mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
fix(gateway): unblock task claim; full Phase 0/1/2 remediation
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.
This commit is contained in:
@@ -78,28 +78,44 @@ def _ready_task(task_id: Any, agent_id: Any) -> MagicMock:
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# E.1 NOT_SELF_VERIFIED
|
||||
# E.1 self_verified is no longer a gate (audit P1-3/D-08)
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_i_am_done_blocks_when_not_self_verified() -> None:
|
||||
async def test_i_am_done_auto_runs_submit_verification_when_in_progress() -> None:
|
||||
"""Strict i_am_done auto-runs submit_verification (in_progress→verifying)
|
||||
so the dev doesn't need a separate verb. The previous NOT_SELF_VERIFIED
|
||||
gate required submit_for_verification which wasn't on any manifest.
|
||||
"""
|
||||
agent_id = uuid4()
|
||||
task_id = uuid4()
|
||||
t = _ready_task(task_id, agent_id)
|
||||
t.self_verified = False
|
||||
t.status = "in_progress"
|
||||
after_verify = MagicMock(
|
||||
**{**t.__dict__, "self_verified": True, "status": "verifying"}
|
||||
)
|
||||
after_submit = MagicMock(**{**after_verify.__dict__, "status": "awaiting_qa"})
|
||||
task_svc = AsyncMock()
|
||||
task_svc.get.return_value = t
|
||||
task_svc.submit_verification.return_value = after_verify
|
||||
task_svc.submit_qa.return_value = after_submit
|
||||
task_svc.qa_agent_for_team.return_value = MagicMock(
|
||||
id=uuid4(), skills=[{"id": "code_review"}]
|
||||
)
|
||||
journal_svc = AsyncMock()
|
||||
journal_svc.has_reflect_for_task.return_value = True
|
||||
deps = _make_deps(task=task_svc, journal=journal_svc)
|
||||
work_svc = AsyncMock()
|
||||
work_svc.files_changed.return_value = ["foo.py"]
|
||||
deps = _make_deps(task=task_svc, journal=journal_svc, work_session=work_svc)
|
||||
c = Choreographer(deps)
|
||||
|
||||
env = await c.i_am_done(agent_id, task_id, "done")
|
||||
body = env.as_dict()
|
||||
assert body["error"] == "tracing_gap"
|
||||
assert "NOT_SELF_VERIFIED" in body["missing"] or "self_verified" in body["missing"]
|
||||
task_svc.submit_qa.assert_not_awaited()
|
||||
assert body["error"] is None
|
||||
task_svc.submit_verification.assert_awaited_once()
|
||||
task_svc.submit_qa.assert_awaited_once()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -188,6 +204,11 @@ async def test_i_am_done_proceeds_when_all_gates_pass() -> None:
|
||||
agent_id = uuid4()
|
||||
task_id = uuid4()
|
||||
t = _ready_task(task_id, agent_id)
|
||||
# Pre-verifying state (caller already ran submit_for_verification or
|
||||
# task is already in `verifying`). i_am_done skips the auto-verify
|
||||
# step and goes straight to submit_qa.
|
||||
t.status = "verifying"
|
||||
t.self_verified = True
|
||||
after_submit = MagicMock(
|
||||
**{**t.__dict__, "status": "awaiting_qa"},
|
||||
)
|
||||
@@ -209,61 +230,17 @@ async def test_i_am_done_proceeds_when_all_gates_pass() -> None:
|
||||
assert body["error"] is None
|
||||
assert body["status"] == "awaiting_qa"
|
||||
task_svc.submit_qa.assert_awaited_once()
|
||||
# Strict path must NOT call submit_verification, push, or create_pr —
|
||||
# those are catch-up side effects which are now opt-in only.
|
||||
# Already-verifying status: no auto-call to submit_verification.
|
||||
task_svc.submit_verification.assert_not_awaited()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# E.6 i_am_done_with_catchup retains the smart-catch-up convenience.
|
||||
# E.6 — Removed: i_am_done_with_catchup verb deleted (audit P2-5/D-16).
|
||||
# Its functionality is now split between submit_for_qa (push + PR) and
|
||||
# i_am_done (auto-run submit_verification then submit_qa).
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_i_am_done_with_catchup_runs_full_chain() -> None:
|
||||
agent_id = uuid4()
|
||||
task_id = uuid4()
|
||||
initial = _ready_task(task_id, agent_id)
|
||||
initial.self_verified = False
|
||||
initial.pr_number = None
|
||||
after_verify = MagicMock(
|
||||
**{**initial.__dict__, "self_verified": True, "status": "verifying"}
|
||||
)
|
||||
after_pr_refresh = MagicMock(
|
||||
**{**after_verify.__dict__, "pr_number": 8, "pr_url": "https://x/pr/8"}
|
||||
)
|
||||
after_submit = MagicMock(**{**after_pr_refresh.__dict__, "status": "awaiting_qa"})
|
||||
task_svc = AsyncMock()
|
||||
task_svc.get.side_effect = [initial, after_pr_refresh]
|
||||
task_svc.submit_verification.return_value = after_verify
|
||||
task_svc.submit_qa.return_value = after_submit
|
||||
task_svc.qa_agent_for_team.return_value = MagicMock(
|
||||
id=uuid4(), skills=[{"id": "code_review"}]
|
||||
)
|
||||
work_svc = AsyncMock()
|
||||
work_svc.has_unpushed_commits.return_value = True
|
||||
work_svc.files_changed.return_value = ["foo.py"]
|
||||
git_svc = AsyncMock()
|
||||
git_svc.create_pr.return_value = {"pr_number": 8, "pr_url": "https://x/pr/8"}
|
||||
journal_svc = AsyncMock()
|
||||
journal_svc.has_reflect_for_task.return_value = True
|
||||
deps = _make_deps(
|
||||
task=task_svc,
|
||||
journal=journal_svc,
|
||||
work_session=work_svc,
|
||||
git=git_svc,
|
||||
)
|
||||
c = Choreographer(deps)
|
||||
|
||||
env = await c.i_am_done_with_catchup(agent_id, task_id, "all done")
|
||||
body = env.as_dict()
|
||||
assert body["error"] is None
|
||||
assert body["status"] == "awaiting_qa"
|
||||
task_svc.submit_verification.assert_awaited_once()
|
||||
git_svc.push_branch.assert_awaited_once()
|
||||
git_svc.create_pr.assert_awaited_once()
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_i_am_done_blocks_unauthorized() -> None:
|
||||
"""Existing not_authorized check still applies."""
|
||||
|
||||
Reference in New Issue
Block a user