fix(issue-30-33): review 5ec8ef33 - a multi-line codex draft is not an empty box, blocked notices reach the loop while the job runs, and both clocks are labelled on every close path
- R1 (P1): without rules the input region runs from the last prompt line to the end of the pane; only a last line matching the adapter's footer pattern (codex: ` <model> · ~/<cwd> · …`) is dropped, so a draft on a second line keeps the nudge withheld. - R2: while the synchronous submit runs, a relay thread finds the job it registers (same session, created since the submit) and prints its stalled:/stall_watch: notices; before, they appeared only after the job. - R3: the broker-unavailable disk wait that runs into the deadline is the wall clock: wall_clock_timeout (caller rc stays 3). - R4: a state_change_seq change seen right before the judgement restarts the idle window (decision 9: S seconds of continuous idle). Regression tests are the reviewer's reproductions, each with its passing twin; the wrapper-level #30 tests now use this environment's broker instead of the #18 harness's public default. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
1 parent
47e42744e7
commit
bf0f5c1014
8 files changed
+269
-12
No files matched your search
@@ -486,6 +486,14 @@ def test_scoped_env_drops_the_pane_inherited_workspace_for_name_lookups_only():
|
||||
import test_issue18_liveness_contract as t18 # noqa: E402
|
||||
|
||||
|
||||
LIVE_BROKER = ("MQTT_BROKER", "MQTT_PORT", "MQTT_TLS", "MQTT_USERNAME", "MQTT_PASSWORD")
|
||||
|
||||
|
||||
def _live_broker() -> dict:
|
||||
"""This environment's broker (the #18 harness defaults to a public one)."""
|
||||
return {k: os.environ[k] for k in LIVE_BROKER if k in os.environ}
|
||||
|
||||
|
||||
def _watchers(jid: str) -> list:
|
||||
out = subprocess.run(["pgrep", "-f", f"lib_py.stall_watch --job {jid}"], capture_output=True, text=True).stdout
|
||||
return [int(p) for p in out.split()]
|
||||
@@ -497,7 +505,7 @@ def test_s9_the_wrapper_runs_the_watcher_for_the_jobs_life(tmp_path, mock_herdr,
|
||||
reg.mkdir()
|
||||
t18._headless_agent(Path(mock_herdr), "headless-codex")
|
||||
proc, env = t18._submit(tmp_path, reg, "herdr:headless-codex", "codex", ["--ack-timeout", "40"],
|
||||
env_extra={"MAM_STALL_WATCH": switch}, timeout_s=60)
|
||||
env_extra={"MAM_STALL_WATCH": switch, **_live_broker()}, timeout_s=60)
|
||||
jid = t18._wait_job_id(reg)
|
||||
try:
|
||||
time.sleep(1)
|
||||
@@ -523,7 +531,7 @@ def test_s10_remote_and_human_jobs_are_not_watched(tmp_path, agent, session, why
|
||||
reg = tmp_path / "jobs"
|
||||
reg.mkdir()
|
||||
proc, env = t18._submit(tmp_path, reg, session, agent, ["--ack-timeout", "40"], timeout_s=60,
|
||||
env_extra={"MAM_DISPATCH_SECRET": "s10-secret"})
|
||||
env_extra={"MAM_DISPATCH_SECRET": "s10-secret", **_live_broker()})
|
||||
jid = t18._wait_job_id(reg)
|
||||
try:
|
||||
time.sleep(1)
|
||||
@@ -563,3 +571,177 @@ def test_s11_the_runner_warns_once_per_stall_notice(mam_sandbox, monkeypatch, ca
|
||||
assert text.count(f"job {jid}: stalled:idle") == 1, text
|
||||
assert text.count(f"job {jid}: stall_watch:herdr_unavailable:protocol_mismatch") == 1, text
|
||||
assert "ordinary" not in text
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Review 5ec8ef33 (planner-reviewer-codex-01) regressions, taken from the
|
||||
# reviewer's independent reproductions (codex-reports/test_review_regressions.py)
|
||||
# R1 multi-line codex draft, R2 live relay during the synchronous submit,
|
||||
# R4 continuous idle after a missed transition. Each has its passing twin.
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
import textwrap # noqa: E402
|
||||
|
||||
@pytest.mark.parametrize("typing", [False, True])
|
||||
def test_r1_a_multi_line_codex_draft_is_not_an_empty_box(mam_sandbox, mock_herdr, typing):
|
||||
reg = mam_sandbox / ".mam" / "jobs"
|
||||
env = _env(mam_sandbox, MAM_STALL_IDLE_S=1)
|
||||
jid = _job(env, reg)
|
||||
agent = _proc("exec sleep 300")
|
||||
w = None
|
||||
try:
|
||||
pane = _pane("codex")
|
||||
if typing:
|
||||
pane = pane.replace("› Ask Codex to do anything", "›\n draft on the second input line")
|
||||
_agent(mock_herdr, "reviewer-codex-t", "codex", agent.pid, "idle", pane)
|
||||
w = _watch(env, reg, jid, "reviewer-codex-t", "codex")
|
||||
if typing:
|
||||
time.sleep(5)
|
||||
else:
|
||||
assert _until(lambda: _prompts(mock_herdr))
|
||||
prompts = _prompts(mock_herdr)
|
||||
_finish(env, reg, jid, w)
|
||||
assert len(prompts) == (0 if typing else 1), prompts
|
||||
finally:
|
||||
if w is not None and w.poll() is None:
|
||||
w.terminate()
|
||||
w.communicate(timeout=10)
|
||||
_kill(agent)
|
||||
|
||||
|
||||
@pytest.mark.parametrize("blocked", [False, True])
|
||||
def test_r2_the_loop_relays_a_blocked_notice_while_the_job_is_open(mam_sandbox, mock_herdr, blocked):
|
||||
reg = mam_sandbox / ".mam" / "jobs"
|
||||
reg.mkdir(parents=True, exist_ok=True)
|
||||
t18._headless_agent(mock_herdr, "headless-codex")
|
||||
env = t18._env(mam_sandbox, {"MAM_STALL_WATCH": "1", "MAM_STALL_IDLE_S": "600",
|
||||
"SKS_IDLE_TIMEOUT_MS": "500", "SKS_EMPTY_GIVEUP": "1",
|
||||
"MAM_ACK_TIMEOUT_S": "40", "MAM_JOBS_DIR": str(reg),
|
||||
"PYTHONPATH": str(SKILLS), "PYTHONUNBUFFERED": "1"})
|
||||
env.update(_live_broker())
|
||||
script = '''from lib_py.loop.runner import LoopRunner
|
||||
r = LoopRunner(["--creator", "headless-codex", "--task", "review check", "--job-timeout", "60"])
|
||||
r.parse_args()
|
||||
jid = r.delegate_job("headless-codex", "codex", "Worker", "review check")
|
||||
assert jid
|
||||
assert r.wait_for_job(jid, max_wait=10)
|
||||
'''
|
||||
p = subprocess.Popen([sys.executable, "-c", script], cwd=mam_sandbox, env=env,
|
||||
stdout=subprocess.PIPE, stderr=subprocess.STDOUT)
|
||||
jid = None
|
||||
try:
|
||||
jid = t18._wait_job_id(reg)
|
||||
time.sleep(1)
|
||||
assert t18._publish(reg, jid, "started", env).returncode == 0
|
||||
assert _until(lambda: (reg / f"{jid}.stall.out").exists())
|
||||
state = json.loads(mock_herdr.read_text())
|
||||
state["wait_blocks_s"] = 0.3
|
||||
state["agents"]["headless-codex"].update(
|
||||
agent_status="blocked" if blocked else "working", pane_id="w1:p1",
|
||||
detection="Approval needed. Do you want to proceed?")
|
||||
mock_herdr.write_text(json.dumps(state))
|
||||
if blocked:
|
||||
assert _until(lambda: any(d.startswith("stalled:blocked") for d in _details(reg, jid)), 40)
|
||||
time.sleep(1)
|
||||
assert _record(reg, jid)["status"] == "running"
|
||||
os.set_blocking(p.stdout.fileno(), False)
|
||||
live = bytearray()
|
||||
while True:
|
||||
try:
|
||||
chunk = os.read(p.stdout.fileno(), 65536)
|
||||
except BlockingIOError:
|
||||
break
|
||||
if not chunk:
|
||||
break
|
||||
live.extend(chunk)
|
||||
os.set_blocking(p.stdout.fileno(), True)
|
||||
assert t18._publish(reg, jid, "completed", env).returncode == 0
|
||||
tail, _ = p.communicate(timeout=60)
|
||||
assert p.returncode == 0, (bytes(live) + tail).decode(errors="replace")
|
||||
assert (b"stalled:blocked" in live) is blocked, {
|
||||
"while_running": bytes(live).decode(errors="replace"),
|
||||
"after_completion": tail.decode(errors="replace"),
|
||||
}
|
||||
finally:
|
||||
if p.poll() is None:
|
||||
p.kill()
|
||||
p.communicate(timeout=10)
|
||||
|
||||
|
||||
@pytest.mark.parametrize("missed_transition", [False, True])
|
||||
def test_r4_a_missed_transition_restarts_the_idle_window(mam_sandbox, mock_herdr, missed_transition):
|
||||
"""Real watcher/clock/process tree; an external herdr stub models a missed transition.
|
||||
|
||||
The wait/get agent snapshots include state_change_seq, unlike the repository's
|
||||
wait mock. process-info retains its measured nested result shape.
|
||||
"""
|
||||
reg = mam_sandbox / ".mam" / "jobs"
|
||||
env = _env(mam_sandbox, MAM_STALL_IDLE_S=10)
|
||||
jid = _job(env, reg)
|
||||
agent = _proc("exec sleep 300")
|
||||
observed = mam_sandbox / "observed.json"
|
||||
observed.write_text(json.dumps({"seq": 0, "miss": missed_transition, "pid": agent.pid,
|
||||
"pane": _pane("codex")}))
|
||||
shim = mam_sandbox / "bin" / "herdr"
|
||||
shim.write_text(textwrap.dedent('''\
|
||||
#!/usr/bin/env python3
|
||||
import json, sys, time
|
||||
from pathlib import Path
|
||||
f = Path(__file__).parent.parent / 'observed.json'
|
||||
state = json.loads(f.read_text())
|
||||
args = sys.argv[1:]
|
||||
if args[:2] == ['agent', 'wait']:
|
||||
if not state.get('started'):
|
||||
state['started'] = time.monotonic()
|
||||
f.write_text(json.dumps(state))
|
||||
print(json.dumps({'result': {'agent': {'agent_status': 'idle', 'state_change_seq': 0, 'pane_id': 'w1:p1'}}}))
|
||||
else:
|
||||
time.sleep(int(args[args.index('--timeout') + 1]) / 1000)
|
||||
print(json.dumps({'error': {'code': 'timeout'}}), file=sys.stderr)
|
||||
sys.exit(1)
|
||||
elif args[:2] == ['agent', 'get']:
|
||||
if state['miss'] and not state.get('changed'):
|
||||
state['changed'] = time.monotonic()
|
||||
state['seq'] = 2
|
||||
f.write_text(json.dumps(state))
|
||||
print(json.dumps({'result': {'agent': {'agent_status': 'idle', 'state_change_seq': state['seq'], 'pane_id': 'w1:p1'}}}))
|
||||
elif args[:2] == ['pane', 'process-info']:
|
||||
print(json.dumps({'result': {'type': 'pane_process_info', 'process_info': {
|
||||
'pane_id': 'w1:p1', 'shell_pid': 1, 'foreground_process_group_id': state['pid'],
|
||||
'foreground_processes': [{'pid': state['pid'], 'name': 'codex', 'argv': ['codex'], 'cmdline': 'codex', 'cwd': '/tmp'}]}}}))
|
||||
elif args[:2] == ['agent', 'read']:
|
||||
print(state['pane'])
|
||||
elif args[:2] == ['agent', 'prompt']:
|
||||
state['prompted'] = time.monotonic()
|
||||
f.write_text(json.dumps(state))
|
||||
print('{}')
|
||||
else:
|
||||
sys.exit(2)
|
||||
'''))
|
||||
shim.chmod(0o755)
|
||||
w = None
|
||||
try:
|
||||
w = _watch(env, reg, jid, "reviewer-codex-t", "codex")
|
||||
assert _until(lambda: 'prompted' in json.loads(observed.read_text()), 90)
|
||||
times = json.loads(observed.read_text())
|
||||
# It may still be in a 30-second herdr wait after sending the prompt.
|
||||
_publish(env, reg, jid, 'completed')
|
||||
w.terminate()
|
||||
w.communicate(timeout=10)
|
||||
idle_time = times['prompted'] - times.get('changed', times['started'])
|
||||
assert idle_time >= 10, {'continuous_idle_seconds': idle_time, 'threshold': 10}
|
||||
finally:
|
||||
if w is not None and w.poll() is None:
|
||||
w.terminate()
|
||||
w.communicate(timeout=10)
|
||||
_kill(agent)
|
||||
|
||||
|
||||
def test_r1_the_codex_extractor_keeps_every_line_under_the_prompt():
|
||||
from lib_py.agents.input_region import extract_input_region
|
||||
idle = _pane("codex")
|
||||
assert extract_input_region(idle, "codex") == ""
|
||||
draft = idle.replace("› Ask Codex to do anything", "›\n draft on the second input line")
|
||||
assert extract_input_region(draft, "codex") == "draft on the second input line"
|
||||
no_footer = "\n".join(idle.splitlines()[:-1]).replace("› Ask Codex to do anything", "›\n a · b · c")
|
||||
assert extract_input_region(no_footer, "codex") != "", "only the last line may be the footer"
|
||||
@@ -322,3 +322,22 @@ def test_b5_a_wall_clock_close_is_closed_unconfirmed(tmp_path, monkeypatch, requ
|
||||
_publish(env, reg, c, "error", "--detail", detail)
|
||||
block = _runner(tmp_path, monkeypatch)._subjobs_block([p])
|
||||
assert f"| CLOSED-UNCONFIRMED | {detail} |" in block, block
|
||||
|
||||
|
||||
# Review 5ec8ef33 R3: the broker-unavailable wait that runs into the deadline
|
||||
# is the wall clock too (caller rc stays 3); broker_up is the passing twin.
|
||||
@pytest.mark.parametrize("broker_up", [True, False])
|
||||
def test_r3_a_budget_spent_waiting_on_an_unreachable_broker_is_wall_clock_timeout(tmp_path, broker_up):
|
||||
env = _env(tmp_path, broker=broker_up)
|
||||
reg = tmp_path / "jobs"
|
||||
p = _run_wrapper_bg(env, reg, "--timeout", "4", "--idle-timeout", "30")
|
||||
try:
|
||||
out, err = p.communicate(timeout=90)
|
||||
jid = next(reg.glob("*.json")).stem
|
||||
assert p.returncode == (2 if broker_up else 3), out + err
|
||||
assert _record(reg, jid)["status"] == "error"
|
||||
assert _last_error(reg, jid) == "wall_clock_timeout", err
|
||||
finally:
|
||||
if p.poll() is None:
|
||||
p.kill()
|
||||
p.communicate(timeout=10)
|
||||
Reference in new issue
Block a user