zen-code 4.8.4 → 4.8.6

package/dist/chunk-aeambwc5.js

@@ -0,0 +1,298 @@
+import{Ia as f,Ka as g}from"./chunk-5kmnxyd8.js";import{Ra as k}from"./chunk-vyejbw66.js";import{wb as o}from"./chunk-fzn8xq6f.js";import{AgentPackage as _,MemoryStorage as E}from"@langgraph-js/standard-agent";import{tool as x}from"@langchain/core/tools";import{z as i}from"zod";var U=i.object({content:i.string().min(1),status:i.enum(["pending","in_progress","completed"]),id:i.string()}),I=i.object({todos:i.array(U).describe("The updated todo list")}),u=x(async()=>{return"todo saved successfully"},{name:"todo_write",description:`Use this tool to create and manage a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.
+It also helps the user understand the progress of the task and overall progress of their requests.
+## When to Use This Tool
+Use this tool proactively in these scenarios:
+
+1. Complex multi-step tasks - When a task requires 3 or more distinct steps or actions
+2. Non-trivial and complex tasks - Tasks that require careful planning or multiple operations
+3. User explicitly requests todo list - When the user directly asks you to use the todo list
+4. User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)
+5. After receiving new instructions - Immediately capture user requirements as todos
+6. When you start working on a task - Mark it as in_progress BEFORE beginning work. Ideally you should only have one todo as in_progress at a time
+7. After completing a task - Mark it as completed and add any new follow-up tasks discovered during implementation
+
+## When NOT to Use This Tool
+
+Skip using this tool when:
+1. There is only a single, straightforward task
+2. The task is trivial and tracking it provides no organizational benefit
+3. The task can be completed in less than 3 trivial steps
+4. The task is purely conversational or informational
+
+NOTE that you should not use this tool if there is only one trivial task to do. In this case you are better off just doing the task directly.
+
+## Examples of When to Use the Todo List
+
+<example>
+User: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you're done!
+Assistant: I'll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.
+*Creates todo list with the following items:*
+1. Create dark mode toggle component in Settings page
+2. Add dark mode state management (context/store)
+3. Implement CSS-in-JS styles for dark theme
+4. Update existing components to support theme switching
+5. Run tests and build process, addressing any failures or errors that occur
+*Begins working on the first task*
+
+<reasoning>
+The assistant used the todo list because:
+1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes
+2. The user explicitly requested tests and build be run afterward
+3. The assistant inferred that tests and build need to pass by adding "Ensure tests and build succeed" as the final task
+</reasoning>
+</example>
+
+<example>
+User: Help me rename the function getCwd to getCurrentWorkingDirectory across my project
+Assistant: Let me first search through your codebase to find all occurrences of 'getCwd'.
+*Uses grep or search tools to locate all instances of getCwd in the codebase*
+Assistant: I've found 15 instances of 'getCwd' across 8 different files. Let me create a todo list to track these changes.
+*Creates todo list with specific items for each file that needs updating*
+
+<reasoning>
+The assistant used the todo list because:
+1. First, the assistant searched to understand the scope of the task
+2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps
+3. The todo list helps ensure every instance is tracked and updated systematically
+4. This approach prevents missing any occurrences and maintains code consistency
+</reasoning>
+</example>
+
+
+<example>
+User: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.
+Assistant: I'll help implement these features. First, let's add all the features to the todo list.
+*Creates a todo list breaking down each feature into specific tasks based on the project architecture*
+Assistant: Let's start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.
+
+<reasoning>
+The assistant used the todo list because:
+1. The user provided multiple complex features to implement in a comma separated list
+2. The todo list helps organize these large features into manageable tasks
+3. This approach allows for tracking progress across the entire implementation
+</reasoning>
+</example>
+
+<example>
+User: Can you help optimize my React application? It's rendering slowly and has performance issues.</user>
+Assistant: I'll help optimize your React application. First, let me examine your codebase to identify potential performance bottlenecks.
+*Reviews component structure, render patterns, state management, and data fetching*
+Assistant: After analyzing your codebase, I've identified several performance issues. Let me create a todo list to track our optimization efforts.
+*Creates todo list with items like: 1) Implement memoization for expensive calculations in ProductList, 2) Add virtualization for long lists in Dashboard, 3) Optimize image loading in Gallery component, 4) Fix state update loops in ShoppingCart, 5) Review bundle size and implement code splitting*
+Let's start by implementing memoization for the expensive calculations in your ProductList component.</assistant>
+
+<reasoning>
+The assistant used the todo list because:
+1. First, the assistant examined the codebase to identify specific performance issues
+2. Based on this analysis, it identified multiple optimization opportunities
+3. Performance optimization is a non-trivial task requiring multiple steps
+4. The todo list helps methodically track improvements across different components
+5. This systematic approach ensures all performance bottlenecks are addressed
+</reasoning>
+</example>
+
+## Examples of When NOT to Use the Todo List
+
+<example>
+User: How do I print 'Hello World' in Python?
+Assistant: In Python, you can print "Hello World" with this simple code:
+
+python
+print("Hello World")
+
+This will output the text "Hello World" to the console when executed.</assistant>
+
+<reasoning>
+The assistant did not use the todo list because this is a single, trivial task that can be completed in one step. There's no need to track multiple tasks or steps for such a straightforward request.
+</reasoning>
+</example>
+
+<example>
+User: What does the git status command do?
+Assistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven't, and which files aren't being tracked by Git. This is a fundamental command for understanding the current state of your repository before making commits.
+
+<reasoning>
+The assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.
+</reasoning>
+</example>
+
+<example>
+User: Can you add a comment to the calculateTotal function to explain what it does?
+Assistant: Sure, let me add a comment to the calculateTotal function to explain what it does.
+* Uses the Edit tool to add a comment to the calculateTotal function *
+
+<reasoning>
+The assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn't require tracking multiple steps or systematic organization.
+</reasoning>
+</example>
+
+<example>
+User: Run npm install for me and tell me what happens.
+Assistant: I'll run the npm install command for you.
+
+*Executes: npm install*
+
+The command completed successfully. Here's the output:
+[Output of npm install command]
+
+All dependencies have been installed according to your package.json file.
+
+<reasoning>
+The assistant did not use the todo list because this is a single command execution with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward task.
+</reasoning>
+</example>
+
+## Task States and Management
+
+1. **Task States**: Use these states to track progress:
+   - pending: Task not yet started
+   - in_progress: Currently working on (limit to ONE task at a time)
+   - completed: Task finished successfully
+
+2. **Task Management**:
+   - Update task status in real-time as you work
+   - Mark tasks complete IMMEDIATELY after finishing (don't batch completions)
+   - Only have ONE task in_progress at any time
+   - Complete current tasks before starting new ones
+   - Remove tasks that are no longer relevant from the list entirely
+
+3. **Task Completion Requirements**:
+   - ONLY mark a task as completed when you have FULLY accomplished it
+   - If you encounter errors, blockers, or cannot finish, keep the task as in_progress
+   - When blocked, create a new task describing what needs to be resolved
+   - Never mark a task as completed if:
+     - Tests are failing
+     - Implementation is partial
+     - You encountered unresolved errors
+     - You couldn't find necessary files or dependencies
+
+4. **Task Breakdown**:
+   - Create specific, actionable items
+   - Break complex tasks into smaller, manageable steps
+   - Use clear, descriptive task names
+
+When in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.
+`,schema:I});import{z as n}from"zod";import{tool as A}from"langchain";var z=n.object({label:n.string().min(1).max(50).describe("选项显示文本，简洁明了（1-50 字符）")}),W=n.object({description:n.string().min(1).describe("向用户提出的问题，清晰具体，包含必要的上下文"),type:n.enum(["single_select","multi_select"]).describe("选择类型：single_select（单选）或 multi_select（多选）"),options:n.array(z).min(2).max(6).describe("选项列表，至少 2 个，最多 6 个"),allow_custom_input:n.boolean().default(!0).describe("是否允许用户输入自定义文本，默认 true"),placeholder:n.string().optional().describe("自定义输入框的占位符文本")}),h=A(()=>{},{name:"ask_user_questions",description:"Ask the user a question with selectable options",schema:W});var q=[h,u];async function C(t,e){await t.addTool({id:e.name,name:e.name,description:e.description});let l={id:e.name,name:e.name,description:e.description,paramsSchema:e.schema,execute:async(d)=>{let a=await e.invoke(d);if(a&&typeof a==="object"&&"content"in a)return a.content;return a}};t.tools.registerImplementation(l)}async function p(t){return await Promise.all(q.map((e)=>C(t,e)))}async function y(t){let e={id:"filesystem",name:"filesystem",description:"File and directory operations (read, write, search, glob)",execute:async()=>{return new f}};await t.addMiddleware(e),t.middlewares.registerImplementation(e);let l={id:"terminal",name:"terminal",description:"Terminal command execution (Bash/CMD, background processes)",execute:async()=>{return new g}};await t.addMiddleware(l),t.middlewares.registerImplementation(l);let d={id:"subagents",name:"subagents",description:"Task delegation to specialized agents",execute:async()=>{let{createSubAgentsMiddleware:s}=await import("./chunk-903s8sk9.js");return await s(t)}};await t.addMiddleware(d),t.middlewares.registerImplementation(d);let a={id:"memories",name:"memories",description:"Knowledge persistence",execute:async(s)=>{s.projectMemoriesDir=s.projectMemoriesDir||"./.claude/memories";let{MemoriesMiddleware:r}=await import("./chunk-6yeg1jc7.js");return new r(s)}};await t.addMiddleware(a),t.middlewares.registerImplementation(a);let c={id:"skills",name:"skills",description:"Progressive skills disclosure",execute:async(s)=>{if(s.projectSkillsDir=s.projectSkillsDir||"./.claude/skills",!s.skillsDir){let T=await import("os"),v=await import("path");s.skillsDir=v.join(T.homedir(),".claude","skills")}let{SkillsMiddleware:r}=await import("@langgraph-js/standard-agent");return new r(s)}};await t.addMiddleware(c),t.middlewares.registerImplementation(c);let m={id:"agents_md",name:"agents_md",description:"Inject agent documentation",execute:async(s)=>{let{AgentsMdMiddleware:r}=await import("@langgraph-js/standard-agent");return new r({projectRoot:s?.projectRoot})}};await t.addMiddleware(m),t.middlewares.registerImplementation(m)}var b=`# 架构师 - 任务派发协调者
+
+你是一位**任务派发架构师**，核心职责是将用户需求分析并拆解为子任务，然后委派给合适的子 agent 执行。
+
+## 核心职责
+
+**你的唯一任务**：
+1. 理解用户需求
+2. 拆解为可执行的子任务
+3. 委派给合适的子 agent
+4. 跟踪和汇总结果
+
+**不要做的事**：
+- ❌ 不要自己编写代码
+- ❌ 不要自己读取文件或搜索代码
+- ❌ 不要自己执行终端命令
+- ❌ 不要做具体的架构分析或设计文档
+
+## 工作流程
+
+### 步骤 1：需求分析
+
+当收到用户请求时，快速判断：
+
+1. **任务类型**：
+   - 代码实现/修改 → 委派给 \`agents/default\`
+   - 任务规划/协调 → 委派给 \`agents/manager\`
+   - 复杂任务 → 先由 \`agents/manager\` 规划，再由 \`agents/default\` 执行
+
+2. **任务规模**：
+   - 单一任务 → 直接委派
+   - 多任务 → 拆分后分别委派
+
+### 步骤 2：任务拆解
+
+使用 \`task\` 工具委派任务：
+
+\`\`\`typescript
+// 示例：委派代码实现任务
+{
+  subagent_id: "agents/default",
+  task_description: "实现用户认证功能，包括登录、注册、登出三个接口",
+  data_transfer: {
+    requirements: "使用 JWT 认证，密码需要加密存储",
+    constraints: "使用现有的数据库连接池"
+  }
+}
+\`\`\`
+
+### 步骤 3：结果汇总
+
+子 agent 完成后：
+1. 检查执行结果
+2. 如果有多个子任务，协调依赖关系
+3. 向用户汇报整体进度和结果
+
+## 委派策略
+
+### 简单任务
+
+用户请求单一功能时，直接委派：
+
+> 用户：添加一个日志工具函数
+
+→ 委派给 \`agents/default\`，任务描述清晰完整
+
+### 复杂任务
+
+用户请求多功能时，拆分后委派：
+
+> 用户：重构用户模块并添加测试
+
+→ 拆分为：
+1. 委派 \`agents/default\`：重构用户模块代码
+2. 等第一步完成后，委派 \`agents/default\`：为用户模块编写测试
+
+### 规划任务
+
+用户需要方案设计时：
+
+> 用户：设计一个新的权限系统
+
+→ 委派 \`agents/manager\` 进行任务规划，然后按规划执行
+
+## 输出格式
+
+### 委派时
+
+\`\`\`markdown
+## 任务分析
+
+**用户需求**：{用户原始请求}
+
+**任务拆解**：
+1. 任务 A → 委派给 agents/default
+2. 任务 B → 委派给 agents/manager
+
+**开始执行**...
+\`\`\`
+
+### 汇报时
+
+\`\`\`markdown
+## 执行结果
+
+**已完成**：
+- ✅ 任务 A：{简要结果}
+- ✅ 任务 B：{简要结果}
+
+**总结**：{整体结果摘要}
+\`\`\`
+
+## 重要约束
+
+1. **立即委派**：收到任务后，不要犹豫，立即分析并委派
+2. **清晰描述**：给子 agent 的任务描述要完整、清晰
+3. **传递上下文**：使用 \`data_transfer\` 传递必要的背景信息
+4. **不要插手**：相信子 agent 的能力，不要自己动手做具体工作
+5. **保持简洁**：你的输出应该简短，重点是协调和汇总
+
+---
+
+**记住**：你是协调者，不是执行者。快速分析需求，立即委派任务，高效汇总结果。`;async function w(){let t=new E,e=new _(t);return await e.addModel({id:"glm-4.7",model_name:"glm-4.7",model_provider:process.env.MODEL_PROVIDER||"openai",stream_usage:!0,enable_thinking:!0,temperature:0.7,max_tokens:4096,top_p:1,frequency_penalty:0,presence_penalty:0}),await e.addPrompt({id:"prompts/default",name:"default",content:k}),await e.addPrompt({id:"prompts/manager",name:"manager",content:b}),await p(e),await y(e),await e.addAgent({id:"agents/default",name:"Jarvis",description:"代码实现助手",system_prompt:"prompts/default",model:"glm-4.7",tools:{ask_user_questions:!0,todo_write:!0},middleware:{filesystem:!0,terminal:!0,agents_md:!0,skills:!0,memories:!0,subagents:!0}}),await e.addAgent({id:"agents/manager",name:"Manager",description:"任务管理员",system_prompt:"prompts/manager",model:"glm-4.7",tools:{ask_user_questions:!0,todo_write:!0},middleware:{filesystem:!0,terminal:!0,agents_md:!0,skills:!0,memories:!0,subagents:!0}}),e}var se=await w();
+export{I as Ca,se as Da};

package/dist/{chunk-n72x5y7a.js → chunk-bzgj8aae.js}

@@ -1,4 +1,4 @@
-import"./chunk-feptb1bb.js";import{Kysely as H,PostgresDialect as I,sql as w}from"kysely";class J{constructor(h){this.pool=h,this.db=new H({dialect:new I({pool:h})})}db;dateToDb(h){return h}dbToDate(h){return h instanceof Date?h:new Date(h)}jsonToDb(h){return h}dbToJson(h){return h}buildJsonQuery(h,x,z,C){return w`${w.ref(x)}->>${w.lit(z)} = ${w.lit(JSON.stringify(C))}`}now(){return new Date}async createTables(h){await w`
+import"./chunk-fzn8xq6f.js";import{Kysely as H,PostgresDialect as I,sql as w}from"kysely";class J{constructor(h){this.pool=h,this.db=new H({dialect:new I({pool:h})})}db;dateToDb(h){return h}dbToDate(h){return h instanceof Date?h:new Date(h)}jsonToDb(h){return h}dbToJson(h){return h}buildJsonQuery(h,x,z,C){return w`${w.ref(x)}->>${w.lit(z)} = ${w.lit(JSON.stringify(C))}`}now(){return new Date}async createTables(h){await w`
             CREATE TABLE IF NOT EXISTS threads (
                 thread_id TEXT PRIMARY KEY,
                 created_at TIMESTAMP NOT NULL,