jinzd-ai-cli 0.4.213 → 0.4.215

package/README.md

@@ -166,7 +166,7 @@ AI autonomously invokes these 27 tools during conversations:
 | `google_search` | safe | Google Custom Search API |
 | `run_interactive` | safe | Run interactive programs with stdin input |
 | `run_tests` | safe | Auto-detect and run project tests (JUnit XML parsing) |
-| `spawn_agent` | safe | Delegate subtasks to isolated child agents |
+| `spawn_agent` | safe | Delegate subtasks to named isolated agents (`agent`: explorer/worker/reviewer/security/tester) |
 | `ask_user` | safe | Pause and ask the user a question |
 | `save_memory` | safe | Persist important info across sessions |
 | `write_todos` | safe | Task breakdown with live progress rendering |
@@ -371,8 +371,11 @@ Built-in profiles:
 Auto Mode may auto-approve low-risk actions such as explicit writes inside the workspace/temp roots, read-only HTTP tools, plain non-force `git push`, and dependency installs already declared in `package.json` or a lockfile. It denies high-risk shapes such as `curl | bash`, force push, and likely secret exfiltration. Production deploys, database migrations, IaC destroy, credential/permission changes, and third-party agent loops fall back to confirmation.
 
 Auto Mode is not enabled by project config. Use `/permissions recently-denied` to inspect actions it blocked, or `/permissions clear-denied` to clear that session list.
-### Network Policy
+### Agent Team
+
+`spawn_agent` can now use named roles from built-ins or JSON configs in `~/.aicli/agents/` and `.aicli/agents/`. Built-ins are `explorer`, `worker`, `reviewer`, `security`, and `tester`. Agent configs may set description, provider/model, system instructions, allowed/blocked tools, permission profile, max tool rounds, and context policy; they can only narrow the inherited sub-agent safety boundary. Use `/agent list|switch|stop|summary` to inspect roles and recent sub-agent runs.
 
+### Network Policy
 `networkPolicy` is disabled by default for backward compatibility. When enabled, it governs network-facing tools before execution: `web_fetch`, `web_search`, `google_search`, MCP tools, and shell commands that look like network access (`curl`, `wget`, `git clone/fetch/pull/push`, package installs, SSH/SCP, etc.).
 
 ```json

package/README.zh-CN.md

@@ -158,7 +158,7 @@ AI 在对话中可自主调用 28 个工具：
 | `google_search` | 安全 | Google 自定义搜索 |
 | `run_interactive` | 安全 | 运行交互式程序并输入 |
 | `run_tests` | 安全 | 自动检测并运行测试（JUnit XML 解析） |
-| `spawn_agent` | 安全 | 委派子任务给隔离子代理 |
+| `spawn_agent` | 安全 | 委派子任务给命名隔离 agent（`agent`: explorer/worker/reviewer/security/tester） |
 | `ask_user` | 安全 | 暂停并向用户提问 |
 | `save_memory` | 安全 | 跨会话持久化重要信息 |
 | `write_todos` | 安全 | 任务拆解，终端实时渲染进度 |
@@ -377,8 +377,11 @@ HTTPS_PROXY=http://127.0.0.1:10809 aicli
 Auto Mode 可自动通过低风险动作，例如 workspace/temp 根目录内的显式写入、只读 HTTP 工具、非 force 的普通 `git push`、已经写在 `package.json` 或 lockfile 中的依赖安装。它会拒绝 `curl | bash`、force push、疑似 secret 外传；生产部署、数据库迁移、IaC destroy、IAM/token/key/权限变更、第三方 agent loop 默认进入确认。
 
 Auto Mode 不会被项目配置静默开启。用 `/permissions recently-denied` 查看最近被 Auto Mode 拒绝的动作，用 `/permissions clear-denied` 清空本会话列表。
-### 可信 Hooks 生命周期
+### Agent Team
+
+`spawn_agent` 现在支持命名角色，来源包括内置角色以及 `~/.aicli/agents/`、`.aicli/agents/` 下的 JSON 配置。内置角色包括 `explorer`、`worker`、`reviewer`、`security`、`tester`。agent 配置可声明 description、provider/model、system instructions、allowed/blocked tools、permission profile、max tool rounds、context policy；这些配置只能在继承的子代理安全边界内继续收窄，不能越权放宽。使用 `/agent list|switch|stop|summary` 查看角色和最近子代理运行记录。
 
+### 可信 Hooks 生命周期
 旧版 `preToolExecution` / `postToolExecution` 仍然兼容。新版生命周期 hooks 配置在 `hooks.events.<EventName>` 下，通过 `AICLI_HOOK_EVENT_JSON` 接收 JSON 事件；命令 stdout 如果输出 JSON，ai-cli 会读取 `allow`、`deny`、`ask`、`warning` 或 `warnings` 等决策。
 
 ```json

package/dist/{batch-PKY63TME.js → batch-74H5SA7P.js}

@@ -1,9 +1,9 @@
 #!/usr/bin/env node
 import {
   ConfigManager
-} from "./chunk-MRGWPCFQ.js";
+} from "./chunk-2224JGA6.js";
 import "./chunk-TZQHYZKT.js";
-import "./chunk-IWLVH32D.js";
+import "./chunk-7JES2NWR.js";
 import {
   atomicWriteFileSync
 } from "./chunk-IW3Q7AE5.js";

package/dist/{chunk-MRGWPCFQ.js → chunk-2224JGA6.js}

@@ -8,7 +8,7 @@ import {
   CONFIG_FILE_NAME,
   HISTORY_DIR_NAME,
   PLUGINS_DIR_NAME
-} from "./chunk-IWLVH32D.js";
+} from "./chunk-7JES2NWR.js";
 import {
   atomicWriteFileSync
 } from "./chunk-IW3Q7AE5.js";

package/dist/{chunk-UDMU4FUF.js → chunk-3TSHNZKI.js}

@@ -1,7 +1,7 @@
 #!/usr/bin/env node
 import {
   TEST_TIMEOUT
-} from "./chunk-IWLVH32D.js";
+} from "./chunk-7JES2NWR.js";
 
 // src/tools/builtin/run-tests.ts
 import { execSync, spawnSync } from "child_process";