628 lines
27 KiB
Python
628 lines
27 KiB
Python
"""派发队列与沙箱执行器的单测。
|
||
|
||
运行（在 ~/workspace/codex-app-server 下）：
|
||
python3 -m unittest discover -s cloud/tests -p "test_queue_sandbox.py" -v
|
||
|
||
说明：cloud/ 没有 __init__.py（协调员统一创建），因此这里把 cloud/
|
||
目录插到 sys.path 前面再导入 queue / sandbox，与 discover 的
|
||
top-level 目录无关。
|
||
"""
|
||
|
||
import json
|
||
import os
|
||
import sys
|
||
import unittest
|
||
from types import SimpleNamespace
|
||
from unittest import mock
|
||
|
||
sys.path.insert(0, os.path.dirname(os.path.dirname(
|
||
os.path.abspath(__file__))))
|
||
|
||
from queue import TaskQueue, budget_exceeded, order_tasks, ready_tasks
|
||
from sandbox import (CloudExecutor, DockerExecutor, Executor,
|
||
LocalExecutor, _parse_goal_output,
|
||
_parse_host_result, _result_text)
|
||
|
||
|
||
def _task(task_id, depends_on=None, priority=0, status="queued"):
|
||
task = {"id": task_id, "priority": priority, "status": status}
|
||
if depends_on is not None:
|
||
task["depends_on"] = depends_on
|
||
return task
|
||
|
||
|
||
class TestOrderTasks(unittest.TestCase):
|
||
def test_dependency_order(self):
|
||
# A -> B 时 B 在 A 后
|
||
ordered = order_tasks([_task("B", depends_on=["A"]),
|
||
_task("A")])
|
||
self.assertEqual([t["id"] for t in ordered], ["A", "B"])
|
||
|
||
def test_dependency_chain(self):
|
||
ordered = order_tasks([_task("C", depends_on=["B"]),
|
||
_task("B", depends_on=["A"]),
|
||
_task("A")])
|
||
self.assertEqual([t["id"] for t in ordered], ["A", "B", "C"])
|
||
|
||
def test_priority_within_wave(self):
|
||
# 同一波（均无依赖）按 priority 大的先
|
||
ordered = order_tasks([_task("low", priority=1),
|
||
_task("high", priority=10),
|
||
_task("mid", priority=5)])
|
||
self.assertEqual([t["id"] for t in ordered],
|
||
["high", "mid", "low"])
|
||
|
||
def test_priority_does_not_jump_dependency(self):
|
||
# 高优先级也不能越过依赖：B 依赖 A，即使 B 优先级更高也排 A 后
|
||
ordered = order_tasks([_task("B", depends_on=["A"], priority=99),
|
||
_task("A", priority=0)])
|
||
self.assertEqual([t["id"] for t in ordered], ["A", "B"])
|
||
|
||
def test_missing_dependency_raises(self):
|
||
with self.assertRaises(ValueError):
|
||
order_tasks([_task("B", depends_on=["NOPE"])])
|
||
|
||
def test_cycle_raises(self):
|
||
with self.assertRaises(ValueError):
|
||
order_tasks([_task("A", depends_on=["B"]),
|
||
_task("B", depends_on=["A"])])
|
||
|
||
def test_self_dependency_raises(self):
|
||
with self.assertRaises(ValueError):
|
||
order_tasks([_task("A", depends_on=["A"])])
|
||
|
||
def test_defaults(self):
|
||
# depends_on / priority 缺省时按 0 处理、不报错
|
||
ordered = order_tasks([{"id": "A"}, {"id": "B"}])
|
||
self.assertEqual([t["id"] for t in ordered], ["A", "B"])
|
||
|
||
|
||
class TestReadyTasks(unittest.TestCase):
|
||
def test_only_dependency_satisfied_queued(self):
|
||
tasks = [_task("A"),
|
||
_task("B", depends_on=["A"]),
|
||
_task("C", depends_on=["A"], status="running"),
|
||
_task("D", depends_on=["MISSING"])]
|
||
ready = ready_tasks(tasks, completed_ids=[])
|
||
self.assertEqual([t["id"] for t in ready], ["A"])
|
||
|
||
# A 已完成（状态随之改为 completed）后，B 依赖满足且 queued；
|
||
# C 是 running 不返回；D 依赖未满足不返回
|
||
done_tasks = [_task("A", status="completed"),
|
||
_task("B", depends_on=["A"]),
|
||
_task("C", depends_on=["A"], status="running"),
|
||
_task("D", depends_on=["MISSING"])]
|
||
ready = ready_tasks(done_tasks, completed_ids=["A"])
|
||
self.assertEqual([t["id"] for t in ready], ["B"])
|
||
|
||
def test_ready_ordered_by_priority(self):
|
||
tasks = [_task("low", priority=1), _task("high", priority=9)]
|
||
ready = ready_tasks(tasks, completed_ids=[])
|
||
self.assertEqual([t["id"] for t in ready], ["high", "low"])
|
||
|
||
|
||
class TestBudgetExceeded(unittest.TestCase):
|
||
def test_below_limits(self):
|
||
self.assertFalse(budget_exceeded(5, 10, 0.5, 1.0))
|
||
|
||
def test_at_limit_counts_as_exceeded(self):
|
||
self.assertTrue(budget_exceeded(10, 10, 0.5, 1.0))
|
||
self.assertTrue(budget_exceeded(5, 10, 1.0, 1.0))
|
||
|
||
def test_none_limit_means_unlimited(self):
|
||
self.assertFalse(budget_exceeded(10 ** 9, None, 10 ** 9, None))
|
||
self.assertTrue(budget_exceeded(10 ** 9, None, 10 ** 9, 1.0))
|
||
|
||
|
||
class TestTaskQueue(unittest.TestCase):
|
||
def test_next_ready_flow(self):
|
||
queue = TaskQueue()
|
||
queue.add(_task("A"))
|
||
queue.add(_task("B", depends_on=["A"]))
|
||
self.assertEqual(queue.next_ready([])["id"], "A")
|
||
queue.mark_running("A")
|
||
# A 在 running，不再是可派任务；B 依赖未完成，也不可派
|
||
self.assertIsNone(queue.next_ready([]))
|
||
queue.mark_done("A", "completed")
|
||
self.assertEqual(queue.next_ready(["A"])["id"], "B")
|
||
|
||
def test_mark_done_validates_status(self):
|
||
queue = TaskQueue([_task("A")])
|
||
with self.assertRaises(ValueError):
|
||
queue.mark_done("A", "bogus-status")
|
||
with self.assertRaises(ValueError):
|
||
queue.add(_task("A")) # 重复 id
|
||
|
||
def test_all_host_statuses_accepted(self):
|
||
queue = TaskQueue()
|
||
for status in ("running", "completed", "failed",
|
||
"interrupted", "merged", "merge-failed"):
|
||
queue.add(_task("t-" + status, status=status))
|
||
# 非 queued 任务一律不可派
|
||
self.assertIsNone(queue.next_ready([]))
|
||
|
||
|
||
class TestExecutors(unittest.TestCase):
|
||
def test_base_executor_must_implement(self):
|
||
with self.assertRaises(NotImplementedError):
|
||
Executor().execute({"id": "x"})
|
||
|
||
def test_local_executor_success(self):
|
||
seen = []
|
||
|
||
def fake_runner(cmd):
|
||
seen.append(cmd)
|
||
return SimpleNamespace(returncode=0, stdout="ok-status")
|
||
|
||
executor = LocalExecutor("/fake/host.py", config_path="/fake/cfg.json",
|
||
runner=fake_runner)
|
||
result = executor.execute({"id": "t1", "project_id": "p",
|
||
"repo": "/r", "prompt": "hi"})
|
||
self.assertEqual(result["executor"], "local")
|
||
self.assertEqual(result["task_id"], "t1")
|
||
self.assertEqual(result["status"], "completed")
|
||
self.assertEqual(result["stdout"], "ok-status")
|
||
# 只发只读 status 命令，不发 dispatch/run（不直接跑模型）
|
||
self.assertIn("status", seen[0])
|
||
self.assertNotIn("dispatch", seen[0])
|
||
self.assertNotIn("run", seen[0])
|
||
self.assertIn("--config", seen[0])
|
||
|
||
def test_local_executor_failure(self):
|
||
def fake_runner(cmd):
|
||
return SimpleNamespace(returncode=1, stdout="boom")
|
||
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=fake_runner).execute({"id": "t2"})
|
||
self.assertEqual(result["status"], "failed")
|
||
self.assertEqual(result["stdout"], "boom")
|
||
|
||
def test_local_executor_truncates_stdout(self):
|
||
# 20000 字上限：5000 字不再截断，25000 字截断并带标记。
|
||
def fake_runner(cmd):
|
||
return SimpleNamespace(returncode=0, stdout="x" * 5000)
|
||
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=fake_runner).execute({"id": "t3"})
|
||
self.assertEqual(len(result["stdout"]), 5000)
|
||
|
||
def long_runner(cmd):
|
||
return SimpleNamespace(returncode=0, stdout="y" * 25000)
|
||
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=long_runner).execute({"id": "t4"})
|
||
self.assertIn("结果已截断", result["stdout"])
|
||
self.assertTrue(result["stdout"].startswith("y" * 20000))
|
||
|
||
def test_result_text_extracts_long_json_text(self):
|
||
# 2026-10-30 生产审计任务的复发：host.py JSON 的 text
|
||
# 超过旧 2000 字截断时，存库的不能是截断的 JSON，
|
||
# 必须是完整提取出的 text（本例 5000 字，全部保留）。
|
||
text = "z" * 5000
|
||
payload = json.dumps({"status": "completed", "text": text})
|
||
result = _parse_host_result(
|
||
"t5", SimpleNamespace(returncode=0, stdout=payload,
|
||
stderr=""))
|
||
self.assertEqual(result["stdout"], text)
|
||
self.assertEqual(result["status"], "completed")
|
||
|
||
def test_result_text_marks_over_limit(self):
|
||
text = "w" * 21000
|
||
self.assertIn("结果已截断", _result_text(
|
||
{"text": text}, "unused"))
|
||
|
||
def test_docker_executor_no_docker_raises_not_local(self):
|
||
with mock.patch("sandbox.shutil.which", return_value=None):
|
||
with self.assertRaises(RuntimeError) as ctx:
|
||
DockerExecutor().execute({"id": "t1"})
|
||
self.assertIn("docker not available", str(ctx.exception))
|
||
# 报错而不是返回 local 结果：绝不静默降级为本地执行
|
||
|
||
def test_docker_executor_with_docker_runs_container(self):
|
||
seen = []
|
||
|
||
def fake_runner(cmd, timeout=None):
|
||
seen.append(cmd)
|
||
return SimpleNamespace(returncode=0, stdout="ok-status")
|
||
|
||
with mock.patch("sandbox.shutil.which",
|
||
return_value="/usr/bin/docker"):
|
||
executor = DockerExecutor(
|
||
"/fake/host.py", runner=fake_runner,
|
||
env={"XCM_API_KEY": "placeholder-not-a-real-key"})
|
||
result = executor.execute({"id": "t1", "worktree": "/tmp/wt1"})
|
||
self.assertEqual(result["executor"], "docker")
|
||
self.assertEqual(result["status"], "completed")
|
||
self.assertEqual(seen[0][0:2], ["docker", "run"])
|
||
self.assertIn("--rm", seen[0])
|
||
self.assertIn("/tmp/wt1:/work", seen[0])
|
||
self.assertIn("/fake:/app:ro", seen[0])
|
||
# -e 只传名，值绝不出现在命令列表里。
|
||
self.assertIn("XCM_API_KEY", seen[0])
|
||
self.assertNotIn("placeholder-not-a-real-key", seen[0])
|
||
self.assertNotIn("placeholder-not-a-real-key", " ".join(seen[0]))
|
||
|
||
def test_cloud_executor_raises_with_cloud_account(self):
|
||
with self.assertRaises(RuntimeError) as ctx:
|
||
CloudExecutor().execute({"id": "t1"})
|
||
self.assertIn("cloud account", str(ctx.exception))
|
||
|
||
|
||
class TestGoalExecutors(unittest.TestCase):
|
||
def test_parse_goal_output(self):
|
||
met, err = _parse_goal_output(
|
||
"round 1: turn=completed verify_rc=0 verify_out=ok\n"
|
||
"goal met after rounds\n")
|
||
self.assertTrue(met)
|
||
self.assertIsNone(err)
|
||
met, err = _parse_goal_output(
|
||
"round 1: turn=completed verify_rc=1 verify_out=file missing\n"
|
||
"round 2: turn=completed verify_rc=1 verify_out=file missing\n"
|
||
"goal unmet after rounds\n")
|
||
self.assertFalse(met)
|
||
self.assertIn("file missing", err)
|
||
self.assertIn("2 rounds", err)
|
||
met, err = _parse_goal_output("some other output\n")
|
||
self.assertIsNone(met)
|
||
met, err = _parse_goal_output("")
|
||
self.assertIsNone(met)
|
||
|
||
def test_local_goal_task_met(self):
|
||
seen = []
|
||
|
||
def fake(cmd):
|
||
seen.append(cmd)
|
||
return SimpleNamespace(
|
||
returncode=0,
|
||
stdout="round 1: turn=completed verify_rc=0 verify_out=ok\n"
|
||
"goal met after rounds\n",
|
||
stderr="")
|
||
|
||
executor = LocalExecutor("/fake/host.py", runner=fake)
|
||
result = executor.goal_task(
|
||
{"id": "t1", "prompt": "do it", "verify_command": "test -f x",
|
||
"goal_max_rounds": 2, "repo": "/r"})
|
||
self.assertEqual(result["status"], "completed")
|
||
self.assertTrue(result["goal_met"])
|
||
self.assertIsNone(result["goal_error"])
|
||
self.assertEqual(result["host_status"], "goal-met")
|
||
self.assertIn("goal", seen[0])
|
||
self.assertIn("--verify", seen[0])
|
||
self.assertIn("test -f x", seen[0])
|
||
self.assertIn("/r", seen[0])
|
||
self.assertEqual(seen[0][seen[0].index("--max-rounds") + 1], "2")
|
||
|
||
def test_local_goal_task_unmet(self):
|
||
def fake(cmd):
|
||
return SimpleNamespace(
|
||
returncode=0,
|
||
stdout="round 1: turn=completed verify_rc=1 "
|
||
"verify_out=file missing\n"
|
||
"goal unmet after rounds\n",
|
||
stderr="")
|
||
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=fake).goal_task(
|
||
{"id": "t1", "prompt": "do it",
|
||
"verify_command": "test -f x"})
|
||
self.assertEqual(result["status"], "failed")
|
||
self.assertFalse(result["goal_met"])
|
||
self.assertIn("file missing", result["goal_error"])
|
||
self.assertEqual(result["host_status"], "goal-unmet")
|
||
|
||
def test_local_goal_task_defaults_prompt_and_rounds(self):
|
||
seen = []
|
||
|
||
def fake(cmd):
|
||
seen.append(list(cmd))
|
||
return SimpleNamespace(
|
||
returncode=0, stdout="goal met after rounds\n", stderr="")
|
||
|
||
LocalExecutor("/fake/host.py", runner=fake).goal_task(
|
||
{"id": "t1", "prompt": "do it", "verify_command": "true"})
|
||
self.assertIn("do it", seen[0])
|
||
self.assertEqual(seen[0][seen[0].index("--max-rounds") + 1], "3")
|
||
|
||
def test_local_goal_task_no_conclusion_is_failed_not_completed(self):
|
||
def fake(cmd):
|
||
return SimpleNamespace(returncode=0, stdout="nothing\n",
|
||
stderr="")
|
||
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=fake).goal_task(
|
||
{"id": "t1", "prompt": "do it",
|
||
"verify_command": "true"})
|
||
self.assertEqual(result["status"], "failed")
|
||
self.assertIsNone(result["goal_met"])
|
||
self.assertIn("无结论", result["goal_error"])
|
||
|
||
def test_local_goal_task_nonzero_without_conclusion_is_interrupted(self):
|
||
# 2026-10-28 长 goal 实弹：无结论的异常退出（进程被杀、
|
||
# 连接断后恢复时抛错）必须记 interrupted 保住断点续跑，
|
||
# 绝不能一律 failed（旧语义直接断了 60 分钟工作的活路）。
|
||
def fake(cmd):
|
||
return SimpleNamespace(returncode=1, stdout="", stderr="boom")
|
||
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=fake).goal_task(
|
||
{"id": "t1", "prompt": "do it",
|
||
"verify_command": "true"})
|
||
self.assertEqual(result["status"], "interrupted")
|
||
self.assertIsNone(result["goal_met"])
|
||
self.assertIn("boom", result["goal_error"])
|
||
|
||
def test_local_goal_task_nonzero_with_unmet_stays_failed(self):
|
||
def fake(cmd):
|
||
return SimpleNamespace(
|
||
returncode=1,
|
||
stdout="round 1: turn=completed verify_rc=1 "
|
||
"verify_out=file missing\n"
|
||
"goal unmet after rounds\n",
|
||
stderr="")
|
||
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=fake).goal_task(
|
||
{"id": "t1", "prompt": "do it",
|
||
"verify_command": "true"})
|
||
self.assertEqual(result["status"], "failed")
|
||
self.assertIs(result["goal_met"], False)
|
||
|
||
def test_local_goal_task_interrupted_marker(self):
|
||
def fake(cmd):
|
||
return SimpleNamespace(
|
||
returncode=0,
|
||
stdout="round 1: turn=interrupted verify_rc=- "
|
||
"verify_out=\n"
|
||
"goal interrupted after rounds: relay boom\n",
|
||
stderr="")
|
||
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=fake).goal_task(
|
||
{"id": "t1", "prompt": "do it",
|
||
"verify_command": "true"})
|
||
self.assertEqual(result["status"], "interrupted")
|
||
self.assertIn("relay boom", result["goal_error"])
|
||
|
||
def test_docker_goal_task_nonzero_without_conclusion_is_interrupted(self):
|
||
def fake_runner(cmd, timeout=None):
|
||
return SimpleNamespace(returncode=1, stdout="",
|
||
stderr="boom")
|
||
|
||
with mock.patch("sandbox.shutil.which",
|
||
return_value="/usr/bin/docker"):
|
||
executor = DockerExecutor(
|
||
"/fake/host.py", runner=fake_runner,
|
||
env={"XCM_API_KEY": "placeholder-not-a-real-key"})
|
||
result = executor.goal_task(
|
||
{"id": "t1", "prompt": "do it",
|
||
"verify_command": "test -f x"})
|
||
self.assertEqual(result["status"], "interrupted")
|
||
self.assertIn("boom", result["goal_error"])
|
||
|
||
def test_docker_goal_resume_nonzero_without_conclusion_is_interrupted(self):
|
||
# 覆盖 docker 侧两处 resume 解析（goal_resume_task 与
|
||
# goal_resume_breakpoint_task 共用 shape B 链路，两个都测）。
|
||
def fake_runner(cmd, timeout=None):
|
||
return SimpleNamespace(returncode=1, stdout="",
|
||
stderr="boom")
|
||
|
||
with mock.patch("sandbox.shutil.which",
|
||
return_value="/usr/bin/docker"):
|
||
executor = DockerExecutor(
|
||
"/fake/host.py", runner=fake_runner,
|
||
env={"XCM_API_KEY": "placeholder-not-a-real-key"})
|
||
for method in ("goal_resume_task",
|
||
"goal_resume_breakpoint_task"):
|
||
result = getattr(executor, method)(
|
||
{"id": "t1", "prompt": "do it"})
|
||
self.assertEqual(result["status"], "interrupted")
|
||
self.assertIn("boom", result["goal_error"])
|
||
|
||
def test_goal_resume_refusal_is_failed_not_interrupted(self):
|
||
# 断点丢失拒绝（2026-10-29 实弹）：host-state 里没有任务时
|
||
# goal-resume 只打印拒绝行、正常退出；三处解析（本地、
|
||
# Docker goal_resume_task、Docker 断点）都必须判 failed
|
||
# 终态，绝不能判 interrupted——否则自动恢复 12 秒一轮
|
||
# 空转到 50 次上限。
|
||
refusal = ("goal-resume 拒绝：host-state 里没有该任务 t1，"
|
||
"断点已丢失，不能续跑\n")
|
||
fake = SimpleNamespace(returncode=0, stdout=refusal, stderr="")
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=lambda cmd: fake
|
||
)._goal_result_from_runner("t1", fake)
|
||
self.assertEqual(result["status"], "failed")
|
||
self.assertIn("goal-resume 拒绝", result["goal_error"])
|
||
|
||
def fake_runner(cmd, timeout=None, env=None):
|
||
return SimpleNamespace(returncode=0, stdout=refusal,
|
||
stderr="")
|
||
|
||
with mock.patch("sandbox.shutil.which",
|
||
return_value="/usr/bin/docker"):
|
||
executor = DockerExecutor(
|
||
"/fake/host.py", runner=fake_runner,
|
||
env={"XCM_API_KEY": "placeholder-not-a-real-key"})
|
||
for method in ("goal_resume_task",
|
||
"goal_resume_breakpoint_task"):
|
||
result = getattr(executor, method)(
|
||
{"id": "t1", "prompt": "do it"})
|
||
self.assertEqual(result["status"], "failed")
|
||
self.assertIn("goal-resume 拒绝", result["goal_error"])
|
||
|
||
def test_local_goal_task_already_exists_names_retry(self):
|
||
def fake(cmd):
|
||
return SimpleNamespace(
|
||
returncode=1, stdout="",
|
||
stderr="Traceback\nRuntimeError: 任务已存在")
|
||
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=fake).goal_task(
|
||
{"id": "t1", "prompt": "do it",
|
||
"verify_command": "true"})
|
||
self.assertEqual(result["status"], "failed")
|
||
# P1 新语义：goal 失败请用继续而非重试（旧“请新建任务”已废）。
|
||
self.assertIn("请用继续而非重试", result["goal_error"])
|
||
|
||
def test_local_goal_task_without_verify_is_llm_decided(self):
|
||
# 新语义：没有验收命令不再抛错——走模型自决分支：
|
||
# 命令里没有 --verify，轮次缺省仍为 3（任务行没写时）。
|
||
seen = []
|
||
|
||
def fake(cmd):
|
||
seen.append(list(cmd))
|
||
return SimpleNamespace(
|
||
returncode=0,
|
||
stdout="goal met after rounds\n",
|
||
stderr="")
|
||
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=fake).goal_task(
|
||
{"id": "t1", "prompt": "do it"})
|
||
self.assertEqual(result["status"], "completed")
|
||
self.assertNotIn("--verify", seen[0])
|
||
self.assertEqual(seen[0][seen[0].index("--max-rounds") + 1], "3")
|
||
|
||
def test_base_goal_task_not_implemented(self):
|
||
with self.assertRaises(NotImplementedError):
|
||
Executor().goal_task({"id": "t1"})
|
||
|
||
def test_popen_goal_command(self):
|
||
seen = []
|
||
|
||
class _FakePopen:
|
||
def __init__(self, cmd, **kwargs):
|
||
seen.append(list(cmd))
|
||
|
||
with mock.patch("sandbox.subprocess.Popen", _FakePopen):
|
||
LocalExecutor("/fake/host.py").popen_task(
|
||
{"id": "t1", "prompt": "do it",
|
||
"verify_command": "test -f x", "goal_max_rounds": 2},
|
||
kind="goal")
|
||
self.assertIn("goal", seen[0])
|
||
self.assertIn("test -f x", seen[0])
|
||
self.assertEqual(seen[0][seen[0].index("--max-rounds") + 1], "2")
|
||
|
||
def test_docker_goal_task_unmet(self):
|
||
seen = []
|
||
|
||
def fake_runner(cmd, timeout=None):
|
||
seen.append(cmd)
|
||
return SimpleNamespace(
|
||
returncode=0,
|
||
stdout="round 1: turn=completed verify_rc=1 "
|
||
"verify_out=file missing\n"
|
||
"goal unmet after rounds\n",
|
||
stderr="")
|
||
|
||
with mock.patch("sandbox.shutil.which",
|
||
return_value="/usr/bin/docker"):
|
||
executor = DockerExecutor(
|
||
"/fake/host.py", runner=fake_runner,
|
||
env={"XCM_API_KEY": "placeholder-not-a-real-key"})
|
||
result = executor.goal_task(
|
||
{"id": "t1", "prompt": "do it",
|
||
"verify_command": "test -f x"})
|
||
self.assertEqual(result["executor"], "docker")
|
||
self.assertEqual(result["status"], "failed")
|
||
self.assertFalse(result["goal_met"])
|
||
self.assertIn("goal", seen[0])
|
||
self.assertIn("test -f x", seen[0])
|
||
|
||
|
||
class TestUsageParsing(unittest.TestCase):
|
||
def test_result_from_runner_usage(self):
|
||
usage = {"input_tokens": 1000, "cached_input_tokens": 400,
|
||
"cache_write_input_tokens": 0, "output_tokens": 100,
|
||
"reasoning_output_tokens": 20, "total_tokens": 1100,
|
||
"completions": 2}
|
||
fake = SimpleNamespace(
|
||
returncode=0,
|
||
stdout=json.dumps({"status": "completed", "text": "done",
|
||
"usage": usage}),
|
||
stderr="")
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=lambda cmd: fake
|
||
)._result_from_runner("t1", fake)
|
||
self.assertEqual(result["usage"], usage)
|
||
self.assertEqual(result["status"], "completed")
|
||
|
||
def test_result_from_runner_usage_survives_long_text(self):
|
||
# usage 在 JSON 末尾：旧的截头解析在 text 很长时会丢 usage、
|
||
# 还会把 failed 误判成 completed；解析必须用完整 stdout。
|
||
usage = {"input_tokens": 100, "cached_input_tokens": 0,
|
||
"cache_write_input_tokens": 0, "output_tokens": 10,
|
||
"reasoning_output_tokens": 0, "total_tokens": 110,
|
||
"completions": 1}
|
||
fake = SimpleNamespace(
|
||
returncode=0,
|
||
stdout=json.dumps({"status": "failed", "text": "x" * 5000,
|
||
"usage": usage}),
|
||
stderr="")
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=lambda cmd: fake
|
||
)._result_from_runner("t1", fake)
|
||
self.assertEqual(result["status"], "failed")
|
||
self.assertEqual(result["usage"], usage)
|
||
|
||
def test_result_from_runner_dirty_usage_dropped(self):
|
||
for bad in ({"input_tokens": "abc"},
|
||
{"input_tokens": 0, "output_tokens": 0,
|
||
"total_tokens": 0},
|
||
"not-a-dict"):
|
||
fake = SimpleNamespace(
|
||
returncode=0,
|
||
stdout=json.dumps({"status": "completed", "usage": bad}),
|
||
stderr="")
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=lambda cmd: fake
|
||
)._result_from_runner("t1", fake)
|
||
self.assertIsNone(result["usage"])
|
||
|
||
def test_goal_usage_line(self):
|
||
fake = SimpleNamespace(
|
||
returncode=0,
|
||
stdout="round 1: turn=completed verify_rc=0 verify_out=ok\n"
|
||
"goal met after rounds\n"
|
||
"usage input=100 cached=40 cache_write=0 output=50 "
|
||
"reasoning=10 total=150 completions=2\n",
|
||
stderr="")
|
||
result = LocalExecutor("/fake/host.py",
|
||
runner=lambda cmd: fake
|
||
)._goal_result_from_runner("t1", fake)
|
||
self.assertEqual(result["usage"], {
|
||
"input_tokens": 100, "cached_input_tokens": 40,
|
||
"cache_write_input_tokens": 0, "output_tokens": 50,
|
||
"reasoning_output_tokens": 10, "total_tokens": 150,
|
||
"completions": 2})
|
||
fake2 = SimpleNamespace(
|
||
returncode=0, stdout="goal met after rounds\n", stderr="")
|
||
result2 = LocalExecutor("/fake/host.py",
|
||
runner=lambda cmd: fake2
|
||
)._goal_result_from_runner("t1", fake2)
|
||
self.assertIsNone(result2["usage"])
|
||
|
||
def test_docker_goal_usage_line(self):
|
||
def fake_runner(cmd, timeout=None):
|
||
return SimpleNamespace(
|
||
returncode=0,
|
||
stdout="round 1: turn=completed verify_rc=0 verify_out=ok\n"
|
||
"goal met after rounds\n"
|
||
"usage input=100 cached=40 cache_write=0 output=50 "
|
||
"reasoning=10 total=150 completions=2\n",
|
||
stderr="")
|
||
|
||
with mock.patch("sandbox.shutil.which",
|
||
return_value="/usr/bin/docker"):
|
||
executor = DockerExecutor(
|
||
"/fake/host.py", runner=fake_runner,
|
||
env={"XCM_API_KEY": "placeholder-not-a-real-key"})
|
||
result = executor.goal_task(
|
||
{"id": "t1", "prompt": "do it",
|
||
"verify_command": "test -f x"})
|
||
self.assertEqual(result["usage"]["total_tokens"], 150)
|
||
self.assertEqual(result["usage"]["cached_input_tokens"], 40)
|
||
|
||
|
||
if __name__ == "__main__":
|
||
unittest.main()
|