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.
152 lines
4.5 KiB
Python
152 lines
4.5 KiB
Python
"""Every gateway commit message gets [task-id-short] prefix.
|
|
|
|
ContentActions.commit promises in the dev prompt that `[task-id]` is
|
|
auto-prefixed onto every commit. The gateway strips any user-supplied
|
|
prefix via `_TASK_ID_PREFIX_RE` but, before this guard, never re-added
|
|
the canonical one. These tests pin the contract.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
from roboco.services.gateway.content_actions import ContentActions, ContentActionsDeps
|
|
|
|
|
|
def _make_deps(**overrides: AsyncMock) -> ContentActionsDeps:
|
|
"""Build a ContentActionsDeps for tests; mirrors test_content_actions."""
|
|
if "task" in overrides:
|
|
task = overrides["task"]
|
|
else:
|
|
task = AsyncMock()
|
|
task.get_active_task_for_agent.return_value = None
|
|
|
|
# commit() now checks caller role; default to developer.
|
|
|
|
task.agent_for.return_value = MagicMock(role="developer")
|
|
|
|
if "git" in overrides:
|
|
git = overrides["git"]
|
|
else:
|
|
git = AsyncMock()
|
|
git.commit.return_value = {"sha": "abc12345"}
|
|
git.diff.return_value = ""
|
|
|
|
messaging = overrides.get("messaging", AsyncMock())
|
|
a2a = overrides.get("a2a", AsyncMock())
|
|
journal = overrides.get("journal", AsyncMock())
|
|
workspace = overrides.get("workspace", AsyncMock())
|
|
notifications = overrides.get("notifications", AsyncMock())
|
|
return ContentActionsDeps(
|
|
task=task,
|
|
git=git,
|
|
messaging=messaging,
|
|
a2a=a2a,
|
|
journal=journal,
|
|
workspace=workspace,
|
|
notifications=notifications,
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_commit_prefixes_with_task_id_short() -> None:
|
|
"""Plain message gets `[task-id-short] ` prepended."""
|
|
aid = uuid4()
|
|
tid = uuid4()
|
|
expected_prefix = f"[{str(tid)[:8]}]"
|
|
|
|
t = MagicMock(
|
|
id=tid,
|
|
assigned_to=aid,
|
|
plan="x",
|
|
status="in_progress",
|
|
branch_name="feature/backend/abcd1234",
|
|
)
|
|
task_svc = AsyncMock()
|
|
task_svc.get_active_task_for_agent.return_value = t
|
|
git_svc = AsyncMock()
|
|
git_svc.commit.return_value = {"sha": "deadbeef"}
|
|
|
|
deps = _make_deps(task=task_svc, git=git_svc)
|
|
actions = ContentActions(deps)
|
|
|
|
await actions.commit(
|
|
agent_id=aid,
|
|
message="feat(api): add login endpoint for session bootstrap",
|
|
)
|
|
|
|
git_svc.commit.assert_awaited()
|
|
# git.commit takes keyword-only args (branch_name, message, task_id, files)
|
|
msg = git_svc.commit.await_args.kwargs["message"]
|
|
assert msg.startswith(expected_prefix), (
|
|
f"expected {expected_prefix} prefix; got {msg!r}"
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_commit_strips_then_re_adds_prefix() -> None:
|
|
"""If the agent supplied a wrong prefix, strip it and add the canonical one."""
|
|
aid = uuid4()
|
|
tid = uuid4()
|
|
expected_prefix = f"[{str(tid)[:8]}]"
|
|
|
|
t = MagicMock(
|
|
id=tid,
|
|
assigned_to=aid,
|
|
plan="x",
|
|
status="in_progress",
|
|
branch_name="feature/backend/abcd1234",
|
|
)
|
|
task_svc = AsyncMock()
|
|
task_svc.get_active_task_for_agent.return_value = t
|
|
git_svc = AsyncMock()
|
|
git_svc.commit.return_value = {"sha": "deadbeef"}
|
|
|
|
deps = _make_deps(task=task_svc, git=git_svc)
|
|
actions = ContentActions(deps)
|
|
|
|
await actions.commit(
|
|
agent_id=aid,
|
|
message="[wrong-id] feat(api): add login endpoint for session bootstrap",
|
|
)
|
|
|
|
msg = git_svc.commit.await_args.kwargs["message"]
|
|
assert msg.startswith(expected_prefix)
|
|
assert "[wrong-id]" not in msg
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_commit_prefix_collapses_multiple_spaces() -> None:
|
|
"""`[old] foo` should become `[new] foo`, not `[new] foo`."""
|
|
aid = uuid4()
|
|
tid = uuid4()
|
|
expected_prefix = f"[{str(tid)[:8]}]"
|
|
|
|
t = MagicMock(
|
|
id=tid,
|
|
assigned_to=aid,
|
|
plan="x",
|
|
status="in_progress",
|
|
branch_name="feature/backend/abcd1234",
|
|
)
|
|
task_svc = AsyncMock()
|
|
task_svc.get_active_task_for_agent.return_value = t
|
|
git_svc = AsyncMock()
|
|
git_svc.commit.return_value = {"sha": "deadbeef"}
|
|
|
|
deps = _make_deps(task=task_svc, git=git_svc)
|
|
actions = ContentActions(deps)
|
|
|
|
await actions.commit(
|
|
agent_id=aid,
|
|
message="[old] feat(api): add login endpoint for session bootstrap",
|
|
)
|
|
|
|
msg = git_svc.commit.await_args.kwargs["message"]
|
|
# Exactly one space after the prefix bracket
|
|
assert msg.startswith(f"{expected_prefix} feat(api):"), (
|
|
f"expected single-space prefix; got {msg!r}"
|
|
)
|