diff --git a/cloud/tests/test_fallback_retry.py b/cloud/tests/test_fallback_retry.py index b66e746..48b7eb9 100644 --- a/cloud/tests/test_fallback_retry.py +++ b/cloud/tests/test_fallback_retry.py @@ -324,6 +324,28 @@ class FallbackRetryTestCase(unittest.TestCase): self.assertEqual(len(self.calls), 1) self.assertEqual(result["events"], []) + def test_crash_without_code_error_text_keeps_stderr(self): + # stdout 为空、stderr 有真实报错时,最终 error_text 必须 + # 留住 stderr,不能被通用的 host execution failed 盖掉 + # (主机实测:缺 repo 的 1 秒失败曾因此完全无法排障)。 + def fake(cmd): + return SimpleNamespace( + returncode=1, stdout="", + stderr="Traceback (most recent call last):\n" + "RuntimeError: 缺少 --repo,也没有在 host-config.json 里配 repo") + + _insert_task(self.db_path, "A") + worker = self._worker( + runner=self._recording(fake), + model="gpt-6.1-sol", + fallback_models=["gpt-6-sol"], + max_retries=0) + result = worker.run_one() + self.assertEqual(result["status"], "failed") + row, cost, audits = _execution(self.db_path, "A") + self.assertIn("缺少 --repo", row[0]) + self.assertEqual(result["events"], []) + if __name__ == "__main__": unittest.main() diff --git a/cloud/worker.py b/cloud/worker.py index 919863e..56a00ff 100644 --- a/cloud/worker.py +++ b/cloud/worker.py @@ -905,6 +905,13 @@ class Worker: parsed = None if isinstance(parsed, dict) and parsed.get("text"): return str(parsed["text"]) + # host.py 崩溃时 stdout 常为空、真正的报错在 stderr(例如 + # “缺少 --repo”、Read-only file system);只用 stdout 时 + # 最终错误会被写成通用的 host execution failed,排障无从 + # 下手,所以 stdout 为空时取 stderr 尾部(实际报错行在尾)。 + stderr = (result or {}).get("stderr", "") or "" + if not stdout.strip() and stderr.strip(): + return stderr.strip()[-1000:] if token is not None: return "host_status=%s" % token return stdout.strip() or "host execution failed" @@ -1124,7 +1131,10 @@ class Worker: fallback_model, second_error)) else: if error is None: - error = stdout.strip() or "host execution failed" + stderr = (result or {}).get("stderr", "") or "" + error = stdout.strip() or \ + (stderr.strip()[-1000:] if stderr.strip() else "") \ + or "host execution failed" if retry_count: error = "[retries=%d] %s" % (retry_count, error) # 未配 fallback_models 时的老行为:只记事件、不重试。 diff --git a/host-config-docker.json b/host-config-docker.json index b2b7a74..99fdfb3 100644 --- a/host-config-docker.json +++ b/host-config-docker.json @@ -1 +1 @@ -{"_note":"Docker 执行器专用配置(容器内路径,绝不是宿主路径):state 必须用相对路径 work/host-state.json——相对配置文件所在目录 /app 解析,得到 /app/work/host-state.json,经额外挂载落到宿主 /opt/codex-app-server/work/host-state.json,属主是 codexsvc(uid 1003,与容器 --user 1003:1004 一致),容器可写。绝不能用默认的 /app/host-state.json(/app 是只读挂载,锁一开就报 Read-only file system),也绝不能用 /work/host-state.json(/work 挂载的宿主目录由 docker 自动创建、属主 root,容器用户写不进去,同样 1 秒内失败)。此文件曾因 deploy 清理被删过(不在仓库里),导致 Docker 派发静默全灭,所以它必须进仓库、随部署一起发。sandbox 用 danger-full-access:主机内核禁止不可信 user namespace,Docker + 内层 bwrap 双重沙箱不可行,生产隔离层就是 Docker 本身。API key 绝不放这里,只走环境变量。","approval":"deny","approval_policy":"never","effort":"low","model":"gpt-6.1-sol","sandbox":"danger-full-access","state":"work/host-state.json"} \ No newline at end of file +{"_note": "Docker 执行器专用配置(容器内路径,绝不是宿主路径):state 必须用相对路径 work/host-state.json——相对配置文件所在目录 /app 解析,得到 /app/work/host-state.json,经额外挂载落到宿主 /opt/codex-app-server/work/host-state.json,属主是 codexsvc(uid 1003,与容器 --user 1003:1004 一致),容器可写。绝不能用默认的 /app/host-state.json(/app 是只读挂载,锁一开就报 Read-only file system),也绝不能用 /work/host-state.json(/work 挂载的宿主目录由 docker 自动创建、属主 root,容器用户写不进去,同样 1 秒内失败)。此文件曾因 deploy 清理被删过(不在仓库里),导致 Docker 派发静默全灭,所以它必须进仓库、随部署一起发。sandbox 用 danger-full-access:主机内核禁止不可信 user namespace,Docker + 内层 bwrap 双重沙箱不可行,生产隔离层就是 Docker 本身。API key 绝不放这里,只走环境变量。 默认仓库是宿主测试仓库:没有 repo_url 的项目走它;有 repo_url 的项目 worker 会把解析出的检出经 --repo 传进去,覆盖它。", "approval": "deny", "approval_policy": "never", "effort": "low", "model": "gpt-6.1-sol", "sandbox": "danger-full-access", "state": "work/host-state.json", "repo": "/var/lib/codex-app-server/test-repo"} \ No newline at end of file