Files
openclaw/src/agents/cli-backends.test.ts
felear2022 623f4d3056 fix: use stream-json output for Claude CLI backend to prevent watchdog timeouts
The Claude CLI backend uses `--output-format json`, which produces no
stdout until the entire request completes. When session context is large
(100K+ tokens) or API response is slow, the no-output watchdog timer
(max 180s for resume sessions) kills the process before it finishes,
resulting in "CLI produced no output for 180s and was terminated" errors.

Switch to `--output-format stream-json --verbose` so Claude CLI emits
NDJSON events throughout processing (init, assistant, rate_limit, result).
Each event resets the watchdog timer, which is the intended behavior —
the watchdog detects truly stuck processes, not slow-but-progressing ones.

Changes:
- cli-backends.ts: `json` → `stream-json --verbose`, `output: "jsonl"`
- helpers.ts: teach parseCliJsonl to extract text from Claude's
  `{"type":"result","result":"..."}` NDJSON line

Note: `--verbose` is required for stream-json in `-p` (print) mode.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-26 16:39:15 -07:00

222 lines
7.7 KiB
TypeScript

import { beforeEach, describe, expect, it } from "vitest";
import { buildAnthropicCliBackend } from "../../extensions/anthropic/cli-backend.js";
import { buildGoogleGeminiCliBackend } from "../../extensions/google/cli-backend.js";
import { buildOpenAICodexCliBackend } from "../../extensions/openai/cli-backend.js";
import type { OpenClawConfig } from "../config/config.js";
import { createEmptyPluginRegistry } from "../plugins/registry.js";
import { setActivePluginRegistry } from "../plugins/runtime.js";
import { resolveCliBackendConfig } from "./cli-backends.js";
beforeEach(() => {
const registry = createEmptyPluginRegistry();
registry.cliBackends = [
{
pluginId: "anthropic",
backend: buildAnthropicCliBackend(),
source: "test",
},
{
pluginId: "openai",
backend: buildOpenAICodexCliBackend(),
source: "test",
},
{
pluginId: "google",
backend: buildGoogleGeminiCliBackend(),
source: "test",
},
];
setActivePluginRegistry(registry);
});
describe("resolveCliBackendConfig reliability merge", () => {
it("defaults codex-cli to workspace-write for fresh and resume runs", () => {
const resolved = resolveCliBackendConfig("codex-cli");
expect(resolved).not.toBeNull();
expect(resolved?.config.args).toEqual([
"exec",
"--json",
"--color",
"never",
"--sandbox",
"workspace-write",
"--skip-git-repo-check",
]);
expect(resolved?.config.resumeArgs).toEqual([
"exec",
"resume",
"{sessionId}",
"--color",
"never",
"--sandbox",
"workspace-write",
"--skip-git-repo-check",
]);
});
it("deep-merges reliability watchdog overrides for codex", () => {
const cfg = {
agents: {
defaults: {
cliBackends: {
"codex-cli": {
command: "codex",
reliability: {
watchdog: {
resume: {
noOutputTimeoutMs: 42_000,
},
},
},
},
},
},
},
} satisfies OpenClawConfig;
const resolved = resolveCliBackendConfig("codex-cli", cfg);
expect(resolved).not.toBeNull();
expect(resolved?.config.reliability?.watchdog?.resume?.noOutputTimeoutMs).toBe(42_000);
// Ensure defaults are retained when only one field is overridden.
expect(resolved?.config.reliability?.watchdog?.resume?.noOutputTimeoutRatio).toBe(0.3);
expect(resolved?.config.reliability?.watchdog?.resume?.minMs).toBe(60_000);
expect(resolved?.config.reliability?.watchdog?.resume?.maxMs).toBe(180_000);
expect(resolved?.config.reliability?.watchdog?.fresh?.noOutputTimeoutRatio).toBe(0.8);
});
});
describe("resolveCliBackendConfig claude-cli defaults", () => {
it("uses non-interactive permission-mode defaults for fresh and resume args", () => {
const resolved = resolveCliBackendConfig("claude-cli");
expect(resolved).not.toBeNull();
expect(resolved?.config.output).toBe("jsonl");
expect(resolved?.config.args).toContain("stream-json");
expect(resolved?.config.args).toContain("--verbose");
expect(resolved?.config.args).toContain("--permission-mode");
expect(resolved?.config.args).toContain("bypassPermissions");
expect(resolved?.config.args).not.toContain("--dangerously-skip-permissions");
expect(resolved?.config.resumeArgs).toContain("stream-json");
expect(resolved?.config.resumeArgs).toContain("--verbose");
expect(resolved?.config.resumeArgs).toContain("--permission-mode");
expect(resolved?.config.resumeArgs).toContain("bypassPermissions");
expect(resolved?.config.resumeArgs).not.toContain("--dangerously-skip-permissions");
});
it("retains default claude safety args when only command is overridden", () => {
const cfg = {
agents: {
defaults: {
cliBackends: {
"claude-cli": {
command: "/usr/local/bin/claude",
},
},
},
},
} satisfies OpenClawConfig;
const resolved = resolveCliBackendConfig("claude-cli", cfg);
expect(resolved).not.toBeNull();
expect(resolved?.config.command).toBe("/usr/local/bin/claude");
expect(resolved?.config.args).toContain("--permission-mode");
expect(resolved?.config.args).toContain("bypassPermissions");
expect(resolved?.config.resumeArgs).toContain("--permission-mode");
expect(resolved?.config.resumeArgs).toContain("bypassPermissions");
});
it("normalizes legacy skip-permissions overrides to permission-mode bypassPermissions", () => {
const cfg = {
agents: {
defaults: {
cliBackends: {
"claude-cli": {
command: "claude",
args: ["-p", "--dangerously-skip-permissions", "--output-format", "json"],
resumeArgs: [
"-p",
"--dangerously-skip-permissions",
"--output-format",
"json",
"--resume",
"{sessionId}",
],
},
},
},
},
} satisfies OpenClawConfig;
const resolved = resolveCliBackendConfig("claude-cli", cfg);
expect(resolved).not.toBeNull();
expect(resolved?.config.args).not.toContain("--dangerously-skip-permissions");
expect(resolved?.config.args).toContain("--permission-mode");
expect(resolved?.config.args).toContain("bypassPermissions");
expect(resolved?.config.resumeArgs).not.toContain("--dangerously-skip-permissions");
expect(resolved?.config.resumeArgs).toContain("--permission-mode");
expect(resolved?.config.resumeArgs).toContain("bypassPermissions");
});
it("keeps explicit permission-mode overrides while removing legacy skip flag", () => {
const cfg = {
agents: {
defaults: {
cliBackends: {
"claude-cli": {
command: "claude",
args: ["-p", "--dangerously-skip-permissions", "--permission-mode", "acceptEdits"],
resumeArgs: [
"-p",
"--dangerously-skip-permissions",
"--permission-mode=acceptEdits",
"--resume",
"{sessionId}",
],
},
},
},
},
} satisfies OpenClawConfig;
const resolved = resolveCliBackendConfig("claude-cli", cfg);
expect(resolved).not.toBeNull();
expect(resolved?.config.args).not.toContain("--dangerously-skip-permissions");
expect(resolved?.config.args).toEqual(["-p", "--permission-mode", "acceptEdits"]);
expect(resolved?.config.resumeArgs).not.toContain("--dangerously-skip-permissions");
expect(resolved?.config.resumeArgs).toEqual([
"-p",
"--permission-mode=acceptEdits",
"--resume",
"{sessionId}",
]);
expect(resolved?.config.args).not.toContain("bypassPermissions");
expect(resolved?.config.resumeArgs).not.toContain("bypassPermissions");
});
});
describe("resolveCliBackendConfig google-gemini-cli defaults", () => {
it("uses Gemini CLI json args and existing-session resume mode", () => {
const resolved = resolveCliBackendConfig("google-gemini-cli");
expect(resolved).not.toBeNull();
expect(resolved?.bundleMcp).toBe(false);
expect(resolved?.config.args).toEqual(["--prompt", "--output-format", "json"]);
expect(resolved?.config.resumeArgs).toEqual([
"--resume",
"{sessionId}",
"--prompt",
"--output-format",
"json",
]);
expect(resolved?.config.modelArg).toBe("--model");
expect(resolved?.config.sessionMode).toBe("existing");
expect(resolved?.config.sessionIdFields).toEqual(["session_id", "sessionId"]);
expect(resolved?.config.modelAliases?.pro).toBe("gemini-3.1-pro-preview");
});
});