mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
Renn F
4829f93a68
Resolves the 100% claim-failure rate introduced by the gateway rewrite
(commit 62bda0c plus 78 follow-ups). Live smoke runs hit
`404 /api/v2/flow/developer/...` on every dev verb plus a manifest
fallback that silently exposed off-role verbs to PMs — confirmed
firing simultaneously in NAS agent logs (be-dev-1, be-pm, main-pm).
Audit reports under docs/internal/audit_2026_05_04/ catalogue 49
defects across gateway, services, prompts, MCP transport, substrate,
and tests (8 detail reports + master synthesis). Six smoking guns;
three proven in production logs.
Phase 0 — unblock claim:
- URL prefix /api/v2/flow/dev → /developer; slug-map board roles
(product_owner, head_marketing) → /board (D-01)
- _i_will_work_on AttributeError on None across pending /
needs_revision / claimed re-entry branches (D-02)
- Seed last_heartbeat_at in _qa_or_doc_claim (D-03)
- Drop misleading i_have_committed verb; dev flow uses commit() (D-04)
- Manifest mount via compose; flow_server + do_server fail loud
instead of exposing all-verbs fallback (D-12)
- MCP _post() surfaces envelope body on 4xx so agents see remediate
hints (D-13)
on git failure so retries aren't blocked by half-state (S-01)
Phase 1 — lifecycle stability:
- _resolve_skill falls back to AgentTable.capabilities (D-06)
- main_pm_complete uses kwargs for escalate_to_ceo (D-07)
- i_am_done auto-runs submit_verification when in_progress (D-08)
- active_claimant_id wired in claim/unclaim paths — single-claimant
invariant now functional (D-05)
- qa_pass/qa_fail assert claimed_by parity with qa_agent_id (D-18)
- Prompt-drift sweep: fail() shape, i_am_done(task_id, notes),
subtask cap (12 hard / 8 soft), error-code symbology rewritten in
base.md + per-role anti-patterns (D-10/11/29/30/31, D-37)
Phase 2 — invariants + architecture:
- Real-DB integration test exercising claim → in_progress → commit
→ submit_for_qa → i_am_done → awaiting_qa (P2-1)
- choreographer.py → package; 3 of 6 role mixins extracted
(board, doc, qa). _impl.py 2,526 → 2,080 lines (-18%). Continuation
plan in docs/internal/audit_2026_05_04/p2_2_decompose_plan.md (P2-2)
- Closure guards consolidated via _subtasks_not_terminal_envelope (P2-3)
- TaskService.unclaim_for_reaper routed through canonical
_validate_and_set_status; in_progress → pending added to
VALID_TRANSITIONS (P2-4)
- Dead code removed: i_am_done_with_catchup verb, _run_catch_up helper
(P2-5)
- 6 state-machine invariants asserted via property test (P2-6)
- attempt_id (uuid4) stamped on every gateway.rejected audit row (P2-7)
- _reconcile_orphan_claims_on_startup rolls back tasks left CLAIMED
with branch_name=NULL from prior crashes (P2-8)
- scripts/regenerate_verb_tables.py introspects Pydantic schemas +
role_config; compose_prompt injects per-role tables as a layer.
Eliminates the prompt-drift class structurally (P2-9)
Other:
- D-48: orchestrator mounts host's ~/.claude.json when present so
agents don't boot from backup recovery on every spawn
- D-49: dev dispatcher rejects role-mismatched spawns (e.g. doc task
assigned to dev agent)
Tests: 553 pass · ruff + mypy clean. Live NAS smoke verification
pending — needs the stack brought back up.
214 lines
6.4 KiB
Python
214 lines
6.4 KiB
Python
"""Choreographer hot verbs must touch last_heartbeat_at via task.heartbeat()."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
from roboco.services.gateway.choreographer import Choreographer, ChoreographerDeps
|
|
|
|
|
|
def _make_deps(**overrides: AsyncMock) -> ChoreographerDeps:
|
|
task = overrides.get("task", AsyncMock())
|
|
work_session = overrides.get("work_session", AsyncMock())
|
|
git = overrides.get("git", AsyncMock())
|
|
a2a = overrides.get("a2a", AsyncMock())
|
|
journal = overrides.get("journal", AsyncMock())
|
|
audit = overrides.get("audit", AsyncMock())
|
|
evidence_repo = overrides.get("evidence_repo", AsyncMock())
|
|
for method in (
|
|
"list_unread_a2a",
|
|
"list_unread_mentions",
|
|
"list_pending_notifications",
|
|
"task_metadata_gaps",
|
|
"recent_team_activity",
|
|
"blockers_in_lane",
|
|
):
|
|
getattr(evidence_repo, method).return_value = []
|
|
return ChoreographerDeps(
|
|
task=task,
|
|
work_session=work_session,
|
|
git=git,
|
|
a2a=a2a,
|
|
journal=journal,
|
|
audit=audit,
|
|
evidence_repo=evidence_repo,
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_i_will_work_on_calls_heartbeat() -> None:
|
|
aid = uuid4()
|
|
tid = uuid4()
|
|
pending = MagicMock(
|
|
id=tid,
|
|
status="pending",
|
|
plan=None,
|
|
assigned_to=None,
|
|
parent_task_id=None,
|
|
sequence=0,
|
|
task_type="code",
|
|
)
|
|
in_progress = MagicMock(
|
|
id=tid, status="in_progress", plan={"text": "go"}, assigned_to=aid
|
|
)
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = pending
|
|
task_svc.agent_for.return_value = MagicMock(role="developer", team="backend")
|
|
task_svc.list_in_progress_for_agent.return_value = []
|
|
task_svc.list_paused_for_agent.return_value = []
|
|
task_svc.get_subtasks.return_value = []
|
|
task_svc.claim.return_value = MagicMock(
|
|
id=tid, status="claimed", plan=None, assigned_to=aid
|
|
)
|
|
task_svc.set_plan.return_value = MagicMock(
|
|
id=tid, status="claimed", plan={"text": "go"}, assigned_to=aid
|
|
)
|
|
task_svc.start.return_value = in_progress
|
|
deps = _make_deps(task=task_svc)
|
|
c = Choreographer(deps)
|
|
|
|
await c.i_will_work_on(aid, tid, plan="go")
|
|
|
|
task_svc.heartbeat.assert_awaited_with(tid)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_i_am_done_calls_heartbeat() -> None:
|
|
aid = uuid4()
|
|
tid = uuid4()
|
|
t = MagicMock(
|
|
id=tid,
|
|
status="verifying",
|
|
assigned_to=aid,
|
|
plan="x",
|
|
self_verified=True,
|
|
commits=[MagicMock()],
|
|
pr_number=42,
|
|
pr_url="http://example/pr/42",
|
|
team="backend",
|
|
work_session_id=None,
|
|
)
|
|
submitted = MagicMock(
|
|
id=tid,
|
|
status="awaiting_qa",
|
|
assigned_to=None,
|
|
plan="x",
|
|
team="backend",
|
|
work_session_id=None,
|
|
pr_url="http://example/pr/42",
|
|
)
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = t
|
|
task_svc.submit_qa.return_value = submitted
|
|
task_svc.qa_agent_for_team.return_value = None
|
|
journal_svc = AsyncMock()
|
|
journal_svc.has_reflect_for_task.return_value = True
|
|
evidence_repo = AsyncMock()
|
|
for method in (
|
|
"list_unread_a2a",
|
|
"list_unread_mentions",
|
|
"list_pending_notifications",
|
|
"task_metadata_gaps",
|
|
"recent_team_activity",
|
|
"blockers_in_lane",
|
|
):
|
|
getattr(evidence_repo, method).return_value = []
|
|
evidence_repo.journal_highlights_for_task.return_value = []
|
|
deps = _make_deps(task=task_svc, journal=journal_svc, evidence_repo=evidence_repo)
|
|
c = Choreographer(deps)
|
|
|
|
# Patch tracing_gate to pass — _check_tracing_gates uses
|
|
# check_requirements, which inspects the Mock's progress_updates etc.
|
|
# By configuring t with all-required attrs we let the real gate pass.
|
|
t.progress_updates = [MagicMock()]
|
|
t.acceptance_criteria = []
|
|
|
|
await c.i_am_done(aid, tid, "done")
|
|
|
|
task_svc.heartbeat.assert_awaited_with(tid)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_i_am_blocked_calls_heartbeat() -> None:
|
|
aid = uuid4()
|
|
tid = uuid4()
|
|
t = MagicMock(id=tid, status="in_progress", assigned_to=aid)
|
|
blocked = MagicMock(id=tid, status="blocked", assigned_to=aid)
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = t
|
|
task_svc.escalate.return_value = blocked
|
|
journal_svc = AsyncMock()
|
|
deps = _make_deps(task=task_svc, journal=journal_svc)
|
|
c = Choreographer(deps)
|
|
|
|
await c.i_am_blocked(aid, tid, "stuck on X")
|
|
|
|
task_svc.heartbeat.assert_awaited_with(tid)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_pm_give_me_work_calls_heartbeat_when_returning_task() -> None:
|
|
pm_id = uuid4()
|
|
tid = uuid4()
|
|
assigned = MagicMock(id=tid, status="pending")
|
|
task_svc = AsyncMock()
|
|
task_svc.list_assigned_for_agent.return_value = [assigned]
|
|
deps = _make_deps(task=task_svc)
|
|
c = Choreographer(deps)
|
|
|
|
await c.pm_give_me_work(pm_id)
|
|
|
|
task_svc.heartbeat.assert_awaited_with(tid)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_pm_give_me_work_does_not_heartbeat_on_idle() -> None:
|
|
pm_id = uuid4()
|
|
task_svc = AsyncMock()
|
|
task_svc.list_assigned_for_agent.return_value = []
|
|
deps = _make_deps(task=task_svc)
|
|
c = Choreographer(deps)
|
|
|
|
await c.pm_give_me_work(pm_id)
|
|
|
|
task_svc.heartbeat.assert_not_awaited()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_i_will_plan_calls_heartbeat() -> None:
|
|
pm_id = uuid4()
|
|
tid = uuid4()
|
|
pending = MagicMock(
|
|
id=tid,
|
|
status="pending",
|
|
plan=None,
|
|
assigned_to=None,
|
|
parent_task_id=None,
|
|
sequence=0,
|
|
task_type="planning",
|
|
)
|
|
in_progress = MagicMock(
|
|
id=tid, status="in_progress", plan="plan-text", assigned_to=pm_id
|
|
)
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = pending
|
|
task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
|
|
task_svc.list_in_progress_for_agent.return_value = []
|
|
task_svc.list_paused_for_agent.return_value = []
|
|
task_svc.get_subtasks.return_value = []
|
|
task_svc.claim.return_value = MagicMock(
|
|
id=tid, status="claimed", plan=None, assigned_to=pm_id
|
|
)
|
|
task_svc.set_plan.return_value = MagicMock(
|
|
id=tid, status="claimed", plan="plan-text", assigned_to=pm_id
|
|
)
|
|
task_svc.start.return_value = in_progress
|
|
deps = _make_deps(task=task_svc)
|
|
c = Choreographer(deps)
|
|
|
|
await c.i_will_plan(pm_id, tid, plan="plan-text")
|
|
|
|
task_svc.heartbeat.assert_awaited_with(tid)
|