feat(issue-33): the job budget travels and the two clocks carry different labels
- wrapper: TIMEOUT falls back to MAM_JOB_TIMEOUT_S (--timeout > env > 3600); an invalid value warns and keeps 3600. - loop: --job-timeout <sec> (run_loop.sh passes it on; refused in the legacy shell loop). The runner always hands the wrapper --timeout, so the budget the wrapper registers is the one its wait caps come from. - runner: wait_for_job and the MAM_CHILD_WAIT_S default are budget + 300 s (MAM_WAIT_GRACE_S), today's 3900 with no option; an explicit MAM_CHILD_WAIT_S still wins. - subscriber: the wall-clock budget returns 4 (RC_WALL_CLOCK), silence keeps 2 (RC_NO_EVENT). The wrapper maps both to caller rc 2 and labels the close from the rc: wall_clock_timeout vs deadline_timeout; the disk-heartbeat grace that ends on the deadline is the wall clock too. - registry close accepts wall_clock_timeout (engine: -> error); the remote runner's deadline and command-timeout details lead with wall_clock_timeout; the sub-job table files it CLOSED-UNCONFIRMED (first token, colon stripped). Test expectations changed only where the contract changed: the loop's contract_args now starts with --timeout, the subscriber's exit-code docstring names rc 2/4, and the registry --help capture lists the new close kind. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
This commit is contained in:
GodopuandClaude Opus 5.5 committed
1 parent
8ea65bb238
commit
ec9586bb9b
11 files changed
+409
-23
No files matched your search
@@ -0,0 +1,324 @@
|
||||
"""Issue #33: the job budget travels, the wait caps follow it, and the two
|
||||
clocks that close a job carry different labels.
|
||||
|
||||
- B1: the real wrapper takes the budget from --timeout > $MAM_JOB_TIMEOUT_S > 3600.
|
||||
- B2: the loop runner derives its wait caps from the budget (+300 s) and hands
|
||||
the wrapper that budget explicitly; both hops run for real.
|
||||
- B3: the real wrapper + subscriber label a spent budget `wall_clock_timeout`
|
||||
(subscriber rc 4) and silence `deadline_timeout` (rc 2); caller rc is 2 for
|
||||
both. These need the live broker from the environment (like test_issue6 t1_1).
|
||||
- B4: the remote runner's two deadline wordings lead with the new label.
|
||||
- B5: the sub-job table files `wall_clock_timeout` closes as unconfirmed.
|
||||
"""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import json
|
||||
import os
|
||||
import re
|
||||
import signal
|
||||
import subprocess
|
||||
import sys
|
||||
import time
|
||||
import uuid
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
REPO_ROOT = Path(__file__).resolve().parent.parent
|
||||
SKILLS = REPO_ROOT / ".agents" / "skills"
|
||||
WRAPPER = SKILLS / "multi-agent-mux-delegate-job" / "multi-agent-mux-delegate-job"
|
||||
REGISTRY = SKILLS / "multi-agent-mux-delegate-job" / "scripts" / "registry.py"
|
||||
PUBLISH = SKILLS / "multi-agent-mux-delegate-job" / "scripts" / "publish_event.py"
|
||||
|
||||
if str(SKILLS) not in sys.path:
|
||||
sys.path.insert(0, str(SKILLS))
|
||||
|
||||
UNREACHABLE = {"MQTT_BROKER": "127.0.0.1", "MQTT_PORT": "9", "MQTT_TLS": "0"}
|
||||
|
||||
|
||||
def _env(home: Path, extra=None, broker: bool = False) -> dict:
|
||||
env = dict(os.environ)
|
||||
env["DELEGATE_JOB_PYTHON"] = sys.executable
|
||||
env["AGENT_PYTHON_BIN"] = sys.executable
|
||||
env["HOME"] = str(home)
|
||||
env["WORKSPACE_ROOT"] = str(home)
|
||||
env["PYTHONPATH"] = str(SKILLS)
|
||||
env["DELEGATE_JOB_LOGS_DIR"] = str(home / "logs")
|
||||
for k in ("MAM_JOBS_DIR", "MAM_REAL_ROOT", "MAM_JOB_ID", "MAM_JOB_TIMEOUT_S", "MAM_CHILD_WAIT_S",
|
||||
"MAM_WAIT_GRACE_S"):
|
||||
env.pop(k, None)
|
||||
if not broker:
|
||||
env["MAM_ENV_FILE"] = str(home / ".mam.env.absent")
|
||||
for k in ("MQTT_BROKER", "MQTT_HOST", "MQTT_PORT", "MQTT_TLS", "MQTT_USERNAME", "MQTT_PASSWORD"):
|
||||
env.pop(k, None)
|
||||
env.update(UNREACHABLE)
|
||||
if extra:
|
||||
env.update({k: str(v) for k, v in extra.items()})
|
||||
return env
|
||||
|
||||
|
||||
def _dry_submit(env: dict, reg: Path, *extra: str) -> subprocess.CompletedProcess:
|
||||
return subprocess.run(["bash", str(WRAPPER), "submit", "--agent", "human", "--dry-run",
|
||||
"--registry-dir", str(reg), "--prompt", "p", *extra],
|
||||
capture_output=True, text=True, env=env, cwd=env["HOME"], timeout=120)
|
||||
|
||||
|
||||
def _jid(res: subprocess.CompletedProcess) -> str:
|
||||
assert res.returncode == 0, res.stdout + res.stderr
|
||||
m = re.search(r"registered job:\s*(\S+)", res.stdout)
|
||||
assert m, res.stdout
|
||||
return m.group(1)
|
||||
|
||||
|
||||
def _record(reg: Path, jid: str) -> dict:
|
||||
return json.loads((reg / f"{jid}.json").read_text(encoding="utf-8"))
|
||||
|
||||
|
||||
def _events(reg: Path, jid: str) -> list:
|
||||
p = reg / f"{jid}.events.log"
|
||||
return [json.loads(l) for l in p.read_text().splitlines() if l.strip()] if p.exists() else []
|
||||
|
||||
|
||||
def _publish(env: dict, reg: Path, jid: str, event: str, *extra: str) -> subprocess.CompletedProcess:
|
||||
tok = _record(reg, jid)["dispatch_token"]
|
||||
res = subprocess.run([sys.executable, str(PUBLISH), "--registry-dir", str(reg), "--job", jid,
|
||||
"--event", event, "--expect-dispatch-token", tok, *extra],
|
||||
capture_output=True, text=True, env=env, timeout=120)
|
||||
assert res.returncode in (0, 2), res.stderr
|
||||
return res
|
||||
|
||||
|
||||
def _kill_timer(reg: Path, jid: str) -> None:
|
||||
try:
|
||||
os.kill(int((reg / f"{jid}.heartbeat.pid").read_text().strip()), signal.SIGKILL)
|
||||
except (OSError, ValueError):
|
||||
pass
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# B1 - the wrapper's budget: --timeout > MAM_JOB_TIMEOUT_S > 3600
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@pytest.mark.parametrize("env_val,flag,expected,warns", [
|
||||
(None, None, 3600, False),
|
||||
("7", None, 7, False),
|
||||
("7", "9", 9, False),
|
||||
("abc", None, 3600, True),
|
||||
])
|
||||
def test_b1_the_wrapper_takes_the_budget_from_flag_env_or_default(tmp_path, env_val, flag, expected, warns):
|
||||
env = _env(tmp_path, {"MAM_JOB_TIMEOUT_S": env_val} if env_val else None)
|
||||
res = _dry_submit(env, tmp_path / "reg", *(["--timeout", flag] if flag else []))
|
||||
assert _record(tmp_path / "reg", _jid(res))["timeout_sec"] == expected
|
||||
assert ("MAM_JOB_TIMEOUT_S=abc ignored" in res.stderr) is warns, res.stderr
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# B2 - the runner: budget -> wait caps, and the budget handed to the wrapper
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def _runner(tmp_path, monkeypatch, *argv, **env):
|
||||
monkeypatch.setenv("WORKSPACE_ROOT", str(tmp_path))
|
||||
monkeypatch.setenv("MAM_JOBS_DIR", str(tmp_path / "reg"))
|
||||
monkeypatch.setenv("DELEGATE_JOB_LOGS_DIR", str(tmp_path / "logs"))
|
||||
for k in ("MAM_REAL_ROOT", "MAM_JOB_TIMEOUT_S", "MAM_CHILD_WAIT_S", "MAM_WAIT_GRACE_S", "MAM_JOB_TREE_MAX"):
|
||||
monkeypatch.delenv(k, raising=False)
|
||||
for k, v in env.items():
|
||||
monkeypatch.setenv(k, str(v))
|
||||
from lib_py.loop import runner as lr
|
||||
r = lr.LoopRunner(["--creator", "c", "--task", "t", *argv])
|
||||
r.parse_args()
|
||||
return r
|
||||
|
||||
|
||||
def test_b2_the_wait_caps_are_the_budget_plus_300(tmp_path, monkeypatch):
|
||||
assert _runner(tmp_path, monkeypatch, "--job-timeout", "10").job_wait_s == 310
|
||||
assert _runner(tmp_path, monkeypatch, MAM_JOB_TIMEOUT_S=20).job_wait_s == 320
|
||||
assert _runner(tmp_path, monkeypatch, "--job-timeout", "10", MAM_JOB_TIMEOUT_S=20).job_wait_s == 310
|
||||
r = _runner(tmp_path, monkeypatch)
|
||||
assert (r.job_budget, r.job_wait_s) == (3600, 3900) # no option: today's numbers
|
||||
assert "--job-timeout" in "\n".join(_usage_lines(r))
|
||||
|
||||
|
||||
def _usage_lines(r):
|
||||
import io, contextlib
|
||||
buf = io.StringIO()
|
||||
with contextlib.redirect_stdout(buf), contextlib.redirect_stderr(buf):
|
||||
try:
|
||||
r.print_usage()
|
||||
except SystemExit:
|
||||
pass
|
||||
return buf.getvalue().splitlines()
|
||||
|
||||
|
||||
def test_b2_an_invalid_job_timeout_is_refused(tmp_path, monkeypatch):
|
||||
with pytest.raises(SystemExit):
|
||||
_runner(tmp_path, monkeypatch, "--job-timeout", "0")
|
||||
|
||||
|
||||
def test_b2_the_child_wait_defaults_to_the_budget_and_an_explicit_value_wins(tmp_path, monkeypatch, capsys):
|
||||
env = _env(tmp_path)
|
||||
reg = tmp_path / "reg"
|
||||
p = _jid(_dry_submit(env, reg))
|
||||
_jid(_dry_submit(env, reg, "--parent-job", p))
|
||||
|
||||
start = time.time()
|
||||
r = _runner(tmp_path, monkeypatch, "--job-timeout", "1", MAM_WAIT_GRACE_S=1)
|
||||
assert r.wait_for_descendants(p, interval=0.5) is False
|
||||
assert 2 <= time.time() - start < 8
|
||||
assert "ended after 2s (MAM_CHILD_WAIT_S default: job budget 1 + 1)" in capsys.readouterr().out
|
||||
|
||||
start = time.time()
|
||||
r = _runner(tmp_path, monkeypatch, "--job-timeout", "600", MAM_CHILD_WAIT_S=2)
|
||||
assert r.wait_for_descendants(p, interval=0.5) is False
|
||||
assert 2 <= time.time() - start < 8
|
||||
assert "ended after 2s (MAM_CHILD_WAIT_S)" in capsys.readouterr().out
|
||||
|
||||
|
||||
def test_b2_the_runner_hands_the_wrapper_its_budget_and_the_wrapper_registers_it(tmp_path, monkeypatch):
|
||||
# hop 1: the runner execs the wrapper with --timeout (a recording wrapper at the control root)
|
||||
rec = tmp_path / "rec.args"
|
||||
w = tmp_path / ".agents" / "skills" / "multi-agent-mux-delegate-job" / "multi-agent-mux-delegate-job"
|
||||
w.parent.mkdir(parents=True)
|
||||
w.write_text(f'#!/usr/bin/env bash\nprintf "%s\\n" "$@" > "{rec}"\necho "registered job: fake33"\n')
|
||||
w.chmod(0o755)
|
||||
r = _runner(tmp_path, monkeypatch, "--job-timeout", "10")
|
||||
assert r.delegate_job("c", "claude", "Worker", "task") == "fake33"
|
||||
args = rec.read_text().splitlines()
|
||||
assert args[args.index("--timeout") + 1] == "10"
|
||||
# env only: still passed explicitly
|
||||
r = _runner(tmp_path, monkeypatch, MAM_JOB_TIMEOUT_S=20)
|
||||
assert r.contract_args()[:2] == ["--timeout", "20"]
|
||||
|
||||
# hop 2: the real wrapper registers what the runner hands it
|
||||
reg = tmp_path / "reg2"
|
||||
res = _dry_submit(_env(tmp_path), reg, *_runner(tmp_path, monkeypatch, "--job-timeout", "10").contract_args())
|
||||
assert _record(reg, _jid(res))["timeout_sec"] == 10
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# B3 - the real wrapper + subscriber: which clock closed the job
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def _run_wrapper_bg(env: dict, reg: Path, *extra: str) -> subprocess.Popen:
|
||||
return subprocess.Popen(["bash", str(WRAPPER), "submit", "--agent", "human", "--registry-dir", str(reg),
|
||||
"--workdir", env["HOME"], "--prompt", "b3", *extra],
|
||||
stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True, env=env, cwd=env["HOME"])
|
||||
|
||||
|
||||
def _wait_subscribed(reg: Path, timeout: float = 30) -> str:
|
||||
deadline = time.time() + timeout
|
||||
while time.time() < deadline:
|
||||
for f in reg.glob("*.subscriber.out"):
|
||||
if "SUBSCRIBED" in f.read_text(errors="replace"):
|
||||
return f.name.split(".")[0]
|
||||
time.sleep(0.1)
|
||||
raise AssertionError("the subscriber never subscribed (is the broker up?)")
|
||||
|
||||
|
||||
def _last_error(reg: Path, jid: str) -> str:
|
||||
errs = [e for e in _events(reg, jid) if e.get("event") == "error"]
|
||||
assert errs, _events(reg, jid)
|
||||
return errs[-1].get("detail", "")
|
||||
|
||||
|
||||
def test_b3_wall_clock_before_idle_is_labelled_wall_clock_timeout(tmp_path):
|
||||
env = _env(tmp_path, broker=True)
|
||||
reg = tmp_path / "jobs"
|
||||
proc = _run_wrapper_bg(env, reg, "--timeout", "3", "--idle-timeout", "30")
|
||||
out, err = proc.communicate(timeout=90)
|
||||
assert proc.returncode == 2, out + err
|
||||
jid = next(reg.glob("*.json")).stem
|
||||
assert _record(reg, jid)["status"] == "error"
|
||||
assert _last_error(reg, jid) == "wall_clock_timeout"
|
||||
assert "wall-clock timeout" in (reg / f"{jid}.subscriber.out").read_text()
|
||||
assert "closed by wall_clock clock" in err
|
||||
|
||||
|
||||
def test_b3_silence_is_still_labelled_deadline_timeout(tmp_path):
|
||||
env = _env(tmp_path, broker=True)
|
||||
reg = tmp_path / "jobs"
|
||||
proc = _run_wrapper_bg(env, reg, "--timeout", "30", "--idle-timeout", "2")
|
||||
try:
|
||||
jid = _wait_subscribed(reg)
|
||||
_publish(env, reg, jid, "started") # then nothing: silence for K x N
|
||||
out, err = proc.communicate(timeout=90)
|
||||
finally:
|
||||
proc.kill()
|
||||
assert proc.returncode == 2, out + err
|
||||
assert _record(reg, jid)["status"] == "error"
|
||||
assert _last_error(reg, jid) == "deadline_timeout"
|
||||
assert "idle timeout" in (reg / f"{jid}.subscriber.out").read_text()
|
||||
assert "closed by no_event clock" in err
|
||||
|
||||
|
||||
def test_b3_a_heartbeating_job_that_spends_its_budget_is_wall_clock_timeout(tmp_path):
|
||||
"""The #33 motivating case: a live agent (heartbeats keep coming) whose
|
||||
work outlasts the budget was reported as `deadline_timeout`."""
|
||||
env = _env(tmp_path, broker=True)
|
||||
reg = tmp_path / "jobs"
|
||||
proc = _run_wrapper_bg(env, reg, "--timeout", "6", "--idle-timeout", "3")
|
||||
jid = None
|
||||
try:
|
||||
jid = _wait_subscribed(reg)
|
||||
_publish(env, reg, jid, "started", "--heartbeat", "1")
|
||||
out, err = proc.communicate(timeout=90)
|
||||
finally:
|
||||
proc.kill()
|
||||
if jid:
|
||||
_kill_timer(reg, jid)
|
||||
assert proc.returncode == 2, out + err
|
||||
assert _last_error(reg, jid) == "wall_clock_timeout"
|
||||
assert "wall-clock timeout" in (reg / f"{jid}.subscriber.out").read_text()
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# B4 - the remote runner's deadlines are wall clocks
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
def _dispatch(timeout_sec=1) -> dict:
|
||||
return {"job_id": uuid.uuid4().hex[:8], "brief": "b", "dispatch_token": "tok-" + uuid.uuid4().hex,
|
||||
"attempt_id": 1, "auth_token": None, "timeout_sec": timeout_sec, "heartbeat_sec": 30,
|
||||
"heartbeat_misses": 4, "ack_timeout_sec": 5}
|
||||
|
||||
|
||||
@pytest.mark.parametrize("cmd,prefix", [("sleep 5", "wall_clock_timeout: agent command exceeded timeout_sec 1"),
|
||||
(None, "wall_clock_timeout (remote runner)")])
|
||||
def test_b4_the_remote_runner_labels_its_deadline_wall_clock_timeout(tmp_path, monkeypatch, cmd, prefix):
|
||||
from lib_py.delegation import remote
|
||||
for k, v in _env(tmp_path).items():
|
||||
monkeypatch.setenv(k, v)
|
||||
monkeypatch.chdir(tmp_path)
|
||||
reg = tmp_path / "jobs"
|
||||
d = _dispatch()
|
||||
try:
|
||||
remote.handle_dispatch(d, str(reg), "s", cmd)
|
||||
assert _record(reg, d["job_id"])["status"] == "error"
|
||||
assert _last_error(reg, d["job_id"]).startswith(prefix)
|
||||
finally:
|
||||
_kill_timer(reg, d["job_id"])
|
||||
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# B5 - the sub-job table: a wall-clock close is unconfirmed, like a deadline close
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
@pytest.mark.parametrize("request_kind,detail", [
|
||||
("wall_clock_timeout", "wall_clock_timeout"),
|
||||
("wall_clock_timeout", "wall_clock_timeout: agent command exceeded timeout_sec 1"),
|
||||
("deadline_timeout", "deadline_timeout"),
|
||||
])
|
||||
def test_b5_a_wall_clock_close_is_closed_unconfirmed(tmp_path, monkeypatch, request_kind, detail):
|
||||
env = _env(tmp_path)
|
||||
reg = tmp_path / "reg"
|
||||
p = _jid(_dry_submit(env, reg))
|
||||
c = _jid(_dry_submit(env, reg, "--parent-job", p))
|
||||
tok = _record(reg, c)["dispatch_token"]
|
||||
res = subprocess.run([sys.executable, str(REGISTRY), "--registry-dir", str(reg), "close", "--job", c,
|
||||
"--request", request_kind, "--expect-dispatch-token", tok],
|
||||
capture_output=True, text=True, env=env, timeout=120)
|
||||
assert res.returncode == 0, res.stderr
|
||||
assert _record(reg, c)["status"] == "error"
|
||||
_publish(env, reg, c, "error", "--detail", detail)
|
||||
block = _runner(tmp_path, monkeypatch)._subjobs_block([p])
|
||||
assert f"| CLOSED-UNCONFIRMED | {detail} |" in block, block
|
||||
Reference in new issue
Block a user