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.
325 lines
10 KiB
Python
325 lines
10 KiB
Python
"""End-to-end test: task pending -> awaiting_ceo_approval through the gateway.
|
|
|
|
Uses a minimal FastAPI app that includes all six v2 routers (no lifespan / no DB).
|
|
Choreographer and ContentActions are replaced by stateful async mocks that track
|
|
the simulated task lifecycle through every role hand-off.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import TYPE_CHECKING
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
|
|
if TYPE_CHECKING:
|
|
from collections.abc import Iterator
|
|
from fastapi import FastAPI
|
|
from fastapi.testclient import TestClient
|
|
from roboco.api.deps import get_choreographer, get_content_actions
|
|
from roboco.api.routes.v2 import do as do_module
|
|
from roboco.api.routes.v2 import flow_cell_pm as flow_cell_pm_module
|
|
from roboco.api.routes.v2 import flow_dev as flow_dev_module
|
|
from roboco.api.routes.v2 import flow_doc as flow_doc_module
|
|
from roboco.api.routes.v2 import flow_main_pm as flow_main_pm_module
|
|
from roboco.api.routes.v2 import flow_qa as flow_qa_module
|
|
from roboco.services.gateway.envelope import Envelope
|
|
|
|
_HTTP_200 = 200
|
|
_PR_NUMBER = 8
|
|
|
|
# Shared mutable state threaded through all mock methods.
|
|
_State = dict[str, object]
|
|
|
|
|
|
def _build_app() -> FastAPI:
|
|
"""Minimal FastAPI app with all v2 routers — no lifespan, no DB."""
|
|
app = FastAPI()
|
|
app.include_router(flow_dev_module.router)
|
|
app.include_router(flow_qa_module.router)
|
|
app.include_router(flow_doc_module.router)
|
|
app.include_router(flow_cell_pm_module.router)
|
|
app.include_router(flow_main_pm_module.router)
|
|
app.include_router(do_module.router)
|
|
return app
|
|
|
|
|
|
class _MockChoreographer:
|
|
"""Stateful stub for Choreographer; methods advance shared lifecycle state."""
|
|
|
|
def __init__(self, state: _State) -> None:
|
|
self._state = state
|
|
|
|
async def give_me_work(self, _agent_id: object) -> Envelope:
|
|
return Envelope.ok(
|
|
status=str(self._state["task_status"]),
|
|
task_id=str(uuid4()),
|
|
next="claim it",
|
|
)
|
|
|
|
async def i_will_work_on(
|
|
self,
|
|
_agent_id: object,
|
|
_task_id: object,
|
|
_plan: object = None,
|
|
) -> Envelope:
|
|
self._state["task_status"] = "in_progress"
|
|
return Envelope.ok(
|
|
status="in_progress",
|
|
task_id=str(uuid4()),
|
|
next="commit + i_am_done",
|
|
)
|
|
|
|
async def i_am_done(
|
|
self,
|
|
_agent_id: object,
|
|
_task_id: object,
|
|
_notes: object,
|
|
) -> Envelope:
|
|
self._state["task_status"] = "awaiting_qa"
|
|
return Envelope.ok(
|
|
status="awaiting_qa",
|
|
task_id=str(uuid4()),
|
|
next="idle until QA",
|
|
evidence={"pr_url": "https://x/pr/8", "pr_number": _PR_NUMBER},
|
|
)
|
|
|
|
async def claim_review(
|
|
self,
|
|
_agent_id: object,
|
|
_task_id: object,
|
|
) -> Envelope:
|
|
self._state["task_status"] = "claimed"
|
|
return Envelope.ok(
|
|
status="claimed",
|
|
task_id=str(uuid4()),
|
|
next="review then pass",
|
|
evidence={"pr_url": "https://x/pr/8", "pr_number": _PR_NUMBER},
|
|
)
|
|
|
|
async def pass_review(
|
|
self,
|
|
_agent_id: object,
|
|
_task_id: object,
|
|
_notes: object,
|
|
) -> Envelope:
|
|
self._state["task_status"] = "awaiting_documentation"
|
|
return Envelope.ok(
|
|
status="awaiting_documentation",
|
|
task_id=str(uuid4()),
|
|
next="idle",
|
|
)
|
|
|
|
async def claim_doc_task(
|
|
self,
|
|
_agent_id: object,
|
|
_task_id: object,
|
|
) -> Envelope:
|
|
self._state["task_status"] = "claimed"
|
|
return Envelope.ok(
|
|
status="claimed",
|
|
task_id=str(uuid4()),
|
|
next="document then i_documented",
|
|
)
|
|
|
|
async def i_documented(
|
|
self,
|
|
_agent_id: object,
|
|
_task_id: object,
|
|
_notes: object,
|
|
_files: object,
|
|
) -> Envelope:
|
|
self._state["task_status"] = "awaiting_pm_review"
|
|
return Envelope.ok(
|
|
status="awaiting_pm_review",
|
|
task_id=str(uuid4()),
|
|
next="idle until PM completes",
|
|
)
|
|
|
|
async def complete(
|
|
self,
|
|
_agent_id: object,
|
|
_task_id: object,
|
|
_notes: object,
|
|
) -> Envelope:
|
|
self._state["task_status"] = "completed"
|
|
return Envelope.ok(
|
|
status="completed",
|
|
task_id=str(uuid4()),
|
|
next="done",
|
|
)
|
|
|
|
async def main_pm_complete(
|
|
self,
|
|
_agent_id: object,
|
|
_root_task_id: object,
|
|
_notes: object,
|
|
) -> Envelope:
|
|
self._state["task_status"] = "awaiting_ceo_approval"
|
|
return Envelope.ok(
|
|
status="awaiting_ceo_approval",
|
|
task_id=str(uuid4()),
|
|
next="idle until CEO",
|
|
)
|
|
|
|
|
|
class _MockContentActions:
|
|
"""Stateful stub for ContentActions; only note() is exercised here."""
|
|
|
|
async def note(
|
|
self,
|
|
*,
|
|
agent_id: object,
|
|
text: object,
|
|
scope: str = "note",
|
|
task_id: object = None,
|
|
) -> Envelope:
|
|
_ = agent_id
|
|
_ = text
|
|
_ = scope
|
|
_ = task_id
|
|
return Envelope.ok(status="noted", task_id=None, next="continue")
|
|
|
|
|
|
@pytest.fixture
|
|
def stateful_app() -> Iterator[tuple[FastAPI, _State]]:
|
|
"""FastAPI app with stateful mocks (Choreographer + ContentActions)."""
|
|
app = _build_app()
|
|
state: _State = {"task_status": "pending"}
|
|
chor = _MockChoreographer(state)
|
|
actions = _MockContentActions()
|
|
app.dependency_overrides[get_choreographer] = lambda: chor
|
|
app.dependency_overrides[get_content_actions] = lambda: actions
|
|
yield app, state
|
|
app.dependency_overrides.clear()
|
|
|
|
|
|
async def test_pending_to_awaiting_ceo_approval(stateful_app: tuple) -> None:
|
|
"""Drive task pending -> awaiting_ceo_approval through all gateway roles."""
|
|
app, _state = stateful_app
|
|
client = TestClient(app)
|
|
dev_id = str(uuid4())
|
|
qa_id = str(uuid4())
|
|
doc_id = str(uuid4())
|
|
cell_pm_id = str(uuid4())
|
|
main_pm_id = str(uuid4())
|
|
|
|
# ------------------------------------------------------------------
|
|
# 1. Dev: give_me_work -> i_will_work_on -> note -> i_am_done
|
|
# ------------------------------------------------------------------
|
|
r = client.post(
|
|
"/api/v2/flow/developer/give_me_work",
|
|
headers={"X-Agent-ID": dev_id, "X-Agent-Role": "developer"},
|
|
json={},
|
|
)
|
|
assert r.status_code == _HTTP_200
|
|
|
|
r = client.post(
|
|
"/api/v2/flow/developer/i_will_work_on",
|
|
headers={"X-Agent-ID": dev_id, "X-Agent-Role": "developer"},
|
|
json={"task_id": str(uuid4()), "plan": "edit x then y"},
|
|
)
|
|
assert r.json()["status"] == "in_progress"
|
|
|
|
r = client.post(
|
|
"/api/v2/do/note",
|
|
headers={"X-Agent-ID": dev_id, "X-Agent-Role": "developer"},
|
|
json={"text": "Reflected: did the work as planned.", "scope": "reflect"},
|
|
)
|
|
assert r.json()["error"] is None
|
|
|
|
r = client.post(
|
|
"/api/v2/flow/developer/i_am_done",
|
|
headers={"X-Agent-ID": dev_id, "X-Agent-Role": "developer"},
|
|
json={"task_id": str(uuid4()), "notes": "all done"},
|
|
)
|
|
assert r.json()["status"] == "awaiting_qa"
|
|
# Inline evidence in the envelope kills issue #15 (QA false-failing "no PR")
|
|
assert r.json()["evidence"]["pr_number"] == _PR_NUMBER
|
|
|
|
# ------------------------------------------------------------------
|
|
# 2. QA: claim_review -> note -> pass
|
|
# ------------------------------------------------------------------
|
|
r = client.post(
|
|
"/api/v2/flow/qa/claim_review",
|
|
headers={"X-Agent-ID": qa_id, "X-Agent-Role": "qa"},
|
|
json={"task_id": str(uuid4())},
|
|
)
|
|
assert r.json()["evidence"]["pr_number"] == _PR_NUMBER
|
|
|
|
r = client.post(
|
|
"/api/v2/do/note",
|
|
headers={"X-Agent-ID": qa_id, "X-Agent-Role": "developer"},
|
|
json={
|
|
"text": "Reviewed; all acceptance criteria addressed.",
|
|
"scope": "learning",
|
|
},
|
|
)
|
|
assert r.json()["error"] is None
|
|
|
|
long_notes = (
|
|
"Reviewed PR #8 carefully. Branch convention correct. Commit message "
|
|
"includes task ID. README diff matches spec. No security concerns."
|
|
)
|
|
r = client.post(
|
|
"/api/v2/flow/qa/pass",
|
|
headers={"X-Agent-ID": qa_id, "X-Agent-Role": "qa"},
|
|
json={"task_id": str(uuid4()), "notes": long_notes},
|
|
)
|
|
assert r.json()["status"] == "awaiting_documentation"
|
|
|
|
# ------------------------------------------------------------------
|
|
# 3. Doc: claim_doc_task -> i_documented
|
|
# ------------------------------------------------------------------
|
|
r = client.post(
|
|
"/api/v2/flow/documenter/claim_doc_task",
|
|
headers={"X-Agent-ID": doc_id, "X-Agent-Role": "documenter"},
|
|
json={"task_id": str(uuid4())},
|
|
)
|
|
assert r.status_code == _HTTP_200
|
|
|
|
r = client.post(
|
|
"/api/v2/flow/documenter/i_documented",
|
|
headers={"X-Agent-ID": doc_id, "X-Agent-Role": "documenter"},
|
|
json={
|
|
"task_id": str(uuid4()),
|
|
"notes": "Wrote backend/guides/feature-x.md covering usage and config.",
|
|
"files": ["backend/guides/feature-x.md"],
|
|
},
|
|
)
|
|
assert r.json()["status"] == "awaiting_pm_review"
|
|
|
|
# ------------------------------------------------------------------
|
|
# 4. Cell PM: note -> complete (auto-merges leaf PR)
|
|
# ------------------------------------------------------------------
|
|
r = client.post(
|
|
"/api/v2/do/note",
|
|
headers={"X-Agent-ID": cell_pm_id, "X-Agent-Role": "developer"},
|
|
json={"text": "Decision: approve and merge.", "scope": "decision"},
|
|
)
|
|
assert r.json()["error"] is None
|
|
|
|
r = client.post(
|
|
"/api/v2/flow/cell_pm/complete",
|
|
headers={"X-Agent-ID": cell_pm_id, "X-Agent-Role": "cell_pm"},
|
|
json={"task_id": str(uuid4()), "notes": "Approved and merged"},
|
|
)
|
|
assert r.json()["status"] == "completed"
|
|
|
|
# ------------------------------------------------------------------
|
|
# 5. Main PM: note -> complete root (opens master PR + escalates to CEO)
|
|
# ------------------------------------------------------------------
|
|
r = client.post(
|
|
"/api/v2/do/note",
|
|
headers={"X-Agent-ID": main_pm_id, "X-Agent-Role": "developer"},
|
|
json={"text": "Root task ready for prod.", "scope": "decision"},
|
|
)
|
|
assert r.json()["error"] is None
|
|
|
|
r = client.post(
|
|
"/api/v2/flow/main_pm/complete",
|
|
headers={"X-Agent-ID": main_pm_id, "X-Agent-Role": "main_pm"},
|
|
json={"task_id": str(uuid4()), "notes": "Ready for prod"},
|
|
)
|
|
assert r.json()["status"] == "awaiting_ceo_approval"
|