autoclaw 1.2.0 → 1.3.0

package/README.md

@@ -111,6 +111,16 @@ autoclaw "Deploy and report" -y -n --json
 ```
 Token usage is collected only when `AUTOCLOW_INCLUDE_USAGE=1` (or `true`) is set — it is opt-in because not every OpenAI-compatible provider accepts `stream_options.include_usage`.
 
+### Batch Mode (Swarm Worker)
+Feed a JSONL manifest of tasks; each task runs in a fresh, isolated agent (one task's context never leaks into another) and per-task results are written as JSONL:
+```bash
+autoclaw batch tasks.jsonl -y                          # results -> tasks.results.jsonl
+autoclaw batch tasks.jsonl -o out.jsonl --fail-fast
+```
+Manifest lines are `{"id": "...", "task": "..."}` — `id` is optional (defaults to `task-N`); blank lines and `#` comments are skipped. Optional per-task overrides: `maxSteps`, `model`, `provider`.
+
+One failing task does not stop the batch (use `--fail-fast` for that). The process exits `0` when every task completed, `1` otherwise, so cron and K8s Jobs can detect bad batches. Task output stays human-readable on stdout — the results file is the machine-readable contract, with `status`, `steps`, `message`, `error` and `usage` per task.
+
 ### Auto-Confirm (CI/CD)
 Automatically approve all tool executions (dangerous, use with caution or in sandboxes).
 ```bash

package/README.zh-CN.md

@@ -112,6 +112,16 @@ autoclaw "执行部署并汇报" -y -n --json
 ```
 Token 用量仅在设置 `AUTOCLOW_INCLUDE_USAGE=1`（或 `true`）时才收集——这是可选项，因为并非所有 OpenAI 兼容端点都接受 `stream_options.include_usage`。
 
+### 批处理模式 (蜂群工人)
+把 JSONL 任务清单交给 AutoClaw；每个任务在全新的隔离 Agent 中执行（任务之间上下文互不污染），结果逐行写入 JSONL 文件：
+```bash
+autoclaw batch tasks.jsonl -y                          # 结果 -> tasks.results.jsonl
+autoclaw batch tasks.jsonl -o out.jsonl --fail-fast
+```
+清单每行为 `{"id": "...", "task": "..."}`——`id` 可省略（默认 `task-N`）；空行和 `#` 注释行会跳过。可选的每任务覆盖项：`maxSteps`、`model`、`provider`。
+
+单个任务失败不会中断批次（需要中断用 `--fail-fast`）。全部完成时进程退出 `0`，否则 `1`，cron 和 K8s Job 由此感知批次成败。任务输出保持人类可读——结果文件才是机器可读契约，含每个任务的 `status`、`steps`、`message`、`error`、`usage`。
+
 ### 自动确认 (CI/CD)
 自动批准所有工具执行（危险操作，请谨慎使用或在沙箱环境下运行）。
 ```bash

package/dist/agent.js

@@ -9,6 +9,14 @@ import { getToolDefinitions, executeToolHandler } from './tools/index.js';
 import { withRetry } from './retry.js';
 import { truncateOutput } from './truncate.js';
 const DEFAULT_MAX_STEPS = 25;
+// The shell behind child_process.exec differs by platform; telling the model
+// up front avoids trial-and-error turns (cmd.exe rejects ; and $()).
+export function buildShellInfo(platform = os.platform()) {
+    if (platform === 'win32') {
+        return 'cmd.exe (Windows). Chain commands with && only, there is no $() command substitution, mkdir has no -p flag, and native tool output may be GBK-garbled. For system queries prefer: powershell -Command "..."';
+    }
+    return 'POSIX shell (sh). Standard Unix tools apply.';
+}
 export class Agent {
     client;
     messages;
@@ -25,6 +33,7 @@ export class Agent {
         const systemInfo = `
 System Information:
 - OS: ${os.type()} ${os.release()} (${os.platform()})
+- Shell: ${buildShellInfo()}
 - Architecture: ${os.arch()}
 - Node.js Version: ${process.version}
 - Current Working Directory: ${process.cwd()}
@@ -32,6 +41,9 @@ System Information:
 - Home Directory: ${os.homedir()}
 - Current Date: ${new Date().toLocaleString()}
 `;
+        const windowsShellRule = os.platform() === 'win32'
+            ? `\n8. Mind the shell noted above: on Windows it is cmd.exe, not bash — && only, no \$(...) substitution, no mkdir -p, GBK output possible; prefer powershell -Command "..." for system queries.`
+            : '';
         this.messages = [
             {
                 role: "system",
@@ -56,7 +68,7 @@ RULES OF ENGAGEMENT:
 4. Container-friendly: stick to standard Unix tools available in Alpine/Debian slim images. No GUI apps, no browser-based debug tools.
 5. For creative or complex tasks (image prompts, long-form writing, intricate scripts): call optimize_prompt first. It significantly raises output quality.
 6. If a command fails, diagnose and try one alternative. Don't retry the same thing, don't give up on first error.
-7. Read before write. When modifying a file, read it first. When installing a package, check if it's already there.
+7. Read before write. When modifying a file, read it first. When installing a package, check if it's already there.${windowsShellRule}
 `
             }
         ];

package/dist/batch.js

@@ -0,0 +1,64 @@
+// Blank lines and lines starting with '#' are skipped. Malformed lines are
+// kept as errored entries (in manifest order) rather than dropped, so the
+// result file accounts for every task the user submitted.
+export function parseManifest(raw) {
+    return raw
+        .split('\n')
+        .map((line, idx) => {
+        const lineNo = idx + 1;
+        const trimmed = line.trim();
+        if (!trimmed || trimmed.startsWith('#'))
+            return null;
+        let parsed = null;
+        try {
+            parsed = JSON.parse(trimmed);
+        }
+        catch {
+            // fall through to the error entry below
+        }
+        const id = parsed && typeof parsed === 'object' && typeof parsed.id === 'string' && parsed.id.trim()
+            ? parsed.id.trim()
+            : `task-${lineNo}`;
+        if (!parsed || typeof parsed !== 'object' || typeof parsed.task !== 'string' || !parsed.task.trim()) {
+            return { lineNo, id, task: '', error: 'not valid JSON or missing "task" field' };
+        }
+        const entry = { lineNo, id, task: parsed.task.trim() };
+        if (typeof parsed.maxSteps === 'number' && parsed.maxSteps > 0)
+            entry.maxSteps = parsed.maxSteps;
+        if (typeof parsed.model === 'string' && parsed.model.trim())
+            entry.model = parsed.model.trim();
+        if (typeof parsed.provider === 'string' && parsed.provider.trim())
+            entry.provider = parsed.provider.trim();
+        return entry;
+    })
+        .filter((entry) => entry !== null);
+}
+export async function runBatch(entries, execute, options = {}) {
+    const total = entries.length;
+    const results = [];
+    let completed = 0;
+    let failed = 0;
+    for (const entry of entries) {
+        let result;
+        if (entry.error) {
+            result = { id: entry.id, status: 'error', error: `Manifest line ${entry.lineNo}: ${entry.error}`, durationMs: 0 };
+        }
+        else {
+            try {
+                result = await execute(entry);
+            }
+            catch (err) {
+                result = { id: entry.id, status: 'error', error: err?.message ?? String(err), durationMs: 0 };
+            }
+        }
+        if (result.status === 'completed')
+            completed++;
+        else
+            failed++;
+        results.push(result);
+        options.onResult?.(entry, result, results.length, total);
+        if (options.failFast && result.status !== 'completed')
+            break;
+    }
+    return { results, completed, failed };
+}

package/dist/index.js

@@ -4,6 +4,7 @@ import inquirer from 'inquirer';
 import chalk from 'chalk';
 import dotenv from 'dotenv';
 import { Agent } from './agent.js';
+import { parseManifest, runBatch } from './batch.js';
 import { PROVIDER_PRESETS, providerNames, resolveProvider } from './providers.js';
 import * as fs from 'fs';
 import * as path from 'path';
@@ -43,7 +44,7 @@ dotenv.config({ path: GLOBAL_ENV_FILE });
 const __dirname = path.dirname(fileURLToPath(import.meta.url));
 // In dist/index.js, package.json is usually up one level in the root
 const pkgPath = path.join(__dirname, '..', 'package.json');
-let version = '1.2.0';
+let version = '1.3.0';
 try {
     const pkg = JSON.parse(fs.readFileSync(pkgPath, 'utf-8'));
     version = pkg.version;
@@ -75,6 +76,15 @@ program
     const options = program.opts();
     await runChat(queryParts, options);
 });
+program
+    .command('batch <manifest>')
+    .description('Run tasks from a JSONL manifest, each in a fresh agent ({"id":"...","task":"..."})')
+    .option('-o, --output <file>', 'Per-task results as JSONL (default: <manifest base>.results.jsonl)')
+    .option('--fail-fast', 'Stop on the first failed task')
+    .action(async (manifest, cmdOptions) => {
+    const options = program.opts();
+    await runBatchCommand(manifest, options, cmdOptions);
+});
 program.parse(process.argv);
 async function runSetup(options = {}) {
     const isProject = options.project;
@@ -354,11 +364,9 @@ async function runSetup(options = {}) {
         console.error(chalk.red(`Failed to write config: ${error.message}`));
     }
 }
-async function runChat(queryParts, options) {
-    if (options.interactive) {
-        console.log(chalk.bold.cyan("Welcome to AutoClaw CLI 🦞"));
-    }
-    const initialQuery = queryParts.join(' ');
+// Shared by `chat` and `batch`: resolve credentials, endpoints and runtime
+// flags from CLI args > env > project config > global config > provider preset.
+async function resolveRuntime(options) {
     // 1. Load Global JSON
     const globalConfig = loadJsonConfig(GLOBAL_CONFIG_FILE);
     // 2. Load Local JSON (Project Level)
@@ -439,6 +447,74 @@ async function runChat(queryParts, options) {
         console.error(chalk.red("API Key is still missing. Exiting."));
         process.exit(1);
     }
+    return { apiKey, baseURL, model, fullConfig };
+}
+async function runBatchCommand(manifestPath, globalOptions, cmdOptions) {
+    const { apiKey, baseURL, model, fullConfig } = await resolveRuntime(globalOptions);
+    let raw;
+    try {
+        raw = fs.readFileSync(manifestPath, 'utf-8');
+    }
+    catch (err) {
+        console.error(chalk.red(`Cannot read manifest ${manifestPath}: ${err.message}`));
+        process.exit(1);
+    }
+    const entries = parseManifest(raw);
+    if (entries.length === 0) {
+        console.error(chalk.red(`Manifest ${manifestPath} contains no tasks (blank lines and '#' comments are skipped).`));
+        process.exit(1);
+    }
+    const outputPath = cmdOptions.output || manifestPath.replace(/\.[^.]+$/, '') + '.results.jsonl';
+    console.log(chalk.bold.cyan(`AutoClaw Batch 🦞  ${entries.length} task(s)`));
+    console.log(chalk.dim(`Results: ${outputPath}\n`));
+    const startedAt = Date.now();
+    const { results, completed, failed } = await runBatch(entries, async (entry) => {
+        // A fresh Agent per task keeps contexts isolated; per-task overrides
+        // beat the globally resolved defaults.
+        const taskPreset = resolveProvider(entry.provider);
+        const taskModel = entry.model || taskPreset?.defaultModel || model;
+        const taskBaseURL = taskPreset?.baseUrl || baseURL;
+        const taskConfig = {
+            ...fullConfig,
+            // The results file is the machine-readable contract in batch mode.
+            jsonMode: false,
+            maxSteps: entry.maxSteps ?? fullConfig.maxSteps
+        };
+        const agent = new Agent(apiKey, taskBaseURL, taskModel, taskConfig);
+        const start = Date.now();
+        const runResult = await agent.chat(entry.task);
+        return {
+            id: entry.id,
+            status: runResult.status,
+            steps: runResult.steps,
+            message: runResult.message ?? null,
+            ...(runResult.error ? { error: runResult.error } : {}),
+            ...(runResult.usage ? { usage: runResult.usage } : {}),
+            durationMs: Date.now() - start
+        };
+    }, {
+        failFast: !!cmdOptions.failFast,
+        onResult: (entry, result, done, total) => {
+            const color = result.status === 'completed' ? chalk.green : chalk.red;
+            console.log(color(`[${done}/${total}] ${entry.id} -> ${result.status} (${Math.round(result.durationMs / 1000)}s)`));
+        }
+    });
+    try {
+        fs.writeFileSync(outputPath, results.map(r => JSON.stringify(r)).join('\n') + '\n', 'utf-8');
+    }
+    catch (err) {
+        console.error(chalk.red(`Failed to write results to ${outputPath}: ${err.message}`));
+        process.exit(1);
+    }
+    console.log(chalk.cyan(`\nBatch done: ${completed}/${results.length} completed, ${failed} failed in ${Math.round((Date.now() - startedAt) / 1000)}s -> ${outputPath}`));
+    process.exit(failed > 0 ? 1 : 0);
+}
+async function runChat(queryParts, options) {
+    if (options.interactive) {
+        console.log(chalk.bold.cyan("Welcome to AutoClaw CLI 🦞"));
+    }
+    const initialQuery = queryParts.join(' ');
+    const { apiKey, baseURL, model, fullConfig } = await resolveRuntime(options);
     const agent = new Agent(apiKey, baseURL, model, fullConfig);
     if (options.interactive) {
         console.log(chalk.green(`Agent initialized with model: ${model}`));

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "autoclaw",
-  "version": "1.2.0",
+  "version": "1.3.0",
   "type": "module",
   "main": "dist/index.js",
   "bin": {
@@ -12,6 +12,7 @@
     "dev": "node --loader ts-node/esm src/index.ts",
     "test": "vitest run",
     "test:watch": "vitest",
+    "coverage": "vitest run --coverage",
     "prepublishOnly": "npm run build"
   },
   "files": [
@@ -65,6 +66,7 @@
     "@types/jsdom": "^27.0.0",
     "@types/node": "^25.2.1",
     "@types/nodemailer": "^7.0.9",
+    "@vitest/coverage-v8": "^4.1.11",
     "ts-node": "^10.9.2",
     "typescript": "^5.9.3",
     "vitest": "^4.1.4"