feat: 支持agent模式

Author: Gil2015

README.md

@@ -324,21 +324,6 @@ Currently, Agent mode is supported by:
 - **DeepSeek** (`deepseek-chat` and other models with function calling)
 - **Zhipu** (`glm-4` and other models with function calling)
 
-### Available Tools
-
-| Tool | Description | Use Case |
-|------|-------------|----------|
-| `read_file` | Read file contents with pagination | View complete source files, type definitions |
-| `search_content` | Search code with regex patterns | Find function definitions, method calls |
-| `list_directory` | List directory structure | Understand project organization |
-
-### How It Works
-
-1. AI receives the diff and list of changed files
-2. AI analyzes the changes and identifies areas needing more context
-3. AI uses tools to retrieve relevant code (e.g., type definitions, related functions)
-4. AI generates a comprehensive review based on full context
-5. Process repeats until AI has enough information or limits are reached
 
 ### Agent Mode Prompt Example
 
@@ -352,6 +337,7 @@ export default {
     maxIterations: 5,
     maxToolCalls: 10
   },
+  ..., // other options
   prompt: `You are a senior code reviewer with access to the full codebase context.
 
 Project Info:
@@ -390,7 +376,24 @@ Final recommendation on whether to merge`
 }
 ```
 
-> **Note**: Agent mode increases API token usage due to multi-turn conversations and tool results. Consider this when reviewing large changes.
+> **Note**: Agent mode increases API token usage due to multi-turn conversations and tool results. Consider this when reviewing large changes. To save tokens, the diff content is also merged and displayed.
+
+
+### Available Tools
+
+| Tool | Description | Use Case |
+|------|-------------|----------|
+| `read_file` | Read file contents with pagination | View complete source files, type definitions |
+| `search_content` | Search code with regex patterns | Find function definitions, method calls |
+| `list_directory` | List directory structure | Understand project organization |
+
+### How It Works
+
+1. AI receives the diff and list of changed files
+2. AI analyzes the changes and identifies areas needing more context
+3. AI uses tools to retrieve relevant code (e.g., type definitions, related functions)
+4. AI generates a comprehensive review based on full context
+5. Process repeats until AI has enough information or limits are reached
 
 ---
 

README_ZH.md

@@ -329,22 +329,6 @@ export default {
 - **DeepSeek**（`deepseek-chat` 及其他支持函数调用的模型）
 - **智谱**（`glm-4` 及其他支持函数调用的模型）
 
-### 可用工具
-
-| 工具 | 描述 | 使用场景 |
-|------|------|----------|
-| `read_file` | 分页读取文件内容 | 查看完整源代码、类型定义 |
-| `search_content` | 使用正则表达式搜索代码 | 查找函数定义、方法调用 |
-| `list_directory` | 列出目录结构 | 了解项目组织方式 |
-
-### 工作原理
-
-1. AI 接收 diff 和变更文件列表
-2. AI 分析变更并识别需要更多上下文的区域
-3. AI 使用工具获取相关代码（如类型定义、关联函数）
-4. AI 基于完整上下文生成全面的审查报告
-5. 重复上述过程直到 AI 获取足够信息或达到限制
-
 ### Agent 模式提示词示例
 
 使用 Agent 模式时，可以优化提示词以充分利用 AI 获取上下文的能力。以下是推荐的 Agent 模式提示词：
@@ -357,6 +341,7 @@ export default {
     maxIterations: 5,
     maxToolCalls: 10
   },
+  ..., // 其它配置
   prompt: `你是一位高级代码审查员，可以访问完整的代码库上下文。
 
 项目信息：
@@ -395,7 +380,23 @@ export default {
 }
 ```
 
-> **注意**：Agent 模式会因多轮对话和工具结果而增加 API Token 消耗。审查大型变更时请注意这一点。
+> **注意**：Agent 模式会因多轮对话和工具结果而增加 API Token 消耗。审查大型变更时请注意这一点。为了节省token的同时，diff内容也会合并展示
+
+### agent可用工具
+
+| 工具 | 描述 | 使用场景 |
+|------|------|----------|
+| `read_file` | 分页读取文件内容 | 查看完整源代码、类型定义 |
+| `search_content` | 使用正则表达式搜索代码 | 查找函数定义、方法调用 |
+| `list_directory` | 列出目录结构 | 了解项目组织方式 |
+
+### 工作原理
+
+1. AI 接收 diff 和变更文件列表
+2. AI 分析变更并识别需要更多上下文的区域
+3. AI 使用工具获取相关代码（如类型定义、关联函数）
+4. AI 基于完整上下文生成全面的审查报告
+5. 重复上述过程直到 AI 获取足够信息或达到限制
 
 ---
 

package.json

@@ -1,6 +1,6 @@
 {
   "name": "code-gate",
-  "version": "1.2.0",
+  "version": "1.3.0",
   "description": "Intelligent Git commit guard and code reviewer. Supports local (Ollama) and cloud models (DeepSeek, OpenAI, Anthropic, etc.) with a rich CLI UI.",
   "type": "module",
   "bin": {