jinzd-ai-cli 0.4.38 → 0.4.40

package/README.md

@@ -7,11 +7,11 @@
 [![npm version](https://img.shields.io/npm/v/jinzd-ai-cli)](https://www.npmjs.com/package/jinzd-ai-cli)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![Node.js](https://img.shields.io/badge/node-%3E%3D20-brightgreen)](https://nodejs.org)
-[![Tests](https://img.shields.io/badge/tests-282%20passing-brightgreen)]()
+[![Tests](https://img.shields.io/badge/tests-343%20passing-brightgreen)]()
 [![GitHub Release](https://img.shields.io/github/v/release/jinzhengdong/ai-cli)](https://github.com/jinzhengdong/ai-cli/releases)
 [![CI](https://github.com/jinzhengdong/ai-cli/actions/workflows/ci.yml/badge.svg)](https://github.com/jinzhengdong/ai-cli/actions/workflows/ci.yml)
 
-**ai-cli** is a powerful AI assistant that connects to 7 providers and executes tasks autonomously through agentic tool calling. Use it as a terminal REPL, a browser-based Web UI, or a standalone Electron desktop app.
+**ai-cli** is a powerful AI assistant that connects to 8 providers (including local Ollama models) and executes tasks autonomously through agentic tool calling. Use it as a terminal REPL, a browser-based Web UI, or a standalone Electron desktop app.
 
 <p align="center">
   <img src="https://img.shields.io/badge/CLI-Terminal-blue" alt="CLI" />
@@ -21,7 +21,7 @@
 
 ## Highlights
 
-- **7 Built-in Providers** — Claude, Gemini, DeepSeek, OpenAI, Zhipu GLM, Kimi, OpenRouter (300+ models)
+- **8 Built-in Providers** — Claude, Gemini, DeepSeek, OpenAI, Zhipu GLM, Kimi, OpenRouter (300+ models), **Ollama** (local models, no API key needed)
 - **3 Interfaces** — Terminal CLI, browser Web UI (`aicli web`), Electron desktop app
 - **Agentic Tool Calling** — AI autonomously runs shell commands, reads/writes files, searches code, fetches web, runs tests (up to 25 rounds)
 - **Streaming Tool Use** — Real-time streaming of AI reasoning and tool calls as they happen
@@ -116,9 +116,28 @@ aicli user delete x          # Delete user
 | **OpenRouter** | 300+ models (Claude, GPT, Gemini, Llama, Qwen, Mistral...) | [openrouter.ai](https://openrouter.ai) |
 | **Zhipu** | GLM-4, GLM-5 | [open.bigmodel.cn](https://open.bigmodel.cn) |
 | **Kimi** | Moonshot, Kimi-K2 | [platform.moonshot.cn](https://platform.moonshot.cn) |
+| **Ollama** | Any locally installed model (Llama, Qwen, Gemma, Mistral...) | No API key — [ollama.com](https://ollama.com) |
 
 Any OpenAI-compatible API can also be used via `customBaseUrls` in config.
 
+### Ollama (Local Models)
+
+Run AI models entirely on your own hardware — no API key, no usage fees, no data leaving your machine.
+
+```bash
+# Install Ollama from https://ollama.com, then pull a model:
+ollama pull qwen3:4b      # recommended: good tool-calling support
+ollama pull gemma3:4b
+ollama pull llama3.1:8b
+
+# Start aicli and switch to Ollama:
+aicli
+[deepseek] > /provider ollama   # auto-discovers installed models
+[ollama] > /model               # select from your local models
+```
+
+> **Note**: Use models 4B+ for best results with tool calling. Small models (<4B) may struggle with the tool definitions injected by MCP servers.
+
 ## Built-in Tools (Agentic)
 
 AI autonomously invokes these 19 tools during conversations:
@@ -354,11 +373,11 @@ The Web UI (`aicli web`) provides a full-featured browser interface:
 ## Testing
 
 ```bash
-npm test              # Run all 282 tests
+npm test              # Run all 343 tests
 npm run test:watch    # Watch mode
 ```
 
-18 test suites covering: authentication, sessions, tool types & danger levels, permissions, output truncation, diff rendering, edit-file similarity, error hierarchy, config management, env loading, provider registry, web-fetch, grep-files, hub renderer, hub discussion, hub presets, dev-state.
+21 test suites covering: authentication, sessions, tool types & danger levels, permissions, output truncation, diff rendering, edit-file similarity, error hierarchy, config management, env loading, provider registry, web-fetch, grep-files, hub renderer, hub discussion, hub presets, dev-state.
 
 ## Documentation
 

package/README.zh-CN.md

@@ -2,18 +2,18 @@
 
 # ai-cli
 
-> 跨平台 AI 编程助手 — CLI 终端、Web 界面、桌面应用三合一，支持 7 大 Provider 与 Agentic 工具调用
+> 跨平台 AI 编程助手 — CLI 终端、Web 界面、桌面应用三合一，支持 8 大 Provider（含本地 Ollama）与 Agentic 工具调用
 
 [![npm version](https://img.shields.io/npm/v/jinzd-ai-cli)](https://www.npmjs.com/package/jinzd-ai-cli)
 [![License: MIT](https://img.shields.io/badge/License-MIT-yellow.svg)](LICENSE)
 [![Node.js](https://img.shields.io/badge/node-%3E%3D20-brightgreen)](https://nodejs.org)
-[![Tests](https://img.shields.io/badge/tests-282%20passing-brightgreen)]()
+[![Tests](https://img.shields.io/badge/tests-343%20passing-brightgreen)]()
 [![GitHub Release](https://img.shields.io/github/v/release/jinzhengdong/ai-cli)](https://github.com/jinzhengdong/ai-cli/releases)
 [![CI](https://github.com/jinzhengdong/ai-cli/actions/workflows/ci.yml/badge.svg)](https://github.com/jinzhengdong/ai-cli/actions/workflows/ci.yml)
 
 ## 特性亮点
 
-- **7 大内置 Provider** — Claude、Gemini、DeepSeek、OpenAI、智谱 GLM、Kimi、OpenRouter（300+ 模型）
+- **8 大内置 Provider** — Claude、Gemini、DeepSeek、OpenAI、智谱 GLM、Kimi、OpenRouter（300+ 模型）、**Ollama**（本地模型，无需 API Key）
 - **三种使用方式** — 终端 CLI、浏览器 Web UI（`aicli web`）、Electron 桌面应用
 - **Agentic 工具调用** — AI 自主执行 bash 命令、读写文件、搜索代码、抓取网页、运行测试（每轮最多 25 次）
 - **流式工具调用** — 实时流式展示 AI 推理过程和工具调用
@@ -108,9 +108,28 @@ aicli user delete x          # 删除用户
 | **OpenRouter** | 300+ 模型（Claude/GPT/Gemini/Llama/Qwen/Mistral...） | [openrouter.ai](https://openrouter.ai) |
 | **智谱清言** | GLM-4, GLM-5 | [open.bigmodel.cn](https://open.bigmodel.cn) |
 | **Kimi** | Moonshot, Kimi-K2 | [platform.moonshot.cn](https://platform.moonshot.cn) |
+| **Ollama** | 任意本地模型（Llama、Qwen、Gemma、Mistral...） | 无需 API Key — [ollama.com](https://ollama.com) |
 
 也可通过 `customBaseUrls` 配置接入任意 OpenAI 兼容 API。
 
+### Ollama（本地模型）
+
+在自己的硬件上完全本地运行 AI，无需 API Key，无使用费，数据不离开本机。
+
+```bash
+# 从 https://ollama.com 安装 Ollama，然后拉取模型：
+ollama pull qwen3:4b      # 推荐：工具调用支持好
+ollama pull gemma3:4b
+ollama pull llama3.1:8b
+
+# 启动 aicli，切换到 Ollama：
+aicli
+[deepseek] > /provider ollama   # 自动发现已安装的模型
+[ollama] > /model               # 从本地模型中选择
+```
+
+> **注意**：建议使用 4B 及以上的模型以获得较好的工具调用支持。小模型（<4B）在 MCP 服务器注入大量工具定义时可能无法正常工作。
+
 ## 内置工具（Agentic 能力）
 
 AI 在对话中可自主调用 19 个工具：
@@ -367,11 +386,11 @@ Web UI（`aicli web`）提供功能完备的浏览器界面：
 ## 测试
 
 ```bash
-npm test              # 运行全部 282 个测试
+npm test              # 运行全部 343 个测试
 npm run test:watch    # 监听模式
 ```
 
-18 个测试套件覆盖：认证、会话、工具类型与危险级别、权限、输出截断、diff 渲染、edit-file 相似度、错误层级、配置管理、环境变量、Provider 注册、web-fetch、grep-files、Hub 渲染、Hub 讨论、Hub 预设、开发状态。
+21 个测试套件覆盖：认证、会话、工具类型与危险级别、权限、输出截断、diff 渲染、edit-file 相似度、错误层级、配置管理、环境变量、Provider 注册、web-fetch、grep-files、Hub 渲染、Hub 讨论、Hub 预设、开发状态。
 
 ## 文档
 

package/dist/{chunk-TNRYHTGD.js → chunk-CYBC7PWO.js}

@@ -6,7 +6,7 @@ import { platform } from "os";
 import chalk from "chalk";
 
 // src/core/constants.ts
-var VERSION = "0.4.38";
+var VERSION = "0.4.40";
 var APP_NAME = "ai-cli";
 var CONFIG_DIR_NAME = ".aicli";
 var CONFIG_FILE_NAME = "config.json";

package/dist/{chunk-OZER6O2H.js → chunk-KPHYJOJT.js}

@@ -9,7 +9,7 @@ import {
   SUBAGENT_DEFAULT_MAX_ROUNDS,
   SUBAGENT_MAX_ROUNDS_LIMIT,
   runTestsTool
-} from "./chunk-XPQEGIFO.js";
+} from "./chunk-RVJMWZEJ.js";
 
 // src/tools/builtin/bash.ts
 import { execSync } from "child_process";

package/dist/{chunk-XPQEGIFO.js → chunk-RVJMWZEJ.js}

@@ -8,7 +8,7 @@ import { platform } from "os";
 import chalk from "chalk";
 
 // src/core/constants.ts
-var VERSION = "0.4.38";
+var VERSION = "0.4.40";
 var APP_NAME = "ai-cli";
 var CONFIG_DIR_NAME = ".aicli";
 var CONFIG_FILE_NAME = "config.json";

package/dist/{chunk-3UUFCRRL.js → chunk-Y4B6HE6J.js}

@@ -7,7 +7,7 @@ import {
   ProviderNotFoundError,
   RateLimitError,
   schemaToJsonSchema
-} from "./chunk-OZER6O2H.js";
+} from "./chunk-KPHYJOJT.js";
 import {
   APP_NAME,
   CONFIG_DIR_NAME,
@@ -20,7 +20,7 @@ import {
   MCP_TOOL_PREFIX,
   PLUGINS_DIR_NAME,
   VERSION
-} from "./chunk-XPQEGIFO.js";
+} from "./chunk-RVJMWZEJ.js";
 
 // src/config/config-manager.ts
 import { readFileSync, writeFileSync, existsSync, mkdirSync } from "fs";
@@ -555,6 +555,8 @@ var ClaudeProvider = class extends BaseProvider {
     const extraMessages = request._extraMessages ?? [];
     const allMessages = [...baseMessages, ...extraMessages];
     const { thinking, temperature } = this.buildThinkingParams(request);
+    let doneEmitted = false;
+    const rawContentBlocks = [];
     try {
       const stream = this.client.messages.stream({
         model: request.model,
@@ -567,8 +569,6 @@ var ClaudeProvider = class extends BaseProvider {
       }, { signal: request.signal });
       let currentBlockType = null;
       let currentToolIndex = 0;
-      let doneEmitted2 = false;
-      const rawContentBlocks2 = [];
       let currentBlockData = {};
       for await (const event of stream) {
         if (event.type === "content_block_start") {
@@ -627,20 +627,20 @@ var ClaudeProvider = class extends BaseProvider {
             }
             delete currentBlockData._inputJson;
           }
-          rawContentBlocks2.push(currentBlockData);
+          rawContentBlocks.push(currentBlockData);
           currentBlockType = null;
           currentBlockData = {};
         } else if (event.type === "message_delta") {
           const usage = event.usage;
           if (usage) {
-            doneEmitted2 = true;
+            doneEmitted = true;
             yield {
               type: "done",
               usage: {
                 inputTokens: usage.input_tokens ?? 0,
                 outputTokens: usage.output_tokens ?? 0
               },
-              rawContent: rawContentBlocks2
+              rawContent: rawContentBlocks
             };
           }
         }

package/dist/{hub-VQPJKWKE.js → hub-YFHYOGDB.js}

@@ -387,7 +387,7 @@ ${content}`);
   }
 }
 async function runTaskMode(config, providers, configManager, topic) {
-  const { TaskOrchestrator } = await import("./task-orchestrator-XNINKBSB.js");
+  const { TaskOrchestrator } = await import("./task-orchestrator-7B3UBHMI.js");
   const orchestrator = new TaskOrchestrator(config, providers, configManager);
   let interrupted = false;
   const onSigint = () => {

package/dist/index.js

@@ -24,7 +24,7 @@ import {
   saveDevState,
   sessionHasMeaningfulContent,
   setupProxy
-} from "./chunk-3UUFCRRL.js";
+} from "./chunk-Y4B6HE6J.js";
 import {
   ToolExecutor,
   ToolRegistry,
@@ -37,7 +37,7 @@ import {
   spawnAgentContext,
   theme,
   undoStack
-} from "./chunk-OZER6O2H.js";
+} from "./chunk-KPHYJOJT.js";
 import {
   fileCheckpoints
 } from "./chunk-4BKXL7SM.js";
@@ -61,7 +61,7 @@ import {
   SKILLS_DIR_NAME,
   VERSION,
   buildUserIdentityPrompt
-} from "./chunk-XPQEGIFO.js";
+} from "./chunk-RVJMWZEJ.js";
 
 // src/index.ts
 import { program } from "commander";
@@ -194,9 +194,9 @@ var Renderer = class {
     console.log(label("Desc") + chalk.white(DESCRIPTION));
     console.log(label("Author") + theme.warning(AUTHOR) + theme.dim("  <" + AUTHOR_EMAIL + ">"));
     console.log(HR);
-    console.log(theme.dim("  Supported Providers (7):"));
+    console.log(theme.dim("  Supported Providers (8):"));
     console.log(theme.dim("    OpenAI \xB7 DeepSeek \xB7 Kimi (Moonshot) \xB7 Claude (Anthropic)"));
-    console.log(theme.dim("    Gemini (Google) \xB7 Zhipu (GLM) \xB7 Custom OpenAI-compatible"));
+    console.log(theme.dim("    Gemini (Google) \xB7 Zhipu (GLM) \xB7 OpenRouter \xB7 Ollama (Local, no API key)"));
     console.log(HR);
     const mcpToolCount = mcpInfo?.tools ?? 0;
     const toolTotal = 19 + pluginCount + mcpToolCount;
@@ -290,6 +290,7 @@ var Renderer = class {
     console.log(feat("Human participation: aicli join --human \u2014 real person joins multi-agent discussion"));
     console.log(feat("Context injection: aicli hub -c doc.md \u2014 inject external documents for all agents"));
     console.log(feat("Task Mode: aicli hub --task \u2014 agents plan, write code, and execute with tools (plan\u2192approve\u2192execute\u2192review)"));
+    console.log(feat("Ollama local models: built-in provider, no API key, auto-discovers installed models via /v1/models"));
     console.log();
   }
   printPrompt(provider, _model) {
@@ -2098,7 +2099,7 @@ ${hint}` : "")
       usage: "/test [command|filter]",
       async execute(args, ctx) {
         try {
-          const { executeTests } = await import("./run-tests-3QVMT5WL.js");
+          const { executeTests } = await import("./run-tests-AXMJPIO7.js");
           const argStr = args.join(" ").trim();
           let testArgs = {};
           if (argStr) {
@@ -5469,7 +5470,7 @@ program.command("web").description("Start Web UI server with browser-based chat
     console.error("Error: Invalid port number. Must be between 1 and 65535.");
     process.exit(1);
   }
-  const { startWebServer } = await import("./server-G6ALWI6B.js");
+  const { startWebServer } = await import("./server-QJSBW5NP.js");
   await startWebServer({ port, host: options.host });
 });
 program.command("user [action] [username]").description("Manage Web UI users (list | create <name> | delete <name> | reset-password <name> | migrate <name>)").action(async (action, username) => {
@@ -5702,7 +5703,7 @@ program.command("hub [topic]").description("Start multi-agent hub (discuss / bra
     }),
     config.get("customProviders")
   );
-  const { startHub } = await import("./hub-VQPJKWKE.js");
+  const { startHub } = await import("./hub-YFHYOGDB.js");
   await startHub(
     {
       topic: topic ?? "",

package/dist/{run-tests-4D4EQB33.js → run-tests-5CFPPABG.js}

@@ -1,7 +1,7 @@
 import {
   executeTests,
   runTestsTool
-} from "./chunk-TNRYHTGD.js";
+} from "./chunk-CYBC7PWO.js";
 export {
   executeTests,
   runTestsTool

package/dist/{run-tests-3QVMT5WL.js → run-tests-AXMJPIO7.js}

@@ -2,7 +2,7 @@
 import {
   executeTests,
   runTestsTool
-} from "./chunk-XPQEGIFO.js";
+} from "./chunk-RVJMWZEJ.js";
 export {
   executeTests,
   runTestsTool

package/dist/{server-G6ALWI6B.js → server-QJSBW5NP.js}

@@ -15,7 +15,7 @@ import {
   hadPreviousWriteToolCalls,
   loadDevState,
   setupProxy
-} from "./chunk-3UUFCRRL.js";
+} from "./chunk-Y4B6HE6J.js";
 import {
   AuthManager
 } from "./chunk-BYNY5JPB.js";
@@ -33,7 +33,7 @@ import {
   spawnAgentContext,
   truncateOutput,
   undoStack
-} from "./chunk-OZER6O2H.js";
+} from "./chunk-KPHYJOJT.js";
 import "./chunk-4BKXL7SM.js";
 import {
   AGENTIC_BEHAVIOR_GUIDELINE,
@@ -52,7 +52,7 @@ import {
   SKILLS_DIR_NAME,
   VERSION,
   buildUserIdentityPrompt
-} from "./chunk-XPQEGIFO.js";
+} from "./chunk-RVJMWZEJ.js";
 
 // src/web/server.ts
 import express from "express";
@@ -1606,7 +1606,7 @@ ${undoResults.map((r) => `  \u2022 ${r}`).join("\n")}` });
       case "test": {
         this.send({ type: "info", message: "\u{1F9EA} Running tests..." });
         try {
-          const { executeTests } = await import("./run-tests-3QVMT5WL.js");
+          const { executeTests } = await import("./run-tests-AXMJPIO7.js");
           const argStr = args.join(" ").trim();
           let testArgs = {};
           if (argStr) {

package/dist/{task-orchestrator-XNINKBSB.js → task-orchestrator-7B3UBHMI.js}

@@ -4,11 +4,11 @@ import {
   getDangerLevel,
   googleSearchContext,
   truncateOutput
-} from "./chunk-OZER6O2H.js";
+} from "./chunk-KPHYJOJT.js";
 import "./chunk-4BKXL7SM.js";
 import {
   SUBAGENT_ALLOWED_TOOLS
-} from "./chunk-XPQEGIFO.js";
+} from "./chunk-RVJMWZEJ.js";
 
 // src/hub/task-orchestrator.ts
 import { createInterface } from "readline";

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "jinzd-ai-cli",
-  "version": "0.4.38",
+  "version": "0.4.40",
   "description": "Cross-platform REPL-style AI CLI with multi-provider support",
   "type": "module",
   "main": "./dist/index.js",