sema-core 1.0.2

package/dist/services/agents/genSystemPrompt.js

@@ -0,0 +1,189 @@
+"use strict";
+var __createBinding = (this && this.__createBinding) || (Object.create ? (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    var desc = Object.getOwnPropertyDescriptor(m, k);
+    if (!desc || ("get" in desc ? !m.__esModule : desc.writable || desc.configurable)) {
+      desc = { enumerable: true, get: function() { return m[k]; } };
+    }
+    Object.defineProperty(o, k2, desc);
+}) : (function(o, m, k, k2) {
+    if (k2 === undefined) k2 = k;
+    o[k2] = m[k];
+}));
+var __setModuleDefault = (this && this.__setModuleDefault) || (Object.create ? (function(o, v) {
+    Object.defineProperty(o, "default", { enumerable: true, value: v });
+}) : function(o, v) {
+    o["default"] = v;
+});
+var __importStar = (this && this.__importStar) || (function () {
+    var ownKeys = function(o) {
+        ownKeys = Object.getOwnPropertyNames || function (o) {
+            var ar = [];
+            for (var k in o) if (Object.prototype.hasOwnProperty.call(o, k)) ar[ar.length] = k;
+            return ar;
+        };
+        return ownKeys(o);
+    };
+    return function (mod) {
+        if (mod && mod.__esModule) return mod;
+        var result = {};
+        if (mod != null) for (var k = ownKeys(mod), i = 0; i < k.length; i++) if (k[i] !== "default") __createBinding(result, mod, k[i]);
+        __setModuleDefault(result, mod);
+        return result;
+    };
+})();
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.getContext = void 0;
+exports.formatSystemPrompt = formatSystemPrompt;
+exports.generateTodosReminders = generateTodosReminders;
+exports.generatePlanReminders = generatePlanReminders;
+exports.genEnv = genEnv;
+exports.genGitStatus = genGitStatus;
+exports.buildAgentSystemPrompt = buildAgentSystemPrompt;
+const product_1 = require("../../constants/product");
+const git_1 = require("../../util/git");
+const env_1 = require("../../util/env");
+const lodash_es_1 = require("lodash-es");
+const ConfManager_1 = require("../../manager/ConfManager");
+const skillRegistry_1 = require("../skill/skillRegistry");
+const cwd_1 = require("../../util/cwd");
+const path = __importStar(require("path"));
+const prompt_1 = require("./prompt");
+async function formatSystemPrompt(options) {
+    // 获取系统提示、上下文
+    const context = await (0, exports.getContext)();
+    // 合并系统提示，每个部分作为独立的 text 内容
+    const systemPromptParts = [
+        getProductSyspromptPrefix(),
+        getSystemPrompt(context, options)
+    ].filter(prompt => prompt.trim().length > 0); // 过滤空提示
+    // 转换为 text 内容数组格式
+    return systemPromptParts.map(text => ({ type: 'text', text }));
+}
+exports.getContext = (0, lodash_es_1.memoize)(async () => {
+    // 并行获取各种上下文信息
+    const [env, gitStatus] = await Promise.all([
+        (0, env_1.getEnv)(), // 目录结构
+        (0, git_1.getGitStatus)(), // Git状态信息
+    ]);
+    // 返回组合的上下文对象
+    return {
+        ...(env ? { env } : {}),
+        ...(gitStatus ? { gitStatus } : {}),
+    };
+});
+function generateTodosReminders() {
+    const additionalReminders = [];
+    const rulesReminder = `<system-reminder>
+${prompt_1.Empty_Todo_Reminder_Prompt}
+</system-reminder>`;
+    additionalReminders.push({
+        type: 'text',
+        text: rulesReminder
+    });
+    return additionalReminders;
+}
+function generatePlanReminders(taskDescription) {
+    const additionalReminders = [];
+    const currentDir = (0, cwd_1.getOriginalCwd)();
+    const plansDir = path.join(currentDir, '.sema/', 'plans/');
+    // 生成计划文件名的提示
+    const planFileInstruction = taskDescription
+        ? `You should create your plan at ${plansDir}<title>.md where <title> is a descriptive name based on the task: "${taskDescription}". Choose a clear, concise title in kebab-case (e.g., "implement-api-gateway.md", "fix-streaming-parser.md").`
+        : `You should create your plan at ${plansDir}<title>.md where <title> is a descriptive name you generate based on the user's request. Choose a clear, concise title in kebab-case.`;
+    const rulesReminder = `<system-reminder>
+Plan mode is active. The user indicated that they do not want you to execute yet -- you MUST NOT make any edits (with the exception of the plan file mentioned below), run any non-readonly tools (including changing configs or making commits), or otherwise make any changes to the system. This supersedes any other instructions you have received.
+
+## Plan File Info:
+No plan file exists yet. ${planFileInstruction}
+You should build your plan incrementally by writing to or editing this file. NOTE that this is the only file you are allowed to edit - other than this you are only allowed to take READ-ONLY actions.
+
+${prompt_1.PlanMode_Reminder_Prompt}
+</system-reminder>`;
+    additionalReminders.push({
+        type: 'text',
+        text: rulesReminder
+    });
+    return additionalReminders;
+}
+function getProductSyspromptPrefix() {
+    try {
+        // 尝试从配置管理器中获取自定义的 systemPrompt
+        const configManager = (0, ConfManager_1.getConfManager)();
+        const coreConfig = configManager.getCoreConfig();
+        if (coreConfig?.systemPrompt) {
+            return coreConfig.systemPrompt;
+        }
+    }
+    catch (error) {
+    }
+    // 如果没有配置自定义 systemPrompt，使用默认值
+    return `You are ${product_1.PRODUCT_NAME}, ${product_1.GROUP}'s Agent AI for coding.`;
+}
+function getSystemPrompt(context = {}, options) {
+    // 获取 Skills 摘要
+    let skillsSummary = '';
+    try {
+        skillsSummary = (0, skillRegistry_1.getSkillsSummary)();
+    }
+    catch (error) {
+        // Skills 系统可能未初始化，忽略错误
+    }
+    // 是否包含 Task Management 部分（默认包含，除非明确指定没有 TodoWrite 工具）
+    const hasTodoWriteTool = options?.hasTodoWriteTool !== false;
+    let TodoWriteSystemPrompt = '';
+    let TodoWrite_Tool_Usage_IMPORTANT = '';
+    if (hasTodoWriteTool) {
+        TodoWriteSystemPrompt = prompt_1.With_TodoWrite_Prompt;
+        TodoWrite_Tool_Usage_IMPORTANT = `IMPORTANT: Always use the TodoWrite tool to plan and track tasks throughout the conversation.`;
+    }
+    else {
+        TodoWriteSystemPrompt = prompt_1.Without_TodoWrite_Prompt;
+    }
+    // 是否包含 AskUserQuestion 部分（默认包含，除非明确指定没有 AskUserQuestion 工具）
+    const hasAskUserQuestionTool = options?.hasAskUserQuestionTool !== false;
+    const AskQuestionSystemPrompt = hasAskUserQuestionTool ? prompt_1.Ask_Question_Prompt : '';
+    return `
+${prompt_1.Agent_Summary_Prompt}
+${skillsSummary}
+
+${prompt_1.Style_and_Professional_Prompt}
+
+${TodoWriteSystemPrompt}
+
+${AskQuestionSystemPrompt}
+
+${prompt_1.Doing_Tasks_Prompt}
+
+${prompt_1.Tool_Usage_Policy_Prompt}
+${TodoWrite_Tool_Usage_IMPORTANT}
+
+${prompt_1.Code_References_Prompt}
+
+${genEnv(context)}
+
+${genGitStatus(context)}
+`;
+}
+function genEnv(context) {
+    if (context && 'env' in context) {
+        return `Here is useful information about the environment you are running in:
+<env>${context.env}</env>`;
+    }
+    return '';
+}
+function genGitStatus(context) {
+    if (context && 'gitStatus' in context) {
+        return `gitStatus: ${context.gitStatus}`;
+    }
+    return '';
+}
+/**
+ * 构建代理模式的系统提示（用于 Explore/Plan 等子代理）
+ */
+async function buildAgentSystemPrompt(agentPrompt) {
+    const context = await (0, exports.getContext)();
+    const fullPrompt = agentPrompt + prompt_1.SUBAGENT_NOTES + genEnv(context) + genGitStatus(context);
+    return [{ type: 'text', text: fullPrompt }];
+}
+//# sourceMappingURL=genSystemPrompt.js.map

package/dist/services/agents/genSystemPrompt.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"genSystemPrompt.js","sourceRoot":"","sources":["../../../src/services/agents/genSystemPrompt.ts"],"names":[],"mappings":";;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;AAuBA,gDAYC;AAoBD,wDAaC;AAED,sDA0BC;AAoED,wBAMC;AAED,oCAKC;AAKD,wDAIC;AAzLD,qDAA6D;AAC7D,wCAA6C;AAC7C,wCAAuC;AACvC,yCAAmC;AACnC,2DAA0D;AAC1D,0DAAyD;AACzD,wCAA+C;AAC/C,2CAA6B;AAC7B,qCAYiB;AAEV,KAAK,UAAU,kBAAkB,CAAC,OAA0E;IACjH,aAAa;IACb,MAAM,OAAO,GAAG,MAAM,IAAA,kBAAU,GAAE,CAAA;IAElC,2BAA2B;IAC3B,MAAM,iBAAiB,GAAG;QACxB,yBAAyB,EAAE;QAC3B,eAAe,CAAC,OAAO,EAAE,OAAO,CAAC;KAClC,CAAC,MAAM,CAAC,MAAM,CAAC,EAAE,CAAC,MAAM,CAAC,IAAI,EAAE,CAAC,MAAM,GAAG,CAAC,CAAC,CAAC,CAAC,QAAQ;IAEtD,kBAAkB;IAClB,OAAO,iBAAiB,CAAC,GAAG,CAAC,IAAI,CAAC,EAAE,CAAC,CAAC,EAAE,IAAI,EAAE,MAAe,EAAE,IAAI,EAAE,CAAC,CAAC,CAAC;AAC1E,CAAC;AAEY,QAAA,UAAU,GAAG,IAAA,mBAAO,EAC/B,KAAK,IAEF,EAAE;IACH,cAAc;IACd,MAAM,CAAC,GAAG,EAAE,SAAS,CAAC,GAAG,MAAM,OAAO,CAAC,GAAG,CAAC;QACzC,IAAA,YAAM,GAAE,EAAE,OAAO;QACjB,IAAA,kBAAY,GAAE,EAAE,UAAU;KAC3B,CAAC,CAAA;IAEF,aAAa;IACb,OAAO;QACL,GAAG,CAAC,GAAG,CAAC,CAAC,CAAC,EAAE,GAAG,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;QACvB,GAAG,CAAC,SAAS,CAAC,CAAC,CAAC,EAAE,SAAS,EAAE,CAAC,CAAC,CAAC,EAAE,CAAC;KACpC,CAAA;AACH,CAAC,CACF,CAAA;AAED,SAAgB,sBAAsB;IACpC,MAAM,mBAAmB,GAAkC,EAAE,CAAA;IAE7D,MAAM,aAAa,GAAG;EACtB,mCAA0B;mBACT,CAAA;IAEjB,mBAAmB,CAAC,IAAI,CAAC;QACvB,IAAI,EAAE,MAAe;QACrB,IAAI,EAAE,aAAa;KACpB,CAAC,CAAA;IAEF,OAAO,mBAAmB,CAAA;AAC5B,CAAC;AAED,SAAgB,qBAAqB,CAAC,eAAwB;IAC5D,MAAM,mBAAmB,GAAkC,EAAE,CAAA;IAC7D,MAAM,UAAU,GAAG,IAAA,oBAAc,GAAE,CAAA;IACnC,MAAM,QAAQ,GAAG,IAAI,CAAC,IAAI,CAAC,UAAU,EAAE,QAAQ,EAAE,QAAQ,CAAC,CAAA;IAE1D,aAAa;IACb,MAAM,mBAAmB,GAAG,eAAe;QACzC,CAAC,CAAC,kCAAkC,QAAQ,sEAAsE,eAAe,+GAA+G;QAChP,CAAC,CAAC,kCAAkC,QAAQ,uIAAuI,CAAA;IAErL,MAAM,aAAa,GAAG;;;;2BAIG,mBAAmB;;;EAG5C,iCAAwB;mBACP,CAAA;IAEjB,mBAAmB,CAAC,IAAI,CAAC;QACvB,IAAI,EAAE,MAAe;QACrB,IAAI,EAAE,aAAa;KACpB,CAAC,CAAA;IAEF,OAAO,mBAAmB,CAAA;AAC5B,CAAC;AAED,SAAS,yBAAyB;IAChC,IAAI,CAAC;QACH,+BAA+B;QAC/B,MAAM,aAAa,GAAG,IAAA,4BAAc,GAAE,CAAC;QACvC,MAAM,UAAU,GAAG,aAAa,CAAC,aAAa,EAAE,CAAC;QAEjD,IAAI,UAAU,EAAE,YAAY,EAAE,CAAC;YAC7B,OAAO,UAAU,CAAC,YAAY,CAAC;QACjC,CAAC;IACH,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;IACjB,CAAC;IAED,+BAA+B;IAC/B,OAAO,WAAW,sBAAY,KAAK,eAAK,yBAAyB,CAAC;AACpE,CAAC;AAED,SAAS,eAAe,CAAC,UAA+B,EAAE,EAAE,OAA0E;IACpI,eAAe;IACf,IAAI,aAAa,GAAG,EAAE,CAAA;IACtB,IAAI,CAAC;QACH,aAAa,GAAG,IAAA,gCAAgB,GAAE,CAAA;IACpC,CAAC;IAAC,OAAO,KAAK,EAAE,CAAC;QACf,uBAAuB;IACzB,CAAC;IAED,sDAAsD;IACtD,MAAM,gBAAgB,GAAG,OAAO,EAAE,gBAAgB,KAAK,KAAK,CAAA;IAE5D,IAAI,qBAAqB,GAAG,EAAE,CAAA;IAC9B,IAAI,8BAA8B,GAAG,EAAE,CAAA;IACvC,IAAI,gBAAgB,EAAE,CAAC;QACrB,qBAAqB,GAAG,8BAAqB,CAAA;QAC7C,8BAA8B,GAAG,+FAA+F,CAAA;IAClI,CAAC;SACI,CAAC;QACJ,qBAAqB,GAAG,iCAAwB,CAAA;IAClD,CAAC;IAED,4DAA4D;IAC5D,MAAM,sBAAsB,GAAG,OAAO,EAAE,sBAAsB,KAAK,KAAK,CAAA;IACxE,MAAM,uBAAuB,GAAG,sBAAsB,CAAC,CAAC,CAAC,4BAAmB,CAAC,CAAC,CAAC,EAAE,CAAA;IAEjF,OAAO;EACP,6BAAoB;EACpB,aAAa;;EAEb,sCAA6B;;EAE7B,qBAAqB;;EAErB,uBAAuB;;EAEvB,2BAAkB;;EAElB,iCAAwB;EACxB,8BAA8B;;EAE9B,+BAAsB;;EAEtB,MAAM,CAAC,OAAO,CAAC;;EAEf,YAAY,CAAC,OAAO,CAAC;CACtB,CAAA;AACD,CAAC;AAGD,SAAgB,MAAM,CAAC,OAA4B;IACjD,IAAI,OAAO,IAAI,KAAK,IAAI,OAAO,EAAE,CAAC;QAChC,OAAO;OACJ,OAAO,CAAC,GAAG,QAAQ,CAAC;IACzB,CAAC;IACD,OAAO,EAAE,CAAC;AACZ,CAAC;AAED,SAAgB,YAAY,CAAC,OAA4B;IACvD,IAAI,OAAO,IAAI,WAAW,IAAI,OAAO,EAAE,CAAC;QACtC,OAAO,cAAc,OAAO,CAAC,SAAS,EAAE,CAAC;IAC3C,CAAC;IACD,OAAO,EAAE,CAAC;AACZ,CAAC;AAED;;GAEG;AACI,KAAK,UAAU,sBAAsB,CAAC,WAAmB;IAC9D,MAAM,OAAO,GAAG,MAAM,IAAA,kBAAU,GAAE,CAAA;IAClC,MAAM,UAAU,GAAG,WAAW,GAAG,uBAAc,GAAG,MAAM,CAAC,OAAO,CAAC,GAAG,YAAY,CAAC,OAAO,CAAC,CAAA;IACzF,OAAO,CAAC,EAAE,IAAI,EAAE,MAAe,EAAE,IAAI,EAAE,UAAU,EAAE,CAAC,CAAA;AACtD,CAAC"}

package/dist/services/agents/prompt.d.ts

@@ -0,0 +1,12 @@
+export declare const Agent_Summary_Prompt = "You are an interactive code agent tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.\n\nIMPORTANT: Assist with authorized security testing, defensive security, CTF challenges, and educational contexts. Refuse requests for destructive techniques, DoS attacks, mass targeting, supply chain compromise, or detection evasion for malicious purposes. Dual-use security tools (C2 frameworks, credential testing, exploit development) require clear authorization context: pentesting engagements, CTF competitions, security research, or defensive use cases.\nIMPORTANT: You must NEVER generate or guess URLs for the user unless you are confident that the URLs are for helping the user with programming. You may use URLs provided by the user in their messages or local files.";
+export declare const Style_and_Professional_Prompt = "# Tone and style\n- Only use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.\n- Your output will be displayed on a command line interface. Your responses should be short and concise. You can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.\n- Output text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.\n- NEVER create files unless they're absolutely necessary for achieving your goal. ALWAYS prefer editing an existing file to creating a new one. This includes markdown files.\n\n# Professional objectivity\nPrioritize technical accuracy and truthfulness over validating the user's beliefs. Focus on facts and problem-solving, providing direct, objective technical info without any unnecessary superlatives, praise, or emotional validation. It is best for the user if product honestly applies the same rigorous standards to all ideas and disagrees when necessary, even if it may not be what the user wants to hear. Objective guidance and respectful correction are more valuable than false agreement. Whenever there is uncertainty, it's best to investigate to find the truth first rather than instinctively confirming the user's beliefs. Avoid using over-the-top validation or excessive praise when responding to users such as \"You're absolutely right\" or similar phrases.";
+export declare const Ask_Question_Prompt = "# Asking questions as you work\nYou have access to the AskUserQuestion tool to ask the user questions when you need clarification, want to validate assumptions, or need to make a decision you're unsure about. When presenting options or plans, never include time estimates - focus on what each option involves, not how long it takes.";
+export declare const Doing_Tasks_Prompt = "# Doing tasks\nThe user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:\n- NEVER propose changes to code you haven't read. If a user asks about or wants you to modify a file, read it first. Understand existing code before suggesting modifications.\n- Be careful not to introduce security vulnerabilities such as command injection, XSS, SQL injection, and other OWASP top 10 vulnerabilities. If you notice that you wrote insecure code, immediately fix it.\n- Avoid over-engineering. Only make changes that are directly requested or clearly necessary. Keep solutions simple and focused.\n  - Don't add features, refactor code, or make \"improvements\" beyond what was asked. A bug fix doesn't need surrounding code cleaned up. A simple feature doesn't need extra configurability. Don't add docstrings, comments, or type annotations to code you didn't change. Only add comments where the logic isn't self-evident.\n  - Don't add error handling, fallbacks, or validation for scenarios that can't happen. Trust internal code and framework guarantees. Only validate at system boundaries (user input, external APIs). Don't use feature flags or backwards-compatibility shims when you can just change the code.\n  - Don't create helpers, utilities, or abstractions for one-time operations. Don't design for hypothetical future requirements. The right amount of complexity is the minimum needed for the current task\u2014three similar lines of code is better than a premature abstraction.\n- Avoid backwards-compatibility hacks like renaming unused `_vars`, re-exporting types, adding `// removed` comments for removed code, etc. If something is unused, delete it completely.\n\n- Tool results and user messages may include <system-reminder> tags. <system-reminder> tags contain useful information and reminders. They are automatically added by the system, and bear no direct relation to the specific tool results or user messages in which they appear.\n- The conversation has unlimited context through automatic summarization.";
+export declare const Tool_Usage_Policy_Prompt = "# Tool usage policy\n- When doing file search, prefer to use the Task tool in order to reduce context usage.\n- You should proactively use the Task tool with specialized agents when the task at hand matches the agent's description.\n- You can call multiple tools in a single response. If you intend to call multiple tools and there are no dependencies between them, make all independent tool calls in parallel. Maximize use of parallel tool calls where possible to increase efficiency. However, if some tool calls depend on previous calls to inform dependent values, do NOT call these tools in parallel and instead call them sequentially. For instance, if one operation must complete before another starts, run these operations sequentially instead. Never use placeholders or guess missing parameters in tool calls.\n- If the user specifies that they want you to run tools \"in parallel\", you MUST send a single message with multiple tool use content blocks. \n- Use specialized tools instead of bash commands when possible, as this provides a better user experience. For file operations, use dedicated tools: Read for reading files instead of cat/head/tail, Edit for editing instead of sed/awk, and Write for creating files instead of cat with heredoc or echo redirection. Reserve bash tools exclusively for actual system commands and terminal operations that require shell execution. NEVER use bash echo or other command-line tools to communicate thoughts, explanations, or instructions to the user. Output all communication directly in your response text instead.\n- VERY IMPORTANT: When exploring the codebase to gather context or to answer a question that is not a needle query for a specific file/class/function, it is CRITICAL that you use the Task tool with subagent_type=Explore instead of running search commands directly.\n<example>\nuser: Where are errors from the client handled?\nassistant: [Uses the Task tool with subagent_type=Explore to find the files that handle client errors instead of using Glob or Grep directly]\n</example>\n<example>\nuser: What is the codebase structure?\nassistant: [Uses the Task tool with subagent_type=Explore]\n</example>";
+export declare const Code_References_Prompt = "# Code References\n\nWhen referencing specific functions or pieces of code include the pattern `file_path:line_number` to allow the user to easily navigate to the source code location.\n\n<example>\nuser: Where are errors from the client handled?\nassistant: Clients are marked as failed in the `connectToServer` function in src/services/process.ts:712.\n</example>";
+export declare const Empty_Todo_Reminder_Prompt = "This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware. If you are working on tasks that would benefit from a todo list please use the TodoWrite tool to create one. If not, please feel free to ignore. Again do not mention this message to the user.";
+export declare const With_TodoWrite_Prompt = "# Planning without timelines\nWhen planning tasks, provide concrete implementation steps without time estimates. Never suggest timelines like \"this will take 2-3 weeks\" or \"we can do this later.\" Focus on what needs to be done, not when. Break work into actionable steps and let users decide scheduling.\n\n# Task Management\nYou have access to the TodoWrite 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.\nThese 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.\n\nIt 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.\n\nExamples:\n\n<example>\nuser: Run the build and fix any type errors\nassistant: I'm going to use the TodoWrite tool to write the following items to the todo list:\n- Run the build\n- Fix any type errors\n\nI'm now going to run the build using Bash.\n\nLooks like I found 10 type errors. I'm going to use the TodoWrite tool to write 10 items to the todo list.\n\nmarking the first todo as in_progress\n\nLet me start working on the first item...\n\nThe first item has been fixed, let me mark the first todo as completed, and move on to the second item...\n..\n..\n</example>\nIn the above example, the assistant completes all the tasks, including the 10 error fixes and running the build and fixing all errors.\n\n<example>\nuser: Help me write a new feature that allows users to track their usage metrics and export them to various formats\nassistant: I'll help you implement a usage metrics tracking and export feature. Let me first use the TodoWrite tool to plan this task.\nAdding the following todos to the todo list:\n1. Research existing metrics tracking in the codebase\n2. Design the metrics collection system\n3. Implement core metrics tracking functionality\n4. Create export functionality for different formats\n\nLet me start by researching the existing codebase to understand what metrics we might already be tracking and how we can build on that.\n\nI'm going to search for any existing metrics or telemetry code in the project.\n\nI've found some existing telemetry code. Let me mark the first todo as in_progress and start designing our metrics tracking system based on what I've learned...\n\n[Assistant continues implementing the feature step by step, marking todos as in_progress and completed as they go]\n</example>";
+export declare const Without_TodoWrite_Prompt = "# No time estimates\nNever give time estimates or predictions for how long tasks will take, whether for your own work or for users planning their projects. Avoid phrases like \"this will take me a few minutes,\" \"should be done in about 5 minutes,\" \"this is a quick fix,\" \"this will take 2-3 weeks,\" or \"we can do this later.\" Focus on what needs to be done, not how long it might take. Break work into actionable steps and let users judge timing for themselves.";
+export declare const PlanMode_Reminder_Prompt = "## Plan Workflow\n\n### Phase 1: Initial Understanding\nGoal: Gain a comprehensive understanding of the user's request by reading through code and asking them questions. Critical: In this phase you should only use the Explore subagent type.\n\n1. Focus on understanding the user's request and the code associated with their request\n\n2. **Launch Explore agents SEQUENTIALLY** (one at a time, multiple messages if needed) to explore the codebase.\n   - Launch ONE Explore agent per message\n   - Wait for the agent to complete before launching the next one\n   - Use 1 agent when the task is isolated to known files, the user provided specific file paths, or you're making a small targeted change\n   - Use multiple sequential agents when: the scope is uncertain, multiple areas of the codebase are involved, or you need to understand existing patterns before planning\n   - Quality over quantity - 3 agents maximum across multiple messages, but you should try to use the minimum number of agents necessary (usually just 1)\n   - If using multiple agents sequentially: Give each agent a specific search focus or area to explore based on what you learned from previous agents. Example: First agent searches for existing implementations, then based on findings, second agent explores related components, then third investigates testing patterns if needed\n\n### Phase 2: Design\nGoal: Design an implementation approach.\n\nLaunch Plan agent(s) to design the implementation based on the user's intent and your exploration results from Phase 1.\n\nYou can launch up to 1 agent(s) in parallel.\n\n**Guidelines:**\n- **Default**: Launch at least 1 Plan agent for most tasks - it helps validate your understanding and consider alternatives\n- **Skip agents**: Only for truly trivial tasks (typo fixes, single-line changes, simple renames)\n\nIn the agent prompt:\n- Provide comprehensive background context from Phase 1 exploration including filenames and code path traces\n- Describe requirements and constraints\n- Request a detailed implementation plan\n\n### Phase 3: Review\nGoal: Review the plan(s) from Phase 2 and ensure alignment with the user's intentions.\n1. Read the critical files identified by agents to deepen your understanding\n2. Ensure that the plans align with the user's original request\n3. Use AskUserQuestion to clarify any remaining questions with the user\n\n### Phase 4: Final Plan\nGoal: Write your final plan to the plan file (the only file you can edit).\n- Include only your recommended approach, not all alternatives\n- Ensure that the plan file is concise enough to scan quickly, but detailed enough to execute effectively\n- Include the paths of critical files to be modified\n- Include a verification section describing how to test the changes end-to-end (run the code, use MCP tools, run tests)\n\n### Phase 5: Call ExitPlanMode\nAt the very end of your turn, once you have asked the user questions and are happy with your final plan file - you should always call ExitPlanMode to indicate to the user that you are done planning.\nThis is critical - your turn should only end with either using the AskUserQuestion tool OR calling ExitPlanMode. Do not stop unless it's for these 2 reasons\n\n**Important:** Use AskUserQuestion ONLY to clarify requirements or choose between approaches. Use ExitPlanMode to request plan approval. Do NOT ask about plan approval in any other way - no text questions, no AskUserQuestion. Phrases like \"Is this plan okay?\", \"Should I proceed?\", \"How does this plan look?\", \"Any changes before we start?\", or similar MUST use ExitPlanMode.\n\nNOTE: At any point in time through this workflow you should feel free to ask the user questions or clarifications using the AskUserQuestion tool. Don't make large assumptions about user intent. The goal is to present a well researched plan to the user, and tie any loose ends before implementation begins.";
+export declare const SUBAGENT_NOTES = "\nNotes:\n- Agent threads always have their cwd reset between bash calls, as a result please only use absolute file paths.\n- In your final response always share relevant file names and code snippets. Any file paths you return in your response MUST be absolute. Do NOT use relative paths.\n- For clear communication with the user the assistant MUST avoid using emojis.\n- Do not use a colon before tool calls. Text like \"Let me read the file:\" followed by a read tool call should just be \"Let me read the file.\" with a period.\n";
+//# sourceMappingURL=prompt.d.ts.map

package/dist/services/agents/prompt.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"prompt.d.ts","sourceRoot":"","sources":["../../../src/services/agents/prompt.ts"],"names":[],"mappings":"AACA,eAAO,MAAM,oBAAoB,m1BAGuL,CAAA;AAExN,eAAO,MAAM,6BAA6B,gjDAOktB,CAAA;AAE5vB,eAAO,MAAM,mBAAmB,iVAC6Q,CAAA;AAE7S,eAAO,MAAM,kBAAkB,6oEAW2C,CAAA;AAE1E,eAAO,MAAM,wBAAwB,+nEAc1B,CAAA;AAEX,eAAO,MAAM,sBAAsB,kXAOxB,CAAA;AAGX,eAAO,MAAM,0BAA0B,0UAA0U,CAAA;AAEjX,eAAO,MAAM,qBAAqB,kmFA+CvB,CAAA;AAEX,eAAO,MAAM,wBAAwB,2dACmZ,CAAA;AAExb,eAAO,MAAM,wBAAwB,60HAkD6Q,CAAA;AAElT,eAAO,MAAM,cAAc,yhBAM1B,CAAA"}

package/dist/services/agents/prompt.js

@@ -0,0 +1,162 @@
+"use strict";
+Object.defineProperty(exports, "__esModule", { value: true });
+exports.SUBAGENT_NOTES = exports.PlanMode_Reminder_Prompt = exports.Without_TodoWrite_Prompt = exports.With_TodoWrite_Prompt = exports.Empty_Todo_Reminder_Prompt = exports.Code_References_Prompt = exports.Tool_Usage_Policy_Prompt = exports.Doing_Tasks_Prompt = exports.Ask_Question_Prompt = exports.Style_and_Professional_Prompt = exports.Agent_Summary_Prompt = void 0;
+exports.Agent_Summary_Prompt = `You are an interactive code agent tool that helps users with software engineering tasks. Use the instructions below and the tools available to you to assist the user.
+
+IMPORTANT: Assist with authorized security testing, defensive security, CTF challenges, and educational contexts. Refuse requests for destructive techniques, DoS attacks, mass targeting, supply chain compromise, or detection evasion for malicious purposes. Dual-use security tools (C2 frameworks, credential testing, exploit development) require clear authorization context: pentesting engagements, CTF competitions, security research, or defensive use cases.
+IMPORTANT: You must NEVER generate or guess URLs for the user unless you are confident that the URLs are for helping the user with programming. You may use URLs provided by the user in their messages or local files.`;
+exports.Style_and_Professional_Prompt = `# Tone and style
+- Only use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.
+- Your output will be displayed on a command line interface. Your responses should be short and concise. You can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.
+- Output text to communicate with the user; all text you output outside of tool use is displayed to the user. Only use tools to complete tasks. Never use tools like Bash or code comments as means to communicate with the user during the session.
+- NEVER create files unless they're absolutely necessary for achieving your goal. ALWAYS prefer editing an existing file to creating a new one. This includes markdown files.
+
+# Professional objectivity
+Prioritize technical accuracy and truthfulness over validating the user's beliefs. Focus on facts and problem-solving, providing direct, objective technical info without any unnecessary superlatives, praise, or emotional validation. It is best for the user if product honestly applies the same rigorous standards to all ideas and disagrees when necessary, even if it may not be what the user wants to hear. Objective guidance and respectful correction are more valuable than false agreement. Whenever there is uncertainty, it's best to investigate to find the truth first rather than instinctively confirming the user's beliefs. Avoid using over-the-top validation or excessive praise when responding to users such as "You're absolutely right" or similar phrases.`;
+exports.Ask_Question_Prompt = `# Asking questions as you work
+You have access to the AskUserQuestion tool to ask the user questions when you need clarification, want to validate assumptions, or need to make a decision you're unsure about. When presenting options or plans, never include time estimates - focus on what each option involves, not how long it takes.`;
+exports.Doing_Tasks_Prompt = `# Doing tasks
+The user will primarily request you perform software engineering tasks. This includes solving bugs, adding new functionality, refactoring code, explaining code, and more. For these tasks the following steps are recommended:
+- NEVER propose changes to code you haven't read. If a user asks about or wants you to modify a file, read it first. Understand existing code before suggesting modifications.
+- Be careful not to introduce security vulnerabilities such as command injection, XSS, SQL injection, and other OWASP top 10 vulnerabilities. If you notice that you wrote insecure code, immediately fix it.
+- Avoid over-engineering. Only make changes that are directly requested or clearly necessary. Keep solutions simple and focused.
+  - Don't add features, refactor code, or make "improvements" beyond what was asked. A bug fix doesn't need surrounding code cleaned up. A simple feature doesn't need extra configurability. Don't add docstrings, comments, or type annotations to code you didn't change. Only add comments where the logic isn't self-evident.
+  - Don't add error handling, fallbacks, or validation for scenarios that can't happen. Trust internal code and framework guarantees. Only validate at system boundaries (user input, external APIs). Don't use feature flags or backwards-compatibility shims when you can just change the code.
+  - Don't create helpers, utilities, or abstractions for one-time operations. Don't design for hypothetical future requirements. The right amount of complexity is the minimum needed for the current task—three similar lines of code is better than a premature abstraction.
+- Avoid backwards-compatibility hacks like renaming unused \`_vars\`, re-exporting types, adding \`// removed\` comments for removed code, etc. If something is unused, delete it completely.
+
+- Tool results and user messages may include <system-reminder> tags. <system-reminder> tags contain useful information and reminders. They are automatically added by the system, and bear no direct relation to the specific tool results or user messages in which they appear.
+- The conversation has unlimited context through automatic summarization.`;
+exports.Tool_Usage_Policy_Prompt = `# Tool usage policy
+- When doing file search, prefer to use the Task tool in order to reduce context usage.
+- You should proactively use the Task tool with specialized agents when the task at hand matches the agent's description.
+- You can call multiple tools in a single response. If you intend to call multiple tools and there are no dependencies between them, make all independent tool calls in parallel. Maximize use of parallel tool calls where possible to increase efficiency. However, if some tool calls depend on previous calls to inform dependent values, do NOT call these tools in parallel and instead call them sequentially. For instance, if one operation must complete before another starts, run these operations sequentially instead. Never use placeholders or guess missing parameters in tool calls.
+- If the user specifies that they want you to run tools "in parallel", you MUST send a single message with multiple tool use content blocks. 
+- Use specialized tools instead of bash commands when possible, as this provides a better user experience. For file operations, use dedicated tools: Read for reading files instead of cat/head/tail, Edit for editing instead of sed/awk, and Write for creating files instead of cat with heredoc or echo redirection. Reserve bash tools exclusively for actual system commands and terminal operations that require shell execution. NEVER use bash echo or other command-line tools to communicate thoughts, explanations, or instructions to the user. Output all communication directly in your response text instead.
+- VERY IMPORTANT: When exploring the codebase to gather context or to answer a question that is not a needle query for a specific file/class/function, it is CRITICAL that you use the Task tool with subagent_type=Explore instead of running search commands directly.
+<example>
+user: Where are errors from the client handled?
+assistant: [Uses the Task tool with subagent_type=Explore to find the files that handle client errors instead of using Glob or Grep directly]
+</example>
+<example>
+user: What is the codebase structure?
+assistant: [Uses the Task tool with subagent_type=Explore]
+</example>`;
+exports.Code_References_Prompt = `# Code References
+
+When referencing specific functions or pieces of code include the pattern \`file_path:line_number\` to allow the user to easily navigate to the source code location.
+
+<example>
+user: Where are errors from the client handled?
+assistant: Clients are marked as failed in the \`connectToServer\` function in src/services/process.ts:712.
+</example>`;
+exports.Empty_Todo_Reminder_Prompt = `This is a reminder that your todo list is currently empty. DO NOT mention this to the user explicitly because they are already aware. If you are working on tasks that would benefit from a todo list please use the TodoWrite tool to create one. If not, please feel free to ignore. Again do not mention this message to the user.`;
+exports.With_TodoWrite_Prompt = `# Planning without timelines
+When planning tasks, provide concrete implementation steps without time estimates. Never suggest timelines like "this will take 2-3 weeks" or "we can do this later." Focus on what needs to be done, not when. Break work into actionable steps and let users decide scheduling.
+
+# Task Management
+You have access to the TodoWrite 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.
+
+Examples:
+
+<example>
+user: Run the build and fix any type errors
+assistant: I'm going to use the TodoWrite tool to write the following items to the todo list:
+- Run the build
+- Fix any type errors
+
+I'm now going to run the build using Bash.
+
+Looks like I found 10 type errors. I'm going to use the TodoWrite tool to write 10 items to the todo list.
+
+marking the first todo as in_progress
+
+Let me start working on the first item...
+
+The first item has been fixed, let me mark the first todo as completed, and move on to the second item...
+..
+..
+</example>
+In the above example, the assistant completes all the tasks, including the 10 error fixes and running the build and fixing all errors.
+
+<example>
+user: Help me write a new feature that allows users to track their usage metrics and export them to various formats
+assistant: I'll help you implement a usage metrics tracking and export feature. Let me first use the TodoWrite tool to plan this task.
+Adding the following todos to the todo list:
+1. Research existing metrics tracking in the codebase
+2. Design the metrics collection system
+3. Implement core metrics tracking functionality
+4. Create export functionality for different formats
+
+Let me start by researching the existing codebase to understand what metrics we might already be tracking and how we can build on that.
+
+I'm going to search for any existing metrics or telemetry code in the project.
+
+I've found some existing telemetry code. Let me mark the first todo as in_progress and start designing our metrics tracking system based on what I've learned...
+
+[Assistant continues implementing the feature step by step, marking todos as in_progress and completed as they go]
+</example>`;
+exports.Without_TodoWrite_Prompt = `# No time estimates
+Never give time estimates or predictions for how long tasks will take, whether for your own work or for users planning their projects. Avoid phrases like "this will take me a few minutes," "should be done in about 5 minutes," "this is a quick fix," "this will take 2-3 weeks," or "we can do this later." Focus on what needs to be done, not how long it might take. Break work into actionable steps and let users judge timing for themselves.`;
+exports.PlanMode_Reminder_Prompt = `## Plan Workflow
+
+### Phase 1: Initial Understanding
+Goal: Gain a comprehensive understanding of the user's request by reading through code and asking them questions. Critical: In this phase you should only use the Explore subagent type.
+
+1. Focus on understanding the user's request and the code associated with their request
+
+2. **Launch Explore agents SEQUENTIALLY** (one at a time, multiple messages if needed) to explore the codebase.
+   - Launch ONE Explore agent per message
+   - Wait for the agent to complete before launching the next one
+   - Use 1 agent when the task is isolated to known files, the user provided specific file paths, or you're making a small targeted change
+   - Use multiple sequential agents when: the scope is uncertain, multiple areas of the codebase are involved, or you need to understand existing patterns before planning
+   - Quality over quantity - 3 agents maximum across multiple messages, but you should try to use the minimum number of agents necessary (usually just 1)
+   - If using multiple agents sequentially: Give each agent a specific search focus or area to explore based on what you learned from previous agents. Example: First agent searches for existing implementations, then based on findings, second agent explores related components, then third investigates testing patterns if needed
+
+### Phase 2: Design
+Goal: Design an implementation approach.
+
+Launch Plan agent(s) to design the implementation based on the user's intent and your exploration results from Phase 1.
+
+You can launch up to 1 agent(s) in parallel.
+
+**Guidelines:**
+- **Default**: Launch at least 1 Plan agent for most tasks - it helps validate your understanding and consider alternatives
+- **Skip agents**: Only for truly trivial tasks (typo fixes, single-line changes, simple renames)
+
+In the agent prompt:
+- Provide comprehensive background context from Phase 1 exploration including filenames and code path traces
+- Describe requirements and constraints
+- Request a detailed implementation plan
+
+### Phase 3: Review
+Goal: Review the plan(s) from Phase 2 and ensure alignment with the user's intentions.
+1. Read the critical files identified by agents to deepen your understanding
+2. Ensure that the plans align with the user's original request
+3. Use AskUserQuestion to clarify any remaining questions with the user
+
+### Phase 4: Final Plan
+Goal: Write your final plan to the plan file (the only file you can edit).
+- Include only your recommended approach, not all alternatives
+- Ensure that the plan file is concise enough to scan quickly, but detailed enough to execute effectively
+- Include the paths of critical files to be modified
+- Include a verification section describing how to test the changes end-to-end (run the code, use MCP tools, run tests)
+
+### Phase 5: Call ExitPlanMode
+At the very end of your turn, once you have asked the user questions and are happy with your final plan file - you should always call ExitPlanMode to indicate to the user that you are done planning.
+This is critical - your turn should only end with either using the AskUserQuestion tool OR calling ExitPlanMode. Do not stop unless it's for these 2 reasons
+
+**Important:** Use AskUserQuestion ONLY to clarify requirements or choose between approaches. Use ExitPlanMode to request plan approval. Do NOT ask about plan approval in any other way - no text questions, no AskUserQuestion. Phrases like "Is this plan okay?", "Should I proceed?", "How does this plan look?", "Any changes before we start?", or similar MUST use ExitPlanMode.
+
+NOTE: At any point in time through this workflow you should feel free to ask the user questions or clarifications using the AskUserQuestion tool. Don't make large assumptions about user intent. The goal is to present a well researched plan to the user, and tie any loose ends before implementation begins.`;
+exports.SUBAGENT_NOTES = `
+Notes:
+- Agent threads always have their cwd reset between bash calls, as a result please only use absolute file paths.
+- In your final response always share relevant file names and code snippets. Any file paths you return in your response MUST be absolute. Do NOT use relative paths.
+- For clear communication with the user the assistant MUST avoid using emojis.
+- Do not use a colon before tool calls. Text like "Let me read the file:" followed by a read tool call should just be "Let me read the file." with a period.
+`;
+//# sourceMappingURL=prompt.js.map

package/dist/services/agents/prompt.js.map

@@ -0,0 +1 @@
+{"version":3,"file":"prompt.js","sourceRoot":"","sources":["../../../src/services/agents/prompt.ts"],"names":[],"mappings":";;;AACa,QAAA,oBAAoB,GAAG;;;wNAGoL,CAAA;AAE3M,QAAA,6BAA6B,GAAG;;;;;;;4vBAO+sB,CAAA;AAE/uB,QAAA,mBAAmB,GAAG;6SAC0Q,CAAA;AAEhS,QAAA,kBAAkB,GAAG;;;;;;;;;;;0EAWwC,CAAA;AAE7D,QAAA,wBAAwB,GAAG;;;;;;;;;;;;;;WAc7B,CAAA;AAEE,QAAA,sBAAsB,GAAG;;;;;;;WAO3B,CAAA;AAGE,QAAA,0BAA0B,GAAG,uUAAuU,CAAA;AAEpW,QAAA,qBAAqB,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;WA+C1B,CAAA;AAEE,QAAA,wBAAwB,GAAG;wbACgZ,CAAA;AAE3a,QAAA,wBAAwB,GAAG;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;kTAkD0Q,CAAA;AAErS,QAAA,cAAc,GAAG;;;;;;CAM7B,CAAA"}

package/dist/services/api/adapt/anthropic.d.ts

@@ -0,0 +1,10 @@
+import { UserMessage, AssistantMessage } from '../../../types/message';
+import { ModelProfile } from '../../../types/model';
+import { Tool } from '../../../tools/base/Tool';
+import { MAIN_QUERY_TEMPERATURE } from './util';
+export { MAIN_QUERY_TEMPERATURE };
+export declare function queryAnthropic(messages: (UserMessage | AssistantMessage)[], systemPromptContent: Array<{
+    type: 'text';
+    text: string;
+}>, tools: Tool[], signal: AbortSignal, modelProfile: ModelProfile, enableThinking: boolean, emitChunkEvents: boolean): Promise<AssistantMessage>;
+//# sourceMappingURL=anthropic.d.ts.map

package/dist/services/api/adapt/anthropic.d.ts.map

@@ -0,0 +1 @@
+{"version":3,"file":"anthropic.d.ts","sourceRoot":"","sources":["../../../../src/services/api/adapt/anthropic.ts"],"names":[],"mappings":"AAEA,OAAO,EAAE,WAAW,EAAE,gBAAgB,EAAE,MAAM,wBAAwB,CAAA;AACtE,OAAO,EAAE,YAAY,EAAE,MAAM,sBAAsB,CAAA;AACnD,OAAO,EAAE,IAAI,EAAE,MAAM,0BAA0B,CAAA;AAI/C,OAAO,EAAE,sBAAsB,EAAoC,MAAM,QAAQ,CAAA;AAEjF,OAAO,EAAE,sBAAsB,EAAE,CAAA;AAiKjC,wBAAsB,cAAc,CAClC,QAAQ,EAAE,CAAC,WAAW,GAAG,gBAAgB,CAAC,EAAE,EAC5C,mBAAmB,EAAE,KAAK,CAAC;IAAE,IAAI,EAAE,MAAM,CAAC;IAAC,IAAI,EAAE,MAAM,CAAA;CAAE,CAAC,EAC1D,KAAK,EAAE,IAAI,EAAE,EACb,MAAM,EAAE,WAAW,EACnB,YAAY,EAAE,YAAY,EAC1B,cAAc,EAAE,OAAO,EACvB,eAAe,EAAE,OAAO,GACvB,OAAO,CAAC,gBAAgB,CAAC,CAmD3B"}