toki/iop
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
iop/agent-ops/skills/project/orchestrate-agent-task-loop/tests/test_dispatch.py
toki 8a4f6c55a1 sync: roadmap, skills, test inventory, streamgate package, docs updates 
- Update roadmap milestones and phase docs across multiple phases
- Update plan, code-review, create-roadmap, update-roadmap, finalize-task-routing skills
- Update dev-corp-runtime-deploy, dev-runtime-deploy, orchestrate-agent-task-loop skills
- Refactor agent-task-loop dispatch script
- Add streamgate Go package (commit_boundary, evidence_tail, filter_registry, stream_release)
- Add test inventory files (dev, dev-corp, unified)
- Update test smoke tests and rules for dev/dev-corp
- Update docs/edge-local-dev-guide and e2e scripts
- Update inventory-query Go package
- Remove deprecated templates and inventory.yaml files
- Add orchestrate-agent-task-loop tests
2026-07-25 11:41:08 +09:00

2925 lines
121 KiB
Python
Raw Blame History

import asyncio
import importlib.util
import json
import os
import signal
import sys
import tempfile
import time
import unittest
from pathlib import Path
from types import SimpleNamespace
from unittest import mock
SCRIPT = Path(__file__).parents[1] / "scripts" / "dispatch.py"
SPEC = importlib.util.spec_from_file_location("agent_task_dispatch", SCRIPT)
assert SPEC and SPEC.loader
dispatch = importlib.util.module_from_spec(SPEC)
sys.modules[SPEC.name] = dispatch
SPEC.loader.exec_module(dispatch)
def pi_session_jsonl(events, version=dispatch.PI_SESSION_SCHEMA_VERSION):
values = [
{
"type": "session",
"version": version,
"id": "test-session",
"timestamp": "2026-07-25T00:00:00.000Z",
"cwd": "/tmp/test",
}
]
parent_id = None
for index, event in enumerate(events):
value = dict(event)
value.setdefault("id", f"entry-{index}")
value.setdefault("parentId", parent_id)
values.append(value)
parent_id = value["id"]
return "".join(json.dumps(value) + "\n" for value in values)
class TaskStageTest(unittest.TestCase):
def make_task(self, root: Path, review_text: str = ""):
plan = root / "PLAN-local-G05.md"
review = root / "CODE_REVIEW-local-G05.md"
plan.write_text("<!-- task=test plan=0 tag=TEST -->\n", encoding="utf-8")
review.write_text(review_text, encoding="utf-8")
return dispatch.Task(
name="test",
directory=root,
plan=plan,
review=review,
user_review=None,
recovery=False,
lane="local",
grade=5,
)
@staticmethod
def blocking_user_review_text():
return (
"# User Review Required - test\n\n"
"## 상태\n\nUSER_REVIEW\n\n"
"## 사유\n\n"
"- 유형: milestone-lock\n"
"- 연결 대상: agent-roadmap/phase/p/milestones/m.md\n\n"
"## 차단 근거\n\n"
"- 차단 판단 근거: API ownership decision blocks implementation.\n\n"
"## 연결 결정 필요\n\n"
"- [ ] API ownership 선택\n\n"
"## 재개 조건\n\n"
"- Milestone 결정 반영 후 재개\n"
)
def test_default_or_arbitrary_status_text_does_not_start_review(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(
root,
"## 사용자 리뷰 요청\n- 상태: 없음\n"
"## unrelated\n- 상태: 확인 필요\n",
)
self.assertEqual(dispatch.task_stage(task, {}), "worker")
def test_verdict_text_outside_official_section_does_not_start_review(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(
root,
"## 검증 결과\n"
"명령 출력 예시: 종합 판정: PASS\n",
)
self.assertEqual(dispatch.task_stage(task, {}), "worker")
def test_exact_official_verdict_section_starts_review_recovery(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(
root,
"## 코드리뷰 결과\n"
"- **종합 판정**: WARN\n",
)
self.assertEqual(dispatch.task_stage(task, {}), "review")
def test_only_explicit_user_review_file_stops_the_loop(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(root, "- 상태: 없음\n")
task.user_review = root / "USER_REVIEW.md"
task.user_review.write_text(
self.blocking_user_review_text(), encoding="utf-8"
)
task.plan = None
task.review = None
task.recovery = True
self.assertEqual(dispatch.task_stage(task, {}), "user-review")
def test_user_review_without_blocking_contract_is_state_blocked(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(root)
task.user_review = root / "USER_REVIEW.md"
task.user_review.write_text(
"## 상태\n\nUSER_REVIEW\n", encoding="utf-8"
)
task.plan = None
task.review = None
task.recovery = True
self.assertEqual(dispatch.task_stage(task, {}), "blocked")
def test_user_review_with_active_pair_is_state_blocked(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(root)
task.user_review = root / "USER_REVIEW.md"
task.user_review.write_text(
self.blocking_user_review_text(), encoding="utf-8"
)
self.assertEqual(dispatch.task_stage(task, {}), "blocked")
def test_user_review_only_directory_without_logs_is_readable(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
directory = workspace / "agent-task" / "group" / "01_gate"
directory.mkdir(parents=True)
user_review = directory / "USER_REVIEW.md"
user_review.write_text(
self.blocking_user_review_text(), encoding="utf-8"
)
task = dispatch.read_task_directory(workspace, directory)
self.assertIsNotNone(task)
self.assertEqual(dispatch.task_stage(task, {}), "user-review")
def test_user_review_none_values_do_not_form_a_valid_stop(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(root)
task.user_review = root / "USER_REVIEW.md"
task.user_review.write_text(
"## 상태\n\nUSER_REVIEW\n\n"
"## 사유\n\n"
"- 유형: milestone-lock\n"
"- 연결 대상: 없음\n\n"
"## 차단 근거\n\n"
"- 차단 판단 근거: 없음\n\n"
"## 연결 결정 필요\n\n"
"- [ ] 없음\n\n"
"## 재개 조건\n\n"
"- 없음\n",
encoding="utf-8",
)
task.plan = None
task.review = None
task.recovery = True
self.assertEqual(dispatch.task_stage(task, {}), "blocked")
def test_completed_implementation_checklist_starts_review(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(
root,
"- [x] CODE_REVIEW-*-G??.md의 구현 에이전트 소유 섹션을 채운다.\n",
)
self.assertEqual(dispatch.task_stage(task, {}), "review")
def test_pi_worker_success_requires_selfcheck_before_review(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(root)
self.assertEqual(
dispatch.task_stage(task, {"worker_done": True, "selfcheck_done": False}),
"selfcheck",
)
self.assertEqual(
dispatch.task_stage(task, {"worker_done": True, "selfcheck_done": True}),
"review",
)
def test_local_route_grade_boundaries(self):
with tempfile.TemporaryDirectory() as temporary:
task = self.make_task(Path(temporary))
expected = {
5: ("pi", "ornith-fast", True),
6: ("pi", "ornith-fast", True),
7: ("pi", "laguna-s:2.1", True),
8: ("pi", "laguna-s:2.1", True),
9: ("claude", "claude-opus-4-8", False),
10: ("claude", "claude-opus-4-8", False),
}
for grade, (cli, model, local_pi) in expected.items():
with self.subTest(grade=grade):
task.grade = grade
spec = dispatch.route_agent(task)
self.assertEqual(spec.cli, cli)
self.assertEqual(spec.model, model)
self.assertEqual(spec.local_pi, local_pi)
def test_selfcheck_requires_all_implementation_review_fields(self):
with tempfile.TemporaryDirectory() as temporary:
task = self.make_task(
Path(temporary),
"## 구현 항목별 완료 여부\n\n"
"| 항목 | 완료 여부 |\n|---|---|\n| TEST-1 | [ ] |\n\n"
"## 구현 체크리스트\n\n- [ ] TEST-1\n"
"- [ ] CODE_REVIEW-*-G??.md의 구현 에이전트 소유 섹션을 채운다.\n\n"
"## 계획 대비 변경 사항\n\n_미작성_\n\n"
"## 주요 설계 결정\n\n_미작성_\n\n"
"## 검증 결과\n\n결과:\n_미실행_\n",
)
self.assertEqual(
dispatch.implementation_review_errors(task),
[
"구현 체크리스트 미완료",
"구현 항목 완료 여부 미작성",
"계획 대비 변경 사항 미작성",
"주요 설계 결정 미작성",
"검증 결과 미작성",
"CODE_REVIEW 동기화 체크 미완료",
],
)
def test_selfcheck_accepts_filled_implementation_review_fields(self):
with tempfile.TemporaryDirectory() as temporary:
task = self.make_task(
Path(temporary),
"## 구현 항목별 완료 여부\n\n"
"| 항목 | 완료 여부 |\n|---|---|\n| TEST-1 | [x] |\n\n"
"## 구현 체크리스트\n\n- [x] TEST-1\n"
"- [x] CODE_REVIEW-*-G??.md의 구현 에이전트 소유 섹션을 채운다.\n\n"
"## 계획 대비 변경 사항\n\n계획과 동일하게 구현했다.\n\n"
"## 주요 설계 결정\n\n상태 전이를 직렬화했다.\n\n"
"## 검증 결과\n\n결과: PASS (exit 0)\n",
)
self.assertEqual(dispatch.implementation_review_errors(task), [])
class LegacyWorkLogContractHelpers:
@staticmethod
def completed_replacements():
return {
"### 목표와 범위\n\n- 미작성": (
"### 목표와 범위\n\n- PLAN 범위 구현 및 검증"
),
"### 체크포인트\n\n- 기록 없음": (
"### 체크포인트\n\n"
"- 2026-07-24T00:01:00Z | 구현 | 완료 | 핵심 경로 수정 | "
"evidence=`src/test.go` | next=검증"
),
"### 예상 밖 이슈\n\n- 기록 없음": (
"### 예상 밖 이슈\n\n"
"- 2026-07-24T00:02:00Z | correctness | 계획 밖 race 가능성 | "
"impact=동시성 오류 | action=수정 및 테스트 | disposition=해결"
),
"### 검증\n\n- 기록 없음": (
"### 검증\n\n- `go test ./...` - PASS"
),
"- 상태: 미작성": "- 상태: 완료",
"- 요약: 미작성": "- 요약: 구현 및 검증 완료",
"- 완료 항목: 미작성": "- 완료 항목: 계획 체크리스트 전체",
"- 변경 파일: 미작성": "- 변경 파일: `src/test.go`",
"- 검증: 미작성": "- 검증: `go test ./...` PASS",
"- 미해결/후속: 미작성": "- 미해결/후속: 없음",
"- 예상 밖 이슈 요약: 미작성": (
"- 예상 밖 이슈 요약: race 가능성 수정 완료"
),
"- CODE_REVIEW 동기화: 미작성": "- CODE_REVIEW 동기화: 완료",
}
def make_completed_log(self, root: Path, task=None):
task = task or TaskStageTest().make_task(root)
spec = dispatch.AgentSpec("pi", "ornith:35b", "pi", local_pi=True)
execution_id = "test__p0__worker__a00"
path = dispatch.append_work_log_attempt(
task,
execution_id,
"worker",
spec,
root / "locator.json",
"2026-07-24T00:00:00+00:00",
)
text = path.read_text(encoding="utf-8")
for before, after in self.completed_replacements().items():
self.assertIn(before, text)
text = text.replace(before, after, 1)
path.write_text(text, encoding="utf-8")
return task, path, execution_id
def test_template_and_attempt_require_checkpoints_and_final_report(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = TaskStageTest().make_task(root)
spec = dispatch.AgentSpec("pi", "ornith:35b", "pi", local_pi=True)
execution_id = "test__p0__worker__a00"
path = dispatch.append_work_log_attempt(
task,
execution_id,
"worker",
spec,
root / "locator.json",
"2026-07-24T00:00:00+00:00",
)
rendered = path.read_text(encoding="utf-8")
self.assertNotIn(dispatch.WORK_LOG_TEMPLATE_START, rendered)
self.assertIn(f"## 실행 `{execution_id}`", rendered)
status, errors = dispatch.work_log_attempt_result(path, execution_id)
self.assertIsNone(status)
self.assertIn("체크포인트 미작성", errors)
self.assertIn("최종 리포트 상태 미작성", errors)
def test_completed_attempt_preserves_unexpected_issue_and_runtime_result(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
_, path, execution_id = self.make_completed_log(root)
status, errors = dispatch.work_log_attempt_result(path, execution_id)
self.assertEqual(status, "완료")
self.assertEqual(errors, [])
dispatch.append_work_log_runtime_result(
path,
execution_id,
exit_code=0,
failure_class=None,
locator=root / "locator.json",
)
text = path.read_text(encoding="utf-8")
self.assertIn("계획 밖 race 가능성", text)
self.assertIn(f"### 런타임 종료 기록 `{execution_id}`", text)
self.assertIn("- failure_class: `none`", text)
def test_checkpoint_cannot_be_replaced_with_none(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
_, path, execution_id = self.make_completed_log(root)
text = path.read_text(encoding="utf-8")
checkpoint = self.completed_replacements()[
"### 체크포인트\n\n- 기록 없음"
]
path.write_text(
text.replace(checkpoint, "### 체크포인트\n\n- 없음", 1),
encoding="utf-8",
)
status, errors = dispatch.work_log_attempt_result(path, execution_id)
self.assertEqual(status, "완료")
self.assertIn("체크포인트 형식 불일치", errors)
def test_unexpected_issue_accepts_explicit_none(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
_, path, execution_id = self.make_completed_log(root)
text = path.read_text(encoding="utf-8")
unexpected = self.completed_replacements()[
"### 예상 밖 이슈\n\n- 기록 없음"
]
path.write_text(
text.replace(unexpected, "### 예상 밖 이슈\n\n- 없음", 1),
encoding="utf-8",
)
status, errors = dispatch.work_log_attempt_result(path, execution_id)
self.assertEqual(status, "완료")
self.assertEqual(errors, [])
def test_code_review_sync_must_be_exactly_complete(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
_, path, execution_id = self.make_completed_log(root)
text = path.read_text(encoding="utf-8")
path.write_text(
text.replace(
"- CODE_REVIEW 동기화: 완료",
"- CODE_REVIEW 동기화: 실패",
1,
),
encoding="utf-8",
)
status, errors = dispatch.work_log_attempt_result(path, execution_id)
self.assertEqual(status, "완료")
self.assertIn(
"최종 리포트 CODE_REVIEW 동기화는 완료여야 한다",
errors,
)
def test_completed_review_checklist_does_not_depend_on_worker_log(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = TaskStageTest().make_task(
root,
"- [x] CODE_REVIEW-*-G??.md의 구현 에이전트 소유 섹션을 "
"실제 구현 내용과 검증 출력으로 채운다.\n"
"- [x] `WORK_LOG.md` 현재 실행 블록의 체크포인트, 예상 밖 이슈, "
"검증, 최종 리포트를 모두 채운다. 이 항목이 완료되기 전에는 "
"구현이 완료된 것이 아니다.\n",
)
task.plan.write_text(
task.plan.read_text(encoding="utf-8")
+ "## 작업 로그 계약\n",
encoding="utf-8",
)
self.assertEqual(dispatch.task_stage(task, {}), "review")
def test_prompt_requires_checkpoints_unexpected_issues_and_final_report(self):
path = Path("/tmp/task/WORK_LOG.md")
prompt = dispatch.work_log_prompt(path, "task__p0__worker__a00")
self.assertIn("checkpoint after each meaningful phase", prompt)
self.assertIn("unexpected issues", prompt)
self.assertIn("최종 리포트", prompt)
self.assertIn("CODE_REVIEW", prompt)
def test_state_loss_skips_execution_id_already_present_in_work_log(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task, _, _ = self.make_completed_log(root)
store = mock.Mock()
store.next_attempt.side_effect = [0, 1]
attempt, execution_id = dispatch.next_execution_identity(
store,
task,
"worker",
)
self.assertEqual(attempt, 1)
self.assertEqual(execution_id, "test__p0__worker__a01")
self.assertEqual(store.next_attempt.call_count, 2)
class WorkLogInvokeIntegrationTest(unittest.IsolatedAsyncioTestCase):
def test_work_log_timestamp_uses_kst_offset(self):
self.assertRegex(dispatch.work_log_now_iso(), r"\+09:00$")
self.assertRegex(dispatch.now_iso(), r"\+00:00$")
async def test_invoke_writes_dispatcher_owned_milestone_timeline(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = TaskStageTest().make_task(workspace)
store = dispatch.StateStore(workspace)
command = [sys.executable, "-c", "print('work complete', flush=True)"]
spec = dispatch.AgentSpec("pi", "ornith:35b", "pi", local_pi=True)
try:
with mock.patch.object(
dispatch,
"build_command",
return_value=command,
) as build_command:
rc, failure, locator = await dispatch.invoke(
workspace,
store,
task,
"worker",
spec,
"Read the plan.",
)
finally:
store.close()
self.assertEqual(rc, 0)
self.assertIsNone(failure)
record = json.loads(locator.read_text(encoding="utf-8"))
self.assertEqual(
record["work_log"],
str((workspace / dispatch.WORK_LOG_NAME).resolve()),
)
self.assertEqual(record["status"], "succeeded")
prompt = build_command.call_args.args[1]
self.assertEqual(prompt, "Read the plan.")
self.assertNotIn("checkpoint after each meaningful phase", prompt)
log = (workspace / dispatch.WORK_LOG_NAME).read_text(encoding="utf-8")
self.assertIn("Dispatcher-owned execution timeline", log)
self.assertRegex(log, r"\| \d+ \| [^|\n]+\+09:00 \| START \|")
self.assertRegex(log, r"\| \d+ \| [^|\n]+\+09:00 \| FINISH \|")
self.assertIn("| START | test | worker | 0 | pi | running |", log)
self.assertIn("| FINISH | test | worker | 0 | pi | succeeded:0 |", log)
async def test_invoke_does_not_require_model_written_work_log(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = TaskStageTest().make_task(workspace)
store = dispatch.StateStore(workspace)
command = [sys.executable, "-c", "print('done without report')"]
spec = dispatch.AgentSpec("pi", "ornith:35b", "pi", local_pi=True)
try:
with mock.patch.object(
dispatch,
"build_command",
return_value=command,
):
rc, failure, locator = await dispatch.invoke(
workspace,
store,
task,
"worker",
spec,
"Read the plan.",
)
finally:
store.close()
self.assertEqual(rc, 0)
self.assertIsNone(failure)
record = json.loads(locator.read_text(encoding="utf-8"))
self.assertEqual(record["status"], "succeeded")
self.assertNotIn("work_log_contract_errors", record)
async def test_existing_milestone_log_is_preserved_and_extended(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = TaskStageTest().make_task(workspace)
(workspace / dispatch.WORK_LOG_NAME).write_text(
"# malformed\n",
encoding="utf-8",
)
store = dispatch.StateStore(workspace)
spec = dispatch.AgentSpec("pi", "ornith:35b", "pi", local_pi=True)
command = [sys.executable, "-c", "print('done')"]
try:
with mock.patch.object(
dispatch, "build_command", return_value=command
) as build_command:
rc, failure, locator = await dispatch.invoke(
workspace,
store,
task,
"worker",
spec,
"Read the plan.",
)
finally:
store.close()
self.assertEqual(rc, 0)
self.assertIsNone(failure)
build_command.assert_called_once()
record = json.loads(locator.read_text(encoding="utf-8"))
self.assertEqual(record["status"], "succeeded")
log = (workspace / dispatch.WORK_LOG_NAME).read_text(encoding="utf-8")
self.assertIn("# malformed", log)
self.assertIn("## Dispatcher Timeline", log)
async def test_runtime_log_write_failure_finishes_locator_as_blocked_failure(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = TaskStageTest().make_task(workspace)
store = dispatch.StateStore(workspace)
command = [sys.executable, "-c", "print('done')"]
spec = dispatch.AgentSpec("pi", "ornith:35b", "pi", local_pi=True)
try:
with (
mock.patch.object(
dispatch,
"build_command",
return_value=command,
),
mock.patch.object(
dispatch,
"append_milestone_event",
side_effect=[
workspace / dispatch.WORK_LOG_NAME,
OSError("disk full"),
],
),
):
rc, failure, locator = await dispatch.invoke(
workspace,
store,
task,
"worker",
spec,
"Read the plan.",
)
finally:
store.close()
self.assertEqual(rc, 0)
self.assertEqual(failure, "work-log-runtime-write")
record = json.loads(locator.read_text(encoding="utf-8"))
self.assertEqual(record["status"], "failed")
self.assertEqual(record["failure_class"], "work-log-runtime-write")
self.assertEqual(record["work_log_runtime_error"], "disk full")
async def test_cancelled_invoke_finishes_locator_and_runtime_record(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = TaskStageTest().make_task(workspace)
store = dispatch.StateStore(workspace)
command = [
sys.executable,
"-c",
"import time; print('ready', flush=True); time.sleep(60)",
]
spec = dispatch.AgentSpec("pi", "ornith:35b", "pi", local_pi=True)
invocation = None
try:
with mock.patch.object(
dispatch,
"build_command",
return_value=command,
):
invocation = asyncio.create_task(
dispatch.invoke(
workspace,
store,
task,
"worker",
spec,
"Read the plan.",
)
)
locator = None
for _ in range(100):
candidates = list(store.runs.glob("*/locator.json"))
if candidates:
candidate = candidates[0]
record = json.loads(
candidate.read_text(encoding="utf-8")
)
output = Path(record["output_log"])
if (
output.is_file()
and "ready" in output.read_text(encoding="utf-8")
):
locator = candidate
break
await asyncio.sleep(0.01)
self.assertIsNotNone(locator)
invocation.cancel()
with self.assertRaises(asyncio.CancelledError):
await invocation
finally:
if invocation is not None and not invocation.done():
invocation.cancel()
await asyncio.gather(invocation, return_exceptions=True)
store.close()
assert locator is not None
record = json.loads(locator.read_text(encoding="utf-8"))
self.assertEqual(record["status"], "failed")
self.assertEqual(record["exit_code"], "cancelled")
self.assertEqual(record["failure_class"], "cancelled")
log = (workspace / dispatch.WORK_LOG_NAME).read_text(encoding="utf-8")
self.assertIn("| FINISH | test | worker | 0 | pi | failed:cancelled |", log)
async def test_heartbeat_updates_output_and_locator_with_pi_native_session(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = TaskStageTest().make_task(workspace)
store = dispatch.StateStore(workspace)
session_id = "11111111-1111-1111-1111-111111111111"
def command_for(
spec,
prompt,
cwd,
actual_session_id,
attempt_dir,
pi_resume_session=None,
):
self.assertEqual(actual_session_id, session_id)
native = attempt_dir / "pi-sessions" / f"session_{session_id}.jsonl"
child = (
"from pathlib import Path\n"
"import sys,time\n"
"path = Path(sys.argv[1])\n"
"path.parent.mkdir(parents=True, exist_ok=True)\n"
"path.write_text("
"'{\"type\":\"session\",\"version\":3,\"id\":\"test\","
"\"timestamp\":\"2026-07-25T00:00:00.000Z\","
"\"cwd\":\"/tmp/test\"}\\n', encoding='utf-8')\n"
"time.sleep(0.05)\n"
"print('done', flush=True)\n"
)
return [sys.executable, "-c", child, str(native)]
spec = dispatch.AgentSpec("pi", "ornith-fast", "pi", local_pi=True)
try:
with (
mock.patch.object(dispatch, "build_command", side_effect=command_for),
mock.patch.object(dispatch.uuid, "uuid4", return_value=session_id),
mock.patch.object(dispatch, "STREAM_HEARTBEAT_SECONDS", 0.01),
):
rc, failure, locator = await dispatch.invoke(
workspace, store, task, "review", spec, "Reply briefly."
)
finally:
store.close()
self.assertEqual(rc, 0)
self.assertIsNone(failure)
record = json.loads(locator.read_text(encoding="utf-8"))
self.assertTrue(record["native_session_path"].endswith(f"{session_id}.jsonl"))
self.assertIsInstance(record["native_session_mtime_ns"], int)
heartbeat = Path(record["heartbeat_log"]).read_text(encoding="utf-8")
self.assertIn("[heartbeat] 작업중...", heartbeat)
self.assertIn("native_session=", heartbeat)
self.assertIn("native_mtime_ns=", heartbeat)
stream = Path(record["stream_log"]).read_text(encoding="utf-8")
self.assertIn("[stdout] done", stream)
self.assertNotIn("[heartbeat]", stream)
async def test_pi_silent_awaiting_model_is_inspected_without_termination(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = TaskStageTest().make_task(workspace)
store = dispatch.StateStore(workspace)
session_id = "22222222-2222-2222-2222-222222222222"
def command_for(
spec,
prompt,
cwd,
actual_session_id,
attempt_dir,
pi_resume_session=None,
):
native = attempt_dir / "pi-sessions" / f"session_{session_id}.jsonl"
child = (
"from pathlib import Path\n"
"import sys,time\n"
"path = Path(sys.argv[1])\n"
"path.parent.mkdir(parents=True, exist_ok=True)\n"
"path.write_text("
"'{\"type\":\"session\",\"version\":3,\"id\":\"test\","
"\"timestamp\":\"2026-07-25T00:00:00.000Z\","
"\"cwd\":\"/tmp/test\"}\\n"
"{\"type\":\"message\",\"id\":\"assistant-1\","
"\"parentId\":null,\"message\":{\"role\":\"assistant\","
"\"content\":[{\"type\":\"toolCall\",\"id\":\"call-1\","
"\"name\":\"read\"}]}}\\n"
"{\"type\":\"message\",\"id\":\"result-1\","
"\"parentId\":\"assistant-1\","
"\"message\":{\"role\":\"toolResult\","
"\"toolCallId\":\"call-1\",\"content\":[]}}\\n', "
"encoding='utf-8')\n"
"time.sleep(0.08)\n"
)
return [sys.executable, "-c", child, str(native)]
spec = dispatch.AgentSpec("pi", "laguna-s:2.1", "pi", local_pi=True)
try:
with (
mock.patch.object(dispatch, "build_command", side_effect=command_for),
mock.patch.object(dispatch.uuid, "uuid4", return_value=session_id),
mock.patch.object(dispatch, "STREAM_HEARTBEAT_SECONDS", 0.01),
mock.patch.object(
dispatch, "PI_MODEL_RESPONSE_STALL_SECONDS", 0.03
),
):
rc, failure, locator = await dispatch.invoke(
workspace, store, task, "review", spec, "Reply briefly."
)
finally:
store.close()
self.assertEqual(rc, 0)
self.assertIsNone(failure)
record = json.loads(locator.read_text(encoding="utf-8"))
self.assertEqual(record["status"], "succeeded")
self.assertEqual(record["pi_session_phase"], "awaiting-model")
self.assertEqual(
record["pi_session_phase_reason"],
"all-tool-results-recorded",
)
self.assertEqual(record["pi_expected_tool_call_ids"], ["call-1"])
self.assertEqual(record["pi_completed_tool_call_ids"], ["call-1"])
self.assertEqual(record["pi_pending_tool_call_ids"], [])
inspection = record["pi_silence_inspection"]
self.assertGreaterEqual(inspection["silence_seconds"], 0.03)
self.assertIn("stream_tail", inspection)
heartbeat = Path(record["heartbeat_log"]).read_text(encoding="utf-8")
self.assertIn("[silence-inspection]", heartbeat)
async def test_pi_silent_starting_state_is_inspected_without_termination(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = TaskStageTest().make_task(workspace)
store = dispatch.StateStore(workspace)
session_id = "24242424-2424-2424-2424-242424242424"
def command_for(
spec,
prompt,
cwd,
actual_session_id,
attempt_dir,
pi_resume_session=None,
):
native = attempt_dir / "pi-sessions" / f"session_{session_id}.jsonl"
child = (
"from pathlib import Path\n"
"import sys,time\n"
"path = Path(sys.argv[1])\n"
"path.parent.mkdir(parents=True, exist_ok=True)\n"
"path.write_text("
"'{\"type\":\"session\",\"version\":3,\"id\":\"test\","
"\"timestamp\":\"2026-07-25T00:00:00.000Z\","
"\"cwd\":\"/tmp/test\"}\\n', encoding='utf-8')\n"
"time.sleep(0.08)\n"
)
return [sys.executable, "-c", child, str(native)]
spec = dispatch.AgentSpec("pi", "laguna-s:2.1", "pi", local_pi=True)
try:
with (
mock.patch.object(dispatch, "build_command", side_effect=command_for),
mock.patch.object(dispatch.uuid, "uuid4", return_value=session_id),
mock.patch.object(dispatch, "STREAM_HEARTBEAT_SECONDS", 0.01),
mock.patch.object(
dispatch, "PI_MODEL_RESPONSE_STALL_SECONDS", 0.03
),
mock.patch.object(
dispatch, "PI_SESSION_START_STALL_SECONDS", 0.03
),
):
rc, failure, locator = await dispatch.invoke(
workspace, store, task, "review", spec, "Reply briefly."
)
finally:
store.close()
self.assertEqual(rc, 0)
self.assertIsNone(failure)
record = json.loads(locator.read_text(encoding="utf-8"))
self.assertEqual(record["status"], "succeeded")
self.assertEqual(record["pi_session_phase"], "starting")
self.assertIsNone(record["pi_stall_timeout_seconds"])
self.assertIn("pi_silence_inspection", record)
heartbeat = Path(record["heartbeat_log"]).read_text(encoding="utf-8")
self.assertNotIn("[session-stall]", heartbeat)
async def test_pi_json_stream_progress_prevents_native_only_stall(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = TaskStageTest().make_task(workspace)
store = dispatch.StateStore(workspace)
session_id = "23232323-2323-2323-2323-232323232323"
def command_for(
spec,
prompt,
cwd,
actual_session_id,
attempt_dir,
pi_resume_session=None,
):
native = attempt_dir / "pi-sessions" / f"session_{session_id}.jsonl"
child = (
"from pathlib import Path\n"
"import json,sys,time\n"
"path = Path(sys.argv[1])\n"
"path.parent.mkdir(parents=True, exist_ok=True)\n"
"path.write_text("
"'{\"type\":\"session\",\"version\":3,\"id\":\"test\","
"\"timestamp\":\"2026-07-25T00:00:00.000Z\","
"\"cwd\":\"/tmp/test\"}\\n', encoding='utf-8')\n"
"for _ in range(8):\n"
" print(json.dumps({'type': 'message_update'}), flush=True)\n"
" time.sleep(0.015)\n"
)
return [sys.executable, "-c", child, str(native)]
spec = dispatch.AgentSpec("pi", "laguna-s:2.1", "pi", local_pi=True)
try:
with (
mock.patch.object(dispatch, "build_command", side_effect=command_for),
mock.patch.object(dispatch.uuid, "uuid4", return_value=session_id),
mock.patch.object(dispatch, "STREAM_HEARTBEAT_SECONDS", 0.01),
mock.patch.object(
dispatch, "PI_SESSION_START_STALL_SECONDS", 0.03
),
):
rc, failure, locator = await dispatch.invoke(
workspace, store, task, "review", spec, "Reply briefly."
)
finally:
store.close()
self.assertEqual(rc, 0)
self.assertIsNone(failure)
record = json.loads(locator.read_text(encoding="utf-8"))
self.assertEqual(record["status"], "succeeded")
self.assertEqual(record["pi_activity_state"], "streaming")
stream = Path(record["stream_log"]).read_text(encoding="utf-8")
self.assertIn('[stdout] {"type": "message_update"}', stream)
async def test_pi_incomplete_sequential_batch_uses_tool_timeout(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = TaskStageTest().make_task(workspace)
store = dispatch.StateStore(workspace)
session_id = "33333333-3333-3333-3333-333333333333"
def command_for(
spec,
prompt,
cwd,
actual_session_id,
attempt_dir,
pi_resume_session=None,
):
native = attempt_dir / "pi-sessions" / f"session_{session_id}.jsonl"
child = (
"from pathlib import Path\n"
"import sys,time\n"
"path = Path(sys.argv[1])\n"
"path.parent.mkdir(parents=True, exist_ok=True)\n"
"path.write_text("
"'{\"type\":\"session\",\"version\":3,\"id\":\"test\","
"\"timestamp\":\"2026-07-25T00:00:00.000Z\","
"\"cwd\":\"/tmp/test\"}\\n"
"{\"type\":\"message\",\"id\":\"assistant-1\","
"\"parentId\":null,\"message\":{\"role\":\"assistant\","
"\"content\":[{\"type\":\"toolCall\",\"id\":\"call-a\","
"\"name\":\"read\"},{\"type\":\"toolCall\",\"id\":\"call-b\","
"\"name\":\"bash\"}]}}\\n"
"{\"type\":\"message\",\"id\":\"result-a\","
"\"parentId\":\"assistant-1\","
"\"message\":{\"role\":\"toolResult\","
"\"toolCallId\":\"call-a\",\"content\":[]}}\\n', "
"encoding='utf-8')\n"
"time.sleep(0.08)\n"
"with path.open('a', encoding='utf-8') as stream:\n"
" stream.write("
"'{\"type\":\"message\",\"id\":\"result-b\","
"\"parentId\":\"result-a\","
"\"message\":{\"role\":\"toolResult\","
"\"toolCallId\":\"call-b\",\"content\":[]}}\\n')\n"
"print('done', flush=True)\n"
)
return [sys.executable, "-c", child, str(native)]
spec = dispatch.AgentSpec(
"pi", "laguna-s:2.1", "pi", local_pi=True
)
try:
with (
mock.patch.object(
dispatch, "build_command", side_effect=command_for
),
mock.patch.object(
dispatch.uuid, "uuid4", return_value=session_id
),
mock.patch.object(
dispatch, "STREAM_HEARTBEAT_SECONDS", 0.01
),
mock.patch.object(
dispatch, "PI_MODEL_RESPONSE_STALL_SECONDS", 0.02
),
mock.patch.object(dispatch, "PI_TOOL_STALL_SECONDS", 1.0),
):
rc, failure, locator = await dispatch.invoke(
workspace, store, task, "review", spec, "Reply briefly."
)
finally:
store.close()
self.assertEqual(rc, 0)
self.assertIsNone(failure)
record = json.loads(locator.read_text(encoding="utf-8"))
heartbeat = Path(record["heartbeat_log"]).read_text(encoding="utf-8")
self.assertNotIn("[session-stall]", heartbeat)
async def test_resume_heartbeat_preserves_prior_native_session_path(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = TaskStageTest().make_task(workspace)
store = dispatch.StateStore(workspace)
native = workspace / "prior-session.jsonl"
native.write_text(pi_session_jsonl([]), encoding="utf-8")
prior_locator = workspace / "prior-locator.json"
prior_locator.write_text(
json.dumps(
{
"session_id": "resume-session",
"native_session_path": str(native),
}
),
encoding="utf-8",
)
def command_for(
spec,
prompt,
cwd,
actual_session_id,
attempt_dir,
pi_resume_session=None,
):
self.assertEqual(pi_resume_session, native)
return [
sys.executable,
"-c",
"import time; time.sleep(0.05); print('done', flush=True)",
]
spec = dispatch.AgentSpec(
"pi", "laguna-s:2.1", "pi", local_pi=True
)
try:
with (
mock.patch.object(
dispatch, "build_command", side_effect=command_for
),
mock.patch.object(
dispatch, "STREAM_HEARTBEAT_SECONDS", 0.01
),
):
rc, failure, locator = await dispatch.invoke(
workspace,
store,
task,
"review",
spec,
"Continue.",
resume_locator=prior_locator,
)
finally:
store.close()
self.assertEqual(rc, 0)
self.assertIsNone(failure)
record = json.loads(locator.read_text(encoding="utf-8"))
self.assertEqual(record["native_session_path"], str(native))
self.assertEqual(
record["resumed_from_locator"], str(prior_locator)
)
async def test_provider_stderr_requires_and_preserves_exact_evidence(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = TaskStageTest().make_task(workspace)
store = dispatch.StateStore(workspace)
provider_line = (
"provider_tunnel_error: dial tcp 192.0.2.1:8001: "
"connect: connection refused"
)
command = [
sys.executable,
"-c",
"import sys; sys.stderr.write(sys.argv[1] + '\\n'); "
"raise SystemExit(1)",
provider_line,
]
spec = dispatch.AgentSpec(
"pi", "ornith-fast", "pi", local_pi=True
)
try:
with mock.patch.object(
dispatch,
"build_command",
return_value=command,
):
rc, failure, locator = await dispatch.invoke(
workspace, store, task, "worker", spec, "Read the plan."
)
finally:
store.close()
self.assertEqual(rc, 1)
self.assertEqual(failure, "provider-connection")
record = json.loads(locator.read_text(encoding="utf-8"))
self.assertEqual(
record["failure_source"], "provider-terminal-diagnostic"
)
self.assertTrue(record["provider_transport_failure_confirmed"])
self.assertEqual(record["failure_evidence_source"], "pi:stderr")
self.assertEqual(record["failure_evidence_excerpt"], provider_line)
self.assertEqual(record["dispatcher_pid"], dispatch.os.getpid())
self.assertEqual(
record["dispatcher_source_path"], str(dispatch.DISPATCHER_SOURCE_PATH)
)
self.assertEqual(
record["dispatcher_source_sha256"],
dispatch.DISPATCHER_SOURCE_SHA256,
)
self.assertEqual(
record["dispatcher_source_current_sha256"],
dispatch.DISPATCHER_SOURCE_SHA256,
)
self.assertTrue(record["dispatcher_source_matches_loaded"])
self.assertEqual(
dispatch.DISPATCHER_SOURCE_SHA256,
dispatch.sha256_file(SCRIPT),
)
report = dispatch.failure_report_lines(failure, locator)
self.assertIn("provider_transport_failure_confirmed=true", report)
self.assertIn(f"dispatcher_pid={dispatch.os.getpid()}", report)
self.assertIn(
f"dispatcher_source_sha256={dispatch.DISPATCHER_SOURCE_SHA256}",
report,
)
self.assertIn(
"dispatcher_source_matches_loaded=true",
report,
)
self.assertIn(f"provider_evidence={provider_line}", report)
async def test_exit_143_is_process_termination_not_provider_failure(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = TaskStageTest().make_task(workspace)
store = dispatch.StateStore(workspace)
provider_line = (
"provider_tunnel_error: dial tcp 192.0.2.1:8001: "
"connect: connection refused"
)
spec = dispatch.AgentSpec(
"pi", "ornith-fast", "pi", local_pi=True
)
try:
with mock.patch.object(
dispatch,
"build_command",
return_value=[
sys.executable,
"-c",
"import sys; sys.stderr.write(sys.argv[1] + '\\n'); "
"raise SystemExit(143)",
provider_line,
],
):
rc, failure, locator = await dispatch.invoke(
workspace, store, task, "worker", spec, "Read the plan."
)
finally:
store.close()
self.assertEqual(rc, 143)
self.assertEqual(failure, "process-terminated")
record = json.loads(locator.read_text(encoding="utf-8"))
self.assertEqual(record["failure_source"], "process-termination")
self.assertFalse(record["provider_transport_failure_confirmed"])
self.assertEqual(record["termination_signal"], "SIGTERM")
self.assertTrue(record["termination_signal_inferred"])
self.assertEqual(record["termination_initiator"], "unknown")
class ReviewControlTest(unittest.TestCase):
def test_classifies_provider_tunnel_connection_refusal(self):
provider_line = (
"provider_tunnel_error: dial tcp 192.0.2.1:8001: "
"connect: connection refused"
)
self.assertEqual(
dispatch.classify_failure(provider_line),
"provider-connection",
)
self.assertEqual(
dispatch.classify_failure_with_evidence(
f"unrelated warning\n{provider_line}"
),
("provider-connection", provider_line),
)
def test_generic_tool_stderr_is_not_provider_transport_evidence(self):
weak_lines = [
"pytest setup failed: connection refused while opening fixture",
"dial tcp 127.0.0.1:9999: connect: connection refused",
"curl error: failure when receiving data from the peer",
]
for line in weak_lines:
with self.subTest(line=line):
self.assertEqual(
dispatch.classify_failure_with_evidence(line),
("generic-error", None),
)
def test_provider_stream_requires_strong_backend_or_sse_context(self):
line = (
"Backend for model crashed before streaming started: "
"SSE stream before DONE"
)
self.assertEqual(
dispatch.classify_failure_with_evidence(line),
("provider-stream-disconnect", line),
)
def test_pi_stdout_provider_words_are_not_terminal_diagnostics(self):
line = "provider_tunnel_error: connection refused"
self.assertIsNone(dispatch.terminal_diagnostic("pi", "stdout", line))
def test_dispatcher_source_provenance_detects_hot_edit(self):
changed_sha256 = "f" * 64
self.assertNotEqual(changed_sha256, dispatch.DISPATCHER_SOURCE_SHA256)
with mock.patch.object(
dispatch,
"sha256_file",
return_value=changed_sha256,
):
provenance = dispatch.dispatcher_source_provenance()
self.assertEqual(
provenance["dispatcher_source_sha256"],
dispatch.DISPATCHER_SOURCE_SHA256,
)
self.assertEqual(
provenance["dispatcher_source_current_sha256"], changed_sha256
)
self.assertFalse(provenance["dispatcher_source_matches_loaded"])
def test_pi_phase_reads_large_last_jsonl_event(self):
with tempfile.TemporaryDirectory() as temporary:
path = Path(temporary) / "session.jsonl"
path.write_text(
pi_session_jsonl(
[
{
"type": "message",
"message": {
"role": "assistant",
"content": [
{
"type": "toolCall",
"id": "large-result",
"name": "read",
}
],
},
},
{
"type": "message",
"message": {
"role": "toolResult",
"toolCallId": "large-result",
"content": [
{"type": "text", "text": "x" * 20000}
],
},
},
]
),
encoding="utf-8",
)
self.assertEqual(
dispatch.pi_native_session_phase(str(path)),
"awaiting-model",
)
def test_pi_phase_keeps_incomplete_sequential_batch_tool_running(self):
with tempfile.TemporaryDirectory() as temporary:
path = Path(temporary) / "session.jsonl"
events = [
{
"type": "message",
"message": {
"role": "assistant",
"content": [
{"type": "toolCall", "id": "call-a", "name": "read"},
{"type": "toolCall", "id": "call-b", "name": "bash"},
],
},
},
{
"type": "message",
"message": {
"role": "toolResult",
"toolCallId": "call-a",
"content": [],
},
},
]
path.write_text(
pi_session_jsonl(events),
encoding="utf-8",
)
state = dispatch.pi_native_session_state(str(path))
self.assertEqual(state.phase, "tool-running")
self.assertEqual(state.expected_tool_call_ids, ("call-a", "call-b"))
self.assertEqual(state.completed_tool_call_ids, ("call-a",))
self.assertEqual(state.pending_tool_call_ids, ("call-b",))
self.assertEqual(
dispatch.pi_stall_timeout_seconds(state.phase),
dispatch.PI_TOOL_STALL_SECONDS,
)
def test_pi_phase_waits_for_model_only_after_entire_batch_completes(self):
with tempfile.TemporaryDirectory() as temporary:
path = Path(temporary) / "session.jsonl"
events = [
{
"type": "message",
"message": {
"role": "assistant",
"content": [
{"type": "toolCall", "id": "call-a", "name": "read"},
{"type": "toolCall", "id": "call-b", "name": "bash"},
],
},
},
{
"type": "message",
"message": {
"role": "toolResult",
"toolCallId": "call-a",
"content": [],
},
},
{
"type": "message",
"message": {
"role": "toolResult",
"toolCallId": "call-b",
"content": [],
},
},
]
path.write_text(
pi_session_jsonl(events),
encoding="utf-8",
)
state = dispatch.pi_native_session_state(str(path))
self.assertEqual(state.phase, "awaiting-model")
self.assertEqual(state.completed_tool_call_ids, ("call-a", "call-b"))
self.assertEqual(state.pending_tool_call_ids, ())
self.assertEqual(
dispatch.pi_stall_timeout_seconds(state.phase),
dispatch.PI_MODEL_RESPONSE_STALL_SECONDS,
)
def test_pi_phase_uses_conservative_timeout_for_unknown_schema(self):
with tempfile.TemporaryDirectory() as temporary:
path = Path(temporary) / "session.jsonl"
path.write_text(
pi_session_jsonl(
[
{
"type": "message",
"message": {
"role": "toolResult",
"content": [],
},
},
]
),
encoding="utf-8",
)
state = dispatch.pi_native_session_state(str(path))
self.assertEqual(state.phase, "unknown")
self.assertEqual(state.reason, "tool-result-id-missing")
self.assertEqual(
dispatch.pi_stall_timeout_seconds(state.phase),
dispatch.PI_TOOL_STALL_SECONDS,
)
def test_pi_phase_does_not_treat_unknown_assistant_content_as_final(self):
with tempfile.TemporaryDirectory() as temporary:
path = Path(temporary) / "session.jsonl"
path.write_text(
pi_session_jsonl(
[
{
"type": "message",
"message": {
"role": "assistant",
"content": [
{
"type": "futureToolCall",
"id": "unknown-call",
}
],
},
},
]
),
encoding="utf-8",
)
state = dispatch.pi_native_session_state(str(path))
self.assertEqual(state.phase, "unknown")
self.assertEqual(state.reason, "unsupported-assistant-content")
self.assertEqual(
dispatch.pi_stall_timeout_seconds(state.phase),
dispatch.PI_TOOL_STALL_SECONDS,
)
def test_pi_phase_uses_conservative_timeout_for_future_session_version(self):
with tempfile.TemporaryDirectory() as temporary:
path = Path(temporary) / "session.jsonl"
path.write_text(
pi_session_jsonl(
[
{
"type": "message",
"message": {
"role": "user",
"content": [],
},
},
],
version=dispatch.PI_SESSION_SCHEMA_VERSION + 1,
),
encoding="utf-8",
)
state = dispatch.pi_native_session_state(str(path))
self.assertEqual(state.phase, "unknown")
self.assertEqual(
state.reason,
f"unsupported-session-version:"
f"{dispatch.PI_SESSION_SCHEMA_VERSION + 1}",
)
self.assertEqual(
dispatch.pi_stall_timeout_seconds(state.phase),
dispatch.PI_TOOL_STALL_SECONDS,
)
def test_pi_phase_uses_conservative_timeout_for_corrupt_session_entries(self):
header = pi_session_jsonl([]).encode()
cases = {
"missing-parent": header
+ json.dumps(
{
"type": "message",
"id": "message-without-parent",
"message": {
"role": "user",
"content": [],
},
}
).encode()
+ b"\n",
"invalid-utf8": header + b'{"type":"message","id":"bad-\\xff"}\n',
}
for name, content in cases.items():
with self.subTest(name=name), tempfile.TemporaryDirectory() as temporary:
path = Path(temporary) / "session.jsonl"
path.write_bytes(content)
state = dispatch.pi_native_session_state(str(path))
self.assertEqual(state.phase, "unknown")
self.assertEqual(
dispatch.pi_stall_timeout_seconds(state.phase),
dispatch.PI_TOOL_STALL_SECONDS,
)
def test_pi_phase_follows_only_the_active_session_branch(self):
with tempfile.TemporaryDirectory() as temporary:
path = Path(temporary) / "session.jsonl"
path.write_text(
pi_session_jsonl(
[
{
"type": "message",
"id": "root-user",
"parentId": None,
"message": {
"role": "user",
"content": [],
},
},
{
"type": "message",
"id": "abandoned-assistant",
"parentId": "root-user",
"message": {
"role": "assistant",
"content": [{"type": "text", "text": "done"}],
},
},
{
"type": "custom",
"id": "active-branch-marker",
"parentId": "root-user",
},
]
),
encoding="utf-8",
)
state = dispatch.pi_native_session_state(str(path))
self.assertEqual(state.phase, "awaiting-model")
self.assertEqual(state.reason, "user-message")
def test_detects_codex_collaboration_wait(self):
line = (
'{"type":"item.started","item":{"type":"collab_tool_call",'
'"tool":"wait"}}'
)
self.assertEqual(dispatch.codex_collaboration_tool(line), "wait")
def test_ignores_completed_or_non_json_events(self):
self.assertIsNone(
dispatch.codex_collaboration_tool(
'{"type":"item.completed","item":{"type":"collab_tool_call",'
'"tool":"wait"}}'
)
)
self.assertIsNone(dispatch.codex_collaboration_tool("not json"))
def test_prompts_keep_local_work_and_official_review_roles_separate(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = TaskStageTest().make_task(root)
pi = dispatch.AgentSpec("pi", "ornith:35b", "pi", local_pi=True)
selfcheck = dispatch.base_prompt(task, "selfcheck", pi)
review = dispatch.base_prompt(
task,
"review",
dispatch.AgentSpec("codex", "gpt-5.6-sol", "codex"),
)
self.assertNotIn("USER_REVIEW", selfcheck)
self.assertNotIn("user review", selfcheck.lower())
self.assertEqual(
selfcheck,
f"Think in English. Final in Korean. Read {task.review.resolve()} "
"and fill every missing implementation field. Do not finish until "
"all implementation fields are complete. This is a self-check of "
f"completed work, not a review. Read {task.plan.resolve()} and "
"finish any missing work. Recheck and fix your work.",
)
self.assertEqual(
review,
f"Read {task.review.resolve()} and start the review. Final in Korean.",
)
def test_local_review_stub_has_no_user_review_control_plane_content(self):
template = (
Path(__file__).parents[3]
/ "common"
/ "plan"
/ "templates"
/ "review-stub-template.md"
).read_text(encoding="utf-8")
self.assertNotIn("USER_REVIEW", template)
self.assertNotIn("사용자 리뷰", template)
self.assertNotIn("user-review", template)
self.assertNotIn("## 작업 로그 계약", template)
self.assertNotIn("WORK_LOG.md", template)
def test_caller_lifecycle_is_not_bound_to_child_dispatcher_exit(self):
skill = (
Path(__file__).parents[1] / "SKILL.md"
).read_text(encoding="utf-8")
self.assertIn(
"기준 주체는 child dispatcher process가 아니라 이 스킬을 실행한 caller agent 자신",
skill,
)
self.assertIn(
"child의 종료, yield, session/cell 유실만으로 caller가 `final`을 보내지 않는다",
skill,
)
self.assertIn(
"exit code `3`은 다른 dispatcher가 소유한 active task가 남은 non-terminal 추적 상태",
skill,
)
self.assertIn(
"모든 CLI의 health/progress는 실제 stdout/stderr `stream.log`를 우선으로, "
"native session event가 있는 CLI는 그 event도 함께 본다",
skill,
)
self.assertIn("dispatcher PID와 agent PID를 즉시 기록", skill)
self.assertIn(
"직전 assistant의 모든 `toolCall.id`와 이후 `toolResult.toolCallId`가 일치할 때만",
skill,
)
self.assertIn(
"tool 실행 구간 밖에서 stream이 3분 멈추면 dispatcher는 마지막 stream 일부를",
skill,
)
self.assertIn(
"동일 task stage의 연속 자동 복구 실패 예산 10회를 공유한다",
skill,
)
self.assertIn(
"10번째 실패에서 해당 task를 차단하고 자동 cooldown 재개하지 않는다",
skill,
)
self.assertIn(
"`session-stall`은 provider 오류가 아니라 dispatcher 정책에 의한 timeout",
skill,
)
self.assertIn(
"실제 provider terminal evidence가 없는 exit code `143`을 provider 오류로 분류하지 않는다",
skill,
)
self.assertIn(
"`pi -p` fresh/isolated session의 한 attempt 결과를 Pi TUI 또는 provider 전체 장애로 일반화하지 않는다",
skill,
)
self.assertIn("provider_transport_failure_confirmed", skill)
self.assertIn(
"일반 tool/test stderr의 `connection refused`, `dial tcp`, `curl` peer failure만으로 provider 오류를 만들지 않는다",
skill,
)
self.assertIn(
"실행 중인 Python dispatcher는 source hot edit를 반영하지 않는다",
skill,
)
self.assertIn("dispatcher_source_sha256", skill)
self.assertIn("`dispatcher_source_matches_loaded=false`", skill)
self.assertIn(
"`laguna-s`의 `context-limit`/`session-stall`은 Prompt 계약의 same-session 재개 규칙을 우선",
skill,
)
self.assertIn(
"그 외 Pi `session-stall`만 fresh session",
skill,
)
class ProcessTerminationTest(unittest.IsolatedAsyncioTestCase):
async def test_terminates_the_exact_process_group(self):
class Process:
pid = 12345
returncode = None
async def wait(self):
self.returncode = -signal.SIGTERM
return self.returncode
process = Process()
with mock.patch.object(
dispatch.os,
"killpg",
side_effect=[None, ProcessLookupError],
) as killpg:
await dispatch.terminate_process_group(process)
self.assertEqual(killpg.call_args_list[0], mock.call(12345, signal.SIGTERM))
self.assertEqual(killpg.call_args_list[1], mock.call(12345, 0))
async def test_kills_sigterm_ignoring_descendant_and_closes_pipe(self):
child_script = (
"import signal,time;"
"signal.signal(signal.SIGTERM,signal.SIG_IGN);"
"time.sleep(60)"
)
parent_script = (
"import signal,subprocess,sys,time;"
"signal.signal(signal.SIGTERM,signal.SIG_IGN);"
f"subprocess.Popen([sys.executable,'-c',{child_script!r}]);"
"print('ready',flush=True);"
"time.sleep(60)"
)
process = await asyncio.create_subprocess_exec(
sys.executable,
"-c",
parent_script,
stdout=asyncio.subprocess.PIPE,
stderr=asyncio.subprocess.PIPE,
start_new_session=True,
)
try:
assert process.stdout is not None
self.assertEqual(
await asyncio.wait_for(process.stdout.readline(), timeout=1),
b"ready\n",
)
await dispatch.terminate_process_group(process, grace_seconds=0.05)
self.assertEqual(process.returncode, -signal.SIGKILL)
self.assertEqual(
await asyncio.wait_for(process.stdout.read(), timeout=1),
b"",
)
finally:
if process.returncode is None:
await dispatch.terminate_process_group(process, grace_seconds=0.05)
class ReviewRetryTest(unittest.IsolatedAsyncioTestCase):
def make_task(self, root: Path):
return TaskStageTest().make_task(root)
async def test_retries_two_control_violations_then_succeeds(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(root)
spec = dispatch.AgentSpec("codex", "gpt-5.6-sol", "codex")
locators = [root / f"locator-{index}.json" for index in range(3)]
results = [
(1, "review-control-violation", locators[0]),
(1, "review-control-violation", locators[1]),
(0, None, locators[2]),
]
with mock.patch.object(
dispatch, "invoke", new=mock.AsyncMock(side_effect=results)
) as invoke:
success, locator = await dispatch.run_escalating(
root, mock.Mock(), task, "review", spec
)
self.assertTrue(success)
self.assertEqual(locator, locators[2])
self.assertEqual(invoke.await_count, 3)
async def test_review_control_retries_do_not_create_a_blocker(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(root)
spec = dispatch.AgentSpec("codex", "gpt-5.6-sol", "codex")
locators = [root / f"locator-{index}.json" for index in range(4)]
results = [
(1, "review-control-violation", locators[0]),
(1, "review-control-violation", locators[1]),
(1, "review-control-violation", locators[2]),
(0, None, locators[3]),
]
with (
mock.patch.object(
dispatch, "invoke", new=mock.AsyncMock(side_effect=results)
) as invoke,
mock.patch.object(dispatch.asyncio, "sleep", new=mock.AsyncMock()),
):
success, locator = await dispatch.run_escalating(
root, mock.Mock(), task, "review", spec
)
self.assertTrue(success)
self.assertEqual(locator, locators[3])
self.assertEqual(invoke.await_count, 4)
async def test_does_not_retry_obsolete_model_work_log_failure(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(root)
spec = dispatch.AgentSpec("pi", "ornith:35b", "pi", local_pi=True)
locators = [root / "locator-0.json", root / "locator-1.json"]
results = [
(0, "work-log-incomplete", locators[0]),
(0, None, locators[1]),
]
with mock.patch.object(
dispatch, "invoke", new=mock.AsyncMock(side_effect=results)
) as invoke:
success, locator = await dispatch.run_escalating(
root, mock.Mock(), task, "worker", spec
)
self.assertFalse(success)
self.assertEqual(locator, locators[0])
self.assertEqual(invoke.await_count, 1)
async def test_retries_pi_session_stall_twice_with_same_model(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(root)
spec = dispatch.AgentSpec("pi", "laguna-s:2.1", "pi", local_pi=True)
locators = [root / f"locator-{index}.json" for index in range(3)]
results = [
(1, "session-stall", locators[0]),
(1, "session-stall", locators[1]),
(0, None, locators[2]),
]
with (
mock.patch.object(
dispatch, "invoke", new=mock.AsyncMock(side_effect=results)
) as invoke,
mock.patch.object(
dispatch.asyncio, "sleep", new=mock.AsyncMock()
),
):
success, locator = await dispatch.run_escalating(
root, mock.Mock(), task, "worker", spec
)
self.assertTrue(success)
self.assertEqual(locator, locators[2])
self.assertEqual(invoke.await_count, 3)
self.assertTrue(all(call.args[4] == spec for call in invoke.await_args_list))
self.assertEqual(
invoke.await_args_list[1].args[-1],
"Think in English. Final in Korean. Continue this session and "
"complete the current task.",
)
self.assertEqual(
invoke.await_args_list[1].kwargs["resume_locator"],
locators[0],
)
self.assertEqual(
invoke.await_args_list[2].kwargs["resume_locator"],
locators[1],
)
def test_failed_laguna_locator_is_recovered_after_dispatcher_restart(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
native = root / "session.jsonl"
native.write_text("{}\n", encoding="utf-8")
locator = root / "locator.json"
locator.write_text(
json.dumps(
{
"cli": "pi",
"model": "laguna-s:2.1",
"status": "failed",
"failure_class": "session-stall",
"native_session_path": str(native),
}
),
encoding="utf-8",
)
self.assertEqual(
dispatch.laguna_resume_locator(
{"active_locator": str(locator)}
),
locator,
)
async def test_retries_pi_connection_and_generic_failures(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(root)
spec = dispatch.AgentSpec("pi", "ornith-fast", "pi", local_pi=True)
locators = [root / f"locator-{index}.json" for index in range(3)]
results = [
(1, "provider-connection", locators[0]),
(1, "generic-error", locators[1]),
(0, None, locators[2]),
]
with (
mock.patch.object(
dispatch, "invoke", new=mock.AsyncMock(side_effect=results)
) as invoke,
mock.patch.object(
dispatch.asyncio, "sleep", new=mock.AsyncMock()
) as sleep,
):
success, locator = await dispatch.run_escalating(
root, mock.Mock(), task, "worker", spec
)
self.assertTrue(success)
self.assertEqual(locator, locators[2])
self.assertEqual(invoke.await_count, 3)
self.assertEqual(sleep.await_count, 2)
async def test_pi_tenth_failure_blocks_without_cooldown(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(root)
spec = dispatch.AgentSpec("pi", "ornith-fast", "pi", local_pi=True)
locators = [
root / f"locator-{index}.json"
for index in range(dispatch.RECOVERY_FAILURE_LIMIT)
]
results = [
(1, "provider-stream-disconnect", locator)
for locator in locators
]
semaphore = asyncio.Semaphore(1)
sleep_observations = []
async def observe_sleep(delay):
sleep_observations.append((delay, semaphore.locked()))
with (
mock.patch.object(
dispatch, "invoke", new=mock.AsyncMock(side_effect=results)
) as invoke,
mock.patch.object(
dispatch.asyncio,
"sleep",
new=mock.AsyncMock(side_effect=observe_sleep),
),
):
success, locator = await dispatch.run_escalating(
root,
mock.Mock(),
task,
"worker",
spec,
invocation_semaphore=semaphore,
)
self.assertFalse(success)
self.assertEqual(locator, locators[-1])
self.assertEqual(invoke.await_count, dispatch.RECOVERY_FAILURE_LIMIT)
self.assertEqual(
len(sleep_observations), dispatch.RECOVERY_FAILURE_LIMIT - 1
)
self.assertTrue(all(not locked for _, locked in sleep_observations))
async def test_recovery_failure_limit_survives_dispatcher_restart(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
(root / ".git").mkdir()
task = self.make_task(root)
store = dispatch.StateStore(root)
locator = root / "locator.json"
store.update_task(
task, recovery_failures={"worker": dispatch.RECOVERY_FAILURE_LIMIT - 1}
)
spec = dispatch.AgentSpec("pi", "ornith-fast", "pi", local_pi=True)
try:
with mock.patch.object(
dispatch,
"invoke",
new=mock.AsyncMock(
return_value=(1, "generic-error", locator)
),
) as invoke:
success, actual_locator = await dispatch.run_escalating(
root, store, task, "worker", spec
)
self.assertFalse(success)
self.assertEqual(actual_locator, locator)
self.assertEqual(invoke.await_count, 1)
self.assertIn(
"recovery failure limit exhausted",
store.task_state(task)["blocked"],
)
finally:
store.close()
async def test_already_exhausted_recovery_budget_does_not_invoke_model(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
(root / ".git").mkdir()
task = self.make_task(root)
store = dispatch.StateStore(root)
locator = root / "locator.json"
store.update_task(
task, recovery_failures={"worker": dispatch.RECOVERY_FAILURE_LIMIT}
)
spec = dispatch.AgentSpec("pi", "ornith-fast", "pi", local_pi=True)
try:
with mock.patch.object(
dispatch, "invoke", new=mock.AsyncMock()
) as invoke:
success, actual_locator = await dispatch.run_escalating(
root,
store,
task,
"worker",
spec,
initial_resume_locator=locator,
)
self.assertFalse(success)
self.assertEqual(actual_locator, locator)
self.assertEqual(invoke.await_count, 0)
finally:
store.close()
async def test_does_not_promote_work_log_infrastructure_failure(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
task = self.make_task(root)
spec = dispatch.AgentSpec("codex", "gpt-5.6-sol", "codex")
locator = root / "locator.json"
with mock.patch.object(
dispatch,
"invoke",
new=mock.AsyncMock(
return_value=(1, "work-log-runtime-write", locator)
),
) as invoke:
success, actual_locator = await dispatch.run_escalating(
root,
mock.Mock(),
task,
"worker",
spec,
)
self.assertFalse(success)
self.assertEqual(actual_locator, locator)
self.assertEqual(invoke.await_count, 1)
class RepetitionLimitTest(unittest.IsolatedAsyncioTestCase):
async def test_exhausted_selfcheck_budget_does_not_invoke_model(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
(root / ".git").mkdir()
task = TaskStageTest().make_task(root)
store = dispatch.StateStore(root)
store.update_task(
task, selfcheck_incomplete=dispatch.SELF_CHECK_INCOMPLETE_LIMIT
)
try:
with mock.patch.object(
dispatch, "run_escalating", new=mock.AsyncMock()
) as run_escalating:
await dispatch.run_selfcheck(
root,
store,
task,
{"pi:ornith-fast": asyncio.Semaphore(1)},
)
self.assertEqual(run_escalating.await_count, 0)
self.assertIn(
"limit already exhausted", store.task_state(task)["blocked"]
)
finally:
store.close()
async def test_exhausted_review_budget_does_not_invoke_model(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
(root / ".git").mkdir()
task = TaskStageTest().make_task(root)
store = dispatch.StateStore(root)
store.update_task(
task, review_no_progress=dispatch.REVIEW_NO_PROGRESS_LIMIT
)
try:
with mock.patch.object(
dispatch, "run_escalating", new=mock.AsyncMock()
) as run_escalating:
result = await dispatch.run_review(root, store, task)
self.assertIsNone(result)
self.assertEqual(run_escalating.await_count, 0)
self.assertIn(
"limit already exhausted", store.task_state(task)["blocked"]
)
finally:
store.close()
async def test_selfcheck_incomplete_tenth_pass_blocks_task(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
(root / ".git").mkdir()
task = TaskStageTest().make_task(root)
store = dispatch.StateStore(root)
store.update_task(
task,
selfcheck_incomplete=dispatch.SELF_CHECK_INCOMPLETE_LIMIT - 1,
)
locator = root / "locator.json"
try:
with (
mock.patch.object(
dispatch,
"run_escalating",
new=mock.AsyncMock(return_value=(True, locator)),
) as run_escalating,
mock.patch.object(
dispatch,
"implementation_review_errors",
return_value=["검증 결과 미완성"],
),
):
await dispatch.run_selfcheck(
root,
store,
task,
{"pi:ornith-fast": asyncio.Semaphore(1)},
)
self.assertEqual(run_escalating.await_count, 1)
self.assertIn(
"selfcheck implementation fields remain incomplete",
store.task_state(task)["blocked"],
)
finally:
store.close()
async def test_review_tenth_no_progress_pass_blocks_task(self):
with tempfile.TemporaryDirectory() as temporary:
root = Path(temporary)
(root / ".git").mkdir()
task = TaskStageTest().make_task(root)
store = dispatch.StateStore(root)
store.update_task(
task,
review_no_progress=dispatch.REVIEW_NO_PROGRESS_LIMIT - 1,
)
locator = root / "locator.json"
try:
with (
mock.patch.object(
dispatch,
"run_escalating",
new=mock.AsyncMock(return_value=(True, locator)),
),
mock.patch.object(
dispatch, "task_signature", return_value="unchanged"
),
mock.patch.object(
dispatch, "review_fingerprints", return_value=set()
),
):
result = await dispatch.run_review(root, store, task)
self.assertIsNone(result)
self.assertIn(
"review made no progress", store.task_state(task)["blocked"]
)
finally:
store.close()
class BlockerDrainTest(unittest.IsolatedAsyncioTestCase):
async def test_user_review_only_holds_its_dependency_closure(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
group = workspace / "agent-task" / "m-test"
gate_dir = group / "01_gate"
dependent_dir = group / "02+01_dependent"
independent_dir = group / "03_independent"
for directory in (gate_dir, dependent_dir, independent_dir):
directory.mkdir(parents=True)
user_review = gate_dir / "USER_REVIEW.md"
user_review.write_text(
TaskStageTest.blocking_user_review_text(), encoding="utf-8"
)
gate = dispatch.Task(
name="m-test/01_gate",
directory=gate_dir,
plan=None,
review=None,
user_review=user_review,
recovery=True,
index=1,
)
def runnable_task(name, directory, index, deps=()):
plan = directory / "PLAN-local-G05.md"
review = directory / "CODE_REVIEW-local-G05.md"
plan.write_text(
f"<!-- task={name} plan=0 tag=TEST -->\n",
encoding="utf-8",
)
review.write_text("", encoding="utf-8")
return dispatch.Task(
name=name,
directory=directory,
plan=plan,
review=review,
user_review=None,
recovery=False,
index=index,
deps=deps,
lane="local",
grade=5,
plan_hash=f"{name}-hash",
)
dependent = runnable_task(
"m-test/02+01_dependent", dependent_dir, 2, ("01",)
)
independent = runnable_task(
"m-test/03_independent", independent_dir, 3
)
completed_archive = workspace / "completed-independent"
completed_archive.mkdir()
(completed_archive / "complete.log").write_text(
"complete\n", encoding="utf-8"
)
args = SimpleNamespace(
task_group="m-test", retry_blocked=False, dry_run=False
)
store = dispatch.StateStore(workspace)
try:
with (
mock.patch.object(
dispatch,
"scan_tasks",
side_effect=[
[gate, dependent, independent],
[gate, dependent],
],
),
mock.patch.object(
dispatch,
"run_worker",
new=mock.AsyncMock(return_value=str(completed_archive)),
) as run_worker,
):
result = await dispatch.dispatch_with_store(
args, workspace, store
)
self.assertEqual(result, 2)
self.assertEqual(run_worker.await_count, 1)
self.assertEqual(
run_worker.await_args.args[2].name, independent.name
)
orchestration = store.data["orchestrations"]["m-test"]["tasks"]
self.assertEqual(orchestration[gate.name]["status"], "blocked")
self.assertEqual(
orchestration[dependent.name]["status"], "waiting"
)
self.assertEqual(
orchestration[independent.name]["status"], "complete"
)
self.assertEqual(
store.data["orchestrations"]["m-test"]["status"],
"blocked",
)
self.assertEqual(
orchestration[independent.name]["archive"],
str(completed_archive.resolve()),
)
finally:
store.close()
async def test_runtime_blocker_still_drains_independent_task(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
group = workspace / "agent-task" / "m-test"
gate_dir = group / "01_gate"
independent_dir = group / "02_independent"
gate_dir.mkdir(parents=True)
independent_dir.mkdir(parents=True)
gate = TaskStageTest().make_task(gate_dir)
gate.name = "m-test/01_gate"
gate.index = 1
gate.plan_hash = "gate-hash"
independent = TaskStageTest().make_task(independent_dir)
independent.name = "m-test/02_independent"
independent.index = 2
independent.plan_hash = "independent-hash"
completed_archive = workspace / "completed-independent"
completed_archive.mkdir()
(completed_archive / "complete.log").write_text(
"complete\n", encoding="utf-8"
)
completed_tasks: list[str] = []
async def fake_worker(workspace_path, state_store, task, semaphores):
if task.name == gate.name:
state_store.update_task(
task,
blocked="worker recovery failure limit exhausted: 10/10",
)
return None
completed_tasks.append(task.name)
return str(completed_archive)
args = SimpleNamespace(
task_group="m-test", retry_blocked=False, dry_run=False
)
store = dispatch.StateStore(workspace)
try:
with (
mock.patch.object(
dispatch,
"scan_tasks",
side_effect=[[gate, independent], [gate]],
),
mock.patch.object(dispatch, "run_worker", new=fake_worker),
):
result = await dispatch.dispatch_with_store(
args, workspace, store
)
self.assertEqual(result, 2)
self.assertEqual(completed_tasks, [independent.name])
group_state = store.data["orchestrations"]["m-test"]
orchestration = group_state["tasks"]
self.assertEqual(group_state["status"], "blocked")
self.assertEqual(orchestration[gate.name]["status"], "blocked")
self.assertEqual(
orchestration[independent.name]["status"], "complete"
)
store.prepare_orchestration("m-test", [gate], workspace)
group_state = store.data["orchestrations"]["m-test"]
self.assertEqual(group_state["status"], "running")
self.assertEqual(
group_state["tasks"][gate.name]["status"], "active"
)
self.assertNotIn(
"reason", group_state["tasks"][gate.name]
)
finally:
store.close()
async def test_external_active_task_returns_non_terminal_exit_three(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
directory = workspace / "agent-task" / "m-test" / "01_active"
directory.mkdir(parents=True)
task = TaskStageTest().make_task(directory)
task.name = "m-test/01_active"
task.index = 1
task.plan_hash = "active-hash"
locator = workspace / "locator.json"
args = SimpleNamespace(
task_group="m-test", retry_blocked=False, dry_run=False
)
store = dispatch.StateStore(workspace)
store.mark_active(task, "worker", locator)
try:
with (
mock.patch.object(
dispatch, "scan_tasks", return_value=[task]
),
mock.patch.object(
dispatch,
"external_active_is_live",
return_value=(True, "pid=123"),
),
mock.patch.object(
dispatch, "run_worker", new=mock.AsyncMock()
) as run_worker,
):
result = await dispatch.dispatch_with_store(
args, workspace, store
)
self.assertEqual(result, 3)
self.assertEqual(run_worker.await_count, 0)
finally:
store.close()
class ReviewSchedulingTest(unittest.TestCase):
def test_all_ready_reviews_are_selected_without_numeric_cap(self):
reviews = [
(mock.sentinel.review_a, "review"),
(mock.sentinel.review_b, "review"),
(mock.sentinel.review_c, "review"),
]
worker = (mock.sentinel.worker, "worker")
selected, deferred, reason = dispatch.select_dispatch_candidates(
[*reviews, worker]
)
self.assertEqual(selected, [*reviews, worker])
self.assertEqual(deferred, [])
self.assertEqual(reason, "")
def test_new_reviews_join_already_running_review_phase(self):
reviews = [
(mock.sentinel.review_a, "review"),
(mock.sentinel.review_b, "review"),
]
worker = (mock.sentinel.worker, "selfcheck")
selected, deferred, reason = dispatch.select_dispatch_candidates(
[*reviews, worker]
)
self.assertEqual(selected, [*reviews, worker])
self.assertEqual(deferred, [])
self.assertEqual(reason, "")
class WriteSetTest(unittest.TestCase):
def test_normalizes_relative_and_absolute_aliases(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
source = workspace / "src" / "shared.go"
source.parent.mkdir()
source.write_text("package src\n", encoding="utf-8")
relative_plan = workspace / "relative.md"
absolute_plan = workspace / "absolute.md"
relative_plan.write_text(
"## 수정 파일 요약\n\n| 파일 | 항목 |\n|---|---|\n"
"| `./src/shared.go` | TEST-1 |\n",
encoding="utf-8",
)
absolute_plan.write_text(
"## 수정 파일 요약\n\n| 파일 | 항목 |\n|---|---|\n"
f"| `{source}` | TEST-1 |\n",
encoding="utf-8",
)
relative, relative_known = dispatch.extract_write_set(
relative_plan, workspace
)
absolute, absolute_known = dispatch.extract_write_set(
absolute_plan, workspace
)
self.assertTrue(relative_known)
self.assertTrue(absolute_known)
self.assertEqual(relative, absolute)
self.assertEqual(relative, {str(source.resolve())})
def test_recovery_restores_write_set_from_matching_archived_plan(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
task = workspace / "agent-task" / "recovery"
task.mkdir(parents=True)
header = "<!-- task=recovery plan=2 tag=REVIEW_TEST -->\n"
(task / "plan_local_G05_2.log").write_text(
header
+ "## 수정 파일 요약\n\n| 파일 | 항목 |\n|---|---|\n"
"| `src/recovery.go` | TEST-1 |\n",
encoding="utf-8",
)
(task / "code_review_local_G05_2.log").write_text(
header + "## 코드리뷰 결과\n- 종합 판정: WARN\n",
encoding="utf-8",
)
(task / "plan_cloud_G09_3.log").write_text(
"<!-- task=recovery plan=3 tag=OTHER -->\n"
"## 수정 파일 요약\n\n| 파일 | 항목 |\n|---|---|\n"
"| `src/unrelated.go` | OTHER-1 |\n",
encoding="utf-8",
)
[scanned] = dispatch.scan_tasks(workspace, None)
self.assertTrue(scanned.write_set_known)
self.assertEqual(
scanned.write_set,
{str((workspace / "src" / "recovery.go").resolve())},
)
self.assertEqual(scanned.errors, [])
def test_recovery_without_matching_plan_does_not_block_dispatch(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
task = workspace / "agent-task" / "recovery"
task.mkdir(parents=True)
(task / "code_review_local_G05_2.log").write_text(
"<!-- task=recovery plan=2 tag=REVIEW_TEST -->\n"
"## 코드리뷰 결과\n"
"- 종합 판정: WARN\n",
encoding="utf-8",
)
[scanned] = dispatch.scan_tasks(workspace, None)
self.assertFalse(scanned.write_set_known)
self.assertEqual(scanned.errors, [])
def test_rejects_broad_or_outside_workspace_write_sets(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / "src").mkdir()
plan = workspace / "unsafe.md"
plan.write_text(
"## 수정 파일 요약\n\n| 파일 | 항목 |\n|---|---|\n"
"| `src/` | TEST-1 |\n"
"| `../outside.go` | TEST-2 |\n"
"| `src/*.go` | TEST-3 |\n",
encoding="utf-8",
)
write_set, known = dispatch.extract_write_set(plan, workspace)
self.assertFalse(known)
self.assertEqual(write_set, set())
def test_review_progress_signature_ignores_dispatcher_work_log(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
task = TaskStageTest().make_task(workspace)
before = dispatch.task_signature(workspace, task)
(workspace / dispatch.WORK_LOG_NAME).write_text(
"| FINISH | test | review |\n", encoding="utf-8"
)
after_work_log = dispatch.task_signature(workspace, task)
self.assertEqual(after_work_log, before)
assert task.review is not None
task.review.write_text(
"## 코드리뷰 결과\n- 종합 판정: WARN\n",
encoding="utf-8",
)
after_review = dispatch.task_signature(workspace, task)
self.assertNotEqual(after_review, before)
class OrchestrationPersistenceTest(unittest.TestCase):
def make_task(self, workspace: Path, name: str = "task"):
directory = workspace / "agent-task" / name
directory.mkdir(parents=True)
plan = directory / "PLAN-local-G05.md"
review = directory / "CODE_REVIEW-local-G05.md"
plan.write_text(
f"<!-- task={name} plan=0 tag=TEST -->\n"
"## 수정 파일 요약\n\n| 파일 | 항목 |\n|---|---|\n"
"| `src/task.go` | TEST-1 |\n",
encoding="utf-8",
)
review.write_text(
f"<!-- task={name} plan=0 tag=TEST -->\n",
encoding="utf-8",
)
return dispatch.scan_tasks(workspace, None)[0]
def test_complete_archive_removes_only_its_task_attempt_logs(self):
with tempfile.TemporaryDirectory() as temporary:
runs = Path(temporary) / "runs"
completed = runs / "completed-attempt"
other = runs / "other-attempt"
for attempt, task_name in ((completed, "group/01_done"), (other, "group/02_open")):
attempt.mkdir(parents=True)
(attempt / "locator.json").write_text(
json.dumps({"task": task_name}), encoding="utf-8"
)
for name in ("stream.log", "heartbeat.log", "session.jsonl"):
(attempt / name).write_text("evidence\n", encoding="utf-8")
removed = dispatch.cleanup_completed_task_attempt_logs(
runs, "group/01_done"
)
self.assertEqual(removed, 1)
self.assertFalse(completed.exists())
self.assertTrue(other.is_dir())
self.assertTrue((other / "stream.log").is_file())
def test_mark_complete_removes_task_attempt_logs(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
store = dispatch.StateStore(workspace)
try:
attempt = store.runs / "attempt"
attempt.mkdir()
(attempt / "locator.json").write_text(
json.dumps({"task": "group/01_done"}), encoding="utf-8"
)
(attempt / "stream.log").write_text("stream\n", encoding="utf-8")
archive = workspace / "archive"
archive.mkdir()
(archive / "complete.log").write_text("complete\n", encoding="utf-8")
store.mark_orchestration_task_complete(
"group", "group/01_done", archive
)
self.assertFalse(attempt.exists())
finally:
store.close()
def test_external_liveness_ignores_heartbeat_mtime(self):
with tempfile.TemporaryDirectory() as temporary:
attempt = Path(temporary)
stream = attempt / "stream.log"
heartbeat = attempt / "heartbeat.log"
locator = attempt / "locator.json"
stream.write_text("old model output\n", encoding="utf-8")
heartbeat.write_text("fresh heartbeat\n", encoding="utf-8")
stale_at = time.time() - dispatch.CODEX_STREAM_STALL_SECONDS - 1
os.utime(stream, (stale_at, stale_at))
locator.write_text(
json.dumps(
{
"status": "running",
"cli": "agy",
"stream_log": str(stream),
"heartbeat_log": str(heartbeat),
}
),
encoding="utf-8",
)
live, detail = dispatch.external_active_is_live(
{"active_locator": str(locator)}
)
self.assertFalse(live)
self.assertIn("stream inactive=", detail)
stream.touch()
live, _ = dispatch.external_active_is_live(
{"active_locator": str(locator)}
)
self.assertTrue(live)
def test_external_liveness_keeps_silent_live_agent_process(self):
with tempfile.TemporaryDirectory() as temporary:
attempt = Path(temporary)
stream = attempt / "stream.log"
locator = attempt / "locator.json"
stream.write_text("old model output\n", encoding="utf-8")
stale_at = time.time() - dispatch.PI_TOOL_STALL_SECONDS - 1
os.utime(stream, (stale_at, stale_at))
locator.write_text(
json.dumps(
{
"status": "running",
"cli": "pi",
"agent_pid": os.getpid(),
"stream_log": str(stream),
}
),
encoding="utf-8",
)
live, detail = dispatch.external_active_is_live(
{"active_locator": str(locator)}
)
self.assertTrue(live)
self.assertIn("agent_pid=", detail)
def test_retry_blocked_only_clears_selected_task_group(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
self.make_task(workspace, "alpha/01_task")
self.make_task(workspace, "beta/01_task")
tasks = {
task.name: task for task in dispatch.scan_tasks(workspace, None)
}
alpha = tasks["alpha/01_task"]
beta = tasks["beta/01_task"]
store = dispatch.StateStore(workspace)
try:
for task in (alpha, beta):
store.update_task(
task,
blocked="recovery failure limit exhausted: 10/10",
review_no_progress=10,
selfcheck_incomplete=10,
recovery_failures={"worker": 10},
)
store.clear_blocked("alpha")
alpha_state = store.task_state(alpha)
self.assertIsNone(alpha_state["blocked"])
self.assertEqual(alpha_state["review_no_progress"], 0)
self.assertEqual(alpha_state["selfcheck_incomplete"], 0)
self.assertEqual(alpha_state["recovery_failures"], {})
beta_state = store.task_state(beta)
self.assertIsNotNone(beta_state["blocked"])
self.assertEqual(beta_state["review_no_progress"], 10)
self.assertEqual(beta_state["selfcheck_incomplete"], 10)
self.assertEqual(beta_state["recovery_failures"], {"worker": 10})
finally:
store.close()
def test_corrupt_persistent_state_fails_closed_and_releases_lock(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
state_root = workspace / ".git" / "agent-task-dispatcher"
state_root.mkdir(parents=True)
state_path = state_root / "state.json"
state_path.write_text("{broken", encoding="utf-8")
with self.assertRaisesRegex(
RuntimeError, "dispatcher state를 읽을 수 없다"
):
dispatch.StateStore(workspace)
state_path.write_text("{}\n", encoding="utf-8")
reopened = dispatch.StateStore(workspace)
reopened.close()
def test_dry_run_retry_blocked_does_not_clear_persistent_limits(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = self.make_task(workspace)
store = dispatch.StateStore(workspace)
store.update_task(
task,
blocked="recovery failure limit exhausted: 10/10",
review_no_progress=10,
selfcheck_incomplete=10,
recovery_failures={"review": 10},
)
store.close()
args = SimpleNamespace(
workspace=str(workspace),
task_group=None,
dry_run=True,
retry_blocked=True,
)
result = asyncio.run(dispatch.dispatch(args))
self.assertEqual(result, 2)
reopened = dispatch.StateStore(workspace)
try:
state = reopened.task_state(task)
self.assertEqual(
state["blocked"],
"recovery failure limit exhausted: 10/10",
)
self.assertEqual(state["review_no_progress"], 10)
self.assertEqual(state["selfcheck_incomplete"], 10)
self.assertEqual(
state["recovery_failures"], {"review": 10}
)
finally:
reopened.close()
def test_child_restart_detects_task_that_disappeared_without_complete_log(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
task = self.make_task(workspace)
first = dispatch.StateStore(workspace)
first.prepare_orchestration("__all__", [task], workspace)
first.close()
task.plan.unlink()
task.review.unlink()
task.directory.rmdir()
restarted = dispatch.StateStore(workspace)
restarted.prepare_orchestration("__all__", [], workspace)
completed, errors = restarted.reconcile_orchestration(
"__all__", workspace, set()
)
self.assertEqual(completed, {})
self.assertIn(task.name, errors)
self.assertIn("새 complete.log archive 모두에서 사라졌다", errors[task.name])
restarted.close()
def test_child_restart_recovers_new_complete_archive_not_baseline_archive(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
old_archive = workspace / "agent-task" / "archive" / "2026" / "06" / "task"
old_archive.mkdir(parents=True)
(old_archive / "complete.log").write_text("old\n", encoding="utf-8")
task = self.make_task(workspace)
first = dispatch.StateStore(workspace)
first.prepare_orchestration("__all__", [task], workspace)
first.close()
new_archive = workspace / "agent-task" / "archive" / "2026" / "07" / "task_1"
new_archive.parent.mkdir(parents=True)
(task.directory / "complete.log").write_text("new\n", encoding="utf-8")
task.directory.rename(new_archive)
restarted = dispatch.StateStore(workspace)
restarted.prepare_orchestration("__all__", [], workspace)
completed, errors = restarted.reconcile_orchestration(
"__all__", workspace, set()
)
self.assertEqual(errors, {})
self.assertEqual(completed, {"task": str(new_archive.resolve())})
restarted.close()
def test_preexisting_incomplete_archive_cannot_become_false_new_completion(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
incomplete_archive = (
workspace / "agent-task" / "archive" / "2026" / "06" / "task"
)
incomplete_archive.mkdir(parents=True)
task = self.make_task(workspace)
first = dispatch.StateStore(workspace)
first.prepare_orchestration("__all__", [task], workspace)
first.close()
task.plan.unlink()
task.review.unlink()
task.directory.rmdir()
(incomplete_archive / "complete.log").write_text(
"late unrelated completion\n",
encoding="utf-8",
)
restarted = dispatch.StateStore(workspace)
restarted.prepare_orchestration("__all__", [], workspace)
completed, errors = restarted.reconcile_orchestration(
"__all__", workspace, set()
)
self.assertEqual(completed, {})
self.assertIn(task.name, errors)
restarted.close()
def test_dry_run_does_not_create_persistent_orchestration_state(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
self.make_task(workspace)
args = SimpleNamespace(
workspace=str(workspace),
task_group=None,
dry_run=True,
retry_blocked=False,
)
result = asyncio.run(dispatch.dispatch(args))
self.assertEqual(result, 0)
state_path = workspace / ".git" / "agent-task-dispatcher" / "state.json"
self.assertFalse(state_path.exists())
class DispatcherConvergenceSimulationTest(unittest.IsolatedAsyncioTestCase):
def write_task(
self,
workspace: Path,
task_name: str,
source_path: str,
) -> None:
directory = workspace / "agent-task" / task_name
directory.mkdir(parents=True)
header = f"<!-- task={task_name} plan=0 tag=SIM -->\n"
(directory / "PLAN-local-G05.md").write_text(
header
+ "## 수정 파일 요약\n\n| 파일 | 항목 |\n|---|---|\n"
+ f"| `{source_path}` | SIM-1 |\n",
encoding="utf-8",
)
(directory / "CODE_REVIEW-local-G05.md").write_text(
header,
encoding="utf-8",
)
async def test_parallel_multi_task_followup_dependency_and_terminal_completion(self):
with tempfile.TemporaryDirectory() as temporary:
workspace = Path(temporary)
(workspace / ".git").mkdir()
(workspace / "agent-task").mkdir()
self.write_task(workspace, "sim/01_alpha", "src/alpha.go")
self.write_task(workspace, "sim/02_beta", "src/beta.go")
self.write_task(workspace, "sim/03+01,02_join", "src/join.go")
self.write_task(workspace, "sim/04_conflict", "./src/alpha.go")
active = {"worker": set(), "selfcheck": set(), "review": set()}
maximum = {"worker": 0, "selfcheck": 0, "review": 0}
overlap_violations: list[tuple[str, set[str]]] = []
review_attempts: dict[str, int] = {}
def enter(stage: str, task_name: str) -> None:
active[stage].add(task_name)
maximum[stage] = max(maximum[stage], len(active[stage]))
if {"sim/01_alpha", "sim/04_conflict"} <= active[stage]:
overlap_violations.append((stage, set(active[stage])))
def leave(stage: str, task_name: str) -> None:
active[stage].remove(task_name)
async def fake_worker(workspace_path, store, task, semaphores):
enter("worker", task.name)
try:
await asyncio.sleep(0.005)
store.update_task(
task,
worker_done=True,
worker_cli="pi",
worker_model="ornith:35b",
selfcheck_done=False,
blocked=None,
)
finally:
leave("worker", task.name)
async def fake_selfcheck(workspace_path, store, task, semaphores):
enter("selfcheck", task.name)
try:
await asyncio.sleep(0.005)
store.update_task(task, selfcheck_done=True, blocked=None)
finally:
leave("selfcheck", task.name)
async def fake_review(workspace_path, store, task):
enter("review", task.name)
try:
await asyncio.sleep(0.005)
attempt = review_attempts.get(task.name, 0) + 1
review_attempts[task.name] = attempt
if task.name == "sim/01_alpha" and attempt == 1:
for path in (task.plan, task.review):
assert path is not None
path.write_text(
path.read_text(encoding="utf-8").replace(
"plan=0", "plan=1"
),
encoding="utf-8",
)
return None
archive = (
workspace_path
/ "agent-task"
/ "archive"
/ "2026"
/ "07"
/ task.name
)
archive.parent.mkdir(parents=True, exist_ok=True)
(task.directory / "complete.log").write_text(
"simulation complete\n", encoding="utf-8"
)
task.directory.rename(archive)
return str(archive)
finally:
leave("review", task.name)
args = SimpleNamespace(
workspace=str(workspace),
task_group="sim",
dry_run=False,
retry_blocked=False,
)
with (
mock.patch.object(dispatch, "run_worker", new=fake_worker),
mock.patch.object(dispatch, "run_selfcheck", new=fake_selfcheck),
mock.patch.object(dispatch, "run_review", new=fake_review),
mock.patch.object(dispatch, "ensure_review_shared_state"),
mock.patch.object(
dispatch, "scan_tasks", wraps=dispatch.scan_tasks
) as scan_tasks,
):
result = await asyncio.wait_for(dispatch.dispatch(args), timeout=2)
self.assertEqual(result, 0)
self.assertGreaterEqual(maximum["worker"], 2)
self.assertGreaterEqual(maximum["selfcheck"], 2)
self.assertGreaterEqual(maximum["review"], 2)
self.assertEqual(
{stage for stage, _ in overlap_violations},
{"worker", "selfcheck", "review"},
)
self.assertGreater(scan_tasks.call_count, 1)
self.assertLessEqual(scan_tasks.call_count, 5)
self.assertEqual(review_attempts["sim/01_alpha"], 2)
self.assertEqual(review_attempts["sim/02_beta"], 1)
self.assertEqual(review_attempts["sim/03+01,02_join"], 1)
self.assertEqual(review_attempts["sim/04_conflict"], 1)
archive_root = workspace / "agent-task" / "archive" / "2026" / "07" / "sim"
for subtask in ("01_alpha", "02_beta", "03+01,02_join", "04_conflict"):
self.assertTrue((archive_root / subtask / "complete.log").is_file())
if __name__ == "__main__":
unittest.main()
Reference in a new issue View git blame Copy permalink