openclaw/src/agents/cli-runner.reliability.test.ts

import { describe, expect, it } from "vitest";
import {
  createManagedRun,
  enqueueSystemEventMock,
  requestHeartbeatNowMock,
  setupCliRunnerTestModule,
  supervisorSpawnMock,
} from "./cli-runner.test-support.js";
import { resolveCliNoOutputTimeoutMs } from "./cli-runner/helpers.js";

describe("runCliAgent reliability", () => {
  it("fails with timeout when no-output watchdog trips", async () => {
    const runCliAgent = await setupCliRunnerTestModule();
    supervisorSpawnMock.mockResolvedValueOnce(
      createManagedRun({
        reason: "no-output-timeout",
        exitCode: null,
        exitSignal: "SIGKILL",
        durationMs: 200,
        stdout: "",
        stderr: "",
        timedOut: true,
        noOutputTimedOut: true,
      }),
    );

    await expect(
      runCliAgent({
        sessionId: "s1",
        sessionFile: "/tmp/session.jsonl",
        workspaceDir: "/tmp",
        prompt: "hi",
        provider: "codex-cli",
        model: "gpt-5.2-codex",
        timeoutMs: 1_000,
        runId: "run-2",
        cliSessionId: "thread-123",
      }),
    ).rejects.toThrow("produced no output");
  });

  it("enqueues a system event and heartbeat wake on no-output watchdog timeout for session runs", async () => {
    const runCliAgent = await setupCliRunnerTestModule();
    supervisorSpawnMock.mockResolvedValueOnce(
      createManagedRun({
        reason: "no-output-timeout",
        exitCode: null,
        exitSignal: "SIGKILL",
        durationMs: 200,
        stdout: "",
        stderr: "",
        timedOut: true,
        noOutputTimedOut: true,
      }),
    );

    await expect(
      runCliAgent({
        sessionId: "s1",
        sessionKey: "agent:main:main",
        sessionFile: "/tmp/session.jsonl",
        workspaceDir: "/tmp",
        prompt: "hi",
        provider: "codex-cli",
        model: "gpt-5.2-codex",
        timeoutMs: 1_000,
        runId: "run-2b",
        cliSessionId: "thread-123",
      }),
    ).rejects.toThrow("produced no output");

    expect(enqueueSystemEventMock).toHaveBeenCalledTimes(1);
    const [notice, opts] = enqueueSystemEventMock.mock.calls[0] ?? [];
    expect(String(notice)).toContain("produced no output");
    expect(String(notice)).toContain("interactive input or an approval prompt");
    expect(opts).toMatchObject({ sessionKey: "agent:main:main" });
    expect(requestHeartbeatNowMock).toHaveBeenCalledWith({
      reason: "cli:watchdog:stall",
      sessionKey: "agent:main:main",
    });
  });

  it("fails with timeout when overall timeout trips", async () => {
    const runCliAgent = await setupCliRunnerTestModule();
    supervisorSpawnMock.mockResolvedValueOnce(
      createManagedRun({
        reason: "overall-timeout",
        exitCode: null,
        exitSignal: "SIGKILL",
        durationMs: 200,
        stdout: "",
        stderr: "",
        timedOut: true,
        noOutputTimedOut: false,
      }),
    );

    await expect(
      runCliAgent({
        sessionId: "s1",
        sessionFile: "/tmp/session.jsonl",
        workspaceDir: "/tmp",
        prompt: "hi",
        provider: "codex-cli",
        model: "gpt-5.2-codex",
        timeoutMs: 1_000,
        runId: "run-3",
        cliSessionId: "thread-123",
      }),
    ).rejects.toThrow("exceeded timeout");
  });

  it("rethrows the retry failure when session-expired recovery retry also fails", async () => {
    const runCliAgent = await setupCliRunnerTestModule();
    supervisorSpawnMock.mockResolvedValueOnce(
      createManagedRun({
        reason: "exit",
        exitCode: 1,
        exitSignal: null,
        durationMs: 150,
        stdout: "",
        stderr: "session expired",
        timedOut: false,
        noOutputTimedOut: false,
      }),
    );
    supervisorSpawnMock.mockResolvedValueOnce(
      createManagedRun({
        reason: "exit",
        exitCode: 1,
        exitSignal: null,
        durationMs: 150,
        stdout: "",
        stderr: "rate limit exceeded",
        timedOut: false,
        noOutputTimedOut: false,
      }),
    );

    await expect(
      runCliAgent({
        sessionId: "s1",
        sessionKey: "agent:main:subagent:retry",
        sessionFile: "/tmp/session.jsonl",
        workspaceDir: "/tmp",
        prompt: "hi",
        provider: "codex-cli",
        model: "gpt-5.2-codex",
        timeoutMs: 1_000,
        runId: "run-retry-failure",
        cliSessionId: "thread-123",
      }),
    ).rejects.toThrow("rate limit exceeded");

    expect(supervisorSpawnMock).toHaveBeenCalledTimes(2);
  });
});

describe("resolveCliNoOutputTimeoutMs", () => {
  it("uses backend-configured resume watchdog override", () => {
    const timeoutMs = resolveCliNoOutputTimeoutMs({
      backend: {
        command: "codex",
        reliability: {
          watchdog: {
            resume: {
              noOutputTimeoutMs: 42_000,
            },
          },
        },
      },
      timeoutMs: 120_000,
      useResume: true,
    });
    expect(timeoutMs).toBe(42_000);
  });
});