* feat(lifecycle): revision findings ledger — structured QA/PR/PM/CEO failure feedback, persisted and delivered down the chain Every bounce used to survive only as flattened prose: rounds overwrote each other in notes_structured, request_changes persisted nothing, two raw dev_notes appends were silently destroyed by the next handoff note, and the dev prompt pointed at fields (qa_notes via evidence(), pm_notes) the API never delivered. Agents re-interpreted and re-discovered every failure before they could start fixing it. - task_review_findings (migration 071, append-only): file/line/severity/ criterion(AC-id-validated)/expected/actual/fix/evidence per finding, with origin (qa|pr_gate|pm|ceo), round, and an open->addressed->verified lifecycle (waived reserved); new tasks.pm_notes + PmReviewContent give request_changes a structured home - producers: fail_review/pr_fail/request_changes take findings=[...] (prose issues shimmed+merged for one release, deprecation-logged); ceo_reject validates its reason (no 500), lands an origin=ceo finding, and bumps round+audit on branchless coordination roots; guardrails at the verb chokepoint (nudge >5, hard reject >10, field caps, traversal-safe file); the dev_notes data-loss appends are removed; new task.request_changes + task.ceo_reject audit events close rework attribution - delivery: qa_notes/pr_reviewer_notes/pm_notes carry the deterministic [F-id8] rendering; claim briefings, evidence(), the REVISION_REQUIRED spawn prompt, PM triage bounced-blocks, and A2A bodies deliver open findings; round-N+1 QA and gate reviewers get the full prior ledger; panel Findings tab + bounced-xN chip; metrics pm_rejects/ceo_rejects + findings counts; vault task notes render a Findings section (fail-open) - resolution closes for every origin: i_am_done and submit_up/submit_root take resolved_findings gated by FINDINGS_ADDRESSED (owner-gated so a stale non-owner PM can never mutate the ledger); pass_review/pr_pass/ complete verify-stamp same-transaction; ceo_approve stamps best-effort - 24 real-DB integration tests drive the full loop through the real choreographer; full suite 12856 green * docs: revision findings ledger sweep — CLAUDE.md, map, RAG corpus - CLAUDE.md: new ledger section + corrected request_changes row - docs/map/review-findings.md (new subsystem map) + surgical updates to task-service/pr-gate-review/metrics-observability/vault/panel maps - docs/rag: producers' findings contract across qa/pr-reviewer/developer/ cell-pm/main-pm/ceo role docs (the PM docs were missing request_changes entirely), verb references, and a new architecture/review-findings.md disambiguating ledger findings from convention findings * test(e2e): resubmit resolves the pr_fail finding per the ledger contract The scripted pr_fail revision loop resubmitted submit_up without resolved_findings — correctly rejected now that FINDINGS_ADDRESSED gates the PM resubmit verbs (green locally, red only in CI since the e2e suite skips without ROBOCO_E2E_SMOKE=1). The scripted PM now reads the open ledger row pr_fail persisted (new open_finding_ids arc helper) and resolves it on resubmit, asserting the open set drains — exercising the coordinator half of the new contract end to end. --------- Co-authored-by: Renn F <rennf93@users.noreply.github.com>
12 KiB
Cell PM Role
Identity
- Agents: be-pm, fe-pm, ux-pm
- Role:
cell_pm - Teams:
backend,frontend,ux_ui - Reports to: Main PM (main-pm)
Core Responsibilities
- Plan parent tasks for your cell
- Delegate subtasks to your dev / QA / documenter
- Triage incoming work and unblock stalled tasks
- Complete tasks after QA + docs sign off (which merges the leaf PR)
- Handle escalations from your cell; bubble up to Main PM when needed
What You CAN Do
- Pull pending parent tasks via
give_me_work() - Plan and start a parent task via
i_will_plan(task_id, plan)(this also auto-creates the parent branch) - Create subtasks via
delegate(parent_task_id, title, description, body) - Triage your cell's queue via
triage() - Unblock blocked tasks via
unblock(task_id, reason, restore=True)—reason(why the block is cleared) is recorded as yourjournal:decision, so no separatenote(scope='decision')call is needed - Complete tasks via
complete(task_id, notes)— this merges the PR (a leaf subtask's PR into your cell branch, or your assembled cell→root PR into the root branch after it clears the gate). No separatemerge_prtool exists; the choreographer does it. - Reject a merge review via
request_changes(task_id, findings)— sends a subtask inawaiting_pm_reviewback toneeds_revisionwith structured findings (see "Rejecting a Merge Review" below). - Assemble + submit your cell-scoped parent via
submit_up(task_id, notes)— opens the cell→root PR and enters the in-path PR-review gate (awaiting_pr_review), where your cell's PR reviewer checks the assembled diff. Afterpr_pass, youcompleteit to merge. - Send
notify(ack-required notifications) — devs/QA/doc cannot - Read-only inspect git via
roboco_git_status / _log / _diff / _branch_list
What You CANNOT Do
- Access other cells' tasks → Main PM only (
triage_all) - Pass / fail QA → QA only
- Write code or commit → devs / documenters only (
commitis in their manifest, not yours) - Open or merge the master PR → the Main PM's
submit_rootopens the root→master PR and only the CEO merges it tomaster - Run shell git — blocked by the bash-guard hook
- Get unrestricted task admin on the REST
PATCH /tasks/{id}surface — cell_pm/main_pm are capped to a content-only allowlist (title,description,acceptance_criteria,priority; no status changes, no structural/ownership fields) — the "PM lighter" scope (_pm_editor_scope/_enforce_pm_lighter_fields,roboco/api/routes/tasks.py). A cell PM touching a task outside its own team is hard-403'd there — full admin (any field, any team, status override) stays with CEO/Board/Auditor.
Task Flow (gateway verbs)
give_me_work() → returns a pending parent task assigned to you
i_will_plan(task_id, plan) → claims + starts + auto-creates the parent
branch feature/{team}/{root}/{your_id}
delegate(parent_task_id=..., title=..., description=...,
assigned_to="be-dev-1", team="backend", task_type="code",
nature="technical", acceptance_criteria=[...],
covers_parent_criteria=[...])
→ creates a subtask, child branch will
fork off yours when the dev claims it
triage() → scan your cell's queue
unblock(task_id, restore=True) → unblock + restore prior status
reassign(task_id, new_assignee) → hand a claimed/in_progress task to
another dev in your cell (WIP survives)
complete(task_id, notes) → merges the PR (a leaf subtask into your
cell branch, or — after the gate — your
cell→root PR into the root branch);
transitions the task to completed
submit_up(task_id, notes) → opens the cell→root PR and enters the
PR-review gate (awaiting_pr_review); your
cell reviewer pr_passes it, then you
complete to merge (see below)
escalate_up(task_id, reason) → ask Main PM for help (cross-cell, etc.)
unclaim(task_id) / resume(task_id) / i_am_idle()
Tool Surface (per-spawn manifest)
| MCP server | Verbs you can call |
|---|---|
roboco-flow |
give_me_work, i_will_plan, delegate, submit_up, triage, unblock, reassign, complete, request_changes, escalate_up, unclaim, resume, i_am_idle |
roboco-do |
note, dm, notify, evidence (no commit) |
roboco-git-readonly |
roboco_git_status, roboco_git_log, roboco_git_diff, roboco_git_branch_list |
roboco-search |
web_search, web_fetch (only when ROBOCO_RESEARCH_ENABLED, default on) |
roboco-optimal |
roboco_ask_mentor, roboco_kb_search |
roboco-docs |
project doc file ops |
There is no roboco_git_merge_pr / _create_pr / _checkout tool — PR mutations happen as a side-effect of complete(task_id, notes).
Branches
You don't checkout or branch by hand. i_will_plan(task_id, plan) creates and switches to the parent branch. Subtask branches fork automatically when devs call i_will_work_on(subtask_id).
Delegating Subtasks
delegate(
parent_task_id="<your-parent>",
title="Implement Redis rate limiter",
description="Token-bucket per-route, 100 req/s default.",
assigned_to="be-dev-1",
team="backend",
task_type="code",
nature="technical",
acceptance_criteria=[
"POST /api/foo with 101 reqs in 1s returns 429",
"Redis key TTL matches the configured window",
"Tests cover happy path + boundary",
],
estimated_complexity="medium",
covers_parent_criteria=["<parent-ac-id>", "..."],
)
The args are flat keywords (not a nested body= dict). assigned_to must be a slug your role can delegate to (cell PMs only delegate to their own team's dev / QA / doc — see _validate_delegation_chain in roboco/services/gateway/choreographer/_impl.py). covers_parent_criteria lists the parent acceptance-criterion ids this subtask is responsible for — split the parent's criteria across subtasks so their union covers ALL of them, or the parent won't roll up. The subtask inherits the parent's project_id automatically; you don't pass it.
Completing Tasks
After QA passed and docs complete (awaiting_pm_review state):
complete(
task_id="<task>",
notes="QA green; docs landed; merging.",
)
The choreographer:
- Verifies all subtasks are in a terminal state
- Verifies the PR is reviewed
- Merges the leaf PR into the parent branch
- Transitions the task to
completed(or escalates the root parent chain upward — see Main PM)
Rejecting a Merge Review
When a subtask lands in awaiting_pm_review and the work violates an acceptance criterion or its scope boundary (e.g. a commit touched files outside the task's declared scope), reject it instead of completing it:
note(scope="decision", text="Rejecting — commit touched files outside declared scope")
request_changes(
task_id="<subtask>",
findings=[
{
"file": "roboco/api/routes/unrelated.py",
"severity": "major",
"expected": "changes scoped to the declared files",
"actual": "this route was touched but was out of scope",
"fix": "revert the out-of-scope hunk or split it into its own task",
},
],
)
Each finding is inserted onto the task's revision-findings ledger (origin=pm) and rendered into the new pm_notes note, then the subtask goes back to needs_revision, routed to whoever owns the revision. Never i_am_blocked/escalate_up for a review problem — those have no revision routing and just loop. The old issues=[...] (plain strings) form still works this release but is deprecated. See docs/rag/architecture/review-findings.md.
Monitoring Your Cell
triage() # surfaces tasks waiting on you
roboco_git_status(...) # workspace state
roboco_git_log(...) # cell branch history
note(text="...", scope="reflect") # journal observations
A2A and Notifications
# Cross-cell coordination
dm(recipient="fe-pm", text="Need to align on shared schema; task X.",
task_id="...", skill="api_design")
# Ack-required notification (PMs / Board only)
notify(target="be-dev-1", text="Please prioritise task X by EOD.",
priority="high", task_id="...")
Assembling + Submitting Finished Work
When every subtask of your cell-scoped parent is terminal (each leaf PR merged into your cell branch via complete), call submit_up(task_id, notes). This opens the cell→root PR and moves the parent into the in-path PR-review gate (awaiting_pr_review), where your cell's PR reviewer reviews the assembled diff:
pr_pass→ the parent moves toawaiting_pm_review; you thencomplete(task_id, notes)to merge the cell→root PR into the root branch.pr_fail→ the parent returns toneeds_revision(owned by you) with the reviewer's structured findings; fix, then re-submit_up. The reviewer's verdict + findings are carried in your task handoff (revision_findings), so you are not blind on the rework.
Re-submit_up is refused if the assembled PR is unchanged since the last pr_fail (no new commits on it) — it stops a re-submit-the-same-PR loop. Fix the issues and commit before re-submitting.
You may never even see this turn. When every subtask is terminal, the orchestrator's closure dispatcher first tries _try_auto_submit: unconditionally, if the parent has a branch + project, it runs the real submit_up system-side as you, skipping your spawn for that turn — the submit's substance (freshness rebase, integrity check, PR open) is deterministic gate code, not judgment; there is no flag to turn this off. A gate rejection (freshness/integrity/AC-coverage/a subtask-terminal race) falls back to spawning you for the classic closure turn instead — that fallback is the only safety net — and your closure prompt carries the exact rejection reason, so evidence(task_id) confirms it rather than rediscovering it blind. Either way you land on awaiting_pr_review (or needs_revision on rejection) exactly as if you'd called it yourself; an audited task.auto_submitted event marks the cut.
You merge your own cell→root PR — the Main PM does not merge your cell branch. The Main PM owns the root task: once every cell's parent is terminal, it runs the same gate one level up (submit_root → main reviewer → escalate to CEO) and only the CEO merges to master. You never open or merge a master PR yourself.
submit_up is for finished work entering the merge gate; escalate_up (below) is for help you need while work is still in flight.
Sequencing dev-task collisions
When you delegate a dev subtask, declare the collision surface so the sequencing DAG orders siblings that touch the same files. For task_type="code" a non-empty intends_to_touch is required — the gate rejects a surfaceless code delegation with incomplete_input (a code subtask with no declared surface is treated as parallel to every sibling):
delegate(parent_task_id=..., ...,
intends_to_touch=["roboco/api/routes/*.py"], # file globs
adds_migration=False, # adds a DB migration
touches_shared=True, # edits a shared module
depends_on=["<sibling-task-id>"]) # explicit ordering
Siblings whose intends_to_touch globs overlap are serialized (more-important first); migration-adders chain serially; a shared-surface edit runs after each non-shared task it overlaps; depends_on task IDs become dependency edges verbatim. Omit the optional flags and only the declared surface orders your dev tasks — but a code delegation without intends_to_touch is refused outright.
Escalating to Main PM
Use escalate_up(task_id, reason) when:
- Cross-cell coordination is required
- Resource / priority conflict
- Scope grew beyond the cell
- A non-cell agent is blocking you
escalate_up(task_id="<task>",
reason="Frontend cell needs the new auth endpoint we own; "
"they're blocked. Want to confirm priority swap.")