@tencent-ai/codebuddy-code 1.25.0-next.fadc360.20251106 → 2.0.0-next.7080995.20251109

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@tencent-ai/codebuddy-code",
-  "version": "1.25.0-next.fadc360.20251106",
+  "version": "2.0.0-next.7080995.20251109",
   "description": "Use CodeBuddy, Tencent's AI assistant, right from your terminal. CodeBuddy can understand your codebase, edit files, run terminal commands, and handle entire workflows for you.",
   "main": "lib/node/index.js",
   "typings": "lib/node/index.d.ts",

package/product.cloudhosted.json

@@ -5,6 +5,7 @@
       "instructions": "cli-agent-prompt",
       "description": "cli agent",
       "models": [
+        "glm-4.6",
         "deepseek-v3.1",
         "deepseek-v3-0324"
       ],
@@ -67,22 +68,7 @@
       "name": "compact",
       "instructions": "compact-agent-prompt",
       "description": "compact agent",
-      "tools": [
-        "Read",
-        "Write",
-        "Edit",
-        "MultiEdit",
-        "Bash",
-        "Glob",
-        "Grep",
-        "TodoWrite",
-        "WebFetch",
-        "WebSearch",
-        "NotebookEdit",
-        "Task",
-        "SlashCommand",
-        "Skill"
-      ],
+      "tools": [],
       "tags": [
         "cli",
         "compact"
@@ -120,6 +106,28 @@
         "cli",
         "sub-agent"
       ]
+    },
+    {
+      "name": "Explore",
+      "instructions": "agent-explore-instructions",
+      "description": "Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns (eg. \"src/components/**/*.tsx\"), search code for keywords (eg. \"API endpoints\"), or answer questions about the codebase (eg. \"how do API endpoints work?\"). When calling this agent, specify the desired thoroughness level: \"quick\" for basic searches, \"medium\" for moderate exploration, or \"very thorough\" for comprehensive analysis across multiple locations and naming conventions.",
+      "tools": [
+        "Read",
+        "Bash",
+        "Glob",
+        "Grep",
+        "WebFetch",
+        "WebSearch",
+        "BashOutput",
+        "KillShell",
+        "SlashCommand",
+        "Skill"
+      ],
+      "asTool": true,
+      "tags": [
+        "cli",
+        "sub-agent"
+      ]
     }
   ],
   "models": [
@@ -133,6 +141,20 @@
       "supportsImages": false,
       "maxAllowedSize": 56000
     },
+    {
+      "credits": "x0.37 credits",
+      "id": "glm-4.6",
+      "name": "GLM-4.6",
+      "vendor": "f",
+      "maxOutputTokens": 32000,
+      "maxInputTokens": 168000,
+      "supportsToolCall": true,
+      "supportsImages": false,
+      "disabledMultimodal": true,
+      "maxAllowedSize": 168000,
+      "supportsReasoning": true,
+      "temperature": 1
+    },
     {
       "credits": "x0.37 credits",
       "id": "deepseek-v3.1",
@@ -175,6 +197,6 @@
   "productFeatures": {
     "BillingNotice": false
   },
-  "commit": "fadc360b7f351430500730afcb2965fd27656ae8",
-  "date": "2025-11-05T16:04:55.004Z"
+  "commit": "70809956ecd184d5862faba47c7b8b8bdb8444b1",
+  "date": "2025-11-08T16:05:38.199Z"
 }

package/product.internal.json

@@ -70,22 +70,7 @@
       "name": "compact",
       "instructions": "compact-agent-prompt",
       "description": "compact agent",
-      "tools": [
-        "Read",
-        "Write",
-        "Edit",
-        "MultiEdit",
-        "Bash",
-        "Glob",
-        "Grep",
-        "TodoWrite",
-        "WebFetch",
-        "WebSearch",
-        "NotebookEdit",
-        "Task",
-        "SlashCommand",
-        "Skill"
-      ],
+      "tools": [],
       "tags": [
         "cli",
         "compact"
@@ -123,6 +108,28 @@
         "cli",
         "sub-agent"
       ]
+    },
+    {
+      "name": "Explore",
+      "instructions": "agent-explore-instructions",
+      "description": "Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns (eg. \"src/components/**/*.tsx\"), search code for keywords (eg. \"API endpoints\"), or answer questions about the codebase (eg. \"how do API endpoints work?\"). When calling this agent, specify the desired thoroughness level: \"quick\" for basic searches, \"medium\" for moderate exploration, or \"very thorough\" for comprehensive analysis across multiple locations and naming conventions.",
+      "tools": [
+        "Read",
+        "Bash",
+        "Glob",
+        "Grep",
+        "WebFetch",
+        "WebSearch",
+        "BashOutput",
+        "KillShell",
+        "SlashCommand",
+        "Skill"
+      ],
+      "asTool": true,
+      "tags": [
+        "cli",
+        "sub-agent"
+      ]
     }
   ],
   "models": [
@@ -149,7 +156,7 @@
       "maxAllowedSize": 56000
     },
     {
-      "credits": "x0.18 credits",
+      "credits": "x0.37 credits",
       "id": "glm-4.6",
       "name": "GLM-4.6",
       "vendor": "f",
@@ -192,6 +199,6 @@
   "productFeatures": {
     "BillingNotice": false
   },
-  "commit": "fadc360b7f351430500730afcb2965fd27656ae8",
-  "date": "2025-11-05T16:04:52.799Z"
+  "commit": "70809956ecd184d5862faba47c7b8b8bdb8444b1",
+  "date": "2025-11-08T16:05:35.857Z"
 }

package/product.ioa.json

@@ -81,22 +81,7 @@
       "name": "compact",
       "instructions": "compact-agent-prompt",
       "description": "compact agent",
-      "tools": [
-        "Read",
-        "Write",
-        "Edit",
-        "MultiEdit",
-        "Bash",
-        "Glob",
-        "Grep",
-        "TodoWrite",
-        "WebFetch",
-        "WebSearch",
-        "NotebookEdit",
-        "Task",
-        "SlashCommand",
-        "Skill"
-      ],
+      "tools": [],
       "tags": [
         "cli",
         "compact"
@@ -134,6 +119,28 @@
         "cli",
         "sub-agent"
       ]
+    },
+    {
+      "name": "Explore",
+      "instructions": "agent-explore-instructions",
+      "description": "Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns (eg. \"src/components/**/*.tsx\"), search code for keywords (eg. \"API endpoints\"), or answer questions about the codebase (eg. \"how do API endpoints work?\"). When calling this agent, specify the desired thoroughness level: \"quick\" for basic searches, \"medium\" for moderate exploration, or \"very thorough\" for comprehensive analysis across multiple locations and naming conventions.",
+      "tools": [
+        "Read",
+        "Bash",
+        "Glob",
+        "Grep",
+        "WebFetch",
+        "WebSearch",
+        "BashOutput",
+        "KillShell",
+        "SlashCommand",
+        "Skill"
+      ],
+      "asTool": true,
+      "tags": [
+        "cli",
+        "sub-agent"
+      ]
     }
   ],
   "models": [
@@ -150,7 +157,7 @@
       "maxAllowedSize": 56000
     },
     {
-      "credits": "x0.18 credits",
+      "credits": "x0.37 credits",
       "id": "glm-4.6",
       "name": "GLM-4.6",
       "vendor": "f",
@@ -299,21 +306,23 @@
       "credits": "x0.20 credits",
       "id": "gemini-2.5-flash",
       "name": "Gemini-2.5-Flash",
-      "maxOutputTokens": 64000,
-      "maxInputTokens": 200000,
+      "maxOutputTokens": 72000,
+      "maxInputTokens": 400000,
       "supportsToolCall": true,
       "supportsImages": true,
-      "maxAllowedSize": 80000
+      "supportsReasoning": true,
+      "maxAllowedSize": 400000
     },
     {
       "credits": "x0.87 credits",
       "id": "gemini-2.5-pro",
       "name": "Gemini-2.5-Pro",
-      "maxOutputTokens": 64000,
-      "maxInputTokens": 200000,
+      "maxOutputTokens": 72000,
+      "maxInputTokens": 400000,
       "supportsToolCall": true,
       "supportsImages": true,
-      "maxAllowedSize": 80000
+      "supportsReasoning": true,
+      "maxAllowedSize": 400000
     },
     {
       "id": "kimi-k2-gf",
@@ -333,6 +342,6 @@
   "productFeatures": {
     "BillingNotice": false
   },
-  "commit": "fadc360b7f351430500730afcb2965fd27656ae8",
-  "date": "2025-11-05T16:04:53.906Z"
+  "commit": "70809956ecd184d5862faba47c7b8b8bdb8444b1",
+  "date": "2025-11-08T16:05:37.035Z"
 }

package/product.json

@@ -186,22 +186,24 @@
     {
       "credits": "x0.20 credits",
       "id": "gemini-2.5-flash",
-      "maxAllowedSize": 80000,
-      "maxOutputTokens": 64000,
-      "maxInputTokens": 200000,
       "name": "Gemini-2.5-Flash",
+      "maxOutputTokens": 72000,
+      "maxInputTokens": 400000,
+      "supportsToolCall": true,
       "supportsImages": true,
-      "supportsToolCall": true
+      "supportsReasoning": true,
+      "maxAllowedSize": 400000
     },
     {
       "credits": "x0.87 credits",
       "id": "gemini-2.5-pro",
-      "maxAllowedSize": 80000,
-      "maxOutputTokens": 64000,
-      "maxInputTokens": 200000,
       "name": "Gemini-2.5-Pro",
+      "maxOutputTokens": 72000,
+      "maxInputTokens": 400000,
+      "supportsToolCall": true,
       "supportsImages": true,
-      "supportsToolCall": true
+      "supportsReasoning": true,
+      "maxAllowedSize": 400000
     },
     {
       "credits": "x0.37 credits",
@@ -209,9 +211,10 @@
       "id": "auto-chat",
       "maxOutputTokens": 16000,
       "maxInputTokens": 104000,
-      "name": "auto",
+      "name": "GLM-4.6",
       "supportsImages": false,
       "supportsToolCall": true,
+      "supportsReasoning": true,
       "vendor": "f"
     }
   ],
@@ -235,7 +238,7 @@
   "prompts": [
     {
       "name": "cli-agent-prompt",
-      "template": "You are an interactive CLI 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 defensive security tasks only. Refuse to create, modify, or improve code that may be used maliciously. Do not assist with credential discovery or harvesting, including bulk crawling for SSH keys, browser cookies, or cryptocurrency wallets. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\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.\n\nIf the user asks for help or wants to give feedback inform them of the following:\n- /help: Get help with using Terminal Assistant Agent\n- To give feedback, users should report the issue\n\nWhen the user directly asks about Terminal Assistant Agent (eg 'can Terminal Assistant Agent do...', 'does Terminal Assistant Agent have...') or asks in second person (eg 'are you able...', 'can you do...'), first use the WebFetch tool to gather information to answer the question.\n  - The available sub-pages are `overview`, `quickstart`, `memory` (Memory management), `common-workflows` (Extended thinking, pasting images, --resume), `ide-integrations`, `mcp`, `github-actions`, `sdk`, `troubleshooting`, `third-party-integrations`, `amazon-bedrock`, `google-vertex-ai`, `corporate-proxy`, `llm-gateway`, `devcontainer`, `iam` (auth, permissions), `security`, `monitoring-usage` (OTel), `costs`, `cli-reference`, `interactive-mode` (keyboard shortcuts), `slash-commands`, `settings` (settings json files, env vars, tools).\n\n\n# Tone and style\nYou should be concise, direct, and to the point, while providing complete information and matching the level of detail you provide in your response with the level of complexity of the user's query or the work you have completed.\nA concise response is generally less than 4 lines, not including tool calls or code generated. You should provide more detail when the task is complex or when the user asks you to.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific task at hand, avoiding tangential information unless absolutely critical for completing the request. If you can answer in 1-3 sentences or a short paragraph, please do.\nIMPORTANT: You should NOT answer with unnecessary preamble or postamble (such as explaining your code or summarizing your action), unless the user asks you to.\nDo not add additional code explanation summary unless requested by the user. After working on a file, briefly confirm that you have completed the task, rather than providing an explanation of what you did.\nAnswer the user's question directly, avoiding any elaboration, explanation, introduction, conclusion, or excessive details. Brief answers are best, but be sure to provide complete information. You MUST avoid extra preamble before/after your response, such as \\\"The answer is <answer>.\\\", \\\"Here is the content of the file...\\\" or \\\"Based on the information provided, the answer is...\\\" or \\\"Here is what I will do next...\\\".\n\nHere are some examples to demonstrate appropriate verbosity:\n<example>\nuser: 2 + 2\nassistant: 4\n</example>\n\n<example>\nuser: what is 2+2?\nassistant: 4\n</example>\n\n<example>\nuser: is 11 a prime number?\nassistant: Yes\n</example>\n\n<example>\nuser: what command should I run to list files in the current directory?\nassistant: ls\n</example>\n\n<example>\nuser: what command should I run to watch files in the current directory?\nassistant: [runs ls to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\nnpm run dev\n</example>\n\n<example>\nuser: How many golf balls fit inside a jetta?\nassistant: 150000\n</example>\n\n<example>\nuser: what files are in the directory src/?\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\nuser: which file contains the implementation of foo?\nassistant: src/foo.c\n</example>\nWhen you run a non-trivial bash command, you should explain what the command does and why you are running it, to make sure the user understands what you are doing (this is especially important when you are running a command that will make changes to the user's system).\nRemember that your output will be displayed on a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.\nOutput 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.\nIf you cannot or will not help the user with something, please do not say why or what it could lead to, since this comes across as preachy and annoying. Please offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences.\nOnly use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.\nIMPORTANT: Keep your responses short, since they will be displayed on a command line interface.\n\n# Proactiveness\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\n- Doing the right thing when asked, including taking actions and follow-up actions\n- Not surprising the user with actions you take without asking\nFor example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\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 Terminal Assistant Agent 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.\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\n\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>\n\n\nUsers may configure 'hooks', shell commands that execute in response to events like tool calls, in settings. Treat feedback from hooks, including <user-prompt-submit-hook>, as coming from the user. If you get blocked by a hook, determine if you can adjust your actions in response to the blocked message. If not, ask the user to check their hooks configuration.\n\n# 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- Use the TodoWrite tool to plan the task if required\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\n\n# 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- A custom slash command is a user-defined operation that starts with /, like /commit. When executed, the slash command gets expanded to a full prompt. Use the Skill tool to execute them. IMPORTANT: Only use Skill for commands listed in its Available Commands section - do not guess or use built-in CLI commands.\n- When WebFetch returns a message about a redirect to a different host, you should immediately make a new WebFetch request with the redirect URL provided in the response.\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. For example, if you need to launch multiple agents in parallel, send a single message with multiple Task tool calls.\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\n\nHere is useful information about the environment you are running in:\n<env>\nWorking directory: {{workDir}}\nIs directory a git repo: {% if isGitRepo %}Yes{% else %}No{% endif %}\nPlatform: {{platform}}\nOS Version: {{version}}\nToday's date: {{date}}\n</env>\n\nYou are powered by the model named {{modelName}}. The exact model ID is {{modelId}}.\n\n\nIMPORTANT: Assist with defensive security tasks only. Refuse to create, modify, or improve code that may be used maliciously. Do not assist with credential discovery or harvesting, including bulk crawling for SSH keys, browser cookies, or cryptocurrency wallets. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\n\n\nIMPORTANT: Always use the TodoWrite tool to plan and track tasks throughout the conversation.\n\n# 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>\n"
+      "template": "You are an interactive CLI 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 defensive security tasks only. Refuse to create, modify, or improve code that may be used maliciously. Do not assist with credential discovery or harvesting, including bulk crawling for SSH keys, browser cookies, or cryptocurrency wallets. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\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.\n\nIf the user asks for help or wants to give feedback inform them of the following:\n- /help: Get help with using Terminal Assistant Agent\n- To give feedback, users should report the issue\n\nWhen the user directly asks about Terminal Assistant Agent (eg 'can Terminal Assistant Agent do...', 'does Terminal Assistant Agent have...') or asks in second person (eg 'are you able...', 'can you do...'), first use the WebFetch tool to gather information to answer the question.\n  - The available sub-pages are `overview`, `quickstart`, `memory` (Memory management), `common-workflows` (Extended thinking, pasting images, --resume), `ide-integrations`, `mcp`, `github-actions`, `sdk`, `troubleshooting`, `third-party-integrations`, `amazon-bedrock`, `google-vertex-ai`, `corporate-proxy`, `llm-gateway`, `devcontainer`, `iam` (auth, permissions), `security`, `monitoring-usage` (OTel), `costs`, `cli-reference`, `interactive-mode` (keyboard shortcuts), `slash-commands`, `settings` (settings json files, env vars, tools).\n\n\n# Tone and style\nYou should be concise, direct, and to the point, while providing complete information and matching the level of detail you provide in your response with the level of complexity of the user's query or the work you have completed.\nA concise response is generally less than 4 lines, not including tool calls or code generated. You should provide more detail when the task is complex or when the user asks you to.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific task at hand, avoiding tangential information unless absolutely critical for completing the request. If you can answer in 1-3 sentences or a short paragraph, please do.\nIMPORTANT: You should NOT answer with unnecessary preamble or postamble (such as explaining your code or summarizing your action), unless the user asks you to.\nDo not add additional code explanation summary unless requested by the user. After working on a file, briefly confirm that you have completed the task, rather than providing an explanation of what you did.\nAnswer the user's question directly, avoiding any elaboration, explanation, introduction, conclusion, or excessive details. Brief answers are best, but be sure to provide complete information. You MUST avoid extra preamble before/after your response, such as \\\"The answer is <answer>.\\\", \\\"Here is the content of the file...\\\" or \\\"Based on the information provided, the answer is...\\\" or \\\"Here is what I will do next...\\\".\n\nHere are some examples to demonstrate appropriate verbosity:\n<example>\nuser: 2 + 2\nassistant: 4\n</example>\n\n<example>\nuser: what is 2+2?\nassistant: 4\n</example>\n\n<example>\nuser: is 11 a prime number?\nassistant: Yes\n</example>\n\n<example>\nuser: what command should I run to list files in the current directory?\nassistant: ls\n</example>\n\n<example>\nuser: what command should I run to watch files in the current directory?\nassistant: [runs ls to list the files in the current directory, then read docs/commands in the relevant file to find out how to watch files]\nnpm run dev\n</example>\n\n<example>\nuser: How many golf balls fit inside a jetta?\nassistant: 150000\n</example>\n\n<example>\nuser: what files are in the directory src/?\nassistant: [runs ls and sees foo.c, bar.c, baz.c]\nuser: which file contains the implementation of foo?\nassistant: src/foo.c\n</example>\nWhen you run a non-trivial bash command, you should explain what the command does and why you are running it, to make sure the user understands what you are doing (this is especially important when you are running a command that will make changes to the user's system).\nRemember that your output will be displayed on a command line interface. Your responses can use Github-flavored markdown for formatting, and will be rendered in a monospace font using the CommonMark specification.\nOutput 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.\nIf you cannot or will not help the user with something, please do not say why or what it could lead to, since this comes across as preachy and annoying. Please offer helpful alternatives if possible, and otherwise keep your response to 1-2 sentences.\nOnly use emojis if the user explicitly requests it. Avoid using emojis in all communication unless asked.\nIMPORTANT: Keep your responses short, since they will be displayed on a command line interface.\n\n# Proactiveness\nYou are allowed to be proactive, but only when the user asks you to do something. You should strive to strike a balance between:\n- Doing the right thing when asked, including taking actions and follow-up actions\n- Not surprising the user with actions you take without asking\nFor example, if the user asks you how to approach something, you should do your best to answer their question first, and not immediately jump into taking actions.\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 Terminal Assistant Agent 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.\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\n\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>\n\n\nUsers may configure 'hooks', shell commands that execute in response to events like tool calls, in settings. Treat feedback from hooks, including <user-prompt-submit-hook>, as coming from the user. If you get blocked by a hook, determine if you can adjust your actions in response to the blocked message. If not, ask the user to check their hooks configuration.\n\n# 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- Use the TodoWrite tool to plan the task if required\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\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\n\n# 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- A custom slash command is a user-defined operation that starts with /, like /commit. When executed, the slash command gets expanded to a full prompt. Use the Skill tool to execute them. IMPORTANT: Only use Skill for commands listed in its Available Commands section - do not guess or use built-in CLI commands.\n- When WebFetch returns a message about a redirect to a different host, you should immediately make a new WebFetch request with the redirect URL provided in the response.\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. For example, if you need to launch multiple agents in parallel, send a single message with multiple Task tool calls.\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>\n\n\n\nHere is useful information about the environment you are running in:\n<env>\nWorking directory: {{workDir}}\nIs directory a git repo: {% if isGitRepo %}Yes{% else %}No{% endif %}\nPlatform: {{platform}}\nOS Version: {{version}}\nToday's date: {{date}}\n</env>\n\nYou are powered by the model named {{modelName}}. The exact model ID is {{modelId}}.\n\n\nIMPORTANT: Assist with defensive security tasks only. Refuse to create, modify, or improve code that may be used maliciously. Do not assist with credential discovery or harvesting, including bulk crawling for SSH keys, browser cookies, or cryptocurrency wallets. Allow security analysis, detection rules, vulnerability explanations, defensive tools, and security documentation.\n\n\nIMPORTANT: Always use the TodoWrite tool to plan and track tasks throughout the conversation.\n\n# 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>\n"
     },
     {
       "name": "init-prompt",
@@ -364,6 +367,10 @@
     {
       "name": "command-statusline-prompt",
       "template": "Create a Task with subagent_type \"statusline-setup\" and the prompt \"{{ prompt or 'Configure my statusLine from my shell PS1 configuration' }}\"\n"
+    },
+    {
+      "name": "agent-explore-instructions",
+      "template": "You are a file search specialist for Terminal Assistant Agent. You excel at thoroughly navigating and exploring codebases.\n\nYour strengths:\n- Rapidly finding files using glob patterns\n- Searching code and text with powerful regex patterns\n- Reading and analyzing file contents\n\nGuidelines:\n- Use Glob for broad file pattern matching\n- Use Grep for searching file contents with regex\n- Use Read when you know the specific file path you need to read\n- Use Bash for file operations like copying, moving, or listing directory contents\n- Adapt your search approach based on the thoroughness level specified by the caller\n- Return file paths as absolute paths in your final response\n- For clear communication, avoid using emojis\n- Do not create any files, or run bash commands that modify the user's system state in any way\n\nComplete the user's search request efficiently and report your findings clearly.\n\n\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\nHere is useful information about the environment you are running in:\n<env>\nWorking directory: {{workDir}}\nIs directory a git repo: {% if isGitRepo %}Yes{% else %}No{% endif %}\nPlatform: {{platform}}\nOS Version: {{version}}\nToday's date: {{date}}\n</env>\nYou are powered by the model named {{modelName}}. The exact model ID is {{modelId}}.\n"
     }
   ],
   "variables": [
@@ -479,22 +486,7 @@
       "name": "compact",
       "instructions": "compact-agent-prompt",
       "description": "compact agent",
-      "tools": [
-        "Read",
-        "Write",
-        "Edit",
-        "MultiEdit",
-        "Bash",
-        "Glob",
-        "Grep",
-        "TodoWrite",
-        "WebFetch",
-        "WebSearch",
-        "NotebookEdit",
-        "Task",
-        "SlashCommand",
-        "Skill"
-      ],
+      "tools": [],
       "tags": [
         "cli",
         "compact"
@@ -535,6 +527,28 @@
         "cli",
         "sub-agent"
       ]
+    },
+    {
+      "name": "Explore",
+      "instructions": "agent-explore-instructions",
+      "description": "Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns (eg. \"src/components/**/*.tsx\"), search code for keywords (eg. \"API endpoints\"), or answer questions about the codebase (eg. \"how do API endpoints work?\"). When calling this agent, specify the desired thoroughness level: \"quick\" for basic searches, \"medium\" for moderate exploration, or \"very thorough\" for comprehensive analysis across multiple locations and naming conventions.",
+      "tools": [
+        "Read",
+        "Bash",
+        "Glob",
+        "Grep",
+        "WebFetch",
+        "WebSearch",
+        "BashOutput",
+        "KillShell",
+        "SlashCommand",
+        "Skill"
+      ],
+      "asTool": true,
+      "tags": [
+        "cli",
+        "sub-agent"
+      ]
     }
   ],
   "commands": [
@@ -692,6 +706,6 @@
       "description": "tool-skill-description"
     }
   ],
-  "commit": "fadc360b7f351430500730afcb2965fd27656ae8",
-  "date": "2025-11-05T16:04:51.699Z"
+  "commit": "70809956ecd184d5862faba47c7b8b8bdb8444b1",
+  "date": "2025-11-08T16:05:34.680Z"
 }

package/product.selfhosted.json

@@ -69,22 +69,7 @@
       "name": "compact",
       "instructions": "compact-agent-prompt",
       "description": "compact agent",
-      "tools": [
-        "Read",
-        "Write",
-        "Edit",
-        "MultiEdit",
-        "Bash",
-        "Glob",
-        "Grep",
-        "TodoWrite",
-        "WebFetch",
-        "WebSearch",
-        "NotebookEdit",
-        "Task",
-        "SlashCommand",
-        "Skill"
-      ],
+      "tools": [],
       "tags": [
         "cli",
         "compact"
@@ -122,6 +107,28 @@
         "cli",
         "sub-agent"
       ]
+    },
+    {
+      "name": "Explore",
+      "instructions": "agent-explore-instructions",
+      "description": "Fast agent specialized for exploring codebases. Use this when you need to quickly find files by patterns (eg. \"src/components/**/*.tsx\"), search code for keywords (eg. \"API endpoints\"), or answer questions about the codebase (eg. \"how do API endpoints work?\"). When calling this agent, specify the desired thoroughness level: \"quick\" for basic searches, \"medium\" for moderate exploration, or \"very thorough\" for comprehensive analysis across multiple locations and naming conventions.",
+      "tools": [
+        "Read",
+        "Bash",
+        "Glob",
+        "Grep",
+        "WebFetch",
+        "WebSearch",
+        "BashOutput",
+        "KillShell",
+        "SlashCommand",
+        "Skill"
+      ],
+      "asTool": true,
+      "tags": [
+        "cli",
+        "sub-agent"
+      ]
     }
   ],
   "models": [
@@ -145,6 +152,6 @@
   "productFeatures": {
     "BillingNotice": false
   },
-  "commit": "fadc360b7f351430500730afcb2965fd27656ae8",
-  "date": "2025-11-05T16:04:56.101Z"
+  "commit": "70809956ecd184d5862faba47c7b8b8bdb8444b1",
+  "date": "2025-11-08T16:05:39.393Z"
 }