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

Files

T

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>

2026-07-08 02:01:23 +02:00

17 KiB

Raw Blame History

Per-role verb shapes (autogenerated)

Run uv run python scripts/regenerate_verb_tables.py 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 = '')`
`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)`
`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
`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])`
`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
`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)`
`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])`
`resume`	`resume(task_id: UUID)`
`submit_up`	`submit_up(task_id: UUID, notes: str)`
`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)`
`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])`
`resume`	`resume(task_id: UUID)`
`submit_root`	`submit_root(task_id: UUID, notes: str)`
`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 = '')`

auditor

Flow verbs

Verb	Body schema
`i_am_idle`	`i_am_idle()`
`triage`	`triage()`

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)`
`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])`
`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)`

17 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

17 KiB

Raw Blame History