mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
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.
259 lines
8.9 KiB
Python
259 lines
8.9 KiB
Python
"""Gate Set E: submit-qa field-level gates in Choreographer.i_am_done.
|
|
|
|
Pre-gateway location: roboco/api/routes/tasks.py:903-940 (route layer).
|
|
The four field-level gates returned 400 errors when the dev tried to
|
|
submit for QA without:
|
|
|
|
- NOT_SELF_VERIFIED: task.self_verified must be true.
|
|
- NO_COMMITS: task.commits must be non-empty.
|
|
- NO_PR: task.pr_number must be set.
|
|
- NO_PROGRESS: task.progress_updates must have at least one entry.
|
|
|
|
The gateway's i_am_done previously called _run_catch_up which silently
|
|
auto-ran the full chain. That hid the missing-commits failure mode
|
|
(catch-up tried to push nothing, opened an empty PR, etc.).
|
|
|
|
Now i_am_done is strict and tells the dev exactly which prerequisite
|
|
is missing. A separate i_am_done_with_catchup verb retains the smart-
|
|
catch-up behavior for the explicit-opt-in case.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
from roboco.services.gateway.choreographer import Choreographer, ChoreographerDeps
|
|
|
|
|
|
def _make_deps(**overrides: Any) -> ChoreographerDeps:
|
|
base: dict[str, Any] = {
|
|
"task": AsyncMock(),
|
|
"work_session": AsyncMock(),
|
|
"git": AsyncMock(),
|
|
"a2a": AsyncMock(),
|
|
"journal": AsyncMock(),
|
|
"audit": AsyncMock(),
|
|
"evidence_repo": AsyncMock(),
|
|
}
|
|
base.update(overrides)
|
|
repo = base["evidence_repo"]
|
|
for method in (
|
|
"list_unread_a2a",
|
|
"list_unread_mentions",
|
|
"list_pending_notifications",
|
|
"task_metadata_gaps",
|
|
"recent_team_activity",
|
|
"blockers_in_lane",
|
|
"journal_highlights_for_task",
|
|
):
|
|
getattr(repo, method).return_value = []
|
|
return ChoreographerDeps(**base)
|
|
|
|
|
|
def _ready_task(task_id: Any, agent_id: Any) -> MagicMock:
|
|
"""Build a task that satisfies tracing AND field-level gates."""
|
|
return MagicMock(
|
|
id=task_id,
|
|
status="in_progress",
|
|
assigned_to=agent_id,
|
|
plan={"x": 1},
|
|
branch_name="feature/backend/abc--def",
|
|
work_session_id=uuid4(),
|
|
self_verified=True,
|
|
pr_number=8,
|
|
pr_url="https://x/pr/8",
|
|
team="backend",
|
|
progress_updates=[{"message": "did x"}],
|
|
acceptance_criteria=["AC1"],
|
|
acceptance_criteria_status=[
|
|
{"criterion": "AC1", "referencing_artifact_id": "c1"}
|
|
],
|
|
commits=[{"sha": "abc"}],
|
|
documents=[],
|
|
dev_notes="",
|
|
)
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# E.1 self_verified is no longer a gate (audit P1-3/D-08)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
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
|
|
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"] is None
|
|
task_svc.submit_verification.assert_awaited_once()
|
|
task_svc.submit_qa.assert_awaited_once()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# E.2 NO_COMMITS
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_i_am_done_blocks_when_no_commits() -> None:
|
|
agent_id = uuid4()
|
|
task_id = uuid4()
|
|
t = _ready_task(task_id, agent_id)
|
|
t.commits = []
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = t
|
|
journal_svc = AsyncMock()
|
|
journal_svc.has_reflect_for_task.return_value = True
|
|
deps = _make_deps(task=task_svc, journal=journal_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 "NO_COMMITS" in body["missing"] or "commits" in body["missing"]
|
|
task_svc.submit_qa.assert_not_awaited()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# E.3 NO_PR
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_i_am_done_blocks_when_no_pr() -> None:
|
|
agent_id = uuid4()
|
|
task_id = uuid4()
|
|
t = _ready_task(task_id, agent_id)
|
|
t.pr_number = None
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = t
|
|
journal_svc = AsyncMock()
|
|
journal_svc.has_reflect_for_task.return_value = True
|
|
deps = _make_deps(task=task_svc, journal=journal_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 "NO_PR" in body["missing"] or "pr_number" in body["missing"]
|
|
task_svc.submit_qa.assert_not_awaited()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# E.4 NO_PROGRESS
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_i_am_done_blocks_when_no_progress() -> None:
|
|
agent_id = uuid4()
|
|
task_id = uuid4()
|
|
t = _ready_task(task_id, agent_id)
|
|
t.progress_updates = []
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = t
|
|
journal_svc = AsyncMock()
|
|
journal_svc.has_reflect_for_task.return_value = True
|
|
deps = _make_deps(task=task_svc, journal=journal_svc)
|
|
c = Choreographer(deps)
|
|
|
|
env = await c.i_am_done(agent_id, task_id, "done")
|
|
body = env.as_dict()
|
|
assert body["error"] == "tracing_gap"
|
|
# progress>=1 is the existing tracing_gate Requirement key.
|
|
assert "progress>=1" in body["missing"] or "NO_PROGRESS" in body["missing"]
|
|
task_svc.submit_qa.assert_not_awaited()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# E.5 happy path: all gates pass → submit_qa runs (NO catch-up)
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
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"},
|
|
)
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = t
|
|
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
|
|
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, "all done")
|
|
body = env.as_dict()
|
|
assert body["error"] is None
|
|
assert body["status"] == "awaiting_qa"
|
|
task_svc.submit_qa.assert_awaited_once()
|
|
# Already-verifying status: no auto-call to submit_verification.
|
|
task_svc.submit_verification.assert_not_awaited()
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# 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_blocks_unauthorized() -> None:
|
|
"""Existing not_authorized check still applies."""
|
|
agent_id = uuid4()
|
|
other_id = uuid4()
|
|
task_id = uuid4()
|
|
t = _ready_task(task_id, other_id)
|
|
task_svc = AsyncMock()
|
|
task_svc.get.return_value = t
|
|
deps = _make_deps(task=task_svc)
|
|
c = Choreographer(deps)
|
|
|
|
env = await c.i_am_done(agent_id, task_id, "done")
|
|
body = env.as_dict()
|
|
assert body["error"] == "not_authorized"
|