@axiom-lattice/core 1.0.1

package/dist/index.js

@@ -0,0 +1,2191 @@
+"use strict";
+var __create = Object.create;
+var __defProp = Object.defineProperty;
+var __getOwnPropDesc = Object.getOwnPropertyDescriptor;
+var __getOwnPropNames = Object.getOwnPropertyNames;
+var __getProtoOf = Object.getPrototypeOf;
+var __hasOwnProp = Object.prototype.hasOwnProperty;
+var __export = (target, all) => {
+  for (var name in all)
+    __defProp(target, name, { get: all[name], enumerable: true });
+};
+var __copyProps = (to, from, except, desc) => {
+  if (from && typeof from === "object" || typeof from === "function") {
+    for (let key of __getOwnPropNames(from))
+      if (!__hasOwnProp.call(to, key) && key !== except)
+        __defProp(to, key, { get: () => from[key], enumerable: !(desc = __getOwnPropDesc(from, key)) || desc.enumerable });
+  }
+  return to;
+};
+var __toESM = (mod, isNodeMode, target) => (target = mod != null ? __create(__getProtoOf(mod)) : {}, __copyProps(
+  // If the importer is in node compatibility mode or this is not an ESM
+  // file that has been converted to a CommonJS file using a Babel-
+  // compatible transform (i.e. "__esModule" has not been set), then set
+  // "default" to the CommonJS "module.exports" for node compatibility.
+  isNodeMode || !mod || !mod.__esModule ? __defProp(target, "default", { value: mod, enumerable: true }) : target,
+  mod
+));
+var __toCommonJS = (mod) => __copyProps(__defProp({}, "__esModule", { value: true }), mod);
+
+// src/index.ts
+var index_exports = {};
+__export(index_exports, {
+  AgentConfig: () => import_protocols.AgentConfig,
+  AgentLatticeManager: () => AgentLatticeManager,
+  AgentType: () => import_protocols.AgentType,
+  GraphBuildOptions: () => import_protocols.GraphBuildOptions,
+  MemoryLatticeManager: () => MemoryLatticeManager,
+  MemoryType: () => import_protocols2.MemoryType,
+  ModelLatticeManager: () => ModelLatticeManager,
+  Protocols: () => Protocols,
+  agentLatticeManager: () => agentLatticeManager,
+  getAgentClient: () => getAgentClient,
+  getAgentConfig: () => getAgentConfig,
+  getAgentLattice: () => getAgentLattice,
+  getAllAgentConfigs: () => getAllAgentConfigs,
+  getCheckpointSaver: () => getCheckpointSaver,
+  getModelLattice: () => getModelLattice,
+  modelLatticeManager: () => modelLatticeManager,
+  registerAgentLattice: () => registerAgentLattice,
+  registerAgentLattices: () => registerAgentLattices,
+  registerCheckpointSaver: () => registerCheckpointSaver,
+  registerModelLattice: () => registerModelLattice,
+  validateAgentInput: () => validateAgentInput
+});
+module.exports = __toCommonJS(index_exports);
+
+// src/base/BaseLatticeManager.ts
+var _BaseLatticeManager = class _BaseLatticeManager {
+  /**
+   * 受保护的构造函数，防止外部直接实例化
+   */
+  constructor() {
+  }
+  /**
+   * 获取管理器实例（由子类实现）
+   */
+  static getInstance() {
+    throw new Error("\u5FC5\u987B\u7531\u5B50\u7C7B\u5B9E\u73B0");
+  }
+  /**
+   * 构造完整的键名，包含类型前缀
+   * @param key 原始键名
+   */
+  getFullKey(key) {
+    return `${this.getLatticeType()}.${key}`;
+  }
+  /**
+   * 注册项目
+   * @param key 项目键名（不含前缀）
+   * @param item 项目实例
+   */
+  register(key, item) {
+    const fullKey = this.getFullKey(key);
+    if (_BaseLatticeManager.registry.has(fullKey)) {
+      throw new Error(`\u9879\u76EE "${fullKey}" \u5DF2\u7ECF\u5B58\u5728\uFF0C\u65E0\u6CD5\u91CD\u590D\u6CE8\u518C`);
+    }
+    _BaseLatticeManager.registry.set(fullKey, item);
+  }
+  /**
+   * 获取指定项目
+   * @param key 项目键名（不含前缀）
+   */
+  get(key) {
+    const fullKey = this.getFullKey(key);
+    return _BaseLatticeManager.registry.get(fullKey);
+  }
+  /**
+   * 获取所有当前类型的项目
+   */
+  getAll() {
+    const prefix = `${this.getLatticeType()}.`;
+    const result = [];
+    for (const [key, value] of _BaseLatticeManager.registry.entries()) {
+      if (key.startsWith(prefix)) {
+        result.push(value);
+      }
+    }
+    return result;
+  }
+  /**
+   * 检查项目是否存在
+   * @param key 项目键名（不含前缀）
+   */
+  has(key) {
+    const fullKey = this.getFullKey(key);
+    return _BaseLatticeManager.registry.has(fullKey);
+  }
+  /**
+   * 移除项目
+   * @param key 项目键名（不含前缀）
+   */
+  remove(key) {
+    const fullKey = this.getFullKey(key);
+    return _BaseLatticeManager.registry.delete(fullKey);
+  }
+  /**
+   * 清空当前类型的所有项目
+   */
+  clear() {
+    const prefix = `${this.getLatticeType()}.`;
+    const keysToDelete = [];
+    for (const key of _BaseLatticeManager.registry.keys()) {
+      if (key.startsWith(prefix)) {
+        keysToDelete.push(key);
+      }
+    }
+    for (const key of keysToDelete) {
+      _BaseLatticeManager.registry.delete(key);
+    }
+  }
+  /**
+   * 获取当前类型的项目数量
+   */
+  count() {
+    const prefix = `${this.getLatticeType()}.`;
+    let count = 0;
+    for (const key of _BaseLatticeManager.registry.keys()) {
+      if (key.startsWith(prefix)) {
+        count++;
+      }
+    }
+    return count;
+  }
+  /**
+   * 获取当前类型的项目键名列表（不含前缀）
+   */
+  keys() {
+    const prefix = `${this.getLatticeType()}.`;
+    const prefixLength = prefix.length;
+    const result = [];
+    for (const key of _BaseLatticeManager.registry.keys()) {
+      if (key.startsWith(prefix)) {
+        result.push(key.substring(prefixLength));
+      }
+    }
+    return result;
+  }
+};
+// 全局统一的Lattice注册表
+_BaseLatticeManager.registry = /* @__PURE__ */ new Map();
+var BaseLatticeManager = _BaseLatticeManager;
+
+// src/model_lattice/ModelLattice.ts
+var import_deepseek = require("@langchain/deepseek");
+var import_openai = require("@langchain/openai");
+var import_chat_models = require("@langchain/core/language_models/chat_models");
+var import_base = require("@langchain/core/language_models/base");
+var ModelLattice = class extends import_chat_models.BaseChatModel {
+  /**
+   * 构造函数
+   * @param config LLM配置
+   */
+  constructor(config) {
+    super({});
+    this.lc_namespace = ["langchain", "model_lattice"];
+    this.config = config;
+    this.llm = this.initChatModel(config);
+  }
+  /**
+   * 返回模型类型
+   */
+  _llmType() {
+    return "model_lattice";
+  }
+  /**
+   * 返回模型类型
+   */
+  _modelType() {
+    return this.llm._modelType();
+  }
+  /**
+   * 实现BaseChatModel的_generate方法
+   * @param messages 消息数组
+   * @param options 调用选项
+   * @param runManager 回调管理器
+   * @returns 聊天结果
+   */
+  async _generate(messages, options, runManager) {
+    return this.llm._generate(messages, options, runManager);
+  }
+  /**
+   * 将工具绑定到模型
+   * @param tools 工具列表
+   * @param tool_choice 工具选择选项
+   * @returns 绑定工具后的模型
+   */
+  bindTools(tools, {
+    tool_choice = "auto",
+    ...kwargs
+  } = {}) {
+    if (typeof this.llm.bindTools === "function") {
+      return this.llm.bindTools(tools, {
+        tool_choice,
+        ...kwargs
+      });
+    }
+    throw new Error("llm not support bindTools");
+  }
+  /**
+   * 使用结构化输出调用LLM
+   * @param input 输入
+   * @param schema 结构化输出的schema
+   * @param options 调用选项
+   * @returns 结构化输出
+   */
+  async invokeWithStructuredOutput(input, schema, options) {
+    if (this.llm.withStructuredOutput) {
+      const structuredLLM = this.llm.withStructuredOutput(schema, {
+        includeRaw: options?.includeRaw ?? false,
+        name: options?.name,
+        method: options?.method
+      });
+      return structuredLLM.invoke(input, options);
+    }
+    throw new Error("\u5F53\u524DLLM\u4E0D\u652F\u6301\u7ED3\u6784\u5316\u8F93\u51FA");
+  }
+  /**
+   * 创建LLM实例
+   * @param config LLM配置
+   * @returns LLM实例
+   */
+  initChatModel(config) {
+    if (config.provider === "azure") {
+      return new import_openai.AzureChatOpenAI({
+        azureOpenAIApiKey: process.env.AZURE_OPENAI_API_KEY,
+        azureOpenAIApiInstanceName: "convertlab-westus",
+        azureOpenAIApiDeploymentName: config.model,
+        azureOpenAIApiVersion: "2024-02-01",
+        temperature: config.temperature || 0,
+        maxTokens: config.maxTokens,
+        timeout: config.timeout,
+        maxRetries: config.maxRetries || 2,
+        streaming: config.streaming
+      });
+    } else if (config.provider === "deepseek") {
+      return new import_deepseek.ChatDeepSeek({
+        model: config.model,
+        temperature: config.temperature || 0,
+        maxTokens: config.maxTokens,
+        timeout: config.timeout,
+        maxRetries: config.maxRetries || 2,
+        apiKey: process.env[config.apiKeyEnvName || "DEEPSEEK_API_KEY"],
+        streaming: config.streaming
+      });
+    } else if (config.provider === "siliconcloud") {
+      return new import_openai.ChatOpenAI({
+        model: config.model,
+        temperature: config.temperature || 0,
+        maxTokens: config.maxTokens,
+        timeout: config.timeout,
+        maxRetries: config.maxRetries || 2,
+        apiKey: process.env[config.apiKeyEnvName || "SILICONCLOUD_API_KEY"],
+        configuration: {
+          baseURL: "https://api.siliconflow.cn/v1"
+        },
+        streaming: config.streaming
+      });
+    } else if (config.provider === "volcengine") {
+      return new import_openai.ChatOpenAI({
+        model: config.model,
+        temperature: config.temperature || 0,
+        maxTokens: config.maxTokens,
+        timeout: config.timeout,
+        maxRetries: config.maxRetries || 2,
+        apiKey: process.env[config.apiKeyEnvName || "VOLCENGINE_API_KEY"],
+        configuration: {
+          baseURL: "https://ark.cn-beijing.volces.com/api/v3"
+        },
+        streaming: config.streaming
+      });
+    } else {
+      return new import_openai.ChatOpenAI({
+        model: config.model,
+        temperature: config.temperature || 0,
+        maxTokens: config.maxTokens,
+        timeout: config.timeout,
+        maxRetries: config.maxRetries || 2,
+        streaming: config.streaming,
+        apiKey: process.env[config.apiKeyEnvName || "OPENAI_API_KEY"],
+        configuration: {
+          baseURL: config.baseURL
+        }
+      });
+    }
+  }
+};
+
+// src/model_lattice/ModelLatticeManager.ts
+var ModelLatticeManager = class _ModelLatticeManager extends BaseLatticeManager {
+  /**
+   * 获取ModelLatticeManager单例实例
+   */
+  static getInstance() {
+    if (!_ModelLatticeManager._instance) {
+      _ModelLatticeManager._instance = new _ModelLatticeManager();
+    }
+    return _ModelLatticeManager._instance;
+  }
+  /**
+   * 获取Lattice类型前缀
+   */
+  getLatticeType() {
+    return "models";
+  }
+  /**
+   * 注册模型Lattice
+   * @param key Lattice键名
+   * @param config 模型配置
+   */
+  registerLattice(key, config) {
+    const client = new ModelLattice(config);
+    const modelLattice = {
+      key,
+      client
+    };
+    this.register(key, modelLattice);
+  }
+  /**
+   * 获取ModelLattice
+   * @param key Lattice键名
+   */
+  getModelLattice(key) {
+    const modelLattice = this.get(key);
+    if (!modelLattice) {
+      throw new Error(`ModelLattice ${key} not found`);
+    }
+    return modelLattice;
+  }
+  /**
+   * 获取所有Lattice
+   */
+  getAllLattices() {
+    return this.getAll();
+  }
+  /**
+   * 检查Lattice是否存在
+   * @param key Lattice键名
+   */
+  hasLattice(key) {
+    return this.has(key);
+  }
+  /**
+   * 移除Lattice
+   * @param key Lattice键名
+   */
+  removeLattice(key) {
+    return this.remove(key);
+  }
+  /**
+   * 清空所有Lattice
+   */
+  clearLattices() {
+    this.clear();
+  }
+  /**
+   * 获取Lattice数量
+   */
+  getLatticeCount() {
+    return this.count();
+  }
+  /**
+   * 获取Lattice键名列表
+   */
+  getLatticeKeys() {
+    return this.keys();
+  }
+};
+var modelLatticeManager = ModelLatticeManager.getInstance();
+var registerModelLattice = (key, config) => modelLatticeManager.registerLattice(key, config);
+var getModelLattice = (key) => modelLatticeManager.getModelLattice(key);
+
+// src/tool_lattice/get_current_date_time/index.ts
+var import_zod = __toESM(require("zod"));
+
+// src/tool_lattice/ToolLatticeManager.ts
+var import_tools = require("@langchain/core/tools");
+var ToolLatticeManager = class _ToolLatticeManager extends BaseLatticeManager {
+  /**
+   * 获取ToolLatticeManager单例实例
+   */
+  static getInstance() {
+    if (!_ToolLatticeManager._instance) {
+      _ToolLatticeManager._instance = new _ToolLatticeManager();
+    }
+    return _ToolLatticeManager._instance;
+  }
+  /**
+   * 获取Lattice类型前缀
+   */
+  getLatticeType() {
+    return "tools";
+  }
+  /**
+   * 注册工具Lattice
+   * @param key Lattice键名
+   * @param config 工具配置（定义）
+   * @param executor 工具执行函数
+   */
+  registerLattice(key, config, executor) {
+    let toolExecutor = async (input, exe_config) => {
+      const result = await executor(input, exe_config);
+      return result;
+    };
+    const toolLattice = {
+      key,
+      config,
+      client: (0, import_tools.tool)(toolExecutor, config)
+    };
+    this.register(key, toolLattice);
+  }
+  /**
+   * 获取ToolLattice
+   * @param key Lattice键名
+   */
+  getToolLattice(key) {
+    return this.get(key);
+  }
+  /**
+   * 获取所有Lattice
+   */
+  getAllLattices() {
+    return this.getAll();
+  }
+  /**
+   * 检查Lattice是否存在
+   * @param key Lattice键名
+   */
+  hasLattice(key) {
+    return this.has(key);
+  }
+  /**
+   * 移除Lattice
+   * @param key Lattice键名
+   */
+  removeLattice(key) {
+    return this.remove(key);
+  }
+  /**
+   * 清空所有Lattice
+   */
+  clearLattices() {
+    this.clear();
+  }
+  /**
+   * 获取Lattice数量
+   */
+  getLatticeCount() {
+    return this.count();
+  }
+  /**
+   * 获取Lattice键名列表
+   */
+  getLatticeKeys() {
+    return this.keys();
+  }
+  /**
+   * 获取工具定义
+   * @param key Lattice键名
+   */
+  getToolDefinition(key) {
+    const toolLattice = this.getToolLattice(key);
+    if (!toolLattice) {
+      throw new Error(`ToolLattice ${key} not found`);
+    }
+    return toolLattice.config;
+  }
+  /**
+   * 获取工具客户端
+   * @param key Lattice键名
+   */
+  getToolClient(key) {
+    const toolLattice = this.getToolLattice(key);
+    if (!toolLattice) {
+      throw new Error(`ToolLattice ${key} not found`);
+    }
+    return toolLattice.client;
+  }
+  /**
+   * 获取所有工具定义
+   */
+  getAllToolDefinitions() {
+    return this.getAllLattices().map((lattice) => lattice.config);
+  }
+  /**
+   * 验证工具输入参数
+   * @param key Lattice键名
+   * @param input 输入参数
+   */
+  validateToolInput(key, input) {
+    const toolLattice = this.getToolLattice(key);
+    if (!toolLattice) {
+      return false;
+    }
+    try {
+      if (toolLattice.config.schema) {
+        toolLattice.config.schema.parse(input);
+      }
+      return true;
+    } catch {
+      return false;
+    }
+  }
+};
+var toolLatticeManager = ToolLatticeManager.getInstance();
+var registerToolLattice = (key, config, executor) => toolLatticeManager.registerLattice(key, config, executor);
+var getToolClient = (key) => toolLatticeManager.getToolClient(key);
+
+// src/tool_lattice/get_current_date_time/index.ts
+registerToolLattice(
+  "get_current_date_time",
+  {
+    name: "\u83B7\u53D6\u5F53\u524D\u65E5\u671F\u65F6\u95F4",
+    description: "\u83B7\u53D6\u5F53\u524D\u65E5\u671F\u65F6\u95F4",
+    schema: import_zod.default.object({})
+  },
+  async () => {
+    return "\u5F53\u524D\u65E5\u671F\u65F6\u95F4\uFF1A" + (/* @__PURE__ */ new Date()).toLocaleString();
+  }
+);
+
+// src/tool_lattice/internet_search/index.ts
+var import_zod2 = __toESM(require("zod"));
+var import_tavily = require("@langchain/tavily");
+var import_config = require("dotenv/config");
+
+// src/util/genUICard.ts
+var genUICard = (title, type, data) => {
+  return [title, "```" + type, JSON.stringify(data), "```"].join("\n");
+};
+
+// src/tool_lattice/internet_search/index.ts
+registerToolLattice(
+  "internet_search",
+  {
+    name: "internet_search",
+    description: "Run a web search",
+    needUserApprove: true,
+    schema: import_zod2.default.object({
+      query: import_zod2.default.string().describe("The search query"),
+      maxResults: import_zod2.default.number().optional().default(5).describe("Maximum number of results to return"),
+      topic: import_zod2.default.enum(["general", "news", "finance"]).optional().default("general").describe("Search topic category"),
+      includeRawContent: import_zod2.default.boolean().optional().default(false).describe("Whether to include raw content")
+    })
+  },
+  async ({
+    query,
+    maxResults = 5,
+    topic = "general",
+    includeRawContent = false
+  }, config) => {
+    const tavilySearch = new import_tavily.TavilySearch({
+      maxResults,
+      tavilyApiKey: process.env.TAVILY_API_KEY,
+      includeRawContent,
+      topic
+    });
+    const tavilyResponse = await tavilySearch.invoke({ query });
+    return genUICard("Internet Search:" + query, "generic_data_table", {
+      dataSource: tavilyResponse.results
+    });
+  }
+);
+
+// src/agent_lattice/types.ts
+var import_protocols = require("@axiom-lattice/protocols");
+
+// src/agent_lattice/builders/ReActAgentGraphBuilder.ts
+var import_prebuilt = require("@langchain/langgraph/prebuilt");
+var ReActAgentGraphBuilder = class {
+  /**
+   * 构建ReAct Agent Graph
+   *
+   * @param agentLattice Agent Lattice对象
+   * @param params Agent构建参数
+   * @returns 返回CompiledGraph对象
+   */
+  build(agentLattice, params) {
+    const tools = params.tools.map((t) => {
+      const tool5 = getToolClient(t.key);
+      return tool5;
+    }).filter((tool5) => tool5 !== void 0);
+    return (0, import_prebuilt.createReactAgent)({
+      llm: params.model,
+      tools,
+      prompt: params.prompt,
+      name: agentLattice.config.name
+    });
+  }
+};
+
+// src/deep_agent/subAgent.ts
+var import_tools3 = require("@langchain/core/tools");
+var import_messages2 = require("@langchain/core/messages");
+var import_langgraph2 = require("@langchain/langgraph");
+var import_prebuilt2 = require("@langchain/langgraph/prebuilt");
+var import_zod4 = require("zod");
+
+// src/deep_agent/tools.ts
+var import_tools2 = require("@langchain/core/tools");
+var import_messages = require("@langchain/core/messages");
+var import_langgraph = require("@langchain/langgraph");
+var import_zod3 = require("zod");
+
+// src/deep_agent/prompts.ts
+var WRITE_TODOS_DESCRIPTION = `Use this tool to create and manage a structured task list for your current work 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:
+
+Complex multi-step tasks - When a task requires 3 or more distinct steps or actions
+Non-trivial and complex tasks - Tasks that require careful planning or multiple operations
+User explicitly requests todo list - When the user directly asks you to use the todo list
+User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)
+After receiving new instructions - Immediately capture user requirements as todos
+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
+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:
+
+There is only a single, straightforward task
+The task is trivial and tracking it provides no organizational benefit
+The task can be completed in less than 3 trivial steps
+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 plan a comprehensive marketing campaign for our new product launch, including social media, email marketing, and press releases.
+Assistant: I'll help you plan a comprehensive marketing campaign for your product launch. Let me create a todo list to organize all the components.
+*Creates todo list with the following items:*
+1. Define target audience and key messaging
+2. Create social media content calendar and posting schedule
+3. Design email marketing sequence and automation flows
+4. Draft press release and identify media contacts
+5. Set up tracking and analytics for campaign performance
+6. Create visual assets and brand materials
+7. Coordinate launch timeline and deliverables
+*Begins working on the first task*
+<reasoning>
+The assistant used the todo list because:
+1. Marketing campaign planning involves multiple distinct channels and activities
+2. Each component requires careful coordination and planning
+3. The systematic approach ensures all aspects of the launch are covered
+4. Progress tracking helps maintain timeline and deliverables
+</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 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 consistency
+</reasoning>
+</example>
+<example>
+User: I need help organizing my home office: decluttering the desk, setting up a filing system, organizing digital files, and creating a daily workflow.
+Assistant: I'll help you organize your home office systematically. Let me create a todo list to track each area of organization.
+*Creates todo list with items like: 1) Sort and declutter desk items, 2) Set up physical filing system for documents, 3) Organize digital files and folders, 4) Create daily workflow and productivity systems, 5) Establish maintenance routines*
+Let's start with decluttering your desk space to create a clean foundation for the other organizational systems.
+<reasoning>
+The assistant used the todo list because:
+1. The user provided multiple distinct organizational tasks
+2. Each area requires different approaches and careful planning
+3. Home organization benefits from systematic, step-by-step completion
+4. Progress tracking ensures all areas are addressed thoroughly
+</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.
+<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's the best way to water houseplants?
+Assistant: The best way to water houseplants depends on the specific plant type, but here are some general guidelines:
+
+Check soil moisture by inserting your finger about 1-2 inches into the soil
+Water thoroughly when the top inch feels dry, allowing water to drain from the bottom
+Use room temperature water and water in the morning when possible
+Avoid overwatering, which is more harmful than underwatering for most plants
+
+Different plants have different needs, so it's important to research your specific varieties for optimal care.
+
+<reasoning>
+The assistant did not use the todo list because this is an informational request with no actual tasks to complete. The user is simply asking for advice and explanation, not for the assistant to perform multiple steps or activities.
+</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. Adding a comment doesn't require tracking multiple steps or systematic organization.
+</reasoning>
+</example>
+<example>
+User: What time is it in Tokyo right now?
+Assistant: I'll check the current time in Tokyo for you.
+
+*Searches for current time in Tokyo*
+
+The current time in Tokyo, Japan is [current time]. Tokyo is in the Japan Standard Time (JST) zone, which is UTC+9.
+
+<reasoning>
+The assistant did not use the todo list because this is a single information lookup with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward request.
+</reasoning>
+</example>
+Task States and Management
+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
+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
+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:
+There are unresolved issues or errors
+Work is partial or incomplete
+You encountered blockers that prevent completion
+You couldn't find necessary resources or dependencies
+Quality standards haven't been met
+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.`;
+var TASK_DESCRIPTION_PREFIX = `Launch a new agent to handle complex, multi-step tasks autonomously.
+
+Available agent types and the tools they have access to:
+
+general-purpose: General-purpose agent for researching complex questions, searching for files and content, and executing multi-step tasks. When you are searching for a keyword or file and are not confident that you will find the right match in the first few tries use this agent to perform the search for you. (Tools: *)
+{other_agents}
+`;
+var TASK_DESCRIPTION_SUFFIX = `When using the Task tool, you must specify a subagent_type parameter to select which agent type to use.
+
+When to use the Agent tool:
+
+When you are instructed to execute custom slash commands. Use the Agent tool with the slash command invocation as the entire prompt. The slash command can take arguments. For example: Task(description="Check the file", prompt="/check-file path/to/file.py")
+When NOT to use the Agent tool:
+
+If you want to read a specific file path, use the Read or Glob tool instead of the Agent tool, to find the match more quickly
+If you are searching for a specific term or definition within a known location, use the Glob tool instead, to find the match more quickly
+If you are searching for content within a specific file or set of 2-3 files, use the Read tool instead of the Agent tool, to find the match more quickly
+Other tasks that are not related to the agent descriptions above
+Usage notes:
+
+Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses
+When the agent is done, it will return a single message back to you. The result returned by the agent is not visible to the user. To show the user the result, you should send a text message back to the user with a concise summary of the result.
+Each agent invocation is stateless. You will not be able to send additional messages to the agent, nor will the agent be able to communicate with you outside of its final report. Therefore, your prompt should contain a highly detailed task description for the agent to perform autonomously and you should specify exactly what information the agent should return back to you in its final and only message to you.
+The agent's outputs should generally be trusted
+Clearly tell the agent whether you expect it to create content, perform analysis, or just do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent
+If the agent description mentions that it should be used proactively, then you should try your best to use it without the user having to ask for it first. Use your judgement.
+Example usage:
+
+<example_agent_descriptions>
+"content-reviewer": use this agent after you are done creating significant content or documents
+"greeting-responder": use this agent when to respond to user greetings with a friendly joke
+"research-analyst": use this agent to conduct thorough research on complex topics
+</example_agent_description>
+
+<example>
+user: "Please write a function that checks if a number is prime"
+assistant: Sure let me write a function that checks if a number is prime
+assistant: First let me use the Write tool to write a function that checks if a number is prime
+assistant: I'm going to use the Write tool to write the following code:
+<code>
+function isPrime(n) {
+  if (n <= 1) return false
+  for (let i = 2; i * i <= n; i++) {
+    if (n % i === 0) return false
+  }
+  return true
+}
+</code>
+<commentary>
+Since significant content was created and the task was completed, now use the content-reviewer agent to review the work
+</commentary>
+assistant: Now let me use the content-reviewer agent to review the code
+assistant: Uses the Task tool to launch with the content-reviewer agent
+</example>
+<example>
+user: "Can you help me research the environmental impact of different renewable energy sources and create a comprehensive report?"
+<commentary>
+This is a complex research task that would benefit from using the research-analyst agent to conduct thorough analysis
+</commentary>
+assistant: I'll help you research the environmental impact of renewable energy sources. Let me use the research-analyst agent to conduct comprehensive research on this topic.
+assistant: Uses the Task tool to launch with the research-analyst agent, providing detailed instructions about what research to conduct and what format the report should take
+</example>
+<example>
+user: "Hello"
+<commentary>
+Since the user is greeting, use the greeting-responder agent to respond with a friendly joke
+</commentary>
+assistant: "I'm going to use the Task tool to launch with the greeting-responder agent"
+</example>`;
+var EDIT_DESCRIPTION = `Performs exact string replacements in files.
+Usage:
+
+You must use your Read tool at least once in the conversation before editing. This tool will error if you attempt an edit without reading the file.
+When editing text from Read tool output, ensure you preserve the exact indentation (tabs/spaces) as it appears AFTER the line number prefix. The line number prefix format is: spaces + line number + tab. Everything after that tab is the actual file content to match. Never include any part of the line number prefix in the old_string or new_string.
+ALWAYS prefer editing existing files. NEVER write new files unless explicitly required.
+Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.
+The edit will FAIL if old_string is not unique in the file. Either provide a larger string with more surrounding context to make it unique or use replace_all to change every instance of old_string.
+Use replace_all for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.`;
+var TOOL_DESCRIPTION = `Reads a file from the local filesystem. You can access any file directly by using this tool. Assume this tool is able to read all files on the machine. If the User provides a path to a file assume that path is valid. It is okay to read a file that does not exist; an error will be returned.
+Usage:
+
+The file_path parameter must be an absolute path, not a relative path
+By default, it reads up to 2000 lines starting from the beginning of the file
+You can optionally specify a line offset and limit (especially handy for long files), but it's recommended to read the whole file by not providing these parameters
+Any lines longer than 2000 characters will be truncated
+Results are returned using cat -n format, with line numbers starting at 1
+You have the capability to call multiple tools in a single response. It is always better to speculatively read multiple files as a batch that are potentially useful.
+If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents.`;
+
+// src/deep_agent/tools.ts
+var writeTodos = (0, import_tools2.tool)(
+  (input, config) => {
+    return new import_langgraph.Command({
+      update: {
+        todos: input.todos,
+        messages: [
+          new import_messages.ToolMessage({
+            content: `Updated todo list to ${JSON.stringify(input.todos)}`,
+            tool_call_id: config.toolCall?.id
+          })
+        ]
+      }
+    });
+  },
+  {
+    name: "write_todos",
+    description: WRITE_TODOS_DESCRIPTION,
+    schema: import_zod3.z.object({
+      todos: import_zod3.z.array(
+        import_zod3.z.object({
+          content: import_zod3.z.string().describe("Content of the todo item"),
+          status: import_zod3.z.enum(["pending", "in_progress", "completed"]).describe("Status of the todo")
+        })
+      ).describe("List of todo items to update")
+    })
+  }
+);
+var ls = (0, import_tools2.tool)(
+  () => {
+    const state = (0, import_langgraph.getCurrentTaskInput)();
+    const files = state.files || {};
+    return Object.keys(files);
+  },
+  {
+    name: "ls",
+    description: "List all files in the mock filesystem",
+    schema: import_zod3.z.object({})
+  }
+);
+var readFile = (0, import_tools2.tool)(
+  (input) => {
+    const state = (0, import_langgraph.getCurrentTaskInput)();
+    const mockFilesystem = state.files || {};
+    const { file_path, offset = 0, limit = 2e3 } = input;
+    if (!(file_path in mockFilesystem)) {
+      return `Error: File '${file_path}' not found`;
+    }
+    const content = mockFilesystem[file_path];
+    if (!content || content.trim() === "") {
+      return "System reminder: File exists but has empty contents";
+    }
+    const lines = content.split("\n");
+    const startIdx = offset;
+    const endIdx = Math.min(startIdx + limit, lines.length);
+    if (startIdx >= lines.length) {
+      return `Error: Line offset ${offset} exceeds file length (${lines.length} lines)`;
+    }
+    const resultLines = [];
+    for (let i = startIdx; i < endIdx; i++) {
+      let lineContent = lines[i];
+      if (lineContent.length > 2e3) {
+        lineContent = lineContent.substring(0, 2e3);
+      }
+      const lineNumber = i + 1;
+      resultLines.push(`${lineNumber.toString().padStart(6)}	${lineContent}`);
+    }
+    return resultLines.join("\n");
+  },
+  {
+    name: "read_file",
+    description: TOOL_DESCRIPTION,
+    schema: import_zod3.z.object({
+      file_path: import_zod3.z.string().describe("Absolute path to the file to read"),
+      offset: import_zod3.z.number().optional().default(0).describe("Line offset to start reading from"),
+      limit: import_zod3.z.number().optional().default(2e3).describe("Maximum number of lines to read")
+    })
+  }
+);
+var writeFile = (0, import_tools2.tool)(
+  (input, config) => {
+    const state = (0, import_langgraph.getCurrentTaskInput)();
+    const files = { ...state.files || {} };
+    files[input.file_path] = input.content;
+    return new import_langgraph.Command({
+      update: {
+        files,
+        messages: [
+          new import_messages.ToolMessage({
+            content: `Updated file ${input.file_path}`,
+            tool_call_id: config.toolCall?.id
+          })
+        ]
+      }
+    });
+  },
+  {
+    name: "write_file",
+    description: "Write content to a file in the mock filesystem",
+    schema: import_zod3.z.object({
+      file_path: import_zod3.z.string().describe("Absolute path to the file to write"),
+      content: import_zod3.z.string().describe("Content to write to the file")
+    })
+  }
+);
+var editFile = (0, import_tools2.tool)(
+  (input, config) => {
+    const state = (0, import_langgraph.getCurrentTaskInput)();
+    const mockFilesystem = { ...state.files || {} };
+    const { file_path, old_string, new_string, replace_all = false } = input;
+    if (!(file_path in mockFilesystem)) {
+      return `Error: File '${file_path}' not found`;
+    }
+    const content = mockFilesystem[file_path];
+    if (!content.includes(old_string)) {
+      return `Error: String not found in file: '${old_string}'`;
+    }
+    if (!replace_all) {
+      const escapedOldString = old_string.replace(
+        /[.*+?^${}()|[\]\\]/g,
+        "\\$&"
+      );
+      const occurrences = (content.match(new RegExp(escapedOldString, "g")) || []).length;
+      if (occurrences > 1) {
+        return `Error: String '${old_string}' appears ${occurrences} times in file. Use replace_all=True to replace all instances, or provide a more specific string with surrounding context.`;
+      } else if (occurrences === 0) {
+        return `Error: String not found in file: '${old_string}'`;
+      }
+    }
+    let newContent;
+    if (replace_all) {
+      const escapedOldString = old_string.replace(
+        /[.*+?^${}()|[\]\\]/g,
+        "\\$&"
+      );
+      newContent = content.replace(
+        new RegExp(escapedOldString, "g"),
+        new_string
+      );
+    } else {
+      newContent = content.replace(old_string, new_string);
+    }
+    mockFilesystem[file_path] = newContent;
+    return new import_langgraph.Command({
+      update: {
+        files: mockFilesystem,
+        messages: [
+          new import_messages.ToolMessage({
+            content: `Updated file ${file_path}`,
+            tool_call_id: config.toolCall?.id
+          })
+        ]
+      }
+    });
+  },
+  {
+    name: "edit_file",
+    description: EDIT_DESCRIPTION,
+    schema: import_zod3.z.object({
+      file_path: import_zod3.z.string().describe("Absolute path to the file to edit"),
+      old_string: import_zod3.z.string().describe("String to be replaced (must match exactly)"),
+      new_string: import_zod3.z.string().describe("String to replace with"),
+      replace_all: import_zod3.z.boolean().optional().default(false).describe("Whether to replace all occurrences")
+    })
+  }
+);
+
+// src/deep_agent/subAgent.ts
+var BUILTIN_TOOLS = {
+  write_todos: writeTodos,
+  read_file: readFile,
+  write_file: writeFile,
+  edit_file: editFile,
+  ls
+};
+function createTaskTool(inputs) {
+  const {
+    subagents,
+    tools = {},
+    model = getModelLattice("default")?.client,
+    stateSchema
+  } = inputs;
+  if (!model) {
+    throw new Error("Model not found");
+  }
+  const allTools = { ...BUILTIN_TOOLS, ...tools };
+  const agentsMap = /* @__PURE__ */ new Map();
+  for (const subagent of subagents) {
+    const subagentTools = [];
+    if (subagent.tools) {
+      for (const toolName of subagent.tools) {
+        const resolvedTool = allTools[toolName];
+        if (resolvedTool) {
+          subagentTools.push(resolvedTool);
+        } else {
+          console.warn(
+            `Warning: Tool '${toolName}' not found for agent '${subagent.name}'`
+          );
+        }
+      }
+    } else {
+      subagentTools.push(...Object.values(allTools));
+    }
+    const reactAgent = (0, import_prebuilt2.createReactAgent)({
+      llm: model,
+      tools: subagentTools,
+      stateSchema,
+      messageModifier: subagent.prompt,
+      checkpointer: false
+    });
+    agentsMap.set(subagent.name, reactAgent);
+  }
+  return (0, import_tools3.tool)(
+    async (input, config) => {
+      const { description, subagent_type } = input;
+      const reactAgent = agentsMap.get(subagent_type);
+      if (!reactAgent) {
+        return `Error: Agent '${subagent_type}' not found. Available agents: ${Array.from(
+          agentsMap.keys()
+        ).join(", ")}`;
+      }
+      try {
+        const currentState = (0, import_langgraph2.getCurrentTaskInput)();
+        const modifiedState = {
+          ...currentState,
+          messages: [
+            {
+              role: "user",
+              content: description
+            }
+          ]
+        };
+        const result = await reactAgent.invoke(modifiedState, config);
+        return new import_langgraph2.Command({
+          update: {
+            files: result.files || {},
+            messages: [
+              new import_messages2.ToolMessage({
+                content: result.messages?.slice(-1)[0]?.content || "Task completed",
+                tool_call_id: config.toolCall?.id
+              })
+            ]
+          }
+        });
+      } catch (error) {
+        if (error instanceof import_langgraph2.GraphInterrupt) {
+          throw error;
+        }
+        const errorMessage = error instanceof Error ? error.message : String(error);
+        return new import_langgraph2.Command({
+          update: {
+            messages: [
+              new import_messages2.ToolMessage({
+                content: `Error executing task '${description}' with agent '${subagent_type}': ${errorMessage}`,
+                tool_call_id: config.toolCall?.id
+              })
+            ]
+          }
+        });
+      }
+    },
+    {
+      name: "task",
+      description: TASK_DESCRIPTION_PREFIX.replace(
+        "{other_agents}",
+        subagents.map((a) => `- ${a.name}: ${a.description}`).join("\n")
+      ) + TASK_DESCRIPTION_SUFFIX,
+      schema: import_zod4.z.object({
+        description: import_zod4.z.string().describe("The task to execute with the selected agent"),
+        subagent_type: import_zod4.z.string().describe(
+          `Name of the agent to use. Available: ${subagents.map((a) => a.name).join(", ")}`
+        )
+      })
+    }
+  );
+}
+
+// src/deep_agent/state.ts
+var import_zod5 = require("@langchain/langgraph/zod");
+var import_langgraph3 = require("@langchain/langgraph");
+var import_zod6 = require("@langchain/langgraph/zod");
+var import_zod7 = require("zod");
+function fileReducer(left, right) {
+  if (left == null) {
+    return right || {};
+  } else if (right == null) {
+    return left;
+  } else {
+    return { ...left, ...right };
+  }
+}
+function todoReducer(left, right) {
+  if (right != null) {
+    return right;
+  }
+  return left || [];
+}
+var DeepAgentState = import_langgraph3.MessagesZodState.extend({
+  todos: (0, import_zod6.withLangGraph)(import_zod7.z.custom(), {
+    reducer: {
+      schema: import_zod7.z.custom(),
+      fn: todoReducer
+    }
+  }),
+  files: (0, import_zod6.withLangGraph)(import_zod7.z.custom(), {
+    reducer: {
+      schema: import_zod7.z.custom(),
+      fn: fileReducer
+    }
+  })
+});
+
+// src/deep_agent/graph.ts
+var import_prebuilt3 = require("@langchain/langgraph/prebuilt");
+
+// src/memory_lattice/MemoryLatticeManager.ts
+var import_protocols2 = require("@axiom-lattice/protocols");
+var _MemoryLatticeManager = class _MemoryLatticeManager extends BaseLatticeManager {
+  /**
+   * 私有构造函数，防止外部直接实例化
+   */
+  constructor() {
+    super();
+  }
+  /**
+   * 获取单例实例
+   */
+  static getInstance() {
+    if (!_MemoryLatticeManager.instance) {
+      _MemoryLatticeManager.instance = new _MemoryLatticeManager();
+    }
+    return _MemoryLatticeManager.instance;
+  }
+  /**
+   * 获取Lattice类型
+   */
+  getLatticeType() {
+    return "memory";
+  }
+  /**
+   * 注册检查点保存器
+   * @param key 保存器键名
+   * @param saver 检查点保存器实例
+   */
+  registerCheckpointSaver(key, saver) {
+    if (_MemoryLatticeManager.checkpointSavers.has(key)) {
+      throw new Error(`\u68C0\u67E5\u70B9\u4FDD\u5B58\u5668 "${key}" \u5DF2\u7ECF\u5B58\u5728\uFF0C\u65E0\u6CD5\u91CD\u590D\u6CE8\u518C`);
+    }
+    _MemoryLatticeManager.checkpointSavers.set(key, saver);
+  }
+  /**
+   * 获取检查点保存器
+   * @param key 保存器键名
+   */
+  getCheckpointSaver(key) {
+    const saver = _MemoryLatticeManager.checkpointSavers.get(key);
+    if (!saver) {
+      throw new Error(`\u68C0\u67E5\u70B9\u4FDD\u5B58\u5668 "${key}" \u4E0D\u5B58\u5728`);
+    }
+    return saver;
+  }
+  /**
+   * 获取所有已注册的检查点保存器键名
+   */
+  getCheckpointSaverKeys() {
+    return Array.from(_MemoryLatticeManager.checkpointSavers.keys());
+  }
+  /**
+   * 检查检查点保存器是否存在
+   * @param key 保存器键名
+   */
+  hasCheckpointSaver(key) {
+    return _MemoryLatticeManager.checkpointSavers.has(key);
+  }
+  /**
+   * 移除检查点保存器
+   * @param key 保存器键名
+   */
+  removeCheckpointSaver(key) {
+    return _MemoryLatticeManager.checkpointSavers.delete(key);
+  }
+};
+// 检查点保存器注册表
+_MemoryLatticeManager.checkpointSavers = /* @__PURE__ */ new Map();
+var MemoryLatticeManager = _MemoryLatticeManager;
+var getCheckpointSaver = (key) => MemoryLatticeManager.getInstance().getCheckpointSaver(key);
+var registerCheckpointSaver = (key, saver) => MemoryLatticeManager.getInstance().registerCheckpointSaver(key, saver);
+
+// src/deep_agent/graph.ts
+var BASE_PROMPT = `You have access to a number of standard tools
+
+## \`write_todos\`
+
+You have access to the \`write_todos\` tools to help you manage and plan tasks. Use these tools VERY frequently to ensure that you are tracking your tasks and giving the user visibility into your progress.
+These tools are also EXTREMELY helpful for planning tasks, and for breaking down larger complex tasks into smaller steps. If you do not use this tool when planning, you may forget to do important tasks - and that is unacceptable.
+
+It is critical that you mark todos as completed as soon as you are done with a task. Do not batch up multiple tasks before marking them as completed.
+## \`task\`
+
+- When doing web search, prefer to use the \`task\` tool in order to reduce context usage.`;
+var BUILTIN_TOOLS2 = [
+  writeTodos,
+  readFile,
+  writeFile,
+  editFile,
+  ls
+];
+function createDeepAgent(params = {}) {
+  const {
+    tools = [],
+    instructions,
+    model = getModelLattice("default")?.client,
+    subagents = []
+  } = params;
+  if (!model) {
+    throw new Error("Model not found");
+  }
+  const stateSchema = params.stateSchema ? DeepAgentState.extend(params.stateSchema.shape) : DeepAgentState;
+  const allTools = [...BUILTIN_TOOLS2, ...tools];
+  if (subagents.length > 0) {
+    const toolsMap = {};
+    for (const tool5 of allTools) {
+      if (tool5.name) {
+        toolsMap[tool5.name] = tool5;
+      }
+    }
+    const taskTool = createTaskTool({
+      subagents,
+      tools: toolsMap,
+      model,
+      stateSchema
+    });
+    allTools.push(taskTool);
+  }
+  const finalInstructions = instructions ? instructions + BASE_PROMPT : BASE_PROMPT;
+  return (0, import_prebuilt3.createReactAgent)({
+    llm: model,
+    tools: allTools,
+    stateSchema,
+    prompt: finalInstructions,
+    checkpointer: getCheckpointSaver("default")
+  });
+}
+
+// src/agent_lattice/builders/DeepAgentGraphBuilder.ts
+var DeepAgentGraphBuilder = class {
+  /**
+   * 构建Deep Agent Graph
+   *
+   * @param agentLattice Agent Lattice对象
+   * @param params Agent构建参数
+   * @returns 返回CompiledGraph对象
+   */
+  build(agentLattice, params) {
+    const tools = params.tools.map((t) => {
+      const toolClient = getToolClient(t.key);
+      return toolClient;
+    }).filter((tool5) => tool5 !== void 0);
+    return createDeepAgent({
+      tools,
+      model: params.model,
+      instructions: params.prompt,
+      subagents: params.subAgents.map((sa) => ({
+        name: sa.key,
+        description: sa.config.description,
+        prompt: sa.config.prompt,
+        tools: sa.config.tools || []
+      }))
+    });
+  }
+};
+
+// src/createPlanExecuteAgent.ts
+var import_langgraph5 = require("@langchain/langgraph");
+var import_messages6 = require("@langchain/core/messages");
+var import_zod8 = require("zod");
+
+// src/logger/Logger.ts
+var import_pino = __toESM(require("pino"));
+var import_pino_pretty = require("pino-pretty");
+var import_pino_roll = require("pino-roll");
+var PinoLoggerFactory = class _PinoLoggerFactory {
+  constructor() {
+    const isProd = process.env.NODE_ENV === "production";
+    const loggerConfig = {
+      // 自定义时间戳格式
+      timestamp: () => `,"@timestamp":"${(/* @__PURE__ */ new Date()).toISOString()}"`,
+      // 关闭默认的时间戳键
+      base: {
+        "@version": "1",
+        app_name: "lattice",
+        service_name: "lattice/graph-server",
+        thread_name: "main",
+        logger_name: "lattice-graph-logger"
+      },
+      formatters: {
+        level: (label, number) => {
+          return {
+            level: label.toUpperCase(),
+            level_value: number * 1e3
+          };
+        }
+      }
+    };
+    if (isProd) {
+      try {
+        this.pinoLogger = (0, import_pino.default)(
+          loggerConfig,
+          import_pino.default.transport({
+            target: "pino-roll",
+            options: {
+              file: "./logs/fin_ai_graph_server",
+              frequency: "daily",
+              mkdir: true
+            }
+          })
+        );
+      } catch (error) {
+        console.error(
+          "\u65E0\u6CD5\u521D\u59CB\u5316 pino-roll \u65E5\u5FD7\u8BB0\u5F55\u5668\uFF0C\u56DE\u9000\u5230\u63A7\u5236\u53F0\u65E5\u5FD7",
+          error
+        );
+        this.pinoLogger = (0, import_pino.default)({
+          ...loggerConfig,
+          transport: {
+            target: "pino-pretty",
+            options: {
+              colorize: true
+            }
+          }
+        });
+      }
+    } else {
+      this.pinoLogger = (0, import_pino.default)({
+        ...loggerConfig,
+        transport: {
+          target: "pino-pretty",
+          options: {
+            colorize: true
+          }
+        }
+      });
+    }
+  }
+  static getInstance() {
+    if (!_PinoLoggerFactory.instance) {
+      _PinoLoggerFactory.instance = new _PinoLoggerFactory();
+    }
+    return _PinoLoggerFactory.instance;
+  }
+  getPinoLogger() {
+    return this.pinoLogger;
+  }
+};
+var Logger = class _Logger {
+  constructor(options) {
+    this.context = options?.context || {};
+    this.name = options?.name || "lattice-graph-logger";
+    this.serviceName = options?.serviceName || "lattice/graph-server";
+  }
+  /**
+   * 获取合并了上下文的日志对象
+   * @param additionalContext 额外的上下文数据
+   * @returns 带有上下文的pino日志对象
+   */
+  getContextualLogger(additionalContext) {
+    const pinoLogger = PinoLoggerFactory.getInstance().getPinoLogger();
+    const contextObj = {
+      "x-user-id": this.context["x-user-id"] || "",
+      "x-tenant-id": this.context["x-tenant-id"] || "",
+      "x-request-id": this.context["x-request-id"] || "",
+      "x-task-id": this.context["x-task-id"] || "",
+      "x-thread-id": this.context["x-thread-id"] || "",
+      service_name: this.serviceName,
+      logger_name: this.name,
+      ...additionalContext
+    };
+    return pinoLogger.child(contextObj);
+  }
+  info(msg, obj) {
+    this.getContextualLogger(obj).info(msg);
+  }
+  error(msg, obj) {
+    this.getContextualLogger(obj).error(msg);
+  }
+  warn(msg, obj) {
+    this.getContextualLogger(obj).warn(msg);
+  }
+  debug(msg, obj) {
+    this.getContextualLogger(obj).debug(msg);
+  }
+  /**
+   * 更新Logger实例的上下文
+   */
+  updateContext(context) {
+    this.context = {
+      ...this.context,
+      ...context
+    };
+  }
+  /**
+   * 创建一个新的Logger实例，继承当前Logger的上下文
+   */
+  child(options) {
+    return new _Logger({
+      name: options.name || this.name,
+      serviceName: options.serviceName || this.serviceName,
+      context: {
+        ...this.context,
+        ...options.context
+      }
+    });
+  }
+};
+
+// src/util/returnToolResponse.ts
+var import_messages3 = require("@langchain/core/messages");
+var import_uuid = require("uuid");
+
+// src/util/genUIMarkdown.ts
+var genUIMarkdown = (type, data) => {
+  return ["```" + type, JSON.stringify(data), "```"].join("\n");
+};
+
+// src/util/returnToolResponse.ts
+var returnToolResponse = (config, think) => {
+  const { think_id = (0, import_uuid.v4)(), content, title, status, type, data } = think;
+  const contents = type ? [title, content, genUIMarkdown(type, data)] : [title, content];
+  const message = {
+    messages: [
+      new import_messages3.ToolMessage({
+        content: contents.filter((item) => item).join("\n\n"),
+        tool_call_id: config.configurable?.run_id + "_tool_" + think_id,
+        status: status || "success"
+      })
+    ]
+  };
+  return message;
+};
+
+// src/util/returnAIResponse.ts
+var import_messages4 = require("@langchain/core/messages");
+var returnAIResponse = (config, content, type, data) => {
+  const contents = type ? [content, genUIMarkdown(type, data)].join("\n") : content;
+  const message = {
+    messages: [
+      new import_messages4.AIMessage({
+        content: contents
+      })
+      // {
+      //   id: v4(),
+      //   role: "ai",
+      //   content: contents,
+      //   type: "message",
+      // }, // 旧的message
+    ]
+  };
+  return message;
+};
+
+// src/util/getLastHumanMessageData.ts
+var import_messages5 = require("@langchain/core/messages");
+var getLastHumanMessageData = (messages) => {
+  for (let i = messages.length - 1; i >= 0; i--) {
+    const message = messages[i];
+    if ((0, import_messages5.isHumanMessage)(message)) {
+      const files = message?.additional_kwargs?.files;
+      return {
+        files,
+        content: message?.content
+      };
+    }
+  }
+  return null;
+};
+
+// src/createPlanExecuteAgent.ts
+var import_tools7 = require("@langchain/core/tools");
+
+// src/util/PGMemory.ts
+var import_langgraph4 = require("@langchain/langgraph");
+var import_langgraph_checkpoint_postgres = require("@langchain/langgraph-checkpoint-postgres");
+var globalMemory = import_langgraph_checkpoint_postgres.PostgresSaver.fromConnString(process.env.DATABASE_URL);
+var memory = new import_langgraph4.MemorySaver();
+var _MemoryManager = class _MemoryManager {
+  static getInstance() {
+    return _MemoryManager.instance;
+  }
+};
+_MemoryManager.instance = memory;
+var MemoryManager = _MemoryManager;
+
+// src/createPlanExecuteAgent.ts
+var import_prebuilt4 = require("@langchain/langgraph/prebuilt");
+var PlanExecuteState = import_langgraph5.Annotation.Root({
+  // 输入
+  input: (0, import_langgraph5.Annotation)({
+    reducer: (x, y) => y ?? x ?? ""
+  }),
+  // 计划步骤列表
+  plan: (0, import_langgraph5.Annotation)({
+    reducer: (x, y) => y ?? x ?? []
+  }),
+  // 已执行的步骤 [步骤名称, 执行结果]
+  pastSteps: (0, import_langgraph5.Annotation)({
+    reducer: (x, y) => x.concat(y),
+    default: () => []
+  }),
+  // 最终响应
+  response: (0, import_langgraph5.Annotation)({
+    reducer: (x, y) => y ?? x
+  }),
+  // 错误信息
+  error: (0, import_langgraph5.Annotation)({
+    reducer: (x, y) => y ?? x
+  }),
+  // 继承基础状态
+  "x-tenant-id": (0, import_langgraph5.Annotation)(),
+  messages: (0, import_langgraph5.Annotation)({
+    reducer: import_langgraph5.messagesStateReducer,
+    default: () => []
+  })
+});
+var planSchema = import_zod8.z.object({
+  steps: import_zod8.z.array(import_zod8.z.string()).describe("\u9700\u8981\u6267\u884C\u7684\u6B65\u9AA4\u5217\u8868\uFF0C\u5E94\u6309\u7167\u6267\u884C\u987A\u5E8F\u6392\u5E8F")
+});
+var responseSchema = import_zod8.z.object({
+  response: import_zod8.z.string().describe("\u7ED9\u7528\u6237\u7684\u6700\u7EC8\u54CD\u5E94\uFF0C\u5982\u679C\u4E0D\u9700\u8981\u6267\u884C\u6B65\u9AA4\uFF0C\u5219\u8FD4\u56DE\u8FD9\u4E2A\u5B57\u6BB5")
+});
+function createPlanExecuteAgent(config) {
+  const {
+    name,
+    description,
+    tools: executorTools = [],
+    checkpointer,
+    llmManager,
+    logger,
+    maxSteps = 10,
+    prompt
+  } = config;
+  const agentLogger = logger || new Logger({ name: `PlanExecuteAgent:${name}` });
+  const llm = llmManager || getModelLattice("default")?.client;
+  if (!llm) {
+    throw new Error("LLM not found");
+  }
+  agentLogger.info(`\u521D\u59CB\u5316Plan-Execute\u4EE3\u7406: ${name}`, {
+    description,
+    maxSteps,
+    toolsCount: executorTools.length
+  });
+  const agentExecutor = (0, import_prebuilt4.createReactAgent)({
+    tools: executorTools,
+    llm
+  });
+  async function planStep(state, config2) {
+    const input = state.input || getLastHumanMessageData(state.messages)?.content;
+    const plannerPrompt = `${prompt || ""}
+\u9488\u5BF9\u7ED9\u5B9A\u7684\u76EE\u6807\uFF0C\u5236\u5B9A\u4E00\u4E2A\u7B80\u5355\u7684\u5206\u6B65\u8BA1\u5212\u3002
+\u8FD9\u4E2A\u8BA1\u5212\u5E94\u8BE5\u5305\u542B\u72EC\u7ACB\u7684\u4EFB\u52A1\uFF0C\u5982\u679C\u6B63\u786E\u6267\u884C\u5C06\u4F1A\u5F97\u5230\u6B63\u786E\u7684\u7B54\u6848\u3002\u4E0D\u8981\u6DFB\u52A0\u591A\u4F59\u7684\u6B65\u9AA4\u3002
+\u6700\u540E\u4E00\u6B65\u7684\u7ED3\u679C\u5E94\u8BE5\u662F\u6700\u7EC8\u7B54\u6848\u3002\u786E\u4FDD\u6BCF\u4E00\u6B65\u90FD\u6709\u6240\u9700\u7684\u6240\u6709\u4FE1\u606F - \u4E0D\u8981\u8DF3\u8FC7\u6B65\u9AA4\u3002
+
+\u53EF\u4EE5\u4F7F\u7528\u7684\u5DE5\u5177\u5982\u4E0B\uFF1A
+${executorTools.map((tool5) => tool5.name).join("\n")}
+
+\u76EE\u6807: ${input}`;
+    try {
+      const planResult = await llm.invokeWithStructuredOutput(
+        [new import_messages6.HumanMessage(plannerPrompt)],
+        planSchema
+      );
+      const { messages } = await returnToolResponse(config2, {
+        title: "\u6211\u7684\u8BA1\u5212",
+        content: planResult.steps.map((step) => step).join("\n\n"),
+        status: "success"
+      });
+      agentLogger.info("\u8BA1\u5212\u5236\u5B9A\u5B8C\u6210", { plan: planResult.steps });
+      return {
+        input,
+        plan: planResult.steps,
+        error: void 0,
+        messages
+      };
+    } catch (error) {
+      const errorMsg = `\u8BA1\u5212\u5236\u5B9A\u5931\u8D25: ${error instanceof Error ? error.message : "\u672A\u77E5\u9519\u8BEF"}`;
+      agentLogger.error(errorMsg, { error });
+      return {
+        error: errorMsg
+      };
+    }
+  }
+  async function executeStep(state, config2) {
+    if (!state.plan || state.plan.length === 0) {
+      agentLogger.warn("\u6CA1\u6709\u53EF\u6267\u884C\u7684\u4EFB\u52A1");
+      return { error: "\u6CA1\u6709\u53EF\u6267\u884C\u7684\u4EFB\u52A1" };
+    }
+    const currentTask = state.plan[0];
+    agentLogger.info("\u5F00\u59CB\u6267\u884C\u4EFB\u52A1", { task: currentTask });
+    try {
+      const executorPrompt = `\u6267\u884C\u4EE5\u4E0B\u4EFB\u52A1\u5E76\u63D0\u4F9B\u7ED3\u679C\uFF1A
+
+\u4EFB\u52A1: ${currentTask}
+
+\u4E0A\u4E0B\u6587\u4FE1\u606F:
+- \u539F\u59CB\u76EE\u6807: ${state.input}
+- \u5DF2\u5B8C\u6210\u7684\u6B65\u9AA4: ${state.pastSteps.map(([step, result]) => `${step}: ${result}`).join("\n")}
+
+\u8BF7\u63D0\u4F9B\u6267\u884C\u6B64\u4EFB\u52A1\u7684\u8BE6\u7EC6\u7ED3\u679C\u3002`;
+      const executionResult = await agentExecutor.invoke({
+        messages: [new import_messages6.HumanMessage(executorPrompt)]
+      });
+      const resultContent = executionResult.messages[executionResult.messages.length - 1].content;
+      return {
+        pastSteps: [[currentTask, resultContent]],
+        plan: state.plan.slice(1),
+        // 移除已执行的任务
+        //messages,
+        error: void 0
+      };
+    } catch (error) {
+      if (error instanceof import_langgraph5.GraphInterrupt) {
+        throw error;
+      }
+      const errorMsg = `\u4EFB\u52A1\u6267\u884C\u5931\u8D25: ${error instanceof Error ? error.message : "\u672A\u77E5\u9519\u8BEF"}`;
+      agentLogger.error(errorMsg, { task: currentTask, error });
+      return {
+        error: errorMsg
+        //messages,
+      };
+    }
+  }
+  const responseTool = (0, import_tools7.tool)(
+    ({ response }) => {
+      return response;
+    },
+    {
+      name: "response",
+      description: "Respond to the user.",
+      schema: responseSchema,
+      returnDirect: true
+    }
+  );
+  const planTool = (0, import_tools7.tool)(
+    ({ steps }) => {
+      return steps.join("\n\n");
+    },
+    {
+      name: "plan",
+      description: "This tool is used to plan the steps to follow.",
+      schema: planSchema,
+      returnDirect: true
+    }
+  );
+  const replanAgent = (0, import_prebuilt4.createReactAgent)({
+    tools: [responseTool, planTool],
+    llm
+  });
+  async function replanStep(state, config2) {
+    agentLogger.info("\u5F00\u59CB\u91CD\u65B0\u89C4\u5212");
+    const replannerPrompt = `${prompt || ""}
+\u9488\u5BF9\u7ED9\u5B9A\u7684\u76EE\u6807\uFF0C\u6839\u636E\u5DF2\u6267\u884C\u7684\u6B65\u9AA4\u6765\u66F4\u65B0\u8BA1\u5212\u3002
+\u8FD9\u4E2A\u8BA1\u5212\u5E94\u8BE5\u5305\u542B\u72EC\u7ACB\u7684\u4EFB\u52A1\uFF0C\u5982\u679C\u6B63\u786E\u6267\u884C\u5C06\u4F1A\u5F97\u5230\u6B63\u786E\u7684\u7B54\u6848\u3002\u4E0D\u8981\u6DFB\u52A0\u591A\u4F59\u7684\u6B65\u9AA4\u3002
+\u6700\u540E\u4E00\u6B65\u7684\u7ED3\u679C\u5E94\u8BE5\u662F\u6700\u7EC8\u7B54\u6848\u3002\u786E\u4FDD\u6BCF\u4E00\u6B65\u90FD\u6709\u6240\u9700\u7684\u6240\u6709\u4FE1\u606F - \u4E0D\u8981\u8DF3\u8FC7\u6B65\u9AA4\u3002
+
+\u4F60\u7684\u76EE\u6807\u662F\uFF1A
+${state.input}
+
+\u4F60\u7684\u539F\u59CB\u8BA1\u5212\u662F\uFF1A
+${state.plan.join("\n")}
+
+\u4F60\u76EE\u524D\u5DF2\u7ECF\u5B8C\u6210\u4E86\u4EE5\u4E0B\u6B65\u9AA4\uFF1A
+${state.pastSteps.map(([step, result]) => `${step}: ${result}`).join("\n")}
+
+Update your plan accordingly. If no more steps are needed and you can return to the user, then respond with that and use the 'response' function.
+Otherwise, fill out the plan.
+Only add steps to the plan that still NEED to be done. Do not return previously done steps as part of the plan.`;
+    try {
+      const responseResult = await replanAgent.invoke({
+        messages: [new import_messages6.HumanMessage(replannerPrompt)]
+      });
+      const toolCall = responseResult.messages[responseResult.messages.length - 1];
+      if (toolCall?.name == "response") {
+        agentLogger.info("\u4EFB\u52A1\u5B8C\u6210\uFF0C\u63D0\u4F9B\u6700\u7EC8\u54CD\u5E94");
+        const { messages } = await returnAIResponse(
+          config2,
+          toolCall.content
+        );
+        return {
+          response: toolCall.content,
+          messages,
+          error: void 0
+        };
+      } else if (toolCall?.name == "plan") {
+        let messages = [];
+        if (toolCall.content?.length > 0) {
+          messages = await returnToolResponse(config2, {
+            title: "\u65B0\u7684\u8BA1\u5212",
+            content: toolCall.content,
+            status: "success"
+          }).messages;
+        }
+        agentLogger.info("\u8BA1\u5212\u66F4\u65B0\u5B8C\u6210", { newPlan: toolCall.content });
+        return {
+          messages,
+          plan: toolCall.content.split("\n\n"),
+          error: void 0
+        };
+      } else {
+        return {
+          error: "\u91CD\u65B0\u89C4\u5212\u5931\u8D25"
+        };
+      }
+    } catch (error) {
+      if (error instanceof import_langgraph5.GraphInterrupt) {
+        throw error;
+      }
+      const errorMsg = `\u91CD\u65B0\u89C4\u5212\u5931\u8D25: ${error instanceof Error ? error.message : "\u672A\u77E5\u9519\u8BEF"}`;
+      agentLogger.error(errorMsg, { error });
+      return {
+        error: errorMsg
+      };
+    }
+  }
+  function shouldEnd(state) {
+    if (state.error) {
+      agentLogger.warn("\u56E0\u9519\u8BEF\u7ED3\u675F\u6267\u884C", { error: state.error });
+      return "end";
+    }
+    if (state.response) {
+      agentLogger.info("\u4EFB\u52A1\u5B8C\u6210\uFF0C\u7ED3\u675F\u6267\u884C");
+      return "end";
+    }
+    if (state.pastSteps.length >= maxSteps) {
+      agentLogger.warn("\u8FBE\u5230\u6700\u5927\u6B65\u9AA4\u6570\u9650\u5236\uFF0C\u7ED3\u675F\u6267\u884C", {
+        maxSteps,
+        currentSteps: state.pastSteps.length
+      });
+      return "end";
+    }
+    if (!state.plan || state.plan.length === 0) {
+      agentLogger.info("\u8BA1\u5212\u4E3A\u7A7A\uFF0C\u7ED3\u675F\u6267\u884C");
+      return "end";
+    }
+    return "continue";
+  }
+  const workflow = new import_langgraph5.StateGraph(PlanExecuteState).addNode("planner", planStep).addNode("executor", executeStep).addNode("replanner", replanStep).addEdge(import_langgraph5.START, "planner").addEdge("planner", "executor").addEdge("executor", "replanner").addConditionalEdges("replanner", shouldEnd, {
+    end: import_langgraph5.END,
+    continue: "executor"
+  });
+  const compiledGraph = workflow.compile({
+    checkpointer: checkpointer || MemoryManager.getInstance(),
+    name: `PlanExecuteAgent:${name}`
+  });
+  agentLogger.info(`Plan-Execute\u4EE3\u7406\u7F16\u8BD1\u5B8C\u6210: ${name}`);
+  return {
+    /**
+     * 执行代理
+     */
+    invoke: async (input, config2) => {
+      agentLogger.info(`\u5F00\u59CB\u6267\u884CPlan-Execute\u4EE3\u7406: ${name}`, {
+        input: input.input
+      });
+      try {
+        const result = await compiledGraph.invoke(input, config2);
+        agentLogger.info(`\u4EE3\u7406\u6267\u884C\u5B8C\u6210: ${name}`);
+        return result;
+      } catch (error) {
+        agentLogger.error(
+          `\u4EE3\u7406\u6267\u884C\u5931\u8D25: ${name}`,
+          error instanceof Error ? error : { error }
+        );
+        throw error;
+      }
+    },
+    /**
+     * 流式执行代理
+     */
+    stream: async (input, config2) => {
+      agentLogger.info(`\u5F00\u59CB\u6D41\u5F0F\u6267\u884CPlan-Execute\u4EE3\u7406: ${name}`, {
+        input: input.input
+      });
+      return compiledGraph.stream(input, config2);
+    },
+    /**
+     * 获取代理信息
+     */
+    getInfo: () => ({
+      name,
+      description,
+      type: "PlanExecuteAgent",
+      toolsCount: executorTools.length,
+      maxSteps
+    }),
+    /**
+     * 获取编译后的图
+     */
+    getCompiledGraph: () => compiledGraph
+  };
+}
+
+// src/agent_lattice/builders/PlanExecuteAgentGraphBuilder.ts
+var PlanExecuteAgentGraphBuilder = class {
+  /**
+   * 构建Plan Execute Agent Graph
+   *
+   * @param agentLattice Agent Lattice对象
+   * @param params Agent构建参数
+   * @returns 返回CompiledGraph对象
+   */
+  build(agentLattice, params) {
+    const tools = params.tools.map((t) => {
+      const tool5 = getToolClient(t.key);
+      return tool5;
+    }).filter((tool5) => tool5 !== void 0);
+    const agent = createPlanExecuteAgent({
+      llmManager: params.model,
+      tools,
+      prompt: params.prompt,
+      name: agentLattice.config.name,
+      description: agentLattice.config.description
+    });
+    return agent.getCompiledGraph();
+  }
+};
+
+// src/agent_lattice/builders/AgentGraphBuilderFactory.ts
+var AgentGraphBuilderFactory = class _AgentGraphBuilderFactory {
+  constructor() {
+    this.builders = /* @__PURE__ */ new Map();
+    this.registerDefaultBuilders();
+  }
+  /**
+   * 获取单例实例
+   */
+  static getInstance() {
+    if (!_AgentGraphBuilderFactory.instance) {
+      _AgentGraphBuilderFactory.instance = new _AgentGraphBuilderFactory();
+    }
+    return _AgentGraphBuilderFactory.instance;
+  }
+  /**
+   * 注册默认的Builder
+   */
+  registerDefaultBuilders() {
+    this.builders.set(import_protocols.AgentType.REACT, new ReActAgentGraphBuilder());
+    this.builders.set(import_protocols.AgentType.DEEP_AGENT, new DeepAgentGraphBuilder());
+    this.builders.set(
+      import_protocols.AgentType.PLAN_EXECUTE,
+      new PlanExecuteAgentGraphBuilder()
+    );
+  }
+  /**
+   * 注册自定义Builder
+   *
+   * @param type Agent类型
+   * @param builder Builder实例
+   */
+  registerBuilder(type, builder) {
+    this.builders.set(type, builder);
+  }
+  /**
+   * 获取Builder
+   *
+   * @param type Agent类型
+   * @returns 返回对应的Builder
+   */
+  getBuilder(type) {
+    const builder = this.builders.get(type);
+    if (!builder) {
+      throw new Error(`\u4E0D\u652F\u6301\u7684Agent\u7C7B\u578B: ${type}`);
+    }
+    return builder;
+  }
+};
+
+// src/agent_lattice/builders/AgentParamsBuilder.ts
+var AgentParamsBuilder = class {
+  /**
+   * constructor
+   *
+   * @param getAgentLatticeFunc get Agent Lattice function
+   */
+  constructor(getAgentLatticeFunc) {
+    this.getAgentLatticeFunc = getAgentLatticeFunc;
+  }
+  /**
+   * build Agent parameters
+   *
+   * @param agentLattice Agent Lattice object
+   * @param options build options
+   * @returns Agent build parameters
+   */
+  buildParams(agentLattice, options) {
+    const toolKeys = options?.overrideTools || agentLattice.config.tools || [];
+    const tools = toolKeys.map((toolKey) => {
+      const toolLattice = toolLatticeManager.getToolLattice(toolKey);
+      if (!toolLattice) {
+        throw new Error(`Tool "${toolKey}" does not exist`);
+      }
+      return {
+        key: toolKey,
+        definition: toolLattice.config,
+        executor: toolLattice.client
+      };
+    });
+    const modelKey = options?.overrideModel || agentLattice.config.modelKey;
+    const model = modelKey ? modelLatticeManager.getModelLattice(modelKey).client : modelLatticeManager.getModelLattice("default").client;
+    if (!model) {
+      throw new Error(`Model "${modelKey}" does not exist`);
+    }
+    const subAgentKeys = agentLattice.config.subAgents || [];
+    const subAgents = subAgentKeys.map((agentKey) => {
+      const subAgentLattice = this.getAgentLatticeFunc(agentKey);
+      if (!subAgentLattice) {
+        throw new Error(`SubAgent "${agentKey}" does not exist`);
+      }
+      return {
+        key: agentKey,
+        config: subAgentLattice.config,
+        client: subAgentLattice.client
+      };
+    });
+    return {
+      tools,
+      model,
+      subAgents,
+      prompt: agentLattice.config.prompt
+    };
+  }
+};
+
+// src/agent_lattice/AgentLatticeManager.ts
+var AgentLatticeManager = class _AgentLatticeManager extends BaseLatticeManager {
+  /**
+   * 获取AgentLatticeManager单例实例
+   */
+  static getInstance() {
+    if (!_AgentLatticeManager._instance) {
+      _AgentLatticeManager._instance = new _AgentLatticeManager();
+    }
+    return _AgentLatticeManager._instance;
+  }
+  /**
+   * 获取Lattice类型前缀
+   */
+  getLatticeType() {
+    return "agents";
+  }
+  /**
+   * 注册Agent Lattice
+   * @param config Agent配置
+   */
+  registerLattice(config) {
+    const agentLattice = {
+      config,
+      client: void 0
+      // 客户端将在需要时由initializeClient创建
+    };
+    this.register(config.key, agentLattice);
+  }
+  /**
+   * 获取AgentLattice
+   * @param key Lattice键名
+   */
+  getAgentLattice(key) {
+    return this.get(key);
+  }
+  /**
+   * 获取所有Lattice
+   */
+  getAllLattices() {
+    return this.getAll();
+  }
+  /**
+   * 检查Lattice是否存在
+   * @param key Lattice键名
+   */
+  hasLattice(key) {
+    return this.has(key);
+  }
+  /**
+   * 移除Lattice
+   * @param key Lattice键名
+   */
+  removeLattice(key) {
+    return this.remove(key);
+  }
+  /**
+   * 获取Agent配置
+   * @param key Lattice键名
+   */
+  getAgentConfig(key) {
+    return this.getAgentLattice(key)?.config;
+  }
+  /**
+   * 获取所有Agent配置
+   */
+  getAllAgentConfigs() {
+    return this.getAllLattices().map((lattice) => lattice.config);
+  }
+  /**
+   * 验证Agent输入参数
+   * @param key Lattice键名
+   * @param input 输入参数
+   */
+  validateAgentInput(key, input) {
+    const agentLattice = this.getAgentLattice(key);
+    if (!agentLattice) {
+      return false;
+    }
+    try {
+      if (agentLattice.config.schema) {
+        agentLattice.config.schema.parse(input);
+      }
+      return true;
+    } catch {
+      return false;
+    }
+  }
+  /**
+   * 构建Agent参数
+   *
+   * @param agentLattice Agent Lattice对象
+   * @param options 构建选项
+   * @returns 返回Agent构建参数
+   */
+  buildAgentParams(agentLattice, options) {
+    const paramsBuilder = new AgentParamsBuilder(
+      (key) => this.getAgentLattice(key)
+    );
+    return paramsBuilder.buildParams(agentLattice, options);
+  }
+  /**
+   * 初始化Agent客户端
+   *
+   * 使用AgentGraphBuilderFactory构建Graph并设置为客户端
+   *
+   * @param key Lattice键名
+   * @param options 构建选项
+   * @returns 返回CompiledGraph对象
+   */
+  initializeClient(key, options) {
+    const agentLattice = this.getAgentLattice(key);
+    if (!agentLattice) {
+      throw new Error(`Agent Lattice "${key}" \u4E0D\u5B58\u5728`);
+    }
+    if (agentLattice.client) {
+      return agentLattice.client;
+    }
+    const factory = AgentGraphBuilderFactory.getInstance();
+    const builder = factory.getBuilder(agentLattice.config.type);
+    const params = this.buildAgentParams(agentLattice, options);
+    const graph = builder.build(agentLattice, params);
+    agentLattice.client = graph;
+    return graph;
+  }
+};
+var agentLatticeManager = AgentLatticeManager.getInstance();
+var registerAgentLattice = (config) => {
+  agentLatticeManager.registerLattice(config);
+};
+var registerAgentLattices = (configs) => {
+  configs.forEach((config) => {
+    agentLatticeManager.registerLattice(config);
+  });
+};
+var getAgentLattice = (key) => agentLatticeManager.getAgentLattice(key);
+var getAgentConfig = (key) => agentLatticeManager.getAgentConfig(key);
+var getAllAgentConfigs = () => agentLatticeManager.getAllAgentConfigs();
+var validateAgentInput = (key, input) => agentLatticeManager.validateAgentInput(key, input);
+var getAgentClient = (key, options) => agentLatticeManager.initializeClient(key, options);
+
+// src/memory_lattice/DefaultMemorySaver.ts
+var import_langgraph6 = require("@langchain/langgraph");
+var memory2 = new import_langgraph6.MemorySaver();
+registerCheckpointSaver("default", memory2);
+
+// src/index.ts
+var Protocols = __toESM(require("@axiom-lattice/protocols"));
+// Annotate the CommonJS export names for ESM import in node:
+0 && (module.exports = {
+  AgentConfig,
+  AgentLatticeManager,
+  AgentType,
+  GraphBuildOptions,
+  MemoryLatticeManager,
+  MemoryType,
+  ModelLatticeManager,
+  Protocols,
+  agentLatticeManager,
+  getAgentClient,
+  getAgentConfig,
+  getAgentLattice,
+  getAllAgentConfigs,
+  getCheckpointSaver,
+  getModelLattice,
+  modelLatticeManager,
+  registerAgentLattice,
+  registerAgentLattices,
+  registerCheckpointSaver,
+  registerModelLattice,
+  validateAgentInput
+});
+//# sourceMappingURL=index.js.map