External/roboco
1
0
Fork 0
mirror of https://github.com/rennf93/roboco.git synced 2026-08-03 07:23:24 +02:00
Code Issues Packages Projects Releases Wiki Activity

fix(gateway): unblock task claim; full Phase 0/1/2 remediation

Browse Source 
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:
Renn F
2026-05-04 23:43:55 +02:00
parent 0a3c963923
commit 4829f93a68
55 changed files with 2470 additions and 1279 deletions
Download Patch File Download Diff File Expand all files Collapse all files
tests/unit/api/routes/v2/test_flow_dev.py
+12 -46
View File
@@ -1,4 +1,4 @@
"""Unit tests for /api/v2/flow/dev/* endpoints.
"""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.
@@ -40,13 +40,13 @@ def _build_app(mock_choreographer: MagicMock) -> FastAPI:
@pytest.mark.asyncio
async def test_give_me_work_returns_envelope() -> None:
"""POST /api/v2/flow/dev/give_me_work returns 200 with envelope shape."""
"""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/dev/give_me_work",
"/api/v2/flow/developer/give_me_work",
json={},
headers=_HEADERS,
)
@@ -59,7 +59,7 @@ async def test_give_me_work_returns_envelope() -> None:
@pytest.mark.asyncio
async def test_i_will_work_on_dispatches_task_id() -> None:
"""POST /api/v2/flow/dev/i_will_work_on forwards task_id and plan."""
"""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)
@@ -67,7 +67,7 @@ async def test_i_will_work_on_dispatches_task_id() -> None:
client = TestClient(_build_app(mock_chore))
resp = client.post(
"/api/v2/flow/dev/i_will_work_on",
"/api/v2/flow/developer/i_will_work_on",
json={"task_id": _TASK_ID, "plan": "implement the feature"},
headers=_HEADERS,
)
@@ -82,29 +82,9 @@ async def test_i_will_work_on_dispatches_task_id() -> None:
assert call_args.args[2] == "implement the feature"
@pytest.mark.asyncio
async def test_i_have_committed_dispatches_message() -> None:
"""POST /api/v2/flow/dev/i_have_committed forwards commit message."""
mock_chore = MagicMock()
mock_chore.i_have_committed = AsyncMock(
return_value=_make_envelope(status="in_progress")
)
client = TestClient(_build_app(mock_chore))
resp = client.post(
"/api/v2/flow/dev/i_have_committed",
json={"message": "add auth endpoint"},
headers=_HEADERS,
)
assert resp.status_code == _HTTP_200
mock_chore.i_have_committed.assert_awaited_once()
assert mock_chore.i_have_committed.call_args.args[1] == "add auth endpoint"
@pytest.mark.asyncio
async def test_i_am_done_dispatches_task_and_notes() -> None:
"""POST /api/v2/flow/dev/i_am_done forwards task_id and notes."""
"""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)
@@ -112,7 +92,7 @@ async def test_i_am_done_dispatches_task_and_notes() -> None:
client = TestClient(_build_app(mock_chore))
resp = client.post(
"/api/v2/flow/dev/i_am_done",
"/api/v2/flow/developer/i_am_done",
json={"task_id": _TASK_ID, "notes": "all tests pass"},
headers=_HEADERS,
)
@@ -125,7 +105,7 @@ async def test_i_am_done_dispatches_task_and_notes() -> None:
@pytest.mark.asyncio
async def test_i_am_blocked_dispatches_reason() -> None:
"""POST /api/v2/flow/dev/i_am_blocked forwards task_id and reason."""
"""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)
@@ -133,7 +113,7 @@ async def test_i_am_blocked_dispatches_reason() -> None:
client = TestClient(_build_app(mock_chore))
resp = client.post(
"/api/v2/flow/dev/i_am_blocked",
"/api/v2/flow/developer/i_am_blocked",
json={"task_id": _TASK_ID, "reason": "waiting for design spec"},
headers=_HEADERS,
)
@@ -145,13 +125,13 @@ async def test_i_am_blocked_dispatches_reason() -> None:
@pytest.mark.asyncio
async def test_i_am_idle_dispatches_agent_id() -> None:
"""POST /api/v2/flow/dev/i_am_idle delegates to Choreographer.i_am_idle."""
"""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/dev/i_am_idle",
"/api/v2/flow/developer/i_am_idle",
json={},
headers=_HEADERS,
)
@@ -162,27 +142,13 @@ async def test_i_am_idle_dispatches_agent_id() -> None:
mock_chore.i_am_idle.assert_awaited_once()
def test_i_have_committed_rejects_empty_message() -> None:
"""POST i_have_committed rejects empty message (min_length=1)."""
mock_chore = MagicMock()
client = TestClient(_build_app(mock_chore))
resp = client.post(
"/api/v2/flow/dev/i_have_committed",
json={"message": ""},
headers=_HEADERS,
)
assert resp.status_code == _HTTP_422
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/dev/i_am_blocked",
"/api/v2/flow/developer/i_am_blocked",
json={"task_id": _TASK_ID, "reason": ""},
headers=_HEADERS,
)
tests/unit/api/test_correlation_id.py
+40 -2
View File
@@ -27,6 +27,9 @@ from __future__ import annotations
import asyncio
import importlib
import json
import tempfile
from pathlib import Path
from typing import TYPE_CHECKING, Any
from unittest.mock import AsyncMock, MagicMock, patch
from uuid import UUID
@@ -95,7 +98,7 @@ def test_route_stamps_request_correlation_id_onto_envelope() -> None:
app, _ = _build_app()
client = TestClient(app)
r = client.post(
"/api/v2/flow/dev/give_me_work",
"/api/v2/flow/developer/give_me_work",
json={},
headers={**_DEV_AGENT_HEADERS, "X-Correlation-ID": "trace-xyz"},
)
@@ -109,7 +112,7 @@ def test_route_stamps_generated_correlation_id_when_header_missing() -> None:
app, _ = _build_app()
client = TestClient(app)
r = client.post(
"/api/v2/flow/dev/give_me_work",
"/api/v2/flow/developer/give_me_work",
json={},
headers=_DEV_AGENT_HEADERS,
)
@@ -132,10 +135,45 @@ def _reload_mcp_module(monkeypatch: pytest.MonkeyPatch, dotted: str) -> ModuleTy
import; we have to re-import after monkey-patching so the test sees
the patched values. The reload itself is the lazy import — keeping
importlib at the top-level keeps PLC0415 happy.
Also writes a stub manifest file and points the MCP server at it,
since both servers now refuse to register any tools without one
(audit P0-5 / D-12).
"""
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000001")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "developer")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
manifest_path = Path(tempfile.mkdtemp()) / "tool-manifest.json"
manifest_path.write_text(
json.dumps(
{
"agent_id": "00000000-0000-0000-0000-000000000001",
"role": "developer",
"team": "backend",
"workspace_path": "/tmp/test",
"flow_tools": [
"give_me_work",
"i_will_work_on",
"submit_for_qa",
"i_am_done",
"i_am_blocked",
"unclaim",
"resume",
"i_am_idle",
],
"do_tools": ["commit", "note", "say", "dm", "evidence"],
"read_tools": [],
"write_tools": [],
"bash_allowed": True,
"subagent_allowed": False,
"subagent_model": None,
"env": {},
}
)
)
monkeypatch.setenv("ROBOCO_TOOL_MANIFEST_PATH", str(manifest_path))
module = importlib.import_module(dotted)
return importlib.reload(module)
tests/unit/api/test_v2_role_dep.py
+4 -4
View File
@@ -34,7 +34,7 @@ def _build_app() -> FastAPI:
def test_dev_route_rejects_qa_role() -> None:
client = TestClient(_build_app())
r = client.post(
"/api/v2/flow/dev/give_me_work",
"/api/v2/flow/developer/give_me_work",
json={},
headers={
"X-Agent-ID": "00000000-0000-0000-0000-000000000001",
@@ -48,7 +48,7 @@ def test_dev_route_rejects_qa_role() -> None:
def test_dev_route_accepts_developer_role() -> None:
client = TestClient(_build_app())
r = client.post(
"/api/v2/flow/dev/give_me_work",
"/api/v2/flow/developer/give_me_work",
json={},
headers={
"X-Agent-ID": "00000000-0000-0000-0000-000000000001",
@@ -62,7 +62,7 @@ def test_dev_route_accepts_developer_role() -> None:
def test_dev_route_accepts_developer_role_case_insensitive() -> None:
client = TestClient(_build_app())
r = client.post(
"/api/v2/flow/dev/give_me_work",
"/api/v2/flow/developer/give_me_work",
json={},
headers={
"X-Agent-ID": "00000000-0000-0000-0000-000000000001",
@@ -75,7 +75,7 @@ def test_dev_route_accepts_developer_role_case_insensitive() -> None:
def test_dev_route_rejects_missing_role_header() -> None:
client = TestClient(_build_app())
r = client.post(
"/api/v2/flow/dev/give_me_work",
"/api/v2/flow/developer/give_me_work",
json={},
headers={"X-Agent-ID": "00000000-0000-0000-0000-000000000001"},
)
tests/unit/gateway/test_audit_on_rejection.py
+5 -61
View File
@@ -96,64 +96,6 @@ async def test_pm_cannot_execute_code_writes_audit_row() -> None:
assert args.kwargs["details"]["reason"] == "not_authorized"
# ---------------------------------------------------------------------------
# tracing_gap path: i_have_committed with no plan
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_i_have_committed_missing_plan_writes_audit_row() -> None:
"""Tracing-gap rejection (missing plan) should also be audited."""
aid = uuid4()
tid = uuid4()
task_with_no_plan = MagicMock(
id=tid,
status="in_progress",
assigned_to=aid,
plan=None,
)
task_svc = AsyncMock()
task_svc.get_active_task_for_agent.return_value = task_with_no_plan
audit_svc = AsyncMock()
deps = _make_deps(task=task_svc, audit=audit_svc)
c = Choreographer(deps)
env = await c.i_have_committed(aid, "wip")
assert env.error == "tracing_gap"
audit_svc.log_event.assert_awaited()
args = audit_svc.log_event.await_args
assert args.kwargs["event_type"] == "gateway.rejected"
assert args.kwargs["details"]["verb"] == "i_have_committed"
assert args.kwargs["details"]["reason"] == "tracing_gap"
assert "plan" in args.kwargs["details"]["missing"]
# ---------------------------------------------------------------------------
# invalid_state path: i_have_committed with no active task
# ---------------------------------------------------------------------------
@pytest.mark.asyncio
async def test_i_have_committed_no_active_task_writes_audit_row() -> None:
"""invalid_state rejection (no active task) is audited."""
aid = uuid4()
task_svc = AsyncMock()
task_svc.get_active_task_for_agent.return_value = None
audit_svc = AsyncMock()
deps = _make_deps(task=task_svc, audit=audit_svc)
c = Choreographer(deps)
env = await c.i_have_committed(aid, "wip")
assert env.error == "invalid_state"
audit_svc.log_event.assert_awaited()
args = audit_svc.log_event.await_args
assert args.kwargs["event_type"] == "gateway.rejected"
assert args.kwargs["details"]["verb"] == "i_have_committed"
assert args.kwargs["details"]["reason"] == "invalid_state"
# ---------------------------------------------------------------------------
# not_found path: unknown task id
# ---------------------------------------------------------------------------
@@ -212,15 +154,17 @@ async def test_successful_verb_does_not_write_audit_row() -> None:
async def test_audit_log_event_failure_does_not_propagate() -> None:
"""If log_event raises, the verb still returns the rejection envelope."""
aid = uuid4()
tid = uuid4()
task_svc = AsyncMock()
task_svc.get_active_task_for_agent.return_value = None
# Unknown task id triggers not_found rejection on i_am_done.
task_svc.get.return_value = None
audit_svc = AsyncMock()
audit_svc.log_event.side_effect = RuntimeError("audit DB down")
deps = _make_deps(task=task_svc, audit=audit_svc)
c = Choreographer(deps)
# Must not raise; the rejection envelope should still come back.
env = await c.i_have_committed(aid, "wip")
env = await c.i_am_done(aid, tid, notes="x")
assert env.error == "invalid_state"
assert env.error == "not_found"
audit_svc.log_event.assert_awaited()
tests/unit/gateway/test_choreographer_dev.py
+3 -183
View File
@@ -210,189 +210,9 @@ async def test_i_will_work_on_invalid_state_returns_invalid_state() -> None:
assert "completed" in body["message"]
@pytest.mark.asyncio
async def test_i_have_committed_records_progress() -> None:
agent_id = uuid4()
task_id = uuid4()
active = MagicMock(
id=task_id, status="in_progress", assigned_to=agent_id, plan={"x": 1}
)
task_svc = AsyncMock()
task_svc.get_active_task_for_agent.return_value = active
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_have_committed(agent_id, "feat(api): add /healthz endpoint")
assert env.error is None
task_svc.add_progress.assert_awaited_once_with(
task_id, agent_id, "feat(api): add /healthz endpoint"
)
@pytest.mark.asyncio
async def test_i_have_committed_no_active_task_returns_invalid_state() -> None:
agent_id = uuid4()
task_svc = AsyncMock()
task_svc.get_active_task_for_agent.return_value = None
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_have_committed(agent_id, "feat: x")
body = env.as_dict()
assert body["error"] == "invalid_state"
assert "give_me_work" in body["remediate"]
@pytest.mark.asyncio
async def test_i_have_committed_no_plan_returns_tracing_gap() -> None:
agent_id = uuid4()
task_id = uuid4()
active = MagicMock(
id=task_id, status="in_progress", assigned_to=agent_id, plan=None
)
task_svc = AsyncMock()
task_svc.get_active_task_for_agent.return_value = active
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_have_committed(agent_id, "feat: x")
body = env.as_dict()
assert body["error"] == "tracing_gap"
assert "plan" in body["missing"]
task_svc.add_progress.assert_not_awaited()
@pytest.mark.asyncio
async def test_i_am_done_with_catchup_full_chain() -> None:
"""The catch-up convenience verb auto-runs verify/push/PR/submit_qa.
Strict ``i_am_done`` requires the dev to have done these steps already
(Gate Set E). When the dev wants the gateway to drive the chain, they
call the explicit catch-up verb.
"""
agent_id = uuid4()
task_id = uuid4()
branch = "feature/backend/abc--def"
ws_id = uuid4()
initial = MagicMock(
id=task_id,
status="in_progress",
assigned_to=agent_id,
plan={"x": 1},
branch_name=branch,
work_session_id=ws_id,
self_verified=False,
pr_number=None,
pr_url=None,
team="backend",
progress_updates=[{"message": "did x"}],
acceptance_criteria=["AC1"],
acceptance_criteria_status=[
{"criterion": "AC1", "referencing_artifact_id": "c1"}
],
commits=[],
documents=[],
dev_notes="",
)
after_verify = MagicMock(
id=task_id,
status="verifying",
assigned_to=agent_id,
plan={"x": 1},
branch_name=branch,
work_session_id=ws_id,
self_verified=True,
pr_number=None,
pr_url=None,
team="backend",
progress_updates=[{"message": "did x"}],
acceptance_criteria=["AC1"],
acceptance_criteria_status=[
{"criterion": "AC1", "referencing_artifact_id": "c1"}
],
commits=[],
documents=[],
dev_notes="",
)
after_pr = MagicMock(
id=task_id,
status="verifying",
assigned_to=agent_id,
plan={"x": 1},
branch_name=branch,
work_session_id=ws_id,
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=[],
documents=[],
dev_notes="",
)
after_submit = MagicMock(
id=task_id,
status="awaiting_qa",
assigned_to=agent_id,
plan={"x": 1},
branch_name=branch,
work_session_id=ws_id,
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=[],
documents=[],
dev_notes="",
)
task_svc = AsyncMock()
task_svc.get.side_effect = [initial, after_pr] # initial fetch + post-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 = ["README.md"]
git_svc = AsyncMock()
git_svc.create_pr.return_value = {"pr_number": 8, "pr_url": "https://x/pr/8"}
a2a_svc = AsyncMock()
journal_svc = AsyncMock()
journal_svc.has_reflect_for_task.return_value = True
deps = _make_deps(
task=task_svc,
work_session=work_svc,
git=git_svc,
a2a=a2a_svc,
journal=journal_svc,
)
deps.evidence_repo.journal_highlights_for_task.return_value = []
c = Choreographer(deps)
env = await c.i_am_done_with_catchup(agent_id, task_id, "all done")
assert env.error is None
assert env.status == "awaiting_qa"
git_svc.push_branch.assert_awaited_once_with(branch)
git_svc.create_pr.assert_awaited_once()
a2a_svc.send.assert_awaited_once()
body = env.as_dict()
assert body["evidence"]["pr_url"] == "https://x/pr/8"
# test_i_am_done_with_catchup_full_chain removed (audit P2-5/D-16):
# i_am_done_with_catchup verb deleted. submit_for_qa now does push + PR
# explicitly; i_am_done auto-runs submit_verification + submit_qa.
@pytest.mark.asyncio
tests/unit/gateway/test_choreographer_submit_qa_gates.py
+31 -54
View File
@@ -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."""
tests/unit/gateway/test_commit_prefix.py
-1
View File
@@ -24,7 +24,6 @@ def _make_deps(**overrides: AsyncMock) -> ContentActionsDeps:
task.get_active_task_for_agent.return_value = None
# commit() now checks caller role; default to developer.
from unittest.mock import MagicMock
task.agent_for.return_value = MagicMock(role="developer")
tests/unit/gateway/test_content_actions.py
-1
View File
@@ -20,7 +20,6 @@ def _make_deps(**overrides: AsyncMock) -> ContentActionsDeps:
# commit() checks caller role server-side; default-created mocks
# need a default developer role so existing tests pass through.
# Caller-supplied mocks must set agent_for themselves.
from unittest.mock import MagicMock
task.agent_for.return_value = MagicMock(role="developer")
tests/unit/gateway/test_content_actions_ownership.py
-1
View File
@@ -29,7 +29,6 @@ def _make_deps(**overrides: AsyncMock) -> ContentActionsDeps:
task.get_active_task_for_agent.return_value = None
# commit() now checks caller role; default to developer.
from unittest.mock import MagicMock
task.agent_for.return_value = MagicMock(role="developer")
tests/unit/gateway/test_heartbeat_wired.py
-15
View File
@@ -74,21 +74,6 @@ async def test_i_will_work_on_calls_heartbeat() -> None:
task_svc.heartbeat.assert_awaited_with(tid)
@pytest.mark.asyncio
async def test_i_have_committed_calls_heartbeat() -> None:
aid = uuid4()
tid = uuid4()
t = MagicMock(id=tid, status="in_progress", assigned_to=aid, plan="x")
task_svc = AsyncMock()
task_svc.get_active_task_for_agent.return_value = t
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
await c.i_have_committed(aid, "did the thing")
task_svc.heartbeat.assert_awaited_with(tid)
@pytest.mark.asyncio
async def test_i_am_done_calls_heartbeat() -> None:
aid = uuid4()
tests/unit/mcp_servers/test_do_server.py
+24
View File
@@ -2,16 +2,40 @@
from __future__ import annotations
import json
import tempfile
from pathlib import Path
from unittest.mock import MagicMock, patch
import pytest
# Same pattern as test_flow_server: do_server now refuses to start without
# a manifest (audit P0-5 / D-12). The test fixture writes a stub manifest
# with the full do-tool superset; production manifests are role-scoped.
_DO_TEST_MANIFEST = {
"agent_id": "00000000-0000-0000-0000-000000000001",
"role": "developer",
"team": "backend",
"workspace_path": "/tmp/test",
"flow_tools": [],
"do_tools": ["commit", "note", "say", "dm", "notify", "evidence"],
"read_tools": [],
"write_tools": [],
"bash_allowed": True,
"subagent_allowed": False,
"subagent_model": None,
"env": {},
}
@pytest.fixture
def do_module(monkeypatch): # type: ignore[no-untyped-def]
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000001")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "developer")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
manifest_path = Path(tempfile.mkdtemp()) / "tool-manifest.json"
manifest_path.write_text(json.dumps(_DO_TEST_MANIFEST))
monkeypatch.setenv("ROBOCO_TOOL_MANIFEST_PATH", str(manifest_path))
import importlib
import roboco.mcp.do_server as srv
tests/unit/mcp_servers/test_flow_server.py
+109 -98
View File
@@ -3,6 +3,7 @@
from __future__ import annotations
import importlib
import json
from typing import TYPE_CHECKING, Any
from unittest.mock import MagicMock, patch
@@ -10,14 +11,60 @@ import pytest
if TYPE_CHECKING:
import types
from pathlib import Path
_FULL_MANIFEST = {
"agent_id": "00000000-0000-0000-0000-000000000001",
"role": "developer",
"team": "backend",
"workspace_path": "/tmp/test",
# Test fixture provides every flow verb so per-verb URL/path tests work
# against a single fixture. Production manifests are role-scoped.
"flow_tools": [
"give_me_work",
"i_will_work_on",
"submit_for_qa",
"i_am_done",
"i_am_blocked",
"unclaim",
"resume",
"i_am_idle",
"claim_review",
"pass",
"fail",
"claim_doc_task",
"i_documented",
"triage",
"triage_all",
"unblock",
"complete",
"escalate_up",
"i_will_plan",
"delegate",
"submit_up",
"escalate_to_ceo",
],
"do_tools": ["commit", "note", "say", "dm", "evidence"],
"read_tools": ["Read", "Glob", "Grep"],
"write_tools": ["Edit", "Write"],
"bash_allowed": True,
"subagent_allowed": False,
"subagent_model": None,
"env": {},
}
@pytest.fixture()
def flow_module(monkeypatch: pytest.MonkeyPatch) -> types.ModuleType:
"""Import the flow_server module with controlled env vars."""
def flow_module(monkeypatch: pytest.MonkeyPatch, tmp_path: Path) -> types.ModuleType:
"""Import the flow_server module with controlled env vars + manifest."""
manifest_path = tmp_path / "tool-manifest.json"
manifest_path.write_text(json.dumps(_FULL_MANIFEST))
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000001")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "developer")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
monkeypatch.setenv("ROBOCO_TOOL_MANIFEST_PATH", str(manifest_path))
import roboco.mcp.flow_server as srv
@@ -36,6 +83,33 @@ def _make_fake_client(return_value: dict[str, Any]) -> MagicMock:
return fake_client
def _reload_for_role(
monkeypatch: pytest.MonkeyPatch, role: str, agent_id: str
) -> types.ModuleType:
"""Set env + write manifest for the given role; reload flow_server.
The manifest provides the full verb superset so role-specific tests
aren't blocked by the manifest filter; the role-scoped URL routing
is what's under test in these per-role cases.
"""
import tempfile
from pathlib import Path
manifest_path = Path(tempfile.mkdtemp()) / "tool-manifest.json"
payload = {**_FULL_MANIFEST, "role": role, "agent_id": agent_id}
manifest_path.write_text(json.dumps(payload))
monkeypatch.setenv("ROBOCO_AGENT_ID", agent_id)
monkeypatch.setenv("ROBOCO_AGENT_ROLE", role)
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
monkeypatch.setenv("ROBOCO_TOOL_MANIFEST_PATH", str(manifest_path))
import roboco.mcp.flow_server as srv
importlib.reload(srv)
return srv
def test_role_path_uses_agent_role(flow_module: types.ModuleType) -> None:
expected = "/api/v2/flow/developer/give_me_work"
assert flow_module._role_path("give_me_work") == expected
@@ -80,17 +154,6 @@ def test_i_will_work_on_plan_defaults_to_none(flow_module: types.ModuleType) ->
assert kwargs["json"] == {"task_id": "task-uuid", "plan": None}
def test_i_have_committed_sends_message(flow_module: types.ModuleType) -> None:
fake_client = _make_fake_client({"status": "recorded"})
with patch("httpx.Client", return_value=fake_client):
result = flow_module.i_have_committed("fix: typo in handler")
assert result == {"status": "recorded"}
_, kwargs = fake_client.post.call_args
assert kwargs["json"] == {"message": "fix: typo in handler"}
def test_i_am_done_sends_task_id_and_notes(flow_module: types.ModuleType) -> None:
fake_client = _make_fake_client({"status": "awaiting_qa"})
@@ -138,13 +201,7 @@ def test_i_am_idle_posts_empty_body(flow_module: types.ModuleType) -> None:
def test_claim_review_posts_to_qa_path(monkeypatch: pytest.MonkeyPatch) -> None:
"""When AGENT_ROLE=qa, claim_review forwards to /api/v2/flow/qa/claim_review."""
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000002")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "qa")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
import roboco.mcp.flow_server as srv
importlib.reload(srv)
srv = _reload_for_role(monkeypatch, "qa", "00000000-0000-0000-0000-000000000002")
fake_client = _make_fake_client({"status": "claimed", "evidence": {}})
@@ -158,13 +215,7 @@ def test_claim_review_posts_to_qa_path(monkeypatch: pytest.MonkeyPatch) -> None:
def test_pass_review_passes_notes(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000002")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "qa")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
import roboco.mcp.flow_server as srv
importlib.reload(srv)
srv = _reload_for_role(monkeypatch, "qa", "00000000-0000-0000-0000-000000000002")
fake_client = _make_fake_client({"status": "awaiting_documentation"})
@@ -178,13 +229,7 @@ def test_pass_review_passes_notes(monkeypatch: pytest.MonkeyPatch) -> None:
def test_fail_review_passes_issues_list(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000002")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "qa")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
import roboco.mcp.flow_server as srv
importlib.reload(srv)
srv = _reload_for_role(monkeypatch, "qa", "00000000-0000-0000-0000-000000000002")
fake_client = _make_fake_client({"status": "needs_revision"})
@@ -201,13 +246,9 @@ def test_claim_doc_task_posts_to_documenter_path(
monkeypatch: pytest.MonkeyPatch,
) -> None:
"""When AGENT_ROLE=documenter, claim_doc_task forwards to documenter flow."""
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000003")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "documenter")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
import roboco.mcp.flow_server as srv
importlib.reload(srv)
srv = _reload_for_role(
monkeypatch, "documenter", "00000000-0000-0000-0000-000000000003"
)
fake_client = _make_fake_client({"status": "claimed"})
@@ -221,13 +262,9 @@ def test_claim_doc_task_posts_to_documenter_path(
def test_i_documented_passes_notes_and_files(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000003")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "documenter")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
import roboco.mcp.flow_server as srv
importlib.reload(srv)
srv = _reload_for_role(
monkeypatch, "documenter", "00000000-0000-0000-0000-000000000003"
)
fake_client = _make_fake_client({"status": "awaiting_pm_review"})
@@ -245,13 +282,9 @@ def test_i_documented_passes_notes_and_files(monkeypatch: pytest.MonkeyPatch) ->
def test_triage_uses_role_path(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000004")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "cell_pm")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
import roboco.mcp.flow_server as srv
importlib.reload(srv)
srv = _reload_for_role(
monkeypatch, "cell_pm", "00000000-0000-0000-0000-000000000004"
)
fake_client = _make_fake_client({"status": "blocked"})
@@ -265,13 +298,9 @@ def test_triage_uses_role_path(monkeypatch: pytest.MonkeyPatch) -> None:
def test_triage_all_uses_role_path(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000005")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "main_pm")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
import roboco.mcp.flow_server as srv
importlib.reload(srv)
srv = _reload_for_role(
monkeypatch, "main_pm", "00000000-0000-0000-0000-000000000005"
)
fake_client = _make_fake_client({"status": "idle"})
@@ -285,13 +314,9 @@ def test_triage_all_uses_role_path(monkeypatch: pytest.MonkeyPatch) -> None:
def test_unblock_with_restore_true(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000004")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "cell_pm")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
import roboco.mcp.flow_server as srv
importlib.reload(srv)
srv = _reload_for_role(
monkeypatch, "cell_pm", "00000000-0000-0000-0000-000000000004"
)
fake_client = _make_fake_client({"status": "in_progress"})
@@ -305,13 +330,9 @@ def test_unblock_with_restore_true(monkeypatch: pytest.MonkeyPatch) -> None:
def test_unblock_with_restore_false(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000004")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "cell_pm")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
import roboco.mcp.flow_server as srv
importlib.reload(srv)
srv = _reload_for_role(
monkeypatch, "cell_pm", "00000000-0000-0000-0000-000000000004"
)
fake_client = _make_fake_client({"status": "in_progress"})
@@ -324,13 +345,9 @@ def test_unblock_with_restore_false(monkeypatch: pytest.MonkeyPatch) -> None:
def test_complete_passes_notes(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000004")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "cell_pm")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
import roboco.mcp.flow_server as srv
importlib.reload(srv)
srv = _reload_for_role(
monkeypatch, "cell_pm", "00000000-0000-0000-0000-000000000004"
)
fake_client = _make_fake_client({"status": "completed"})
@@ -344,13 +361,9 @@ def test_complete_passes_notes(monkeypatch: pytest.MonkeyPatch) -> None:
def test_escalate_up_passes_reason(monkeypatch: pytest.MonkeyPatch) -> None:
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000004")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "cell_pm")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
import roboco.mcp.flow_server as srv
importlib.reload(srv)
srv = _reload_for_role(
monkeypatch, "cell_pm", "00000000-0000-0000-0000-000000000004"
)
fake_client = _make_fake_client({"status": "blocked"})
@@ -368,13 +381,9 @@ def test_escalate_up_passes_reason(monkeypatch: pytest.MonkeyPatch) -> None:
def test_escalate_to_ceo_passes_reason(monkeypatch: pytest.MonkeyPatch) -> None:
"""Board / Main PM verb forwards to /api/v2/flow/<role>/escalate_to_ceo."""
monkeypatch.setenv("ROBOCO_AGENT_ID", "00000000-0000-0000-0000-000000000005")
monkeypatch.setenv("ROBOCO_AGENT_ROLE", "product_owner")
monkeypatch.setenv("ROBOCO_ORCHESTRATOR_URL", "http://test-orchestrator:8000")
import roboco.mcp.flow_server as srv
importlib.reload(srv)
srv = _reload_for_role(
monkeypatch, "product_owner", "00000000-0000-0000-0000-000000000005"
)
fake_client = _make_fake_client({"status": "awaiting_ceo_approval"})
@@ -383,7 +392,9 @@ def test_escalate_to_ceo_passes_reason(monkeypatch: pytest.MonkeyPatch) -> None:
assert result["status"] == "awaiting_ceo_approval"
args, kwargs = fake_client.post.call_args
assert "/api/v2/flow/product_owner/escalate_to_ceo" in args[0]
# Board route serves PO + Head Marketing under one prefix; the slug
# map in flow_server translates product_owner → board.
assert "/api/v2/flow/board/escalate_to_ceo" in args[0]
assert kwargs["json"] == {
"task_id": "task-uuid",
"reason": "strategic decision needed",
tests/unit/scripts/test_bash_guard.py
+1 -1
View File
@@ -42,7 +42,7 @@ def test_blocks_internal_curl_to_orchestrator() -> None:
def test_blocks_internal_curl_to_localhost() -> None:
assert _run("curl http://localhost:8000/api/v2/flow/dev/i_am_done") == _DENIED
assert _run("curl http://localhost:8000/api/v2/flow/developer/i_am_done") == _DENIED
def test_blocks_internal_curl_to_127() -> None:
tests/unit/services/test_task.py
+13 -6
View File
@@ -442,27 +442,34 @@ async def test_doc_claim_sets_assignment_on_awaiting_documentation() -> None:
@pytest.mark.asyncio
async def test_qa_pass_delegates_to_pass_qa() -> None:
svc = TaskService(MagicMock())
pass_qa_mock = AsyncMock(return_value=MagicMock())
_bind(svc, "pass_qa", pass_qa_mock)
qa_id = uuid4()
task_id = uuid4()
await svc.qa_pass(uuid4(), task_id, "looks good")
task = _build_task(id=task_id, claimed_by=qa_id)
svc = TaskService(MagicMock(flush=AsyncMock()))
pass_qa_mock = AsyncMock(return_value=MagicMock())
_bind(svc, "get", AsyncMock(return_value=task))
_bind(svc, "pass_qa", pass_qa_mock)
await svc.qa_pass(qa_id, task_id, "looks good")
pass_qa_mock.assert_awaited_once_with(task_id, notes="looks good", agent_role="qa")
# active_claimant_id cleared so the documenter can claim cleanly.
assert task.active_claimant_id is None
@pytest.mark.asyncio
async def test_qa_fail_appends_issues_to_dev_notes() -> None:
task = _build_task(dev_notes=None)
qa_id = uuid4()
task = _build_task(dev_notes=None, claimed_by=qa_id)
svc = TaskService(MagicMock(flush=AsyncMock()))
fail_qa_mock = AsyncMock(return_value=task)
_bind(svc, "get", AsyncMock(return_value=task))
_bind(svc, "fail_qa", fail_qa_mock)
issues = ["missing test", "no docstring"]
await svc.qa_fail(uuid4(), task.id, "blocking", issues)
await svc.qa_fail(qa_id, task.id, "blocking", issues)
assert task.dev_notes is not None
assert "missing test" in task.dev_notes
assert "no docstring" in task.dev_notes
fail_qa_mock.assert_awaited_once_with(task.id, notes="blocking", agent_role="qa")
assert task.active_claimant_id is None
# ---------------------------------------------------------------------------