Files
roboco/tests/unit/gateway/test_choreographer_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

398 lines
13 KiB
Python

"""Tests for the developer-facing Choreographer methods."""
from __future__ import annotations
from unittest.mock import AsyncMock, MagicMock
from uuid import uuid4
import pytest
from roboco.services.gateway.choreographer import Choreographer, ChoreographerDeps
def _make_deps(**overrides: AsyncMock) -> ChoreographerDeps:
task = overrides.get("task", AsyncMock())
work_session = overrides.get("work_session", AsyncMock())
git = overrides.get("git", AsyncMock())
a2a = overrides.get("a2a", AsyncMock())
journal = overrides.get("journal", AsyncMock())
audit = overrides.get("audit", AsyncMock())
evidence_repo = overrides.get("evidence_repo", AsyncMock())
# Ensure evidence_repo returns empty lists by default
for method in (
"list_unread_a2a",
"list_unread_mentions",
"list_pending_notifications",
"task_metadata_gaps",
"recent_team_activity",
"blockers_in_lane",
):
getattr(evidence_repo, method).return_value = []
return ChoreographerDeps(
task=task,
work_session=work_session,
git=git,
a2a=a2a,
journal=journal,
audit=audit,
evidence_repo=evidence_repo,
)
@pytest.mark.asyncio
async def test_give_me_work_returns_assigned_task() -> None:
agent_id = uuid4()
task_obj = MagicMock(id=uuid4(), status="pending", title="t1")
task_svc = AsyncMock()
task_svc.list_assigned_for_agent.return_value = [task_obj]
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.give_me_work(agent_id)
body = env.as_dict()
assert body["status"] == "pending"
assert body["task_id"] == str(task_obj.id)
assert "i_will_work_on" in body["next"]
@pytest.mark.asyncio
async def test_give_me_work_returns_paused_when_no_assigned() -> None:
agent_id = uuid4()
paused_obj = MagicMock(id=uuid4(), status="paused")
task_svc = AsyncMock()
task_svc.list_assigned_for_agent.return_value = []
task_svc.list_paused_for_agent.return_value = [paused_obj]
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.give_me_work(agent_id)
body = env.as_dict()
assert body["task_id"] == str(paused_obj.id)
assert "resume" in body["next"]
@pytest.mark.asyncio
async def test_give_me_work_returns_idle_when_no_work() -> None:
agent_id = uuid4()
task_svc = AsyncMock()
task_svc.list_assigned_for_agent.return_value = []
task_svc.list_paused_for_agent.return_value = []
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.give_me_work(agent_id)
body = env.as_dict()
assert body["status"] == "idle"
assert "i_am_idle" in body["next"]
@pytest.mark.asyncio
async def test_i_will_work_on_pending_with_plan() -> None:
agent_id = uuid4()
task_id = uuid4()
pending_task = MagicMock(
id=task_id,
status="pending",
plan=None,
assigned_to=None,
parent_task_id=None,
sequence=0,
task_type="code",
)
in_progress_task = MagicMock(
id=task_id, status="in_progress", plan={"text": "do x"}, assigned_to=agent_id
)
task_svc = AsyncMock()
task_svc.get.return_value = pending_task
task_svc.agent_for.return_value = MagicMock(role="developer", team="backend")
task_svc.list_in_progress_for_agent.return_value = []
task_svc.list_paused_for_agent.return_value = []
task_svc.get_subtasks.return_value = []
task_svc.claim.return_value = MagicMock(
id=task_id, status="claimed", plan=None, assigned_to=agent_id
)
task_svc.set_plan.return_value = MagicMock(
id=task_id, status="claimed", plan={"text": "do x"}, assigned_to=agent_id
)
task_svc.start.return_value = in_progress_task
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_will_work_on(agent_id, task_id, plan="do x then y")
assert env.error is None
assert env.status == "in_progress"
task_svc.claim.assert_awaited_once_with(task_id, agent_id)
task_svc.set_plan.assert_awaited_once()
task_svc.start.assert_awaited_once_with(task_id, agent_id)
@pytest.mark.asyncio
async def test_i_will_work_on_pending_no_plan_returns_tracing_gap() -> None:
agent_id = uuid4()
task_id = uuid4()
pending_task = MagicMock(
id=task_id,
status="pending",
plan=None,
assigned_to=None,
description="task description",
parent_task_id=None,
sequence=0,
task_type="code",
)
task_svc = AsyncMock()
task_svc.get.return_value = pending_task
task_svc.agent_for.return_value = MagicMock(role="developer", team="backend")
task_svc.list_in_progress_for_agent.return_value = []
task_svc.list_paused_for_agent.return_value = []
task_svc.get_subtasks.return_value = []
task_svc.claim.return_value = MagicMock(
id=task_id, status="claimed", plan=None, assigned_to=agent_id
)
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_will_work_on(agent_id, task_id, plan=None)
body = env.as_dict()
assert body["error"] == "tracing_gap"
assert "plan" in body["missing"]
assert "i_will_work_on" in body["remediate"]
@pytest.mark.asyncio
async def test_i_will_work_on_needs_revision_re_starts() -> None:
agent_id = uuid4()
task_id = uuid4()
nr_task = MagicMock(
id=task_id, status="needs_revision", assigned_to=agent_id, plan={"x": 1}
)
in_progress_task = MagicMock(
id=task_id, status="in_progress", assigned_to=agent_id, plan={"x": 1}
)
task_svc = AsyncMock()
task_svc.get.return_value = nr_task
task_svc.start.return_value = in_progress_task
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_will_work_on(agent_id, task_id)
assert env.status == "in_progress"
task_svc.claim.assert_not_awaited() # already assigned
task_svc.start.assert_awaited_once_with(task_id, agent_id)
@pytest.mark.asyncio
async def test_i_will_work_on_task_not_found_returns_not_found() -> None:
agent_id = uuid4()
task_id = uuid4()
task_svc = AsyncMock()
task_svc.get.return_value = None
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_will_work_on(agent_id, task_id)
body = env.as_dict()
assert body["error"] == "not_found"
@pytest.mark.asyncio
async def test_i_will_work_on_invalid_state_returns_invalid_state() -> None:
agent_id = uuid4()
task_id = uuid4()
completed_task = MagicMock(id=task_id, status="completed", assigned_to=agent_id)
task_svc = AsyncMock()
task_svc.get.return_value = completed_task
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_will_work_on(agent_id, task_id)
body = env.as_dict()
assert body["error"] == "invalid_state"
assert "completed" in body["message"]
# 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
async def test_i_am_done_blocks_when_acceptance_criteria_unaddressed() -> None:
agent_id = uuid4()
task_id = uuid4()
t = MagicMock(
id=task_id,
status="in_progress",
assigned_to=agent_id,
plan={"x": 1},
branch_name="feature/backend/abc",
work_session_id=uuid4(),
self_verified=False,
progress_updates=[{"message": "p"}],
acceptance_criteria=["AC1", "AC2"],
acceptance_criteria_status=[
{"criterion": "AC1", "referencing_artifact_id": "c1"}
],
commits=[],
documents=[],
dev_notes="",
)
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 any("AC2" in m for m in body["missing"])
@pytest.mark.asyncio
async def test_i_am_done_blocks_when_journal_reflect_missing() -> None:
agent_id = uuid4()
task_id = uuid4()
t = MagicMock(
id=task_id,
status="in_progress",
assigned_to=agent_id,
plan={"x": 1},
branch_name="feature/backend/abc",
work_session_id=uuid4(),
self_verified=False,
progress_updates=[{"message": "p"}],
acceptance_criteria=["AC1"],
acceptance_criteria_status=[
{"criterion": "AC1", "referencing_artifact_id": "c1"}
],
commits=[],
documents=[],
dev_notes="",
)
task_svc = AsyncMock()
task_svc.get.return_value = t
journal_svc = AsyncMock()
journal_svc.has_reflect_for_task.return_value = False # no reflect
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 "journal:reflect" in body["missing"]
@pytest.mark.asyncio
async def test_i_am_done_not_assigned_returns_not_authorized() -> None:
agent_id = uuid4()
other_agent = uuid4()
task_id = uuid4()
t = MagicMock(id=task_id, status="in_progress", assigned_to=other_agent)
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, "x")
body = env.as_dict()
assert body["error"] == "not_authorized"
@pytest.mark.asyncio
async def test_i_am_done_skill_resolution_picks_existing_skill() -> None:
"""Resolver picks first matching skill.
Falls back to the first preference entry when no match is found.
"""
deps = _make_deps()
c = Choreographer(deps)
qa = MagicMock(id=uuid4(), skills=[{"id": "qa_review"}, {"id": "test_validation"}])
skill = c._resolve_skill(qa, ["code_review", "qa_review"])
assert skill == "qa_review"
qa_with_canonical = MagicMock(id=uuid4(), skills=[{"id": "code_review"}])
skill2 = c._resolve_skill(qa_with_canonical, ["code_review", "qa_review"])
assert skill2 == "code_review"
qa_with_neither = MagicMock(id=uuid4(), skills=[{"id": "other_skill"}])
skill3 = c._resolve_skill(qa_with_neither, ["code_review", "qa_review"])
assert skill3 == "code_review" # fallback to first
@pytest.mark.asyncio
async def test_i_am_blocked_escalates_and_journals() -> None:
agent_id = uuid4()
task_id = uuid4()
t = MagicMock(
id=task_id, status="in_progress", assigned_to=agent_id, pre_block_state=None
)
after = MagicMock(id=task_id, status="blocked")
task_svc = AsyncMock()
task_svc.get.return_value = t
task_svc.escalate.return_value = after
journal_svc = AsyncMock()
deps = _make_deps(task=task_svc, journal=journal_svc)
c = Choreographer(deps)
env = await c.i_am_blocked(agent_id, task_id, "external API down")
assert env.error is None
assert env.status == "blocked"
journal_svc.write_struggle.assert_awaited_once()
task_svc.escalate.assert_awaited_once()
@pytest.mark.asyncio
async def test_i_am_blocked_task_not_found_returns_not_found() -> None:
agent_id = uuid4()
task_id = uuid4()
task_svc = AsyncMock()
task_svc.get.return_value = None
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.i_am_blocked(agent_id, task_id, "x")
body = env.as_dict()
assert body["error"] == "not_found"
@pytest.mark.asyncio
async def test_i_am_idle_with_unread_a2a_soft_blocks() -> None:
agent_id = uuid4()
deps = _make_deps()
deps.evidence_repo.list_unread_a2a.return_value = [{"from": "x", "task_id": "t1"}]
c = Choreographer(deps)
env = await c.i_am_idle(agent_id)
body = env.as_dict()
assert body["status"] == "idle_with_unread"
assert "address" in body["next"].lower()
@pytest.mark.asyncio
async def test_i_am_idle_with_unread_mentions_soft_blocks() -> None:
agent_id = uuid4()
deps = _make_deps()
deps.evidence_repo.list_unread_mentions.return_value = [
{"channel": "#x", "from": "y"}
]
c = Choreographer(deps)
env = await c.i_am_idle(agent_id)
body = env.as_dict()
assert body["status"] == "idle_with_unread"
@pytest.mark.asyncio
async def test_i_am_idle_clean_returns_idle() -> None:
agent_id = uuid4()
task_svc = AsyncMock()
deps = _make_deps(task=task_svc)
# All evidence_repo lists are already empty per _make_deps default
c = Choreographer(deps)
env = await c.i_am_idle(agent_id)
assert env.status == "idle"
task_svc.mark_agent_idle.assert_awaited_once_with(agent_id)