Files
roboco/tests/unit/api/routes/v2/test_flow_dev.py
T
Renn F 4829f93a68 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.
2026-05-04 23:43:55 +02:00

157 lines
4.9 KiB
Python

"""Unit tests for /api/v2/flow/developer/* endpoints.
Uses a minimal FastAPI test client built from the new router only.
No DB required — Choreographer is mocked.
"""
from __future__ import annotations
from unittest.mock import AsyncMock, MagicMock
from uuid import uuid4
import pytest
from fastapi import FastAPI
from fastapi.testclient import TestClient
from roboco.api.deps import get_choreographer
from roboco.api.routes.v2.flow_dev import router
_HTTP_200 = 200
_HTTP_422 = 422
_AGENT_ID = str(uuid4())
_TASK_ID = str(uuid4())
_HEADERS = {"X-Agent-ID": _AGENT_ID, "X-Agent-Role": "developer"}
def _make_envelope(status: str = "ok", task_id: str | None = None) -> MagicMock:
"""Return a mock Envelope whose as_dict() returns a predictable payload."""
env = MagicMock()
env.as_dict.return_value = {"status": status, "task_id": task_id, "next": "..."}
return env
def _build_app(mock_choreographer: MagicMock) -> FastAPI:
"""Build minimal FastAPI app with the flow_dev router and a mocked dep."""
app = FastAPI()
app.include_router(router)
app.dependency_overrides[get_choreographer] = lambda: mock_choreographer
return app
@pytest.mark.asyncio
async def test_give_me_work_returns_envelope() -> None:
"""POST /api/v2/flow/developer/give_me_work returns 200 with envelope shape."""
mock_chore = MagicMock()
mock_chore.give_me_work = AsyncMock(return_value=_make_envelope(status="idle"))
client = TestClient(_build_app(mock_chore))
resp = client.post(
"/api/v2/flow/developer/give_me_work",
json={},
headers=_HEADERS,
)
assert resp.status_code == _HTTP_200
body = resp.json()
assert body["status"] == "idle"
mock_chore.give_me_work.assert_awaited_once()
@pytest.mark.asyncio
async def test_i_will_work_on_dispatches_task_id() -> None:
"""POST /api/v2/flow/developer/i_will_work_on forwards task_id and plan."""
mock_chore = MagicMock()
mock_chore.i_will_work_on = AsyncMock(
return_value=_make_envelope(status="in_progress", task_id=_TASK_ID)
)
client = TestClient(_build_app(mock_chore))
resp = client.post(
"/api/v2/flow/developer/i_will_work_on",
json={"task_id": _TASK_ID, "plan": "implement the feature"},
headers=_HEADERS,
)
assert resp.status_code == _HTTP_200
body = resp.json()
assert body["status"] == "in_progress"
mock_chore.i_will_work_on.assert_awaited_once()
call_args = mock_chore.i_will_work_on.call_args
# second positional arg is task_id (UUID), third is plan
assert str(call_args.args[1]) == _TASK_ID
assert call_args.args[2] == "implement the feature"
@pytest.mark.asyncio
async def test_i_am_done_dispatches_task_and_notes() -> None:
"""POST /api/v2/flow/developer/i_am_done forwards task_id and notes."""
mock_chore = MagicMock()
mock_chore.i_am_done = AsyncMock(
return_value=_make_envelope(status="awaiting_qa", task_id=_TASK_ID)
)
client = TestClient(_build_app(mock_chore))
resp = client.post(
"/api/v2/flow/developer/i_am_done",
json={"task_id": _TASK_ID, "notes": "all tests pass"},
headers=_HEADERS,
)
assert resp.status_code == _HTTP_200
body = resp.json()
assert body["status"] == "awaiting_qa"
mock_chore.i_am_done.assert_awaited_once()
@pytest.mark.asyncio
async def test_i_am_blocked_dispatches_reason() -> None:
"""POST /api/v2/flow/developer/i_am_blocked forwards task_id and reason."""
mock_chore = MagicMock()
mock_chore.i_am_blocked = AsyncMock(
return_value=_make_envelope(status="blocked", task_id=_TASK_ID)
)
client = TestClient(_build_app(mock_chore))
resp = client.post(
"/api/v2/flow/developer/i_am_blocked",
json={"task_id": _TASK_ID, "reason": "waiting for design spec"},
headers=_HEADERS,
)
assert resp.status_code == _HTTP_200
mock_chore.i_am_blocked.assert_awaited_once()
assert mock_chore.i_am_blocked.call_args.args[2] == "waiting for design spec"
@pytest.mark.asyncio
async def test_i_am_idle_dispatches_agent_id() -> None:
"""POST /api/v2/flow/developer/i_am_idle delegates to Choreographer.i_am_idle."""
mock_chore = MagicMock()
mock_chore.i_am_idle = AsyncMock(return_value=_make_envelope(status="idle"))
client = TestClient(_build_app(mock_chore))
resp = client.post(
"/api/v2/flow/developer/i_am_idle",
json={},
headers=_HEADERS,
)
assert resp.status_code == _HTTP_200
body = resp.json()
assert body["status"] == "idle"
mock_chore.i_am_idle.assert_awaited_once()
def test_i_am_blocked_rejects_empty_reason() -> None:
"""POST i_am_blocked rejects empty reason (min_length=1)."""
mock_chore = MagicMock()
client = TestClient(_build_app(mock_chore))
resp = client.post(
"/api/v2/flow/developer/i_am_blocked",
json={"task_id": _TASK_ID, "reason": ""},
headers=_HEADERS,
)
assert resp.status_code == _HTTP_422