPostResponse. e2e smoke tests/e2e_smoke/test_video_pipeline.py (full flow, sidecar+X/TikTok mocked; asserts dispatcher skips, render-loop materialize, propose_video team-gate, approve idempotency). NAS arming: docker-compose.yml/.yaml ROBOCO_VIDEO_ENGINE_ENABLED/ON_RELEASE/ON_SPOTLIGHT default-on (.yaml resynced to .yml); registry stays off. CLAUDE.md video-engine section + CHANGELOG. Fixed 2 pre-existing route-test pollution leaks. Full suite 11763 passed.
* fix(video): auth-carrying preview, media route confinement, VideoPost type drift
Three fixes along the video preview path:
1. panel video preview auth: the <video> element was pointed straight at
GET /video/posts/{id}/media, but a native <video src> GET carries none
of axios's X-Agent-ID/X-Agent-Role headers — so in the default
header-trust deployment the request 401s. Fetch the cut via
videoApi.getMediaBlob (axios, responseType: blob) and drive <video>
off a URL.createObjectURL result instead. The object URL is revoked
on cut-change (the previous cut's URL) and on unmount, so neither
cut switches nor row teardown leak blob URLs.
2. backend media route confinement: GET /video/posts/{id}/media now
resolves mp4_path and refuses it with 404 when it falls outside
settings.video_output_dir. Defense-in-depth against any future
writer of mp4_paths serving files from arbitrary disk locations.
3. panel VideoPost type/comment drift: added mp4_paths to the
VideoPost interface (the committed VideoPostResponse already
carries it), and corrected the stale comment on videoMediaUrl
that claimed no route served the rendered bytes — the route has
existed since the media endpoint landed; the comment now describes
why getMediaBlob exists instead of a direct <video src>.
* Persist rendered videos to data in physical storage.
* ++
* docs(video): 0.18.0 CHANGELOG entry + RAG + map reference for video engine
- Move the video engine bullet from [Unreleased] into [0.18.0] and note
the ROBOCO_VIDEO_OUTPUT_DIR bind-mount persistence.
- Add docs/rag/architecture/video-engine.md (mirrors x-engine.md shape:
enable/disable, three triggers, render loop + sidecar, CEO gate, media
route confinement, credentials).
- Reference the video render loop in docs/map/orchestrator.md's engine list.
* chore(video): re-bump to 0.19.0 + sync registry compose defaults
Version was wrongly bumped to 0.18.0; 0.18.0 is an already-released
section. Restore its 2026-07-04 date and move the video-engine CHANGELOG
bullet into a new [0.19.0] - 2026-07-05 section above it. Bump
pyproject.toml, roboco/__init__.py, roboco/config.py (app_version),
panel/package.json, and the motion/README inputProps example to 0.19.0.
docker-compose.registry.yml: add ROBOCO_VIDEO_ENGINE_ENABLED /
_VIDEO_ON_RELEASE / _VIDEO_ON_SPOTLIGHT defaulted false (NAS arms them
true), and comment out the video-renders bind mount with a short note
so the public registry image ships video off by default. Structural
sync with docker-compose.yml maintained.
* fix(video): rate-limit /render + reflow motion/README
CodeQL flagged js/missing-rate-limiting on the renderer /render route.
The sidecar is container-network-only with one trusted caller (the
orchestrator, which renders cuts serially), so this limiter is a
retry-storm ceiling (30/min, well above legit render rate), not the
primary control. Also reflows motion/README.md hard-wrapped prose that
failed the markdown quality gate.
* fix(build): finish pnpm 11 migration + regen verb tables
The panel Docker image build failed on `pnpm install --frozen-lockfile`:
node:22-alpine's corepack resolved to its bundled pnpm 11, but
panel/package.json pinned packageManager to pnpm@10.25.0, and pnpm 11
refuses to run against that pin. The Dockerfiles were already written for
pnpm 11 (comments, CI=true, strictDepBuilds); the package.json pin was the
stale outlier. Finish the migration instead of working around it:
- panel/package.json: packageManager pnpm@10.25.0 -> pnpm@11.10.0; drop the
`pnpm` field (pnpm 11 ignores it — build approval lives in
panel/pnpm-workspace.yaml's allowBuilds). Lockfile unchanged (pnpm 11
accepts it as-is); frozen-lockfile verified.
- remotion-renderer/package.json: pin packageManager pnpm@11.10.0 for
determinism (was relying on corepack's implicit default); engines.node
>=22.13 (pnpm 11 requirement).
- docker/panel.Dockerfile + docker/remotion.Dockerfile: `corepack prepare
pnpm@11.10.0 --activate` so the build uses the pinned version explicitly
instead of trusting corepack's bundled default (which a future
node:22-alpine could change).
- .github/workflows/panel-ci.yml: Node 20 -> 22 (pnpm 11 requires
Node >=22.13; Node 20 fails the engines check).
Also regenerate agents/prompts/_generated/{developer,head_marketing,verbs}.md
— the video engine added propose_video and extended propose_feature_spotlight
(wants_video, video_script) but the verb tables weren't refreshed, failing
the foundation-check quality gate.
* chore(build): approve esbuild build script in remotion pnpm-workspace.yaml
pnpm 11 generated this file with a placeholder ('set this to true or false')
during install; resolve it to true so local dev of the renderer doesn't
re-prompt. esbuild's postinstall only verifies the prebuilt platform binary
(@esbuild/<platform> is installed as an optional dep), so approving it is
safe and silences the ERR_PNPM_IGNORED_BUILDS warning.
* fix(build): copy pnpm-workspace.yaml into panel + remotion images
pnpm 11 hard-errors with [ERR_PNPM_IGNORED_BUILDS] (exit 1) when a
dependency ships a postinstall script that isn't approved in
allowBuilds. Both Dockerfiles copied only package.json + pnpm-lock.yaml,
so the build-approval map in pnpm-workspace.yaml never made it into the
image — the remotion image build died on esbuild@0.28.1's postinstall.
Copy pnpm-workspace.yaml alongside the manifests in both images. In
panel, this also drops the --config.strictDepBuilds=false workaround:
with sharp and unrs-resolver now approved, their postinstalls run and
install the platform-specific binaries (previously skipped, leaving
sharp without its @img/sharp-* binary at runtime).
Verified locally: remotion + panel `pnpm install --frozen-lockfile`
exit 0 with the workspace file present; both exit 1 without it.
* fix(perf): offload conventions + release-readiness blocking I/O off the event loop
The orchestrator runs uvicorn and the orchestration background loops on a
single shared event loop, so any sync I/O anywhere — even inside a background
loop — blocks API responsiveness for its duration. Two call sites were missing
asyncio.to_thread wrappers:
- ConventionsService.get_map/health/restore called the sync _resolve
(`git rev-parse`), _read_committed_standard (file read + yaml parse), and
_derive (filesystem walk via derive_from_scan) inline. Reachable from
GET /api/projects/{id}/conventions and from the agent spawn-prepare path.
- ReleaseManagerEngine._production_assess called gather_snapshot inline —
multiple `subprocess.run` git calls + a filesystem walk, running inside the
release-manager background loop.
Wrap each blocking call in asyncio.to_thread at the async boundary. No
signature changes; helpers stay sync. Verified: targeted tests pass
(196 passed, 36 DB-skipped), ruff + format clean.
These were the only responsiveness gaps surfaced by the concurrency audit —
the rest of the heavy paths (agent spawn via `docker run -d`, video render
loop, git ops via the 16-worker ThreadPoolExecutor, workspace subprocess
calls) already offload correctly. No API/worker container split needed.
* feat(storage): add MinIO config + dep + compose (no-op, default-off)
Chunk 1 of the MinIO video-storage plan (§1, §2, §6). No behavior change:
minio_endpoint defaults to empty = disabled, the existing FileResponse serve
path is untouched (chunk 4 wires the serve path; chunk 2 adds the client).
- pyproject.toml: add `minio` (minio-py) to dependencies; regenerate uv.lock
(resolves minio v7.2.20 + pycryptodome transitive).
- roboco/config.py: add 5 settings fields after video_output_dir
(minio_endpoint/_access_key/_secret_key/_bucket/_region). Plain str Fields
matching the existing ROBOCO_ENCRYPTION_KEY style; no SecretStr, no
presign_ttl_seconds (YAGNI — we don't presign in phase 1).
- docker-compose.yml: add `minio` service (data network only, named
minio-data volume, host ports 19000/19001 for debugging, mc healthcheck)
and a one-shot `minio-init` service mirroring the ollama-init pattern
(mc alias set + mb -p, idempotent via || true). Add ROBOCO_MINIO_* env to
the orchestrator env block (endpoint, access/secret key, bucket, region).
- docker-compose.registry.yml: intentionally omit the minio/minio-init
services and leave ROBOCO_MINIO_* unset (NAS default-on, registry
default-off — the established pattern); comment added to the orchestrator
env block noting the omission.
* docs(storage): 0.19.0 CHANGELOG + RAG + map reference for MinIO chunk 1
Backfills the release-polish docs for MinIO chunk 1 (§10 of the plan):
- docker-compose.yaml synced to docker-compose.yml (the two NAS compose files
must stay byte-identical; .yml was edited in chunk 1, .yaml was stale).
- CHANGELOG [0.19.0]: Added (MinIO scaffolding) + Fixed (event-loop I/O offload).
- docs/rag/architecture/minio-storage.md: RAG doc mirroring video-engine.md.
- docs/map/deployment-tooling.md: one-line storage reference.
* MinIO chunk 2: minio_client module (singleton + unconfigured guard) (#309)
* feat(storage): minio_client module (singleton + unconfigured guard)
Chunk 2 of the MinIO plan (§3). roboco/services/minio_client.py adds:
- get_client(): singleton minio-py Minio from settings; returns None when
minio_endpoint is empty (the disabled path used by the chunk 3/4 guards).
Parses http://... endpoint into host:port + secure flag.
- put_object(bytes, key): no-ops when unconfigured; otherwise PUTs to
settings.minio_bucket with ContentType video/mp4.
- get_object_stream(key): yields object bytes for StreamingResponse; lets
S3Error propagate so the serve route (chunk 4) can fall back to disk.
Sync calls — every call site wraps in asyncio.to_thread (chunks 3/4). One
unit test covers the unconfigured guard + endpoint scheme parsing (mocks,
no real MinIO). Not yet wired into remotion_client._save or the media route.
* MinIO chunk 3: wire write path (remotion_client._save PUT) (#310)
* feat(storage): wire MinIO write path in remotion_client._save
Chunk 3 of the MinIO plan (§3). After the local mp4 write, _save PUTs the bytes
to MinIO under key = Path(mp4_path).name (already {render_key}-{orientation}.mp4),
guarded by minio_client.get_client() (None when minio_endpoint empty) and
wrapped in asyncio.to_thread. Local disk stays the source of truth for the
poster publish path (x_video_client/tiktok_client read mp4_path from disk);
the PUT is additive. _save still returns the local path str — mp4_paths,
marker, and schema unchanged. Disabled (local-only) when MinIO unconfigured.
One test: asserts put_object is called with the basename key when configured
and the local file is still written; existing test stays green via the
unconfigured-default path. Mocks only.
* fix(storage): make MinIO PUT non-fatal in remotion_client._save
A configured-but-down MinIO made put_object raise inside the worker thread,
failing the render and retry-looping a task whose local file was already
written. Local disk is the source of truth and the serve route falls back to
FileResponse on S3Error, so a failed durable-copy PUT must never fail the
render — log and continue; the next render re-attempts the PUT.
Adds test_save_swallows_minio_put_failure (PUT raises -> _save still returns
the local path and the local file is written). Extends the CHANGELOG write-
path bullet with the non-fatal guarantee.
* MinIO chunk 4: serve path (StreamingResponse + FileResponse fallback) (#311)
* feat(storage): serve MinIO via the media route (StreamingResponse + FileResponse fallback)
Chunk 4 of the MinIO plan (§4 — the crux). GET /api/video/posts/{id}/media
derives key = Path(mp4_path).name and, when minio_endpoint is set, returns a
StreamingResponse over minio_client.get_object_stream(key), keeping
_require_ceo so auth stays end-to-end (no presigned URLs). Falls back to
FileResponse on S3Error (old render not in MinIO) or when MinIO is
unconfigured — the panel's axios-blob flow is unchanged (same URL, headers,
body, just chunked). The confinement check is kept as defense-in-depth (the
key is a basename so traversal is impossible, but the check is cheap and
protects the poster path).
Two integration tests: configured serve path streams from a stubbed
get_object_stream (CEO 200, non-CEO 403); unconfigured fallback serves the
local file via FileResponse. Mocks only — no real MinIO.
* fix(storage): eager stat_object probe so the MinIO serve fallback actually fires
The chunk-4 route wrapped StreamingResponse(get_object_stream(key), ...) in a
try/except, but get_object_stream is a lazy generator — its client.get_object
call runs on the first next(), i.e. AFTER the route returned and Starlette
started streaming. An S3Error (NoSuchKey / MinIO down) there is uncatchable;
the try/except caught nothing and the FileResponse fallback never triggered.
Add minio_client.stat_object(key): an eager existence/readiness probe that
runs INSIDE the route's try/except, so a missing object or down MinIO raises
before the StreamingResponse starts and the fallback serves the local file.
stat-then-get is two round trips; a mid-stream failure after a successful stat
is a rare race the CEO can retry (documented ceiling).
Tests: the configured test now stubs stat_object; a new test asserts the
S3Error fallback serves the local file via FileResponse and that
get_object_stream is never called. RAG doc updated to record the eager-probe
correctness detail + the non-fatal PUT.
* docs(rag): mark MinIO deployment note landed (chunk 5) (#312)
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
* fix(video): offload minio stat_object off the event loop
stat_object was called inline in the async media route, blocking the
shared event loop for one sync urllib3 round-trip per preview request —
contradicting minio_client's own 'every call site wraps in to_thread'
docstring and this PR's perf-fix theme. Wrap in asyncio.to_thread; the
try/except still catches S3Error (to_thread re-raises) so the
FileResponse fallback is unchanged. Also add the trailing newline to
the minio-storage RAG doc.
* Fix red CI
* Make CI green
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
|
||
|
|
e9d0e0bd48 |
feat(video): 0.19.0 video engine (Remotion) + preview auth + render persistence (#307)
* feat(video): Phase A — VideoEngine origination spine + held-source gates
New default-off engine skeleton: opens a UX/UI authoring task (source=video, assigned to a ux-dev, LOW complexity to clear the dev-needs-subtasks guard) and materializes a held CEO-approval draft (source=video_post). Excludes video_post from all three held-source skip sites; adds the video_draft marker, six config flags, and the feature-flag entries. Origination + gate behavior unit-tested.
* refactor(orchestrator): fold _dispatch_dev_work skip chain into a helper
The per-source if/continue chain grew past xenon's --max-absolute B when the video_post held source joined it. Extract _is_non_dev_dispatch_source (every held-CEO source plus the two Board exploration sources) so the dev loop's skip is one flat call. Behavior-identical.
* feat(video): Phase B — propose_video do-tool (metadata-only, team-gated)
UX/UI dev records a video's composition ref + per-platform captions onto the authoring task's video_draft marker. Team-gated at runtime via _caller_team (Role.DEVELOPER can't tell a ux-dev from a be-dev). Resolves the caller's ACTIVE task via get_active_task_for_agent, not an oldest-first scan that would clobber a second open video task. Metadata only, no render. Wired through do_server + route + schema; added to _DEV_DO.
* feat(video): Phase D — render loop + RemotionRenderer client
Orchestrator-async _video_render_loop renders a completed authoring task's merged composition to MP4 (vertical + square) via the remotion-renderer sidecar and materializes the held video_post draft. RemotionRenderer tars the read-clone's motion/ source, POSTs it, and saves the returned MP4 bytes to a TASK-scoped local path (no shared volume; a composition is reused across videos so a composition-scoped path would clobber an earlier draft). Render failures bounded-retry (read-clone catch-up window, transient sidecar) up to a cap, then terminal-fail. Client tested vs a mock transport; loop vs a mock renderer + real DB.
* feat(video): Phase C — release / spotlight / on-demand video triggers
Three entry points open a UX/UI video-authoring task via VideoEngine.open_video_task: (1) a published release drafts a companion video — best-effort in ReleaseProposalService.approve, never fails the publish; script from the CHANGELOG via the local model with a template fallback. (2) propose_feature_spotlight gains optional wants_video/video_script — best-effort, gated on video_on_spotlight, default-off leaves the spotlight flow byte-for-byte unchanged. (3) POST /video/request (CEO-only) for an on-demand brief, with clean disabled/not_opened responses. All gated on video_engine_enabled.
* fix(video): savepoint-isolate video-task inserts (F042 poisoned session)
The best-effort try/except around open_video_task (release-publish + spotlight hooks) swallowed the Python exception, but a DBAPI error at the insert flush left the shared session must-rollback — so the caller's next commit (release finalize / request boundary) threw PendingRollbackError: the release stuck 'pending' after actually publishing, or the spotlight draft + HTTP response were lost. Wrap both inserts (open_video_task, _originate_video_post) in a begin_nested savepoint (the repo's established F042 pattern) so a DB error rolls back only the insert. open_video_task returns None (every caller already handles it); _originate_video_post propagates to the render loop's handler. Regression test: an insert FK error returns None with the session left usable. Dormant while the flags were off; armed on the NAS.
* feat(video): Phase G — motion/ package + remotion-renderer sidecar + compose
In-repo Remotion v4 motion/ package (ReleaseAnnouncement composition; calculateMetadata returns 1080x1920 vertical / 1080x1080 square from inputProps.orientation) + a credential-free remotion-renderer sidecar: untar the POSTed motion/ source, bundle (LRU-cached per source sha), selectComposition + renderMedia h264, stream the MP4 bytes back — matching the RemotionRenderer client contract. docker/remotion.Dockerfile on Debian (Chrome apt deps, build-time Chrome pre-warm, ffmpeg bundled in @remotion/renderer). Wired into both compose files (roboco_default only, shm_size 1gb, /health check) + the release publish matrix. Verified via a real local render of both cuts; the Debian docker build is the CEO's to run.
* chore(video): D-hardening — video_post source_task_id + render-loop docstring
Add a source_task_id back-reference to the video_post held-draft marker (traceability from a draft to its authoring task; also makes the render loop's two-key idempotency check wireable later). Fix the render-loop test's stale docstring ('never retried' -> bounded-retry). Both from the Phase D critic's non-blocking follow-ups.
* feat(video): Phase E1 — VideoPostService + heartbeat mutex (approve->post)
CEO-approve->post service: heartbeat-renewed Redis mutex (fail-closed, grace=ttl-2*heartbeat), re-read-in-lock double-post guard, per-platform durable commits (asyncio.shield-ed, settle-before-rollback on lock-loss), all writes inside the lock (captions validated pre-lock, applied in-lock — no stale whole-column clobber), idempotent, per-platform retry-skip. Poster interfaces (X/TikTok, mocked here). Reject + list-held-drafts. Survived 3 adversarial rounds; residual = a crash in the poster->commit window (CEO-gated low-freq, documented).
* fix(video): G-hardening — renderer leaks + Share Tech Mono brand font
Sidecar: give bundle() an explicit outDir tracked + deleted on LRU eviction (was leaking ~19MB remotion-webpack-bundle-* per source); res.on('close') cleanup so an aborted/retried download no longer leaks its remotion-out-* MP4 dir. Fonts: vendor Share Tech Mono (roboco-website brand font) as the display face (self-hosted woff2, 400-weight, headline fontWeight 700->400 to avoid faux-bold) + self-hosted Inter body — no gstatic fetch at render time (lsof-verified). Extras: composition_id whitelist (400) + Multer error middleware (400/413).
* feat(video): Phase E2 — X v2 + TikTok posters, tiktok_credentials, routes
LiveXVideoPoster (X v2 chunked media upload: init/append/finalize/STATUS-poll -> tweet w/ media_ids, OAuth1 signer reused). LiveTikTokPoster (OAuth2 inbox: init -> chunked PUT with asymmetric final chunk -> status-fetch; 401 -> refresh_token grant, rotated token persisted). tiktok_credentials Fernet singleton + migration 062 (single head). Routes: CEO approve/reject + list held drafts + write-only tiktok creds, wiring real posters into VideoPostService. Residual: a lock-loss right after a token-refresh flush can discard the rotated token (same rare CEO-gated class as the documented post->commit window).
* feat(video): Phase F — panel video-post queue + TikTok creds card + flags
video-post-queue.tsx: <video> MP4 preview with 9:16/1:1 cut switch, per-platform editable captions (280/2200 counters, over-limit disables approve), approve/reject, Request-a-video dialog. tiktok-credentials-card.tsx (4 write-only OAuth2 fields). feature-flags-card inlines TikTokCredentialsForm under video_engine_enabled. Mounted in command-center. tsc/eslint clean, 273 panel tests green. NOTE: needs the GET /video/posts/{id}/media route + mp4_paths on VideoPostResponse (folded into H) for the preview source.
* feat(video): Phase H — media route + e2e smoke + NAS arming + docs
GET /video/posts/{id}/media?cut= (CEO-gated FileResponse of the rendered MP4; closes the panel preview gap) + mp4_paths on VideoPostResponse. e2e smoke tests/e2e_smoke/test_video_pipeline.py (full flow, sidecar+X/TikTok mocked; asserts dispatcher skips, render-loop materialize, propose_video team-gate, approve idempotency). NAS arming: docker-compose.yml/.yaml ROBOCO_VIDEO_ENGINE_ENABLED/ON_RELEASE/ON_SPOTLIGHT default-on (.yaml resynced to .yml); registry stays off. CLAUDE.md video-engine section + CHANGELOG. Fixed 2 pre-existing route-test pollution leaks. Full suite 11763 passed.
* fix(video): auth-carrying preview, media route confinement, VideoPost type drift
Three fixes along the video preview path:
1. panel video preview auth: the <video> element was pointed straight at
GET /video/posts/{id}/media, but a native <video src> GET carries none
of axios's X-Agent-ID/X-Agent-Role headers — so in the default
header-trust deployment the request 401s. Fetch the cut via
videoApi.getMediaBlob (axios, responseType: blob) and drive <video>
off a URL.createObjectURL result instead. The object URL is revoked
on cut-change (the previous cut's URL) and on unmount, so neither
cut switches nor row teardown leak blob URLs.
2. backend media route confinement: GET /video/posts/{id}/media now
resolves mp4_path and refuses it with 404 when it falls outside
settings.video_output_dir. Defense-in-depth against any future
writer of mp4_paths serving files from arbitrary disk locations.
3. panel VideoPost type/comment drift: added mp4_paths to the
VideoPost interface (the committed VideoPostResponse already
carries it), and corrected the stale comment on videoMediaUrl
that claimed no route served the rendered bytes — the route has
existed since the media endpoint landed; the comment now describes
why getMediaBlob exists instead of a direct <video src>.
* Persist rendered videos to data in physical storage.
* ++
* docs(video): 0.18.0 CHANGELOG entry + RAG + map reference for video engine
- Move the video engine bullet from [Unreleased] into [0.18.0] and note
the ROBOCO_VIDEO_OUTPUT_DIR bind-mount persistence.
- Add docs/rag/architecture/video-engine.md (mirrors x-engine.md shape:
enable/disable, three triggers, render loop + sidecar, CEO gate, media
route confinement, credentials).
- Reference the video render loop in docs/map/orchestrator.md's engine list.
* chore(video): re-bump to 0.19.0 + sync registry compose defaults
Version was wrongly bumped to 0.18.0; 0.18.0 is an already-released
section. Restore its 2026-07-04 date and move the video-engine CHANGELOG
bullet into a new [0.19.0] - 2026-07-05 section above it. Bump
pyproject.toml, roboco/__init__.py, roboco/config.py (app_version),
panel/package.json, and the motion/README inputProps example to 0.19.0.
docker-compose.registry.yml: add ROBOCO_VIDEO_ENGINE_ENABLED /
_VIDEO_ON_RELEASE / _VIDEO_ON_SPOTLIGHT defaulted false (NAS arms them
true), and comment out the video-renders bind mount with a short note
so the public registry image ships video off by default. Structural
sync with docker-compose.yml maintained.
* fix(video): rate-limit /render + reflow motion/README
CodeQL flagged js/missing-rate-limiting on the renderer /render route.
The sidecar is container-network-only with one trusted caller (the
orchestrator, which renders cuts serially), so this limiter is a
retry-storm ceiling (30/min, well above legit render rate), not the
primary control. Also reflows motion/README.md hard-wrapped prose that
failed the markdown quality gate.
* fix(build): finish pnpm 11 migration + regen verb tables
The panel Docker image build failed on `pnpm install --frozen-lockfile`:
node:22-alpine's corepack resolved to its bundled pnpm 11, but
panel/package.json pinned packageManager to pnpm@10.25.0, and pnpm 11
refuses to run against that pin. The Dockerfiles were already written for
pnpm 11 (comments, CI=true, strictDepBuilds); the package.json pin was the
stale outlier. Finish the migration instead of working around it:
- panel/package.json: packageManager pnpm@10.25.0 -> pnpm@11.10.0; drop the
`pnpm` field (pnpm 11 ignores it — build approval lives in
panel/pnpm-workspace.yaml's allowBuilds). Lockfile unchanged (pnpm 11
accepts it as-is); frozen-lockfile verified.
- remotion-renderer/package.json: pin packageManager pnpm@11.10.0 for
determinism (was relying on corepack's implicit default); engines.node
>=22.13 (pnpm 11 requirement).
- docker/panel.Dockerfile + docker/remotion.Dockerfile: `corepack prepare
pnpm@11.10.0 --activate` so the build uses the pinned version explicitly
instead of trusting corepack's bundled default (which a future
node:22-alpine could change).
- .github/workflows/panel-ci.yml: Node 20 -> 22 (pnpm 11 requires
Node >=22.13; Node 20 fails the engines check).
Also regenerate agents/prompts/_generated/{developer,head_marketing,verbs}.md
— the video engine added propose_video and extended propose_feature_spotlight
(wants_video, video_script) but the verb tables weren't refreshed, failing
the foundation-check quality gate.
* chore(build): approve esbuild build script in remotion pnpm-workspace.yaml
pnpm 11 generated this file with a placeholder ('set this to true or false')
during install; resolve it to true so local dev of the renderer doesn't
re-prompt. esbuild's postinstall only verifies the prebuilt platform binary
(@esbuild/<platform> is installed as an optional dep), so approving it is
safe and silences the ERR_PNPM_IGNORED_BUILDS warning.
* fix(build): copy pnpm-workspace.yaml into panel + remotion images
pnpm 11 hard-errors with [ERR_PNPM_IGNORED_BUILDS] (exit 1) when a
dependency ships a postinstall script that isn't approved in
allowBuilds. Both Dockerfiles copied only package.json + pnpm-lock.yaml,
so the build-approval map in pnpm-workspace.yaml never made it into the
image — the remotion image build died on esbuild@0.28.1's postinstall.
Copy pnpm-workspace.yaml alongside the manifests in both images. In
panel, this also drops the --config.strictDepBuilds=false workaround:
with sharp and unrs-resolver now approved, their postinstalls run and
install the platform-specific binaries (previously skipped, leaving
sharp without its @img/sharp-* binary at runtime).
Verified locally: remotion + panel `pnpm install --frozen-lockfile`
exit 0 with the workspace file present; both exit 1 without it.
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
|
||
|
Renn F
|
a69bc0184b | Bump version uv.lock | ||
|
Renn F
|
d6fffae6dd | uv.lock Upgrade | ||
|
|
7901ea419e |
Retire channels/sessions/messages; A2A becomes primary agent comms (#306)
* feat(a2a): deliver latest incoming message preview into the claim briefing
list_unread_a2a now carries last_message_preview (the latest message from the
OTHER agent, never the agent's own reply), fetched via a correlated subquery in
the same query — no N+1 on the per-verb briefing path.
* feat(a2a): read_a2a verb delivers unread message bodies to the agent
A2AService.get_unread_messages returns the caller's unread INCOMING messages
(never its own sends), marking exactly those rows read atomically so a message
arriving mid-call is preserved. Wired as the read_a2a content verb (route +
do_server tool + granted to every delivery role) — the content-bearing read the
A2A inbox lacked (read_messages only zeroed the counter).
* docs(rag): document read_a2a as the A2A content-read path
* fix(task): backlog activation no longer requires a discussion session
Removes the SessionTaskTable gate in activate() (and its dangling log field),
deletes _inherit_parent_session + its create() call, and drops the now-unused
SessionTaskTable import. Coordination rides task state; the session subsystem is
being retired. Tests updated to the new (no-session) behavior.
* fix(orchestrator): drop session sweep from _run_sweep
Removes the messaging import + sweep_timed_out_sessions call. That import sat
outside the try/except, so once messaging.py is deleted it would have killed the
entire sweep cascade (budget kill-switch, token rollups, retention, image prune,
superseded-PR reconcile). Notification sweep + all maintenance sweeps unchanged.
* release-manager --no-tags read-clone fix
* test: update evidence_repo unit test for a2a last_message_preview
* refactor(gateway): drop session propagation on delegate
Removes propagate_sessions_to_subtask from delegate(), the ChoreographerDeps
messaging field + property, and the ChoreographerDeps messaging arg in deps.py
(ContentActions messaging + import stay until the verbs are removed). Deletes the
propagation test; strips the now-invalid messaging kwarg from ChoreographerDeps
test builders.
* refactor(gateway): remove say/open_session/link_session/channels verbs
Removes the four channel/session verbs across content_actions (impls +
ContentActionsDeps.messaging), do_server (tools + registry), role_config (grants
+ _CHANNEL_DISCOVERY), do.py (routes), schemas/v1/do.py (request models), and
deps.py (MessagingService import + construction). Regenerates the prompt verb
tables. dm/notify/read_messages/read_a2a stay. Tests deleted/updated accordingly.
* uv.lock Upgrade
* refactor: remove conversation RAG indexing; Secretary announces via notification
Drops the CONVERSATIONS index (index_conversation, ConversationsIndexPlugin,
IndexType.CONVERSATIONS enum, IndexConversationParams, mentor.py type-label, the
messaging index hook) and its chunk-table manifest entries. The Secretary's
ANNOUNCE/RELAY_MESSAGE now fan out a BROADCAST notification to every agent's
inbox (NotificationService.broadcast) instead of posting to a dead channel.
* fix(panel): label RAG health error lines by subsystem
A red llm_error (e.g. the glm-5.2:cloud weekly-limit 429) rendered under
the 'Embedding: ok' header with no label, reading as an embedding failure.
Prefix each error line with LLM / Embedding / Vector store.
* refactor: remove channel/message reads from metrics, dashboard, git, events
MetricsService drops get_communication_volume + the MessageTable
message-count in get_agent_metrics (and the now-dead messages_sent_week
field). DashboardService drops get_channel_feeds/_compute_channel_status
and the message read in get_recent_activity (task activity kept);
get_auditor_metrics no longer reports communication_volume.
GitService's two primary-session-id helpers always return None now
(callers already treat None as "no primary session"). events/handlers.py
drops the SESSION_CLOSED/SESSION_TIMEOUT subscriptions + the
handle_session_boundary handler.
Forced follow-on: api/routes/dashboard.py + api/schemas/dashboard.py
dropped the now-dangling live_feeds/ChannelFeed surface and the
/metrics/communication route, which wrapped the removed service calls
directly (mypy would otherwise fail on the missing attributes).
* refactor: delete MessagingService + channel seeding
Edited db/__init__.py and services/__init__.py first (drop the unconditional
Channel/Group/Message/Session table + MessagingService re-exports), then
deleted services/messaging.py, then trimmed db/seed.py to only create_agents
(create_channels/create_channel_memberships/create_initial_messages gone).
Forced expansion: api/routes/{channels,groups,sessions,messages}.py import
roboco.services.messaging directly (not through the package __init__), as
does api/routes/tasks.py (the session-links embed on GET /tasks/{id} and the
GET /{id}/sessions route). Deleting messaging.py without addressing these
breaks `import roboco.api.app` immediately, since app.py eagerly imports all
route modules at startup. Since the 4 CRUD route files are 100%
MessagingService-backed with zero independent logic (and are wholesale
deletes in the plan's later API-routes task anyway), deleted them now +
unmounted from app.py/routes/__init__.py; tasks.py got the same surgical
trim its later task already specified (drop session-links embed +
TaskSessionLinkResponse/TaskResponse.sessions). This pulls a slice of that
later work forward — the routes/schemas for channels/groups/sessions/messages
still need their own pass, but their messaging-coupled parts are gone.
Verified with a full-suite collection sweep (12010 tests collected, zero
import errors) beyond the directly touched test dirs, given the expanded
blast radius.
* refactor: remove channel/session/message models, tables, and channel policy
Models: deleted channel.py/group.py/session.py/messaging.py wholesale
(zero external consumers besides the models/__init__.py re-export).
message.py surgically trimmed: removed MessageCreate (dead) and MessageEdit
(never instantiated; ExtractedMessage.edit_history retyped to
list[dict[str, Any]] to match how it's actually persisted — confirmed
ExtractedMessage was never written to any DB table, so MessageTable's
removal carries no functional risk to the kept extraction pipeline).
base.py: removed SessionStatus + ChannelType, kept MessageType. Also
removed the confirmed-dead channels_read/channels_write fields from
models/agent.py:AgentPermissions and models/dashboard.py:ChannelFeedData.
db/tables.py: deleted ChannelTable/GroupTable/SessionTable/SessionTaskTable/
MessageTable, TaskTable.session_links, and JournalEntryTable.session_id —
cascaded through models/journal.py, services/journal.py, and
api/schemas+routes/journals.py (22 plumbing sites).
foundation/policy/communications.py: removed the ChannelSpec/CHANNELS
catalog + TEAM_SCOPED_ROLES/_CELL_*/_AUDITOR_ONLY helpers, kept the
notification policy (Priority/parse_priority/NOTIFY_SENDER_ROLES/
ACK_REQUIRED_BY_TYPE). enforcement/channel_access.py deleted (confirmed
fully dead in production). agents_config.py: removed CHANNEL_ACCESS
(kept A2A_ALLOWED_PAIRS). seeds/initial_data.py: removed
DEFAULT_CHANNELS/CHANNEL_MEMBERSHIPS/AUDITOR_SILENT_ACCESS + the
never-consumed INITIAL_MESSAGES. config.py: removed
session_idle_timeout_seconds (zero consumers). exceptions.py: removed
dead ChannelError/ChannelAccessDeniedError/SessionClosedError.
Forced expansion beyond the original file list — ChannelType cascaded
into a live, mounted surface the plan didn't trace: agents_config.
CHANNEL_ACCESS -> services/permissions.py's channel-RBAC methods (not
models/permissions.py, which turned out to have no channel code at all)
-> two real endpoints in api/routes/stream.py (GET /permissions,
GET /permissions/channel/{name}) and two dependency factories in
api/deps.py. Removed the channel methods + fields, deleted the
channel-specific stream.py endpoint, deleted require_channel_read/write.
Also deleted api/schemas/{channels,sessions}.py (hard dependency on the
removed enums; already fully dead after the Task 10 route deletions) and
api/schemas/messages.py (a TYPE_CHECKING-only import of the deleted
MessageTable; likewise already fully dead) + its dedicated test file.
Test updates: test_permissions.py -14 channel tests (matches the planned
count exactly), test_communications.py / test_communications_consumers.py
split to keep only notification-policy coverage, test_exceptions.py -9,
test_deps.py -4, plus the journal/stream/foundation-smoke fallout. Also
fixed a pre-existing (Task 7) broken assertion in
test_foundation_phase3_smoke.py that inspected a `say()` method already
removed from ContentActions.
Verified: full-suite collection (11961 tests, zero import errors) and a
complete test run (11567 passed, 394 skipped, 0 failed) in addition to
the targeted suites.
* migration: drop channels/groups/sessions/session_tasks/messages + enum types
alembic/versions/060_drop_messaging.py: drop_column journal_entries.
session_id (sidesteps hardcoding the FK constraint name — verified
empirically against a live migrated DB that it's actually
fk_journal_entries_session_id_sessions, but drop_column doesn't care
either way); drop_table in FK order (messages -> session_tasks ->
sessions -> groups -> channels); DROP TABLE IF EXISTS chunks_conversations
(runtime-provisioned, not alembic-managed, would otherwise orphan); DROP
TYPE IF EXISTS for messagetype/sessionstatus/sessionscope/channeltype
(messagetype's Python enum stays for ExtractedMessage, but the DB type
had zero live columns left once MessageTable was dropped in the prior
commit). downgrade() raises NotImplementedError — one-way removal.
Pruned scripts/reset_runtime_state.sql + .sh: removed the DELETE/COUNT
lines for messages/session_tasks/sessions/groups/channels and the
groups.active_session_id reset block.
Verified end-to-end against a scratch Postgres DB: full migration chain
001->060 applies cleanly, alembic heads shows a single head, all 6 dropped
tables + 4 enum types + the journal_entries.session_id column are
confirmed gone, journal_entries keeps only its journal_id/task_id FKs,
downgrade correctly raises NotImplementedError without corrupting DB
state, and the pruned reset_runtime_state.sql runs clean (no errors)
against a fully-migrated DB.
* refactor(api): remove channel/session/message routes + WS streams
Most of this task's file list was already forced through in earlier
commits (routes/{channels,groups,sessions,messages}.py + app.py/__init__.py
unmounting in the MessagingService-deletion commit; tasks.py's
session-links embed + GET /{id}/sessions + schemas/tasks.py's
TaskResponse.sessions in that same commit; deps.py's require_channel_read/
write + schemas/{channels,sessions}.py in the models/tables commit). This
closes out what was left:
- api/websocket.py: deleted the channel_stream + session_stream routes,
ConnectionManager's channel_connections/session_connections dicts,
connect_channel/connect_session, broadcast_to_channel/broadcast_to_session,
get_channel_subscriber_count, and their cleanup lines in disconnect().
Agent streams, notification streams, and the operator system stream are
untouched.
- api/websocket_bridge.py: deleted _handle_session_event +
_handle_message_event and their SESSION_CREATED/SESSION_CLOSED/
SESSION_TIMEOUT/MESSAGE_SENT subscriptions. The A2A live-view, rate-limit,
usage, agent-lifecycle, and notification bridges are untouched.
- api/schemas/websocket.py: removed NewMessageBroadcast, WSMessageNew,
WSMessageEdit, WSMessageDelete, WSSessionClosed — kept the WSMessage base
class (still subclassed by the kept WSAgentStream/WSNotification) plus
those two.
- api/schemas/groups.py: deleted (already fully orphaned since routes/
groups.py was removed; its GroupResponse/GroupDetailResponse had zero
consumers).
Updated the 5 websocket test files accordingly (removed the channel/
session-specific tests + fixed imports); test_websocket_bridge.py's
registration-coverage test dropped the SESSION_*/MESSAGE_SENT assertions.
Verified: full-suite collection (11943 tests, zero import errors) and a
complete test run (11549 passed, 394 skipped, 0 failed).
* docs: retire channels/sessions/messages from agent-facing docs + CLAUDE.md
Rewrites docs/rag (RAG-indexed) + docs/map + CLAUDE.md to reflect A2A (dm +
read_a2a) as primary agent comms; deletes the channel docs, splits messaging-tools
+ messaging-notification (renamed notification.md), swaps the WS worked example to
A2A_MESSAGE_SENT. _complete_map.md still needs regeneration (generated file).
* refactor(panel): remove Communications surface (channels/sessions)
Deletes the /communications routes, message components, task-detail Sessions tab,
use-channels + channel/session WS hooks, and the channels/sessions/messages/groups
api clients; prunes the Channel/Session/Message/Group types + mock data. (Auditor
live-feeds + dashboard.ts dead-route cleanup is a follow-up.)
* refactor(panel): drop auditor channel-feed + dead communication-metric route
* docs(map): regenerate _complete_map from updated slices
* fix(a2a): reduce get_unread_messages complexity below xenon C + stale comments
Extract the per-conversation unread-counter recompute into _reset_unread_counter
(the CI quality gate flagged get_unread_messages as rank C). Also drop the deleted
open_session from a content_actions comment and reword an evidence_repo docstring
that cited the removed messaging._notify_mentions.
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
|
||
|
|
3ccc723cd4 |
v0.17.0 — Wave 3: sandbox DB, DB isolation, mobile UI, cloud auth, X account, roadmap engine (#303)
* feat(sandbox): throwaway per-agent Postgres/Redis sandbox containers
Orchestrator-provisioned sibling containers per agent spawn
(SandboxProvisioner, roboco/runtime/sandbox.py). Per-project opt-in via
projects.sandbox_services (migration 057); master switch
ROBOCO_SANDBOX_DB_ENABLED, default-off, armed in the NAS compose only.
When active, ROBOCO_TEST_DB_* / ROBOCO_TEST_REDIS_* point at the sandbox
and the prod-creds gate-env injection is suppressed (sandbox replaces,
never coexists). Sandbox lifetime tracks the agent container: teardown at
every removal path, orphan janitor at startup + each reaper tick with a
grace window for mid-flight spawns. The pre-spawn stale-clear spares the
just-provisioned sandbox; provision pre-clears stale same-named
containers from a crash-missed teardown.
Panel: per-project sandbox-service switches in the edit dialog + feature
flag card entry.
* docs: CLAUDE.md entry for the sandboxed dev DB/Redis subsystem
* feat(security): isolate prod Postgres/Redis from agent containers (roboco_data network)
Second user-defined bridge roboco_data carries postgres+redis only; the
orchestrator is multi-homed (default + data). Spawned agents and their
sandbox sidecars stay on roboco_default and can no longer resolve or
reach roboco-postgres:5432 / roboco-redis:6379 (redis has no auth —
membership is its only containment). Normal bridge, so host-published
ports (15432/16379) keep working. Applied to both build composes and
the registry compose; docker-compose.yml re-synced byte-identical with
docker-compose.yaml (it had drifted by the sandbox flag block).
ROBOCO_DB_NETWORK_ISOLATED (config default false, armed alongside the
topology) suppresses the legacy _append_gate_env prod-creds injection:
under isolation those creds dead-end, and unreachable creds are worse
than none. DB-needing projects opt into sandbox_services instead. The
flag is deliberately not a panel feature flag - it must travel with the
compose networks: stanzas.
Preserved by construction: agent<->agent A2A and orchestrator->agent SDK
polls on :9000, MCP->orchestrator on :8000, ollama reachability, docker
exec/inspect (daemon socket), host port publishing.
* feat(panel): full mobile responsiveness pass
Shared primitives: useIsMobile (useSyncExternalStore, hydration-safe,
memoized matchMedia subscribe), ResponsiveTable table->card switch below
md (single subtree mounted, no duplicated interactive rows), scrollable
snap TabsList in the base primitive (justify-center-safe so the first
tab stays reachable on overflow), persistent md:hidden bottom tab bar
(Overview/Tasks/Kanban/Chat, safe-area padded).
Applied: card lists for tasks/projects/products/work-sessions/sessions
+ the three raw metrics tables; CEO approval queue / release proposal /
playbook review action rows stack on narrow; command-center reorders
approvals above the fold on mobile; task-header metadata wraps;
Communications + A2A become URL-driven single-pane drill-downs below lg
(fixes the unconstrained-height ScrollArea bug) with dvh heights;
recharts label density/radius adapts via useIsMobile; git diff viewer
gets mobile font + wrap toggle; vh->dvh sweep; chat composers get
safe-area-inset padding; dashboard main p-4 md:p-6 + pb-20 for the bar.
Verified at 375px on the built app: bottom bar, drawer, approval-first
overview, swipeable kanban tab strip. All gates green (eslint, tsc,
vitest 249, next build 24/24 routes).
* feat(auth): cloud auth via FastAPI Users (default-off, single-user cookie session)
ROBOCO_CLOUD_AUTH_ENABLED (default off) lets the panel/API be exposed
beyond localhost without changing the CEO's local no-login flow while
off — get_agent_context and the WS gate are byte-for-byte unchanged in
off-mode. On: header-trust dies for humans — any agent-role claim (ceo
or a privileged PM/board role) with no valid HMAC token or session
cookie is 401, closing the header-spoof hole on the host-published
:8000 port for every role. The agent-fleet HMAC path and the system
self-PATCH keep working unmodified in both modes.
Single seeded CEO user (migration 058 users table, UserTable), no
registration router — idempotent env-driven upsert at startup by PK.
Cookie transport (httponly/secure/samesite=lax) + a JWTStrategy bound
to a fingerprint of the current password hash (rotating the password
invalidates every prior session). Sliding 30-day session: every
authenticated request re-mints the cookie, so an active session never
expires — no unexpected logouts.
Panel: (auth)/login page + proxy.ts (Next 16 rename of middleware; probes
/auth/status over the docker-internal URL, fails open to off) gate the
dashboard; client.ts gets withCredentials + 401->/login. nginx unchanged.
Review hardening: broadened the on-mode rejection from ceo-only to every
non-CEO role without a valid token (was only closed when
ROBOCO_AGENT_AUTH_REQUIRED was also armed); Next-16 proxy.ts rename to
clear the middleware deprecation warning.
* feat(x): RoboCo X account engine — HoM drafts, per-post CEO approval (default-off)
ROBOCO_X_ENGINE_ENABLED (default off, inert without creds). Mirrors the
ReleaseManagerEngine held-artifact shape: XEngine drafts a post when a
release publishes (via a draft_release_post seam on ReleaseProposalService
.approve) and drafts replies to meaningful mentions (dedicated poll loop,
x_seen_mentions dedup ledger, per-cycle/open caps). Drafting is
local-model-only, clamped to 280 chars. Nothing auto-posts — every tweet
is a held task (source x_post/x_reply, confirmed_by_human=False,
Secretary-owned, dispatcher-skipped) the CEO edits/approves/rejects in a
panel queue.
The four OAuth 1.0a secrets live Fernet-encrypted in a singleton
x_credentials row (migration 059, all-or-nothing, API returns only
has_credentials); decryption is server-side, agents never hold creds or
egress. Hand-rolled OAuth 1.0a HMAC-SHA1 signer, no new dependency;
NullXClient makes the unconfigured path a graceful no-op.
XPostService.approve (CEO-only) is the sole caller of post_tweet.
Review hardening: closed a double-post race — the approve path now
re-reads committed task state inside the Redis lock and commits COMPLETED
before releasing, so a concurrent approve that acquires the lock after the
winner released can't re-post (SET-NX is non-waiting, and the route-level
commit landed after the lock dropped). Added a regression test.
* feat(roadmap): board roadmap engine — PO proposes themed cycles, CEO approves per-item (default-off)
ROBOCO_ROADMAP_ENGINE_ENABLED (default off). Weekly, RoadmapEngine opens
ONE held exploration task (source=board_roadmap, confirmed_by_human=False,
Product-Owner-assigned), deduped to one open cycle. A dedicated one-shot
_dispatch_roadmap_exploration spawns the PO solo (not the two-reviewer
board path, which would also spawn HoM + fire Approve-&-Start). The PO
explores read-only (git/KB/metrics/releases/charter/web) and makes one
propose_roadmap call (PO-only content verb) authoring a themed cycle —
goal + 3-7 item drafts — persisted as a roadmap_cycle marker (no table,
no migration; head stays 059).
The CEO acts per-item in the panel roadmap queue: approve materializes a
BACKLOG task (source=roadmap, no assignee — never auto-starts), reject
records a reason; all-items-terminal completes the exploration task.
RoadmapService is idempotent per item. Dispatchers skip board_roadmap.
Includes a real SQLAlchemy dirty-check fix (deep-copy the JSON marker
before mutating, or the in-place edit + reassign compares equal to its
own baseline and the UPDATE is skipped).
Review hardening: create_task_from_draft now honors a draft-declared
source only from a {prompter, roadmap} whitelist — drafts are
LLM-authored, so an unbounded source could impersonate a privileged
origin (release_manager would even wedge that engine's dedup).
* chore(release): 0.17.0
Wave 3 — six default-off subsystems: sandboxed dev DB/Redis, prod
Postgres/Redis network isolation, full mobile UI pass, cloud auth
(FastAPI Users), the RoboCo X account engine, and the board roadmap
engine. Plus the waves 1+2 work already on master since 0.16.0.
Version bumped across the canonical set (config.py, __init__.py,
pyproject.toml, panel/package.json, uv.lock); CHANGELOG [Unreleased]
cut to [0.17.0]; docs/map delta added.
Compose: every optional feature armed :-true in the NAS composes, OFF
in the user-facing registry compose. Two opt-in exceptions default off
(CLOUD_AUTH — needs email/password/secret + TLS, would otherwise fail
startup; ROUTING_STRICT — fail-closed spawning). DB_NETWORK_ISOLATED
stays on in both (coupled to the roboco_data topology).
* chore(compose): arm cloud_auth + routing_strict ON in the NAS composes
Every feature defaults ON in the NAS composes per policy — these two
were wrongly left off. Both keep the ${VAR:-true} form so the operator
controls the real runtime via .env: cloud auth needs
ROBOCO_CLOUD_AUTH_EMAIL/_PASSWORD/_SECRET + TLS set there before a boot
(else startup fails loud), and routing_strict is fail-closed. Registry
compose keeps both off.
* fix(ci): reflow board.md prose (quality gate) + document v0.17.0 env creds
The roadmap section added hard-wrapped prose that failed the markdown
prose gate; reflowed (token-invariant). Also brought .env.example
current: cloud auth (now armed — needs SECRET or startup fails), routing
strict, the X engine (panel-entered OAuth), and web research.
* fix(ci): reduce cyclomatic complexity of five wave-3 blocks (xenon gate)
The wave-3 subagents introduced C-rank functions the CI xenon gate
rejects (my per-item reviews ran ruff/mypy/pytest but not xenon):
- sandbox.janitor_sweep -> extract _list_labeled_sandboxes /
_list_live_agent_containers / _prune_grace
- x_client.fetch_mentions -> extract _parse_mention_items
- x_engine.run_cycle -> extract _process_mentions
- orchestrator._dispatch_pm_work -> extract the source-skip into a
MODULE-level _is_held_ceo_source (module, not method, so the
wholesale-mocked dispatcher unit tests exercise the real logic)
- auth/seed.ensure_seed_user -> extract _apply_seed_updates (module avg -> A)
Behavior-preserving; full suite green (11902), xenon clean.
* fix(ci): declare pyjwt + fastapi-users-db-sqlalchemy as direct deps (deptry)
The cloud-auth code imports jwt and fastapi_users_db_sqlalchemy directly
but they were only transitive deps (via fastapi-users), which deptry
(quality gate, DEP003) rejects. Declared explicitly; deptry roboco/ clean.
Missed originally because local make quality stopped at earlier gates
before reaching deptry.
* feat(x): gate mention replies behind ROBOCO_X_REPLIES_ENABLED (default off)
Per CEO decision: the X engine should only post about releases by
default. Reading mentions needs a paid X API tier, so the mention-reply
half is now a deliberate opt-in on top of release posting.
New default-off flag x_replies_enabled gates the mentions poll loop
(_x_mentions_poll_loop) and XEngine.run_cycle; release-post drafting
(the release-proposal approve hook) is unaffected and still runs when
x_engine_enabled + credentials are set. Added to FEATURE_FLAGS + the
panel card. Tests: release posting works with replies off; run_cycle +
the poll loop are no-ops with replies off.
* fix: 401 only redirects to /login when cloud auth is on; panel-token strips .env quotes
Two bugs that together dead-ended login in secure mode:
- client.ts redirected to /login on ANY 401, so a mismatched panel
token (header-trust/secure mode, cloud auth off) bounced the user to a
login page whose backend route isn't mounted -> 404. Now it probes
/auth/status (bare fetch, no interceptor re-entry) and only redirects
when cloud_auth_enabled.
- make panel-token read the .env secret with grep|cut without stripping
surrounding quotes, so a quoted ROBOCO_AGENT_AUTH_SECRET produced a
token signed with the quotes included — which never verifies against
the orchestrator (docker-compose/pydantic unquote the secret). Now
strips surrounding single/double quotes.
* fix: git-log 500 on '|' in commit message; X queue shows an empty state
- GET /api/git/log 500'd (ValueError: Invalid isoformat) when a commit
SUBJECT contained a '|' (e.g. the 'curl|sh' lockdown commit): the
fixed '|' field delimiter let the subject's pipe shift the split so
author+date collapsed into one field. Switched to \x1f (Unit
Separator), which can't appear in commit content. Regression test with
a piped subject.
- The X Post Queue returned null when empty, so there was no visible
place for the X drafts. It now renders a discoverable empty state
pointing at Settings -> X credentials.
* docs: bring docs/rag + docs/map current for v0.17.0 (waves 1-3)
Agent-facing RAG corpus and codebase map updated for every feature in
the 0.17.0 span, code-verified:
- wave 3: sandbox DB, DB network isolation, cloud auth, X engine
(+ x_replies_enabled sub-flag), board roadmap engine — new RAG
architecture pages + role/tool/config-reference updates; new symbols,
migrations 057-059, panel surfaces, and the get_agent_context
dual-path across the map slices.
- waves 1-2: A2A live view + switchboard, prompter memory
(search_past_tasks), Secretary edit access + PM-lighter scope, the
PR-gate auto-submit turn cut (ROBOCO_PR_GATE_AUTO_SUBMIT_ENABLED).
- correctness fix: api-routes-schemas.md no longer claims the A2A admin
routes are reachable by any authenticated agent — they carry a
_require_ceo gate (wave 2c).
docs/internal, _front.md deltas, and the frozen _complete_map.md
snapshot untouched.
* fix(rag): atomic upsert for indexed-doc tracking (kills e2e segfault)
The indexed-document tracking write used check-then-insert in two paths
(IndexedDocumentRepository.upsert_batch and the file-source
_upsert_doc_record). Under concurrent indexing both callers saw no row
and both inserted, so the second violated uq_indexed_doc_source and
poisoned its transaction — surfacing in CI as the intermittent
_checkin_failed SIGSEGV on the failed connection's pool checkin.
Both paths now use INSERT ... ON CONFLICT DO UPDATE against the
constraint: coalesce keeps an existing title/preview when the new value
is empty (matching the old guards) and metadata is jsonb-merged. The
batch dedupes within itself first (ON CONFLICT can't touch a row twice
in one statement). expire_all after the Core upsert keeps same-session
ORM reads consistent with the merged DB row.
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
|
||
|
|
5936c2bdea |
Docs split Phase 1: docs.roboco.tech becomes canonical — redirect stubs, user tree removed, MkDocs retired (#299)
* docs: replace MkDocs deploy with static redirect stubs docs.roboco.tech (roboco-website) is now the canonical user-facing docs site (spec: docs/internal/specs/2026-07-03-docs-site-split.md). Every URL this repo's Pages site published needs to keep resolving, so scripts/gen_docs_redirects.py generates one meta-refresh + rel=canonical stub per page — derived from mkdocs.yml's nav while it still lists every page — into the committed docs-redirects/ directory. All 58 stub targets verify against the website repo's nav.ts (0 unmapped); the only rename is how-to/* -> tour/* per the spec's slug map. Rewrite .github/workflows/docs.yml to deploy docs-redirects/ directly instead of running `mkdocs build`. The user-facing docs/ tree and mkdocs.yml itself are untouched here — deleting them is the next step, gated on these stubs resolving correctly. * docs: delete the MkDocs user-facing tree, docs.roboco.tech is canonical Per docs/internal/specs/2026-07-03-docs-site-split.md decision (1): Material->MDX is not verbatim-portable, so repo A's user-facing docs are deleted rather than kept as a permanently-drifting mirror. Deletes index/get-started/company/how-to/panel/models/operations/optional/deploy/ api/troubleshooting plus images/videos/assets. KEEPS docs/rag/ (indexed agent corpus), docs/map/, docs/internal/, and the team buckets (backend/frontend/ux_ui) — none of these were ever in mkdocs.yml's nav. mkdocs.yml's entire nav mapped 1:1 onto the deleted tree, so pruning it "accordingly" leaves nothing — remove it outright, along with the now-dead `docs` optional-dependency group (mkdocs/mkdocs-material/mkdocstrings/ pymarkdownlnt — mkdocstrings was already unused, not wired into any mkdocs plugin), the matching deptry DEP002 ignore entries, .pymarkdown.json, and the serve-docs/build-docs/lint-docs/fix-docs Makefile targets (all scoped only to the deleted paths). Add regen-docs-redirects as the one remaining docs Makefile target. Repointed everything that linked into the deleted tree or the old Pages URL: README's hero video/gif and walkthrough links now hit the docs.roboco.tech-hosted copies (already duplicated there per the spec's ground truth), usage.md / deployment.md's jump-links, pyproject's Documentation URL, and CLAUDE.md's Blueprint Reference paragraph. * chore: sync uv.lock after removing the docs optional-dependency group Follow-up to the mkdocs.yml / docs extra removal — mkdocs, mkdocs-material, mkdocstrings, pymarkdownlnt, and their transitive-only dependencies drop out of the lockfile now that nothing in pyproject.toml declares them. --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com> |
||
|
Renn F
|
6b5691b02a | chore(release): 0.16.0 | ||
|
|
0f1ed3cc6a |
Hotfixes (#293)
* fix(mcp): delegate tool carries the collision surface the B1a gate demands
TASK_AT_DELEGATE (
|
||
|
|
cfde4369b1 |
Token optimization levers — claim-scoped briefing, payload caps, role-scoped optimal, notification-spawn cooldown (#292)
* feat(gateway): claim-scoped context briefing — heavy sections only on context-acquisition verbs
* feat(gateway): cap unbounded LLM-facing payloads — embedded diffs, notification bodies, handoff journal content, north star
* feat(mcp): role-scope the optimal server's tool groups; index management becomes dev/test-only
* feat(mcp): cap per-result content on kb/error/learning search, mentor sources, rag citations
* refactor(gateway): extract heavy-briefing sections + clip helper to keep xenon ranks
* feat(orchestrator): cross-tick cooldown for notification-triggered spawns
* feat(usage,orchestrator): scope spawn-waste to anthropic sessions; cap agent Bash output via settings env
* docs: claim-scoped briefing, payload caps, optimal role-scoping, notification-spawn cooldown
* test(mcp): type the mixed-item cap fixture explicitly
* fix(orchestrator): lazy-init the notification-spawn cooldown store
* fix(lifecycle): admin-override claim reconciliation + PM request_changes verb (S6 postmortem B3+B4)
B3 — admin_set_status now reconciles claim ownership when leaving BLOCKED:
review/queue targets clear claimed_by/claimed_at/active_claimant_id and
consume the pre-block snapshot (a stale escalation claim was stranding the
next claimant: give_me_work handed the task out while note() bounced
not_authorized — the live b8fe0494 wedge). The pending/in_progress restore
path also syncs active_claimant_id, and a REST PATCH unassign releases the
claim with it.
B4 — new PM verb request_changes: awaiting_pm_review -> needs_revision with
concrete issues. The PM previously had no reject at merge review (only
complete/escalate), so an AC/scope violation looped i_am_blocked->escalate
4x live. Full vertical: lifecycle transition + ActionSpec + IntentSpec,
TaskService.request_changes (routes like a QA fail — original dev for a
leaf, revision PM for assembled; issues appended to dev_notes), verb-runner
compose, choreographer verb (spec gate + non-empty issues + soup check +
a2a delivery of the reject reason), HTTP routes on both PM flows, MCP tool,
journal:decision tracing, PM prompts, regenerated lifecycle artifacts.
* fix(panel): stop scorecard fetches for fallback-roster placeholder ids
useAgents() serves the static AGENT_ROSTER (ids "1".."22") while agent
definitions load; the Scorecards tab fetched a member scorecard per row
immediately, firing 22 guaranteed-422 requests per refetch cycle. Through
the browser's per-origin connection limit those queued every metrics-page
query behind them (~10s of skeletons on every tab). Gate the fetch on a
real member id (agent UUID or the "ceo" alias).
* Upgraded uv.lock
* fix(sequencing): declared deps become real edges + full loop-breaker coverage + assembled-branch freshness (S6 postmortem B1/B2/B6 + breaker)
B1a — code delegations REQUIRE a collision surface: new TASK_AT_DELEGATE
completeness spec (conditional FieldRequirement, when=('task_type','code'))
enforced at the gateway delegate gate. A no-surface code sibling is
'parallel to everything' by analyzer design, which is how two devs ran the
CEO's explicitly-ordered work out of order (f3e1afc5: seq#1 started before
seq#0, zero dependency edges). PM prompts updated; REST/manual creation
(TASK_AT_CREATE) unchanged.
B1b — the CEO's declared 'Depends on' lists become real edges: DraftSurface
gains declared_depends_on; SequencingService.analyze unions declared edges
(validated: self/out-of-range rejected) with the derived collision rules,
cycle-checked by the existing toposort. confirm_live_batch/preview_batch
map each draft's depends_on through (string indices coerced); intake tool
doc + prompter role prompt instruct verbatim copying. The live S6 root got
1 of its 3 declared in-batch edges and started alongside still-running R3.
Breaker coverage — the progress-aware respawn circuit breaker
(_pm_respawn_should_gate: strike counting, status-advance reset,
tracing-gap budget, DB durability, one-shot CEO notification) was consulted
by only 3 spawn paths; the doc/QA/dev/PR-review/PR-gate/revision/board
paths spawned unguarded at fixed cadence (the 26-respawn fe-doc loop,
~$7.20). Now consulted at every task-keyed spawn site (14 total).
B2 — assembled-branch freshness: submit_up/submit_root auto-sync the
assembled branch when it has fallen behind its base (children are terminal
at submit time, so the rebase is safe; master is never written). A rebase
conflict is a hard reject naming the files instead of a blind re-review —
kills the needs_revision↔awaiting_pr_review ping-pong of re-submitting a
stale head. Leaf i_am_done already had the behind-base gate; claim-time
fetch-fresh cut already existed.
B6 — documenter revision-pass loop: the awaiting_documentation bail
rejections (i_am_blocked/unclaim) now name the actual exit (i_documented
re-affirm) and the documenter prompt gets an explicit revision-pass rule.
* fix(orchestration): assembly-integrity gate + dispatcher heartbeat (incidents #11, #1)
Assembly integrity — submit_up/submit_root refuse when a completed child's
commits are not patch-present in the assembled branch (git cherry —
rebase-safe; branch pruned after merge or any git error fails open). Live
incident #11: a completed revert subtask's merge was lost from the cell
branch and the review gate re-flagged the exact violation the revert fixed,
spawning another revision cycle.
Dispatcher heartbeat — a dispatcher.alive audit row every 5 minutes from
the dispatch loop. The 2026-07-01 outage was 4h25m of fleet-wide silence
with no way to distinguish 'loop dead' from 'no work'; the loop's stdout
died with the container while audit_log survives. CHANGELOG for tonight's
full sweep included.
* style: ruff format for the orchestration sweep
* refactor(gateway): fold the assembled-submit guards + trim complexity under the xenon gate
_assembled_submit_guards combines the #11 integrity check and B2 freshen for
submit_up/submit_root; lifecycle's invalid-source remediate and git's
per-child cherry probe extracted into helpers. Test harnesses built via
__new__ stub the respawn tracker (the breaker now runs on their paths).
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
|
||
|
|
0ca9d91b72 |
v0.16.0: fastapi-guard HTTP security layer — calibrated + scanner honeytrap (#290)
* [fastapi-guard] Phase 1a: gated config flags for the HTTP security layer Adds the ROBOCO_GUARD_* settings (all default-off / secure-default) for the upcoming fastapi-guard 7.2.0 hardening — guard_enabled (master switch), guard_fail_secure (fail-closed default; NAS overrides to false), guard_telemetry_enabled + guard_agent_api_key + guard_project_id (guard-agent telemetry, opt-in), guard_emergency + guard_emergency_whitelist (lockdown kill switch). Inert until consumed: nothing reads them yet, so the request path is unchanged. Foundation for v0.16.0. * [fastapi-guard] Phase 1b: security foundation module + gated wiring Add fastapi-guard 7.2.0 + guard-core 3.3.0 (bare, unpinned) and roboco/security.py: - build_security_config() from settings — behind-nginx real-IP (trusted_proxies + trust_x_forwarded_proto), HSTS/CSP headers, threat-ban + 404-sweep rules, redis-backed state, exclude_paths (/ws + health + docs), env-driven enforce_https, fail_secure (secure default), emergency lockdown, guard-agent telemetry (opt-in), passive-mode calibration switch. - guard_deco singleton (SecurityDecorator) for per-route decorators (Phase 2+). - Three custom content validators guard's WAF can't cover: prompt-injection / role-override, secret-exfil / credential-in-body, internal-SSRF. - apply_guard(app) + guarded_lifespan() wired into create_app AFTER settings. guard_passive_mode config flag added. Entirely gated by ROBOCO_GUARD_ENABLED (default off): create_app mounts nothing and returns the unchanged app when off (verified). make quality GREEN (cov 95.32%, pip-audit clean, import-linter 2/0). 12 new unit tests. * [fastapi-guard] Phase 2: critical-path decorators Apply guard decorators to the highest-value endpoints (metadata-only; enforced only when the middleware is mounted, so no-op while ROBOCO_GUARD_ENABLED is off): - provider keys (ollama/grok/self-hosted writes): strict rate_limit + max_request_size + block_clouds (no datacenter IP should touch secret writes). - settings write + release approve/reject (CEO-gated): strict rate_limit. - intake chat (prompter start/messages/events): rate_limit + max_request_size + custom_validation(prompt_injection_validator) — the prompt-facing free-text ingress gets the injection/role-override/secret-exfil content scan. make quality GREEN (cov 95.32%, contracts 2/0). App builds with guard off, decorators inert (verified). * [fastapi-guard] Phase 3: wide decorator coverage across ingress + sensitive routes Targeted-wide application (metadata-only; no-op until ROBOCO_GUARD_ENABLED). The global SecurityMiddleware already rate-limits + WAF-scans every request, so this adds the custom content validators on free-text ingress + tight limits on sensitive ops (not blanket per-route rate_limit on reads): - agent gateway do verbs (note/say/commit/dm/pitch/progress/draft_playbook/...): rate_limit + max_request_size + custom_validation(secret_exfil or prompt_injection). - a2a message/send + chat writes: rate_limit + size + prompt_injection. - optimal/RAG (kb/search, rag/query, mentor/ask, errors/decisions/standards/ learnings): prompt_injection on searches, secret_exfil on record writes; docs index → internal_ssrf. - tasks: create/update → prompt_injection; QA/doc/PM transitions → secret_exfil; CEO-gated verbs → tight rate_limit. - secretary chat → prompt_injection; research → internal_ssrf; orchestrator spawn/mutations → rate_limit; git ops + flow verbs → tight rate_limit. Pure GET/reads left to the global middleware. Applied via a Sonnet workflow, then verified: app builds with guard off (decorators inert), make quality GREEN (cov 95.37%, contracts 2/0). Decoy/honeypot-path surface deferred (needs verified guard ban-API integration — not rushed). * [fastapi-guard] Phase 5: arm the NAS composes in passive/log-only mode Arm ROBOCO_GUARD_ENABLED=true + ROBOCO_GUARD_PASSIVE_MODE=true + ROBOCO_GUARD_FAIL_SECURE=false on the two NAS composes (docker-compose.yaml + .yml). Passive = guard mounts and logs what it WOULD block but blocks nothing, so the next NAS deploy calibrates against real traffic; flip PASSIVE_MODE off after the false-positive review to enforce. fail_secure=false keeps a guard-internal error from 500ing the personal deploy. The registry (user-facing) compose is deliberately left unarmed so its published default stays conservative. Phase 4 (passive calibration) is the operational step this enables. * feat(security): Phase 3b — full-arsenal per-route guard enrichment Stack the applicable guard decorators per surface instead of the minimal rate_limit/max_request_size/custom_validation triad: content_type_filter on every JSON-body write, honeypot_detection form-traps on human-facing POSTs, block_clouds on key-writes + CEO release ops, behavior_analysis runaway-rate rules on the agent flow/do verbs, suspicious_detection + usage_monitor on the sensitive surfaces. Nine distinct decorators now applied thoughtfully per endpoint. All metadata-only — no-op while ROBOCO_GUARD_ENABLED is off. * fix(a2a): permit PR reviewer to deliver gate verdicts to the owning PM can_a2a_direct had no pr_reviewer rule, so a reviewer (team=board, or a cell team) fell through to the cell-member path and was cross-cell-denied when the in-path gate delivered a pr_fail change-request to main-pm (or a cross-cell cell-pm): "Cannot A2A main-pm ... Ask None to coordinate with None". The delivery is best-effort, so pr_fail still transitioned but the verdict never reached the owning PM — the blind-re-submit signal-gap the pr_fail fix closes. Add an explicit pr_reviewer handler: it may A2A only cell_pm / main_pm (its sole comms surface — everything else it posts on the PR itself), with a matching route hint. The cell reviewers kept same-team access by coincidence; this scopes every reviewer to PM-only, the correct model, with no other A2A caller affected. Refresh uv.lock to the current resolution. * feat(models): adopt Claude Sonnet 5 as the sonnet tier Point the 'sonnet' alias at claude-sonnet-5 (MODEL_MAP) and give pr_reviewer its own opus tier in ROLE_MODEL_MAP — it was falling through to the sonnet default, and the role gates untrusted external/fork PRs plus root→master, which warrants opus. Price claude-sonnet-5 at the promotional 33% off Sonnet 4.6 ($2.01 / $10.05, cache 0.201 / 0.5025) through 2026-08-31 via a dedicated pricing fragment that beats the bare 'sonnet' alias; revert to full rate when the promo ends. Bare 'sonnet' stays full-rate as a conservative fallback (prod prices the resolved claude-sonnet-5 id from the transcript). Update the model docs and the billing / usage / manifest / spawn tests. * feat(security): calibrate the guard WAF for RoboCo traffic + document the layer The first end-to-end run of the fastapi-guard layer showed active enforcement would block ~50% of legitimate agent traffic — RoboCo request bodies are code, SQL, diffs, file paths, HTML, and URLs, which the stock signature WAF reads as attacks. build_security_config now excludes RoboCo's free-text top-level body fields (derived from the real request models, including the free-form container fields whose nested prose is stringified and scanned) from WAF scanning, dropping the active-mode false-positive rate to zero while keeping the WAF on every non-excluded (id/enum/slug/branch) field and leaving the prompt-injection / secret-exfil / internal-SSRF validators — which run independently of the exclusion — fully in force. enable_penetration_detection is made explicit. Only excluded_detection_body_fields is reliable on guard 7.2.1: the per-route categories knob is bypassed for JSON bodies, and the body scanner excludes top-level keys only (scanning str(value) of every non-excluded field), so free-form container fields must be excluded wholesale. Adds tests/unit/test_security_middleware.py — the first end-to-end exercise of the middleware (mounts it, drives guard's lifespan, fires real requests): proves passive mode is log-only, active mode does not false-positive on realistic agent payloads, threats are still blocked inside excluded fields, and the WAF still fires on non-excluded fields. Docs: CHANGELOG (Unreleased); a user-facing Optional-subsystems page + nav + env reference for the HTTP security layer; the agent-facing RAG corpus (what it is + why a request could be blocked); and the roboco mapping (api-core-websocket / deployment-tooling / _complete_map). * feat(security): Surface N — scanner honeytrap (guard /api auto-ban + nginx edge-drop) Turns scanner probes against the scanner, in two layers matched to where traffic lands. Behind nginx only /api, /ws, /health, /ready reach the orchestrator, so guard can only see (and ban) scanner probes on those paths; the classic root probes (/.env, /wp-login.php, /phpmyadmin, /.git/config) hit the panel. So: - build_security_config's threat_ban_config gains recon / sensitive_file / cms_probing categories. A scanner probing those fingerprints on an /api path is detected on the URL-path scan; repeated probes from one IP trip an adaptive per-IP auto-ban (redis-backed, 24h). Only bans in active mode (passive logs the recon hit) and needs redis (the 24h ban exceeds the in-memory cap). The spec's decoy-route file is redundant — the WAF url-path scan bans regardless of a registered route — so it is intentionally omitted. - docker/nginx.conf drops the classic root scanner paths at the edge with 444 (connection closed, no response) before they reach the panel, anchored to known scanner fingerprints so /.well-known and every real panel/API route are untouched. Always on, independent of ROBOCO_GUARD_ENABLED. Tests: 2 unit (the exclusion set + the scanner-ban categories are present) and 2 integration (a decoy path is blocked in active mode, passes in passive). The nginx regex was validated against 15 scanner + 19 legit paths (0 false positives). Docs: CHANGELOG, the HTTP-security page, the roboco mapping, and the agent-facing RAG corpus. * Token optimization — per-role observability, compute policy, spawn preflight (#291) * test(models): lock the sonnet→claude-sonnet-5 MODEL_MAP invariant * feat(usage): surface cache tokens + cache_hit_rate in usage breakdowns * feat(usage): add per-role usage breakdown endpoint * feat(usage): add spawn-waste signal (per-role unproductive rate + respawn strikes) * feat(panel): surface per-role cost/cache + spawn-waste on the metrics page * feat(routing): Phase 2 per-role compute policy — qa→haiku, main_pm→sonnet, per-role effort env mechanism (default-inert) * feat(orchestrator): Phase 3 flag-gated spawn preflight — refuse non-gateway delivery roles (respawn-forever guard) * chore(compose): arm ROBOCO_SPAWN_PREFLIGHT_ENABLED on the NAS composes * docs: per-role usage observability, per-role compute policy, and spawn preflight --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com> * fix(panel): pin outputFileTracingRoot so the standalone build isn't broken by stray lockfiles * feat(routing): populate ROLE_EFFORT_MAP + wire the verified --effort flag (cell_pm/board/auditor to medium) * feat(gateway): omit empty context_briefing sections (Phase 4 payload compaction) * refactor(orchestrator): extract spawn chokepoint guards to restore xenon rank B on spawn_agent --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com> |
||
|
|
a8cb2470ba |
v0.15.0: Metrics granularity — per-member / per-task / org + CEO scorecards (#289)
* feat(metrics): capture per-session turns + tool_calls (phase 1)
Persist LLM iterations (turns) and tool invocations per agent spawn session,
the raw signal the granular per-member performance metrics build on (real
effort/iterations vs wall-clock).
- sum_transcript_usage returns a 5-tuple adding turns = unique assistant
message-id count; _usage_from_transcript + _resolve_active_tokens updated to
the 5-tuple (active-tokens keeps its 4-tuple contract by slicing).
- SDK: _SessionState.turns, set by /usage/sync; /usage/status (TokenUsageStatus)
now carries turns + tool_calls (= total_calls).
- orchestrator: new _resolve_final_turns_tools (SDK primary, transcript fallback
for turns only; Grok -> 0/0) wired into _finalize_spawn_session, which writes
turns + tool_calls to agent_spawn_sessions.
- migration 055 adds turns + tool_calls (BigInteger DEFAULT 0 -> historical/Grok
rows read 0, surfaced as n/a). Verified real alembic upgrade/downgrade.
Part of metrics-granularity (v0.15.0); recon-adjusted plan on disk.
* feat(metrics): pure compute_stage_effort helper (phase 2, part 1)
Foundation-layer overlap math (no DB): split each task status window into
active (merged wall-clock overlap of spawn stints — concurrent stints counted
once, so active <= window) vs wait (queue/review idle). Distinct from summed
effort. The per-task metrics service will feed it audit-log windows + spawn
stints. 9 unit tests (disjoint/nested/partial/merged/clamped/zero/multi-window).
* feat(metrics): per-task live metrics + GET /metrics/task/{id} (phase 2)
TaskMetrics dataclass + MetricsService.get_task_metrics: summed spawn effort
(vs wall-clock), turns/tool_calls/tokens/cost, per-stage active-vs-wait
(compute_stage_effort over audit windows x spawn stints), and who-caused-rework
(revision_count + named qa/pr fail events). Open stints and the open final
stage window close at completed_at for a terminal task (else now), so stages
don't grow past completion. Exposed at GET /dashboard/metrics/task/{task_id}
(404 if absent). Real-PG tests (compose/none/in-flight) + route tests (200/404).
* feat(metrics): CEO-as-member scorecard + ceo_reject audit regression (phase 3)
The human CEO is a measured member, read purely from audit_log (agent_role='ceo'
serializes from the CEO StrEnum): approval dwell (awaiting_ceo_approval -> a CEO
decision, incl. the coordination-root reject that lands in pending), unblock
dwell (blocked -> a CEO revive), and god-mode action count (every CEO-attributed
transition). CeoScorecard + MetricsService.get_ceo_scorecard (p50/p90 via
PERCENTILE_CONT, expanding IN for the decision sets) + GET
/dashboard/metrics/member/ceo (declared before any future member/{id} route).
The ceo_reject coordination-root audit gap the plan meant to close was already
closed by the gap-sweep (routes through admin_set_status -> agent_role='ceo'
audit); locked with a regression assertion in the existing coordination-reject
test. Real-PG tests: approval/unblock/godmode, non-ceo exclusion, empty->zeros.
* feat(metrics): audit instrumentation for escalations/blocked-others/idle (phase 4a)
The three extra per-member metrics that had no data source get durable,
in-session audit events (additive; never gate the underlying action):
- apply_escalation -> task.escalated (details.escalator_slug) on both the
normal block path and the pool-divert path -> escalations count.
- _unblock_dependents -> task.unblocked_dependents (details.count) on the
completed BLOCKER task, captured before the dependency edges are pruned ->
blocked-others count (sweeper attributes to the blocker's owner).
- mark_agent_idle -> agent.idle (details.agent_slug) -> idle/utilization (the
sweeper pairs an idle mark to the member's next spawn for idle duration).
(QA pass-rate needs no new event — reuses task.awaiting_documentation[qa] +
task.qa_fail.) Real-PG tests for each; 111 transition tests still green.
* feat(metrics): member_performance_daily rollup table + migration 056 (phase 4b)
The per-member scorecard rollup: one row per (date, member_kind, agent_slug),
CEO as a first-class member_kind='ceo' row (agent_slug='' NOT NULL so the
NULL-distinct UNIQUE keeps it unique). Full column set + the four CEO-approved
extras (qa_reviews_total/passed, escalations, blocked_others, idle_seconds) plus
blocked_seconds. Overwrite-upsert on (date, member_kind, agent_slug) for an
idempotent sweep. Migration 056 verified real up/down (24 cols, 4 indexes).
* feat(metrics): _sweep_member_performance rollup sweeper (phase 4c)
The daily per-member rollup sweep (mirrors _sweep_daily_rollup): a trailing
7-day, idempotent overwrite-upsert wired into _run_sweep. One focused query per
metric merges into a (date, agent_slug) accumulator — spawn effort/turns/tokens/
cost, completed/first-pass/revisions-received, revisions-caused (qa/pr fails),
QA pass-rate (passed + total), escalations (by escalator_slug), blocked-others
(unblocked_dependents by blocker owner), idle_seconds (idle mark -> next spawn),
blocked_seconds (blocked dwell) — plus one CEO row/day (approval/unblock dwell +
god-mode). Real-PG test asserts every facet + idempotency (a 2nd sweep
overwrites, never doubles); spawn-day != completion-day split is by-design.
* feat(metrics): member/org rollup scorecards + endpoints + live overlay (phase 5)
MemberScorecard + OrgScorecard with derived rates (FPY, effort-throughput,
turns/tool-calls per task, QA pass-rate, utilization) — all division-guarded to
None. get_member_scorecard reads member_performance_daily by slug and overlays
the member's live in-flight (non-terminal) tasks' effort via get_task_metrics
(disjoint by status: completion counts stay rollup-only, overlay only enriches
effort/turns/cost; includes_live_inflight flags it). get_org_scorecard
aggregates the cell (?team=) or whole org. Routes: GET /metrics/member/{agent_id}
(404 if absent, after the ceo literal route) + GET /metrics/org?team=. Real-PG
tests (derived rates, overlay no double-count, guards, org) + route tests.
* feat(metrics): granular CEO completion notification (phase 6)
There was no CEO completion notification at all (EventType.TASK_COMPLETED was
defined but never emitted). Add notify_ceo_of_completion in
NotificationDeliveryService — a granular body (real effort vs wall-clock +
stints/turns/tool-calls/revisions[QA/PR]/cost from get_task_metrics; degrades to
wall-clock-only, turns 'n/a', when there are no spawn sessions). Reuses the
existing ALERT type (no enum migration; the notificationtype PG enum is fixed at
001). ceo_approve now emits TASK_COMPLETED + fires the notification (best-effort
via _notify_completion — never blocks completion); complete() emits
TASK_COMPLETED too (closes the dead-code gap; the WS bridge can forward it).
Pure formatter tests + real-PG notification test.
* [metrics-granularity] Phase 7: panel Scorecards tab + dashboard overview
Add the CEO-facing metrics surfaces for the granularity feature:
- New "Scorecards" tab on the Metrics page: org rollup headline, the
CEO-as-member card (approval/unblock dwell + god-mode count), and a
per-member table (completed, first-pass yield, active effort, turns/task,
QA pass-rate, escalations, blocked-others, utilization). Each member row
self-fetches its rollup scorecard; live in-flight rows carry a "live" badge.
- New dashboard overview card (ScorecardOverviewPanel): org-wide 30-day
headline (completed, FPY, throughput/hr, active effort, cost) deep-linking
into the Scorecards tab.
- Plumbing: TaskMetrics/MemberScorecard/OrgScorecard/CeoScorecard types,
observability API client methods + empty fallbacks, and the four
useCeoScorecard/useMemberScorecard/useOrgScorecard/useTaskMetrics hooks.
Panel gate green: tsc, eslint, prettier, vitest (175 tests, +6 new).
* [metrics-granularity] test: make completion-notification robust to shared-DB CEO
test_notify_ceo_of_completion_creates_alert errored in the full suite (passed
in isolation): the session-scoped test DB is shared across the run, and the
sibling real-DB board-gate test commits a role=CEO agent (slug="ceo") without
cleanup — so my env fixture's hardcoded slug="ceo" insert hit a unique-constraint
violation, and a second role=CEO row would also make _get_ceo_agent()'s
scalar_one_or_none() raise. Reuse an existing CEO when present (the singleton the
production system actually has), else create one with a unique slug. Order-
independent. Also reflow test_metrics_instrumentation.py to ruff format.
* chore(release): 0.15.0
Metrics granularity: per-member/per-task/org + CEO-as-member scorecards,
turn/tool-call capture (migration 055), member_performance_daily rollup
(migration 056) with QA pass-rate / escalations / blocked-others / utilization,
per-task active-vs-wait metrics, granular completion notification, panel
Scorecards tab + dashboard Performance card, and the ceo_reject audit fix.
Version bump across the canonical set + CHANGELOG.
* [metrics-granularity] fix pre-tag audit findings (overlay double-count + panel error states)
Adversarial review before the v0.15.0 tag surfaced two real logical gaps:
- MAJOR (backend): the live in-flight overlay re-summed ALL sessions of every
non-terminal task via get_task_metrics, but _msweep_spawn already rolls up
every CLOSED session regardless of task status — so a closed session on a
still-open task was counted twice (rollup + overlay), permanently inflating a
member's effort/turns/tokens/cost on the common reap/respawn path. The overlay
now sums only OPEN sessions (ended_at IS NULL), which the closed-only rollup
can never contain — disjoint by construction. A just-closed session lands in
the rollup on the next ~60s sweep (no gap of note). Aggregated in SQL to mirror
_msweep_spawn. Regression test reproduces the double-count (turns 10→5).
- MAJOR (panel): the four new scorecard surfaces used `isLoading || !data` with
no isError branch, so a failed query span forever on a skeleton. They now
surface a load error. Tests added.
Also: OrgSummary active-effort formatting no longer round-trips hours→seconds→
hours; dashboard grid uses xl:grid-cols-4 (was 2xl) so 4 panels show at 1280px;
corrected the inaccurate "NULL distinct" CEO-row uniqueness comment (agent_slug
is NOT NULL; the '' tuple is simply distinct from agent rows).
make quality GREEN (cov 95.31%); panel GREEN (vitest 178).
* [metrics-granularity] fix: decode bytes stream message-id before XCLAIM
StreamEventBus._recover_stream passed the pending message id to XCLAIM via
str() on the raw bytes the client returns (redis client has no
decode_responses), producing "b'1782066556728-0'". Redis rejects that with
"Unrecognized XCLAIM option", so pending-message recovery threw on every
reclaim tick and unacked messages from crashed/slow consumers were never
reclaimed (leaking in the PEL on every stream, spamming the error log). Decode
via the existing _to_str helper — the fix the sibling claim path already uses.
Pre-existing in v0.14.0 (unrelated to metrics granularity); folded into this
release per CEO. TDD regression test + CHANGELOG entry. make quality GREEN.
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
|
||
|
|
15effce014 |
Chore: 141 Gaps fill-in (#283)
* Updated uv.lock
* Bunch of fixes we need to verify first..
* feat(megatask): per-cell project map root-subtasks (multi-project, multi-cell)
A MegaTask root-subtask can now target an ad-hoc per-cell project map — a
third targeting shape that mirrors the existing product fan-out root. In
RoboCo a project is per-cell (ProjectTable.assigned_cell); a monorepo is N
per-cell projects sharing one git_url. So 'multi-cell' IS 'multi-project',
and a task may mix per-cell projects across products or include OSS-library
projects not in any product.
Storage: migration 052 adds task_cell_projects (mirrors product_projects;
unique per (task, team)). TaskTable gains a cascade-delete cell_projects
relationship; TaskCreateRequest / TaskCreate / Task response carry the map.
Policy: batch.is_branchless_coordination + is_valid_batch_shape gain a
has_cell_projects param — a root-subtask targets exactly one of project /
product / cell-map; the umbrella still targets none. TaskService passes
has_cell_projects at every predicate call site and persists the rows in
create(). _ensure_branch_for_task cuts feature/main_pm/{root} per distinct
project in the map (via _distinct_projects_for_task); _require_target_or_umbrella
and _validate_batch_membership accept the map shape.
Fan-out: every distinct_project_ids site (task.py branch creation, routes
_project_for_complete + _resolve_project_for_merge, orchestrator
_ambient_projects_for_task, pr_review._project_slug_for, git._project_for_task)
generalizes to first-distinct-project-of-map-or-product. Choreographer
_resolve_subtask_project resolves a delegated subtask's cell from the parent's
cell map. The product-scoped _slugs_for_product intake helper is unchanged.
Intake: prompter._draft_cell_map extracts the per-cell map from the_work[].
_validate_batch_scope counts distinct projects across all drafts' cells
(>=2 min stays; one 2-cell draft satisfies it). create_task_from_draft
persists cell_projects for >=2-cell drafts (project_id/product_id None),
collapses a 1-cell map to the single-project shape, and leaves single-cell
top-level project_id drafts unchanged. _resolve_owning_team routes a
multi-cell map to Main PM (coordination root, like a product root — a cell
PM can't delegate cross-cell). propose_draft/propose_batch tool descriptions
declare the per-cell project_id (both Claude SDK + grok runtimes).
The umbrella stays branchless / pure-coordination / submit_root-rejected;
the CEO-escalation pr_number gate is not widened (the map root is
is_umbrella=False, mirroring a product root, so submit_root supplies it).
Single-cell root-subtasks and everything below them are byte-for-byte
unchanged. Un-run MegaTask waves (multi-cell drafts) become runnable.
* [feature] Panel per-cell project picker + pnpm format infra
MegaTask root-subtasks can fan out across cells (be+fe, fe+uxui). Since a
RoboCo project is per-cell (ProjectTable.assigned_cell), a monorepo is N
per-cell projects sharing one git_url — so multi-cell IS multi-project. The
batch-review card now shows one project Select per the_work entry, scoped to
that cell's repos, instead of one Select bound to a single top-level
project_id. confirmBatch validates each cell's project is in scope and the
batch still spans >=2 distinct projects.
- prompter.ts: CellWork gains optional project_id (the per-cell picker seam).
- batch-review-card.tsx: per-cell Selects (one per the_work entry), scoped to
the cell's projects; legacy single-cell drafts keep the one-Select path.
- use-prompter.ts: updateBatchDraftProject edits per-cell (entryIndex); confirmBatch validates every cell; batchFromEvent parses per-cell map.
Also adds the missing pnpm format infrastructure (the panel had no formatter
at all): prettier devDep + .prettierrc.json (default-style config: 80-col,
double-quote, semi, trailing-comma-all) + .prettierignore, plus format /
format:check scripts. Only the 3 changed files above were reformatted; the
~222 pre-existing non-compliant files are left untouched (a wholesale reformat
is a separate explicit decision, not bundled into this feature).
* [fix] MegaTask verification: migration 052 enum + async cell-map read
Two real bugs surfaced running the full gate against a containerized
Postgres (and the orchestrator boot log):
1. Migration 052 crashed a real orchestrator boot with
'type "team" already exists'. The generic sa.Enum(create_type=False)
does NOT set the postgres enum's create_type attribute, so op.create_table
(checkfirst=False) emitted a redundant CREATE TYPE against the pre-existing
team enum. Switched to postgresql.ENUM(create_type=False) — the postgres-
native enum whose create_type _check_for_name_in_memos actually reads, so
the CREATE TYPE is suppressed. Verified: 051->052 upgrade against a DB where
the team enum pre-existed (the exact path that crashed) now succeeds;
downgrade 052->051 drops the table and preserves the shared enum; fresh
upgrade head clean. (Migration 016 has the same latent sa.Enum pattern but
never re-runs in prod, so it's noted, not touched here.)
2. _ensure_branch_for_task read task.cell_projects (lazy=selectin to-many)
directly, tripping MissingGreenlet on a freshly-created/unqueried task —
which then poisoned the async session (PendingRollbackError). Replaced with
_task_has_cell_map: peeks InstanceState.unloaded (no IO) and reads the
already-loaded map, falling back to an awaited count query only when the
relationship is genuinely unloaded. Non-ORM stubs route to the plain
attribute. Fixes 2 integration tests; the 6 cell-map unit tests still pass.
Also: typed the self stub as Any in test_choreographer_subtask_project
(mypy tests/ wants Choreographer, not SimpleNamespace) — the codebase idiom.
Gate: ruff format/check clean; mypy roboco/ + tests/ clean; full pytest
10371 passed / 388 skipped against containerized pgvector:pg16; vulture clean.
Pre-existing xenon C-rank on reassign (from prior commit
|
||
|
|
5612375cba |
Feat/v0.13.0 (#270)
* feat(release): add release-manager feature flag (default off) * feat(release): change classification + semver-bump derivation * feat(release): readiness audit (changelog/version-ref/docs/migration/gate) * feat(release): release-manager engine proposes a gated release * feat(release): fail-closed release executor (bump, gate, publish) * feat(release): CEO approve/reject release-proposal surface * docs(release): document the gated release manager * feat(memory): add org-memory feature flags (default off) * feat(memory): add playbooks table + status enum + migration * feat(memory): playbook service with auditor curation transitions * feat(memory): playbooks RAG index plugin * feat(memory): index a playbook into RAG on approval * feat(memory): distill a high-signal lesson at task completion * feat(memory): keep private journal reflections out of the shared RAG corpus * feat(memory): draft_playbook verb + auditor curation verbs * fix(ci): resolve mypy tests/ errors blocking the gate (UUID casts, annotations) * feat(memory): auto-inject similar lessons/playbooks into the briefing * feat(memory): auditor playbook review queue (api + panel) * docs(memory): document the org-memory loop + playbook verbs * fix(provisioning): idempotent pitch provisioning (reuse product/project by slug on re-approval) * fix(memory): add chunks_playbooks to the chunk schema + isolate release route tests - Migration 030's CHUNK_TABLES was missing chunks_playbooks, breaking the IndexType<->migration parity guard once the PLAYBOOKS index landed. The upgrade is ALTER ... IF EXISTS so adding it is safe on any DB shape. - The release-route fixture's approve/reject paths call db.commit() (real behavior), so a held proposal outlived the per-test rollback and leaked into engine tests that read the global list_open_release_proposals(). Tear down source=release_manager rows after each test. - Make the gather_snapshot real-repo smoke version-agnostic (semver match) so it stops pinning the literal repo version. * chore(release): 0.13.0 * ++ --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com> |
||
|
|
153723406e |
Feat/autonomous maintenance (#264)
* feat(ci-watch): config flags Default-off CI-watch config (mirrors self_heal_*): ci_watch_enabled, ci_watch_default_workflow (ci.yml), ci_watch_interval_seconds (1800), ci_watch_max_open_tasks (3), ci_watch_max_per_cycle (1). Registers ci_watch_enabled in the panel FEATURE_FLAGS. 4 tests. * feat(ci-watch): per-project ci_watch_enabled/workflow (migration 048) Adds projects.ci_watch_enabled (bool NOT NULL default false) + projects.ci_watch_workflow (varchar null) — the per-project opt-in for multi-repo CI-watch. ProjectTable + Pydantic Project fields + migration 048 (off 047_ws_single_active). Real upgrade->downgrade->upgrade chain verified against a throwaway Postgres; 2 ORM round-trip tests. * feat(runtime): prune dangling agent images in the background sweeper Every agent-image rebuild orphans the prior build's layers as an untagged <none> image; across deploys these pile up (the operator hit ~80). The sweeper now runs 'docker image prune -f --filter dangling=true' (dangling only — a tagged image or one backing a running container is never dangling), throttled to settings.image_prune_interval_seconds (default 6h) and gated by image_prune_enabled (default on). Best-effort: any failure is logged, never raised into the sweeper. Mirrors the transcript-retention prune. 4 tests. * feat(ci-watch): source tag + open-task dedupe query CI_WATCH_SOURCE='ci_watch' + TaskService.list_open_ci_watch_tasks(git_url=None): non-terminal ci_watch tasks (the dedupe + open-cap basis), optionally scoped to one repo by git_url — a monorepo registers several cell-projects on one git_url, so dedupe keys on the repo, not the slug. 2 real-PG tests. * feat(ci-watch): multi-project CI telemetry fan-out MultiProjectCITelemetrySource.fetch(projects) reuses the hardened per-project get_latest_ci_conclusion for each opted-in project (passing its ci_watch_workflow or the configured default). Per-project isolation: a GitHub error or absent signal yields NO sample (unknown, never read as green) and never aborts the sweep; only a real conclusion yields a sample (fail→breach, pass→non-breach). self-heal source untouched. 3 tests + self-heal regression green. * feat(ci-watch): engine — fan-out, originate, dedupe, cap CiWatchEngine.run_cycle(projects) mirrors SelfHealEngine: assess via MultiProjectCITelemetrySource, open one PENDING ci_watch fix task per red repo (team=main_pm, assigned_to=main-pm, confirmed_by_human=True so it dispatches without an Approve-&-Start — the |
||
|
Renn F
|
9702955f0c |
chore(release): 0.11.1
Patch release bundling the post-0.11.0 run-hardening + PR-gate fixes: - PMs can re-claim needs_revision coordination roots (runtime/spec claim parity) - finished merges don't respawn-loop when the target branch is gone from origin - no phantom re-delegation from text-vs-id acceptance-criteria ref mismatch - PRECONDITION_OWNERSHIP surfaces as not_authorized, not a tracing gap - the spawn gate suppresses respawns for every parked provider, not just Grok - the Claude session limit is detected from the agent transcript so the park fires - the in-path PR-review gate lands its verdict on product-scoped (root->master) PRs - the gate persists its verdict to notes_structured.pr_review (no stale "passed") Bumps all canonical version refs (pyproject / uv.lock / panel package.json / __init__ / config.app_version + README / deployment / agent-image-tag examples). |
||
|
|
fe6c8e387f |
docs: sync prompts/RAG/CLAUDE + bump to 0.11.0 (run-hardening wave) (#254)
* docs: sync prompts/RAG/CLAUDE + bump to 0.11.0 for the run-hardening wave
Documentation + version sweep for everything shipped since
|
||
|
|
c09cf80b40 |
Feature/observability gateway health (#247)
* feat(observability): revision_count + audit_log query index (migration 045)
Adds tasks.revision_count (the O(1) rework counter — forward-only, existing
rows default 0) and the composite index audit_log(target_id, event_type,
timestamp) that powers the cycle-time and rework reconstruction queries.
Verified the real upgrade/downgrade/upgrade chain on a throwaway pgvector PG.
First task of the 0.10.0 observability dashboards.
* feat(observability): count reworks + attribute qa_fail/pr_fail to the rejector
Every transition into needs_revision increments tasks.revision_count at the
single audit chokepoint (exactly once per bounce, across all paths incl. pr_fail
and ceo_reject), so the rework rate is an O(1) read. A QA or PR-review bounce
also emits a named task.qa_fail / task.pr_fail audit event carrying the
rejector's agent_id, so the per-agent rework scorecard charges the rejection to
the reviewer who made it, not the developer who owns the task.
* feat(observability): cycle-time, bottleneck, rework, and scorecard metrics
MetricsService gains four read methods on the audit_log + tasks data: per-stage
cycle time reconstructed from the transition journey (excluding the named
qa_fail/pr_fail events), bottleneck distribution (cumulative dwell + live parked
counts), rework rate (overall/by-team/by-agent with rejector attribution + cost
via spawn-session task_id), and a fused per-agent/per-cell scorecard. Dataclass
models with to_dict(). Verified against a real Postgres journey.
* feat(observability): cycle-time/bottleneck/rework/scorecard read endpoints
Thin read-only routes on the dashboard router delegating to MetricsService:
/metrics/cycle-time, /metrics/bottlenecks, /metrics/rework, and
/metrics/scorecard/{agent,team}. 404 when an agent scorecard target is absent.
5 route tests (200 + shape + the agent-404 case).
* feat(panel): Delivery observability tab (cycle-time, bottlenecks, rework, scorecards)
A third Metrics tab built on the observability endpoints: a per-stage
cycle-time bar chart, a bottleneck panel (worst stage + cumulative dwell +
live parked counts), a rework panel (rate + by-team + by-agent attribution +
cost), and per-cell scorecards. Reuses Recharts + Card/Badge/Skeleton and the
React-Query hook pattern; observabilityApi mirrors usageApi with mock-mode
fallbacks. tsc + eslint clean; 113 panel tests pass.
* docs(observability): changelog + CLAUDE.md for the delivery dashboards
* feat(gateway-health): recover a broken-but-alive agent instead of protecting it
The verb-heartbeat cannot tell a quiet-healthy agent from one whose MCP gateway
is broken (a corrupted /app/.venv firing no verb) yet whose container is up — the
reaper's live-skip would shield it forever. The reaper now probes the gateway
out-of-band (docker exec: does the gateway venv import its deps?) and, once it
has been broken past gateway_health_grace_seconds (tolerating a transient probe
miss), kills + evicts the container so it falls through to release + respawn.
Probe-inconclusive or healthy spares the container. Gated by
gateway_health_enabled (default-on reliability fix; in the panel Feature Flags).
Defers the optional agent-side self-check + full registry re-adoption — the
reaper's docker-liveness fallback already recovers a broken-after-restart agent.
* docs(gateway-health): changelog + CLAUDE.md for broken-but-alive recovery
* docs(observability): user-facing docs for the Delivery dashboards + gateway-health
Documents the new Metrics -> Delivery tab (cycle-time, bottlenecks, rework with
rejector attribution, cell scorecards) in the panel guide and the operations
health-and-metrics guide, and adds the gateway-health env vars + an agent-gateway
recovery note. Published MkDocs site only; settings.md's default-off flag table
intentionally omits the default-on gateway-health flag (same as overload-break).
* chore(release): cut 0.10.0 (changelog section + version refs)
* fix(gateway): exempt PM coordinators from single-task claim guards
A Main/Cell PM plans and delegates many root tasks in parallel; the work
then runs in the delegated cells, not in the PM's own hands. But the
claim-time concurrency guards meant for developers — already_active and
paused (the latter firing after i_am_idle auto-pauses the PM's own
umbrella) — were applied to the PM too, so once it held one root it could
never plan a second: it thrashed between its claimed roots and respawned
forever, burning tokens for zero progress.
_run_claim_guards now skips already_active/paused for the coordinator PM
roles (_COORDINATOR_ROLES = {main_pm, cell_pm}); only unmet_dependency — a
real upstream sequence constraint, which parks the root back to pending —
still gates a PM. paused_tasks_guard also excludes the target task itself,
so a PM re-entering its own paused umbrella never self-blocks.
Tests: a coordinator plans a second root with one in_progress + one paused
sibling (full path + claimed-recovery path), the paused target exclusion,
and the developer guards still fire. Repurposed the pre-fix test that
asserted the now-removed PM block.
* fix(metrics): coerce SQL avg/extract hours aggregates to float (panel toFixed crash)
EXTRACT(epoch ...) returns numeric on PostgreSQL 14+, which asyncpg surfaces
as a Decimal; a Decimal serializes to a quoted JSON string, so the panel's
avg_cycle_hours.toFixed(1) (and the other hours fields) threw 'toFixed is not
a function' and blanked the Delivery tab.
A single _as_hours helper now rounds every SQL-averaged hours field to a real
float — avg_cycle_hours on the new scorecards plus the pre-existing
avg_completion_hours / avg_blocked_hours / longest_blocked_hours. Token and
cost fields were already float()-cast and are unaffected.
Regression test asserts _as_hours coerces Decimal -> float and preserves the
None/zero behavior.
* feat(panel): edit a task's sequence from the details page
A task's sequence (order within siblings, lower runs first) was display-only
with no way to change it from the UI, and TaskUpdate didn't carry the field
so PATCH couldn't set it either. The details page's Dependencies tab now has
an inline sequence editor mirroring the parent / dependency editors, and
PATCH /tasks/{id} accepts a sequence field (owner or privileged role) through
the existing generic update path.
* fix(mypy): green the full make-quality type gate
make quality runs 'mypy roboco/ tests/', which the per-module checks on the
0.10.0 branch never exercised. Two issues surfaced:
- The coordinator-exemption change added role_str to
Choreographer._run_claim_guards but not to the ChoreographerHelpers
protocol base, so the composed Choreographer had incompatible base-class
signatures. Sync the protocol signature.
- The gateway-health / stale-reaper tests stubbed methods by direct
assignment (orch._m = AsyncMock()) and typed their duck-typed task doubles
as object, tripping method-assign / assignment / attr-defined. Switch to
monkeypatch.setattr (keeping a local mock ref for the assertions) and type
the doubles as Any — no type: ignore.
Full mypy roboco/ tests/ clean (785 files); the 21 runtime tests pass.
* fix(metrics): static cycle-time SQL — clear bandit B608 (CI gate)
The cycle-time query interpolated an optional team clause into the text() SQL
via an f-string, which bandit flags as B608 (hardcoded SQL) and turned the
merge gate red. The team value was always a bound parameter, so it was a false
positive — but the f-string is the trigger. Rebuilt as one static query with
(CAST(:team AS text) IS NULL OR a.details->>'team' = :team) and an always-bound
team param (CAST, not ::text — SQLAlchemy's :param parser collides with
PostgreSQL's :: cast operator, which broke the query as a stray param).
Full make quality green vs a real pgvector PG (all 21 gate steps).
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
|
||
|
Renn F
|
6456322746 |
chore: bump version to 0.9.0
Bump the canonical version refs (pyproject, roboco.__init__, config.app_version, panel/package.json, uv.lock) plus the version-pin examples in the docs. The release tag + CHANGELOG date are deferred to the actual 0.9.0 cut. |
||
|
Renn F
|
2fb63fed1f |
docs: add the user-facing MkDocs documentation site
Build a complete user-facing documentation site (MkDocs Material) under docs/, served at roboco.dev/docs via a new gh-pages deploy workflow. - Sections: Get Started, The Company, the Tour, Operating the Panel, Choosing & Running Models, Cost & Observability, Optional Subsystems, Configure & Deploy, API Reference, Troubleshooting & Security (55 pages). - mkdocs.yml (Material theme; excludes the agent-facing rag/ corpus, internal scratch, and orphaned stub trees) and .github/workflows/docs.yml (mkdocs gh-deploy to gh-pages). - Retire the stale root usage.md and deployment.md to redirect stubs into the site. - Fix the docs tooling: add the pymarkdownlnt dependency + .pymarkdown.json, run serve-docs/lint-docs/fix-docs under the docs extra, add a build-docs strict gate. - Fix the roboco console-script entry point (cli, not the un-awaited async main). - README: correct the project-structure tree (optimal.py, alembic) and link the docs site. |
||
|
Renn F
|
c49dcebae4 |
fix(toolchain): raise requires-python floor to 3.13 so the resolver matches the runtime
RoboCo's code imports tomllib (3.11+) and the stack runs on 3.13, but requires-python declared >=3.10. The toolchain resolver picks the lowest satisfying version, so it provisioned agent workspaces of the self-hosted roboco-api project at Python 3.10 — an interpreter the suite cannot even be collected under, leaving the workspace .venv unusable and the gate running in an ad-hoc fallback env. Raising the floor to >=3.13 makes resolve_target_python return 3.13, matching the agent image. Re-locks to drop the now-unreachable 3.10-3.12 backports; a guard test pins the repo's own resolution to 3.13. |
||
|
|
16789c1ca7 |
Feature/architectural conventions standard (#243)
* feat(conventions): standard schema models + effective-map merge * feat(conventions): tree-sitter Python classifier + placement checks * feat(conventions): TS classifier, hygiene/custom checks, runner + CLI * feat(conventions): ROBOCO_CONVENTIONS_ENABLED flag + cache table + migration * feat(conventions): repo auto-scan + scaffold draft renderer * feat(conventions): ConventionsService (cache/baseline/ambient/scaffold/restore) * feat(conventions): auto-scaffold on project registration (flag-gated) * feat(conventions): TaskDescription.constraints + auto-baseline attach * feat(conventions): ambient architecture-map injection at spawn * test(conventions): subprocess CLI smoke for the agent-image entrypoint * feat(conventions): block i_am_done on block-level convention violations * feat(conventions): block pr_pass on unresolved convention violations * feat(conventions): surface convention findings into QA evidence * docs(prompts): convention awareness for PO/Intake/Dev/QA/PR-reviewer * feat(conventions): panel Conventions tab + flag toggle + parity * test(conventions): end-to-end block, fix, and waiver through the gate * refactor(conventions): extract pr_pass guards to keep pr_gate under the gate * style(conventions): format the baseline-constraints attach in task.create * test(conventions): type-annotate test helpers for the full mypy gate * build(conventions): ignore types-PyYAML in deptry (mypy-only type stub) * docs(conventions): document the standard in CLAUDE.md + PM prompt awareness * fix(conventions): baseline constraints are non-suppressible (dedup-append) * feat(conventions): scaffold on first workspace clone (threaded workspace) * feat(conventions): multi-project ambient map for PO/Intake (per-product) * feat(conventions): persist findings + violations-feed route (migration 044) * feat(conventions): panel violations feed in the Conventions tab * test(conventions): intake-spawn mock accepts the ambient layer kwarg * fix(docker): ollama-init best-effort pull, gate startup on cached models present A degraded/slow ollama registry made the model manifest re-check fail under set -e, so ollama-init exited 1 and blocked the orchestrator's service_completed_successfully gate — taking the whole stack down even though both models were already cached. Pulls are now best-effort; success is gated on the models being present, so a flaky registry can't down a cached deployment. * refactor(content): drop dead TaskDescription.with_baseline_constraints The structured baseline-merge helper had zero production callers. Project-task baseline constraints are attached by the wired string backstop (TaskService._attach_baseline_constraints), and a real task is free-form prose that cannot form a valid TaskDescription (requires a non-trivial objective + non-empty the_work), so the helper was unreachable from any live path — a leftover from the structured-merge -> string-append design pivot. Removing it leaves a single enforcement path. The constraints field itself stays: it is a member of the well-formed-spec schema (Objective / What This Builds / The Work / Notes / Constraints / Acceptance Criteria), rendered by render_markdown and unit-tested. --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com> |
||
|
|
01e10ad693 |
Feat/provider overload break (#242)
* feat(conventions): standard schema models + effective-map merge * feat(orchestrator): park provider on persistent server overload (529/500) A 429 rate limit already parks a provider — queue its spawns, probe until it recovers — but a persistent 529/500/503 overload had no such break: the run died and the orchestrator crash-retried straight back into the overload, burning tokens in a respawn loop. Generalize the park to provider-unavailability. On a non-graceful Anthropic agent exit, match the API's overload markers (overloaded_error / internal_server_error / "API Error: 5xx") against the dead container's own output and park the provider with kind="overloaded"; the existing spawn gate already queues any parked provider, and the probe-resume loop revives the task when it recovers. Grok keeps its exit-75 path; both now route through one _park_provider_unavailable helper. Markers are kept specific so an agent that merely writes about HTTP 500/529 can't trip the break. Fix the recovery probe to require a 2xx: it treated any non-429 as recovered, so a probe that itself got a 529 would have resumed agents straight back into the overload — wrong for the new path and for a 429 that lifts into a 5xx. Gated by ROBOCO_OVERLOAD_BREAK_ENABLED (default on; off => crash-retry). --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com> |
||
|
Renn F
|
9274cd4584 |
feat(toolchain): resolve target interpreter from requires-python
Pure resolver (services/toolchain.py) that derives the Python version an agent should provision a target workspace with. Defends against uv's resolution order — a .python-version file overrides requires-python during interpreter selection — by honoring the pin only when it satisfies requires-python, else resolving a concrete version from requires-python for the caller to pass via --python. This is the root cause behind the live guard-core-app failure (pin 3.13 vs packages needing 3.14). Promotes packaging to a direct dependency. |
||
|
Renn F
|
818333f626 | chore(release): 0.8.0 | ||
|
|
028b49161b |
[6d7fb817] chore(deps): upgrade pydantic-settings from 2.14.1 to 2.14.2 to fix GHSA-4xgf-cpjx-pc3j (#238) (#240) (#241)
- Add pydantic-settings>=2.14.2 constraint in pyproject.toml - Regenerate uv.lock: pydantic_settings-2.14.1 -> pydantic_settings-2.14.2 - Fix pre-existing xenon CC=12 in _fetch_latest_ci_run (self-heal CI signal commit introduced the complexity): extract HTTP retry loop into _get_ci_runs_response helper, bringing both methods to rank B All acceptance criteria verified: uv.lock shows 2.14.2, pip-audit --ignore-vuln CVE-2025-3000 exits 0 with no GHSA-4xgf-cpjx-pc3j mention, make gate (ruff/mypy/xenon) exits 0, no GHSA suppression in Makefile or pyproject.toml. Co-authored-by: Backend Developer 1 <be-dev-1@agents.roboco.dev> |
||
|
Renn F
|
fb2b14e931 | Updated uv.lock | ||
|
Renn F
|
01e082ff63 |
chore(release): 0.7.0
Roll up everything since 0.6.0 into the 0.7.0 CHANGELOG and bump the version (pyproject / __init__ / config.app_version). Rewrite the stale Unreleased Grok entry — which described the now-deleted opencode runtime — to the shipped reality: Grok agents on xAI's official grok CLI on a SuperGrok subscription, plus the token auto-refresh, the self-healing CI loop, the Company Scorecard, and the pr-reviewer / observability / usage / path-injection fixes. Also folds the uv.lock claude-agent-sdk spec sync (>=0.2.105) merged via #216. |
||
|
|
fa3e25e656 |
feat(grok): pluggable agent providers + Grok on the official grok CLI (#218)
* feat(providers): pluggable agent providers + Grok (xAI) backend
Add a roboco/llm/providers/ seam — an AgentProvider lifecycle ABC and a
ProviderRegistry keyed by ModelProvider — so the orchestrator can drive
agent backends other than Claude Code.
The first non-Claude backend is GrokProvider for xAI's grok-build-0.1.
xAI is OpenAI-compatible only (no Anthropic-Messages endpoint), so a Grok
agent runs an OpenAI-protocol runtime pointed at https://api.x.ai/v1
rather than the ANTHROPIC_BASE_URL injection the other providers use. It
reuses the orchestrator's existing mount/auth assembly, so it inherits the
same MCP gateway + tool-manifest wiring as every other agent by
construction, and passes its prompt via env (never an argv positional).
The change is purely additive: only GROK routes through the registry;
Anthropic / Ollama Cloud / self-hosted spawns run the existing
_spawn_container path unchanged.
Includes:
- ModelProvider.GROK (migration 038) + a seeded Grok provider row
(migration 039) + a grok-build-0.1 catalog entry
- GET/PUT /api/providers/grok-key to store the xAI key (Fernet-encrypted,
reusing the existing provider-key machinery)
- ClaudeCodeProvider reference adapter over the current spawn
- unit tests for the registry, GrokProvider (gateway wiring, no
ANTHROPIC_* leak, prompt-injection safety, failure paths) and routing
The dedicated roboco-agent-grok image and the exact OpenAI-protocol CLI
invocation are the remaining piece to finalise with xAI.
* feat(providers): native Grok runtime — opencode image, config gen, panel key
Complete the native Grok (xAI) path so grok-build-0.1 runs as a real
RoboCo agent, not just the provider seam.
- roboco-agent-grok image (docker/agent-grok.Dockerfile): FROM agent-base
+ opencode (the OpenAI-protocol runtime). One image serves every role;
role behaviour comes from the mounted manifest / mcp-config / system
prompt, exactly as on the Claude path.
- Entrypoint renders opencode.json at spawn from the GrokProvider env
contract + the mounted Claude Code mcp-config.json
(roboco.llm.providers.opencode_config): translates RoboCo's gateway
servers (roboco-flow / roboco-do / ...) into opencode's mcp block,
declares the xAI OpenAI-compatible provider + model, and wires
permissions + instructions. Pure, unit-tested translation.
- Orchestrator registers GrokProvider with the registry-qualified image
(_qualify_agent_image) so it resolves in local and registry deploys.
- Compose (both files + the registry compose) gain an agent-grok-image
builder service.
- Panel: a Grok (xAI) API key card on the AI Providers page, plus the
grok ModelProvider value.
KNOWN PARITY GAP (opencode runtime): the bash-guard PAT-scrub and the
transcript-based usage/cost capture are Claude Code hooks and do not
transfer to opencode. bash permission is operator-tunable
(ROBOCO_GROK_BASH_PERMISSION) so a deployment can fail closed until a
security/usage-parity opencode plugin lands. That plugin and live E2E
validation are the remaining work to finalize with xAI.
* ci(release): build + publish the roboco-agent-grok image
Add roboco-agent-grok to the release workflow's image build/publish map so
registry deploys carry the Grok runtime image (parity with every other
agent image). Split from the feature commit because pushing a workflow
change requires a workflow-scoped token.
* fix(migration): commit the grok enum value before seeding (autocommit_block)
CI's "Apply database migrations" failed with asyncpg
UnsafeNewEnumValueUsageError: alembic runs the whole upgrade in a single
transaction, so migration 039's INSERT used 'grok' in the same transaction
that 038 added it — which Postgres forbids. Splitting into two migration
files did not help (one transaction spans both). Wrap the ALTER TYPE ADD
VALUE in op.get_context().autocommit_block() so the value commits before 039
(and any later migration) uses it. Still renders in offline --sql, so the
enum-migration-parity test is unaffected.
* feat(grok): price grok-build-0.1 + secret-scrub opencode plugin
- pricing.py: add grok-build-0.1 rates ($1/1M input, $0.20 cached, $2/1M
output), verified against xAI's published pricing. Grok is a priced
non-Anthropic model, so cost computes the moment usage is captured.
- secret-scrub.js: an opencode tool.execute.before plugin porting the
security-critical bash-guard deny rules (git network ops, credential-file
reads, /proc env, internal-host HTTP, roboco.* imports, ROBOCO_AGENT_ID
forgery, env dumps, destructive rm) to the opencode runtime — restoring the
guard the Claude Code hook can't provide there. Throwing denies the call
(confirmed by opencode's env-protection example). Wired into the generated
opencode.json plugin array + baked into the grok image.
Deny logic verified via node (9 deny + 5 allow cases). UNVALIDATED against a
live opencode runtime: confirm it fires in the live E2E spawn before a Grok
dev-agent touches a real repo; the bash permission is operator-tunable as a
second gate.
Cost CAPTURE (distinct from pricing) is intentionally NOT built yet: opencode's
plugin hooks expose model info but no token/usage object, so the capture path
is unconfirmed and needs the live spawn to settle.
* feat(grok): read opencode session usage for cost capture
Confirmed by inspecting a local opencode run: opencode persists per-session
usage in SQLite at ~/.local/share/opencode/opencode.db — the `session` table
carries cost + tokens_input/output/reasoning/cache_read/cache_write. xAI's
response usage object (prompt_tokens, completion_tokens,
prompt_tokens_details.cached_tokens, completion_tokens_details.reasoning_tokens)
maps directly onto those columns.
Add opencode_usage.read_session_usage / cost_for_session: read the opencode DB
and price the tokens via roboco.billing.pricing (our cost stays authoritative;
opencode's own `cost` column is kept for reference). Tested against a fixture DB
mirroring the real schema (single session, summed sessions, missing/empty DB).
Remaining wiring (for the live spawn): mount the opencode data dir on grok
spawn + call cost_for_session at reap to record the usage rollup.
* fix(grok): correct opencode provider (Responses API), stdin, reasoning cost
A live opencode run against api.x.ai/v1 surfaced three real bugs:
1. Provider package — grok-build-0.1 is driven via the OpenAI Responses API
(opencode calls model.responses()). @ai-sdk/openai-compatible is
chat/completions only and errors "responses is not a function". Switch the
generated opencode.json provider + the grok image to @ai-sdk/openai.
2. Headless hang — `opencode run` blocks after init without a TTY; close stdin
(`< /dev/null`) in the entrypoint so it proceeds to the model call.
3. Reasoning-token cost — grok-build-0.1 is a reasoning model; reasoning tokens
bill as output but opencode stores them in a separate column. cost_for_session
folds tokens_reasoning into output (else ~22x undercount).
Verified end-to-end against a real session row (input=6120, output=1,
reasoning=226, cache_read=1856): our pricing reproduces opencode's stored USD
cost ($0.0069452) exactly. Tests anchored to that real row.
* feat(grok): first-class xAI/Grok routing mode (UI + backend)
The Routing-mode toggle had Anthropic / Ollama / Self-Hosted / Mix but no way
to route the whole org to Grok. Add it end to end:
- backend: apply_mode("grok") + _apply_grok (GLOBAL default -> grok-build-0.1) +
derive_mode "grok" detection; ApplyModeRequest/ModeResponse accept "grok".
- panel: a "Grok" routing-mode card (between Anthropic and Ollama, gated on the
xAI key) + flipToGrok; a Grok group in the per-agent mix dropdown +
catalogGrokOnly + a grok ProviderBadge variant; the mix-save key check and
the AI-routing description now cover Grok.
- tests: integration derive_mode/apply_mode "grok" cases (+ grok provider row
in the fixture).
Gated: ruff + mypy clean; panel typecheck + lint clean.
* feat(grok): reasoning-effort by role (cut grok-build cost on cheap roles)
grok-build-0.1 reasons heavily by default and reasoning bills at the output
rate (a live "say ok" call emitted ~300 reasoning tokens, ~85% of its cost).
Confirmed live that opencode's `--variant minimal` cuts reasoning ~54%
(298 -> 136 tokens, same prompt).
GrokProvider now picks reasoning effort by role: code-quality roles (developer,
qa, pr_reviewer) keep full reasoning; coordination / docs / board roles
(cell_pm, main_pm, documenter, product_owner, head_marketing, auditor, prompter,
secretary) run "minimal". It's passed to opencode via the entrypoint's
`--variant`. Operators can force one effort for ALL grok agents with the
ROBOCO_GROK_REASONING_EFFORT env (minimal | high | max, or default/full).
Tests cover the role map, the env override, and the spawn env wiring.
* style(panel): show the Grok (xAI) key card above the Ollama card
* fix(grok): stop opencode subagent-stream hang at the config layer
The Grok pr_reviewer wedged in_progress forever: opencode's default agent ran
with the subagent `task` tool enabled, spawned an Explore subagent on
grok-build-0.1 whose model call opened an SSE stream that went idle, and the
run hung with no timeout.
- Hard-disable opencode's subagent `task` tool in the generated opencode.json.
No RoboCo role uses opencode-internal subagents — work flows through the
gateway verbs — so removing the tool kills the hang trigger outright.
- Set provider.xai.options.timeout + chunkTimeout (operator-tunable via
ROBOCO_GROK_REQUEST_TIMEOUT_MS / ROBOCO_GROK_CHUNK_TIMEOUT_MS) as the
defence-in-depth backstop; chunkTimeout aborts an idle stream.
- Bundle the permission + timeout + subagent knobs into an OpencodeGuards
dataclass (keeps the builder under the arg-count gate).
- Drop the dead ROBOCO_AGENT_TOOLS spawn env (it had no consumer); opencode
tool restriction lives in the rendered config now.
* feat(grok): reaper watchdog kills wedged opencode containers
The heartbeat reaper deliberately skips a task whose assignee holds a live
ACTIVE container, so a Claude agent deep in a long edit/test cycle isn't
churned out from under live work. A wedged opencode container breaks that
assumption: it stays ACTIVE while firing no gateway verb, so its heartbeat
never advances and the live-instance skip would shield its task forever — the
exact way the Grok pr_reviewer parked in_progress.
Add a longer grok-idle kill threshold (ROBOCO_GROK_IDLE_KILL_SECONDS, default
900s, well past the stream chunk timeout). A GROK instance idle past it is
force-removed (its logs dumped to disk first) and evicted from the instance
registry, so the same reaper pass then releases the task. Only GROK runtimes
are eligible — a quiet Claude agent keeps the heartbeat-skip protection.
* feat(grok): guard interactive roles from GROK routes (interim)
intake (prompter) and secretary run a held-open chat session driven by the
Claude Agent SDK. GROK has no interactive runtime yet, and a GROK route for
those slugs would be spawned with the route creds injected as ANTHROPIC_*
against api.x.ai/v1 — the wrong protocol — producing a silent, empty reply
(the blank intake we observed).
Downgrade a GROK route for intake-1/secretary-1 to the Anthropic default with
a logged warning. The one-shot delivery roles route to GROK unchanged. This
guard is replaced by the real interactive fork once the opencode interactive
driver lands.
* feat(grok): capture one-shot Grok usage/cost from the opencode store
A GROK agent runs opencode, not Claude Code: it has no SDK /usage/status
server and writes no Claude transcript, so _resolve_final_token_usage found
nothing and every Grok agent finalized at 0 tokens / $0 — the opencode_usage
reader existed but had no caller.
- Mount a per-agent opencode data dir ($DATA/opencode/<agent_id> →
/home/agent/.local/share/opencode) so opencode.db is captured, and mount the
same host dir into the orchestrator (/data/opencode) in all three compose
files so the finalizer can read it back — the opencode analogue of the
mounted Claude transcript.
- _resolve_final_token_usage branches on provider_type: GROK reads opencode.db
via opencode_usage (reasoning folded into output, billed at the output rate)
and skips the SDK/transcript path. A 0-token read logs a WARNING so a silent
mount failure isn't mistaken for a real zero-cost run.
- ROBOCO_OPENCODE_DATA_DIR overrides the in-orchestrator path for local runs.
* feat(grok): make interactive spawns first-class on AgentProvider (additive)
The AgentProvider ABC modelled only the one-shot lifecycle (spawn/stop/
health_check/remove), so the interactive intake/secretary roles could never
route through a provider. Add an opt-in interactive surface:
- supports_interactive class flag (default False).
- InteractiveSpawnSpec: the resolved AgentConfig + session id + role-specific
image + optional HMAC token — everything a provider needs without importing
orchestrator internals.
- spawn_interactive(spec): a non-abstract default that declines via
ProviderError, so every existing one-shot provider is unchanged.
Pure scaffolding — no provider opts in yet (GrokProvider flips the flag when
its interactive driver lands). Zero behavioural change.
* feat(grok): Grok-native interactive runtime (opencode serve) — container side
Builds the Grok analogue of the Claude intake/secretary live-session runtime,
satisfying the same IntakeSession seam so the existing IntakeDriver loop,
message source, relay, and StreamChunk panel contract are reused unchanged:
- OpencodeServeSession: a held-open `opencode serve` session (context persists
across turns) where each human turn is one synchronous POST /session/:id/
message; normalize_opencode_message maps the reply parts to text/thinking/
tool_use/draft/turn_end chunks (draft via a propose_draft tool part or the
fenced roboco-draft fallback). Doc-verified against opencode's server API.
- grok_intake_main / grok_secretary_main: container entrypoints mirroring the
Claude mains but yielding an OpencodeServeSession; they render opencode.json
(xAI provider + MCP + system prompt) first, then run the receiver + driver.
- roboco-agent-grok-prompter / -secretary images (FROM roboco-agent-grok) +
their builder services in all three compose files.
UNVERIFIED-LIVE: the opencode serve flow + exact Part schema + draft path need
a live run against grok-build-0.1 (the part mapping is defensive). The
orchestrator wiring that routes a GROK intake/secretary route to these images
is the next step (a design decision is open — see the handoff notes).
* feat(grok): route interactive intake/secretary to opencode-serve images
Wire the GROK interactive path the in-place way (matching how the interactive
roles already choose ANTHROPIC_* per route), so a GROK route launches the
Grok-native opencode-serve image instead of the Claude SDK-driver image:
- _spawn_intake_container / _spawn_secretary_container pick the
grok-prompter / grok-secretary image (ensuring the base→grok→interactive
build chain) when the route is GROK, and stamp provider_type on the spec +
AgentConfig so finalize routes usage to the opencode store.
- _build_intake_run_cmd / _build_secretary_run_cmd inject OPENAI_* + the
opencode store mount + system-prompt env for GROK via a shared
_append_interactive_provider_env, keeping ANTHROPIC_* for every other
provider. The intake's minimal mounts (no gateway MCP) are preserved, so
Grok intake matches the Claude intake's tool surface (the spec).
- Add a per-agent opencode store mount to the interactive host paths so
interactive Grok usage/cost is captured like the one-shot path.
Removes the interim Phase-0 routing guard (the real path supersedes it) and
retires the unused AgentProvider.spawn_interactive/InteractiveSpawnSpec seam —
the interactive roles have a bespoke assembly that the one-shot provider
surface doesn't fit, so the fork lives in their own builders.
UNVERIFIED-LIVE: end-to-end intake/secretary chat on Grok needs the stack up +
opencode serve confirmed against grok-build-0.1.
* feat(grok): surface intake/secretary in the mix-mode picker; doc guardrail parity
- Panel: add intake-1 (prompter) and secretary-1 to the mix-mode per-agent
routing list so an operator can assign Grok (or Claude) to the interactive
roles from the UI; assigning a Grok model routes them to the opencode-serve
image. tsc + eslint clean.
- opencode_config: correct the now-stale parity note — bash-guard is ported
(secret-scrub.js) and usage/cost is captured (opencode store); the remaining
gap is the budget/loop/stop/prompt-injection hooks, which need a sidecar
plugin (open decision), with ROBOCO_GROK_BASH_PERMISSION as the interim gate.
* test(grok): mypy-clean the reaper watchdog + interactive spawn tests
The CI mypy scope (roboco/ tests/) flagged test-only typing issues my per-file
runs missed: direct method assignment (orch._remove_container = AsyncMock())
trips [method-assign], and a module-level dict[str,str] is invariant against
the dict[str, str|None] the run-spec expects.
- Use monkeypatch.setattr for _remove_container in the watchdog tests.
- Annotate the shared _HOSTS as dict[str, str | None].
Production code unchanged; mypy roboco/ tests/ is green.
* feat(grok): cost-ceiling kill-switch (budget-guardrail parity)
Claude Code's per-agent token-budget hook fires against the SDK :9000 server;
opencode exposes NO usage/budget hook to a plugin (confirmed against its plugin
docs), so the budget kill-switch can't be a plugin/sidecar — the orchestrator
enforces it instead.
_enforce_grok_cost_budget runs each dispatch tick: for every ACTIVE GROK
container it reads cumulative cost from the opencode store (the Phase-2 reader)
and kills + evicts it past ROBOCO_GROK_MAX_COST_USD (0 = off), after which the
reaper releases the freed task. This also catches a runaway loop that keeps
firing verbs (so it evades the idle watchdog) but still burns cost.
Covers the budget/runaway-burn slice of guardrail parity. The remaining Claude
hooks (prompt-injection PRE-gate, stop-guard terminal-verb) have no blocking
opencode equivalent — opencode's message/stop hooks are observe-only — and the
interactive reasoning-variant has no opencode.json/serve knob (CLI-flag only);
both are pinned for a live probe rather than shipped as a guess.
* docs(grok): document Grok's reduced guardrail posture (honest, not blocking)
Grok agents run on opencode, not Claude Code, so they do NOT have full
guardrail parity — claiming otherwise would be false. Document it truthfully
and keep them usable rather than blocking them.
- Panel routing card: an amber caveat shown in Grok/Mix mode — command/
secret-exfil guard + cost cap apply to Grok, but the prompt-injection guard
does NOT (opencode cannot block a turn); Anthropic/Ollama/Self-Hosted run
through Claude Code with the full guard set; prefer those for agents that
ingest untrusted or cross-agent content; Grok is safe for trusted work.
- docs/self/architecture/llm-provider-security.md: the reference — the two
runtimes, which provider uses which, the per-guardrail parity matrix, why
the injection/stop gaps exist (opencode hooks are observe-only), and the
routing recommendation (delivery roles handling untrusted content → a
Claude-Code-runtime provider).
Panel tsc + eslint clean.
* fix(grok): make the live interactive path work — store perms, error surfacing, variant
Found by actually running opencode serve locally (the path was doc-verified but
never executed). Three fixes:
1. EACCES on the opencode store mount (the live intake crash): on Linux docker
auto-creates a missing bind source as root:root, so the non-root agent user
could not mkdir/write in /home/agent/.local/share/opencode and opencode died
at boot. _ensure_opencode_data_dir pre-creates the per-agent dir 0777 before
the mount (one-shot via the _GrokHost seam, interactive in both spawns).
2. Silent blank reply on a model error: opencode reports a turn failure in
info.error with parts=[], NOT as a part — verified live (a bad xAI key
returns info.error APIError). send() / normalize_opencode_message now surface
it as an "error" StreamChunk so a failed turn is never blank (the original
intake bug class). Confirmed live: the error now renders.
3. Reasoning variant on the serve path: the live OpenAPI shows the message body
accepts a "variant" field (it is NOT CLI-only, as the docs implied), so the
pin is unblocked. send() passes ROBOCO_GROK_VARIANT as the per-turn variant;
the orchestrator sets it per-role (_reasoning_effort_for) for interactive
Grok, the same lever as the one-shot --variant.
opencode serve startup, POST /session, session-id extraction, the part-type
mapping (text/reasoning/tool), and the error path are all validated against a
live opencode 1.17.8. A real successful grok reply still needs a funded key.
* fix(grok): pre-create agent-owned ~/.local in the grok image (opencode state EACCES)
Running the built grok-prompter container surfaced a second EACCES the
mechanism analysis missed: bind-mounting the opencode store at
~/.local/share/opencode makes docker create the intermediate ~/.local AS ROOT,
so the non-root agent user then cannot create its sibling ~/.local/state and
opencode dies at boot. Pre-create the ~/.local tree agent-owned in the image so
the mount leaves the parents writable. Complements the orchestrator 0777
host-source pre-create (which covers the bind source on Linux).
Verified live: with this fix the container starts clean, opencode serve opens
the session, a POST /turn produces a real grok reply, and all chunks
(thinking/text/turn_end) reach the relay endpoint.
* feat(grok): prompt-injection guard for Grok (parity with the Claude hook)
The injection guard is RoboCo's own hook (user-prompt-hook.sh), not a runtime
built-in, so it can be recreated at our input boundary regardless of runtime —
opencode's lack of a blocking pre-prompt hook is irrelevant.
- prompt_guard.detect_injection: the deny patterns ported to reusable Python.
- IntakeDriver._run_turn scans every interactive turn before sending it to the
model and denies a match as an error chunk. Covers BOTH Grok (opencode) and
the Claude SDK intake (which runs with setting_sources=[] and so never loaded
the bash hook — it was unguarded too).
- The one-shot grok entrypoint scans ROBOCO_INITIAL_PROMPT and refuses a
poisoned task prompt (parity with the Claude UserPromptSubmit deny).
- Broadened the pattern (Python + the bash hook, kept in sync) to catch the
multi-qualifier canonical phrasing "ignore all previous instructions", which
the single-qualifier original missed — without false-positiving on
"ignore the linting rules" (an intermediate non-qualifier word breaks it).
So Grok now has the command/secret-exfil guard (secret-scrub), the cost cap,
AND the injection guard. Verified: 94 agent_sdk tests pass; bash + Python agree
on detect/miss cases.
* docs(grok): drop the security disclaimers — injection guard closes the gap
With the prompt-injection guard now recreated for Grok (prior commit), the
"Grok lacks the injection guard / prefer Claude for delivery roles" warning is
no longer true, so remove it:
- Panel routing card: replace the amber "prefer Claude / not safe" caveat with
a neutral one-liner — Grok agents run on opencode; the command/secret-exfil
guard, the prompt-injection guard, and the cost cap all apply.
- docs/self/architecture/llm-provider-security.md: prompt-injection row flips to
"yes" for Grok; intro + routing recommendation updated to "effective security
parity, any agent (incl. delivery roles) can run on Grok"; the only remaining
unported hook is the non-security stop-guard.
- opencode_config docstring: the remaining gap is now just the stop-guard
(budget + injection are covered).
Panel tsc + eslint clean.
* fix(grok): allow external-directory reads so the pr-reviewer can work
Live NAS run showed the Grok pr-reviewer claim the review and fetch the diff,
then write it to /tmp and FAIL to read it back: opencode auto-denied
"external_directory (/tmp/*)" — its file tools refuse paths outside the project
cwd, and in headless serve/run mode an "ask" permission auto-rejects (no human).
Add permission.external_directory (default "allow", env
ROBOCO_GROK_EXTERNAL_DIR_PERMISSION) to the generated opencode.json. The
container is the sandbox and secret-scrub still blocks credential-file reads, so
allowing in-container external-dir reads is safe and unblocks legitimate scratch
use (e.g. the pr-reviewer grepping a large diff in /tmp).
Verified live against grok-build-0.1: with external_directory:"allow" the Read
tool reads a file outside cwd and returns its contents (no auto-reject); the
plain-string form is accepted by opencode 1.17.8.
Needs a rebuild of roboco-agent-grok + a pr-reviewer re-run on the NAS to confirm.
* refactor(grok): split eligibility out of _maybe_kill_wedged_grok (xenon C -> B)
CI complexity gate (make quality -> xenon --max-absolute B) flagged
_maybe_kill_wedged_grok at rank C — too many guard branches in one method.
Extract the kill-candidate decision into _wedged_grok_slug(task, last_heartbeat)
-> slug | None (recent-heartbeat / no-owner / not-ACTIVE / not-GROK all yield
None); _maybe_kill_wedged_grok now just kills + evicts the returned slug.
Behaviour is identical (same guards, same order) — the reaper watchdog tests
pass unchanged. xenon now passes on the full package; ruff + mypy clean.
* feat(grok): start the in-container SDK server + budget feed (Claude parity)
The keystone of the Grok parity work (CEO's "take Claude as baseline, create
what's missing" call): the one-shot Grok container now starts the same SDK
server the Claude path runs, so the per-verb circuit breaker (the flow/do MCP
servers already POST /verb/attempted to it), the per-session budget/loop
counters, the terminal-verb tracking, and the SessionEnd post-mortem all work
on Grok instead of being silently absent.
- entrypoint: launch roboco.agent_sdk.server (bare venv python, not `uv run`
which would re-sync the drifted clone lock and stall), wait for /health,
reset counters; run opencode WITHOUT exec so the script regains control to
run the post-mortem and the silent-exit substitute after the run returns.
- budget-feed.js: opencode plugin that gates on /budget/status in
tool.execute.before (halt/loop deny — the only place to stop a runaway
one-shot run; opencode has no PostToolUse-deny) and records the executed
tool + args-hash in tool.execute.after. Fail-open; bare-verb normalization
for MCP-namespaced terminal verbs.
- silent-exit substitute: on a graceful exit with no terminal verb the
entrypoint posts /terminal/force_substitute so the task isn't left stuck
claimed/in_progress (Stop-hook parity at the boundary).
- opencode_config: wire budget-feed into the plugin array; add
ROBOCO_OPENCODE_EXTRA_PLUGINS so per-image role tool plugins load scoped to
one role; read the per-role ROBOCO_GROK_EDIT_PERMISSION.
Targeted gate green (ruff/mypy/xenon + opencode_config tests; node --check on
the plugins; bash -n on the entrypoint).
* feat(grok): give the Grok Secretary its CEO-authority tools (blocker)
The Grok Secretary could chat but had zero directive tools — it could not read
company state or act on a CEO command, so it was non-functional. This is the
integration blocker.
- secretary-tools.js: opencode plugin registering read_company_state /
read_task / submit_directive via the Hooks.tool API, each calling
/api/secretary/* with the container's HMAC agent token — a direct port of the
Claude Secretary's SDK tools (secretary_driver.build_secretary_options). The
high-impact directive kinds stay gated server-side (queued for CEO confirm).
- agent-grok-secretary.Dockerfile: bake the plugin and scope it to this image
via ROBOCO_OPENCODE_EXTRA_PLUGINS, so only the Secretary carries CEO authority.
- grok_secretary_main: correct the docstring that falsely claimed the tools
reached the API "through the mounted MCP gateway" (there is no gateway mount;
they're an opencode plugin).
- secretary.md: name the three tools and restate the confirm-before-act gate.
Verified locally that opencode loads a file-path plugin importing
@opencode-ai/plugin and resolves the package; the live model-tool-call +
backend round-trip is flagged UNVERIFIED-LIVE for the NAS.
* feat(grok): give the Grok Intake its propose_draft tool (draft card)
The prompter prompt tells the model to call propose_draft when the spec is
ready, but on Grok that tool didn't exist — so no draft chunk, no panel draft
card, and the human couldn't launch a task from a Grok intake chat.
- intake-tools.js: opencode plugin registering propose_draft via Hooks.tool;
the execute() only ACKs — the driver (OpencodeServeSession.normalize ->
_is_propose_draft -> _draft_from_tool_input) intercepts the tool CALL and
emits the `draft` chunk the panel renders.
- agent-grok-prompter.Dockerfile: bake the plugin, scoped to this image via
ROBOCO_OPENCODE_EXTRA_PLUGINS (delivery roles never draft).
- test: a propose_draft tool part normalizes to a draft chunk (not a tool_use).
The live tool-call -> draft-card path is flagged UNVERIFIED-LIVE for the NAS.
* feat(grok): scope opencode edit/bash/external-dir permissions per role
Grok wrote ONE global permission block, so a Grok pr_reviewer (or qa / PM /
auditor) ran with edit=allow + bash=allow on untrusted PR content. Now the
permissions are derived per role, mirroring orchestrator._get_role_permissions
on the Claude path:
- edit — allow only roles that write code (role_config.allows_write:
developer / documenter); everyone else edit=deny.
- bash — allow only roles that legitimately run a shell (developer /
documenter / cell_pm / main_pm); the read-only reviewers (qa / pr_reviewer /
auditor) and the board get bash=deny. secret-scrub still guards the rest.
- external_directory — only the pr_reviewer reads scratch outside its cwd (the
/tmp diff); delivery roles get deny.
One-shot roles resolve these in GrokProvider._append_grok_env; the interactive
intake/secretary set edit=deny + bash=deny in the orchestrator (intake keeps
external-dir reads for sibling product repos, the secretary does not). The
Claude path is untouched — the permission env is a GROK-only contract.
Targeted gate green (ruff/mypy/xenon + provider + interactive-spawn tests).
* feat(grok): park the provider on an xAI 429 (break the respawn loop)
A one-shot grok run that hit an xAI 429 exited without a terminal verb; the
dispatcher then re-spawned the same task every tick (429 -> exit -> respawn), a
container/token/cost loop with no living agent to call i_am_blocked.
- entrypoint: detect a rate-limit signature in the run output and exit 75
(EX_TEMPFAIL); a rate-limited task is NOT substituted — it must be retried.
- _handle_stopped_container: on a grok exit 75, park the provider via the
rate-limit tracker (retry_after window) instead of crash-retrying, and don't
count it as a crash. The existing probe-resume loop clears the park after the
window (unknown-provider time-expiry fallback) and the task is retried.
- spawn_agent: a grok-only, fail-open guard skips the launch while the provider
is parked, so the dispatcher no-ops instead of looping. The Claude path is
untouched.
Targeted gate green (ruff/mypy/xenon + new rate-limit tests; bash -n on the
entrypoint).
* feat(grok): close the secret-scrub bash-guard parity gaps
secret-scrub.js (the opencode bash guard) was missing three rules the Claude
bash-guard hook has, leaving a Grok dev able to read secrets the Claude path
blocks:
- source / dot-source of a credential-bearing file (source .env, . ./.env,
.bashrc / .git-credentials / .netrc / /proc/*/environ).
- interpreter one-liner reading a credential file
(python -c "open('.env')", node -e "readFileSync('.git-credentials')").
- git-ops check now runs on a SKELETONIZED command (heredoc bodies + echo/printf
args stripped) so a README/heredoc that merely documents `git push` is no
longer mistaken for invoking it — a false-positive parity fix from the Claude
guard.
Functionally smoke-tested with node against the real plugin (git push denied;
echo/heredoc "git push" allowed; source/interpreter cred reads denied; normal
commands allowed). Live opencode firing stays flagged in the file header.
* fix(grok): record a usage session for interactive intake/secretary (M1+M7)
_spawn_intake_container / _spawn_secretary_container built the AgentInstance by
hand and never recorded an agent_spawn_sessions row, so the reap finalizer had
no usage_session_id to look up — every interactive session (Claude or Grok)
finalized at 0 tokens / $0 in the rollups. Record the session (task_id=None) and
pin its id on the instance, mirroring _launch_spawn; the GROK path reads
opencode.db by this id, the Claude path reads the transcript.
Also correct the grok_intake_main docstring (M7): it claimed the serve process
was "gateway-wired" with an "MCP gateway", but interactive intake mounts no
gateway — its only tool is propose_draft, registered by the intake-tools.js
plugin.
* fix(grok): surface a dead opencode-serve clearly instead of a zombie chat (M2)
If `opencode serve` died after the session opened, every subsequent turn failed
with an opaque httpx connection error while the container lingered. send() now
detects the exited subprocess (returncode set) and yields a clear error chunk +
turn_end so the panel shows a real "session ended — start a new chat" message;
the idle watchdog / a human reap then tears the container down.
* fix(grok): close the panel relay when the cost-cap kills an interactive chat (M4)
_enforce_grok_cost_budget killed + evicted a container directly. For the
interactive roles (intake/secretary) that left the panel SSE relay open with no
close sentinel, so the chat froze with no explanation. Add
PrompterLiveRegistry.close_by_agent (push a final error event, then close every
session bound to that agent) and call it from the cost-cap watchdog when the
killed agent is the intake or secretary, so the panel reports the chat ended on
the cost cap instead of hanging.
* fix(grok): make the opencode runtime actually load — proven live on grok-build-0.1
Live verification (opencode 1.17.8 + grok-build-0.1, funded key) showed the Grok
runtime was loading INERT, three ways:
1. The provider override `provider.xai.npm=@ai-sdk/openai` failed model
resolution (ProviderModelNotFoundError) — opencode can't resolve that package
from its module path. Worse, ANY custom `provider.xai` block (even just
options) breaks plugin-tool registration. opencode's BUILT-IN xai provider
drives grok-build-0.1 with working tool-calls, so emit NO provider block; the
key + base reach it via XAI_API_KEY / XAI_BASE_URL env (provider.options.apiKey
alone does NOT authenticate).
2. Plugins referenced by absolute path in the config `plugin:` array never
registered their hooks/tools. opencode 1.17.8 only registers from the plugin
AUTO-DISCOVERY dir (~/.config/opencode/plugin/). Bake all plugins there.
3. Plugins must use a NAMED export, not `export default`.
Changes:
- opencode_config: no `provider` block, no `plugin` array; drop the dead
XaiTarget + timeout machinery; build_opencode_config now takes a model string.
- GrokProvider / orchestrator interactive env: inject XAI_API_KEY + XAI_BASE_URL
(drop the now-unused OPENAI_*).
- secret-scrub / budget-feed / secretary-tools / intake-tools: named exports;
baked into /home/agent/.config/opencode/plugin/ (drop the EXTRA_PLUGINS env).
- agent-grok* Dockerfiles: plugin dir + agent ownership; drop the unneeded
@ai-sdk/openai global install.
Verified live end-to-end: grok-build-0.1 calls read_company_state AND
submit_directive through secretary-tools.js and the backend receives both with
the agent token; a tool.execute.before guard fires; built-in tool-calls work.
Targeted gate green (ruff/mypy/xenon + opencode_config/providers/interactive
tests; node --check the plugins).
* fix(grok): deliver intake draft via the relay + correct opencode-mechanism docs
Live end-to-end verification (opencode 1.17.8 + grok-build-0.1) of the WHOLE
integration, then fixes for what it surfaced:
1) Intake draft card (FUNCTIONAL): opencode's synchronous serve reply
(POST /session/:id/message) returns only [step-start, text, step-finish] — it
does NOT include tool-call parts, so the driver could never extract the
propose_draft draft. intake-tools.js now POSTs the draft straight to the
prompter-live relay (/api/prompter/live/{session}/events, the same endpoint
the driver's relay sink uses), so the panel renders the card regardless.
Verified live: grok calls propose_draft -> the relay receives the draft.
2) Correct misattributed opencode "bugs" (DOCS): earlier comments asserted as
general opencode behavior that a provider.xai block / npm override / config
plugin:-array "break" registration. Re-testing showed those were artifacts of
a PROJECT-level .opencode/opencode.json; from the GLOBAL config (which
opencode_config writes) the built-in provider, model resolution, the plugin
array AND the auto-discovery dir all work, and MCP gateway verbs register
(delivery agents verified). Reframed the comments as design choices (built-in
provider + XAI_API_KEY env + plugins baked in the auto-discovery dir with
named exports) and dropped the false claims.
3) Reasoning --variant: passing it does not error, but whether opencode applies a
named reasoning variant to grok-build-0.1 (no provider-defined variants) is
UNVERIFIED — comment softened from a "~54% cut" claim to best-effort,
measure-on-NAS.
Verified live this session: one-shot delivery (model + MCP verbs + plugins +
hooks), secretary tools (read_company_state + submit_directive -> backend with
token), intake draft (relay), grok built-in-provider tool-calling. Remaining
NAS-only: full container assembly (SDK :9000 startup, entrypoint hooks, 429
parking) + the --variant cost measurement. Gate green (ruff/mypy + 51 tests;
node --check the plugins).
* feat(grok): reap abandoned interactive chats (M3)
An interactive intake/secretary chat the human abandoned (closed the tab without
confirming or stopping) leaked its container until the orchestrator restarted —
the wedged-grok reaper is task-driven and these run task_id=None, and an SSE
disconnect intentionally does NOT reap (so a page reload can reconnect).
Reap by IDLE TIME, not connection state: PrompterLiveRegistry tracks
last_activity (bumped on every push/deliver = a turn), and the 60s sweeper
retires sessions idle past ROBOCO_INTERACTIVE_IDLE_REAP_SECONDS (default 1800;
0 disables) via reap_intake_session / reap_secretary_session. An active or
page-reloaded chat that keeps exchanging turns stays fresh and is never reaped;
board-review-parked sessions (task_id set) are exempt. Provider-agnostic — fixes
the leak for both Claude and Grok interactive.
Tests: idle-only reap (active/parked/closed excluded), activity bump keeps a
session alive, threshold 0 disables. Gate green (ruff/mypy/xenon + prompter_live).
* fix(panel): resolve agent names from the live roster so they never drift
A review task assigned to the pr-reviewer rendered as a truncated raw
UUID instead of its name. Root cause: the panel resolved assignees from a
hardcoded static roster in agent-utils.ts that had drifted — it never
gained the board-adjacent agents added backend-side (intake-1,
secretary-1, pr-reviewer-1). Their UUIDs hit no map entry, so
getAgentDisplayName fell through to the unknown-UUID branch and returned
agentId.slice(0, 8). Every assignee surface (task table, task detail,
subtasks, journals, communications, commit cards) shares that resolver, so
all of them showed the fragment.
Make the live /api/agents roster the source of truth instead of a static
duplicate that silently rots:
- agent-utils: add a runtime registry (registerAgentRoster) keyed by both
UUID and slug; resolveToSlug / getAgentDisplayName / isKnownAgent consult
it first. The static maps remain only as an offline / first-paint
fallback (now complete with the three agents).
- api/agents: surface the backend UUID on AgentDefinition (getAll/getOne
previously dropped it), so the registry can key by UUID.
- use-agents: add useAgentRosterSync (registers the live roster) and derive
useAgents from live definitions, falling back to the static roster.
- providers: mount the sync once inside QueryClientProvider.
Now any agent the backend knows about resolves, including ones added after
this change — the panel can no longer drift out of sync.
Tests: agent-utils unit tests cover the three agents end-to-end, a
live-roster-only agent (drift-proofing), live-overrides-static, and a
regression guard for the existing roster.
* fix(pr-review): post a COMMENT review when GitHub forbids self-review
A pr-reviewer review of an org-authored PR never reached GitHub. The agent
side ran correctly (claim → read-only diff → review → post_pr_review →
completed + CEO notify), but the GitHub publish 422'd with "Can not request
changes on your own pull request": the PR was authored by the same account
that owns the project PAT. post_pr_review posts best-effort after the DB
transition, so the failure was logged and swallowed — the task completed and
the CEO was notified "reviewed" while the PR showed no review.
GitHub forbids APPROVE / REQUEST_CHANGES on your own PR but DOES allow a
plain COMMENT review. The org's internal PRs (and any PR the PAT owner
opened) hit this. Retry once as a COMMENT review on the self-review 422 so
the review actually lands; the verdict is already stated in the body. The
external/fork-PR path (different author) is unchanged — REQUEST_CHANGES
succeeds there and the fallback never fires.
Tests: self-review 422 downgrades to COMMENT and returns the COMMENT result;
a failing COMMENT retry still surfaces GitError with no infinite loop; the
existing non-self 422 still raises.
* fix(grok): harden cost-guard, pin runtime, refresh stale plugin comments
Address review findings on the Grok provider work:
- budget-feed plugin failed open unconditionally, so a one-shot task agent
whose in-container SDK budget server went unreachable would run with the
cost cap unenforced. The entrypoint now exports ROBOCO_BUDGET_ENFORCE=1
(one-shot agents always start that server) and the plugin's pre-exec gate
fails CLOSED when the flag is set and the budget endpoint is unreachable,
halting an uncapped burn. Interactive serve agents (intake/secretary) set
no flag and keep failing open (they run no budget server by design).
- Pin opencode-ai to the live-verified 1.17.8 (was an unpinned global npm
install). Untrusted model output runs under it; bump the pin deliberately.
- Document the ROBOCO_GROK_* operator vars in .env.example (image, the three
opencode permissions, reasoning effort, idle-kill, cost ceiling).
- Refresh stale plugin comments: the MCP tool-name shape and the secretary
tool-registration path are confirmed live, and secret-scrub's load route is
the auto-discovery dir (not a config plugin: array). Keep the honest
not-yet-exercised caveat on secret-scrub's deny path and the reasoning
variant — those remain genuinely unverified.
* fix(grok): unbreak workspace-cwd agents, free trapped agents, stop self-PR review
Three bugs surfaced by the first live Grok lifecycle run:
- Dev/QA/doc agents crash-looped at startup with ModuleNotFoundError on
roboco.llm.providers. The entrypoint ran the opencode-config render from the
agent's workspace-clone cwd, whose own roboco/ dir shadows /app on the
sys.path front; a branch without the grok code lacks the providers package.
Render from /app so the installed package always resolves (the render has no
cwd dependency — writes global, reads ROBOCO_MCP_CONFIG).
- A budget/loop halt blocked EVERY tool, including i_am_idle, unclaim, and
i_am_blocked, so a halted agent could neither continue nor stop and flailed —
one billed model turn per blocked retry. The before-gate now always lets the
release verbs through so a halted agent can exit cleanly.
- The inbound reviewer ingested the org's OWN PRs (authored by the repo-owner
account), which can't take a REQUEST_CHANGES review (GitHub 422) and get
re-reviewed every poll. The normalizer flags author_is_owner and ingestion
skips them — the reviewer reviews only PRs the org did not author.
External/contributor PRs are unaffected.
Tests: owner-authored PR flagged + skipped; normalize shape covers the new
field. Gate green on the changed modules (ruff/mypy/xenon + 48 tests).
* feat(grok-cli): render config.toml + map per-role grok CLI flags
First piece of the Grok CLI provider that replaces the opencode runtime: a
pure, unit-tested module the agent entrypoint runs to translate the mounted
mcp-config.json into ~/.grok/config.toml ([mcp_servers]) and compute the
per-role 'grok -p' flags — subagent/shell/edit tool removal, raw-git-mutation
and rm-rf denies, reasoning effort — mirroring ClaudeCodeProvider's per-role
permissions with native grok flags instead of an opencode permission block +
JS guard plugins. Uses tomli_w. The rendered config + env injection are
validated live against grok-build (the model called the server through it).
* feat(grok-cli): grok CLI agent image + headless entrypoint
The roboco-agent-grok image now installs xAI's official grok CLI (Grok Build,
pinned 0.2.56) instead of opencode, authenticated by the SuperGrok subscription
via a mounted ~/.grok/auth.json (parity with the Claude ~/.claude mount, no
metered API key). The entrypoint renders ~/.grok/config.toml + per-role flags
from /app (the ModuleNotFound-shadowing lesson), runs grok -p headless with
--output-format json, keeps the prompt-injection guard, and exits 75 on a
rate-limit so the orchestrator parks the provider. No in-container SDK server or
budget-feed — native --max-turns + server-side terminal-substitute replace them.
* feat(grok-cli): GrokCliProvider — subscription auth mount, mirrors ClaudeCodeProvider
Replace the opencode GrokProvider with GrokCliProvider: reuses the orchestrator's
shared mount/auth/git assembly (gateway + identity) exactly like the Claude path,
mounts the host ~/.grok/auth.json read-only (SuperGrok subscription) instead of
injecting an xAI key, and sets the slim env the grok-cli entrypoint + renderer
read (ROBOCO_AGENT_ID for per-role flags, model, mcp-config, prompt). Provider
routing fields are blanked before the shared step so the grok endpoint is never
mislabelled ANTHROPIC_*. Per-role permission logic now lives in grok_cli_config,
so the provider is slim. Registry/orchestrator/exports updated; provider tests
rewritten for the CLI behavior (no XAI key, auth mount present/absent).
* feat(grok-cli): capture per-session token usage + notional cost
Grok runs on the SuperGrok subscription, but — exactly like Claude on Max — we
still record per-agent tokens and a notional cost for the dashboard. The grok
CLI writes a cumulative totalTokens per turn into
~/.grok/sessions/<cwd>/<session-id>/updates.jsonl (the grok analogue of the
Claude transcript / old opencode.db); the max is the session total. This reader
locates that file (url-encoded cwd), extracts the total, and prices it at the
output rate (no input/output split from the CLI; conservative + matches the
reasoning-at-output convention). Validated against a real grok-build session
(18253 tokens -> $0.0365). Entrypoint + finalize wiring follows.
* feat(grok-cli): wire usage capture into the run (session id + post-run extract)
The provider pins a fixed session id (ROBOCO_AGENT_SESSION_ID, reused from the
agent session id as on the Claude path); the entrypoint passes it to
'grok -p -s <id>' so the run's session store is locatable, then runs the usage
reader post-run (best-effort) to write the captured tokens + cost. The
orchestrator-side finalize that reads that file follows.
* feat(grok-cli): read captured usage at finalize; keep interactive serve working
The provider mounts the per-agent data dir and points the entrypoint's usage
file at it; the orchestrator's grok finalize reads that usage.json first (the
grok-CLI total, priced at the output rate) and falls back to opencode.db for the
still-opencode interactive intake/secretary path. Re-add _reasoning_effort_for to
grok.py as a clearly-temporary shim for that interactive path (it needs opencode's
"minimal" variant, distinct from the CLI's --effort) until it is converted too.
* feat(grok): convert interactive intake/secretary to the grok CLI; delete opencode
Move the last Grok runtime off opencode onto xAI's official `grok` CLI, for full
parity with the Claude path. The intake/secretary chat now runs per-turn headless
`grok -p` invocations that resume one session id (proven live: context carries
across runs), with streaming-json deltas mapped to the existing panel StreamChunk
kinds — the IntakeDriver loop, message source, relay, and idle reaper are reused
unchanged; only the SessionFactory differs (GrokCliSession replaces the
opencode-serve session).
- GrokCliSession + a pure, unit-tested streaming-json -> StreamChunk assembler
(thought coalesced to one block, text streamed live, end captures the session
id for -r, fenced-draft fallback, clear errors incl. rate-limit).
- intake propose_draft and secretary read_company_state/read_task/submit_directive
are now FastMCP servers (roboco-intake / roboco-secretary) wired into
~/.grok/config.toml, launched via `uv run --directory /app` to resolve the
installed package. The secretary tools reuse the shared backend helpers.
- Orchestrator: interactive spawn mounts the subscription auth + per-agent usage
dir (no metered xAI key, no permission env — grok flags carry per-role perms);
usage/cost now read a captured usage.json (drop the opencode.db reader, the
_opencode_db_path/_grok_usage_from_opencode methods, and the cost-cap's
opencode read). hosts["opencode"] -> hosts["grok_usage"]; OPENCODE_DATA_DIR ->
GROK_USAGE_DATA_DIR.
- Fix one-shot usage capture: `-s` does not pin the session id (grok generates
its own), so the entrypoint now reads the real id back from the JSON run log
and the reader uses it; usage is captured per-turn on the interactive path.
- Delete the opencode layer: opencode_config/opencode_usage/opencode_session, the
docker/grok/*.js plugins, the old one-shot entrypoint, and their tests.
- Compose (all three files), .env.example, and stale comments updated to the
grok-CLI runtime; add the SuperGrok auth mount + grok-usage dir.
Gate green: ruff, mypy (296 files), xenon, tests. NAS build/verify pending.
* fix(grok): deliver the role blueprint as grok's system prompt via ~/.grok/AGENTS.md
The blueprint was mounted at /app/system-prompt.md but never reached grok — a real
parity gap vs the Claude path (which passes --system-prompt-file). grok agents ran
only on the per-task prompt, missing their RoboCo role/org context.
Verified live on grok 0.2.56 that the obvious flags do NOT work headless:
`--system-prompt-override` and `--rules` are silently ignored under `grok -p`
(identical output with and without). What IS honoured is grok's instruction-file
discovery — and `$HOME/.grok/AGENTS.md` is loaded GLOBALLY regardless of --cwd
(a project AGENTS.md only loads from the cwd/project root, which would pollute the
agent's git workspace). Proven end to end: a blueprint written there makes grok
adopt the role ("I am the RoboCo intake interviewer ... -- intake-1").
write_agents_md() copies /app/system-prompt.md -> ~/.grok/AGENTS.md; the one-shot
render (grok_cli_config.main) and both interactive mains call it. No git pollution
(it lives in ~/.grok, not the workspace), and it covers repo-cwd and /app-cwd
roles alike. Reverted the non-working --system-prompt-override wiring.
* feat(grok): close the Claude-parity divergences (reasoning, subagents, web, bash-guard)
Bring the grok CLI to parity with the Claude path on the four deliberate
differences:
- Reasoning: drop the per-role `--effort low` default — Claude sets no per-role
thinking budget, so grok now uses the model default for every role. The
fleet-wide ROBOCO_GROK_REASONING_EFFORT override stays as a cost lever. (This
also un-caps intake-draft quality, the one that actually mattered.)
- Subagents: the intake interviewer may now fan out to subagents (parity with the
Claude intake's `Task` allowance); every other role still has `Agent` removed.
- Web: `--disable-web-search` for every role — no agent gets direct web (Claude's
tool set has none either); the roles that get web reach it through the gated
roboco-search MCP, unaffected.
- Bash command filtering: full parity, split by deny semantics. Verified live that
a grok PreToolUse hook deny CANCELS the run, while native `--deny` denies
GRACEFULLY (the agent gets a permission error and recovers). So:
* git network/branch/history ops -> native `--deny` (operational reflex; the
agent must recover, not drop the task). Expanded to the full bash-guard set.
* credential-exfil / identity-forgery / internal-API / env-dump patterns ->
the SAME bash-guard the Claude path runs, wired as a grok PreToolUse hook
(ROBOCO_GUARD_SKIP_GIT=1 so it leaves git to `--deny`). A hard cancel is the
right response there — no legitimate agent reads ~/.netrc or forges an
X-Agent-ID. One tolerance line (accept grok's camelCase `toolInput`) makes
the one tested script guard both runtimes; +5 grok cases (50/50 green).
Also cleaned stale internal task-number / smoke labels out of bash-guard-hook.sh.
* fix(grok): install grok CLI to ~/.grok/bin (its real default), not ~/.local/bin
The image build failed at `chown ... /home/agent/.local: No such file or
directory`. The grok installer's default is $HOME/.grok/bin — the binary lands at
~/.grok/bin/grok; ~/.local/bin/grok is only a convenience SYMLINK the installer
creates on macOS but not in the Linux container. So the Dockerfile referenced a
directory that never existed:
- PATH pointed at ~/.local/bin -> `grok` would not be found at runtime even if
the build had passed;
- chown targeted ~/.local -> the build aborted.
Point PATH + chown at ~/.grok/bin / ~/.grok. Also harden the install: download the
script to a file (a `curl | bash` pipe swallows a curl failure as a silent no-op)
and verify the binary installed and runs (`test -x` + `grok --version`), so a
broken install fails the build loudly instead of producing a grok-less image.
* fix(grok): address adversarial-review findings across the grok-CLI conversion
A 7-dimension adversarial review (find -> independently refute) surfaced 14 real
issues; fixed each:
Runtime bugs
- GrokCliSession.send drained stdout fully BEFORE stderr — a >64KB stderr burst
would deadlock the turn forever (spinner never clears). Drain stderr
concurrently, and add a per-turn watchdog (ROBOCO_GROK_TURN_TIMEOUT_SECONDS,
default 600s) that kills a wedged process and emits error+turn_end.
- Crash-restarted grok agents launched `grok -p ""` (empty prompt) — Claude gets
a scan-for-work fallback. Default the prompt in _spawn_container so every
dedicated provider gets it too.
- _grok_usage_json read /data/grok-usage unconditionally while its writers branch
compose-vs-local, so a local-mode agent finalized at $0 and the cost-cap was
inert. Single-source the path in a new _grok_usage_dir helper (read == write).
- GrokCliSession secretary role fell through to "unknown" (get_agent_role returns
a truthy sentinel, never None), defeating the ROBOCO_AGENT_ROLE fallback.
Parity / hardening
- --deny set was missing `git tag -d` / `git reflog delete` that the Claude
bash-guard blocks — added them (the "same set" claim is now true).
- Interactive mains now install the bash-guard hook too (defense-in-depth).
- Compose: collapse the GROK_AUTH_DIR / ROBOCO_HOST_GROK_DIR auth-mount pair into
one canonical var so a partial override can't silently break agent auth.
Docs / comments
- Panel routing card + architecture security doc no longer say Grok runs on the
deleted opencode runtime; orchestrator comments point at the renamed entrypoint.
Tests
- Cover the interactive _render_grok_config MCP wiring (ModuleNotFound guard +
secretary HMAC env), the cost-cap kill-failure + interactive relay-close paths,
the local-mode usage read, the role fallback, the turn timeout, and the new
git denies. (#13 — a separate grok "Write" tool — investigated: grok's only
built-in file-mutation tool is search_replace, already removed; no gap.)
Gate green: ruff, mypy, xenon, tests.
* fix(grok): declare tomli-w as a runtime dependency (agent image needs it)
The grok agent image failed at spawn with `ModuleNotFoundError: No module named
'tomli_w'` when rendering ~/.grok/config.toml. tomli_w was only a transitive dep
of a dev-extra package, so it was present in dev/orchestrator envs but excluded
from the agent image, which builds its venv with `uv sync --frozen --no-dev`.
grok_cli_config imports it at module load to serialize the MCP gateway config, so
without it a Grok agent gets no gateway verbs.
Promote tomli-w to a direct [project.dependencies] entry. Locked with
`--upgrade-package tomli-w` so only tomli-w is added — no incidental churn of the
8 unrelated packages a full re-resolve would have bumped.
* Updated uv.lock
* fix(grok): auto-approve tool execution (--always-approve) so headless agents can call tools
Live smoke caught every grok agent (Main PM, pr-reviewer, dev, …) ending its run
with stopReason=Cancelled and empty output the instant it reached for a tool. Root
cause: headless `grok -p` cannot approve a tool call without `--always-approve`
(grok's docs: required for unattended automation), and the per-role args didn't
pass it — so no agent could call a gateway verb, an edit, or an MCP tool, and the
run was cancelled.
Add `--always-approve` to grok_cli_args_for_role (one place → every role, one-shot
and interactive). Safety is unaffected: `--disallowed-tools` still removes tools
and `--deny` still hard-blocks command patterns regardless of approval (a denied
command returns a permission error and the agent recovers — verified live).
Proven in the rebuilt image side-by-side: without the flag a tool call yields
Cancelled/not-called; with the real rendered args it returns EndTurn and the MCP
tool actually runs. (My earlier in-image tool-calling check passed `--always-approve`
manually, which masked that the production args omitted it — fixed.)
* fix(pr-review): seed claim heartbeat so the grok reviewer isn't wedge-killed
pr_review_claim transitioned a review task pending -> in_progress but never
seeded last_heartbeat_at, unlike every sibling claim path (_finalize_claim,
qa_claim, doc claim). The reaper treats a NULL heartbeat as a stale claim, and
the GROK idle-kill watchdog bypasses the live-container skip on a NULL
heartbeat -- so the reviewer container was killed (Cancelled) before it could
post_pr_review, churning the task back to pending on a respawn loop. A Claude
reviewer was shielded by the live-instance skip; only GROK manifested it.
Seed the heartbeat at claim time, matching the established invariant. Verified
against a real Postgres (10/10 test_pr_review_db tests, incl. the new
last_heartbeat_at assertion).
* fix(grok): stream one-shot output live + capture real token usage
Two gaps the buffered run hid, both verified in the real image with mounted
SuperGrok auth:
- Observability: the entrypoint buffered grok's output to a temp file and only
cat it after the run, so `docker logs` was blank while the agent worked.
Switch the one-shot to --output-format streaming-json piped through tee:
grok flushes each thought/text event incrementally (confirmed token-by-token
live in-container), so the agent's reasoning shows in docker logs in real
time, parity with the Claude stream-json path. Read the session id back from
the NDJSON run log (the terminal `end` event) since -s does not pin it.
- Usage: total_tokens read 0 for every grok run. grok nests the cumulative
totalTokens on params.update._meta, but the reader looked at params._meta
(which only holds event ids); the unit fixture had the same wrong shape, so
the tests masked it. Read the real path (with params._meta / top-level
fallbacks) and fix the fixture to the real grok shape. Verified live:
usage.json now reports total_tokens=3262, cost_usd=0.006524 (was 0).
* fix(grok): validate agent_id before using it as a usage-dir path segment
CodeQL flagged a high-severity py/path-injection: agent_id flowed from
request-facing call sites into _grok_usage_dir() and on to read_text(), so a
value containing '..' or a separator could traverse the filesystem. Validate
agent_id against the slug/uuid allowlist ([A-Za-z0-9_-]+) at the single
chokepoint (_grok_usage_dir feeds both the mount and the finalize read);
anything else raises. Rejects traversal; accepts every real agent slug.
* fix(grok): use explicit-guard path sanitizer CodeQL recognizes as a barrier
The re.fullmatch allowlist from
|
||
|
Renn F
|
1d835ff50f |
chore(release): prepare v0.6.0
Bump the version to 0.6.0 across pyproject, the package, the config, and the panel, and add the 0.6.0 CHANGELOG entry: inbound external/internal PR review with a CEO decision queue and supersede, the panel feature-flags card, the required-cells decomposition gate, the CEO-rejected coordination-root deadlock fix, the panel UI pass, and registry-image deploy. Also refresh the locked dependencies, update the release-tag examples in the README and deployment docs, and correct the package docstring's agent count to 22. |
||
|
Renn F
|
cb7cbb69fa | Update uv.lock | ||
|
Renn F
|
99c2ac5c62 |
docs(changelog): cut RoboCo 0.5.0
Promote the Unreleased section to [0.5.0] - 2026-06-16 — AC/decomposition guardrails, per-dev sequenced code queues, the unified Business page, the 26 panel UI fixes, and the spawn/PR/ownership firefight fixes — and add the 0.5.0 compare link. Correct the Removed note: the /cockpit, /company-goals, /secretary, and /pitches panel routes are deleted (404), not redirected; the relocated strategy signals are served by the new GET /api/cockpit/signals endpoint. Bump the version 0.2.0 -> 0.5.0 across pyproject, __init__, config app_version, panel package.json, and the uv.lock self-entry — these had drifted unbumped since 0.3.0. |
||
|
Renn F
|
128c3cf908 | updated uv.lock | ||
|
|
2aef3c7db5 |
Replace piragi/torch with in-house RAG engine (#168)
* [437e398a] Wave 1A — Remove piragi/torch dependencies entirely (#161) * [437e398a] chore(deps): remove piragi and torch from pyproject.toml and uv.lock - Remove piragi[postgres] from [project.dependencies] - Remove torch entry and its CPU-only comment from [project.dependencies] - Remove [[tool.uv.index]] pytorch-cpu block and [tool.uv.sources] torch override - Remove torch from [tool.deptry.per_rule_ignores] DEP002 - Keep piragi.* in [[tool.mypy.overrides]] ignore_missing_imports so the remaining optimal_brain/ piragi references don't break the mypy gate (Wave 1B will complete that migration) - Regenerate uv.lock: neither piragi nor torch appear in the resolved set * [437e398a] feat(kb): add piragi-free roboco/kb module with Chunk, OllamaEmbedder, shared embedder singleton - roboco/kb/__init__.py: new package entry point; 'import roboco.kb' works without piragi - roboco/kb/ollama_embedder.py: local Chunk dataclass (text/embedding/metadata), full OllamaEmbedder with parallel batch, LRU cache, retry/rate-limit logic - roboco/kb/shared_embedder.py: async singleton factory (OllamaEmbedder only, piragi EmbeddingGenerator branch removed) - All files pass ruff format+check and mypy with zero errors --------- Co-authored-by: Backend Developer 2 <be-dev-2@agents.roboco.dev> * [df01fa23] Replace piragi/torch with in-house RAG engine (#160) * [df01fa23] feat(rag): replace piragi/torch with in-house RAG engine - Remove piragi[postgres] and torch from pyproject.toml dependencies - Delete piragi_patches.py; all piragi.types imports replaced with local types - Add text_chunker.py: character-based sliding-window chunker with local Chunk/Document/Citation dataclasses (no tiktoken, no HuggingFace AutoTokenizer) - Add vector_store.py: VectorStore using asyncpg + pgvector, CREATE TABLE IF NOT EXISTS, ivfflat index, before/after startup timing note in docstring - Rewrite base.py: HyDE in _compute_query_embedding() via Ollama LLM with raw-query fallback; zero references to _sync/_conn/_init_schema/AsyncRagi - Update shared_embedder.py, ollama_embedder.py, code.py, docs.py to import Chunk from text_chunker instead of piragi.types - Refresh uv.lock removing piragi/torch entries - ruff check exits 0; mypy exits 0 on 253 source files; 2301 unit tests pass * [df01fa23] fix(tests): remove piragi stub block from conftest.py and clean up remaining piragi references in tests/ - Replace tests/unit/services/optimal_brain/conftest.py content with a minimal one-line docstring (removes _StubChunker, _ensure_piragi_stubbed, and its module-level call) — satisfies AC#7 explicitly - Remove piragi stub injection block from test_rate_limit_retry.py (_PIRAGI_STUB_NAMES, _stub_piragi(), and the call); also drop unused sys/types imports and now-redundant # noqa: E402 directives - Update _make_journal_plugin() helper to use the new _store/_chunker/_embedder attributes instead of the removed _ragi attribute - Remove dead piragi comment from test_indexes_base.py - All 28 rate-limit tests + 15 optimal_brain tests pass; ruff=0, mypy=0 * [df01fa23] fix(rag): delete piragi_patches.py to satisfy AC2 - file staged for removal --------- Co-authored-by: Backend Developer 1 <be-dev-1@agents.roboco.dev> * fix(rag): VectorStore.close tolerates a closed event loop The in-house engine's asyncpg pool is bound to the loop that created it. The optimal-service singleton can outlive that loop (cross-loop teardown between tests), so pool.close() raised 'RuntimeError: Event loop is closed' — failing test_optimal_grounding in the full suite (the work's first end-to-end gate). Swallow that specific RuntimeError (connections died with the loop); other RuntimeErrors still propagate. +3 unit tests. * fix(rag): validate table identifier + bandit-clean SQL construction bandit flagged B608 (SQL injection) on the in-house VectorStore's f-string queries interpolating the table name. The name is enum-derived (never user input), but the gate runs bandit -ll with skips=[] so it failed. Fix at the root, no nosec: validate the table identifier against a strict allowlist in __init__ (raises on anything unsafe), and inject it via _q()/str.replace (not %/format/f-string/+) so the controlled substitution isn't a B608 vector. Values remain $N bind params. +tests for the identifier guard. --------- Co-authored-by: Backend Developer 2 <be-dev-2@agents.roboco.dev> Co-authored-by: Backend Developer 1 <be-dev-1@agents.roboco.dev> Co-authored-by: Renn F <rennf93@users.noreply.github.com> |
||
|
Renn F
|
1d1ec88aad | chore(release): sync uv.lock to version 0.2.0 | ||
|
|
303c2db289 |
Fix: rate limit real probe (#110)
* fix(rate-limit): real provider liveness probe instead of time-based stub
The rate-limit recovery sweeper cleared a provider and resumed parked agents
purely on elapsed time — _do_probe was a stub that always returned True once
the retry_after window passed, so it never confirmed the provider had actually
stopped rate-limiting us. Under a sustained limit that resumes agents straight
into another 429, re-parking them: avoidable churn.
Make the probe real. _do_probe now issues a free, unmetered liveness call —
Anthropic GET /v1/models or Ollama GET /api/tags — and treats any non-429
response as the limit having lifted. A 429 keeps the provider parked; a
network error keeps it parked too (retry next sweep). When the provider can't
be probed (no API key, or an unrecognized provider), it falls back to the
prior time-expiry optimism rather than stranding agents. _probe_target keeps
URL/header resolution separate and testable, and _do_probe stays a
monkeypatchable boundary so the existing sweep tests are unaffected.
Also drop two acceptance-criteria-number labels from comments in this file.
* chore(rate-limit): clear merged gate debt in rate-limit tests + deps lint
The rate-limit PR landed with ruff violations the full gate flags but the
authors' runs missed: test_rate_limit_sweep.py was unformatted, and
test_rate_limit_tracker.py had unsorted/unused imports and magic-value
comparisons. Format the sweep test, drop the dead imports, and bind the
magic comparison values to locals. Also strip acceptance-criteria-number
labels from comments/docstrings across the three rate-limit test files
(leaving genuine acceptance_criteria=[...] test data untouched), and add
api/deps.py to the PLC0415 per-file-ignore — it is the DI wiring hub and
defers a couple of service imports to call time to avoid import cycles,
the same rationale already applied to api/routes, runtime, and services.
* fix(rate-limit): resolve redis type errors in RateLimitStateTracker
A cold mypy run (the gate's true state — prior passes were warm-cache only)
flagged four redis-typing errors in rate_limit_tracker.py that the merge
missed: three unused type:ignore[type-arg] on redis.Redis, and an
aclose() the bundled redis type stub doesn't expose.
Drop the now-unused ignores, and close the scan client via
'async with redis.from_url(...) as r:' instead of a finally-block
aclose(). The context manager closes the client on exit using the modern
redis.asyncio API — no deprecated close(), no stub-missing aclose(), no
suppression. Extend the test's redis mock to model the async
context-manager protocol so it returns itself on enter.
* test(prompter): pass route='main_pm' in the product main-PM routing test
Pre-existing master failure, unrelated to the rate-limit work. The test is
named ...product_routes_to_main_pm and asserts team=MAIN_PM, but called
confirm_live_draft without a route, so it got the 'board' default — which
assigns the Product Owner and yields team=BOARD by design (the board-review
path keeps the root at team=board until the CEO approves). The Main-PM path
is selected with route='main_pm', exactly as the sibling
...main_pm_route_assigns_main_pm test does. Add the missing kwarg so the test
verifies the path it names; behaviour under test is unchanged.
* Updated uv.lock
* refactor(complexity): bring all rank-C blocks under the xenon B ceiling
The full quality gate's xenon step (--max-absolute B --max-modules A
--max-average A) failed on eight rank-C blocks plus the extraction module
average — debt the rate-limit and token-analytics merges deferred. Reduce
each by extracting cohesive helpers, behaviour unchanged:
- orchestrator._probe_one_provider: split into _too_early_to_probe,
_on_probe_success, _on_probe_failure, _parked_agents_for.
- rate_limit_tracker.list_rate_limited_providers: extract _read_rate_limited_entry
and a _decode helper.
- trigger_filter.decide_spawn: extract _stale_trigger_decision (drops the
PLR0911 suppression too).
- ollama_embedder (embed_query, _embed_batch_sync, aembed_query,
_embed_batch_async): share _rl_backoff / _map_embed_error / _log_429 /
_sleep_connect_retry / _asleep_connect_retry; remove a dead post-loop guard
in aembed_query.
- mentor._synthesize_answer: extract _select_system_prompt and
_answer_from_response.
- indexes/base.ask: extract the 429-retried LLM call into _ask_llm.
- extraction.__init__: extract _compile_patterns so the module average
lands at rank A.
xenon now exits 0; rate-limit, optimal_brain, extraction, and events suites
all green.
* chore(deps): drop obsolete types-redis stub; honor redis 8.0 inline types
types-redis 4.6 (typed for redis 4.x) shadowed redis 8.0's own inline types,
which both masked real annotation mismatches in stream_bus.py and forced
awkward workarounds elsewhere. The stale stub is why the mypy gate only ever
passed warm-cached: a cold run under the wrong stub disagreed with the code.
Remove types-redis (and its orphaned transitive stubs) so mypy uses redis's
shipped types. That surfaces that xreadgroup/xclaim return bytes-keyed records
while _handle_message is annotated str — the code already decodes bytes
defensively, so this is an annotation gap, not a runtime bug. Make the types
honest: cast each result to its concrete shape and decode the stream name and
message id to str at the dispatch boundary via a _to_str helper.
mypy roboco/ is now clean cold (247 files) against redis's real types; events
suite green.
* Updated uv.lock
* fix(workspace): install the dev extra so agents can run make quality
Agent workspaces were set up with plain `uv sync`, which installs only the
project's default dependency group (pytest) — not the `dev` *extra* where the
gate tools live (ruff, mypy, xenon, radon, vulture, bandit, deptry). So an
agent's .venv had pytest but no linters, and `make quality` died immediately
on `ruff: command not found`. Agents literally could not lint, type-check, or
complexity-check their own work, which is how format/mypy/xenon debt merged
unseen. Sync the `dev` extra (`uv sync --extra dev`) so the workspace gets the
full toolchain the setup's own docstring already promised.
* fix(panel): rate-limit endpoint shape + websocket path
Two panel-facing breakages from the rate-limit rework:
- GET /api/system/rate-limits returned a raw list, but the panel store reads
response.entries — so `r.entries is not iterable` crashed the banner sync on
page load. Return the panel's contract: a { entries: [...] } envelope whose
items are camelCase {provider, affectedAgents, hitAt, resumeAt,
retryAfterSeconds}, derived from the raw Redis state (resumeAt = hitAt +
retryAfter).
- The rate-limit websocket hook passed "/ws/system" while getWebSocketUrl()
already supplies the "/ws" base, producing the doubled "/ws/ws/system" URL.
Pass "/system" to match the agents/channels/notifications hooks.
Note: the backend /ws/system endpoint itself does not yet exist (the rework
shipped the panel hook only); the REST fix keeps the banner correct on load
and reconnect until that endpoint is built.
* test(workspace): assert uv sync installs the dev extra
Follow the workspace setup change: the dependency-install command is now
`uv sync --extra dev` so the agent workspace gets the lint/type/complexity
toolchain. Update the three assertions that pinned the old `uv sync`.
* feat(ws): add /ws/system stream and bridge rate-limit events to the panel
The rate-limit rework shipped the panel's websocket hook but no backend: there
was no /ws/system endpoint and nothing forwarded RATE_LIMIT_HIT/LIFTED to a
socket, so the banner got no live updates.
Build the missing half:
- ConnectionManager grows a system-wide connection set with connect_system /
broadcast_system, and disconnect() now clears it.
- A /ws/system websocket endpoint (operator stream, no per-agent keying) with
the same connected + ping/pong lifecycle as the other streams.
- websocket_bridge subscribes RATE_LIMIT_HIT/LIFTED and forwards each to
broadcast_system tagged with the type the panel switches on. Both events
ride the same StreamEventBus singleton, and the subscriptions register
before start_listening(), so the consumer reads their streams.
Pairs with the panel hook now passing '/system' (getWebSocketUrl supplies the
'/ws' base). Covered by handler, manager, and endpoint-lifecycle tests.
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
|
||
|
|
9f8834155a |
Feature: prompter gold upgrade (#84)
* feat(prompter): make the assistant a RoboCo insider and fully wire launch
The Prompter's intelligence lived in two thin static prompts, so it asked
generic checklist questions and produced a flat task. The launch path was
also only half-wired: the panel called the generic task-create endpoint with
no project, bypassing the Prompter's own confirm flow.
Interview brain
- Rewrite the chat system prompt with RoboCo's org model, the task-spec
standard, a dimensions playbook, and a reflect-back, 1-2-questions-per-turn,
auto-stop discipline.
- Inject the live projects/products list each turn so the assistant grounds
questions in real surfaces and resolves the target itself.
- Replace the brittle phrase-match readiness with a parsed roboco-meta control
block (parse_readiness); the block is stripped from the visible reply and the
turn now returns draft_ready + scale.
Structured GOLD draft
- Add first-class draft fields (objective, what_this_builds, the_work, notes)
carried in the existing draft_data JSONB — no migration.
- Compose the GOLD markdown description deterministically from those fields
(compose_description); the model never hand-formats the body.
Adaptive routing + wired launch
- Confirm now runs through the Prompter confirm endpoint with the human's
project/product choice and edited structured draft.
- Single-cell targets a project and the cell team; a multi-cell feature targets
a product and becomes a Main-PM coordination root that fans out.
Frontend
- Turn-envelope draft_ready (drop the duplicated phrase-match), structured
draft card, confirm dialog with a project/product picker and a per-cell
The Work editor, and the corrected priority labels (0 highest .. 3 lowest).
* fix(prompter): commit session writes so they survive across requests
Session create returned 201 but the row was never durably committed, so the
immediately-following /messages call could not find it and 404'd. The prompter
routes were the only write surface that never called db.commit() — every other
write route (tasks, a2a, groups, docs, product) commits explicitly rather than
rely on the request-teardown auto-commit, which is sensitive to middleware and
teardown ordering under the production server.
- Commit explicitly in all four prompter write routes (create session, send
message, get/generate draft, confirm).
- Fix _get_session's NotFoundError: it passed a full sentence as resource_type,
producing the doubled "... not found not found" message; now uses the
(resource_type, resource_id) signature.
- Panel: when a message hits a session the server no longer has, start a fresh
session and retry once instead of dead-ending on a stale id.
Add a regression test that gives each request its own non-committing session —
the real cross-request boundary the shared-session integration tests never
crossed. It reproduces the production 404 without the route commit and passes
with it.
* refactor(prompter): drop the "GOLD" jargon for plain wording
"GOLD" was informal shorthand for "a good/well-formed spec" that should never
have been baked into the LLM prompts, comments, and docstrings as if it were a
defined term. Replace it everywhere with plain language ("a well-formed task",
"a complete task spec", "the markdown description", "structured spec fields").
No behaviour change.
* feat(intake): add the intake interviewer agent role (static definition)
Phase 1 of the intake-agent feature: a new first-class `prompter` role — the
intake interviewer the CEO chats with to draft a task. This commit defines the
role across every foundation layer (no runtime yet); spawning + the live
session come next.
- identity: Role.PROMPTER, RoleLevel.INTAKE (lowest authority), an AGENTS row
(intake-1) on the board team, ROLE_LEVEL entry. Deliberately NOT in
BOARD_ROLES — it interviews, it does not review.
- lifecycle: gets i_am_idle like every agent (its only verb); no
delivery-lifecycle intents.
- journaling: ReadTier.OWN — isolated, reads only its own journal.
- role_config: human-only manifest — note + evidence only, no say/dm/notify/
channels; allows_subagent=True (research), allows_write=False.
- agents_config derives it automatically and correctly excludes it from
TASK_CREATOR_ROLES (it drafts, it never creates tasks).
- seed presentation ("Intake"); regenerated lifecycle artifacts.
- role system prompt: read the code first, single-CEO awareness, propose
rather than interrogate — written against the failures we saw.
- docs: roster count 19 -> 20, org charts, verb-surface table, usage roster.
All foundation drift checks pass; role/manifest/permission tests green.
* feat(intake): migrate agentrole enum to add 'prompter'
ALTER TYPE agentrole ADD VALUE IF NOT EXISTS 'prompter' so the intake agent
row seeds/spawns against a migrated production DB. Forward-only (postgres
can't drop enum values), guarded for offline mode — matches migration 012.
* style(intake): ruff format the role additions
* fix(intake): unguard the agentrole migration so it renders offline
The enum-migration-parity test renders 'alembic upgrade head --sql' (offline)
and greps for ALTER TYPE ... ADD VALUE. The is_offline_mode() guard skipped
emitting it, so the parity check couldn't see 'prompter'. Drop the guard —
PG16 permits ADD VALUE in a transaction, same as migration 020's backfill.
* feat(intake): the live-session driver (Claude Agent SDK loop)
Phase 2 begins. The intake agent isn't a one-shot `claude -p`; it's a live
Claude Code session the human chats with. This driver is the container's loop:
open one long-lived claude-agent-sdk ClaudeSDKClient, then per human message
run a turn (query + receive_response) and stream its events out, keeping
conversation context in-process — verified against the real SDK (v0.2.94).
- StreamChunk + normalize(): map SDK messages (StreamEvent text deltas,
AssistantMessage text/thinking/tool_use blocks, ResultMessage→session_id) to
panel-facing chunks. Duck-typed, so it works on real SDK objects and on test
fakes alike — SDK-free, fully unit-tested.
- IntakeDriver.run(): the loop, with injected session/source/sink seams; a turn
failure surfaces as an error chunk without killing the session.
- SdkIntakeSession + build_intake_options: the only SDK-coupled code (lazy
import; needs the live claude binary, so excluded from coverage).
- Add claude-agent-sdk dependency + mypy ignore-missing-stubs.
Relay, panel SSE, and the persistent on-demand spawn are the next steps.
* Updated uv.lock
* feat(intake): the panel<->agent live bridge (registry, routes, entrypoint, image)
Wires the live intake chat end to end (Phase 2 integration layer):
- prompter_live.py: the orchestrator-side per-session registry — open/close,
push (agent->panel), stream (SSE drain), deliver (panel->container). In-process
(the orchestrator is single-process). 7 unit tests.
- routes/prompter_live.py: GET /live/{id}/stream (SSE), POST /live/{id}/messages
(deliver), POST /live/{id}/events (relay in); registered under /api/prompter.
5 integration tests.
- agent_sdk/intake_main.py: the container entrypoint — a POST /turn receiver
(the driver's MessageSource) + a relay-poster EventSink + the ClaudeSDKClient
session, run concurrently. 4 unit tests on the wiring helpers.
- docker/agent-prompter.Dockerfile: FROM base, ENTRYPOINT = the driver (not the
one-shot `claude` the other agents use).
Remaining for Phase 2: the orchestrator persistent-spawn path (scope->workspace
clone, CMD = driver, registry.open on spawn, reap-on-confirm) — the deploy-side
piece, best finalized against a buildable image.
* feat(intake): orchestrator persistent spawn + start/stop for the live chat
Add the task-free spawn path for the intake (prompter) agent: one fixed
intake-1 container running the Agent-SDK driver (image ENTRYPOINT, not
claude -p), one live session at a time.
- spawn_intake_session clones the scope's repo(s) via WorkspaceService
(project -> one; product -> each distinct project, primary first),
composes the intake-1 prompt, resolves the model, and builds docker run
via _build_intake_run_cmd: no settings/hook mount (driver owns 9000),
no MCP config, no -w; registers the live relay and best-effort delivers
the opening message once the receiver is up.
- reap_intake_session closes the relay and stops the container.
- Routes: POST /live/start (project XOR product) and POST /live/{id}/stop.
- ROLE_MODEL_MAP[prompter]=opus; intake-1 -> roboco-agent-prompter image map.
- Replace the budget-sweep try/except/continue with _fetch_budget_status,
which logs the swallow at debug instead of silently dropping it.
25 new tests; docker + the clone are mocked. End-to-end container spawn is
pending a built image and the stack.
* feat(intake): wire /prompter to the live agent — scope form + SSE chat
Replace the Ollama chat loop on /prompter with the spawned-agent flow.
- IntakeForm: pick scope (project XOR product) + opening message + Start
before the chat; the agent clones that scope and reads the real code.
- use-prompter rewritten as the live brain (lib/api/prompter-live.ts): Start
spawns via POST /live/start, then an EventSource on /live/{id}/stream
streams the agent working — token deltas fill the assistant bubble,
tool_use/thinking drive a live activity line, a draft event renders the
existing DraftProposalCard. Messages go via POST /live/{id}/messages.
- Chat UX unchanged (Keep Chatting / Review & Confirm / ConfirmDialog reused);
reap-on-confirm and reap-on-leave call POST /live/{id}/stop.
- Drop the dead Ollama prompterApi client; trim prompter.ts to shared types.
Frontend gate green (tsc --noEmit, lint, build). The draft event + the
/live/{id}/confirm endpoint are the Phase 4 backend seam.
* feat(intake): confirm draft -> backlog task + agent draft emission
Complete the live intake vertical: the agent proposes a structured draft and
Review & Confirm turns it into a task.
- Draft emission: the prompter prompt instructs the agent to emit a fenced
roboco-draft JSON block when the spec is ready; the driver parses it into a
'draft' event over the existing relay -> the panel's DraftProposalCard. The
panel strips the raw block from the chat bubble.
- Fix a double-text bug: with include_partial_messages the reply arrives as
both StreamEvent deltas and the final AssistantMessage; the driver now takes
text from deltas only and the AssistantMessage for thinking/tool_use/draft.
- POST /live/{id}/confirm -> confirm_live_draft, reusing a draft->task core
extracted from confirm_draft; reaps the session on success.
- Both prompter confirm paths create at BACKLOG, not pending: backlog is the
holding area a draft waits in until it's reviewed and promoted to pending
(TaskService.activate). The legacy Ollama confirm was creating at pending,
skipping that gate — fixed.
- Remove the dead 'context' bootstrap param from the Ollama session-create
chain (schema + route + method + tests), superseded by the live scope form.
- No suppressions: replace every type:ignore/noqa across the intake surface
with a real fix (ORM .id -> UUID(str(x)); fakes -> monkeypatch.setattr;
lazy imports -> pyproject per-file ignore; union-attr -> recipients[0]).
Full make quality green; frontend tsc + lint green.
* build(intake): add the agent-prompter image builder to compose
The orchestrator references roboco-agent-prompter (AGENT_IMAGES + the
_ensure_agent_image dockerfile map) and docker/agent-prompter.Dockerfile
exists, but docker-compose.yml built every other agent image up front and
left this one out — so the image wasn't pre-built for a stack bring-up.
Mirror the other specialized agent-*-image builders: build from
docker/agent-prompter.Dockerfile, tag roboco-agent-prompter, depend on
agent-base-image.
* Created docker-compose.yaml for the NAS
* fix(intake): non-blocking /live/start so spawn never times out
The start POST awaited the whole spawn — workspace clone + first-time image
build + docker run — which blew past the panel's 60s HTTP timeout ('Request
timed out. The server may be busy.') and triggered a duplicate send. Found on
the 2026-06-09 NAS smoke.
- start_intake_session opens the live relay synchronously, then spawns the
container in the background (_spawn_intake_container_guarded). The route
returns the session id immediately; the panel opens the SSE stream right away.
- A background spawn failure is pushed onto the relay as an 'error' event and
closes the session, so the panel shows it instead of hanging.
- spawn_intake_session stays as the synchronous variant for direct callers/tests.
- Panel shows a 'Preparing the agent…' indicator until the first event arrives.
18 intake-spawn tests green; tsc + lint green. E2E re-validates on next smoke.
* fix(intake): propose_draft MCP tool + lock the agent down
Smoke 2026-06-09 exposed two compounding problems: the agent never reliably
emitted the draft (it narrated the spec instead of typing the magic fence), and
it had inherited the CEO's entire Claude Code env — Write/Edit/Bash + Gmail/
Notion/Calendar/Drive MCP — because bypassPermissions ignored the allowlist and
the mounted ~/.claude leaked the host MCP config.
- propose_draft: build_intake_options now registers an in-process SDK MCP tool
(create_sdk_mcp_server + @tool). The agent calls it to submit the draft; the
driver turns that ToolUseBlock into a 'draft' event (_is_propose_draft /
_draft_from_tool_input, tolerant of nested/flat/JSON-string input). The fenced
roboco-draft block stays as a fallback.
- Lockdown: strict_mcp_config=True + setting_sources=[] (ignore host MCP +
settings); permission_mode 'dontAsk' + a can_use_tool gate enforcing a hard
allowlist (Read/Grep/Glob/Task + propose_draft) replaces bypassPermissions.
- Prompt: call propose_draft (not a fence); the draft's downstream chain is
backlog -> Board (PO + HoM) -> CEO approve -> Main PM, and the agent's job ends
at the draft (it never routes or hands off).
SDK API verified against the installed claude-agent-sdk. Driver detection unit-
tested; the SDK-construction is validated on the next NAS smoke (incl. that
setting_sources=[] doesn't break the mounted-~/.claude auth).
* fix(intake): panel UX cluster from the smoke (#3/#4/#6/#12)
- #3 message boundaries: a tool call now ends the current text bubble, so the
agent's words before and after a tool render as separate messages instead of
one merged wall (the 'two waves merged into one bubble' the CEO saw).
- #4 activity indicator: promoted from tiny grey text to a prominent primary-
tinted pill so 'watch it work' is actually visible.
- #12 End chat: a header button (any chat state) reaps the agent and resets to
the form, reusing startAnother (which already stops the session). Backend
POST /live/{id}/stop already existed.
- #6 log noise: the opening-message delivery retry logs at debug, not error —
those failures are expected until the container receiver is up.
- Also fix a latent test gap from the #1 commit: the live-route test's fake
orchestrator now exposes start_intake_session (the route's non-blocking entry).
Frontend tsc + lint green; live-route + prompter_live tests green.
* fix(intake): render markdown in the chat bubbles (#8)
The agent emits rich markdown (### headers, **bold**, tables, lists) but the
bubble rendered raw text, so it was illegible (CEO-flagged on the smoke). Render
assistant content with react-markdown + remark-gfm (GFM tables) in a prose
container. Adds react-markdown + remark-gfm to the panel.
* feat(intake): #14 — two start routes (Board review vs straight to Main PM)
Per the CEO spec, the draft confirm now starts the task at PENDING with an
explicit assignment instead of parking it at backlog:
- route="board" (Board review & Start): assigned to the Product Owner, so the
orchestrator dispatches the full Board review (PO + Head of Marketing) before
the Main PM picks it up.
- route="main_pm" (Approve & Start): assigned straight to the Main PM, who
delegates to the cells (Board review skipped).
create_task_from_draft gains status + assigned_to params (default BACKLOG, so the
legacy confirm_draft is unchanged); confirm_live_draft + the /live/{id}/confirm
request carry the route. Service tests cover both routes.
* feat(intake): #14 draft-card buttons — Board review vs Approve & Start
Three buttons on the draft card now (CEO spec): Keep chatting / Board review &
Start / Approve & Start. The two action buttons confirm directly with their
route — launchTask(route) sends route to POST /live/{id}/confirm, which starts
the task at pending assigned to the Board (PO+HoM) or straight to the Main PM.
Supersedes the ConfirmDialog review step (scope is chosen up front in the form),
so it's removed from the page flow. The ConfirmDialog component + its sub-editors
are now unused — flagged for a follow-up cleanup, left in place to avoid churn.
tsc + lint green.
* fix(intake): keep the live SSE stream bound to its relay session
The orchestrator opened the relay session twice per live chat — once on the
request path (before the start call returns) and again inside the background
container spawn. The SSE stream binds to the session's queue the moment the
panel connects, so the second open swapped in a fresh queue and stranded the
stream: the agent replied normally, but its events went to the new queue while
the panel kept reading the old one, so the chat looked frozen on "Preparing…".
The second open was always redundant (the relay is opened by the caller before
the spawn). Remove it, and make open() idempotent so a live session is never
replaced out from under a stream that is already connected to it.
* fix(intake): draft-card launch buttons silently did nothing
The launch path required a `description` field, but the prompter draft schema
intentionally has none — it sends `objective` + the structured spec and the
backend composes the description (compose_description). `editableDraft.description`
was therefore undefined, so `description.trim()` inside launch validation threw a
TypeError that propagated out of the button's onClick. Clicking "Board review &
Start" / "Approve & Start" did nothing, with no feedback — the wall blocking the
whole confirm → task → reap flow.
- Map a proposed draft's description from `objective` as a fallback.
- Make launch validation null-safe.
- Replace the silent early-return with a toast that names what's missing, so a
blocked launch is never a dead, feedback-less button again.
* fix(intake): steer the agent to ask inline, not via AskUserQuestion
The intake's job is to ask clarifying questions, so it reached for the
AskUserQuestion tool — which isn't wired to the live chat panel and isn't in its
allowlist. The bare deny left it to stumble ("let me clarify… — no worries, let
me just lay it out") and waste a visible turn.
- Prompt: spell out that it asks by writing in the chat (the human reads every
message live) and that no question/prompt tool is available to it.
- Gate: give AskUserQuestion a specific deny message that nudges it to ask inline,
so even a reflex attempt degrades gracefully.
Also refresh the now-stale "what happens after propose_draft" section: the draft
card has three choices (Keep chatting / Board review & Start / Approve & Start)
and produces a pending task — not the old two-button "backlog" description.
* feat(intake): copy buttons on agent messages and the draft card
The CEO asked for a way to save the agent's plan/spec elsewhere "just in case" —
a cheap manual backstop until refresh-durability lands.
- New CopyButton: async Clipboard API when available, plus a legacy
textarea+execCommand fallback. The fallback is load-bearing — the panel is
served over plain http on a LAN IP, where navigator.clipboard is absent
(clipboard needs a secure context), so the modern API alone would never copy.
- Copy button under each assistant message (copies its text).
- Copy button on the draft card (copies the full spec as markdown: title,
objective, what-this-builds, the-work per cell, notes, success criteria).
* feat(intake): unbuffer logs + log each turn so the container isn't a black box
Debugging the intake smoke was painful for two reasons: (a) the orchestrator
block-buffered stdout, so `docker logs` lagged minutes behind reality, and (b)
the intake container logged only "session opened" then went silent for the whole
conversation (the chat streams to the relay, not stdout).
- Set PYTHONUNBUFFERED=1 on the orchestrator and agent-base images so structured
logs reach `docker logs` in real time instead of in large delayed chunks.
- Log each intake turn: "turn received" (with char count) and "turn streamed"
(chunk count + whether a draft was emitted), so the container logs show the
conversation's shape at a glance.
* chore(intake): remove the dead ConfirmDialog draft editor
The three-button draft card (Keep chatting / Board review & Start / Approve &
Start) replaced the old review-modal confirm flow, leaving ConfirmDialog and its
sub-editors (StringListEditor, TheWorkEditor) referenced by nothing but the
barrel export. Remove the three files and the export — typecheck + lint confirm
no remaining references.
* fix(intake): coerce bad draft enums on confirm instead of hard-failing
The intake agent is an LLM and will emit off-enum values — e.g. task_type="feature",
which is not a valid TaskType (code/documentation/research/planning/design/
administrative). `_coerce_draft_enums` called `TaskType(value)` directly, which
raised, and the confirm 400'd with "Draft has invalid or missing required fields:
'feature' is not a valid TaskType". That forced the agent to discover the valid
values and self-correct in-chat — unacceptable: clicking "Approve & Start" must
never blow up on a cosmetic enum guess.
Coerce each enum to a sane default on invalid/missing (task_type→code,
nature→technical, complexity→medium); team falls back to the first valid cell in
the_work, then backend. `_lead_cell_team` now skips invalid cell names too. The
confirm/launch action no longer hard-fails on an enum the model got wrong.
* fix(intake): draft card no longer renders above the user's latest message
attachDraft fell back to "the last assistant message anywhere" when the current
turn had no streamed text yet (propose_draft called first). That last message was
often the PREVIOUS turn's — sitting above the user's "Yes, propose it" — so the
draft card rendered above the user's message. Attach only to the current turn's
streaming message; otherwise append a fresh assistant message so the card always
lands at the bottom of the thread.
* test(intake): guard draft enum coercion + invalid-cell skipping
Regression tests for the confirm-time enum coercion: an off-enum task_type
("feature") / nature / complexity coerce to code/technical/medium instead of
raising, and _lead_cell_team skips invalid cell names. Locks in that a bad enum
guess from the agent can never 400 the launch again.
* fix(intake): stop the agent fumbling through Claude Code meta-tools
In smoke it reflexively probed CC built-ins before reaching propose_draft —
plan mode + ExitPlanMode (it announced a written plan and waited instead of
emitting the draft), ToolSearch, Write — each correctly denied by the lockdown
but stumbly, and it only proposed after explicit CEO nudges.
- Gate: ExitPlanMode now gets a specific deny nudge ("you don't use plan mode;
call propose_draft"), and the generic deny names the actual toolset instead
of a bare "not available", so any probe degrades into guidance.
- Prompt: forbid plan mode/ExitPlanMode/ToolSearch explicitly and spell out
"you do not plan and wait — call propose_draft directly when the spec is
ready," plus an anti-pattern bullet.
* feat(intake): make the container logs transparent mid-turn
`docker logs` on the intake container was a black box: only turn start/end, while
the agent read the codebase and spawned 20+ subagents invisibly (the conversation
streams to the relay, not stdout), and the benign 3x ~/.claude.json warning was
the only thing visible.
- Driver logs each tool call mid-turn ("Intake tool use" with the tool name) and
the draft emission, plus a tools count in the turn-streamed summary. Text deltas
stay unlogged (they'd spam). Now the logs show the turn's real shape.
- Pre-create ~/.claude.json ({}) at container boot so the CLI's "config not found"
warning (printed 3x, self-healed anyway) stops drowning the real logs.
* fix(intake): render markdown in user messages + scope copy to code blocks
Two display fixes from the smoke:
- User messages collapsed newlines (plain {content} in a div) and rendered no
markdown — a "1.\n2.\n3." answer showed as one run-on line. Render user AND
assistant bubbles through a shared GFM markdown body that inherits the bubble's
text color, so lists / newlines / styling render correctly on both.
- Copy was blanketed on every assistant message; scope it to KEY parts — a copy
button on fenced code blocks (the draft card keeps its own). Removed the
per-message button.
* fix(intake): prevent duplicate tasks from a double-click on launch
Clicking a draft launch button twice fired two confirms and created duplicate
tasks. Add a synchronous re-entry guard (a ref — no stale-closure window) at the
top of launchTask so a second click returns immediately, and disable + spin the
draft-card buttons while a launch is in flight so it's visually clear it's working.
* docs(how-to): lead task creation with the Task Assistant flow
Rewrite "1 · It starts with you" to walk the Prompter/Task Assistant path —
scope form, the agent reading the codebase, its grounded analysis, the draft
card, and the created task — then flow into the Board review. Replaces the old
manual task-definition form shots.
Image placeholder: images/prompter_draft_card.png (the 3-button card) is
referenced but not yet captured — TODO comment marks it for the next smoke run.
A second comment flags an optional re-capture of prompter_run_2 after the
markdown-rendering fix.
* fix(intake): restore assistant message text contrast
The markdown refactor dropped `dark:prose-invert` and made text inherit the
bubble's color, but the assistant bubble had no explicit text color — so its text
rendered near-invisible (dark-on-dark on bg-muted). Give the assistant bubble an
explicit text-foreground; the user bubble already carries text-primary-foreground,
and [&_*]:!text-inherit now resolves to a readable color on both.
* fix(intake): coerce draft priority too — confirm 500'd on priority="high"
The enum-coercion fix covered task_type/nature/complexity/team, but priority is a
non-enum int field handled by `int(draft_data.get("priority", 2))`, and the agent
guesses a word ("high") as readily as a number — so int("high") raised ValueError
and the confirm 500'd. Same class of bug, one field missed.
Add _coerce_priority: map words (urgent/high/medium/low → 0/1/2/3), clamp numbers
to 0-3, default to 2 (medium) on anything else. The launch can no longer crash on
any field the LLM guessed. + regression test.
* fix(intake): draft card shows distinct cells, not one badge per work item
the_work has one entry per work item, so a cell with several items rendered its
badge repeatedly ("Board-led across Backend Backend Backend Frontend Frontend
…"). De-dupe to distinct teams so the card reads "Board-led across Backend
Frontend" — and the "Cell:" vs "Board-led across" label keys off distinct count.
* docs(how-to): hero the teaser gif + resolve the Prompter/Task Assistant thread
- Move the 12s teaser gif to the top as the hero — it was buried between the
"prefer video" link and the first screenshot.
- Name the connection: the Task Assistant IS the Prompter, so section 1 (using
the tool) and the rest (RoboCo building it) read as one story — you use the
tool the company built for itself, then watch the build.
- Re-anchor the section 1 → Board transition to follow the Prompter's own
journey, instead of implying section 1's example task is the one reviewed next.
* Included images for how-to.md
* docs(how-to): align agent count to 20 (matches README + CLAUDE.md)
The how-to said "18 agents" with UX/UI at one dev and no Intake — stale against
the authoritative count. Bump 18→20 (prose + spelled-out eighteen→twenty), give
UX/UI 2 devs, and add the Intake line to the org tree (Intake leads section 1, so
it belongs in the tree). README + CLAUDE.md already say 20.
* ci(release): publish all RoboCo images to GHCR + Docker Hub
The release published only the orchestrator to GHCR. Build and push the full set
the stack needs — agent-base, the 8 agent images, orchestrator, and panel — to
BOTH ghcr.io/rennf93/* and docker.io/renzof93/*, at :<version> and :latest, so
consumers can pull instead of compose-building.
- agent-base builds first (the agent images build FROM roboco-agent-base, a local
tag), then the rest; push only after every build succeeds.
- Image names mirror the docker-compose `image:` values 1:1.
- Free disk on the runner first (11 images is space-heavy).
- Needs a DOCKERHUB_TOKEN repo secret for the Docker Hub login.
- SECURITY.md updated to reference both registries.
* ci(release): use short SHA as the image tag on manual dispatch
A workflow_dispatch runs against a branch, and the branch name (e.g.
feature/prompter-gold-upgrade) was used verbatim as the image tag — but "/" is
illegal in a Docker tag, so the first build failed instantly with "invalid
reference format". Releases still tag from the release tag; manual dispatch now
always uses the short SHA, which is a valid tag.
---------
Co-authored-by: Renn F <rennf93@users.noreply.github.com>
|
||
|
|
3205443119 |
Fix: dependency spawn gate and cell ownership (#73)
* Cleanup + Missing greenlet error * fix(messaging): persist a group's active-session pointer so posts reuse it create_session and create_session_with_access_check set group.active_session_id from session.id BEFORE the flush that materializes it — the id is a flush-time uuid4 default, so the pointer was written as NULL and every post opened a fresh session, fragmenting one conversation across many. Flush first, then link, the same ordering the seed path already uses. Two tests fabricated "two distinct sessions" by calling create_session twice on one group, which only differed because of this bug; switch them to two groups so they keep testing their real intent. Add a regression guard that the pointer is actually persisted and a second create reuses the live session. * fix(orchestrator): gate spawns on dependencies and keep cell tasks in their cell The cross-task dependency check ran only on the dev dispatch path, so cell-PM, Main-PM and board agents were spawned onto dependency-blocked tasks and flailed unblock / escalate / notify against an unfinished upstream — climbing ownership of cell work up to the board, which cannot drive it, and deadlocking the task. - Move the dependency gate into the shared spawn readiness check so it covers every role, and auto-block the task so it leaves the pending pool until the upstream reaches a terminal state (then the existing auto-unblock revives it). - Cell-ownership invariant: a backend/frontend/ux_ui task may only be worked or owned by its own cell. The readiness gate refuses a board or Main-PM spawn onto a cell task; reassign refuses and clears such an owner; and on dependency-clear a mis-owned cell task is re-homed to its cell's pending pool instead of reviving under an owner that cannot progress it. - A dependency block is never a CEO signal: notify(target=ceo) is refused while the task is waiting on an unfinished upstream, with a remediate to idle and wait — the block clears on its own. * Uploading images + Fixing pyproject.toml * ++ * revert(orchestrator): drop the cell-ownership block pending a tooling audit The cell-ownership invariant added earlier — a board / Main-PM role may never be spawned onto or reassigned to a cell task, plus re-homing a mis-owned cell task on dependency-clear — was too absolute. It forbids a higher role from stepping in when something genuinely deeper is going on, and contradicts the existing rule that main_pm may hold a task at awaiting_pm_review. The dependency spawn gate already prevents the cascade that handed the board cell tasks; the deadlock it guarded against will be addressed with a return-path approach after auditing what tools the cell PMs actually need. Keeps the dependency gate and the CEO dependency-block notify guard. * docs(prompts): a dependency wait is wait-and-idle, not escalate The cell-PM and Main-PM prompts told agents to escalate_up / retry unblock on a blocked task without distinguishing a dependency wait (which auto-clears the moment the upstream completes) from a real wedge — the source of the escalate/unblock flail and the CEO-notification spam. Split the blocked-state guidance: a cross-cell dependency wait = note + i_am_idle (do not escalate, unblock, or notify the CEO); escalate only a genuinely broken upstream. Fix two stale references to i_am_blocked, a developer-only verb the PMs do not have, to escalate_up. Correct the CLAUDE.md verb-surface table, which understated every role: it listed 4 cell_pm verbs while the flow manifest derives the full set (11, including unclaim and i_am_idle) from lifecycle.spec.intents_for_role. * feat(gateway): cell_pm reassign verb — intra-cell developer hand-off A cell PM can now hand a claimed/in_progress task to another developer in its own cell without unclaim (which drops the work back to the pool and loses the assignee). The branch is keyed to the task, so the work-in-progress is preserved; the new dev is respawned to continue. Intra-cell only: the task must be in the caller's cell and new_assignee must be a developer of that same cell. Wired through every layer: the reassign IntentSpec (composes=(), cell_pm-only), the choreographer verb + intra-cell guard, a reaper-safe TaskService.reassign_active_claim (reseeds the claim heartbeat so the new dev is not immediately reaped), the ReassignRequest schema, the cell_pm flow route, and the MCP flow-server tool. Tracing-waived like unclaim (mechanical hand-off). Regenerated lifecycle/verb artifacts; prompt + CLAUDE.md updated. --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com> |