mirror of https://github.com/rennf93/roboco.git synced 2026-08-03 07:23:24 +02:00

Files

T

e9ca7d4036 Delegation detail-fidelity + PM-loop hardening (#541 )

* feat(gateway): delegation detail-fidelity — details survive hand-off, both directions

Details thinned out at every delegation hop: a PM child task mapped to no
parent criterion was legal (coverage only surfaced at submit_up, after the
whole wave ran — a 12-subtask docs tree grew through 8 review rounds that
way, one child titled 'docs page and route wrapper' shipping only the
page), and QA could pass work on a gestalt read (a 4-scene video brief
shipped 3 scenes past every gate because the features existed only in
prose). Three chokepoint gates:

- delegate (down): every child must declare covers_parent_criteria
  resolving against the parent's real acceptance criteria — no mapping or
  an unresolvable ref rejects naming every offending child and the valid
  criteria; the success envelope carries parent_ac_coverage
  {covered, uncovered} so a wave-planning PM sees remaining gaps in the
  same turn. Full coverage stays enforced at submit_up (waves stay legal).
- pass_review (up): mandatory criteria_verified — one {criterion,
  evidence} entry per task AC, matched by the findings ledger's
  id-or-exact-text matcher, evidence soup-checked and capped; rejects
  naming the unverified criteria; entries render deterministically into
  qa_notes as '[AC] <criterion> — verified: <evidence>' lines. The old
  count-only ac_verdicts gate is superseded (arg kept for back-compat).
- video briefs (structured detail at origination): an enumerable feature
  list (release highlights, or input_props.highlights carried onto a
  reject re-author) becomes its own scene acceptance criterion, bounded to
  the AC caps; a re-author without highlights carries the
  feedback-addressed criterion instead.

Extracted findings.py's criterion matcher into shared unmatched_criteria /
uncovered_acceptance_criteria instead of duplicating it; criteria_verified
joins the WAF free-text exclusion set like findings/issues.

* fix(gateway): break the block/unblock wedge — four hardening fixes from the live PM loop

A cell task looped fe-pm/main-pm block/unblock for hours (10 cycles, 43
spawns): a transient GitHub API error resolving CI became an unwaivable
blocker finding whose own fix text said no code change was required, the
submit freshness guard then demanded a commit no finding called for,
escalate_up auto-blocked, and main-pm's correct recovery plan 422'd on
the approach length cap, degrading it to a bare unblock. Four fixes:

- pr_pass CI-unresolvable refusal is now explicitly transient-worded:
  retry pr_pass shortly, do NOT pr_fail over a CI-status lookup error —
  a platform blip is not a code finding
- submit freshness guard grants ONE unchanged-head resubmission per
  head sha when the findings ledger has zero open rows (all addressed
  without code changes) — stamped via the resubmit_unchanged_head
  marker so the same head can never loop a second time
- unblock carries a flip breaker: block_flip_count marker, and at the
  third flip a one-shot CEO notification flags the task as structurally
  wedged (unblock itself still succeeds — the breaker signals, it does
  not wedge recovery)
- i_will_plan's approach cap truncates at 800 chars instead of
  rejecting — an over-detailed plan must never cost the PM its turn

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>

2026-07-17 01:52:33 +02:00

18 KiB

Raw Blame History

Per-role verb shapes (autogenerated)

Run make foundation-check after changing any role config or schema. Role prompts reference this file's sections as the source of truth for verb signatures.

Driver-based roles (prompter, secretary) are intentionally omitted — their real tools live in their agent_sdk drivers, not role_config.

developer

Flow verbs

Verb	Body schema
`give_me_work`	`give_me_work()`
`i_am_blocked`	`i_am_blocked(task_id: UUID, reason: str, blocker_type: str
`i_am_done`	`i_am_done(task_id: UUID, notes: str = '', resolved_findings: list[ResolvedFindingInput] = PydanticUndefined)`
`i_am_idle`	`i_am_idle()`
`i_will_work_on`	`i_will_work_on(task_id: UUID, plan: str
`open_pr`	`open_pr(task_id: UUID)`
`resume`	`resume(task_id: UUID)`
`sync_branch`	`sync_branch(task_id: UUID, stash: bool = False)`
`unclaim`	`unclaim(task_id: UUID)`

Content (do) tools

Tool	Body schema
`commit`	`commit(message: str, files: list[str]
`note`	`note(text: str, scope: str = 'note', task_id: UUID
`dm`	`dm(recipient: str, text: str, task_id: UUID
`evidence`	`evidence(task_id: UUID)`
`progress`	`progress(task_id: UUID, message: str, plan_step: str
`pr_update`	`pr_update(see do_server)`
`draft_playbook`	`draft_playbook(title: str, problem: str, procedure: str, tags: list[str] = PydanticUndefined, source_task_id: UUID
`propose_video`	`propose_video(composition_id: str, x_caption: str, tiktok_caption: str, platforms: list[str], input_props: str
`request_sandbox`	`request_sandbox(services: list[str]
`request_render`	`request_render(composition_id: str
`notify_list`	`notify_list(unread_only: bool = True, pending_ack_only: bool = False, limit: int = 20)`
`notify_get`	`notify_get(notification_id: UUID)`
`notify_ack`	`notify_ack(notification_id: UUID)`
`read_messages`	`read_messages()`
`read_a2a`	`read_a2a(see do_server)`

qa

Flow verbs

Verb	Body schema
`claim_review`	`claim_review(task_id: UUID)`
`fail_review`	`fail_review(task_id: UUID, issues: list[str] = PydanticUndefined, findings: list[str
`give_me_work`	`give_me_work()`
`i_am_blocked`	`i_am_blocked(task_id: UUID, reason: str, blocker_type: str
`i_am_idle`	`i_am_idle()`
`pass_review`	`pass_review(task_id: UUID, notes: str, ac_verdicts: list[str]
`resume`	`resume(task_id: UUID)`
`unclaim`	`unclaim(task_id: UUID)`

Content (do) tools

Tool	Body schema
`note`	`note(text: str, scope: str = 'note', task_id: UUID
`dm`	`dm(recipient: str, text: str, task_id: UUID
`evidence`	`evidence(task_id: UUID)`
`draft_playbook`	`draft_playbook(title: str, problem: str, procedure: str, tags: list[str] = PydanticUndefined, source_task_id: UUID
`request_sandbox`	`request_sandbox(services: list[str]
`request_render`	`request_render(composition_id: str
`notify_list`	`notify_list(unread_only: bool = True, pending_ack_only: bool = False, limit: int = 20)`
`notify_get`	`notify_get(notification_id: UUID)`
`notify_ack`	`notify_ack(notification_id: UUID)`
`read_messages`	`read_messages()`
`read_a2a`	`read_a2a(see do_server)`

documenter

Flow verbs

Verb	Body schema
`claim_doc_task`	`claim_doc_task(task_id: UUID)`
`give_me_work`	`give_me_work()`
`i_am_blocked`	`i_am_blocked(task_id: UUID, reason: str, blocker_type: str
`i_am_idle`	`i_am_idle()`
`i_documented`	`i_documented(task_id: UUID, notes: str, files: list[str])`
`resume`	`resume(task_id: UUID)`
`unclaim`	`unclaim(task_id: UUID)`

Content (do) tools

Tool	Body schema
`commit`	`commit(message: str, files: list[str]
`note`	`note(text: str, scope: str = 'note', task_id: UUID
`dm`	`dm(recipient: str, text: str, task_id: UUID
`evidence`	`evidence(task_id: UUID)`
`progress`	`progress(task_id: UUID, message: str, plan_step: str
`pr_update`	`pr_update(see do_server)`
`draft_playbook`	`draft_playbook(title: str, problem: str, procedure: str, tags: list[str] = PydanticUndefined, source_task_id: UUID
`notify_list`	`notify_list(unread_only: bool = True, pending_ack_only: bool = False, limit: int = 20)`
`notify_get`	`notify_get(notification_id: UUID)`
`notify_ack`	`notify_ack(notification_id: UUID)`
`read_messages`	`read_messages()`
`read_a2a`	`read_a2a(see do_server)`

cell_pm

Flow verbs

Verb	Body schema
`complete`	`complete(task_id: UUID, notes: str)`
`declare_coverage`	`declare_coverage(task_id: UUID, criteria: list[str])`
`delegate`	`delegate(parent_task_id: UUID, title: str, description: str, assigned_to: str, team: str, task_type: str, nature: str, estimated_complexity: Complexity, acceptance_criteria: list[str], project_id: UUID
`escalate_up`	`escalate_up(task_id: UUID, reason: str)`
`give_me_work`	`give_me_work()`
`i_am_idle`	`i_am_idle()`
`i_will_plan`	`i_will_plan(task_id: UUID, plan: str, approach: str, sub_tasks: list[SubTaskCreate] = PydanticUndefined, technical_considerations: list[str] = PydanticUndefined, risks: list[RiskCreate] = PydanticUndefined, open_questions: list[OpenQuestionCreate] = PydanticUndefined)`
`reassign`	`reassign(task_id: UUID, new_assignee: str)`
`request_changes`	`request_changes(task_id: UUID, issues: list[str] = PydanticUndefined, findings: list[str
`resume`	`resume(task_id: UUID)`
`submit_up`	`submit_up(task_id: UUID, notes: str, resolved_findings: list[ResolvedFindingInput] = PydanticUndefined)`
`triage`	`triage()`
`unblock`	`unblock(task_id: UUID, reason: str, restore: bool = True)`
`unclaim`	`unclaim(task_id: UUID)`

Content (do) tools

Tool	Body schema
`note`	`note(text: str, scope: str = 'note', task_id: UUID
`dm`	`dm(recipient: str, text: str, task_id: UUID
`notify`	`notify(target: str, text: str, priority: str = 'normal', task_id: UUID
`evidence`	`evidence(task_id: UUID)`
`pr_update`	`pr_update(see do_server)`
`draft_playbook`	`draft_playbook(title: str, problem: str, procedure: str, tags: list[str] = PydanticUndefined, source_task_id: UUID
`notify_list`	`notify_list(unread_only: bool = True, pending_ack_only: bool = False, limit: int = 20)`
`notify_get`	`notify_get(notification_id: UUID)`
`notify_ack`	`notify_ack(notification_id: UUID)`
`read_messages`	`read_messages()`
`read_a2a`	`read_a2a(see do_server)`

main_pm

Flow verbs

Verb	Body schema
`complete`	`complete(task_id: UUID, notes: str)`
`declare_coverage`	`declare_coverage(task_id: UUID, criteria: list[str])`
`delegate`	`delegate(parent_task_id: UUID, title: str, description: str, assigned_to: str, team: str, task_type: str, nature: str, estimated_complexity: Complexity, acceptance_criteria: list[str], project_id: UUID
`escalate_to_ceo`	`escalate_to_ceo(task_id: UUID, reason: str)`
`escalate_up`	`escalate_up(task_id: UUID, reason: str)`
`give_me_work`	`give_me_work()`
`i_am_idle`	`i_am_idle()`
`i_will_plan`	`i_will_plan(task_id: UUID, plan: str, approach: str, sub_tasks: list[SubTaskCreate] = PydanticUndefined, technical_considerations: list[str] = PydanticUndefined, risks: list[RiskCreate] = PydanticUndefined, open_questions: list[OpenQuestionCreate] = PydanticUndefined)`
`request_changes`	`request_changes(task_id: UUID, issues: list[str] = PydanticUndefined, findings: list[str
`resume`	`resume(task_id: UUID)`
`submit_root`	`submit_root(task_id: UUID, notes: str, resolved_findings: list[ResolvedFindingInput] = PydanticUndefined)`
`triage`	`triage()`
`triage_all`	`triage_all()`
`unblock`	`unblock(task_id: UUID, reason: str, restore: bool = True)`
`unclaim`	`unclaim(task_id: UUID)`

Content (do) tools

Tool	Body schema
`note`	`note(text: str, scope: str = 'note', task_id: UUID
`dm`	`dm(recipient: str, text: str, task_id: UUID
`notify`	`notify(target: str, text: str, priority: str = 'normal', task_id: UUID
`evidence`	`evidence(task_id: UUID)`
`pr_update`	`pr_update(see do_server)`
`draft_playbook`	`draft_playbook(title: str, problem: str, procedure: str, tags: list[str] = PydanticUndefined, source_task_id: UUID
`notify_list`	`notify_list(unread_only: bool = True, pending_ack_only: bool = False, limit: int = 20)`
`notify_get`	`notify_get(notification_id: UUID)`
`notify_ack`	`notify_ack(notification_id: UUID)`
`read_messages`	`read_messages()`
`read_a2a`	`read_a2a(see do_server)`

product_owner

Flow verbs

Verb	Body schema
`escalate_to_ceo`	`escalate_to_ceo(task_id: UUID, reason: str)`
`i_am_idle`	`i_am_idle()`
`triage`	`triage()`

Content (do) tools

Tool	Body schema
`note`	`note(text: str, scope: str = 'note', task_id: UUID
`pitch`	`pitch(title: str, slug: str, problem: str, proposed_solution: str, target_cells: list[str])`
`dm`	`dm(recipient: str, text: str, task_id: UUID
`notify`	`notify(target: str, text: str, priority: str = 'normal', task_id: UUID
`evidence`	`evidence(task_id: UUID)`
`notify_list`	`notify_list(unread_only: bool = True, pending_ack_only: bool = False, limit: int = 20)`
`notify_get`	`notify_get(notification_id: UUID)`
`notify_ack`	`notify_ack(notification_id: UUID)`
`read_messages`	`read_messages()`
`read_a2a`	`read_a2a(see do_server)`
`propose_roadmap`	`propose_roadmap(cycle_goal: str, items: list[RoadmapItemInput])`

head_marketing

Flow verbs

Verb	Body schema
`escalate_to_ceo`	`escalate_to_ceo(task_id: UUID, reason: str)`
`i_am_idle`	`i_am_idle()`
`triage`	`triage()`

Content (do) tools

Tool	Body schema
`note`	`note(text: str, scope: str = 'note', task_id: UUID
`pitch`	`pitch(title: str, slug: str, problem: str, proposed_solution: str, target_cells: list[str])`
`dm`	`dm(recipient: str, text: str, task_id: UUID
`notify`	`notify(target: str, text: str, priority: str = 'normal', task_id: UUID
`evidence`	`evidence(task_id: UUID)`
`notify_list`	`notify_list(unread_only: bool = True, pending_ack_only: bool = False, limit: int = 20)`
`notify_get`	`notify_get(notification_id: UUID)`
`notify_ack`	`notify_ack(notification_id: UUID)`
`read_messages`	`read_messages()`
`read_a2a`	`read_a2a(see do_server)`
`propose_feature_spotlight`	`propose_feature_spotlight(feature_slug: str = '', feature_title: str = '', body: str = '', wants_video: bool = False, video_script: str = '', skip: bool = False, skip_reason: str = '')`

auditor

Flow verbs

Verb	Body schema
`i_am_idle`	`i_am_idle()`
`triage`	`triage()`
`waive_finding`	`waive_finding(finding_id: UUID, note: str)`

Content (do) tools

Tool	Body schema
`note`	`note(text: str, scope: str = 'note', task_id: UUID
`evidence`	`evidence(task_id: UUID)`
`approve_playbook`	`approve_playbook(playbook_id: UUID)`
`reject_playbook`	`reject_playbook(playbook_id: UUID, reason: str)`
`archive_playbook`	`archive_playbook(playbook_id: UUID)`
`curate_vault`	`curate_vault(task_id: UUID, narrative: str)`
`notify_list`	`notify_list(unread_only: bool = True, pending_ack_only: bool = False, limit: int = 20)`
`notify_get`	`notify_get(notification_id: UUID)`

pr_reviewer

Flow verbs

Verb	Body schema
`claim_gate_review`	`claim_gate_review(task_id: UUID)`
`claim_pr_review`	`claim_pr_review(task_id: UUID)`
`give_me_work`	`give_me_work()`
`i_am_idle`	`i_am_idle()`
`post_pr_review`	`post_pr_review(task_id: UUID, body: str, event: str = 'REQUEST_CHANGES', findings: list[str
`pr_fail`	`pr_fail(task_id: UUID, issues: list[str] = PydanticUndefined, findings: list[str
`pr_pass`	`pr_pass(task_id: UUID, notes: str)`
`unclaim`	`unclaim(task_id: UUID)`

Content (do) tools

Tool	Body schema
`note`	`note(text: str, scope: str = 'note', task_id: UUID
`evidence`	`evidence(task_id: UUID)`
`notify_list`	`notify_list(unread_only: bool = True, pending_ack_only: bool = False, limit: int = 20)`
`notify_get`	`notify_get(notification_id: UUID)`

18 KiB Raw Blame History

Per-role verb shapes (autogenerated)

developer

Flow verbs

Content (do) tools

qa

Flow verbs

Content (do) tools

documenter

Flow verbs

Content (do) tools

cell_pm

Flow verbs

Content (do) tools

main_pm

Flow verbs

Content (do) tools

product_owner

Flow verbs

Content (do) tools

head_marketing

Flow verbs

Content (do) tools

auditor

Flow verbs

Content (do) tools

pr_reviewer

Flow verbs

Content (do) tools

18 KiB

Raw Blame History