anomalyco/opencode
1
0
Fork 0
mirror of https://github.com/anomalyco/opencode.git synced 2026-07-22 02:05:26 -04:00
Code Issues 5.9k Packages Projects Releases 19 Wiki Activity

Thinking Function and Thinking Blocks Visibility Issues #1650

New Issue
Closed
opened 2026-02-16 17:31:57 -05:00 by yindo · 10 comments
yindo commented 2026-02-16 17:31:57 -05:00
Owner
Copy Link
Copy Source

Originally created by @clomia on GitHub (Sep 7, 2025).

Originally assigned to: @rekram1-node on GitHub.

opencode.json

"provider": {
    "anthropic": {
      "models": {
        "claude-opus-4-1-20250805": {
          "options": {
            "thinking": {
              "type": "enabled",
              "budgetTokens": 1024,
            },
          },
        },
      },
    },
    "google": {
      "models": {
        "gemini-2.5-pro": {
          "options": {
            "thinkingBudget": 32768
          }
        }
      }
    }
  },

I configured opencode.json like this and used the /thinking command to set thinking blocks to be visible. When using Grok Code Fast 1, I was able to see the thought process through thinking blocks.

However, the gemini-2.5-pro and claude-opus-4-1 that I configured did not have thinking functionality working.

First, when using claude-opus, this error appears:

AI_APICallError: max_tokens: 33024 > 32000, which is the maximum allowed number of output
tokens for claude-opus-4-1-20250805

I suspect that internally, output_tokens is set to the maximum value (32000), and when budgetTokens is added to output_tokens, it causes the problem.

And when using gemini-2.5-pro, thinking blocks do not appear without any errors. It looks the same before and after setting thinkingBudget. Since gemini 2.5 models do thinking by default, thinking blocks should be visible, but the main issue is that thinking blocks are not showing.

  1. The problem of thinking blocks not being visible.
  2. The output_tokens error that occurs when using claude-opus.

I would like you to fix these two issues.

Originally created by @clomia on GitHub (Sep 7, 2025). Originally assigned to: @rekram1-node on GitHub. opencode.json ``` "provider": { "anthropic": { "models": { "claude-opus-4-1-20250805": { "options": { "thinking": { "type": "enabled", "budgetTokens": 1024, }, }, }, }, }, "google": { "models": { "gemini-2.5-pro": { "options": { "thinkingBudget": 32768 } } } } }, ``` I configured opencode.json like this and used the `/thinking` command to set thinking blocks to be visible. When using Grok Code Fast 1, I was able to see the thought process through thinking blocks. However, the gemini-2.5-pro and claude-opus-4-1 that I configured did not have thinking functionality working. First, when using claude-opus, this error appears: ``` AI_APICallError: max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805 ``` I suspect that internally, output_tokens is set to the maximum value (32000), and when budgetTokens is added to output_tokens, it causes the problem. And when using gemini-2.5-pro, thinking blocks do not appear without any errors. It looks the same before and after setting thinkingBudget. Since gemini 2.5 models do thinking by default, thinking blocks should be visible, but the main issue is that thinking blocks are not showing. 1. The problem of thinking blocks not being visible. 2. The output_tokens error that occurs when using claude-opus. I would like you to fix these two issues.
yindo closed this issue 2026-02-16 17:31:57 -05:00
yindo commented 2026-02-16 17:31:57 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Sep 7, 2025):

@clomia this issue:

AI_APICallError: max_tokens: 33024 > 32000, which is the maximum allowed number of output
tokens for claude-opus-4-1-20250805

Was just fixed today, so your opus should work w/ thinking enabled

@rekram1-node commented on GitHub (Sep 7, 2025): @clomia this issue: > AI_APICallError: max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805 Was just fixed today, so your opus should work w/ thinking enabled
yindo commented 2026-02-16 17:31:57 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Sep 7, 2025):

@clomia as for google you appear to not be configuring thinking correctly, here is correct config:

"gemini-2.5-pro": {
          "options": {
            "thinkingConfig": {
              "thinkingBudget": 8192,
              "includeThoughts": true
            }
          }
        }
@rekram1-node commented on GitHub (Sep 7, 2025): @clomia as for google you appear to not be configuring thinking correctly, here is correct config: ``` "gemini-2.5-pro": { "options": { "thinkingConfig": { "thinkingBudget": 8192, "includeThoughts": true } } } ```
yindo commented 2026-02-16 17:31:57 -05:00
Author
Owner
Copy Link
Copy Source

@clomia commented on GitHub (Sep 7, 2025):

@rekram1-node The gemini 2.5 issue has been resolved! Thank you.
However, claude opus still outputs an APICallError. Even when I open the TUI through the opencode command in a new shell, the problem persists. Do I need to wait a bit for the fixes you mentioned today to be applied?

@clomia commented on GitHub (Sep 7, 2025): @rekram1-node The gemini 2.5 issue has been resolved! Thank you. However, claude opus still outputs an APICallError. Even when I open the TUI through the opencode command in a new shell, the problem persists. Do I need to wait a bit for the fixes you mentioned today to be applied?
yindo commented 2026-02-16 17:31:57 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Sep 7, 2025):

@clomia run:

opencode upgrade

then reopen opencode (so if you have a running instance, close and reopen), then try again

the issue should resolve

@rekram1-node commented on GitHub (Sep 7, 2025): @clomia run: ``` opencode upgrade ``` then reopen opencode (so if you have a running instance, close and reopen), then try again the issue should resolve
yindo commented 2026-02-16 17:31:57 -05:00
Author
Owner
Copy Link
Copy Source

@clomia commented on GitHub (Sep 8, 2025):

It still doesn't work, but I found the problem.

In claude-sonnet-4-20250514, thinking works well as you mentioned. However, in claude opus models, errors occur.

AI_APICallError: max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-20250514

AI_APICallError: max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805

According to the Anthropic documentation, both opus models support Extended thinking, but I don't understand why it doesn't work only with opus. It seems really strange.

@clomia commented on GitHub (Sep 8, 2025): It still doesn't work, but I found the problem. In `claude-sonnet-4-20250514`, thinking works well as you mentioned. However, in `claude opus` models, errors occur. ``` AI_APICallError: max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-20250514 ``` ``` AI_APICallError: max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805 ``` According to the Anthropic documentation, both opus models support Extended thinking, but I don't understand why it doesn't work only with opus. It seems really strange.
yindo commented 2026-02-16 17:31:57 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Sep 8, 2025):

@clomia okay last request, can you run this?

opencode run "hello" --model anthropic/claude-opus-4-1-20250805 --print-logs

and show me output

@rekram1-node commented on GitHub (Sep 8, 2025): @clomia okay last request, can you run this? ``` opencode run "hello" --model anthropic/claude-opus-4-1-20250805 --print-logs ``` and show me output
yindo commented 2026-02-16 17:31:57 -05:00
Author
Owner
Copy Link
Copy Source

@clomia commented on GitHub (Sep 8, 2025):

❯ opencode run "hello" --model anthropic/claude-opus-4-1-20250805 --print-logs

INFO  2025-09-08T04:05:42 +40ms service=default version=0.5.12 args=["run","hello","--model","anthropic/claude-opus-4-1-20250805","--print-logs"] opencode
INFO  2025-09-08T04:05:42 +0ms service=app cwd=/Users/jeonghoowon/dev/agent-system creating
INFO  2025-09-08T04:05:42 +1ms service=app git=/Users/jeonghoowon/dev/agent-system git
INFO  2025-09-08T04:05:42 +1ms service=bus type=storage.write subscribing
INFO  2025-09-08T04:05:42 +0ms service=app name=bus registering service
INFO  2025-09-08T04:05:42 +0ms service=format init
INFO  2025-09-08T04:05:42 +0ms service=bus type=file.edited subscribing
INFO  2025-09-08T04:05:42 +0ms service=bus type=* subscribing
INFO  2025-09-08T04:05:42 +0ms service=config.hooks init
INFO  2025-09-08T04:05:42 +0ms service=bus type=file.edited subscribing
INFO  2025-09-08T04:05:42 +0ms service=bus type=session.idle subscribing
INFO  2025-09-08T04:05:42 +0ms service=app name=lsp registering service
INFO  2025-09-08T04:05:42 +2ms service=app name=config registering service
INFO  2025-09-08T04:05:42 +1ms service=session id=ses_6d87fb977ffe4t8lAGRnplye3K version=0.5.12 title=New session - 2025-09-08T04:05:42.153Z time={"created":1757304342153,"updated":1757304342153} created
INFO  2025-09-08T04:05:42 +0ms service=app name=session registering service
INFO  2025-09-08T04:05:42 +0ms service=app name=storage registering service
INFO  2025-09-08T04:05:42 +0ms service=config path=/Users/jeonghoowon/.config/opencode/config.json loading
INFO  2025-09-08T04:05:42 +0ms service=config path=/Users/jeonghoowon/.config/opencode/opencode.json loading
INFO  2025-09-08T04:05:42 +4ms service=config path=/Users/jeonghoowon/.config/opencode/opencode.jsonc loading
INFO  2025-09-08T04:05:42 +1ms service=bus type=storage.write publishing
INFO  2025-09-08T04:05:42 +0ms service=app name=plugin registering service
INFO  2025-09-08T04:05:42 +1ms service=config path=/Users/jeonghoowon/dev/agent-system/opencode.json loading
INFO  2025-09-08T04:05:42 +3ms service=config $schema=https://opencode.ai/config.json mcp={"firecrawl-mcp":{"type":"local","command":["npx","-y","firecrawl-mcp"],"environment":{"FIRECRAWL_API_KEY":"fc-348813255c7e4365b7e83aad95886f7e"}},"context7":{"type":"local","command":["npx","-y","@upstash/context7-mcp","--api-key","ctx7sk-c13b65cd-5d1e-492c-978e-ba9dc36f1e14"]},"playwright":{"type":"local","command":["npx","@playwright/mcp@latest"]},"firecrawl":{"type":"local","command":["npx","-y","firecrawl-mcp"],"environment":{"FIRECRAWL_API_KEY":"fc-348813255c7e4365b7e83aad95886f7e"}}} instructions=[".opencode/base-instructions.md"] keybinds={"leader":"ctrl+x","app_help":"<leader>h","app_exit":"ctrl+c,<leader>q","editor_open":"<leader>e","theme_list":"<leader>t","project_init":"<leader>i","tool_details":"<leader>d","thinking_blocks":"<leader>b","session_export":"<leader>x","session_new":"<leader>n","session_list":"<leader>l","session_timeline":"<leader>g","session_share":"<leader>s","session_unshare":"none","session_interrupt":"esc","session_compact":"<leader>c","session_child_cycle":"<leader>right","session_child_cycle_reverse":"<leader>left","messages_page_up":"pgup","messages_page_down":"pgdown","messages_half_page_up":"ctrl+alt+u","messages_half_page_down":"ctrl+alt+d","messages_first":"ctrl+g","messages_last":"ctrl+alt+g","messages_copy":"<leader>y","messages_undo":"<leader>u","messages_redo":"<leader>r","model_list":"<leader>m","model_cycle_recent":"f2","model_cycle_recent_reverse":"shift+f2","agent_list":"<leader>a","agent_cycle":"tab","agent_cycle_reverse":"shift+tab","input_clear":"ctrl+c","input_paste":"ctrl+v","input_submit":"enter","input_newline":"shift+enter,ctrl+j","switch_mode":"none","switch_mode_reverse":"none","switch_agent":"tab","switch_agent_reverse":"shift+tab","file_list":"none","file_close":"none","file_search":"none","file_diff_toggle":"none","messages_previous":"none","messages_next":"none","messages_layout_toggle":"none","messages_revert":"none"} provider={"anthropic":{"models":{"claude-opus-4-1-20250805":{"options":{"thinking":{"type":"enabled","budgetTokens":1024}}}}},"google":{"models":{"gemini-2.5-pro":{"options":{"thinkingConfig":{"thinkingBudget":32768,"includeThoughts":true}}}}}} agent={"senior-software-engineer":{"prompt":"","name":"senior-software-engineer"},"software-engineer":{"prompt":"","name":"software-engineer"},"engineering-manager":{"model":"google/gemini-2.5-pro","prompt":"","description":"소프트웨어","mode":"primary","name":"engineering-manager"}} mode={} plugin=[] username=jeonghoowon loaded
INFO  2025-09-08T04:05:42 +0ms service=lsp serverIds=typescript, vue, eslint, golang, ruby-lsp, pyright, elixir-ls, zls, csharp, rust, clangd enabled LSP servers
INFO  2025-09-08T04:05:42 +0ms service=plugin path=opencode-copilot-auth@0.0.2 loading plugin
INFO  2025-09-08T04:05:42 +1ms service=bus type=session.updated publishing
INFO  2025-09-08T04:05:42 +0ms service=app name=agent registering service
INFO  2025-09-08T04:05:42 +0ms service=bus type=message.part.updated subscribing
INFO  2025-09-08T04:05:42 +0ms service=bus type=session.error subscribing
INFO  2025-09-08T04:05:42 +1ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K chatting
INFO  2025-09-08T04:05:42 +2ms service=plugin path=opencode-anthropic-auth@0.0.2 loading plugin
INFO  2025-09-08T04:05:42 +15ms service=bus type=storage.write publishing
INFO  2025-09-08T04:05:42 +0ms service=bus type=message.updated publishing
INFO  2025-09-08T04:05:42 +1ms service=bus type=storage.write publishing
INFO  2025-09-08T04:05:42 +0ms service=bus type=message.part.updated publishing
INFO  2025-09-08T04:05:42 +0ms service=bus type=storage.write publishing
INFO  2025-09-08T04:05:42 +0ms service=bus type=session.updated publishing
INFO  2025-09-08T04:05:42 +0ms service=app name=provider registering service
INFO  2025-09-08T04:05:42 +1ms service=models.dev file={} refreshing
INFO  2025-09-08T04:05:42 +1ms service=provider init
INFO  2025-09-08T04:05:42 +1ms service=provider providerID=xai found
INFO  2025-09-08T04:05:42 +0ms service=provider providerID=google found
INFO  2025-09-08T04:05:42 +0ms service=provider providerID=opencode found
INFO  2025-09-08T04:05:42 +0ms service=provider providerID=anthropic found
INFO  2025-09-08T04:05:42 +0ms service=provider providerID=anthropic modelID=claude-opus-4-1-20250805 getModel
INFO  2025-09-08T04:05:42 +0ms service=provider status=started providerID=anthropic getSDK
INFO  2025-09-08T04:05:42 +38ms service=provider status=completed duration=38 providerID=anthropic getSDK
INFO  2025-09-08T04:05:42 +0ms service=provider providerID=anthropic modelID=claude-opus-4-1-20250805 found
INFO  2025-09-08T04:05:42 +1ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K sessionID=ses_6d87fb977ffe4t8lAGRnplye3K locking
INFO  2025-09-08T04:05:42 +0ms service=provider providerID=anthropic modelID=claude-3-5-haiku-20241022 getModel
INFO  2025-09-08T04:05:42 +0ms service=provider status=started providerID=anthropic getSDK
INFO  2025-09-08T04:05:42 +0ms service=provider status=completed duration=0 providerID=anthropic getSDK
INFO  2025-09-08T04:05:42 +0ms service=provider providerID=anthropic modelID=claude-3-5-haiku-20241022 found
INFO  2025-09-08T04:05:42 +22ms service=bus type=storage.write publishing
INFO  2025-09-08T04:05:42 +0ms service=bus type=message.updated publishing
INFO  2025-09-08T04:05:42 +1ms service=app name=mcp registering service
INFO  2025-09-08T04:05:42 +0ms service=mcp key=firecrawl-mcp type=local found
INFO  2025-09-08T04:05:42 +477ms service=mcp key=context7 type=local found
INFO  2025-09-08T04:05:43 +418ms service=mcp key=playwright type=local found
INFO  2025-09-08T04:05:43 +0ms service=bus type=storage.write publishing
INFO  2025-09-08T04:05:43 +0ms service=bus type=session.updated publishing
INFO  2025-09-08T04:05:43 +510ms service=mcp key=firecrawl type=local found
INFO  2025-09-08T04:05:44 +372ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K type=start part
ERROR 2025-09-08T04:05:44 +378ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K error={"error":{"name":"AI_APICallError","url":"https://api.anthropic.com/v1/messages","requestBodyValues":{"model":"claude-opus-4-1-20250805","max_tokens":33024,"thinking":{"type":"enabled","budget_tokens":1024},"system":[{"type":"text","text":"You are Claude Code, Anthropic's official CLI for Claude.","cache_control":{"type":"ephemeral"}},{"type":"text","text":"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: 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 opencode\n- To give feedback, users should report the issue at https://github.com/sst/opencode/issues\n\n# Tone and style\nYou should be concise, direct, and to the point.\nYou MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or 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, just stop, rather than providing an explanation of what you did.\nAnswer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text 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...\". Here 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: [use the ls tool 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# Following conventions\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\n\n# Code style\n- IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked\n\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# 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- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.\n- Implement the solution using all tools available to you\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\n- VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CLAUDE.md so that you will know to run it next time.\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked, otherwise the user will feel that you are being too proactive.\n\n- Tool results and user messages may include <system-reminder> tags. <system-reminder> tags contain useful information and reminders. They are NOT part of the user's provided input or the tool result.\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\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 have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. When making multiple bash tool calls, you MUST send a single message with multiple tools calls to run the calls in parallel. For example, if you need to run \"git status\" and \"git diff\", send a single message with two tool calls to run the calls in parallel.\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\nHere is some useful information about the environment you are running in:\n<env>\n  Working directory: /Users/jeonghoowon/dev/agent-system\n  Is directory a git repo: yes\n  Platform: darwin\n  Today's date: Mon Sep 08 2025\n</env>\n<project>\n  opencode.json\nREADME.md\n</project>\n- 항상 한국어로 응답.\n- 완료 후 `git add . && git commit`.\n- 처음에는 List 툴로 디렉토리 구조 파악.\n- 커멘드를 백그라운드에서 실행시킨 경우 잊지말고 정리.\n- 웹 페이지는 playwright MCP를 사용해서 테스트.","cache_control":{"type":"ephemeral"}}],"messages":[{"role":"user","content":[{"type":"text","text":"hello","cache_control":{"type":"ephemeral"}}]}],"tools":[{"name":"bash","description":"Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.\n\nBefore executing the command, please follow these steps:\n\n1. Directory Verification:\n   - If the command will create new directories or files, first use the LS tool to verify the parent directory exists and is the correct location\n   - For example, before running \"mkdir foo/bar\", first use LS to check that \"foo\" exists and is the intended parent directory\n\n2. Command Execution:\n   - Always quote file paths that contain spaces with double quotes (e.g., cd \"path with spaces/file.txt\")\n   - Examples of proper quoting:\n     - cd \"/Users/name/My Documents\" (correct)\n     - cd /Users/name/My Documents (incorrect - will fail)\n     - python \"/path/with spaces/script.py\" (correct)\n     - python /path/with spaces/script.py (incorrect - will fail)\n   - After ensuring proper quoting, execute the command.\n   - Capture the output of the command.\n\nUsage notes:\n  - The command argument is required.\n  - You can specify an optional timeout in milliseconds (up to 600000ms / 10 minutes). If not specified, commands will timeout after 120000ms (2 minutes).\n  - It is very helpful if you write a clear, concise description of what this command does in 5-10 words.\n  - If the output exceeds 30000 characters, output will be truncated before being returned to you.\n  - VERY IMPORTANT: You MUST avoid using search commands like `find` and `grep`. Instead use Grep, Glob, or Task to search. You MUST avoid read tools like `cat`, `head`, `tail`, and `ls`, and use Read and LS to read files.\n  - If you _still_ need to run `grep`, STOP. ALWAYS USE ripgrep at `rg` (or /usr/bin/rg) first, which all opencode users have pre-installed.\n  - When issuing multiple commands, use the ';' or '&&' operator to separate them. DO NOT use newlines (newlines are ok in quoted strings).\n  - Try to maintain your current working directory throughout the session by using absolute paths and avoiding usage of `cd`. You may use `cd` if the User explicitly requests it.\n    <good-example>\n    pytest /foo/bar/tests\n    </good-example>\n    <bad-example>\n    cd /foo/bar && pytest tests\n    </bad-example>\n\n\n# Committing changes with git\n\nWhen the user asks you to create a new git commit, follow these steps carefully:\n\n1. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following bash commands in parallel, each using the Bash tool:\n   - Run a git status command to see all untracked files.\n   - Run a git diff command to see both staged and unstaged changes that will be committed.\n   - Run a git log command to see recent commit messages, so that you can follow this repository's commit message style.\n\n2. Analyze all staged changes (both previously staged and newly added) and draft a commit message. Wrap your analysis process in <commit_analysis> tags:\n\n<commit_analysis>\n- List the files that have been changed or added\n- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)\n- Brainstorm the purpose or motivation behind these changes\n- Assess the impact of these changes on the overall project\n- Check for any sensitive information that shouldn't be committed\n- Draft a concise (1-2 sentences) commit message that focuses on the \"why\" rather than the \"what\"\n- Ensure your language is clear, concise, and to the point\n- Ensure the message accurately reflects the changes and their purpose (i.e. \"add\" means a wholly new feature, \"update\" means an enhancement to an existing feature, \"fix\" means a bug fix, etc.)\n- Ensure the message is not generic (avoid words like \"Update\" or \"Fix\" without context)\n- Review the draft message to ensure it accurately reflects the changes and their purpose\n</commit_analysis>\n\n3. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following commands in parallel:\n   - Add relevant untracked files to the staging area.\n   - Run git status to make sure the commit succeeded.\n\n4. If the commit fails due to pre-commit hook changes, retry the commit ONCE to include these automated changes. If it fails again, it usually means a pre-commit hook is preventing the commit. If the commit succeeds but you notice that files were modified by the pre-commit hook, you MUST amend your commit to include them.\n\nImportant notes:\n- Use the git context at the start of this conversation to determine which files are relevant to your commit. Be careful not to stage and commit files (e.g. with `git add .`) that aren't relevant to your commit.\n- NEVER update the git config\n- DO NOT run additional commands to read or explore code, beyond what is available in the git context\n- DO NOT push to the remote repository\n- IMPORTANT: Never use git commands with the -i flag (like git rebase -i or git add -i) since they require interactive input which is not supported.\n- If there are no changes to commit (i.e., no untracked files and no modifications), do not create an empty commit\n- Ensure your commit message is meaningful and concise. It should explain the purpose of the changes, not just describe them.\n- Return an empty response - the user will see the git output directly\n\n# Creating pull requests\nUse the gh command via the Bash tool for ALL GitHub-related tasks including working with issues, pull requests, checks, and releases. If given a Github URL use the gh command to get the information needed.\n\nIMPORTANT: When the user asks you to create a pull request, follow these steps carefully:\n\n1. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following bash commands in parallel using the Bash tool, in order to understand the current state of the branch since it diverged from the main branch:\n   - Run a git status command to see all untracked files\n   - Run a git diff command to see both staged and unstaged changes that will be committed\n   - Check if the current branch tracks a remote branch and is up to date with the remote, so you know if you need to push to the remote\n   - Run a git log command and `git diff main...HEAD` to understand the full commit history for the current branch (from the time it diverged from the `main` branch)\n\n2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request summary. Wrap your analysis process in <pr_analysis> tags:\n\n<pr_analysis>\n- List the commits since diverging from the main branch\n- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)\n- Brainstorm the purpose or motivation behind these changes\n- Assess the impact of these changes on the overall project\n- Do not use tools to explore code, beyond what is available in the git context\n- Check for any sensitive information that shouldn't be committed\n- Draft a concise (1-2 bullet points) pull request summary that focuses on the \"why\" rather than the \"what\"\n- Ensure the summary accurately reflects all changes since diverging from the main branch\n- Ensure your language is clear, concise, and to the point\n- Ensure the summary accurately reflects the changes and their purpose (ie. \"add\" means a wholly new feature, \"update\" means an enhancement to an existing feature, \"fix\" means a bug fix, etc.)\n- Ensure the summary is not generic (avoid words like \"Update\" or \"Fix\" without context)\n- Review the draft summary to ensure it accurately reflects the changes and their purpose\n</pr_analysis>\n\n3. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following commands in parallel:\n   - Create new branch if needed\n   - Push to remote with -u flag if needed\n   - Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.\n<example>\ngh pr create --title \"the pr title\" --body \"$(cat <<'EOF'\n## Summary\n<1-3 bullet points>\n\nImportant:\n- NEVER update the git config\n- Return the PR URL when you're done, so the user can see it\n\n# Other common operations\n- View comments on a Github PR: gh api repos/foo/bar/pulls/123/comments\n","input_schema":{"type":"object","properties":{"command":{"type":"string","description":"The command to execute"},"timeout":{"type":"number","description":"Optional timeout in milliseconds"},"description":{"type":"string","description":"Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory\n\nInput: git status\nOutput: Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: mkdir foo\nOutput: Creates directory 'foo'"}},"required":["command","description"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"edit","description":"Performs exact string replacements in files. \n\nUsage:\n- You must use your `Read` tool at least once in the conversation before editing. This tool will error if you attempt an edit without reading the file. \n- When editing text from Read tool output, ensure you preserve the exact indentation (tabs/spaces) as it appears AFTER the line number prefix. The line number prefix format is: spaces + line number + tab. Everything after that tab is the actual file content to match. Never include any part of the line number prefix in the oldString or newString.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.\n- The edit will FAIL if `oldString` is not unique in the file. Either provide a larger string with more surrounding context to make it unique or use `replaceAll` to change every instance of `oldString`. \n- Use `replaceAll` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.\n","input_schema":{"type":"object","properties":{"filePath":{"type":"string","description":"The absolute path to the file to modify"},"oldString":{"type":"string","description":"The text to replace"},"newString":{"type":"string","description":"The text to replace it with (must be different from oldString)"},"replaceAll":{"type":"boolean","description":"Replace all occurrences of oldString (default false)"}},"required":["filePath","oldString","newString"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"webfetch","description":"- Fetches content from a specified URL\n- Takes a URL and a prompt as input\n- Fetches the URL content, converts HTML to markdown\n- Returns the model's response about the content\n- Use this tool when you need to retrieve and analyze web content\n\nUsage notes:\n  - IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions. All MCP-provided tools start with \"mcp__\".\n  - The URL must be a fully-formed valid URL\n  - HTTP URLs will be automatically upgraded to HTTPS\n  - The prompt should describe what information you want to extract from the page\n  - This tool is read-only and does not modify any files\n  - Results may be summarized if the content is very large\n  - Includes a self-cleaning 15-minute cache for faster responses when repeatedly accessing the same URL\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to fetch content from"},"format":{"type":"string","enum":["text","markdown","html"],"description":"The format to return the content in (text, markdown, or html)"},"timeout":{"type":"number","description":"Optional timeout in seconds (max 120)"}},"required":["url","format"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"glob","description":"- Fast file pattern matching tool that works with any codebase size\n- Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\"\n- Returns matching file paths sorted by modification time\n- Use this tool when you need to find files by name patterns\n- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead\n- You have the capability to call multiple tools in a single response. It is always better to speculatively perform multiple searches as a batch that are potentially useful.\n","input_schema":{"type":"object","properties":{"pattern":{"type":"string","description":"The glob pattern to match files against"},"path":{"type":"string","description":"The directory to search in. If not specified, the current working directory will be used. IMPORTANT: Omit this field to use the default directory. DO NOT enter \"undefined\" or \"null\" - simply omit it for the default behavior. Must be a valid directory path if provided."}},"required":["pattern"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"grep","description":"- Fast content search tool that works with any codebase size\n- Searches file contents using regular expressions\n- Supports full regex syntax (eg. \"log.*Error\", \"function\\s+\\w+\", etc.)\n- Filter files by pattern with the include parameter (eg. \"*.js\", \"*.{ts,tsx}\")\n- Returns file paths with at least one match sorted by modification time\n- Use this tool when you need to find files containing specific patterns\n- If you need to identify/count the number of matches within files, use the Bash tool with `rg` (ripgrep) directly. Do NOT use `grep`.\n- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead\n","input_schema":{"type":"object","properties":{"pattern":{"type":"string","description":"The regex pattern to search for in file contents"},"path":{"type":"string","description":"The directory to search in. Defaults to the current working directory."},"include":{"type":"string","description":"File pattern to include in the search (e.g. \"*.js\", \"*.{ts,tsx}\")"}},"required":["pattern"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"list","description":"Lists files and directories in a given path. The path parameter must be an absolute path, not a relative path. You can optionally provide an array of glob patterns to ignore with the ignore parameter. You should generally prefer the Glob and Grep tools, if you know which directories to search.\n","input_schema":{"type":"object","properties":{"path":{"type":"string","description":"The absolute path to the directory to list (must be absolute, not relative)"},"ignore":{"type":"array","items":{"type":"string"},"description":"List of glob patterns to ignore"}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"read","description":"Reads a file from the local filesystem. You can access any file directly by using this tool.\nAssume 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.\n\nUsage:\n- The filePath parameter must be an absolute path, not a relative path\n- By default, it reads up to 2000 lines starting from the beginning of the file\n- 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\n- Any lines longer than 2000 characters will be truncated\n- Results are returned using cat -n format, with line numbers starting at 1\n- This tool cannot read binary files, including images\n- 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. \n- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents.\n","input_schema":{"type":"object","properties":{"filePath":{"type":"string","description":"The path to the file to read"},"offset":{"type":"number","description":"The line number to start reading from (0-based)"},"limit":{"type":"number","description":"The number of lines to read (defaults to 2000)"}},"required":["filePath"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"write","description":"Writes a file to the local filesystem.\n\nUsage:\n- This tool will overwrite the existing file if there is one at the provided path.\n- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.\n- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked.\n","input_schema":{"type":"object","properties":{"filePath":{"type":"string","description":"The absolute path to the file to write (must be absolute, not relative)"},"content":{"type":"string","description":"The content to write to the file"}},"required":["filePath","content"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"todowrite","description":"Use this tool to create and manage a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.\nIt also helps the user understand the progress of the task and overall progress of their requests.\n\n## When to Use This Tool\nUse this tool proactively in these scenarios:\n\n1. Complex multi-step tasks - When a task requires 3 or more distinct steps or actions\n2. Non-trivial and complex tasks - Tasks that require careful planning or multiple operations\n3. User explicitly requests todo list - When the user directly asks you to use the todo list\n4. User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)\n5. After receiving new instructions - Immediately capture user requirements as todos. Feel free to edit the todo list based on new information.\n6. After completing a task - Mark it complete and add any new follow-up tasks\n7. When you start working on a new task, mark the todo as in_progress. Ideally you should only have one todo as in_progress at a time. Complete existing tasks before starting new ones.\n\n## When NOT to Use This Tool\n\nSkip using this tool when:\n1. There is only a single, straightforward task\n2. The task is trivial and tracking it provides no organizational benefit\n3. The task can be completed in less than 3 trivial steps\n4. The task is purely conversational or informational\n\nNOTE 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.\n\n## Examples of When to Use the Todo List\n\n<example>\nUser: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you're done!\nAssistant: I'll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.\n*Creates todo list with the following items:*\n1. Create dark mode toggle component in Settings page\n2. Add dark mode state management (context/store)\n3. Implement CSS-in-JS styles for dark theme\n4. Update existing components to support theme switching\n5. Run tests and build process, addressing any failures or errors that occur\n*Begins working on the first task*\n\n<reasoning>\nThe assistant used the todo list because:\n1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes\n2. The user explicitly requested tests and build be run afterward\n3. The assistant inferred that tests and build need to pass by adding \"Ensure tests and build succeed\" as the final task\n</reasoning>\n</example>\n\n<example>\nUser: Help me rename the function getCwd to getCurrentWorkingDirectory across my project\nAssistant: Let me first search through your codebase to find all occurrences of 'getCwd'.\n*Uses grep or search tools to locate all instances of getCwd in the codebase*\nAssistant: I've found 15 instances of 'getCwd' across 8 different files. Let me create a todo list to track these changes.\n*Creates todo list with specific items for each file that needs updating*\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant searched to understand the scope of the task\n2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps\n3. The todo list helps ensure every instance is tracked and updated systematically\n4. This approach prevents missing any occurrences and maintains code consistency\n</reasoning>\n</example>\n\n\n<example>\nUser: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.\nAssistant: I'll help implement these features. First, let's add all the features to the todo list.\n*Creates a todo list breaking down each feature into specific tasks based on the project architecture*\nAssistant: Let's start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.\n\n<reasoning>\nThe assistant used the todo list because:\n1. The user provided multiple complex features to implement in a comma separated list\n2. The todo list helps organize these large features into manageable tasks\n3. This approach allows for tracking progress across the entire implementation\n</reasoning>\n</example>\n\n<example>\nUser: Can you help optimize my React application? It's rendering slowly and has performance issues.</user>\nAssistant: I'll help optimize your React application. First, let me examine your codebase to identify potential performance bottlenecks.\n*Reviews component structure, render patterns, state management, and data fetching*\nAssistant: After analyzing your codebase, I've identified several performance issues. Let me create a todo list to track our optimization efforts.\n*Creates todo list with items like: 1) Implement memoization for expensive calculations in ProductList, 2) Add virtualization for long lists in Dashboard, 3) Optimize image loading in Gallery component, 4) Fix state update loops in ShoppingCart, 5) Review bundle size and implement code splitting*\nLet's start by implementing memoization for the expensive calculations in your ProductList component.</assistant>\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant examined the codebase to identify specific performance issues\n2. Based on this analysis, it identified multiple optimization opportunities\n3. Performance optimization is a non-trivial task requiring multiple steps\n4. The todo list helps methodically track improvements across different components\n5. This systematic approach ensures all performance bottlenecks are addressed\n</reasoning>\n</example>\n\n## Examples of When NOT to Use the Todo List\n\n<example>\nUser: How do I print 'Hello World' in Python?\nAssistant: In Python, you can print \"Hello World\" with this simple code:\n\npython\nprint(\"Hello World\")\n\nThis will output the text \"Hello World\" to the console when executed.</assistant>\n\n<reasoning>\nThe 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.\n</reasoning>\n</example>\n\n<example>\nUser: What does the git status command do?\nAssistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven't, and which files aren't being tracked by Git. This is a fundamental command for understanding the current state of your repository before making commits.\n\n<reasoning>\nThe assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.\n</reasoning>\n</example>\n\n<example>\nUser: Can you add a comment to the calculateTotal function to explain what it does?\nAssistant: Sure, let me add a comment to the calculateTotal function to explain what it does.\n* Uses the Edit tool to add a comment to the calculateTotal function *\n\n<reasoning>\nThe assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn't require tracking multiple steps or systematic organization.\n</reasoning>\n</example>\n\n<example>\nUser: Run npm install for me and tell me what happens.\nAssistant: I'll run the npm install command for you.\n\n*Executes: npm install*\n\nThe command completed successfully. Here's the output:\n[Output of npm install command]\n\nAll dependencies have been installed according to your package.json file.\n\n<reasoning>\nThe assistant did not use the todo list because this is a single command execution with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward task.\n</reasoning>\n</example>\n\n## Task States and Management\n\n1. **Task States**: Use these states to track progress:\n   - pending: Task not yet started\n   - in_progress: Currently working on (limit to ONE task at a time)\n   - completed: Task finished successfully\n   - cancelled: Task no longer needed\n\n2. **Task Management**:\n   - Update task status in real-time as you work\n   - Mark tasks complete IMMEDIATELY after finishing (don't batch completions)\n   - Only have ONE task in_progress at any time\n   - Complete current tasks before starting new ones\n   - Cancel tasks that become irrelevant\n\n3. **Task Breakdown**:\n   - Create specific, actionable items\n   - Break complex tasks into smaller, manageable steps\n   - Use clear, descriptive task names\n\nWhen in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.\n\n","input_schema":{"type":"object","properties":{"todos":{"type":"array","items":{"type":"object","properties":{"content":{"type":"string","description":"Brief description of the task"},"status":{"type":"string","description":"Current status of the task: pending, in_progress, completed, cancelled"},"priority":{"type":"string","description":"Priority level of the task: high, medium, low"},"id":{"type":"string","description":"Unique identifier for the todo item"}},"required":["content","status","priority","id"],"additionalProperties":false},"description":"The updated todo list"}},"required":["todos"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"todoread","description":"Use this tool to read your todo list","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"task","description":"Launch a new agent to handle complex, multi-step tasks autonomously.\n\nAvailable agent types and the tools they have access to:\n- general: General-purpose agent for researching complex questions, searching for code, 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.\n- senior-software-engineer: This subagent should only be called manually by the user.\n- software-engineer: This subagent should only be called manually by the user.\n\nWhen using the Task tool, you must specify a subagent_type parameter to select which agent type to use.\n\nWhen to use the Agent tool:\n- 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\")\n\nWhen NOT to use the Agent tool:\n- 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\n- If you are searching for a specific class definition like \"class Foo\", use the Glob tool instead, to find the match more quickly\n- If you are searching for code 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\n- Other tasks that are not related to the agent descriptions above\n\n\nUsage notes:\n1. Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses\n2. 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.\n3. 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.\n4. The agent's outputs should generally be trusted\n5. Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent\n6. 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.\n\nExample usage (NOTE: The agents below are fictional examples for illustration only - use the actual agents listed above):\n\n<example_agent_descriptions>\n\"code-reviewer\": use this agent after you are done writing a signficant piece of code\n\"greeting-responder\": use this agent when to respond to user greetings with a friendly joke\n</example_agent_description>\n\n<example>\nuser: \"Please write a function that checks if a number is prime\"\nassistant: Sure let me write a function that checks if a number is prime\nassistant: First let me use the Write tool to write a function that checks if a number is prime\nassistant: I'm going to use the Write tool to write the following code:\n<code>\nfunction isPrime(n) {\n  if (n <= 1) return false\n  for (let i = 2; i * i <= n; i++) {\n    if (n % i === 0) return false\n  }\n  return true\n}\n</code>\n<commentary>\nSince a signficant piece of code was written and the task was completed, now use the code-reviewer agent to review the code\n</commentary>\nassistant: Now let me use the code-reviewer agent to review the code\nassistant: Uses the Task tool to launch the code-reviewer agent\n</example>\n\n<example>\nuser: \"Hello\"\n<commentary>\nSince the user is greeting, use the greeting-responder agent to respond with a friendly joke\n</commentary>\nassistant: \"I'm going to use the Task tool to launch the with the greeting-responder agent\"\n</example>\n","input_schema":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 words) description of the task"},"prompt":{"type":"string","description":"The task for the agent to perform"},"subagent_type":{"type":"string","description":"The type of specialized agent to use for this task"}},"required":["description","prompt","subagent_type"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"firecrawl-mcp_firecrawl_scrape","description":"\nScrape content from a single URL with advanced options. \nThis is the most powerful, fastest and most reliable scraper tool, if available you should always default to using this tool for any web scraping needs.\n\n**Best for:** Single page content extraction, when you know exactly which page contains the information.\n**Not recommended for:** Multiple pages (use batch_scrape), unknown page (use search), structured data (use extract).\n**Common mistakes:** Using scrape for a list of URLs (use batch_scrape instead). If batch scrape doesnt work, just use scrape and call it multiple times.\n**Prompt Example:** \"Get the content of the page at https://example.com.\"\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_scrape\",\n  \"arguments\": {\n    \"url\": \"https://example.com\",\n    \"formats\": [\"markdown\"],\n    \"maxAge\": 172800000\n  }\n}\n```\n**Performance:** Add maxAge parameter for 500% faster scrapes using cached data.\n**Returns:** Markdown, HTML, or other formats as specified.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to scrape"},"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary","changeTracking"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean","default":true,"description":"Extract only the main content, filtering out navigation, footers, etc."},"includeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to specifically include in extraction"},"excludeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to exclude from extraction"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content to load"},"actions":{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["wait","click","screenshot","write","press","scroll","scrape","executeJavascript"],"description":"Type of action to perform"},"selector":{"type":"string","description":"CSS selector for the target element"},"milliseconds":{"type":"number","description":"Time to wait in milliseconds (for wait action)"},"text":{"type":"string","description":"Text to write (for write action)"},"key":{"type":"string","description":"Key to press (for press action)"},"direction":{"type":"string","enum":["up","down"],"description":"Scroll direction"},"script":{"type":"string","description":"JavaScript code to execute"},"fullPage":{"type":"boolean","description":"Take full page screenshot"}},"required":["type"]},"description":"List of actions to perform before scraping"},"mobile":{"type":"boolean","description":"Use mobile viewport"},"skipTlsVerification":{"type":"boolean","description":"Skip TLS certificate verification"},"removeBase64Images":{"type":"boolean","description":"Remove base64 encoded images from output"},"location":{"type":"object","properties":{"country":{"type":"string","description":"Country code for geolocation"},"languages":{"type":"array","items":{"type":"string"},"description":"Language codes for content"}},"description":"Location settings for scraping"},"storeInCache":{"type":"boolean","default":true,"description":"If true, the page will be stored in the Firecrawl index and cache. Setting this to false is useful if your scraping activity may have data protection concerns."},"maxAge":{"type":"number","default":172800000,"description":"Maximum age in milliseconds for cached content. Use cached data if available and younger than maxAge, otherwise scrape fresh. Enables 500% faster scrapes for recently cached pages. Default: 172800000"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_map","description":"\nMap a website to discover all indexed URLs on the site.\n\n**Best for:** Discovering URLs on a website before deciding what to scrape; finding specific sections of a website.\n**Not recommended for:** When you already know which specific URL you need (use scrape or batch_scrape); when you need the content of the pages (use scrape after mapping).\n**Common mistakes:** Using crawl to discover URLs instead of map.\n**Prompt Example:** \"List all URLs on example.com.\"\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_map\",\n  \"arguments\": {\n    \"url\": \"https://example.com\"\n  }\n}\n```\n**Returns:** Array of URLs found on the site.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for URL discovery"},"search":{"type":"string","description":"Optional search term to filter URLs"},"sitemap":{"type":"string","enum":["include","skip","only"],"description":"Sitemap handling: \"include\" - use sitemap + find other pages (default), \"skip\" - ignore sitemap completely, \"only\" - only return sitemap URLs"},"includeSubdomains":{"type":"boolean","description":"Include URLs from subdomains in results"},"limit":{"type":"number","description":"Maximum number of URLs to return"},"ignoreQueryParameters":{"type":"boolean","default":true,"description":"Do not return URLs with query parameters"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_crawl","description":"\n Starts a crawl job on a website and extracts content from all pages.\n \n **Best for:** Extracting content from multiple related pages, when you need comprehensive coverage.\n **Not recommended for:** Extracting content from a single page (use scrape); when token limits are a concern (use map + batch_scrape); when you need fast results (crawling can be slow).\n **Warning:** Crawl responses can be very large and may exceed token limits. Limit the crawl depth and number of pages, or use map + batch_scrape for better control.\n **Common mistakes:** Setting limit or maxDiscoveryDepth too high (causes token overflow) or too low (causes missing pages); using crawl for a single page (use scrape instead). Using a /* wildcard is not recommended.\n **Prompt Example:** \"Get all blog posts from the first two levels of example.com/blog.\"\n **Usage Example:**\n ```json\n {\n   \"name\": \"firecrawl_crawl\",\n   \"arguments\": {\n     \"url\": \"https://example.com/blog/*\",\n     \"maxDiscoveryDepth\": 5,\n     \"limit\": 20,\n     \"allowExternalLinks\": false,\n     \"deduplicateSimilarURLs\": true,\n     \"sitemap\": \"include\"\n   }\n }\n ```\n **Returns:** Operation ID for status checking; use firecrawl_check_crawl_status to check progress.\n ","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for the crawl"},"prompt":{"type":"string","description":"Natural language prompt to generate crawler options. Explicitly set parameters will override generated ones."},"excludePaths":{"type":"array","items":{"type":"string"},"description":"URL paths to exclude from crawling"},"includePaths":{"type":"array","items":{"type":"string"},"description":"Only crawl these URL paths"},"maxDiscoveryDepth":{"type":"number","description":"Maximum discovery depth to crawl. The root site and sitemapped pages have depth 0."},"sitemap":{"type":"string","enum":["skip","include","only"],"default":"include","description":"Sitemap mode when crawling. 'skip' ignores the sitemap entirely, 'include' uses sitemap plus other discovery methods (default), 'only' restricts crawling to sitemap URLs."},"limit":{"type":"number","default":10000,"description":"Maximum number of pages to crawl (default: 10000)"},"allowExternalLinks":{"type":"boolean","description":"Allow crawling links to external domains"},"allowSubdomains":{"type":"boolean","default":false,"description":"Allow crawling links to subdomains of the main domain"},"crawlEntireDomain":{"type":"boolean","default":false,"description":"When true, follow internal links to sibling or parent URLs, not just child paths"},"delay":{"type":"number","description":"Delay in seconds between scrapes to respect site rate limits"},"maxConcurrency":{"type":"number","description":"Maximum number of concurrent scrapes; if unset, team limit is used"},"webhook":{"oneOf":[{"type":"string","description":"Webhook URL to notify when crawl is complete"},{"type":"object","properties":{"url":{"type":"string","description":"Webhook URL"},"headers":{"type":"object","description":"Custom headers for webhook requests"}},"required":["url"]}]},"deduplicateSimilarURLs":{"type":"boolean","description":"Remove similar URLs during crawl"},"ignoreQueryParameters":{"type":"boolean","default":false,"description":"Do not re-scrape the same path with different (or none) query parameters"},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean"},"includeTags":{"type":"array","items":{"type":"string"}},"excludeTags":{"type":"array","items":{"type":"string"}},"waitFor":{"type":"number"}},"description":"Options for scraping each page"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_check_crawl_status","description":"\nCheck the status of a crawl job.\n\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_check_crawl_status\",\n  \"arguments\": {\n    \"id\": \"550e8400-e29b-41d4-a716-446655440000\"\n  }\n}\n```\n**Returns:** Status and progress of the crawl job, including results if available.\n","input_schema":{"type":"object","properties":{"id":{"type":"string","description":"Crawl job ID to check"}},"required":["id"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_search","description":"\nSearch the web and optionally extract content from search results. This is the most powerful web search tool available, and if available you should always default to using this tool for any web search needs.\n\n**Best for:** Finding specific information across multiple websites, when you don't know which website has the information; when you need the most relevant content for a query.\n**Not recommended for:** When you need to search the filesystem. When you already know which website to scrape (use scrape); when you need comprehensive coverage of a single website (use map or crawl.\n**Common mistakes:** Using crawl or map for open-ended questions (use search instead).\n**Prompt Example:** \"Find the latest research papers on AI published in 2023.\"\n**Sources:** web, images, news, default to web unless needed images or news.\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_search\",\n  \"arguments\": {\n    \"query\": \"latest AI research papers 2023\",\n    \"limit\": 5,\n    \"lang\": \"en\",\n    \"country\": \"us\",\n    \"sources\": [\n      \"web\",\n      \"images\",\n      \"news\"\n    ],\n    \"scrapeOptions\": {\n      \"formats\": [\"markdown\"],\n      \"onlyMainContent\": true\n    }\n  }\n}\n```\n**Returns:** Array of search results (with optional scraped content).\n","input_schema":{"type":"object","properties":{"query":{"type":"string","description":"Search query string"},"limit":{"type":"number","description":"Maximum number of results to return (default: 5)"},"tbs":{"type":"string","description":"Time-based search filter"},"filter":{"type":"string","description":"Search filter"},"location":{"type":"string","description":"Location parameter for search results"},"sources":{"type":"array","description":"Sources to search. Determines which result arrays are included in the response.","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["web"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["images"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["news"]}},"required":["type"],"additionalProperties":false}]}},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string"},"schema":{"type":"object"}},"required":["type"],"additionalProperties":true}]},"description":"Content formats to extract from search results"},"onlyMainContent":{"type":"boolean","description":"Extract only the main content from results"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content"}},"description":"Options for scraping search results"}},"required":["query"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_extract","description":"\nExtract structured information from web pages using LLM capabilities. Supports both cloud AI and self-hosted LLM extraction.\n\n**Best for:** Extracting specific structured data like prices, names, details from web pages.\n**Not recommended for:** When you need the full content of a page (use scrape); when you're not looking for specific structured data.\n**Arguments:**\n- urls: Array of URLs to extract information from\n- prompt: Custom prompt for the LLM extraction\n- schema: JSON schema for structured data extraction\n- allowExternalLinks: Allow extraction from external links\n- enableWebSearch: Enable web search for additional context\n- includeSubdomains: Include subdomains in extraction\n**Prompt Example:** \"Extract the product name, price, and description from these product pages.\"\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_extract\",\n  \"arguments\": {\n    \"urls\": [\"https://example.com/page1\", \"https://example.com/page2\"],\n    \"prompt\": \"Extract product information including name, price, and description\",\n    \"schema\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"name\": { \"type\": \"string\" },\n        \"price\": { \"type\": \"number\" },\n        \"description\": { \"type\": \"string\" }\n      },\n      \"required\": [\"name\", \"price\"]\n    },\n    \"allowExternalLinks\": false,\n    \"enableWebSearch\": false,\n    \"includeSubdomains\": false\n  }\n}\n```\n**Returns:** Extracted structured data as defined by your schema.\n","input_schema":{"type":"object","properties":{"urls":{"type":"array","items":{"type":"string"},"description":"List of URLs to extract information from"},"prompt":{"type":"string","description":"Prompt for the LLM extraction"},"schema":{"type":"object","description":"JSON schema for structured data extraction"},"allowExternalLinks":{"type":"boolean","description":"Allow extraction from external links"},"enableWebSearch":{"type":"boolean","description":"Enable web search for additional context"},"includeSubdomains":{"type":"boolean","description":"Include subdomains in extraction"}},"required":["urls"],"additionalProperties":false}},{"name":"context7_resolve_library_id","description":"Resolves a package/product name to a Context7-compatible library ID and returns a list of matching libraries.\n\nYou MUST call this function before 'get-library-docs' to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nSelection Process:\n1. Analyze the query to understand what library/package the user is looking for\n2. Return the most relevant match based on:\n- Name similarity to the query (exact matches prioritized)\n- Description relevance to the query's intent\n- Documentation coverage (prioritize libraries with higher Code Snippet counts)\n- Trust score (consider libraries with scores of 7-10 more authoritative)\n\nResponse Format:\n- Return the selected library ID in a clearly marked section\n- Provide a brief explanation for why this library was chosen\n- If multiple good matches exist, acknowledge this but proceed with the most relevant one\n- If no good matches exist, clearly state this and suggest query refinements\n\nFor ambiguous queries, request clarification before proceeding with a best-guess match.","input_schema":{"type":"object","properties":{"libraryName":{"type":"string","description":"Library name to search for and retrieve a Context7-compatible library ID."}},"required":["libraryName"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"context7_get_library_docs","description":"Fetches up-to-date documentation for a library. You must call 'resolve-library-id' first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.","input_schema":{"type":"object","properties":{"context7CompatibleLibraryID":{"type":"string","description":"Exact Context7-compatible library ID (e.g., '/mongodb/docs', '/vercel/next.js', '/supabase/supabase', '/vercel/next.js/v14.3.0-canary.87') retrieved from 'resolve-library-id' or directly from user query in the format '/org/project' or '/org/project/version'."},"topic":{"type":"string","description":"Topic to focus documentation on (e.g., 'hooks', 'routing')."},"tokens":{"type":"number","description":"Maximum number of tokens of documentation to retrieve (default: 5000). Higher values provide more context but consume more tokens."}},"required":["context7CompatibleLibraryID"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_close","description":"Close the page","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_resize","description":"Resize the browser window","input_schema":{"type":"object","properties":{"width":{"type":"number","description":"Width of the browser window"},"height":{"type":"number","description":"Height of the browser window"}},"required":["width","height"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_console_messages","description":"Returns all console messages","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_handle_dialog","description":"Handle a dialog","input_schema":{"type":"object","properties":{"accept":{"type":"boolean","description":"Whether to accept the dialog."},"promptText":{"type":"string","description":"The text of the prompt in case of a prompt dialog."}},"required":["accept"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_evaluate","description":"Evaluate JavaScript expression on page or element","input_schema":{"type":"object","properties":{"function":{"type":"string","description":"() => { /* code */ } or (element) => { /* code */ } when element is provided"},"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["function"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_file_upload","description":"Upload one or multiple files","input_schema":{"type":"object","properties":{"paths":{"type":"array","items":{"type":"string"},"description":"The absolute paths to the files to upload. Can be a single file or multiple files."}},"required":["paths"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_fill_form","description":"Fill multiple form fields","input_schema":{"type":"object","properties":{"fields":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Human-readable field name"},"type":{"type":"string","enum":["textbox","checkbox","radio","combobox","slider"],"description":"Type of the field"},"ref":{"type":"string","description":"Exact target field reference from the page snapshot"},"value":{"type":"string","description":"Value to fill in the field. If the field is a checkbox, the value should be `true` or `false`. If the field is a combobox, the value should be the text of the option."}},"required":["name","type","ref","value"],"additionalProperties":false},"description":"Fields to fill in"}},"required":["fields"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_install","description":"Install the browser specified in the config. Call this if you get an error about the browser not being installed.","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_press_key","description":"Press a key on the keyboard","input_schema":{"type":"object","properties":{"key":{"type":"string","description":"Name of the key to press or a character to generate, such as `ArrowLeft` or `a`"}},"required":["key"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_type","description":"Type text into editable element","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"text":{"type":"string","description":"Text to type into the element"},"submit":{"type":"boolean","description":"Whether to submit entered text (press Enter after)"},"slowly":{"type":"boolean","description":"Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once."}},"required":["element","ref","text"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_navigate","description":"Navigate to a URL","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to navigate to"}},"required":["url"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_navigate_back","description":"Go back to the previous page","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_network_requests","description":"Returns all network requests since loading the page","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_take_screenshot","description":"Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.","input_schema":{"type":"object","properties":{"type":{"type":"string","enum":["png","jpeg"],"default":"png","description":"Image format for the screenshot. Default is png."},"filename":{"type":"string","description":"File name to save the screenshot to. Defaults to `page-{timestamp}.{png|jpeg}` if not specified."},"element":{"type":"string","description":"Human-readable element description used to obtain permission to screenshot the element. If not provided, the screenshot will be taken of viewport. If element is provided, ref must be provided too."},"ref":{"type":"string","description":"Exact target element reference from the page snapshot. If not provided, the screenshot will be taken of viewport. If ref is provided, element must be provided too."},"fullPage":{"type":"boolean","description":"When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots."}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_snapshot","description":"Capture accessibility snapshot of the current page, this is better than screenshot","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_click","description":"Perform click on a web page","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"doubleClick":{"type":"boolean","description":"Whether to perform a double click instead of a single click"},"button":{"type":"string","enum":["left","right","middle"],"description":"Button to click, defaults to left"}},"required":["element","ref"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_drag","description":"Perform drag and drop between two elements","input_schema":{"type":"object","properties":{"startElement":{"type":"string","description":"Human-readable source element description used to obtain the permission to interact with the element"},"startRef":{"type":"string","description":"Exact source element reference from the page snapshot"},"endElement":{"type":"string","description":"Human-readable target element description used to obtain the permission to interact with the element"},"endRef":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["startElement","startRef","endElement","endRef"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_hover","description":"Hover over element on page","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["element","ref"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_select_option","description":"Select an option in a dropdown","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"values":{"type":"array","items":{"type":"string"},"description":"Array of values to select in the dropdown. This can be a single value or multiple values."}},"required":["element","ref","values"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_tabs","description":"List, create, close, or select a browser tab.","input_schema":{"type":"object","properties":{"action":{"type":"string","enum":["list","new","close","select"],"description":"Operation to perform"},"index":{"type":"number","description":"Tab index, used for close/select. If omitted for close, current tab is closed."}},"required":["action"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_wait_for","description":"Wait for text to appear or disappear or a specified time to pass","input_schema":{"type":"object","properties":{"time":{"type":"number","description":"The time to wait in seconds"},"text":{"type":"string","description":"The text to wait for"},"textGone":{"type":"string","description":"The text to wait for to disappear"}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"firecrawl_firecrawl_scrape","description":"\nScrape content from a single URL with advanced options. \nThis is the most powerful, fastest and most reliable scraper tool, if available you should always default to using this tool for any web scraping needs.\n\n**Best for:** Single page content extraction, when you know exactly which page contains the information.\n**Not recommended for:** Multiple pages (use batch_scrape), unknown page (use search), structured data (use extract).\n**Common mistakes:** Using scrape for a list of URLs (use batch_scrape instead). If batch scrape doesnt work, just use scrape and call it multiple times.\n**Prompt Example:** \"Get the content of the page at https://example.com.\"\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_scrape\",\n  \"arguments\": {\n    \"url\": \"https://example.com\",\n    \"formats\": [\"markdown\"],\n    \"maxAge\": 172800000\n  }\n}\n```\n**Performance:** Add maxAge parameter for 500% faster scrapes using cached data.\n**Returns:** Markdown, HTML, or other formats as specified.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to scrape"},"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary","changeTracking"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean","default":true,"description":"Extract only the main content, filtering out navigation, footers, etc."},"includeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to specifically include in extraction"},"excludeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to exclude from extraction"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content to load"},"actions":{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["wait","click","screenshot","write","press","scroll","scrape","executeJavascript"],"description":"Type of action to perform"},"selector":{"type":"string","description":"CSS selector for the target element"},"milliseconds":{"type":"number","description":"Time to wait in milliseconds (for wait action)"},"text":{"type":"string","description":"Text to write (for write action)"},"key":{"type":"string","description":"Key to press (for press action)"},"direction":{"type":"string","enum":["up","down"],"description":"Scroll direction"},"script":{"type":"string","description":"JavaScript code to execute"},"fullPage":{"type":"boolean","description":"Take full page screenshot"}},"required":["type"]},"description":"List of actions to perform before scraping"},"mobile":{"type":"boolean","description":"Use mobile viewport"},"skipTlsVerification":{"type":"boolean","description":"Skip TLS certificate verification"},"removeBase64Images":{"type":"boolean","description":"Remove base64 encoded images from output"},"location":{"type":"object","properties":{"country":{"type":"string","description":"Country code for geolocation"},"languages":{"type":"array","items":{"type":"string"},"description":"Language codes for content"}},"description":"Location settings for scraping"},"storeInCache":{"type":"boolean","default":true,"description":"If true, the page will be stored in the Firecrawl index and cache. Setting this to false is useful if your scraping activity may have data protection concerns."},"maxAge":{"type":"number","default":172800000,"description":"Maximum age in milliseconds for cached content. Use cached data if available and younger than maxAge, otherwise scrape fresh. Enables 500% faster scrapes for recently cached pages. Default: 172800000"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_map","description":"\nMap a website to discover all indexed URLs on the site.\n\n**Best for:** Discovering URLs on a website before deciding what to scrape; finding specific sections of a website.\n**Not recommended for:** When you already know which specific URL you need (use scrape or batch_scrape); when you need the content of the pages (use scrape after mapping).\n**Common mistakes:** Using crawl to discover URLs instead of map.\n**Prompt Example:** \"List all URLs on example.com.\"\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_map\",\n  \"arguments\": {\n    \"url\": \"https://example.com\"\n  }\n}\n```\n**Returns:** Array of URLs found on the site.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for URL discovery"},"search":{"type":"string","description":"Optional search term to filter URLs"},"sitemap":{"type":"string","enum":["include","skip","only"],"description":"Sitemap handling: \"include\" - use sitemap + find other pages (default), \"skip\" - ignore sitemap completely, \"only\" - only return sitemap URLs"},"includeSubdomains":{"type":"boolean","description":"Include URLs from subdomains in results"},"limit":{"type":"number","description":"Maximum number of URLs to return"},"ignoreQueryParameters":{"type":"boolean","default":true,"description":"Do not return URLs with query parameters"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_crawl","description":"\n Starts a crawl job on a website and extracts content from all pages.\n \n **Best for:** Extracting content from multiple related pages, when you need comprehensive coverage.\n **Not recommended for:** Extracting content from a single page (use scrape); when token limits are a concern (use map + batch_scrape); when you need fast results (crawling can be slow).\n **Warning:** Crawl responses can be very large and may exceed token limits. Limit the crawl depth and number of pages, or use map + batch_scrape for better control.\n **Common mistakes:** Setting limit or maxDiscoveryDepth too high (causes token overflow) or too low (causes missing pages); using crawl for a single page (use scrape instead). Using a /* wildcard is not recommended.\n **Prompt Example:** \"Get all blog posts from the first two levels of example.com/blog.\"\n **Usage Example:**\n ```json\n {\n   \"name\": \"firecrawl_crawl\",\n   \"arguments\": {\n     \"url\": \"https://example.com/blog/*\",\n     \"maxDiscoveryDepth\": 5,\n     \"limit\": 20,\n     \"allowExternalLinks\": false,\n     \"deduplicateSimilarURLs\": true,\n     \"sitemap\": \"include\"\n   }\n }\n ```\n **Returns:** Operation ID for status checking; use firecrawl_check_crawl_status to check progress.\n ","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for the crawl"},"prompt":{"type":"string","description":"Natural language prompt to generate crawler options. Explicitly set parameters will override generated ones."},"excludePaths":{"type":"array","items":{"type":"string"},"description":"URL paths to exclude from crawling"},"includePaths":{"type":"array","items":{"type":"string"},"description":"Only crawl these URL paths"},"maxDiscoveryDepth":{"type":"number","description":"Maximum discovery depth to crawl. The root site and sitemapped pages have depth 0."},"sitemap":{"type":"string","enum":["skip","include","only"],"default":"include","description":"Sitemap mode when crawling. 'skip' ignores the sitemap entirely, 'include' uses sitemap plus other discovery methods (default), 'only' restricts crawling to sitemap URLs."},"limit":{"type":"number","default":10000,"description":"Maximum number of pages to crawl (default: 10000)"},"allowExternalLinks":{"type":"boolean","description":"Allow crawling links to external domains"},"allowSubdomains":{"type":"boolean","default":false,"description":"Allow crawling links to subdomains of the main domain"},"crawlEntireDomain":{"type":"boolean","default":false,"description":"When true, follow internal links to sibling or parent URLs, not just child paths"},"delay":{"type":"number","description":"Delay in seconds between scrapes to respect site rate limits"},"maxConcurrency":{"type":"number","description":"Maximum number of concurrent scrapes; if unset, team limit is used"},"webhook":{"oneOf":[{"type":"string","description":"Webhook URL to notify when crawl is complete"},{"type":"object","properties":{"url":{"type":"string","description":"Webhook URL"},"headers":{"type":"object","description":"Custom headers for webhook requests"}},"required":["url"]}]},"deduplicateSimilarURLs":{"type":"boolean","description":"Remove similar URLs during crawl"},"ignoreQueryParameters":{"type":"boolean","default":false,"description":"Do not re-scrape the same path with different (or none) query parameters"},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean"},"includeTags":{"type":"array","items":{"type":"string"}},"excludeTags":{"type":"array","items":{"type":"string"}},"waitFor":{"type":"number"}},"description":"Options for scraping each page"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_check_crawl_status","description":"\nCheck the status of a crawl job.\n\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_check_crawl_status\",\n  \"arguments\": {\n    \"id\": \"550e8400-e29b-41d4-a716-446655440000\"\n  }\n}\n```\n**Returns:** Status and progress of the crawl job, including results if available.\n","input_schema":{"type":"object","properties":{"id":{"type":"string","description":"Crawl job ID to check"}},"required":["id"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_search","description":"\nSearch the web and optionally extract content from search results. This is the most powerful web search tool available, and if available you should always default to using this tool for any web search needs.\n\n**Best for:** Finding specific information across multiple websites, when you don't know which website has the information; when you need the most relevant content for a query.\n**Not recommended for:** When you need to search the filesystem. When you already know which website to scrape (use scrape); when you need comprehensive coverage of a single website (use map or crawl.\n**Common mistakes:** Using crawl or map for open-ended questions (use search instead).\n**Prompt Example:** \"Find the latest research papers on AI published in 2023.\"\n**Sources:** web, images, news, default to web unless needed images or news.\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_search\",\n  \"arguments\": {\n    \"query\": \"latest AI research papers 2023\",\n    \"limit\": 5,\n    \"lang\": \"en\",\n    \"country\": \"us\",\n    \"sources\": [\n      \"web\",\n      \"images\",\n      \"news\"\n    ],\n    \"scrapeOptions\": {\n      \"formats\": [\"markdown\"],\n      \"onlyMainContent\": true\n    }\n  }\n}\n```\n**Returns:** Array of search results (with optional scraped content).\n","input_schema":{"type":"object","properties":{"query":{"type":"string","description":"Search query string"},"limit":{"type":"number","description":"Maximum number of results to return (default: 5)"},"tbs":{"type":"string","description":"Time-based search filter"},"filter":{"type":"string","description":"Search filter"},"location":{"type":"string","description":"Location parameter for search results"},"sources":{"type":"array","description":"Sources to search. Determines which result arrays are included in the response.","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["web"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["images"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["news"]}},"required":["type"],"additionalProperties":false}]}},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string"},"schema":{"type":"object"}},"required":["type"],"additionalProperties":true}]},"description":"Content formats to extract from search results"},"onlyMainContent":{"type":"boolean","description":"Extract only the main content from results"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content"}},"description":"Options for scraping search results"}},"required":["query"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_extract","description":"\nExtract structured information from web pages using LLM capabilities. Supports both cloud AI and self-hosted LLM extraction.\n\n**Best for:** Extracting specific structured data like prices, names, details from web pages.\n**Not recommended for:** When you need the full content of a page (use scrape); when you're not looking for specific structured data.\n**Arguments:**\n- urls: Array of URLs to extract information from\n- prompt: Custom prompt for the LLM extraction\n- schema: JSON schema for structured data extraction\n- allowExternalLinks: Allow extraction from external links\n- enableWebSearch: Enable web search for additional context\n- includeSubdomains: Include subdomains in extraction\n**Prompt Example:** \"Extract the product name, price, and description from these product pages.\"\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_extract\",\n  \"arguments\": {\n    \"urls\": [\"https://example.com/page1\", \"https://example.com/page2\"],\n    \"prompt\": \"Extract product information including name, price, and description\",\n    \"schema\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"name\": { \"type\": \"string\" },\n        \"price\": { \"type\": \"number\" },\n        \"description\": { \"type\": \"string\" }\n      },\n      \"required\": [\"name\", \"price\"]\n    },\n    \"allowExternalLinks\": false,\n    \"enableWebSearch\": false,\n    \"includeSubdomains\": false\n  }\n}\n```\n**Returns:** Extracted structured data as defined by your schema.\n","input_schema":{"type":"object","properties":{"urls":{"type":"array","items":{"type":"string"},"description":"List of URLs to extract information from"},"prompt":{"type":"string","description":"Prompt for the LLM extraction"},"schema":{"type":"object","description":"JSON schema for structured data extraction"},"allowExternalLinks":{"type":"boolean","description":"Allow extraction from external links"},"enableWebSearch":{"type":"boolean","description":"Enable web search for additional context"},"includeSubdomains":{"type":"boolean","description":"Include subdomains in extraction"}},"required":["urls"],"additionalProperties":false}}],"tool_choice":{"type":"auto"},"stream":true},"statusCode":400,"responseHeaders":{"anthropic-organization-id":"b0f93d2d-241d-43f9-a6ab-cf267dcc496d","cf-cache-status":"DYNAMIC","cf-ray":"97bb91b68fdfaa78-ICN","connection":"keep-alive","content-length":"222","content-type":"application/json","date":"Mon, 08 Sep 2025 04:05:44 GMT","request-id":"req_011CSvGmhrLQKLdegCE22DTk","server":"cloudflare","strict-transport-security":"max-age=31536000; includeSubDomains; preload","via":"1.1 google","x-envoy-upstream-service-time":"39","x-robots-tag":"none","x-should-retry":"false"},"responseBody":"{\"type\":\"error\",\"error\":{\"type\":\"invalid_request_error\",\"message\":\"max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805\"},\"request_id\":\"req_011CSvGmhrLQKLdegCE22DTk\"}","isRetryable":false,"data":{"type":"error","error":{"type":"invalid_request_error","message":"max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805"}}}} streamText error
INFO  2025-09-08T04:05:44 +6ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K type=error part
ERROR 2025-09-08T04:05:44 +1ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K error={"name":"AI_APICallError","url":"https://api.anthropic.com/v1/messages","requestBodyValues":{"model":"claude-opus-4-1-20250805","max_tokens":33024,"thinking":{"type":"enabled","budget_tokens":1024},"system":[{"type":"text","text":"You are Claude Code, Anthropic's official CLI for Claude.","cache_control":{"type":"ephemeral"}},{"type":"text","text":"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: 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 opencode\n- To give feedback, users should report the issue at https://github.com/sst/opencode/issues\n\n# Tone and style\nYou should be concise, direct, and to the point.\nYou MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or 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, just stop, rather than providing an explanation of what you did.\nAnswer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text 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...\". Here 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: [use the ls tool 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# Following conventions\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\n\n# Code style\n- IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked\n\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# 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- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.\n- Implement the solution using all tools available to you\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\n- VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CLAUDE.md so that you will know to run it next time.\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked, otherwise the user will feel that you are being too proactive.\n\n- Tool results and user messages may include <system-reminder> tags. <system-reminder> tags contain useful information and reminders. They are NOT part of the user's provided input or the tool result.\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\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 have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. When making multiple bash tool calls, you MUST send a single message with multiple tools calls to run the calls in parallel. For example, if you need to run \"git status\" and \"git diff\", send a single message with two tool calls to run the calls in parallel.\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\nHere is some useful information about the environment you are running in:\n<env>\n  Working directory: /Users/jeonghoowon/dev/agent-system\n  Is directory a git repo: yes\n  Platform: darwin\n  Today's date: Mon Sep 08 2025\n</env>\n<project>\n  opencode.json\nREADME.md\n</project>\n- 항상 한국어로 응답.\n- 완료 후 `git add . && git commit`.\n- 처음에는 List 툴로 디렉토리 구조 파악.\n- 커멘드를 백그라운드에서 실행시킨 경우 잊지말고 정리.\n- 웹 페이지는 playwright MCP를 사용해서 테스트.","cache_control":{"type":"ephemeral"}}],"messages":[{"role":"user","content":[{"type":"text","text":"hello","cache_control":{"type":"ephemeral"}}]}],"tools":[{"name":"bash","description":"Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.\n\nBefore executing the command, please follow these steps:\n\n1. Directory Verification:\n   - If the command will create new directories or files, first use the LS tool to verify the parent directory exists and is the correct location\n   - For example, before running \"mkdir foo/bar\", first use LS to check that \"foo\" exists and is the intended parent directory\n\n2. Command Execution:\n   - Always quote file paths that contain spaces with double quotes (e.g., cd \"path with spaces/file.txt\")\n   - Examples of proper quoting:\n     - cd \"/Users/name/My Documents\" (correct)\n     - cd /Users/name/My Documents (incorrect - will fail)\n     - python \"/path/with spaces/script.py\" (correct)\n     - python /path/with spaces/script.py (incorrect - will fail)\n   - After ensuring proper quoting, execute the command.\n   - Capture the output of the command.\n\nUsage notes:\n  - The command argument is required.\n  - You can specify an optional timeout in milliseconds (up to 600000ms / 10 minutes). If not specified, commands will timeout after 120000ms (2 minutes).\n  - It is very helpful if you write a clear, concise description of what this command does in 5-10 words.\n  - If the output exceeds 30000 characters, output will be truncated before being returned to you.\n  - VERY IMPORTANT: You MUST avoid using search commands like `find` and `grep`. Instead use Grep, Glob, or Task to search. You MUST avoid read tools like `cat`, `head`, `tail`, and `ls`, and use Read and LS to read files.\n  - If you _still_ need to run `grep`, STOP. ALWAYS USE ripgrep at `rg` (or /usr/bin/rg) first, which all opencode users have pre-installed.\n  - When issuing multiple commands, use the ';' or '&&' operator to separate them. DO NOT use newlines (newlines are ok in quoted strings).\n  - Try to maintain your current working directory throughout the session by using absolute paths and avoiding usage of `cd`. You may use `cd` if the User explicitly requests it.\n    <good-example>\n    pytest /foo/bar/tests\n    </good-example>\n    <bad-example>\n    cd /foo/bar && pytest tests\n    </bad-example>\n\n\n# Committing changes with git\n\nWhen the user asks you to create a new git commit, follow these steps carefully:\n\n1. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following bash commands in parallel, each using the Bash tool:\n   - Run a git status command to see all untracked files.\n   - Run a git diff command to see both staged and unstaged changes that will be committed.\n   - Run a git log command to see recent commit messages, so that you can follow this repository's commit message style.\n\n2. Analyze all staged changes (both previously staged and newly added) and draft a commit message. Wrap your analysis process in <commit_analysis> tags:\n\n<commit_analysis>\n- List the files that have been changed or added\n- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)\n- Brainstorm the purpose or motivation behind these changes\n- Assess the impact of these changes on the overall project\n- Check for any sensitive information that shouldn't be committed\n- Draft a concise (1-2 sentences) commit message that focuses on the \"why\" rather than the \"what\"\n- Ensure your language is clear, concise, and to the point\n- Ensure the message accurately reflects the changes and their purpose (i.e. \"add\" means a wholly new feature, \"update\" means an enhancement to an existing feature, \"fix\" means a bug fix, etc.)\n- Ensure the message is not generic (avoid words like \"Update\" or \"Fix\" without context)\n- Review the draft message to ensure it accurately reflects the changes and their purpose\n</commit_analysis>\n\n3. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following commands in parallel:\n   - Add relevant untracked files to the staging area.\n   - Run git status to make sure the commit succeeded.\n\n4. If the commit fails due to pre-commit hook changes, retry the commit ONCE to include these automated changes. If it fails again, it usually means a pre-commit hook is preventing the commit. If the commit succeeds but you notice that files were modified by the pre-commit hook, you MUST amend your commit to include them.\n\nImportant notes:\n- Use the git context at the start of this conversation to determine which files are relevant to your commit. Be careful not to stage and commit files (e.g. with `git add .`) that aren't relevant to your commit.\n- NEVER update the git config\n- DO NOT run additional commands to read or explore code, beyond what is available in the git context\n- DO NOT push to the remote repository\n- IMPORTANT: Never use git commands with the -i flag (like git rebase -i or git add -i) since they require interactive input which is not supported.\n- If there are no changes to commit (i.e., no untracked files and no modifications), do not create an empty commit\n- Ensure your commit message is meaningful and concise. It should explain the purpose of the changes, not just describe them.\n- Return an empty response - the user will see the git output directly\n\n# Creating pull requests\nUse the gh command via the Bash tool for ALL GitHub-related tasks including working with issues, pull requests, checks, and releases. If given a Github URL use the gh command to get the information needed.\n\nIMPORTANT: When the user asks you to create a pull request, follow these steps carefully:\n\n1. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following bash commands in parallel using the Bash tool, in order to understand the current state of the branch since it diverged from the main branch:\n   - Run a git status command to see all untracked files\n   - Run a git diff command to see both staged and unstaged changes that will be committed\n   - Check if the current branch tracks a remote branch and is up to date with the remote, so you know if you need to push to the remote\n   - Run a git log command and `git diff main...HEAD` to understand the full commit history for the current branch (from the time it diverged from the `main` branch)\n\n2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request summary. Wrap your analysis process in <pr_analysis> tags:\n\n<pr_analysis>\n- List the commits since diverging from the main branch\n- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)\n- Brainstorm the purpose or motivation behind these changes\n- Assess the impact of these changes on the overall project\n- Do not use tools to explore code, beyond what is available in the git context\n- Check for any sensitive information that shouldn't be committed\n- Draft a concise (1-2 bullet points) pull request summary that focuses on the \"why\" rather than the \"what\"\n- Ensure the summary accurately reflects all changes since diverging from the main branch\n- Ensure your language is clear, concise, and to the point\n- Ensure the summary accurately reflects the changes and their purpose (ie. \"add\" means a wholly new feature, \"update\" means an enhancement to an existing feature, \"fix\" means a bug fix, etc.)\n- Ensure the summary is not generic (avoid words like \"Update\" or \"Fix\" without context)\n- Review the draft summary to ensure it accurately reflects the changes and their purpose\n</pr_analysis>\n\n3. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following commands in parallel:\n   - Create new branch if needed\n   - Push to remote with -u flag if needed\n   - Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.\n<example>\ngh pr create --title \"the pr title\" --body \"$(cat <<'EOF'\n## Summary\n<1-3 bullet points>\n\nImportant:\n- NEVER update the git config\n- Return the PR URL when you're done, so the user can see it\n\n# Other common operations\n- View comments on a Github PR: gh api repos/foo/bar/pulls/123/comments\n","input_schema":{"type":"object","properties":{"command":{"type":"string","description":"The command to execute"},"timeout":{"type":"number","description":"Optional timeout in milliseconds"},"description":{"type":"string","description":"Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory\n\nInput: git status\nOutput: Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: mkdir foo\nOutput: Creates directory 'foo'"}},"required":["command","description"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"edit","description":"Performs exact string replacements in files. \n\nUsage:\n- 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. \n- 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 oldString or newString.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.\n- The edit will FAIL if `oldString` is not unique in the file. Either provide a larger string with more surrounding context to make it unique or use `replaceAll` to change every instance of `oldString`. \n- Use `replaceAll` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.\n","input_schema":{"type":"object","properties":{"filePath":{"type":"string","description":"The absolute path to the file to modify"},"oldString":{"type":"string","description":"The text to replace"},"newString":{"type":"string","description":"The text to replace it with (must be different from oldString)"},"replaceAll":{"type":"boolean","description":"Replace all occurrences of oldString (default false)"}},"required":["filePath","oldString","newString"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"webfetch","description":"- Fetches content from a specified URL\n- Takes a URL and a prompt as input\n- Fetches the URL content, converts HTML to markdown\n- Returns the model's response about the content\n- Use this tool when you need to retrieve and analyze web content\n\nUsage notes:\n  - IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions. All MCP-provided tools start with \"mcp__\".\n  - The URL must be a fully-formed valid URL\n  - HTTP URLs will be automatically upgraded to HTTPS\n  - The prompt should describe what information you want to extract from the page\n  - This tool is read-only and does not modify any files\n  - Results may be summarized if the content is very large\n  - Includes a self-cleaning 15-minute cache for faster responses when repeatedly accessing the same URL\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to fetch content from"},"format":{"type":"string","enum":["text","markdown","html"],"description":"The format to return the content in (text, markdown, or html)"},"timeout":{"type":"number","description":"Optional timeout in seconds (max 120)"}},"required":["url","format"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"glob","description":"- Fast file pattern matching tool that works with any codebase size\n- Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\"\n- Returns matching file paths sorted by modification time\n- Use this tool when you need to find files by name patterns\n- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead\n- You have the capability to call multiple tools in a single response. It is always better to speculatively perform multiple searches as a batch that are potentially useful.\n","input_schema":{"type":"object","properties":{"pattern":{"type":"string","description":"The glob pattern to match files against"},"path":{"type":"string","description":"The directory to search in. If not specified, the current working directory will be used. IMPORTANT: Omit this field to use the default directory. DO NOT enter \"undefined\" or \"null\" - simply omit it for the default behavior. Must be a valid directory path if provided."}},"required":["pattern"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"grep","description":"- Fast content search tool that works with any codebase size\n- Searches file contents using regular expressions\n- Supports full regex syntax (eg. \"log.*Error\", \"function\\s+\\w+\", etc.)\n- Filter files by pattern with the include parameter (eg. \"*.js\", \"*.{ts,tsx}\")\n- Returns file paths with at least one match sorted by modification time\n- Use this tool when you need to find files containing specific patterns\n- If you need to identify/count the number of matches within files, use the Bash tool with `rg` (ripgrep) directly. Do NOT use `grep`.\n- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead\n","input_schema":{"type":"object","properties":{"pattern":{"type":"string","description":"The regex pattern to search for in file contents"},"path":{"type":"string","description":"The directory to search in. Defaults to the current working directory."},"include":{"type":"string","description":"File pattern to include in the search (e.g. \"*.js\", \"*.{ts,tsx}\")"}},"required":["pattern"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"list","description":"Lists files and directories in a given path. The path parameter must be an absolute path, not a relative path. You can optionally provide an array of glob patterns to ignore with the ignore parameter. You should generally prefer the Glob and Grep tools, if you know which directories to search.\n","input_schema":{"type":"object","properties":{"path":{"type":"string","description":"The absolute path to the directory to list (must be absolute, not relative)"},"ignore":{"type":"array","items":{"type":"string"},"description":"List of glob patterns to ignore"}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"read","description":"Reads a file from the local filesystem. You can access any file directly by using this tool.\nAssume this tool is able to read all files on the machine. If the User provides a path to a file assume that path is valid. It is okay to read a file that does not exist; an error will be returned.\n\nUsage:\n- The filePath parameter must be an absolute path, not a relative path\n- By default, it reads up to 2000 lines starting from the beginning of the file\n- You can optionally specify a line offset and limit (especially handy for long files), but it's recommended to read the whole file by not providing these parameters\n- Any lines longer than 2000 characters will be truncated\n- Results are returned using cat -n format, with line numbers starting at 1\n- This tool cannot read binary files, including images\n- You have the capability to call multiple tools in a single response. It is always better to speculatively read multiple files as a batch that are potentially useful. \n- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents.\n","input_schema":{"type":"object","properties":{"filePath":{"type":"string","description":"The path to the file to read"},"offset":{"type":"number","description":"The line number to start reading from (0-based)"},"limit":{"type":"number","description":"The number of lines to read (defaults to 2000)"}},"required":["filePath"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"write","description":"Writes a file to the local filesystem.\n\nUsage:\n- This tool will overwrite the existing file if there is one at the provided path.\n- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.\n- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked.\n","input_schema":{"type":"object","properties":{"filePath":{"type":"string","description":"The absolute path to the file to write (must be absolute, not relative)"},"content":{"type":"string","description":"The content to write to the file"}},"required":["filePath","content"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"todowrite","description":"Use this tool to create and manage a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.\nIt also helps the user understand the progress of the task and overall progress of their requests.\n\n## When to Use This Tool\nUse this tool proactively in these scenarios:\n\n1. Complex multi-step tasks - When a task requires 3 or more distinct steps or actions\n2. Non-trivial and complex tasks - Tasks that require careful planning or multiple operations\n3. User explicitly requests todo list - When the user directly asks you to use the todo list\n4. User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)\n5. After receiving new instructions - Immediately capture user requirements as todos. Feel free to edit the todo list based on new information.\n6. After completing a task - Mark it complete and add any new follow-up tasks\n7. When you start working on a new task, mark the todo as in_progress. Ideally you should only have one todo as in_progress at a time. Complete existing tasks before starting new ones.\n\n## When NOT to Use This Tool\n\nSkip using this tool when:\n1. There is only a single, straightforward task\n2. The task is trivial and tracking it provides no organizational benefit\n3. The task can be completed in less than 3 trivial steps\n4. The task is purely conversational or informational\n\nNOTE 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.\n\n## Examples of When to Use the Todo List\n\n<example>\nUser: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you're done!\nAssistant: I'll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.\n*Creates todo list with the following items:*\n1. Create dark mode toggle component in Settings page\n2. Add dark mode state management (context/store)\n3. Implement CSS-in-JS styles for dark theme\n4. Update existing components to support theme switching\n5. Run tests and build process, addressing any failures or errors that occur\n*Begins working on the first task*\n\n<reasoning>\nThe assistant used the todo list because:\n1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes\n2. The user explicitly requested tests and build be run afterward\n3. The assistant inferred that tests and build need to pass by adding \"Ensure tests and build succeed\" as the final task\n</reasoning>\n</example>\n\n<example>\nUser: Help me rename the function getCwd to getCurrentWorkingDirectory across my project\nAssistant: Let me first search through your codebase to find all occurrences of 'getCwd'.\n*Uses grep or search tools to locate all instances of getCwd in the codebase*\nAssistant: I've found 15 instances of 'getCwd' across 8 different files. Let me create a todo list to track these changes.\n*Creates todo list with specific items for each file that needs updating*\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant searched to understand the scope of the task\n2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps\n3. The todo list helps ensure every instance is tracked and updated systematically\n4. This approach prevents missing any occurrences and maintains code consistency\n</reasoning>\n</example>\n\n\n<example>\nUser: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.\nAssistant: I'll help implement these features. First, let's add all the features to the todo list.\n*Creates a todo list breaking down each feature into specific tasks based on the project architecture*\nAssistant: Let's start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.\n\n<reasoning>\nThe assistant used the todo list because:\n1. The user provided multiple complex features to implement in a comma separated list\n2. The todo list helps organize these large features into manageable tasks\n3. This approach allows for tracking progress across the entire implementation\n</reasoning>\n</example>\n\n<example>\nUser: Can you help optimize my React application? It's rendering slowly and has performance issues.</user>\nAssistant: I'll help optimize your React application. First, let me examine your codebase to identify potential performance bottlenecks.\n*Reviews component structure, render patterns, state management, and data fetching*\nAssistant: After analyzing your codebase, I've identified several performance issues. Let me create a todo list to track our optimization efforts.\n*Creates todo list with items like: 1) Implement memoization for expensive calculations in ProductList, 2) Add virtualization for long lists in Dashboard, 3) Optimize image loading in Gallery component, 4) Fix state update loops in ShoppingCart, 5) Review bundle size and implement code splitting*\nLet's start by implementing memoization for the expensive calculations in your ProductList component.</assistant>\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant examined the codebase to identify specific performance issues\n2. Based on this analysis, it identified multiple optimization opportunities\n3. Performance optimization is a non-trivial task requiring multiple steps\n4. The todo list helps methodically track improvements across different components\n5. This systematic approach ensures all performance bottlenecks are addressed\n</reasoning>\n</example>\n\n## Examples of When NOT to Use the Todo List\n\n<example>\nUser: How do I print 'Hello World' in Python?\nAssistant: In Python, you can print \"Hello World\" with this simple code:\n\npython\nprint(\"Hello World\")\n\nThis will output the text \"Hello World\" to the console when executed.</assistant>\n\n<reasoning>\nThe 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.\n</reasoning>\n</example>\n\n<example>\nUser: What does the git status command do?\nAssistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven't, and which files aren't being tracked by Git. This is a fundamental command for understanding the current state of your repository before making commits.\n\n<reasoning>\nThe assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.\n</reasoning>\n</example>\n\n<example>\nUser: Can you add a comment to the calculateTotal function to explain what it does?\nAssistant: Sure, let me add a comment to the calculateTotal function to explain what it does.\n* Uses the Edit tool to add a comment to the calculateTotal function *\n\n<reasoning>\nThe assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn't require tracking multiple steps or systematic organization.\n</reasoning>\n</example>\n\n<example>\nUser: Run npm install for me and tell me what happens.\nAssistant: I'll run the npm install command for you.\n\n*Executes: npm install*\n\nThe command completed successfully. Here's the output:\n[Output of npm install command]\n\nAll dependencies have been installed according to your package.json file.\n\n<reasoning>\nThe assistant did not use the todo list because this is a single command execution with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward task.\n</reasoning>\n</example>\n\n## Task States and Management\n\n1. **Task States**: Use these states to track progress:\n   - pending: Task not yet started\n   - in_progress: Currently working on (limit to ONE task at a time)\n   - completed: Task finished successfully\n   - cancelled: Task no longer needed\n\n2. **Task Management**:\n   - Update task status in real-time as you work\n   - Mark tasks complete IMMEDIATELY after finishing (don't batch completions)\n   - Only have ONE task in_progress at any time\n   - Complete current tasks before starting new ones\n   - Cancel tasks that become irrelevant\n\n3. **Task Breakdown**:\n   - Create specific, actionable items\n   - Break complex tasks into smaller, manageable steps\n   - Use clear, descriptive task names\n\nWhen in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.\n\n","input_schema":{"type":"object","properties":{"todos":{"type":"array","items":{"type":"object","properties":{"content":{"type":"string","description":"Brief description of the task"},"status":{"type":"string","description":"Current status of the task: pending, in_progress, completed, cancelled"},"priority":{"type":"string","description":"Priority level of the task: high, medium, low"},"id":{"type":"string","description":"Unique identifier for the todo item"}},"required":["content","status","priority","id"],"additionalProperties":false},"description":"The updated todo list"}},"required":["todos"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"todoread","description":"Use this tool to read your todo list","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"task","description":"Launch a new agent to handle complex, multi-step tasks autonomously.\n\nAvailable agent types and the tools they have access to:\n- general: General-purpose agent for researching complex questions, searching for code, 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.\n- senior-software-engineer: This subagent should only be called manually by the user.\n- software-engineer: This subagent should only be called manually by the user.\n\nWhen using the Task tool, you must specify a subagent_type parameter to select which agent type to use.\n\nWhen to use the Agent tool:\n- 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\")\n\nWhen NOT to use the Agent tool:\n- 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\n- If you are searching for a specific class definition like \"class Foo\", use the Glob tool instead, to find the match more quickly\n- If you are searching for code 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\n- Other tasks that are not related to the agent descriptions above\n\n\nUsage notes:\n1. Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses\n2. 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.\n3. 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.\n4. The agent's outputs should generally be trusted\n5. Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent\n6. 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.\n\nExample usage (NOTE: The agents below are fictional examples for illustration only - use the actual agents listed above):\n\n<example_agent_descriptions>\n\"code-reviewer\": use this agent after you are done writing a signficant piece of code\n\"greeting-responder\": use this agent when to respond to user greetings with a friendly joke\n</example_agent_description>\n\n<example>\nuser: \"Please write a function that checks if a number is prime\"\nassistant: Sure let me write a function that checks if a number is prime\nassistant: First let me use the Write tool to write a function that checks if a number is prime\nassistant: I'm going to use the Write tool to write the following code:\n<code>\nfunction isPrime(n) {\n  if (n <= 1) return false\n  for (let i = 2; i * i <= n; i++) {\n    if (n % i === 0) return false\n  }\n  return true\n}\n</code>\n<commentary>\nSince a signficant piece of code was written and the task was completed, now use the code-reviewer agent to review the code\n</commentary>\nassistant: Now let me use the code-reviewer agent to review the code\nassistant: Uses the Task tool to launch the code-reviewer agent\n</example>\n\n<example>\nuser: \"Hello\"\n<commentary>\nSince the user is greeting, use the greeting-responder agent to respond with a friendly joke\n</commentary>\nassistant: \"I'm going to use the Task tool to launch the with the greeting-responder agent\"\n</example>\n","input_schema":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 words) description of the task"},"prompt":{"type":"string","description":"The task for the agent to perform"},"subagent_type":{"type":"string","description":"The type of specialized agent to use for this task"}},"required":["description","prompt","subagent_type"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"firecrawl-mcp_firecrawl_scrape","description":"\nScrape content from a single URL with advanced options. \nThis is the most powerful, fastest and most reliable scraper tool, if available you should always default to using this tool for any web scraping needs.\n\n**Best for:** Single page content extraction, when you know exactly which page contains the information.\n**Not recommended for:** Multiple pages (use batch_scrape), unknown page (use search), structured data (use extract).\n**Common mistakes:** Using scrape for a list of URLs (use batch_scrape instead). If batch scrape doesnt work, just use scrape and call it multiple times.\n**Prompt Example:** \"Get the content of the page at https://example.com.\"\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_scrape\",\n  \"arguments\": {\n    \"url\": \"https://example.com\",\n    \"formats\": [\"markdown\"],\n    \"maxAge\": 172800000\n  }\n}\n```\n**Performance:** Add maxAge parameter for 500% faster scrapes using cached data.\n**Returns:** Markdown, HTML, or other formats as specified.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to scrape"},"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary","changeTracking"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean","default":true,"description":"Extract only the main content, filtering out navigation, footers, etc."},"includeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to specifically include in extraction"},"excludeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to exclude from extraction"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content to load"},"actions":{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["wait","click","screenshot","write","press","scroll","scrape","executeJavascript"],"description":"Type of action to perform"},"selector":{"type":"string","description":"CSS selector for the target element"},"milliseconds":{"type":"number","description":"Time to wait in milliseconds (for wait action)"},"text":{"type":"string","description":"Text to write (for write action)"},"key":{"type":"string","description":"Key to press (for press action)"},"direction":{"type":"string","enum":["up","down"],"description":"Scroll direction"},"script":{"type":"string","description":"JavaScript code to execute"},"fullPage":{"type":"boolean","description":"Take full page screenshot"}},"required":["type"]},"description":"List of actions to perform before scraping"},"mobile":{"type":"boolean","description":"Use mobile viewport"},"skipTlsVerification":{"type":"boolean","description":"Skip TLS certificate verification"},"removeBase64Images":{"type":"boolean","description":"Remove base64 encoded images from output"},"location":{"type":"object","properties":{"country":{"type":"string","description":"Country code for geolocation"},"languages":{"type":"array","items":{"type":"string"},"description":"Language codes for content"}},"description":"Location settings for scraping"},"storeInCache":{"type":"boolean","default":true,"description":"If true, the page will be stored in the Firecrawl index and cache. Setting this to false is useful if your scraping activity may have data protection concerns."},"maxAge":{"type":"number","default":172800000,"description":"Maximum age in milliseconds for cached content. Use cached data if available and younger than maxAge, otherwise scrape fresh. Enables 500% faster scrapes for recently cached pages. Default: 172800000"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_map","description":"\nMap a website to discover all indexed URLs on the site.\n\n**Best for:** Discovering URLs on a website before deciding what to scrape; finding specific sections of a website.\n**Not recommended for:** When you already know which specific URL you need (use scrape or batch_scrape); when you need the content of the pages (use scrape after mapping).\n**Common mistakes:** Using crawl to discover URLs instead of map.\n**Prompt Example:** \"List all URLs on example.com.\"\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_map\",\n  \"arguments\": {\n    \"url\": \"https://example.com\"\n  }\n}\n```\n**Returns:** Array of URLs found on the site.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for URL discovery"},"search":{"type":"string","description":"Optional search term to filter URLs"},"sitemap":{"type":"string","enum":["include","skip","only"],"description":"Sitemap handling: \"include\" - use sitemap + find other pages (default), \"skip\" - ignore sitemap completely, \"only\" - only return sitemap URLs"},"includeSubdomains":{"type":"boolean","description":"Include URLs from subdomains in results"},"limit":{"type":"number","description":"Maximum number of URLs to return"},"ignoreQueryParameters":{"type":"boolean","default":true,"description":"Do not return URLs with query parameters"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_crawl","description":"\n Starts a crawl job on a website and extracts content from all pages.\n \n **Best for:** Extracting content from multiple related pages, when you need comprehensive coverage.\n **Not recommended for:** Extracting content from a single page (use scrape); when token limits are a concern (use map + batch_scrape); when you need fast results (crawling can be slow).\n **Warning:** Crawl responses can be very large and may exceed token limits. Limit the crawl depth and number of pages, or use map + batch_scrape for better control.\n **Common mistakes:** Setting limit or maxDiscoveryDepth too high (causes token overflow) or too low (causes missing pages); using crawl for a single page (use scrape instead). Using a /* wildcard is not recommended.\n **Prompt Example:** \"Get all blog posts from the first two levels of example.com/blog.\"\n **Usage Example:**\n ```json\n {\n   \"name\": \"firecrawl_crawl\",\n   \"arguments\": {\n     \"url\": \"https://example.com/blog/*\",\n     \"maxDiscoveryDepth\": 5,\n     \"limit\": 20,\n     \"allowExternalLinks\": false,\n     \"deduplicateSimilarURLs\": true,\n     \"sitemap\": \"include\"\n   }\n }\n ```\n **Returns:** Operation ID for status checking; use firecrawl_check_crawl_status to check progress.\n ","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for the crawl"},"prompt":{"type":"string","description":"Natural language prompt to generate crawler options. Explicitly set parameters will override generated ones."},"excludePaths":{"type":"array","items":{"type":"string"},"description":"URL paths to exclude from crawling"},"includePaths":{"type":"array","items":{"type":"string"},"description":"Only crawl these URL paths"},"maxDiscoveryDepth":{"type":"number","description":"Maximum discovery depth to crawl. The root site and sitemapped pages have depth 0."},"sitemap":{"type":"string","enum":["skip","include","only"],"default":"include","description":"Sitemap mode when crawling. 'skip' ignores the sitemap entirely, 'include' uses sitemap plus other discovery methods (default), 'only' restricts crawling to sitemap URLs."},"limit":{"type":"number","default":10000,"description":"Maximum number of pages to crawl (default: 10000)"},"allowExternalLinks":{"type":"boolean","description":"Allow crawling links to external domains"},"allowSubdomains":{"type":"boolean","default":false,"description":"Allow crawling links to subdomains of the main domain"},"crawlEntireDomain":{"type":"boolean","default":false,"description":"When true, follow internal links to sibling or parent URLs, not just child paths"},"delay":{"type":"number","description":"Delay in seconds between scrapes to respect site rate limits"},"maxConcurrency":{"type":"number","description":"Maximum number of concurrent scrapes; if unset, team limit is used"},"webhook":{"oneOf":[{"type":"string","description":"Webhook URL to notify when crawl is complete"},{"type":"object","properties":{"url":{"type":"string","description":"Webhook URL"},"headers":{"type":"object","description":"Custom headers for webhook requests"}},"required":["url"]}]},"deduplicateSimilarURLs":{"type":"boolean","description":"Remove similar URLs during crawl"},"ignoreQueryParameters":{"type":"boolean","default":false,"description":"Do not re-scrape the same path with different (or none) query parameters"},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean"},"includeTags":{"type":"array","items":{"type":"string"}},"excludeTags":{"type":"array","items":{"type":"string"}},"waitFor":{"type":"number"}},"description":"Options for scraping each page"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_check_crawl_status","description":"\nCheck the status of a crawl job.\n\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_check_crawl_status\",\n  \"arguments\": {\n    \"id\": \"550e8400-e29b-41d4-a716-446655440000\"\n  }\n}\n```\n**Returns:** Status and progress of the crawl job, including results if available.\n","input_schema":{"type":"object","properties":{"id":{"type":"string","description":"Crawl job ID to check"}},"required":["id"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_search","description":"\nSearch the web and optionally extract content from search results. This is the most powerful web search tool available, and if available you should always default to using this tool for any web search needs.\n\n**Best for:** Finding specific information across multiple websites, when you don't know which website has the information; when you need the most relevant content for a query.\n**Not recommended for:** When you need to search the filesystem. When you already know which website to scrape (use scrape); when you need comprehensive coverage of a single website (use map or crawl.\n**Common mistakes:** Using crawl or map for open-ended questions (use search instead).\n**Prompt Example:** \"Find the latest research papers on AI published in 2023.\"\n**Sources:** web, images, news, default to web unless needed images or news.\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_search\",\n  \"arguments\": {\n    \"query\": \"latest AI research papers 2023\",\n    \"limit\": 5,\n    \"lang\": \"en\",\n    \"country\": \"us\",\n    \"sources\": [\n      \"web\",\n      \"images\",\n      \"news\"\n    ],\n    \"scrapeOptions\": {\n      \"formats\": [\"markdown\"],\n      \"onlyMainContent\": true\n    }\n  }\n}\n```\n**Returns:** Array of search results (with optional scraped content).\n","input_schema":{"type":"object","properties":{"query":{"type":"string","description":"Search query string"},"limit":{"type":"number","description":"Maximum number of results to return (default: 5)"},"tbs":{"type":"string","description":"Time-based search filter"},"filter":{"type":"string","description":"Search filter"},"location":{"type":"string","description":"Location parameter for search results"},"sources":{"type":"array","description":"Sources to search. Determines which result arrays are included in the response.","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["web"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["images"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["news"]}},"required":["type"],"additionalProperties":false}]}},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string"},"schema":{"type":"object"}},"required":["type"],"additionalProperties":true}]},"description":"Content formats to extract from search results"},"onlyMainContent":{"type":"boolean","description":"Extract only the main content from results"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content"}},"description":"Options for scraping search results"}},"required":["query"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_extract","description":"\nExtract structured information from web pages using LLM capabilities. Supports both cloud AI and self-hosted LLM extraction.\n\n**Best for:** Extracting specific structured data like prices, names, details from web pages.\n**Not recommended for:** When you need the full content of a page (use scrape); when you're not looking for specific structured data.\n**Arguments:**\n- urls: Array of URLs to extract information from\n- prompt: Custom prompt for the LLM extraction\n- schema: JSON schema for structured data extraction\n- allowExternalLinks: Allow extraction from external links\n- enableWebSearch: Enable web search for additional context\n- includeSubdomains: Include subdomains in extraction\n**Prompt Example:** \"Extract the product name, price, and description from these product pages.\"\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_extract\",\n  \"arguments\": {\n    \"urls\": [\"https://example.com/page1\", \"https://example.com/page2\"],\n    \"prompt\": \"Extract product information including name, price, and description\",\n    \"schema\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"name\": { \"type\": \"string\" },\n        \"price\": { \"type\": \"number\" },\n        \"description\": { \"type\": \"string\" }\n      },\n      \"required\": [\"name\", \"price\"]\n    },\n    \"allowExternalLinks\": false,\n    \"enableWebSearch\": false,\n    \"includeSubdomains\": false\n  }\n}\n```\n**Returns:** Extracted structured data as defined by your schema.\n","input_schema":{"type":"object","properties":{"urls":{"type":"array","items":{"type":"string"},"description":"List of URLs to extract information from"},"prompt":{"type":"string","description":"Prompt for the LLM extraction"},"schema":{"type":"object","description":"JSON schema for structured data extraction"},"allowExternalLinks":{"type":"boolean","description":"Allow extraction from external links"},"enableWebSearch":{"type":"boolean","description":"Enable web search for additional context"},"includeSubdomains":{"type":"boolean","description":"Include subdomains in extraction"}},"required":["urls"],"additionalProperties":false}},{"name":"context7_resolve_library_id","description":"Resolves a package/product name to a Context7-compatible library ID and returns a list of matching libraries.\n\nYou MUST call this function before 'get-library-docs' to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nSelection Process:\n1. Analyze the query to understand what library/package the user is looking for\n2. Return the most relevant match based on:\n- Name similarity to the query (exact matches prioritized)\n- Description relevance to the query's intent\n- Documentation coverage (prioritize libraries with higher Code Snippet counts)\n- Trust score (consider libraries with scores of 7-10 more authoritative)\n\nResponse Format:\n- Return the selected library ID in a clearly marked section\n- Provide a brief explanation for why this library was chosen\n- If multiple good matches exist, acknowledge this but proceed with the most relevant one\n- If no good matches exist, clearly state this and suggest query refinements\n\nFor ambiguous queries, request clarification before proceeding with a best-guess match.","input_schema":{"type":"object","properties":{"libraryName":{"type":"string","description":"Library name to search for and retrieve a Context7-compatible library ID."}},"required":["libraryName"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"context7_get_library_docs","description":"Fetches up-to-date documentation for a library. You must call 'resolve-library-id' first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.","input_schema":{"type":"object","properties":{"context7CompatibleLibraryID":{"type":"string","description":"Exact Context7-compatible library ID (e.g., '/mongodb/docs', '/vercel/next.js', '/supabase/supabase', '/vercel/next.js/v14.3.0-canary.87') retrieved from 'resolve-library-id' or directly from user query in the format '/org/project' or '/org/project/version'."},"topic":{"type":"string","description":"Topic to focus documentation on (e.g., 'hooks', 'routing')."},"tokens":{"type":"number","description":"Maximum number of tokens of documentation to retrieve (default: 5000). Higher values provide more context but consume more tokens."}},"required":["context7CompatibleLibraryID"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_close","description":"Close the page","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_resize","description":"Resize the browser window","input_schema":{"type":"object","properties":{"width":{"type":"number","description":"Width of the browser window"},"height":{"type":"number","description":"Height of the browser window"}},"required":["width","height"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_console_messages","description":"Returns all console messages","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_handle_dialog","description":"Handle a dialog","input_schema":{"type":"object","properties":{"accept":{"type":"boolean","description":"Whether to accept the dialog."},"promptText":{"type":"string","description":"The text of the prompt in case of a prompt dialog."}},"required":["accept"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_evaluate","description":"Evaluate JavaScript expression on page or element","input_schema":{"type":"object","properties":{"function":{"type":"string","description":"() => { /* code */ } or (element) => { /* code */ } when element is provided"},"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["function"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_file_upload","description":"Upload one or multiple files","input_schema":{"type":"object","properties":{"paths":{"type":"array","items":{"type":"string"},"description":"The absolute paths to the files to upload. Can be a single file or multiple files."}},"required":["paths"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_fill_form","description":"Fill multiple form fields","input_schema":{"type":"object","properties":{"fields":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Human-readable field name"},"type":{"type":"string","enum":["textbox","checkbox","radio","combobox","slider"],"description":"Type of the field"},"ref":{"type":"string","description":"Exact target field reference from the page snapshot"},"value":{"type":"string","description":"Value to fill in the field. If the field is a checkbox, the value should be `true` or `false`. If the field is a combobox, the value should be the text of the option."}},"required":["name","type","ref","value"],"additionalProperties":false},"description":"Fields to fill in"}},"required":["fields"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_install","description":"Install the browser specified in the config. Call this if you get an error about the browser not being installed.","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_press_key","description":"Press a key on the keyboard","input_schema":{"type":"object","properties":{"key":{"type":"string","description":"Name of the key to press or a character to generate, such as `ArrowLeft` or `a`"}},"required":["key"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_type","description":"Type text into editable element","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"text":{"type":"string","description":"Text to type into the element"},"submit":{"type":"boolean","description":"Whether to submit entered text (press Enter after)"},"slowly":{"type":"boolean","description":"Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once."}},"required":["element","ref","text"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_navigate","description":"Navigate to a URL","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to navigate to"}},"required":["url"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_navigate_back","description":"Go back to the previous page","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_network_requests","description":"Returns all network requests since loading the page","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_take_screenshot","description":"Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.","input_schema":{"type":"object","properties":{"type":{"type":"string","enum":["png","jpeg"],"default":"png","description":"Image format for the screenshot. Default is png."},"filename":{"type":"string","description":"File name to save the screenshot to. Defaults to `page-{timestamp}.{png|jpeg}` if not specified."},"element":{"type":"string","description":"Human-readable element description used to obtain permission to screenshot the element. If not provided, the screenshot will be taken of viewport. If element is provided, ref must be provided too."},"ref":{"type":"string","description":"Exact target element reference from the page snapshot. If not provided, the screenshot will be taken of viewport. If ref is provided, element must be provided too."},"fullPage":{"type":"boolean","description":"When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots."}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_snapshot","description":"Capture accessibility snapshot of the current page, this is better than screenshot","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_click","description":"Perform click on a web page","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"doubleClick":{"type":"boolean","description":"Whether to perform a double click instead of a single click"},"button":{"type":"string","enum":["left","right","middle"],"description":"Button to click, defaults to left"}},"required":["element","ref"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_drag","description":"Perform drag and drop between two elements","input_schema":{"type":"object","properties":{"startElement":{"type":"string","description":"Human-readable source element description used to obtain the permission to interact with the element"},"startRef":{"type":"string","description":"Exact source element reference from the page snapshot"},"endElement":{"type":"string","description":"Human-readable target element description used to obtain the permission to interact with the element"},"endRef":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["startElement","startRef","endElement","endRef"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_hover","description":"Hover over element on page","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["element","ref"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_select_option","description":"Select an option in a dropdown","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"values":{"type":"array","items":{"type":"string"},"description":"Array of values to select in the dropdown. This can be a single value or multiple values."}},"required":["element","ref","values"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_tabs","description":"List, create, close, or select a browser tab.","input_schema":{"type":"object","properties":{"action":{"type":"string","enum":["list","new","close","select"],"description":"Operation to perform"},"index":{"type":"number","description":"Tab index, used for close/select. If omitted for close, current tab is closed."}},"required":["action"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_wait_for","description":"Wait for text to appear or disappear or a specified time to pass","input_schema":{"type":"object","properties":{"time":{"type":"number","description":"The time to wait in seconds"},"text":{"type":"string","description":"The text to wait for"},"textGone":{"type":"string","description":"The text to wait for to disappear"}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"firecrawl_firecrawl_scrape","description":"\nScrape content from a single URL with advanced options. \nThis is the most powerful, fastest and most reliable scraper tool, if available you should always default to using this tool for any web scraping needs.\n\n**Best for:** Single page content extraction, when you know exactly which page contains the information.\n**Not recommended for:** Multiple pages (use batch_scrape), unknown page (use search), structured data (use extract).\n**Common mistakes:** Using scrape for a list of URLs (use batch_scrape instead). If batch scrape doesnt work, just use scrape and call it multiple times.\n**Prompt Example:** \"Get the content of the page at https://example.com.\"\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_scrape\",\n  \"arguments\": {\n    \"url\": \"https://example.com\",\n    \"formats\": [\"markdown\"],\n    \"maxAge\": 172800000\n  }\n}\n```\n**Performance:** Add maxAge parameter for 500% faster scrapes using cached data.\n**Returns:** Markdown, HTML, or other formats as specified.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to scrape"},"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary","changeTracking"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean","default":true,"description":"Extract only the main content, filtering out navigation, footers, etc."},"includeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to specifically include in extraction"},"excludeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to exclude from extraction"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content to load"},"actions":{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["wait","click","screenshot","write","press","scroll","scrape","executeJavascript"],"description":"Type of action to perform"},"selector":{"type":"string","description":"CSS selector for the target element"},"milliseconds":{"type":"number","description":"Time to wait in milliseconds (for wait action)"},"text":{"type":"string","description":"Text to write (for write action)"},"key":{"type":"string","description":"Key to press (for press action)"},"direction":{"type":"string","enum":["up","down"],"description":"Scroll direction"},"script":{"type":"string","description":"JavaScript code to execute"},"fullPage":{"type":"boolean","description":"Take full page screenshot"}},"required":["type"]},"description":"List of actions to perform before scraping"},"mobile":{"type":"boolean","description":"Use mobile viewport"},"skipTlsVerification":{"type":"boolean","description":"Skip TLS certificate verification"},"removeBase64Images":{"type":"boolean","description":"Remove base64 encoded images from output"},"location":{"type":"object","properties":{"country":{"type":"string","description":"Country code for geolocation"},"languages":{"type":"array","items":{"type":"string"},"description":"Language codes for content"}},"description":"Location settings for scraping"},"storeInCache":{"type":"boolean","default":true,"description":"If true, the page will be stored in the Firecrawl index and cache. Setting this to false is useful if your scraping activity may have data protection concerns."},"maxAge":{"type":"number","default":172800000,"description":"Maximum age in milliseconds for cached content. Use cached data if available and younger than maxAge, otherwise scrape fresh. Enables 500% faster scrapes for recently cached pages. Default: 172800000"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_map","description":"\nMap a website to discover all indexed URLs on the site.\n\n**Best for:** Discovering URLs on a website before deciding what to scrape; finding specific sections of a website.\n**Not recommended for:** When you already know which specific URL you need (use scrape or batch_scrape); when you need the content of the pages (use scrape after mapping).\n**Common mistakes:** Using crawl to discover URLs instead of map.\n**Prompt Example:** \"List all URLs on example.com.\"\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_map\",\n  \"arguments\": {\n    \"url\": \"https://example.com\"\n  }\n}\n```\n**Returns:** Array of URLs found on the site.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for URL discovery"},"search":{"type":"string","description":"Optional search term to filter URLs"},"sitemap":{"type":"string","enum":["include","skip","only"],"description":"Sitemap handling: \"include\" - use sitemap + find other pages (default), \"skip\" - ignore sitemap completely, \"only\" - only return sitemap URLs"},"includeSubdomains":{"type":"boolean","description":"Include URLs from subdomains in results"},"limit":{"type":"number","description":"Maximum number of URLs to return"},"ignoreQueryParameters":{"type":"boolean","default":true,"description":"Do not return URLs with query parameters"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_crawl","description":"\n Starts a crawl job on a website and extracts content from all pages.\n \n **Best for:** Extracting content from multiple related pages, when you need comprehensive coverage.\n **Not recommended for:** Extracting content from a single page (use scrape); when token limits are a concern (use map + batch_scrape); when you need fast results (crawling can be slow).\n **Warning:** Crawl responses can be very large and may exceed token limits. Limit the crawl depth and number of pages, or use map + batch_scrape for better control.\n **Common mistakes:** Setting limit or maxDiscoveryDepth too high (causes token overflow) or too low (causes missing pages); using crawl for a single page (use scrape instead). Using a /* wildcard is not recommended.\n **Prompt Example:** \"Get all blog posts from the first two levels of example.com/blog.\"\n **Usage Example:**\n ```json\n {\n   \"name\": \"firecrawl_crawl\",\n   \"arguments\": {\n     \"url\": \"https://example.com/blog/*\",\n     \"maxDiscoveryDepth\": 5,\n     \"limit\": 20,\n     \"allowExternalLinks\": false,\n     \"deduplicateSimilarURLs\": true,\n     \"sitemap\": \"include\"\n   }\n }\n ```\n **Returns:** Operation ID for status checking; use firecrawl_check_crawl_status to check progress.\n ","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for the crawl"},"prompt":{"type":"string","description":"Natural language prompt to generate crawler options. Explicitly set parameters will override generated ones."},"excludePaths":{"type":"array","items":{"type":"string"},"description":"URL paths to exclude from crawling"},"includePaths":{"type":"array","items":{"type":"string"},"description":"Only crawl these URL paths"},"maxDiscoveryDepth":{"type":"number","description":"Maximum discovery depth to crawl. The root site and sitemapped pages have depth 0."},"sitemap":{"type":"string","enum":["skip","include","only"],"default":"include","description":"Sitemap mode when crawling. 'skip' ignores the sitemap entirely, 'include' uses sitemap plus other discovery methods (default), 'only' restricts crawling to sitemap URLs."},"limit":{"type":"number","default":10000,"description":"Maximum number of pages to crawl (default: 10000)"},"allowExternalLinks":{"type":"boolean","description":"Allow crawling links to external domains"},"allowSubdomains":{"type":"boolean","default":false,"description":"Allow crawling links to subdomains of the main domain"},"crawlEntireDomain":{"type":"boolean","default":false,"description":"When true, follow internal links to sibling or parent URLs, not just child paths"},"delay":{"type":"number","description":"Delay in seconds between scrapes to respect site rate limits"},"maxConcurrency":{"type":"number","description":"Maximum number of concurrent scrapes; if unset, team limit is used"},"webhook":{"oneOf":[{"type":"string","description":"Webhook URL to notify when crawl is complete"},{"type":"object","properties":{"url":{"type":"string","description":"Webhook URL"},"headers":{"type":"object","description":"Custom headers for webhook requests"}},"required":["url"]}]},"deduplicateSimilarURLs":{"type":"boolean","description":"Remove similar URLs during crawl"},"ignoreQueryParameters":{"type":"boolean","default":false,"description":"Do not re-scrape the same path with different (or none) query parameters"},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean"},"includeTags":{"type":"array","items":{"type":"string"}},"excludeTags":{"type":"array","items":{"type":"string"}},"waitFor":{"type":"number"}},"description":"Options for scraping each page"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_check_crawl_status","description":"\nCheck the status of a crawl job.\n\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_check_crawl_status\",\n  \"arguments\": {\n    \"id\": \"550e8400-e29b-41d4-a716-446655440000\"\n  }\n}\n```\n**Returns:** Status and progress of the crawl job, including results if available.\n","input_schema":{"type":"object","properties":{"id":{"type":"string","description":"Crawl job ID to check"}},"required":["id"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_search","description":"\nSearch the web and optionally extract content from search results. This is the most powerful web search tool available, and if available you should always default to using this tool for any web search needs.\n\n**Best for:** Finding specific information across multiple websites, when you don't know which website has the information; when you need the most relevant content for a query.\n**Not recommended for:** When you need to search the filesystem. When you already know which website to scrape (use scrape); when you need comprehensive coverage of a single website (use map or crawl.\n**Common mistakes:** Using crawl or map for open-ended questions (use search instead).\n**Prompt Example:** \"Find the latest research papers on AI published in 2023.\"\n**Sources:** web, images, news, default to web unless needed images or news.\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_search\",\n  \"arguments\": {\n    \"query\": \"latest AI research papers 2023\",\n    \"limit\": 5,\n    \"lang\": \"en\",\n    \"country\": \"us\",\n    \"sources\": [\n      \"web\",\n      \"images\",\n      \"news\"\n    ],\n    \"scrapeOptions\": {\n      \"formats\": [\"markdown\"],\n      \"onlyMainContent\": true\n    }\n  }\n}\n```\n**Returns:** Array of search results (with optional scraped content).\n","input_schema":{"type":"object","properties":{"query":{"type":"string","description":"Search query string"},"limit":{"type":"number","description":"Maximum number of results to return (default: 5)"},"tbs":{"type":"string","description":"Time-based search filter"},"filter":{"type":"string","description":"Search filter"},"location":{"type":"string","description":"Location parameter for search results"},"sources":{"type":"array","description":"Sources to search. Determines which result arrays are included in the response.","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["web"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["images"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["news"]}},"required":["type"],"additionalProperties":false}]}},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string"},"schema":{"type":"object"}},"required":["type"],"additionalProperties":true}]},"description":"Content formats to extract from search results"},"onlyMainContent":{"type":"boolean","description":"Extract only the main content from results"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content"}},"description":"Options for scraping search results"}},"required":["query"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_extract","description":"\nExtract structured information from web pages using LLM capabilities. Supports both cloud AI and self-hosted LLM extraction.\n\n**Best for:** Extracting specific structured data like prices, names, details from web pages.\n**Not recommended for:** When you need the full content of a page (use scrape); when you're not looking for specific structured data.\n**Arguments:**\n- urls: Array of URLs to extract information from\n- prompt: Custom prompt for the LLM extraction\n- schema: JSON schema for structured data extraction\n- allowExternalLinks: Allow extraction from external links\n- enableWebSearch: Enable web search for additional context\n- includeSubdomains: Include subdomains in extraction\n**Prompt Example:** \"Extract the product name, price, and description from these product pages.\"\n**Usage Example:**\n```json\n{\n  \"name\": \"firecrawl_extract\",\n  \"arguments\": {\n    \"urls\": [\"https://example.com/page1\", \"https://example.com/page2\"],\n    \"prompt\": \"Extract product information including name, price, and description\",\n    \"schema\": {\n      \"type\": \"object\",\n      \"properties\": {\n        \"name\": { \"type\": \"string\" },\n        \"price\": { \"type\": \"number\" },\n        \"description\": { \"type\": \"string\" }\n      },\n      \"required\": [\"name\", \"price\"]\n    },\n    \"allowExternalLinks\": false,\n    \"enableWebSearch\": false,\n    \"includeSubdomains\": false\n  }\n}\n```\n**Returns:** Extracted structured data as defined by your schema.\n","input_schema":{"type":"object","properties":{"urls":{"type":"array","items":{"type":"string"},"description":"List of URLs to extract information from"},"prompt":{"type":"string","description":"Prompt for the LLM extraction"},"schema":{"type":"object","description":"JSON schema for structured data extraction"},"allowExternalLinks":{"type":"boolean","description":"Allow extraction from external links"},"enableWebSearch":{"type":"boolean","description":"Enable web search for additional context"},"includeSubdomains":{"type":"boolean","description":"Include subdomains in extraction"}},"required":["urls"],"additionalProperties":false}}],"tool_choice":{"type":"auto"},"stream":true},"statusCode":400,"responseHeaders":{"anthropic-organization-id":"b0f93d2d-241d-43f9-a6ab-cf267dcc496d","cf-cache-status":"DYNAMIC","cf-ray":"97bb91b68fdfaa78-ICN","connection":"keep-alive","content-length":"222","content-type":"application/json","date":"Mon, 08 Sep 2025 04:05:44 GMT","request-id":"req_011CSvGmhrLQKLdegCE22DTk","server":"cloudflare","strict-transport-security":"max-age=31536000; includeSubDomains; preload","via":"1.1 google","x-envoy-upstream-service-time":"39","x-robots-tag":"none","x-should-retry":"false"},"responseBody":"{\"type\":\"error\",\"error\":{\"type\":\"invalid_request_error\",\"message\":\"max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805\"},\"request_id\":\"req_011CSvGmhrLQKLdegCE22DTk\"}","isRetryable":false,"data":{"type":"error","error":{"type":"invalid_request_error","message":"max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805"}}}
INFO  2025-09-08T04:05:44 +20ms service=bus type=session.error publishing
Error: AI_APICallError: max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805
INFO  2025-09-08T04:05:44 +1ms service=bus type=storage.write publishing
INFO  2025-09-08T04:05:44 +0ms service=bus type=message.updated publishing
INFO  2025-09-08T04:05:44 +0ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K sessionID=ses_6d87fb977ffe4t8lAGRnplye3K unlocking
INFO  2025-09-08T04:05:44 +0ms service=bus type=session.idle publishing

INFO  2025-09-08T04:05:44 +0ms service=app name=lsp shutdown
INFO  2025-09-08T04:05:44 +0ms service=app name=session shutdown
INFO  2025-09-08T04:05:44 +1ms service=app name=mcp shutdown

Thank you for looking into it quickly.

@clomia commented on GitHub (Sep 8, 2025): ``` ❯ opencode run "hello" --model anthropic/claude-opus-4-1-20250805 --print-logs INFO 2025-09-08T04:05:42 +40ms service=default version=0.5.12 args=["run","hello","--model","anthropic/claude-opus-4-1-20250805","--print-logs"] opencode INFO 2025-09-08T04:05:42 +0ms service=app cwd=/Users/jeonghoowon/dev/agent-system creating INFO 2025-09-08T04:05:42 +1ms service=app git=/Users/jeonghoowon/dev/agent-system git INFO 2025-09-08T04:05:42 +1ms service=bus type=storage.write subscribing INFO 2025-09-08T04:05:42 +0ms service=app name=bus registering service INFO 2025-09-08T04:05:42 +0ms service=format init INFO 2025-09-08T04:05:42 +0ms service=bus type=file.edited subscribing INFO 2025-09-08T04:05:42 +0ms service=bus type=* subscribing INFO 2025-09-08T04:05:42 +0ms service=config.hooks init INFO 2025-09-08T04:05:42 +0ms service=bus type=file.edited subscribing INFO 2025-09-08T04:05:42 +0ms service=bus type=session.idle subscribing INFO 2025-09-08T04:05:42 +0ms service=app name=lsp registering service INFO 2025-09-08T04:05:42 +2ms service=app name=config registering service INFO 2025-09-08T04:05:42 +1ms service=session id=ses_6d87fb977ffe4t8lAGRnplye3K version=0.5.12 title=New session - 2025-09-08T04:05:42.153Z time={"created":1757304342153,"updated":1757304342153} created INFO 2025-09-08T04:05:42 +0ms service=app name=session registering service INFO 2025-09-08T04:05:42 +0ms service=app name=storage registering service INFO 2025-09-08T04:05:42 +0ms service=config path=/Users/jeonghoowon/.config/opencode/config.json loading INFO 2025-09-08T04:05:42 +0ms service=config path=/Users/jeonghoowon/.config/opencode/opencode.json loading INFO 2025-09-08T04:05:42 +4ms service=config path=/Users/jeonghoowon/.config/opencode/opencode.jsonc loading INFO 2025-09-08T04:05:42 +1ms service=bus type=storage.write publishing INFO 2025-09-08T04:05:42 +0ms service=app name=plugin registering service INFO 2025-09-08T04:05:42 +1ms service=config path=/Users/jeonghoowon/dev/agent-system/opencode.json loading INFO 2025-09-08T04:05:42 +3ms service=config $schema=https://opencode.ai/config.json mcp={"firecrawl-mcp":{"type":"local","command":["npx","-y","firecrawl-mcp"],"environment":{"FIRECRAWL_API_KEY":"fc-348813255c7e4365b7e83aad95886f7e"}},"context7":{"type":"local","command":["npx","-y","@upstash/context7-mcp","--api-key","ctx7sk-c13b65cd-5d1e-492c-978e-ba9dc36f1e14"]},"playwright":{"type":"local","command":["npx","@playwright/mcp@latest"]},"firecrawl":{"type":"local","command":["npx","-y","firecrawl-mcp"],"environment":{"FIRECRAWL_API_KEY":"fc-348813255c7e4365b7e83aad95886f7e"}}} instructions=[".opencode/base-instructions.md"] keybinds={"leader":"ctrl+x","app_help":"<leader>h","app_exit":"ctrl+c,<leader>q","editor_open":"<leader>e","theme_list":"<leader>t","project_init":"<leader>i","tool_details":"<leader>d","thinking_blocks":"<leader>b","session_export":"<leader>x","session_new":"<leader>n","session_list":"<leader>l","session_timeline":"<leader>g","session_share":"<leader>s","session_unshare":"none","session_interrupt":"esc","session_compact":"<leader>c","session_child_cycle":"<leader>right","session_child_cycle_reverse":"<leader>left","messages_page_up":"pgup","messages_page_down":"pgdown","messages_half_page_up":"ctrl+alt+u","messages_half_page_down":"ctrl+alt+d","messages_first":"ctrl+g","messages_last":"ctrl+alt+g","messages_copy":"<leader>y","messages_undo":"<leader>u","messages_redo":"<leader>r","model_list":"<leader>m","model_cycle_recent":"f2","model_cycle_recent_reverse":"shift+f2","agent_list":"<leader>a","agent_cycle":"tab","agent_cycle_reverse":"shift+tab","input_clear":"ctrl+c","input_paste":"ctrl+v","input_submit":"enter","input_newline":"shift+enter,ctrl+j","switch_mode":"none","switch_mode_reverse":"none","switch_agent":"tab","switch_agent_reverse":"shift+tab","file_list":"none","file_close":"none","file_search":"none","file_diff_toggle":"none","messages_previous":"none","messages_next":"none","messages_layout_toggle":"none","messages_revert":"none"} provider={"anthropic":{"models":{"claude-opus-4-1-20250805":{"options":{"thinking":{"type":"enabled","budgetTokens":1024}}}}},"google":{"models":{"gemini-2.5-pro":{"options":{"thinkingConfig":{"thinkingBudget":32768,"includeThoughts":true}}}}}} agent={"senior-software-engineer":{"prompt":"","name":"senior-software-engineer"},"software-engineer":{"prompt":"","name":"software-engineer"},"engineering-manager":{"model":"google/gemini-2.5-pro","prompt":"","description":"소프트웨어","mode":"primary","name":"engineering-manager"}} mode={} plugin=[] username=jeonghoowon loaded INFO 2025-09-08T04:05:42 +0ms service=lsp serverIds=typescript, vue, eslint, golang, ruby-lsp, pyright, elixir-ls, zls, csharp, rust, clangd enabled LSP servers INFO 2025-09-08T04:05:42 +0ms service=plugin path=opencode-copilot-auth@0.0.2 loading plugin INFO 2025-09-08T04:05:42 +1ms service=bus type=session.updated publishing INFO 2025-09-08T04:05:42 +0ms service=app name=agent registering service INFO 2025-09-08T04:05:42 +0ms service=bus type=message.part.updated subscribing INFO 2025-09-08T04:05:42 +0ms service=bus type=session.error subscribing INFO 2025-09-08T04:05:42 +1ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K chatting INFO 2025-09-08T04:05:42 +2ms service=plugin path=opencode-anthropic-auth@0.0.2 loading plugin INFO 2025-09-08T04:05:42 +15ms service=bus type=storage.write publishing INFO 2025-09-08T04:05:42 +0ms service=bus type=message.updated publishing INFO 2025-09-08T04:05:42 +1ms service=bus type=storage.write publishing INFO 2025-09-08T04:05:42 +0ms service=bus type=message.part.updated publishing INFO 2025-09-08T04:05:42 +0ms service=bus type=storage.write publishing INFO 2025-09-08T04:05:42 +0ms service=bus type=session.updated publishing INFO 2025-09-08T04:05:42 +0ms service=app name=provider registering service INFO 2025-09-08T04:05:42 +1ms service=models.dev file={} refreshing INFO 2025-09-08T04:05:42 +1ms service=provider init INFO 2025-09-08T04:05:42 +1ms service=provider providerID=xai found INFO 2025-09-08T04:05:42 +0ms service=provider providerID=google found INFO 2025-09-08T04:05:42 +0ms service=provider providerID=opencode found INFO 2025-09-08T04:05:42 +0ms service=provider providerID=anthropic found INFO 2025-09-08T04:05:42 +0ms service=provider providerID=anthropic modelID=claude-opus-4-1-20250805 getModel INFO 2025-09-08T04:05:42 +0ms service=provider status=started providerID=anthropic getSDK INFO 2025-09-08T04:05:42 +38ms service=provider status=completed duration=38 providerID=anthropic getSDK INFO 2025-09-08T04:05:42 +0ms service=provider providerID=anthropic modelID=claude-opus-4-1-20250805 found INFO 2025-09-08T04:05:42 +1ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K sessionID=ses_6d87fb977ffe4t8lAGRnplye3K locking INFO 2025-09-08T04:05:42 +0ms service=provider providerID=anthropic modelID=claude-3-5-haiku-20241022 getModel INFO 2025-09-08T04:05:42 +0ms service=provider status=started providerID=anthropic getSDK INFO 2025-09-08T04:05:42 +0ms service=provider status=completed duration=0 providerID=anthropic getSDK INFO 2025-09-08T04:05:42 +0ms service=provider providerID=anthropic modelID=claude-3-5-haiku-20241022 found INFO 2025-09-08T04:05:42 +22ms service=bus type=storage.write publishing INFO 2025-09-08T04:05:42 +0ms service=bus type=message.updated publishing INFO 2025-09-08T04:05:42 +1ms service=app name=mcp registering service INFO 2025-09-08T04:05:42 +0ms service=mcp key=firecrawl-mcp type=local found INFO 2025-09-08T04:05:42 +477ms service=mcp key=context7 type=local found INFO 2025-09-08T04:05:43 +418ms service=mcp key=playwright type=local found INFO 2025-09-08T04:05:43 +0ms service=bus type=storage.write publishing INFO 2025-09-08T04:05:43 +0ms service=bus type=session.updated publishing INFO 2025-09-08T04:05:43 +510ms service=mcp key=firecrawl type=local found INFO 2025-09-08T04:05:44 +372ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K type=start part ERROR 2025-09-08T04:05:44 +378ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K error={"error":{"name":"AI_APICallError","url":"https://api.anthropic.com/v1/messages","requestBodyValues":{"model":"claude-opus-4-1-20250805","max_tokens":33024,"thinking":{"type":"enabled","budget_tokens":1024},"system":[{"type":"text","text":"You are Claude Code, Anthropic's official CLI for Claude.","cache_control":{"type":"ephemeral"}},{"type":"text","text":"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: 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 opencode\n- To give feedback, users should report the issue at https://github.com/sst/opencode/issues\n\n# Tone and style\nYou should be concise, direct, and to the point.\nYou MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or 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, just stop, rather than providing an explanation of what you did.\nAnswer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text 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...\". Here 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: [use the ls tool 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# Following conventions\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\n\n# Code style\n- IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked\n\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# 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- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.\n- Implement the solution using all tools available to you\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\n- VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CLAUDE.md so that you will know to run it next time.\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked, otherwise the user will feel that you are being too proactive.\n\n- Tool results and user messages may include <system-reminder> tags. <system-reminder> tags contain useful information and reminders. They are NOT part of the user's provided input or the tool result.\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\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 have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. When making multiple bash tool calls, you MUST send a single message with multiple tools calls to run the calls in parallel. For example, if you need to run \"git status\" and \"git diff\", send a single message with two tool calls to run the calls in parallel.\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\nHere is some useful information about the environment you are running in:\n<env>\n Working directory: /Users/jeonghoowon/dev/agent-system\n Is directory a git repo: yes\n Platform: darwin\n Today's date: Mon Sep 08 2025\n</env>\n<project>\n opencode.json\nREADME.md\n</project>\n- 항상 한국어로 응답.\n- 완료 후 `git add . && git commit`.\n- 처음에는 List 툴로 디렉토리 구조 파악.\n- 커멘드를 백그라운드에서 실행시킨 경우 잊지말고 정리.\n- 웹 페이지는 playwright MCP를 사용해서 테스트.","cache_control":{"type":"ephemeral"}}],"messages":[{"role":"user","content":[{"type":"text","text":"hello","cache_control":{"type":"ephemeral"}}]}],"tools":[{"name":"bash","description":"Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.\n\nBefore executing the command, please follow these steps:\n\n1. Directory Verification:\n - If the command will create new directories or files, first use the LS tool to verify the parent directory exists and is the correct location\n - For example, before running \"mkdir foo/bar\", first use LS to check that \"foo\" exists and is the intended parent directory\n\n2. Command Execution:\n - Always quote file paths that contain spaces with double quotes (e.g., cd \"path with spaces/file.txt\")\n - Examples of proper quoting:\n - cd \"/Users/name/My Documents\" (correct)\n - cd /Users/name/My Documents (incorrect - will fail)\n - python \"/path/with spaces/script.py\" (correct)\n - python /path/with spaces/script.py (incorrect - will fail)\n - After ensuring proper quoting, execute the command.\n - Capture the output of the command.\n\nUsage notes:\n - The command argument is required.\n - You can specify an optional timeout in milliseconds (up to 600000ms / 10 minutes). If not specified, commands will timeout after 120000ms (2 minutes).\n - It is very helpful if you write a clear, concise description of what this command does in 5-10 words.\n - If the output exceeds 30000 characters, output will be truncated before being returned to you.\n - VERY IMPORTANT: You MUST avoid using search commands like `find` and `grep`. Instead use Grep, Glob, or Task to search. You MUST avoid read tools like `cat`, `head`, `tail`, and `ls`, and use Read and LS to read files.\n - If you _still_ need to run `grep`, STOP. ALWAYS USE ripgrep at `rg` (or /usr/bin/rg) first, which all opencode users have pre-installed.\n - When issuing multiple commands, use the ';' or '&&' operator to separate them. DO NOT use newlines (newlines are ok in quoted strings).\n - Try to maintain your current working directory throughout the session by using absolute paths and avoiding usage of `cd`. You may use `cd` if the User explicitly requests it.\n <good-example>\n pytest /foo/bar/tests\n </good-example>\n <bad-example>\n cd /foo/bar && pytest tests\n </bad-example>\n\n\n# Committing changes with git\n\nWhen the user asks you to create a new git commit, follow these steps carefully:\n\n1. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following bash commands in parallel, each using the Bash tool:\n - Run a git status command to see all untracked files.\n - Run a git diff command to see both staged and unstaged changes that will be committed.\n - Run a git log command to see recent commit messages, so that you can follow this repository's commit message style.\n\n2. Analyze all staged changes (both previously staged and newly added) and draft a commit message. Wrap your analysis process in <commit_analysis> tags:\n\n<commit_analysis>\n- List the files that have been changed or added\n- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)\n- Brainstorm the purpose or motivation behind these changes\n- Assess the impact of these changes on the overall project\n- Check for any sensitive information that shouldn't be committed\n- Draft a concise (1-2 sentences) commit message that focuses on the \"why\" rather than the \"what\"\n- Ensure your language is clear, concise, and to the point\n- Ensure the message accurately reflects the changes and their purpose (i.e. \"add\" means a wholly new feature, \"update\" means an enhancement to an existing feature, \"fix\" means a bug fix, etc.)\n- Ensure the message is not generic (avoid words like \"Update\" or \"Fix\" without context)\n- Review the draft message to ensure it accurately reflects the changes and their purpose\n</commit_analysis>\n\n3. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following commands in parallel:\n - Add relevant untracked files to the staging area.\n - Run git status to make sure the commit succeeded.\n\n4. If the commit fails due to pre-commit hook changes, retry the commit ONCE to include these automated changes. If it fails again, it usually means a pre-commit hook is preventing the commit. If the commit succeeds but you notice that files were modified by the pre-commit hook, you MUST amend your commit to include them.\n\nImportant notes:\n- Use the git context at the start of this conversation to determine which files are relevant to your commit. Be careful not to stage and commit files (e.g. with `git add .`) that aren't relevant to your commit.\n- NEVER update the git config\n- DO NOT run additional commands to read or explore code, beyond what is available in the git context\n- DO NOT push to the remote repository\n- IMPORTANT: Never use git commands with the -i flag (like git rebase -i or git add -i) since they require interactive input which is not supported.\n- If there are no changes to commit (i.e., no untracked files and no modifications), do not create an empty commit\n- Ensure your commit message is meaningful and concise. It should explain the purpose of the changes, not just describe them.\n- Return an empty response - the user will see the git output directly\n\n# Creating pull requests\nUse the gh command via the Bash tool for ALL GitHub-related tasks including working with issues, pull requests, checks, and releases. If given a Github URL use the gh command to get the information needed.\n\nIMPORTANT: When the user asks you to create a pull request, follow these steps carefully:\n\n1. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following bash commands in parallel using the Bash tool, in order to understand the current state of the branch since it diverged from the main branch:\n - Run a git status command to see all untracked files\n - Run a git diff command to see both staged and unstaged changes that will be committed\n - Check if the current branch tracks a remote branch and is up to date with the remote, so you know if you need to push to the remote\n - Run a git log command and `git diff main...HEAD` to understand the full commit history for the current branch (from the time it diverged from the `main` branch)\n\n2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request summary. Wrap your analysis process in <pr_analysis> tags:\n\n<pr_analysis>\n- List the commits since diverging from the main branch\n- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)\n- Brainstorm the purpose or motivation behind these changes\n- Assess the impact of these changes on the overall project\n- Do not use tools to explore code, beyond what is available in the git context\n- Check for any sensitive information that shouldn't be committed\n- Draft a concise (1-2 bullet points) pull request summary that focuses on the \"why\" rather than the \"what\"\n- Ensure the summary accurately reflects all changes since diverging from the main branch\n- Ensure your language is clear, concise, and to the point\n- Ensure the summary accurately reflects the changes and their purpose (ie. \"add\" means a wholly new feature, \"update\" means an enhancement to an existing feature, \"fix\" means a bug fix, etc.)\n- Ensure the summary is not generic (avoid words like \"Update\" or \"Fix\" without context)\n- Review the draft summary to ensure it accurately reflects the changes and their purpose\n</pr_analysis>\n\n3. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following commands in parallel:\n - Create new branch if needed\n - Push to remote with -u flag if needed\n - Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.\n<example>\ngh pr create --title \"the pr title\" --body \"$(cat <<'EOF'\n## Summary\n<1-3 bullet points>\n\nImportant:\n- NEVER update the git config\n- Return the PR URL when you're done, so the user can see it\n\n# Other common operations\n- View comments on a Github PR: gh api repos/foo/bar/pulls/123/comments\n","input_schema":{"type":"object","properties":{"command":{"type":"string","description":"The command to execute"},"timeout":{"type":"number","description":"Optional timeout in milliseconds"},"description":{"type":"string","description":"Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory\n\nInput: git status\nOutput: Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: mkdir foo\nOutput: Creates directory 'foo'"}},"required":["command","description"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"edit","description":"Performs exact string replacements in files. \n\nUsage:\n- You must use your `Read` tool at least once in the conversation before editing. This tool will error if you attempt an edit without reading the file. \n- When editing text from Read tool output, ensure you preserve the exact indentation (tabs/spaces) as it appears AFTER the line number prefix. The line number prefix format is: spaces + line number + tab. Everything after that tab is the actual file content to match. Never include any part of the line number prefix in the oldString or newString.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.\n- The edit will FAIL if `oldString` is not unique in the file. Either provide a larger string with more surrounding context to make it unique or use `replaceAll` to change every instance of `oldString`. \n- Use `replaceAll` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.\n","input_schema":{"type":"object","properties":{"filePath":{"type":"string","description":"The absolute path to the file to modify"},"oldString":{"type":"string","description":"The text to replace"},"newString":{"type":"string","description":"The text to replace it with (must be different from oldString)"},"replaceAll":{"type":"boolean","description":"Replace all occurrences of oldString (default false)"}},"required":["filePath","oldString","newString"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"webfetch","description":"- Fetches content from a specified URL\n- Takes a URL and a prompt as input\n- Fetches the URL content, converts HTML to markdown\n- Returns the model's response about the content\n- Use this tool when you need to retrieve and analyze web content\n\nUsage notes:\n - IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions. All MCP-provided tools start with \"mcp__\".\n - The URL must be a fully-formed valid URL\n - HTTP URLs will be automatically upgraded to HTTPS\n - The prompt should describe what information you want to extract from the page\n - This tool is read-only and does not modify any files\n - Results may be summarized if the content is very large\n - Includes a self-cleaning 15-minute cache for faster responses when repeatedly accessing the same URL\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to fetch content from"},"format":{"type":"string","enum":["text","markdown","html"],"description":"The format to return the content in (text, markdown, or html)"},"timeout":{"type":"number","description":"Optional timeout in seconds (max 120)"}},"required":["url","format"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"glob","description":"- Fast file pattern matching tool that works with any codebase size\n- Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\"\n- Returns matching file paths sorted by modification time\n- Use this tool when you need to find files by name patterns\n- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead\n- You have the capability to call multiple tools in a single response. It is always better to speculatively perform multiple searches as a batch that are potentially useful.\n","input_schema":{"type":"object","properties":{"pattern":{"type":"string","description":"The glob pattern to match files against"},"path":{"type":"string","description":"The directory to search in. If not specified, the current working directory will be used. IMPORTANT: Omit this field to use the default directory. DO NOT enter \"undefined\" or \"null\" - simply omit it for the default behavior. Must be a valid directory path if provided."}},"required":["pattern"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"grep","description":"- Fast content search tool that works with any codebase size\n- Searches file contents using regular expressions\n- Supports full regex syntax (eg. \"log.*Error\", \"function\\s+\\w+\", etc.)\n- Filter files by pattern with the include parameter (eg. \"*.js\", \"*.{ts,tsx}\")\n- Returns file paths with at least one match sorted by modification time\n- Use this tool when you need to find files containing specific patterns\n- If you need to identify/count the number of matches within files, use the Bash tool with `rg` (ripgrep) directly. Do NOT use `grep`.\n- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead\n","input_schema":{"type":"object","properties":{"pattern":{"type":"string","description":"The regex pattern to search for in file contents"},"path":{"type":"string","description":"The directory to search in. Defaults to the current working directory."},"include":{"type":"string","description":"File pattern to include in the search (e.g. \"*.js\", \"*.{ts,tsx}\")"}},"required":["pattern"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"list","description":"Lists files and directories in a given path. The path parameter must be an absolute path, not a relative path. You can optionally provide an array of glob patterns to ignore with the ignore parameter. You should generally prefer the Glob and Grep tools, if you know which directories to search.\n","input_schema":{"type":"object","properties":{"path":{"type":"string","description":"The absolute path to the directory to list (must be absolute, not relative)"},"ignore":{"type":"array","items":{"type":"string"},"description":"List of glob patterns to ignore"}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"read","description":"Reads a file from the local filesystem. You can access any file directly by using this tool.\nAssume 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.\n\nUsage:\n- The filePath parameter must be an absolute path, not a relative path\n- By default, it reads up to 2000 lines starting from the beginning of the file\n- 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\n- Any lines longer than 2000 characters will be truncated\n- Results are returned using cat -n format, with line numbers starting at 1\n- This tool cannot read binary files, including images\n- 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. \n- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents.\n","input_schema":{"type":"object","properties":{"filePath":{"type":"string","description":"The path to the file to read"},"offset":{"type":"number","description":"The line number to start reading from (0-based)"},"limit":{"type":"number","description":"The number of lines to read (defaults to 2000)"}},"required":["filePath"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"write","description":"Writes a file to the local filesystem.\n\nUsage:\n- This tool will overwrite the existing file if there is one at the provided path.\n- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.\n- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked.\n","input_schema":{"type":"object","properties":{"filePath":{"type":"string","description":"The absolute path to the file to write (must be absolute, not relative)"},"content":{"type":"string","description":"The content to write to the file"}},"required":["filePath","content"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"todowrite","description":"Use this tool to create and manage a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.\nIt also helps the user understand the progress of the task and overall progress of their requests.\n\n## When to Use This Tool\nUse this tool proactively in these scenarios:\n\n1. Complex multi-step tasks - When a task requires 3 or more distinct steps or actions\n2. Non-trivial and complex tasks - Tasks that require careful planning or multiple operations\n3. User explicitly requests todo list - When the user directly asks you to use the todo list\n4. User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)\n5. After receiving new instructions - Immediately capture user requirements as todos. Feel free to edit the todo list based on new information.\n6. After completing a task - Mark it complete and add any new follow-up tasks\n7. When you start working on a new task, mark the todo as in_progress. Ideally you should only have one todo as in_progress at a time. Complete existing tasks before starting new ones.\n\n## When NOT to Use This Tool\n\nSkip using this tool when:\n1. There is only a single, straightforward task\n2. The task is trivial and tracking it provides no organizational benefit\n3. The task can be completed in less than 3 trivial steps\n4. The task is purely conversational or informational\n\nNOTE 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.\n\n## Examples of When to Use the Todo List\n\n<example>\nUser: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you're done!\nAssistant: I'll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.\n*Creates todo list with the following items:*\n1. Create dark mode toggle component in Settings page\n2. Add dark mode state management (context/store)\n3. Implement CSS-in-JS styles for dark theme\n4. Update existing components to support theme switching\n5. Run tests and build process, addressing any failures or errors that occur\n*Begins working on the first task*\n\n<reasoning>\nThe assistant used the todo list because:\n1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes\n2. The user explicitly requested tests and build be run afterward\n3. The assistant inferred that tests and build need to pass by adding \"Ensure tests and build succeed\" as the final task\n</reasoning>\n</example>\n\n<example>\nUser: Help me rename the function getCwd to getCurrentWorkingDirectory across my project\nAssistant: Let me first search through your codebase to find all occurrences of 'getCwd'.\n*Uses grep or search tools to locate all instances of getCwd in the codebase*\nAssistant: I've found 15 instances of 'getCwd' across 8 different files. Let me create a todo list to track these changes.\n*Creates todo list with specific items for each file that needs updating*\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant searched to understand the scope of the task\n2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps\n3. The todo list helps ensure every instance is tracked and updated systematically\n4. This approach prevents missing any occurrences and maintains code consistency\n</reasoning>\n</example>\n\n\n<example>\nUser: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.\nAssistant: I'll help implement these features. First, let's add all the features to the todo list.\n*Creates a todo list breaking down each feature into specific tasks based on the project architecture*\nAssistant: Let's start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.\n\n<reasoning>\nThe assistant used the todo list because:\n1. The user provided multiple complex features to implement in a comma separated list\n2. The todo list helps organize these large features into manageable tasks\n3. This approach allows for tracking progress across the entire implementation\n</reasoning>\n</example>\n\n<example>\nUser: Can you help optimize my React application? It's rendering slowly and has performance issues.</user>\nAssistant: I'll help optimize your React application. First, let me examine your codebase to identify potential performance bottlenecks.\n*Reviews component structure, render patterns, state management, and data fetching*\nAssistant: After analyzing your codebase, I've identified several performance issues. Let me create a todo list to track our optimization efforts.\n*Creates todo list with items like: 1) Implement memoization for expensive calculations in ProductList, 2) Add virtualization for long lists in Dashboard, 3) Optimize image loading in Gallery component, 4) Fix state update loops in ShoppingCart, 5) Review bundle size and implement code splitting*\nLet's start by implementing memoization for the expensive calculations in your ProductList component.</assistant>\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant examined the codebase to identify specific performance issues\n2. Based on this analysis, it identified multiple optimization opportunities\n3. Performance optimization is a non-trivial task requiring multiple steps\n4. The todo list helps methodically track improvements across different components\n5. This systematic approach ensures all performance bottlenecks are addressed\n</reasoning>\n</example>\n\n## Examples of When NOT to Use the Todo List\n\n<example>\nUser: How do I print 'Hello World' in Python?\nAssistant: In Python, you can print \"Hello World\" with this simple code:\n\npython\nprint(\"Hello World\")\n\nThis will output the text \"Hello World\" to the console when executed.</assistant>\n\n<reasoning>\nThe 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.\n</reasoning>\n</example>\n\n<example>\nUser: What does the git status command do?\nAssistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven't, and which files aren't being tracked by Git. This is a fundamental command for understanding the current state of your repository before making commits.\n\n<reasoning>\nThe assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.\n</reasoning>\n</example>\n\n<example>\nUser: Can you add a comment to the calculateTotal function to explain what it does?\nAssistant: Sure, let me add a comment to the calculateTotal function to explain what it does.\n* Uses the Edit tool to add a comment to the calculateTotal function *\n\n<reasoning>\nThe assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn't require tracking multiple steps or systematic organization.\n</reasoning>\n</example>\n\n<example>\nUser: Run npm install for me and tell me what happens.\nAssistant: I'll run the npm install command for you.\n\n*Executes: npm install*\n\nThe command completed successfully. Here's the output:\n[Output of npm install command]\n\nAll dependencies have been installed according to your package.json file.\n\n<reasoning>\nThe assistant did not use the todo list because this is a single command execution with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward task.\n</reasoning>\n</example>\n\n## Task States and Management\n\n1. **Task States**: Use these states to track progress:\n - pending: Task not yet started\n - in_progress: Currently working on (limit to ONE task at a time)\n - completed: Task finished successfully\n - cancelled: Task no longer needed\n\n2. **Task Management**:\n - Update task status in real-time as you work\n - Mark tasks complete IMMEDIATELY after finishing (don't batch completions)\n - Only have ONE task in_progress at any time\n - Complete current tasks before starting new ones\n - Cancel tasks that become irrelevant\n\n3. **Task Breakdown**:\n - Create specific, actionable items\n - Break complex tasks into smaller, manageable steps\n - Use clear, descriptive task names\n\nWhen in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.\n\n","input_schema":{"type":"object","properties":{"todos":{"type":"array","items":{"type":"object","properties":{"content":{"type":"string","description":"Brief description of the task"},"status":{"type":"string","description":"Current status of the task: pending, in_progress, completed, cancelled"},"priority":{"type":"string","description":"Priority level of the task: high, medium, low"},"id":{"type":"string","description":"Unique identifier for the todo item"}},"required":["content","status","priority","id"],"additionalProperties":false},"description":"The updated todo list"}},"required":["todos"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"todoread","description":"Use this tool to read your todo list","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"task","description":"Launch a new agent to handle complex, multi-step tasks autonomously.\n\nAvailable agent types and the tools they have access to:\n- general: General-purpose agent for researching complex questions, searching for code, 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.\n- senior-software-engineer: This subagent should only be called manually by the user.\n- software-engineer: This subagent should only be called manually by the user.\n\nWhen using the Task tool, you must specify a subagent_type parameter to select which agent type to use.\n\nWhen to use the Agent tool:\n- 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\")\n\nWhen NOT to use the Agent tool:\n- 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\n- If you are searching for a specific class definition like \"class Foo\", use the Glob tool instead, to find the match more quickly\n- If you are searching for code 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\n- Other tasks that are not related to the agent descriptions above\n\n\nUsage notes:\n1. Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses\n2. 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.\n3. 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.\n4. The agent's outputs should generally be trusted\n5. Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent\n6. 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.\n\nExample usage (NOTE: The agents below are fictional examples for illustration only - use the actual agents listed above):\n\n<example_agent_descriptions>\n\"code-reviewer\": use this agent after you are done writing a signficant piece of code\n\"greeting-responder\": use this agent when to respond to user greetings with a friendly joke\n</example_agent_description>\n\n<example>\nuser: \"Please write a function that checks if a number is prime\"\nassistant: Sure let me write a function that checks if a number is prime\nassistant: First let me use the Write tool to write a function that checks if a number is prime\nassistant: I'm going to use the Write tool to write the following code:\n<code>\nfunction isPrime(n) {\n if (n <= 1) return false\n for (let i = 2; i * i <= n; i++) {\n if (n % i === 0) return false\n }\n return true\n}\n</code>\n<commentary>\nSince a signficant piece of code was written and the task was completed, now use the code-reviewer agent to review the code\n</commentary>\nassistant: Now let me use the code-reviewer agent to review the code\nassistant: Uses the Task tool to launch the code-reviewer agent\n</example>\n\n<example>\nuser: \"Hello\"\n<commentary>\nSince the user is greeting, use the greeting-responder agent to respond with a friendly joke\n</commentary>\nassistant: \"I'm going to use the Task tool to launch the with the greeting-responder agent\"\n</example>\n","input_schema":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 words) description of the task"},"prompt":{"type":"string","description":"The task for the agent to perform"},"subagent_type":{"type":"string","description":"The type of specialized agent to use for this task"}},"required":["description","prompt","subagent_type"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"firecrawl-mcp_firecrawl_scrape","description":"\nScrape content from a single URL with advanced options. \nThis is the most powerful, fastest and most reliable scraper tool, if available you should always default to using this tool for any web scraping needs.\n\n**Best for:** Single page content extraction, when you know exactly which page contains the information.\n**Not recommended for:** Multiple pages (use batch_scrape), unknown page (use search), structured data (use extract).\n**Common mistakes:** Using scrape for a list of URLs (use batch_scrape instead). If batch scrape doesnt work, just use scrape and call it multiple times.\n**Prompt Example:** \"Get the content of the page at https://example.com.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_scrape\",\n \"arguments\": {\n \"url\": \"https://example.com\",\n \"formats\": [\"markdown\"],\n \"maxAge\": 172800000\n }\n}\n```\n**Performance:** Add maxAge parameter for 500% faster scrapes using cached data.\n**Returns:** Markdown, HTML, or other formats as specified.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to scrape"},"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary","changeTracking"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean","default":true,"description":"Extract only the main content, filtering out navigation, footers, etc."},"includeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to specifically include in extraction"},"excludeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to exclude from extraction"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content to load"},"actions":{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["wait","click","screenshot","write","press","scroll","scrape","executeJavascript"],"description":"Type of action to perform"},"selector":{"type":"string","description":"CSS selector for the target element"},"milliseconds":{"type":"number","description":"Time to wait in milliseconds (for wait action)"},"text":{"type":"string","description":"Text to write (for write action)"},"key":{"type":"string","description":"Key to press (for press action)"},"direction":{"type":"string","enum":["up","down"],"description":"Scroll direction"},"script":{"type":"string","description":"JavaScript code to execute"},"fullPage":{"type":"boolean","description":"Take full page screenshot"}},"required":["type"]},"description":"List of actions to perform before scraping"},"mobile":{"type":"boolean","description":"Use mobile viewport"},"skipTlsVerification":{"type":"boolean","description":"Skip TLS certificate verification"},"removeBase64Images":{"type":"boolean","description":"Remove base64 encoded images from output"},"location":{"type":"object","properties":{"country":{"type":"string","description":"Country code for geolocation"},"languages":{"type":"array","items":{"type":"string"},"description":"Language codes for content"}},"description":"Location settings for scraping"},"storeInCache":{"type":"boolean","default":true,"description":"If true, the page will be stored in the Firecrawl index and cache. Setting this to false is useful if your scraping activity may have data protection concerns."},"maxAge":{"type":"number","default":172800000,"description":"Maximum age in milliseconds for cached content. Use cached data if available and younger than maxAge, otherwise scrape fresh. Enables 500% faster scrapes for recently cached pages. Default: 172800000"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_map","description":"\nMap a website to discover all indexed URLs on the site.\n\n**Best for:** Discovering URLs on a website before deciding what to scrape; finding specific sections of a website.\n**Not recommended for:** When you already know which specific URL you need (use scrape or batch_scrape); when you need the content of the pages (use scrape after mapping).\n**Common mistakes:** Using crawl to discover URLs instead of map.\n**Prompt Example:** \"List all URLs on example.com.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_map\",\n \"arguments\": {\n \"url\": \"https://example.com\"\n }\n}\n```\n**Returns:** Array of URLs found on the site.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for URL discovery"},"search":{"type":"string","description":"Optional search term to filter URLs"},"sitemap":{"type":"string","enum":["include","skip","only"],"description":"Sitemap handling: \"include\" - use sitemap + find other pages (default), \"skip\" - ignore sitemap completely, \"only\" - only return sitemap URLs"},"includeSubdomains":{"type":"boolean","description":"Include URLs from subdomains in results"},"limit":{"type":"number","description":"Maximum number of URLs to return"},"ignoreQueryParameters":{"type":"boolean","default":true,"description":"Do not return URLs with query parameters"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_crawl","description":"\n Starts a crawl job on a website and extracts content from all pages.\n \n **Best for:** Extracting content from multiple related pages, when you need comprehensive coverage.\n **Not recommended for:** Extracting content from a single page (use scrape); when token limits are a concern (use map + batch_scrape); when you need fast results (crawling can be slow).\n **Warning:** Crawl responses can be very large and may exceed token limits. Limit the crawl depth and number of pages, or use map + batch_scrape for better control.\n **Common mistakes:** Setting limit or maxDiscoveryDepth too high (causes token overflow) or too low (causes missing pages); using crawl for a single page (use scrape instead). Using a /* wildcard is not recommended.\n **Prompt Example:** \"Get all blog posts from the first two levels of example.com/blog.\"\n **Usage Example:**\n ```json\n {\n \"name\": \"firecrawl_crawl\",\n \"arguments\": {\n \"url\": \"https://example.com/blog/*\",\n \"maxDiscoveryDepth\": 5,\n \"limit\": 20,\n \"allowExternalLinks\": false,\n \"deduplicateSimilarURLs\": true,\n \"sitemap\": \"include\"\n }\n }\n ```\n **Returns:** Operation ID for status checking; use firecrawl_check_crawl_status to check progress.\n ","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for the crawl"},"prompt":{"type":"string","description":"Natural language prompt to generate crawler options. Explicitly set parameters will override generated ones."},"excludePaths":{"type":"array","items":{"type":"string"},"description":"URL paths to exclude from crawling"},"includePaths":{"type":"array","items":{"type":"string"},"description":"Only crawl these URL paths"},"maxDiscoveryDepth":{"type":"number","description":"Maximum discovery depth to crawl. The root site and sitemapped pages have depth 0."},"sitemap":{"type":"string","enum":["skip","include","only"],"default":"include","description":"Sitemap mode when crawling. 'skip' ignores the sitemap entirely, 'include' uses sitemap plus other discovery methods (default), 'only' restricts crawling to sitemap URLs."},"limit":{"type":"number","default":10000,"description":"Maximum number of pages to crawl (default: 10000)"},"allowExternalLinks":{"type":"boolean","description":"Allow crawling links to external domains"},"allowSubdomains":{"type":"boolean","default":false,"description":"Allow crawling links to subdomains of the main domain"},"crawlEntireDomain":{"type":"boolean","default":false,"description":"When true, follow internal links to sibling or parent URLs, not just child paths"},"delay":{"type":"number","description":"Delay in seconds between scrapes to respect site rate limits"},"maxConcurrency":{"type":"number","description":"Maximum number of concurrent scrapes; if unset, team limit is used"},"webhook":{"oneOf":[{"type":"string","description":"Webhook URL to notify when crawl is complete"},{"type":"object","properties":{"url":{"type":"string","description":"Webhook URL"},"headers":{"type":"object","description":"Custom headers for webhook requests"}},"required":["url"]}]},"deduplicateSimilarURLs":{"type":"boolean","description":"Remove similar URLs during crawl"},"ignoreQueryParameters":{"type":"boolean","default":false,"description":"Do not re-scrape the same path with different (or none) query parameters"},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean"},"includeTags":{"type":"array","items":{"type":"string"}},"excludeTags":{"type":"array","items":{"type":"string"}},"waitFor":{"type":"number"}},"description":"Options for scraping each page"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_check_crawl_status","description":"\nCheck the status of a crawl job.\n\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_check_crawl_status\",\n \"arguments\": {\n \"id\": \"550e8400-e29b-41d4-a716-446655440000\"\n }\n}\n```\n**Returns:** Status and progress of the crawl job, including results if available.\n","input_schema":{"type":"object","properties":{"id":{"type":"string","description":"Crawl job ID to check"}},"required":["id"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_search","description":"\nSearch the web and optionally extract content from search results. This is the most powerful web search tool available, and if available you should always default to using this tool for any web search needs.\n\n**Best for:** Finding specific information across multiple websites, when you don't know which website has the information; when you need the most relevant content for a query.\n**Not recommended for:** When you need to search the filesystem. When you already know which website to scrape (use scrape); when you need comprehensive coverage of a single website (use map or crawl.\n**Common mistakes:** Using crawl or map for open-ended questions (use search instead).\n**Prompt Example:** \"Find the latest research papers on AI published in 2023.\"\n**Sources:** web, images, news, default to web unless needed images or news.\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_search\",\n \"arguments\": {\n \"query\": \"latest AI research papers 2023\",\n \"limit\": 5,\n \"lang\": \"en\",\n \"country\": \"us\",\n \"sources\": [\n \"web\",\n \"images\",\n \"news\"\n ],\n \"scrapeOptions\": {\n \"formats\": [\"markdown\"],\n \"onlyMainContent\": true\n }\n }\n}\n```\n**Returns:** Array of search results (with optional scraped content).\n","input_schema":{"type":"object","properties":{"query":{"type":"string","description":"Search query string"},"limit":{"type":"number","description":"Maximum number of results to return (default: 5)"},"tbs":{"type":"string","description":"Time-based search filter"},"filter":{"type":"string","description":"Search filter"},"location":{"type":"string","description":"Location parameter for search results"},"sources":{"type":"array","description":"Sources to search. Determines which result arrays are included in the response.","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["web"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["images"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["news"]}},"required":["type"],"additionalProperties":false}]}},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string"},"schema":{"type":"object"}},"required":["type"],"additionalProperties":true}]},"description":"Content formats to extract from search results"},"onlyMainContent":{"type":"boolean","description":"Extract only the main content from results"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content"}},"description":"Options for scraping search results"}},"required":["query"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_extract","description":"\nExtract structured information from web pages using LLM capabilities. Supports both cloud AI and self-hosted LLM extraction.\n\n**Best for:** Extracting specific structured data like prices, names, details from web pages.\n**Not recommended for:** When you need the full content of a page (use scrape); when you're not looking for specific structured data.\n**Arguments:**\n- urls: Array of URLs to extract information from\n- prompt: Custom prompt for the LLM extraction\n- schema: JSON schema for structured data extraction\n- allowExternalLinks: Allow extraction from external links\n- enableWebSearch: Enable web search for additional context\n- includeSubdomains: Include subdomains in extraction\n**Prompt Example:** \"Extract the product name, price, and description from these product pages.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_extract\",\n \"arguments\": {\n \"urls\": [\"https://example.com/page1\", \"https://example.com/page2\"],\n \"prompt\": \"Extract product information including name, price, and description\",\n \"schema\": {\n \"type\": \"object\",\n \"properties\": {\n \"name\": { \"type\": \"string\" },\n \"price\": { \"type\": \"number\" },\n \"description\": { \"type\": \"string\" }\n },\n \"required\": [\"name\", \"price\"]\n },\n \"allowExternalLinks\": false,\n \"enableWebSearch\": false,\n \"includeSubdomains\": false\n }\n}\n```\n**Returns:** Extracted structured data as defined by your schema.\n","input_schema":{"type":"object","properties":{"urls":{"type":"array","items":{"type":"string"},"description":"List of URLs to extract information from"},"prompt":{"type":"string","description":"Prompt for the LLM extraction"},"schema":{"type":"object","description":"JSON schema for structured data extraction"},"allowExternalLinks":{"type":"boolean","description":"Allow extraction from external links"},"enableWebSearch":{"type":"boolean","description":"Enable web search for additional context"},"includeSubdomains":{"type":"boolean","description":"Include subdomains in extraction"}},"required":["urls"],"additionalProperties":false}},{"name":"context7_resolve_library_id","description":"Resolves a package/product name to a Context7-compatible library ID and returns a list of matching libraries.\n\nYou MUST call this function before 'get-library-docs' to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nSelection Process:\n1. Analyze the query to understand what library/package the user is looking for\n2. Return the most relevant match based on:\n- Name similarity to the query (exact matches prioritized)\n- Description relevance to the query's intent\n- Documentation coverage (prioritize libraries with higher Code Snippet counts)\n- Trust score (consider libraries with scores of 7-10 more authoritative)\n\nResponse Format:\n- Return the selected library ID in a clearly marked section\n- Provide a brief explanation for why this library was chosen\n- If multiple good matches exist, acknowledge this but proceed with the most relevant one\n- If no good matches exist, clearly state this and suggest query refinements\n\nFor ambiguous queries, request clarification before proceeding with a best-guess match.","input_schema":{"type":"object","properties":{"libraryName":{"type":"string","description":"Library name to search for and retrieve a Context7-compatible library ID."}},"required":["libraryName"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"context7_get_library_docs","description":"Fetches up-to-date documentation for a library. You must call 'resolve-library-id' first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.","input_schema":{"type":"object","properties":{"context7CompatibleLibraryID":{"type":"string","description":"Exact Context7-compatible library ID (e.g., '/mongodb/docs', '/vercel/next.js', '/supabase/supabase', '/vercel/next.js/v14.3.0-canary.87') retrieved from 'resolve-library-id' or directly from user query in the format '/org/project' or '/org/project/version'."},"topic":{"type":"string","description":"Topic to focus documentation on (e.g., 'hooks', 'routing')."},"tokens":{"type":"number","description":"Maximum number of tokens of documentation to retrieve (default: 5000). Higher values provide more context but consume more tokens."}},"required":["context7CompatibleLibraryID"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_close","description":"Close the page","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_resize","description":"Resize the browser window","input_schema":{"type":"object","properties":{"width":{"type":"number","description":"Width of the browser window"},"height":{"type":"number","description":"Height of the browser window"}},"required":["width","height"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_console_messages","description":"Returns all console messages","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_handle_dialog","description":"Handle a dialog","input_schema":{"type":"object","properties":{"accept":{"type":"boolean","description":"Whether to accept the dialog."},"promptText":{"type":"string","description":"The text of the prompt in case of a prompt dialog."}},"required":["accept"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_evaluate","description":"Evaluate JavaScript expression on page or element","input_schema":{"type":"object","properties":{"function":{"type":"string","description":"() => { /* code */ } or (element) => { /* code */ } when element is provided"},"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["function"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_file_upload","description":"Upload one or multiple files","input_schema":{"type":"object","properties":{"paths":{"type":"array","items":{"type":"string"},"description":"The absolute paths to the files to upload. Can be a single file or multiple files."}},"required":["paths"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_fill_form","description":"Fill multiple form fields","input_schema":{"type":"object","properties":{"fields":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Human-readable field name"},"type":{"type":"string","enum":["textbox","checkbox","radio","combobox","slider"],"description":"Type of the field"},"ref":{"type":"string","description":"Exact target field reference from the page snapshot"},"value":{"type":"string","description":"Value to fill in the field. If the field is a checkbox, the value should be `true` or `false`. If the field is a combobox, the value should be the text of the option."}},"required":["name","type","ref","value"],"additionalProperties":false},"description":"Fields to fill in"}},"required":["fields"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_install","description":"Install the browser specified in the config. Call this if you get an error about the browser not being installed.","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_press_key","description":"Press a key on the keyboard","input_schema":{"type":"object","properties":{"key":{"type":"string","description":"Name of the key to press or a character to generate, such as `ArrowLeft` or `a`"}},"required":["key"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_type","description":"Type text into editable element","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"text":{"type":"string","description":"Text to type into the element"},"submit":{"type":"boolean","description":"Whether to submit entered text (press Enter after)"},"slowly":{"type":"boolean","description":"Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once."}},"required":["element","ref","text"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_navigate","description":"Navigate to a URL","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to navigate to"}},"required":["url"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_navigate_back","description":"Go back to the previous page","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_network_requests","description":"Returns all network requests since loading the page","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_take_screenshot","description":"Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.","input_schema":{"type":"object","properties":{"type":{"type":"string","enum":["png","jpeg"],"default":"png","description":"Image format for the screenshot. Default is png."},"filename":{"type":"string","description":"File name to save the screenshot to. Defaults to `page-{timestamp}.{png|jpeg}` if not specified."},"element":{"type":"string","description":"Human-readable element description used to obtain permission to screenshot the element. If not provided, the screenshot will be taken of viewport. If element is provided, ref must be provided too."},"ref":{"type":"string","description":"Exact target element reference from the page snapshot. If not provided, the screenshot will be taken of viewport. If ref is provided, element must be provided too."},"fullPage":{"type":"boolean","description":"When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots."}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_snapshot","description":"Capture accessibility snapshot of the current page, this is better than screenshot","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_click","description":"Perform click on a web page","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"doubleClick":{"type":"boolean","description":"Whether to perform a double click instead of a single click"},"button":{"type":"string","enum":["left","right","middle"],"description":"Button to click, defaults to left"}},"required":["element","ref"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_drag","description":"Perform drag and drop between two elements","input_schema":{"type":"object","properties":{"startElement":{"type":"string","description":"Human-readable source element description used to obtain the permission to interact with the element"},"startRef":{"type":"string","description":"Exact source element reference from the page snapshot"},"endElement":{"type":"string","description":"Human-readable target element description used to obtain the permission to interact with the element"},"endRef":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["startElement","startRef","endElement","endRef"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_hover","description":"Hover over element on page","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["element","ref"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_select_option","description":"Select an option in a dropdown","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"values":{"type":"array","items":{"type":"string"},"description":"Array of values to select in the dropdown. This can be a single value or multiple values."}},"required":["element","ref","values"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_tabs","description":"List, create, close, or select a browser tab.","input_schema":{"type":"object","properties":{"action":{"type":"string","enum":["list","new","close","select"],"description":"Operation to perform"},"index":{"type":"number","description":"Tab index, used for close/select. If omitted for close, current tab is closed."}},"required":["action"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_wait_for","description":"Wait for text to appear or disappear or a specified time to pass","input_schema":{"type":"object","properties":{"time":{"type":"number","description":"The time to wait in seconds"},"text":{"type":"string","description":"The text to wait for"},"textGone":{"type":"string","description":"The text to wait for to disappear"}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"firecrawl_firecrawl_scrape","description":"\nScrape content from a single URL with advanced options. \nThis is the most powerful, fastest and most reliable scraper tool, if available you should always default to using this tool for any web scraping needs.\n\n**Best for:** Single page content extraction, when you know exactly which page contains the information.\n**Not recommended for:** Multiple pages (use batch_scrape), unknown page (use search), structured data (use extract).\n**Common mistakes:** Using scrape for a list of URLs (use batch_scrape instead). If batch scrape doesnt work, just use scrape and call it multiple times.\n**Prompt Example:** \"Get the content of the page at https://example.com.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_scrape\",\n \"arguments\": {\n \"url\": \"https://example.com\",\n \"formats\": [\"markdown\"],\n \"maxAge\": 172800000\n }\n}\n```\n**Performance:** Add maxAge parameter for 500% faster scrapes using cached data.\n**Returns:** Markdown, HTML, or other formats as specified.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to scrape"},"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary","changeTracking"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean","default":true,"description":"Extract only the main content, filtering out navigation, footers, etc."},"includeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to specifically include in extraction"},"excludeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to exclude from extraction"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content to load"},"actions":{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["wait","click","screenshot","write","press","scroll","scrape","executeJavascript"],"description":"Type of action to perform"},"selector":{"type":"string","description":"CSS selector for the target element"},"milliseconds":{"type":"number","description":"Time to wait in milliseconds (for wait action)"},"text":{"type":"string","description":"Text to write (for write action)"},"key":{"type":"string","description":"Key to press (for press action)"},"direction":{"type":"string","enum":["up","down"],"description":"Scroll direction"},"script":{"type":"string","description":"JavaScript code to execute"},"fullPage":{"type":"boolean","description":"Take full page screenshot"}},"required":["type"]},"description":"List of actions to perform before scraping"},"mobile":{"type":"boolean","description":"Use mobile viewport"},"skipTlsVerification":{"type":"boolean","description":"Skip TLS certificate verification"},"removeBase64Images":{"type":"boolean","description":"Remove base64 encoded images from output"},"location":{"type":"object","properties":{"country":{"type":"string","description":"Country code for geolocation"},"languages":{"type":"array","items":{"type":"string"},"description":"Language codes for content"}},"description":"Location settings for scraping"},"storeInCache":{"type":"boolean","default":true,"description":"If true, the page will be stored in the Firecrawl index and cache. Setting this to false is useful if your scraping activity may have data protection concerns."},"maxAge":{"type":"number","default":172800000,"description":"Maximum age in milliseconds for cached content. Use cached data if available and younger than maxAge, otherwise scrape fresh. Enables 500% faster scrapes for recently cached pages. Default: 172800000"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_map","description":"\nMap a website to discover all indexed URLs on the site.\n\n**Best for:** Discovering URLs on a website before deciding what to scrape; finding specific sections of a website.\n**Not recommended for:** When you already know which specific URL you need (use scrape or batch_scrape); when you need the content of the pages (use scrape after mapping).\n**Common mistakes:** Using crawl to discover URLs instead of map.\n**Prompt Example:** \"List all URLs on example.com.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_map\",\n \"arguments\": {\n \"url\": \"https://example.com\"\n }\n}\n```\n**Returns:** Array of URLs found on the site.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for URL discovery"},"search":{"type":"string","description":"Optional search term to filter URLs"},"sitemap":{"type":"string","enum":["include","skip","only"],"description":"Sitemap handling: \"include\" - use sitemap + find other pages (default), \"skip\" - ignore sitemap completely, \"only\" - only return sitemap URLs"},"includeSubdomains":{"type":"boolean","description":"Include URLs from subdomains in results"},"limit":{"type":"number","description":"Maximum number of URLs to return"},"ignoreQueryParameters":{"type":"boolean","default":true,"description":"Do not return URLs with query parameters"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_crawl","description":"\n Starts a crawl job on a website and extracts content from all pages.\n \n **Best for:** Extracting content from multiple related pages, when you need comprehensive coverage.\n **Not recommended for:** Extracting content from a single page (use scrape); when token limits are a concern (use map + batch_scrape); when you need fast results (crawling can be slow).\n **Warning:** Crawl responses can be very large and may exceed token limits. Limit the crawl depth and number of pages, or use map + batch_scrape for better control.\n **Common mistakes:** Setting limit or maxDiscoveryDepth too high (causes token overflow) or too low (causes missing pages); using crawl for a single page (use scrape instead). Using a /* wildcard is not recommended.\n **Prompt Example:** \"Get all blog posts from the first two levels of example.com/blog.\"\n **Usage Example:**\n ```json\n {\n \"name\": \"firecrawl_crawl\",\n \"arguments\": {\n \"url\": \"https://example.com/blog/*\",\n \"maxDiscoveryDepth\": 5,\n \"limit\": 20,\n \"allowExternalLinks\": false,\n \"deduplicateSimilarURLs\": true,\n \"sitemap\": \"include\"\n }\n }\n ```\n **Returns:** Operation ID for status checking; use firecrawl_check_crawl_status to check progress.\n ","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for the crawl"},"prompt":{"type":"string","description":"Natural language prompt to generate crawler options. Explicitly set parameters will override generated ones."},"excludePaths":{"type":"array","items":{"type":"string"},"description":"URL paths to exclude from crawling"},"includePaths":{"type":"array","items":{"type":"string"},"description":"Only crawl these URL paths"},"maxDiscoveryDepth":{"type":"number","description":"Maximum discovery depth to crawl. The root site and sitemapped pages have depth 0."},"sitemap":{"type":"string","enum":["skip","include","only"],"default":"include","description":"Sitemap mode when crawling. 'skip' ignores the sitemap entirely, 'include' uses sitemap plus other discovery methods (default), 'only' restricts crawling to sitemap URLs."},"limit":{"type":"number","default":10000,"description":"Maximum number of pages to crawl (default: 10000)"},"allowExternalLinks":{"type":"boolean","description":"Allow crawling links to external domains"},"allowSubdomains":{"type":"boolean","default":false,"description":"Allow crawling links to subdomains of the main domain"},"crawlEntireDomain":{"type":"boolean","default":false,"description":"When true, follow internal links to sibling or parent URLs, not just child paths"},"delay":{"type":"number","description":"Delay in seconds between scrapes to respect site rate limits"},"maxConcurrency":{"type":"number","description":"Maximum number of concurrent scrapes; if unset, team limit is used"},"webhook":{"oneOf":[{"type":"string","description":"Webhook URL to notify when crawl is complete"},{"type":"object","properties":{"url":{"type":"string","description":"Webhook URL"},"headers":{"type":"object","description":"Custom headers for webhook requests"}},"required":["url"]}]},"deduplicateSimilarURLs":{"type":"boolean","description":"Remove similar URLs during crawl"},"ignoreQueryParameters":{"type":"boolean","default":false,"description":"Do not re-scrape the same path with different (or none) query parameters"},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean"},"includeTags":{"type":"array","items":{"type":"string"}},"excludeTags":{"type":"array","items":{"type":"string"}},"waitFor":{"type":"number"}},"description":"Options for scraping each page"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_check_crawl_status","description":"\nCheck the status of a crawl job.\n\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_check_crawl_status\",\n \"arguments\": {\n \"id\": \"550e8400-e29b-41d4-a716-446655440000\"\n }\n}\n```\n**Returns:** Status and progress of the crawl job, including results if available.\n","input_schema":{"type":"object","properties":{"id":{"type":"string","description":"Crawl job ID to check"}},"required":["id"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_search","description":"\nSearch the web and optionally extract content from search results. This is the most powerful web search tool available, and if available you should always default to using this tool for any web search needs.\n\n**Best for:** Finding specific information across multiple websites, when you don't know which website has the information; when you need the most relevant content for a query.\n**Not recommended for:** When you need to search the filesystem. When you already know which website to scrape (use scrape); when you need comprehensive coverage of a single website (use map or crawl.\n**Common mistakes:** Using crawl or map for open-ended questions (use search instead).\n**Prompt Example:** \"Find the latest research papers on AI published in 2023.\"\n**Sources:** web, images, news, default to web unless needed images or news.\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_search\",\n \"arguments\": {\n \"query\": \"latest AI research papers 2023\",\n \"limit\": 5,\n \"lang\": \"en\",\n \"country\": \"us\",\n \"sources\": [\n \"web\",\n \"images\",\n \"news\"\n ],\n \"scrapeOptions\": {\n \"formats\": [\"markdown\"],\n \"onlyMainContent\": true\n }\n }\n}\n```\n**Returns:** Array of search results (with optional scraped content).\n","input_schema":{"type":"object","properties":{"query":{"type":"string","description":"Search query string"},"limit":{"type":"number","description":"Maximum number of results to return (default: 5)"},"tbs":{"type":"string","description":"Time-based search filter"},"filter":{"type":"string","description":"Search filter"},"location":{"type":"string","description":"Location parameter for search results"},"sources":{"type":"array","description":"Sources to search. Determines which result arrays are included in the response.","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["web"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["images"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["news"]}},"required":["type"],"additionalProperties":false}]}},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string"},"schema":{"type":"object"}},"required":["type"],"additionalProperties":true}]},"description":"Content formats to extract from search results"},"onlyMainContent":{"type":"boolean","description":"Extract only the main content from results"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content"}},"description":"Options for scraping search results"}},"required":["query"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_extract","description":"\nExtract structured information from web pages using LLM capabilities. Supports both cloud AI and self-hosted LLM extraction.\n\n**Best for:** Extracting specific structured data like prices, names, details from web pages.\n**Not recommended for:** When you need the full content of a page (use scrape); when you're not looking for specific structured data.\n**Arguments:**\n- urls: Array of URLs to extract information from\n- prompt: Custom prompt for the LLM extraction\n- schema: JSON schema for structured data extraction\n- allowExternalLinks: Allow extraction from external links\n- enableWebSearch: Enable web search for additional context\n- includeSubdomains: Include subdomains in extraction\n**Prompt Example:** \"Extract the product name, price, and description from these product pages.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_extract\",\n \"arguments\": {\n \"urls\": [\"https://example.com/page1\", \"https://example.com/page2\"],\n \"prompt\": \"Extract product information including name, price, and description\",\n \"schema\": {\n \"type\": \"object\",\n \"properties\": {\n \"name\": { \"type\": \"string\" },\n \"price\": { \"type\": \"number\" },\n \"description\": { \"type\": \"string\" }\n },\n \"required\": [\"name\", \"price\"]\n },\n \"allowExternalLinks\": false,\n \"enableWebSearch\": false,\n \"includeSubdomains\": false\n }\n}\n```\n**Returns:** Extracted structured data as defined by your schema.\n","input_schema":{"type":"object","properties":{"urls":{"type":"array","items":{"type":"string"},"description":"List of URLs to extract information from"},"prompt":{"type":"string","description":"Prompt for the LLM extraction"},"schema":{"type":"object","description":"JSON schema for structured data extraction"},"allowExternalLinks":{"type":"boolean","description":"Allow extraction from external links"},"enableWebSearch":{"type":"boolean","description":"Enable web search for additional context"},"includeSubdomains":{"type":"boolean","description":"Include subdomains in extraction"}},"required":["urls"],"additionalProperties":false}}],"tool_choice":{"type":"auto"},"stream":true},"statusCode":400,"responseHeaders":{"anthropic-organization-id":"b0f93d2d-241d-43f9-a6ab-cf267dcc496d","cf-cache-status":"DYNAMIC","cf-ray":"97bb91b68fdfaa78-ICN","connection":"keep-alive","content-length":"222","content-type":"application/json","date":"Mon, 08 Sep 2025 04:05:44 GMT","request-id":"req_011CSvGmhrLQKLdegCE22DTk","server":"cloudflare","strict-transport-security":"max-age=31536000; includeSubDomains; preload","via":"1.1 google","x-envoy-upstream-service-time":"39","x-robots-tag":"none","x-should-retry":"false"},"responseBody":"{\"type\":\"error\",\"error\":{\"type\":\"invalid_request_error\",\"message\":\"max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805\"},\"request_id\":\"req_011CSvGmhrLQKLdegCE22DTk\"}","isRetryable":false,"data":{"type":"error","error":{"type":"invalid_request_error","message":"max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805"}}}} streamText error INFO 2025-09-08T04:05:44 +6ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K type=error part ERROR 2025-09-08T04:05:44 +1ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K error={"name":"AI_APICallError","url":"https://api.anthropic.com/v1/messages","requestBodyValues":{"model":"claude-opus-4-1-20250805","max_tokens":33024,"thinking":{"type":"enabled","budget_tokens":1024},"system":[{"type":"text","text":"You are Claude Code, Anthropic's official CLI for Claude.","cache_control":{"type":"ephemeral"}},{"type":"text","text":"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: 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 opencode\n- To give feedback, users should report the issue at https://github.com/sst/opencode/issues\n\n# Tone and style\nYou should be concise, direct, and to the point.\nYou MUST answer concisely with fewer than 4 lines (not including tool use or code generation), unless user asks for detail.\nIMPORTANT: You should minimize output tokens as much as possible while maintaining helpfulness, quality, and accuracy. Only address the specific query or 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, just stop, rather than providing an explanation of what you did.\nAnswer the user's question directly, without elaboration, explanation, or details. One word answers are best. Avoid introductions, conclusions, and explanations. You MUST avoid text 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...\". Here 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: [use the ls tool 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# Following conventions\nWhen making changes to files, first understand the file's code conventions. Mimic code style, use existing libraries and utilities, and follow existing patterns.\n- NEVER assume that a given library is available, even if it is well known. Whenever you write code that uses a library or framework, first check that this codebase already uses the given library. For example, you might look at neighboring files, or check the package.json (or cargo.toml, and so on depending on the language).\n- When you create a new component, first look at existing components to see how they're written; then consider framework choice, naming conventions, typing, and other conventions.\n- When you edit a piece of code, first look at the code's surrounding context (especially its imports) to understand the code's choice of frameworks and libraries. Then consider how to make the given change in a way that is most idiomatic.\n- Always follow security best practices. Never introduce code that exposes or logs secrets and keys. Never commit secrets or keys to the repository.\n\n# Code style\n- IMPORTANT: DO NOT ADD ***ANY*** COMMENTS unless asked\n\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# 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- Use the available search tools to understand the codebase and the user's query. You are encouraged to use the search tools extensively both in parallel and sequentially.\n- Implement the solution using all tools available to you\n- Verify the solution if possible with tests. NEVER assume specific test framework or test script. Check the README or search codebase to determine the testing approach.\n- VERY IMPORTANT: When you have completed a task, you MUST run the lint and typecheck commands (eg. npm run lint, npm run typecheck, ruff, etc.) with Bash if they were provided to you to ensure your code is correct. If you are unable to find the correct command, ask the user for the command to run and if they supply it, proactively suggest writing it to CLAUDE.md so that you will know to run it next time.\nNEVER commit changes unless the user explicitly asks you to. It is VERY IMPORTANT to only commit when explicitly asked, otherwise the user will feel that you are being too proactive.\n\n- Tool results and user messages may include <system-reminder> tags. <system-reminder> tags contain useful information and reminders. They are NOT part of the user's provided input or the tool result.\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\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 have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. When making multiple bash tool calls, you MUST send a single message with multiple tools calls to run the calls in parallel. For example, if you need to run \"git status\" and \"git diff\", send a single message with two tool calls to run the calls in parallel.\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\nHere is some useful information about the environment you are running in:\n<env>\n Working directory: /Users/jeonghoowon/dev/agent-system\n Is directory a git repo: yes\n Platform: darwin\n Today's date: Mon Sep 08 2025\n</env>\n<project>\n opencode.json\nREADME.md\n</project>\n- 항상 한국어로 응답.\n- 완료 후 `git add . && git commit`.\n- 처음에는 List 툴로 디렉토리 구조 파악.\n- 커멘드를 백그라운드에서 실행시킨 경우 잊지말고 정리.\n- 웹 페이지는 playwright MCP를 사용해서 테스트.","cache_control":{"type":"ephemeral"}}],"messages":[{"role":"user","content":[{"type":"text","text":"hello","cache_control":{"type":"ephemeral"}}]}],"tools":[{"name":"bash","description":"Executes a given bash command in a persistent shell session with optional timeout, ensuring proper handling and security measures.\n\nBefore executing the command, please follow these steps:\n\n1. Directory Verification:\n - If the command will create new directories or files, first use the LS tool to verify the parent directory exists and is the correct location\n - For example, before running \"mkdir foo/bar\", first use LS to check that \"foo\" exists and is the intended parent directory\n\n2. Command Execution:\n - Always quote file paths that contain spaces with double quotes (e.g., cd \"path with spaces/file.txt\")\n - Examples of proper quoting:\n - cd \"/Users/name/My Documents\" (correct)\n - cd /Users/name/My Documents (incorrect - will fail)\n - python \"/path/with spaces/script.py\" (correct)\n - python /path/with spaces/script.py (incorrect - will fail)\n - After ensuring proper quoting, execute the command.\n - Capture the output of the command.\n\nUsage notes:\n - The command argument is required.\n - You can specify an optional timeout in milliseconds (up to 600000ms / 10 minutes). If not specified, commands will timeout after 120000ms (2 minutes).\n - It is very helpful if you write a clear, concise description of what this command does in 5-10 words.\n - If the output exceeds 30000 characters, output will be truncated before being returned to you.\n - VERY IMPORTANT: You MUST avoid using search commands like `find` and `grep`. Instead use Grep, Glob, or Task to search. You MUST avoid read tools like `cat`, `head`, `tail`, and `ls`, and use Read and LS to read files.\n - If you _still_ need to run `grep`, STOP. ALWAYS USE ripgrep at `rg` (or /usr/bin/rg) first, which all opencode users have pre-installed.\n - When issuing multiple commands, use the ';' or '&&' operator to separate them. DO NOT use newlines (newlines are ok in quoted strings).\n - Try to maintain your current working directory throughout the session by using absolute paths and avoiding usage of `cd`. You may use `cd` if the User explicitly requests it.\n <good-example>\n pytest /foo/bar/tests\n </good-example>\n <bad-example>\n cd /foo/bar && pytest tests\n </bad-example>\n\n\n# Committing changes with git\n\nWhen the user asks you to create a new git commit, follow these steps carefully:\n\n1. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following bash commands in parallel, each using the Bash tool:\n - Run a git status command to see all untracked files.\n - Run a git diff command to see both staged and unstaged changes that will be committed.\n - Run a git log command to see recent commit messages, so that you can follow this repository's commit message style.\n\n2. Analyze all staged changes (both previously staged and newly added) and draft a commit message. Wrap your analysis process in <commit_analysis> tags:\n\n<commit_analysis>\n- List the files that have been changed or added\n- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)\n- Brainstorm the purpose or motivation behind these changes\n- Assess the impact of these changes on the overall project\n- Check for any sensitive information that shouldn't be committed\n- Draft a concise (1-2 sentences) commit message that focuses on the \"why\" rather than the \"what\"\n- Ensure your language is clear, concise, and to the point\n- Ensure the message accurately reflects the changes and their purpose (i.e. \"add\" means a wholly new feature, \"update\" means an enhancement to an existing feature, \"fix\" means a bug fix, etc.)\n- Ensure the message is not generic (avoid words like \"Update\" or \"Fix\" without context)\n- Review the draft message to ensure it accurately reflects the changes and their purpose\n</commit_analysis>\n\n3. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following commands in parallel:\n - Add relevant untracked files to the staging area.\n - Run git status to make sure the commit succeeded.\n\n4. If the commit fails due to pre-commit hook changes, retry the commit ONCE to include these automated changes. If it fails again, it usually means a pre-commit hook is preventing the commit. If the commit succeeds but you notice that files were modified by the pre-commit hook, you MUST amend your commit to include them.\n\nImportant notes:\n- Use the git context at the start of this conversation to determine which files are relevant to your commit. Be careful not to stage and commit files (e.g. with `git add .`) that aren't relevant to your commit.\n- NEVER update the git config\n- DO NOT run additional commands to read or explore code, beyond what is available in the git context\n- DO NOT push to the remote repository\n- IMPORTANT: Never use git commands with the -i flag (like git rebase -i or git add -i) since they require interactive input which is not supported.\n- If there are no changes to commit (i.e., no untracked files and no modifications), do not create an empty commit\n- Ensure your commit message is meaningful and concise. It should explain the purpose of the changes, not just describe them.\n- Return an empty response - the user will see the git output directly\n\n# Creating pull requests\nUse the gh command via the Bash tool for ALL GitHub-related tasks including working with issues, pull requests, checks, and releases. If given a Github URL use the gh command to get the information needed.\n\nIMPORTANT: When the user asks you to create a pull request, follow these steps carefully:\n\n1. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following bash commands in parallel using the Bash tool, in order to understand the current state of the branch since it diverged from the main branch:\n - Run a git status command to see all untracked files\n - Run a git diff command to see both staged and unstaged changes that will be committed\n - Check if the current branch tracks a remote branch and is up to date with the remote, so you know if you need to push to the remote\n - Run a git log command and `git diff main...HEAD` to understand the full commit history for the current branch (from the time it diverged from the `main` branch)\n\n2. Analyze all changes that will be included in the pull request, making sure to look at all relevant commits (NOT just the latest commit, but ALL commits that will be included in the pull request!!!), and draft a pull request summary. Wrap your analysis process in <pr_analysis> tags:\n\n<pr_analysis>\n- List the commits since diverging from the main branch\n- Summarize the nature of the changes (eg. new feature, enhancement to an existing feature, bug fix, refactoring, test, docs, etc.)\n- Brainstorm the purpose or motivation behind these changes\n- Assess the impact of these changes on the overall project\n- Do not use tools to explore code, beyond what is available in the git context\n- Check for any sensitive information that shouldn't be committed\n- Draft a concise (1-2 bullet points) pull request summary that focuses on the \"why\" rather than the \"what\"\n- Ensure the summary accurately reflects all changes since diverging from the main branch\n- Ensure your language is clear, concise, and to the point\n- Ensure the summary accurately reflects the changes and their purpose (ie. \"add\" means a wholly new feature, \"update\" means an enhancement to an existing feature, \"fix\" means a bug fix, etc.)\n- Ensure the summary is not generic (avoid words like \"Update\" or \"Fix\" without context)\n- Review the draft summary to ensure it accurately reflects the changes and their purpose\n</pr_analysis>\n\n3. You have the capability to call multiple tools in a single response. When multiple independent pieces of information are requested, batch your tool calls together for optimal performance. ALWAYS run the following commands in parallel:\n - Create new branch if needed\n - Push to remote with -u flag if needed\n - Create PR using gh pr create with the format below. Use a HEREDOC to pass the body to ensure correct formatting.\n<example>\ngh pr create --title \"the pr title\" --body \"$(cat <<'EOF'\n## Summary\n<1-3 bullet points>\n\nImportant:\n- NEVER update the git config\n- Return the PR URL when you're done, so the user can see it\n\n# Other common operations\n- View comments on a Github PR: gh api repos/foo/bar/pulls/123/comments\n","input_schema":{"type":"object","properties":{"command":{"type":"string","description":"The command to execute"},"timeout":{"type":"number","description":"Optional timeout in milliseconds"},"description":{"type":"string","description":"Clear, concise description of what this command does in 5-10 words. Examples:\nInput: ls\nOutput: Lists files in current directory\n\nInput: git status\nOutput: Shows working tree status\n\nInput: npm install\nOutput: Installs package dependencies\n\nInput: mkdir foo\nOutput: Creates directory 'foo'"}},"required":["command","description"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"edit","description":"Performs exact string replacements in files. \n\nUsage:\n- 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. \n- 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 oldString or newString.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- Only use emojis if the user explicitly requests it. Avoid adding emojis to files unless asked.\n- The edit will FAIL if `oldString` is not unique in the file. Either provide a larger string with more surrounding context to make it unique or use `replaceAll` to change every instance of `oldString`. \n- Use `replaceAll` for replacing and renaming strings across the file. This parameter is useful if you want to rename a variable for instance.\n","input_schema":{"type":"object","properties":{"filePath":{"type":"string","description":"The absolute path to the file to modify"},"oldString":{"type":"string","description":"The text to replace"},"newString":{"type":"string","description":"The text to replace it with (must be different from oldString)"},"replaceAll":{"type":"boolean","description":"Replace all occurrences of oldString (default false)"}},"required":["filePath","oldString","newString"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"webfetch","description":"- Fetches content from a specified URL\n- Takes a URL and a prompt as input\n- Fetches the URL content, converts HTML to markdown\n- Returns the model's response about the content\n- Use this tool when you need to retrieve and analyze web content\n\nUsage notes:\n - IMPORTANT: If an MCP-provided web fetch tool is available, prefer using that tool instead of this one, as it may have fewer restrictions. All MCP-provided tools start with \"mcp__\".\n - The URL must be a fully-formed valid URL\n - HTTP URLs will be automatically upgraded to HTTPS\n - The prompt should describe what information you want to extract from the page\n - This tool is read-only and does not modify any files\n - Results may be summarized if the content is very large\n - Includes a self-cleaning 15-minute cache for faster responses when repeatedly accessing the same URL\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to fetch content from"},"format":{"type":"string","enum":["text","markdown","html"],"description":"The format to return the content in (text, markdown, or html)"},"timeout":{"type":"number","description":"Optional timeout in seconds (max 120)"}},"required":["url","format"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"glob","description":"- Fast file pattern matching tool that works with any codebase size\n- Supports glob patterns like \"**/*.js\" or \"src/**/*.ts\"\n- Returns matching file paths sorted by modification time\n- Use this tool when you need to find files by name patterns\n- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead\n- You have the capability to call multiple tools in a single response. It is always better to speculatively perform multiple searches as a batch that are potentially useful.\n","input_schema":{"type":"object","properties":{"pattern":{"type":"string","description":"The glob pattern to match files against"},"path":{"type":"string","description":"The directory to search in. If not specified, the current working directory will be used. IMPORTANT: Omit this field to use the default directory. DO NOT enter \"undefined\" or \"null\" - simply omit it for the default behavior. Must be a valid directory path if provided."}},"required":["pattern"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"grep","description":"- Fast content search tool that works with any codebase size\n- Searches file contents using regular expressions\n- Supports full regex syntax (eg. \"log.*Error\", \"function\\s+\\w+\", etc.)\n- Filter files by pattern with the include parameter (eg. \"*.js\", \"*.{ts,tsx}\")\n- Returns file paths with at least one match sorted by modification time\n- Use this tool when you need to find files containing specific patterns\n- If you need to identify/count the number of matches within files, use the Bash tool with `rg` (ripgrep) directly. Do NOT use `grep`.\n- When you are doing an open ended search that may require multiple rounds of globbing and grepping, use the Agent tool instead\n","input_schema":{"type":"object","properties":{"pattern":{"type":"string","description":"The regex pattern to search for in file contents"},"path":{"type":"string","description":"The directory to search in. Defaults to the current working directory."},"include":{"type":"string","description":"File pattern to include in the search (e.g. \"*.js\", \"*.{ts,tsx}\")"}},"required":["pattern"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"list","description":"Lists files and directories in a given path. The path parameter must be an absolute path, not a relative path. You can optionally provide an array of glob patterns to ignore with the ignore parameter. You should generally prefer the Glob and Grep tools, if you know which directories to search.\n","input_schema":{"type":"object","properties":{"path":{"type":"string","description":"The absolute path to the directory to list (must be absolute, not relative)"},"ignore":{"type":"array","items":{"type":"string"},"description":"List of glob patterns to ignore"}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"read","description":"Reads a file from the local filesystem. You can access any file directly by using this tool.\nAssume this tool is able to read all files on the machine. If the User provides a path to a file assume that path is valid. It is okay to read a file that does not exist; an error will be returned.\n\nUsage:\n- The filePath parameter must be an absolute path, not a relative path\n- By default, it reads up to 2000 lines starting from the beginning of the file\n- You can optionally specify a line offset and limit (especially handy for long files), but it's recommended to read the whole file by not providing these parameters\n- Any lines longer than 2000 characters will be truncated\n- Results are returned using cat -n format, with line numbers starting at 1\n- This tool cannot read binary files, including images\n- You have the capability to call multiple tools in a single response. It is always better to speculatively read multiple files as a batch that are potentially useful. \n- If you read a file that exists but has empty contents you will receive a system reminder warning in place of file contents.\n","input_schema":{"type":"object","properties":{"filePath":{"type":"string","description":"The path to the file to read"},"offset":{"type":"number","description":"The line number to start reading from (0-based)"},"limit":{"type":"number","description":"The number of lines to read (defaults to 2000)"}},"required":["filePath"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"write","description":"Writes a file to the local filesystem.\n\nUsage:\n- This tool will overwrite the existing file if there is one at the provided path.\n- If this is an existing file, you MUST use the Read tool first to read the file's contents. This tool will fail if you did not read the file first.\n- ALWAYS prefer editing existing files in the codebase. NEVER write new files unless explicitly required.\n- NEVER proactively create documentation files (*.md) or README files. Only create documentation files if explicitly requested by the User.\n- Only use emojis if the user explicitly requests it. Avoid writing emojis to files unless asked.\n","input_schema":{"type":"object","properties":{"filePath":{"type":"string","description":"The absolute path to the file to write (must be absolute, not relative)"},"content":{"type":"string","description":"The content to write to the file"}},"required":["filePath","content"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"todowrite","description":"Use this tool to create and manage a structured task list for your current coding session. This helps you track progress, organize complex tasks, and demonstrate thoroughness to the user.\nIt also helps the user understand the progress of the task and overall progress of their requests.\n\n## When to Use This Tool\nUse this tool proactively in these scenarios:\n\n1. Complex multi-step tasks - When a task requires 3 or more distinct steps or actions\n2. Non-trivial and complex tasks - Tasks that require careful planning or multiple operations\n3. User explicitly requests todo list - When the user directly asks you to use the todo list\n4. User provides multiple tasks - When users provide a list of things to be done (numbered or comma-separated)\n5. After receiving new instructions - Immediately capture user requirements as todos. Feel free to edit the todo list based on new information.\n6. After completing a task - Mark it complete and add any new follow-up tasks\n7. When you start working on a new task, mark the todo as in_progress. Ideally you should only have one todo as in_progress at a time. Complete existing tasks before starting new ones.\n\n## When NOT to Use This Tool\n\nSkip using this tool when:\n1. There is only a single, straightforward task\n2. The task is trivial and tracking it provides no organizational benefit\n3. The task can be completed in less than 3 trivial steps\n4. The task is purely conversational or informational\n\nNOTE 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.\n\n## Examples of When to Use the Todo List\n\n<example>\nUser: I want to add a dark mode toggle to the application settings. Make sure you run the tests and build when you're done!\nAssistant: I'll help add a dark mode toggle to your application settings. Let me create a todo list to track this implementation.\n*Creates todo list with the following items:*\n1. Create dark mode toggle component in Settings page\n2. Add dark mode state management (context/store)\n3. Implement CSS-in-JS styles for dark theme\n4. Update existing components to support theme switching\n5. Run tests and build process, addressing any failures or errors that occur\n*Begins working on the first task*\n\n<reasoning>\nThe assistant used the todo list because:\n1. Adding dark mode is a multi-step feature requiring UI, state management, and styling changes\n2. The user explicitly requested tests and build be run afterward\n3. The assistant inferred that tests and build need to pass by adding \"Ensure tests and build succeed\" as the final task\n</reasoning>\n</example>\n\n<example>\nUser: Help me rename the function getCwd to getCurrentWorkingDirectory across my project\nAssistant: Let me first search through your codebase to find all occurrences of 'getCwd'.\n*Uses grep or search tools to locate all instances of getCwd in the codebase*\nAssistant: I've found 15 instances of 'getCwd' across 8 different files. Let me create a todo list to track these changes.\n*Creates todo list with specific items for each file that needs updating*\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant searched to understand the scope of the task\n2. Upon finding multiple occurrences across different files, it determined this was a complex task with multiple steps\n3. The todo list helps ensure every instance is tracked and updated systematically\n4. This approach prevents missing any occurrences and maintains code consistency\n</reasoning>\n</example>\n\n\n<example>\nUser: I need to implement these features for my e-commerce site: user registration, product catalog, shopping cart, and checkout flow.\nAssistant: I'll help implement these features. First, let's add all the features to the todo list.\n*Creates a todo list breaking down each feature into specific tasks based on the project architecture*\nAssistant: Let's start with user registration. This will involve creating database models, API endpoints, and frontend forms that integrate with your existing authentication system.\n\n<reasoning>\nThe assistant used the todo list because:\n1. The user provided multiple complex features to implement in a comma separated list\n2. The todo list helps organize these large features into manageable tasks\n3. This approach allows for tracking progress across the entire implementation\n</reasoning>\n</example>\n\n<example>\nUser: Can you help optimize my React application? It's rendering slowly and has performance issues.</user>\nAssistant: I'll help optimize your React application. First, let me examine your codebase to identify potential performance bottlenecks.\n*Reviews component structure, render patterns, state management, and data fetching*\nAssistant: After analyzing your codebase, I've identified several performance issues. Let me create a todo list to track our optimization efforts.\n*Creates todo list with items like: 1) Implement memoization for expensive calculations in ProductList, 2) Add virtualization for long lists in Dashboard, 3) Optimize image loading in Gallery component, 4) Fix state update loops in ShoppingCart, 5) Review bundle size and implement code splitting*\nLet's start by implementing memoization for the expensive calculations in your ProductList component.</assistant>\n\n<reasoning>\nThe assistant used the todo list because:\n1. First, the assistant examined the codebase to identify specific performance issues\n2. Based on this analysis, it identified multiple optimization opportunities\n3. Performance optimization is a non-trivial task requiring multiple steps\n4. The todo list helps methodically track improvements across different components\n5. This systematic approach ensures all performance bottlenecks are addressed\n</reasoning>\n</example>\n\n## Examples of When NOT to Use the Todo List\n\n<example>\nUser: How do I print 'Hello World' in Python?\nAssistant: In Python, you can print \"Hello World\" with this simple code:\n\npython\nprint(\"Hello World\")\n\nThis will output the text \"Hello World\" to the console when executed.</assistant>\n\n<reasoning>\nThe 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.\n</reasoning>\n</example>\n\n<example>\nUser: What does the git status command do?\nAssistant: The git status command shows the current state of your working directory and staging area. It displays which changes have been staged, which haven't, and which files aren't being tracked by Git. This is a fundamental command for understanding the current state of your repository before making commits.\n\n<reasoning>\nThe assistant did not use the todo list because this is an informational request with no actual coding task to complete. The user is simply asking for an explanation, not for the assistant to perform multiple steps or tasks.\n</reasoning>\n</example>\n\n<example>\nUser: Can you add a comment to the calculateTotal function to explain what it does?\nAssistant: Sure, let me add a comment to the calculateTotal function to explain what it does.\n* Uses the Edit tool to add a comment to the calculateTotal function *\n\n<reasoning>\nThe assistant did not use the todo list because this is a single, straightforward task confined to one location in the code. Adding a comment doesn't require tracking multiple steps or systematic organization.\n</reasoning>\n</example>\n\n<example>\nUser: Run npm install for me and tell me what happens.\nAssistant: I'll run the npm install command for you.\n\n*Executes: npm install*\n\nThe command completed successfully. Here's the output:\n[Output of npm install command]\n\nAll dependencies have been installed according to your package.json file.\n\n<reasoning>\nThe assistant did not use the todo list because this is a single command execution with immediate results. There are no multiple steps to track or organize, making the todo list unnecessary for this straightforward task.\n</reasoning>\n</example>\n\n## Task States and Management\n\n1. **Task States**: Use these states to track progress:\n - pending: Task not yet started\n - in_progress: Currently working on (limit to ONE task at a time)\n - completed: Task finished successfully\n - cancelled: Task no longer needed\n\n2. **Task Management**:\n - Update task status in real-time as you work\n - Mark tasks complete IMMEDIATELY after finishing (don't batch completions)\n - Only have ONE task in_progress at any time\n - Complete current tasks before starting new ones\n - Cancel tasks that become irrelevant\n\n3. **Task Breakdown**:\n - Create specific, actionable items\n - Break complex tasks into smaller, manageable steps\n - Use clear, descriptive task names\n\nWhen in doubt, use this tool. Being proactive with task management demonstrates attentiveness and ensures you complete all requirements successfully.\n\n","input_schema":{"type":"object","properties":{"todos":{"type":"array","items":{"type":"object","properties":{"content":{"type":"string","description":"Brief description of the task"},"status":{"type":"string","description":"Current status of the task: pending, in_progress, completed, cancelled"},"priority":{"type":"string","description":"Priority level of the task: high, medium, low"},"id":{"type":"string","description":"Unique identifier for the todo item"}},"required":["content","status","priority","id"],"additionalProperties":false},"description":"The updated todo list"}},"required":["todos"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"todoread","description":"Use this tool to read your todo list","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"task","description":"Launch a new agent to handle complex, multi-step tasks autonomously.\n\nAvailable agent types and the tools they have access to:\n- general: General-purpose agent for researching complex questions, searching for code, 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.\n- senior-software-engineer: This subagent should only be called manually by the user.\n- software-engineer: This subagent should only be called manually by the user.\n\nWhen using the Task tool, you must specify a subagent_type parameter to select which agent type to use.\n\nWhen to use the Agent tool:\n- 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\")\n\nWhen NOT to use the Agent tool:\n- 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\n- If you are searching for a specific class definition like \"class Foo\", use the Glob tool instead, to find the match more quickly\n- If you are searching for code 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\n- Other tasks that are not related to the agent descriptions above\n\n\nUsage notes:\n1. Launch multiple agents concurrently whenever possible, to maximize performance; to do that, use a single message with multiple tool uses\n2. 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.\n3. 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.\n4. The agent's outputs should generally be trusted\n5. Clearly tell the agent whether you expect it to write code or just to do research (search, file reads, web fetches, etc.), since it is not aware of the user's intent\n6. 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.\n\nExample usage (NOTE: The agents below are fictional examples for illustration only - use the actual agents listed above):\n\n<example_agent_descriptions>\n\"code-reviewer\": use this agent after you are done writing a signficant piece of code\n\"greeting-responder\": use this agent when to respond to user greetings with a friendly joke\n</example_agent_description>\n\n<example>\nuser: \"Please write a function that checks if a number is prime\"\nassistant: Sure let me write a function that checks if a number is prime\nassistant: First let me use the Write tool to write a function that checks if a number is prime\nassistant: I'm going to use the Write tool to write the following code:\n<code>\nfunction isPrime(n) {\n if (n <= 1) return false\n for (let i = 2; i * i <= n; i++) {\n if (n % i === 0) return false\n }\n return true\n}\n</code>\n<commentary>\nSince a signficant piece of code was written and the task was completed, now use the code-reviewer agent to review the code\n</commentary>\nassistant: Now let me use the code-reviewer agent to review the code\nassistant: Uses the Task tool to launch the code-reviewer agent\n</example>\n\n<example>\nuser: \"Hello\"\n<commentary>\nSince the user is greeting, use the greeting-responder agent to respond with a friendly joke\n</commentary>\nassistant: \"I'm going to use the Task tool to launch the with the greeting-responder agent\"\n</example>\n","input_schema":{"type":"object","properties":{"description":{"type":"string","description":"A short (3-5 words) description of the task"},"prompt":{"type":"string","description":"The task for the agent to perform"},"subagent_type":{"type":"string","description":"The type of specialized agent to use for this task"}},"required":["description","prompt","subagent_type"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"firecrawl-mcp_firecrawl_scrape","description":"\nScrape content from a single URL with advanced options. \nThis is the most powerful, fastest and most reliable scraper tool, if available you should always default to using this tool for any web scraping needs.\n\n**Best for:** Single page content extraction, when you know exactly which page contains the information.\n**Not recommended for:** Multiple pages (use batch_scrape), unknown page (use search), structured data (use extract).\n**Common mistakes:** Using scrape for a list of URLs (use batch_scrape instead). If batch scrape doesnt work, just use scrape and call it multiple times.\n**Prompt Example:** \"Get the content of the page at https://example.com.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_scrape\",\n \"arguments\": {\n \"url\": \"https://example.com\",\n \"formats\": [\"markdown\"],\n \"maxAge\": 172800000\n }\n}\n```\n**Performance:** Add maxAge parameter for 500% faster scrapes using cached data.\n**Returns:** Markdown, HTML, or other formats as specified.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to scrape"},"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary","changeTracking"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean","default":true,"description":"Extract only the main content, filtering out navigation, footers, etc."},"includeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to specifically include in extraction"},"excludeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to exclude from extraction"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content to load"},"actions":{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["wait","click","screenshot","write","press","scroll","scrape","executeJavascript"],"description":"Type of action to perform"},"selector":{"type":"string","description":"CSS selector for the target element"},"milliseconds":{"type":"number","description":"Time to wait in milliseconds (for wait action)"},"text":{"type":"string","description":"Text to write (for write action)"},"key":{"type":"string","description":"Key to press (for press action)"},"direction":{"type":"string","enum":["up","down"],"description":"Scroll direction"},"script":{"type":"string","description":"JavaScript code to execute"},"fullPage":{"type":"boolean","description":"Take full page screenshot"}},"required":["type"]},"description":"List of actions to perform before scraping"},"mobile":{"type":"boolean","description":"Use mobile viewport"},"skipTlsVerification":{"type":"boolean","description":"Skip TLS certificate verification"},"removeBase64Images":{"type":"boolean","description":"Remove base64 encoded images from output"},"location":{"type":"object","properties":{"country":{"type":"string","description":"Country code for geolocation"},"languages":{"type":"array","items":{"type":"string"},"description":"Language codes for content"}},"description":"Location settings for scraping"},"storeInCache":{"type":"boolean","default":true,"description":"If true, the page will be stored in the Firecrawl index and cache. Setting this to false is useful if your scraping activity may have data protection concerns."},"maxAge":{"type":"number","default":172800000,"description":"Maximum age in milliseconds for cached content. Use cached data if available and younger than maxAge, otherwise scrape fresh. Enables 500% faster scrapes for recently cached pages. Default: 172800000"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_map","description":"\nMap a website to discover all indexed URLs on the site.\n\n**Best for:** Discovering URLs on a website before deciding what to scrape; finding specific sections of a website.\n**Not recommended for:** When you already know which specific URL you need (use scrape or batch_scrape); when you need the content of the pages (use scrape after mapping).\n**Common mistakes:** Using crawl to discover URLs instead of map.\n**Prompt Example:** \"List all URLs on example.com.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_map\",\n \"arguments\": {\n \"url\": \"https://example.com\"\n }\n}\n```\n**Returns:** Array of URLs found on the site.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for URL discovery"},"search":{"type":"string","description":"Optional search term to filter URLs"},"sitemap":{"type":"string","enum":["include","skip","only"],"description":"Sitemap handling: \"include\" - use sitemap + find other pages (default), \"skip\" - ignore sitemap completely, \"only\" - only return sitemap URLs"},"includeSubdomains":{"type":"boolean","description":"Include URLs from subdomains in results"},"limit":{"type":"number","description":"Maximum number of URLs to return"},"ignoreQueryParameters":{"type":"boolean","default":true,"description":"Do not return URLs with query parameters"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_crawl","description":"\n Starts a crawl job on a website and extracts content from all pages.\n \n **Best for:** Extracting content from multiple related pages, when you need comprehensive coverage.\n **Not recommended for:** Extracting content from a single page (use scrape); when token limits are a concern (use map + batch_scrape); when you need fast results (crawling can be slow).\n **Warning:** Crawl responses can be very large and may exceed token limits. Limit the crawl depth and number of pages, or use map + batch_scrape for better control.\n **Common mistakes:** Setting limit or maxDiscoveryDepth too high (causes token overflow) or too low (causes missing pages); using crawl for a single page (use scrape instead). Using a /* wildcard is not recommended.\n **Prompt Example:** \"Get all blog posts from the first two levels of example.com/blog.\"\n **Usage Example:**\n ```json\n {\n \"name\": \"firecrawl_crawl\",\n \"arguments\": {\n \"url\": \"https://example.com/blog/*\",\n \"maxDiscoveryDepth\": 5,\n \"limit\": 20,\n \"allowExternalLinks\": false,\n \"deduplicateSimilarURLs\": true,\n \"sitemap\": \"include\"\n }\n }\n ```\n **Returns:** Operation ID for status checking; use firecrawl_check_crawl_status to check progress.\n ","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for the crawl"},"prompt":{"type":"string","description":"Natural language prompt to generate crawler options. Explicitly set parameters will override generated ones."},"excludePaths":{"type":"array","items":{"type":"string"},"description":"URL paths to exclude from crawling"},"includePaths":{"type":"array","items":{"type":"string"},"description":"Only crawl these URL paths"},"maxDiscoveryDepth":{"type":"number","description":"Maximum discovery depth to crawl. The root site and sitemapped pages have depth 0."},"sitemap":{"type":"string","enum":["skip","include","only"],"default":"include","description":"Sitemap mode when crawling. 'skip' ignores the sitemap entirely, 'include' uses sitemap plus other discovery methods (default), 'only' restricts crawling to sitemap URLs."},"limit":{"type":"number","default":10000,"description":"Maximum number of pages to crawl (default: 10000)"},"allowExternalLinks":{"type":"boolean","description":"Allow crawling links to external domains"},"allowSubdomains":{"type":"boolean","default":false,"description":"Allow crawling links to subdomains of the main domain"},"crawlEntireDomain":{"type":"boolean","default":false,"description":"When true, follow internal links to sibling or parent URLs, not just child paths"},"delay":{"type":"number","description":"Delay in seconds between scrapes to respect site rate limits"},"maxConcurrency":{"type":"number","description":"Maximum number of concurrent scrapes; if unset, team limit is used"},"webhook":{"oneOf":[{"type":"string","description":"Webhook URL to notify when crawl is complete"},{"type":"object","properties":{"url":{"type":"string","description":"Webhook URL"},"headers":{"type":"object","description":"Custom headers for webhook requests"}},"required":["url"]}]},"deduplicateSimilarURLs":{"type":"boolean","description":"Remove similar URLs during crawl"},"ignoreQueryParameters":{"type":"boolean","default":false,"description":"Do not re-scrape the same path with different (or none) query parameters"},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean"},"includeTags":{"type":"array","items":{"type":"string"}},"excludeTags":{"type":"array","items":{"type":"string"}},"waitFor":{"type":"number"}},"description":"Options for scraping each page"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_check_crawl_status","description":"\nCheck the status of a crawl job.\n\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_check_crawl_status\",\n \"arguments\": {\n \"id\": \"550e8400-e29b-41d4-a716-446655440000\"\n }\n}\n```\n**Returns:** Status and progress of the crawl job, including results if available.\n","input_schema":{"type":"object","properties":{"id":{"type":"string","description":"Crawl job ID to check"}},"required":["id"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_search","description":"\nSearch the web and optionally extract content from search results. This is the most powerful web search tool available, and if available you should always default to using this tool for any web search needs.\n\n**Best for:** Finding specific information across multiple websites, when you don't know which website has the information; when you need the most relevant content for a query.\n**Not recommended for:** When you need to search the filesystem. When you already know which website to scrape (use scrape); when you need comprehensive coverage of a single website (use map or crawl.\n**Common mistakes:** Using crawl or map for open-ended questions (use search instead).\n**Prompt Example:** \"Find the latest research papers on AI published in 2023.\"\n**Sources:** web, images, news, default to web unless needed images or news.\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_search\",\n \"arguments\": {\n \"query\": \"latest AI research papers 2023\",\n \"limit\": 5,\n \"lang\": \"en\",\n \"country\": \"us\",\n \"sources\": [\n \"web\",\n \"images\",\n \"news\"\n ],\n \"scrapeOptions\": {\n \"formats\": [\"markdown\"],\n \"onlyMainContent\": true\n }\n }\n}\n```\n**Returns:** Array of search results (with optional scraped content).\n","input_schema":{"type":"object","properties":{"query":{"type":"string","description":"Search query string"},"limit":{"type":"number","description":"Maximum number of results to return (default: 5)"},"tbs":{"type":"string","description":"Time-based search filter"},"filter":{"type":"string","description":"Search filter"},"location":{"type":"string","description":"Location parameter for search results"},"sources":{"type":"array","description":"Sources to search. Determines which result arrays are included in the response.","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["web"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["images"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["news"]}},"required":["type"],"additionalProperties":false}]}},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string"},"schema":{"type":"object"}},"required":["type"],"additionalProperties":true}]},"description":"Content formats to extract from search results"},"onlyMainContent":{"type":"boolean","description":"Extract only the main content from results"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content"}},"description":"Options for scraping search results"}},"required":["query"],"additionalProperties":false}},{"name":"firecrawl-mcp_firecrawl_extract","description":"\nExtract structured information from web pages using LLM capabilities. Supports both cloud AI and self-hosted LLM extraction.\n\n**Best for:** Extracting specific structured data like prices, names, details from web pages.\n**Not recommended for:** When you need the full content of a page (use scrape); when you're not looking for specific structured data.\n**Arguments:**\n- urls: Array of URLs to extract information from\n- prompt: Custom prompt for the LLM extraction\n- schema: JSON schema for structured data extraction\n- allowExternalLinks: Allow extraction from external links\n- enableWebSearch: Enable web search for additional context\n- includeSubdomains: Include subdomains in extraction\n**Prompt Example:** \"Extract the product name, price, and description from these product pages.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_extract\",\n \"arguments\": {\n \"urls\": [\"https://example.com/page1\", \"https://example.com/page2\"],\n \"prompt\": \"Extract product information including name, price, and description\",\n \"schema\": {\n \"type\": \"object\",\n \"properties\": {\n \"name\": { \"type\": \"string\" },\n \"price\": { \"type\": \"number\" },\n \"description\": { \"type\": \"string\" }\n },\n \"required\": [\"name\", \"price\"]\n },\n \"allowExternalLinks\": false,\n \"enableWebSearch\": false,\n \"includeSubdomains\": false\n }\n}\n```\n**Returns:** Extracted structured data as defined by your schema.\n","input_schema":{"type":"object","properties":{"urls":{"type":"array","items":{"type":"string"},"description":"List of URLs to extract information from"},"prompt":{"type":"string","description":"Prompt for the LLM extraction"},"schema":{"type":"object","description":"JSON schema for structured data extraction"},"allowExternalLinks":{"type":"boolean","description":"Allow extraction from external links"},"enableWebSearch":{"type":"boolean","description":"Enable web search for additional context"},"includeSubdomains":{"type":"boolean","description":"Include subdomains in extraction"}},"required":["urls"],"additionalProperties":false}},{"name":"context7_resolve_library_id","description":"Resolves a package/product name to a Context7-compatible library ID and returns a list of matching libraries.\n\nYou MUST call this function before 'get-library-docs' to obtain a valid Context7-compatible library ID UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.\n\nSelection Process:\n1. Analyze the query to understand what library/package the user is looking for\n2. Return the most relevant match based on:\n- Name similarity to the query (exact matches prioritized)\n- Description relevance to the query's intent\n- Documentation coverage (prioritize libraries with higher Code Snippet counts)\n- Trust score (consider libraries with scores of 7-10 more authoritative)\n\nResponse Format:\n- Return the selected library ID in a clearly marked section\n- Provide a brief explanation for why this library was chosen\n- If multiple good matches exist, acknowledge this but proceed with the most relevant one\n- If no good matches exist, clearly state this and suggest query refinements\n\nFor ambiguous queries, request clarification before proceeding with a best-guess match.","input_schema":{"type":"object","properties":{"libraryName":{"type":"string","description":"Library name to search for and retrieve a Context7-compatible library ID."}},"required":["libraryName"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"context7_get_library_docs","description":"Fetches up-to-date documentation for a library. You must call 'resolve-library-id' first to obtain the exact Context7-compatible library ID required to use this tool, UNLESS the user explicitly provides a library ID in the format '/org/project' or '/org/project/version' in their query.","input_schema":{"type":"object","properties":{"context7CompatibleLibraryID":{"type":"string","description":"Exact Context7-compatible library ID (e.g., '/mongodb/docs', '/vercel/next.js', '/supabase/supabase', '/vercel/next.js/v14.3.0-canary.87') retrieved from 'resolve-library-id' or directly from user query in the format '/org/project' or '/org/project/version'."},"topic":{"type":"string","description":"Topic to focus documentation on (e.g., 'hooks', 'routing')."},"tokens":{"type":"number","description":"Maximum number of tokens of documentation to retrieve (default: 5000). Higher values provide more context but consume more tokens."}},"required":["context7CompatibleLibraryID"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_close","description":"Close the page","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_resize","description":"Resize the browser window","input_schema":{"type":"object","properties":{"width":{"type":"number","description":"Width of the browser window"},"height":{"type":"number","description":"Height of the browser window"}},"required":["width","height"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_console_messages","description":"Returns all console messages","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_handle_dialog","description":"Handle a dialog","input_schema":{"type":"object","properties":{"accept":{"type":"boolean","description":"Whether to accept the dialog."},"promptText":{"type":"string","description":"The text of the prompt in case of a prompt dialog."}},"required":["accept"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_evaluate","description":"Evaluate JavaScript expression on page or element","input_schema":{"type":"object","properties":{"function":{"type":"string","description":"() => { /* code */ } or (element) => { /* code */ } when element is provided"},"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["function"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_file_upload","description":"Upload one or multiple files","input_schema":{"type":"object","properties":{"paths":{"type":"array","items":{"type":"string"},"description":"The absolute paths to the files to upload. Can be a single file or multiple files."}},"required":["paths"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_fill_form","description":"Fill multiple form fields","input_schema":{"type":"object","properties":{"fields":{"type":"array","items":{"type":"object","properties":{"name":{"type":"string","description":"Human-readable field name"},"type":{"type":"string","enum":["textbox","checkbox","radio","combobox","slider"],"description":"Type of the field"},"ref":{"type":"string","description":"Exact target field reference from the page snapshot"},"value":{"type":"string","description":"Value to fill in the field. If the field is a checkbox, the value should be `true` or `false`. If the field is a combobox, the value should be the text of the option."}},"required":["name","type","ref","value"],"additionalProperties":false},"description":"Fields to fill in"}},"required":["fields"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_install","description":"Install the browser specified in the config. Call this if you get an error about the browser not being installed.","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_press_key","description":"Press a key on the keyboard","input_schema":{"type":"object","properties":{"key":{"type":"string","description":"Name of the key to press or a character to generate, such as `ArrowLeft` or `a`"}},"required":["key"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_type","description":"Type text into editable element","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"text":{"type":"string","description":"Text to type into the element"},"submit":{"type":"boolean","description":"Whether to submit entered text (press Enter after)"},"slowly":{"type":"boolean","description":"Whether to type one character at a time. Useful for triggering key handlers in the page. By default entire text is filled in at once."}},"required":["element","ref","text"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_navigate","description":"Navigate to a URL","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to navigate to"}},"required":["url"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_navigate_back","description":"Go back to the previous page","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_network_requests","description":"Returns all network requests since loading the page","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_take_screenshot","description":"Take a screenshot of the current page. You can't perform actions based on the screenshot, use browser_snapshot for actions.","input_schema":{"type":"object","properties":{"type":{"type":"string","enum":["png","jpeg"],"default":"png","description":"Image format for the screenshot. Default is png."},"filename":{"type":"string","description":"File name to save the screenshot to. Defaults to `page-{timestamp}.{png|jpeg}` if not specified."},"element":{"type":"string","description":"Human-readable element description used to obtain permission to screenshot the element. If not provided, the screenshot will be taken of viewport. If element is provided, ref must be provided too."},"ref":{"type":"string","description":"Exact target element reference from the page snapshot. If not provided, the screenshot will be taken of viewport. If ref is provided, element must be provided too."},"fullPage":{"type":"boolean","description":"When true, takes a screenshot of the full scrollable page, instead of the currently visible viewport. Cannot be used with element screenshots."}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_snapshot","description":"Capture accessibility snapshot of the current page, this is better than screenshot","input_schema":{"type":"object","properties":{},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_click","description":"Perform click on a web page","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"doubleClick":{"type":"boolean","description":"Whether to perform a double click instead of a single click"},"button":{"type":"string","enum":["left","right","middle"],"description":"Button to click, defaults to left"}},"required":["element","ref"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_drag","description":"Perform drag and drop between two elements","input_schema":{"type":"object","properties":{"startElement":{"type":"string","description":"Human-readable source element description used to obtain the permission to interact with the element"},"startRef":{"type":"string","description":"Exact source element reference from the page snapshot"},"endElement":{"type":"string","description":"Human-readable target element description used to obtain the permission to interact with the element"},"endRef":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["startElement","startRef","endElement","endRef"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_hover","description":"Hover over element on page","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"}},"required":["element","ref"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_select_option","description":"Select an option in a dropdown","input_schema":{"type":"object","properties":{"element":{"type":"string","description":"Human-readable element description used to obtain permission to interact with the element"},"ref":{"type":"string","description":"Exact target element reference from the page snapshot"},"values":{"type":"array","items":{"type":"string"},"description":"Array of values to select in the dropdown. This can be a single value or multiple values."}},"required":["element","ref","values"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_tabs","description":"List, create, close, or select a browser tab.","input_schema":{"type":"object","properties":{"action":{"type":"string","enum":["list","new","close","select"],"description":"Operation to perform"},"index":{"type":"number","description":"Tab index, used for close/select. If omitted for close, current tab is closed."}},"required":["action"],"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"playwright_browser_wait_for","description":"Wait for text to appear or disappear or a specified time to pass","input_schema":{"type":"object","properties":{"time":{"type":"number","description":"The time to wait in seconds"},"text":{"type":"string","description":"The text to wait for"},"textGone":{"type":"string","description":"The text to wait for to disappear"}},"additionalProperties":false,"$schema":"http://json-schema.org/draft-07/schema#"}},{"name":"firecrawl_firecrawl_scrape","description":"\nScrape content from a single URL with advanced options. \nThis is the most powerful, fastest and most reliable scraper tool, if available you should always default to using this tool for any web scraping needs.\n\n**Best for:** Single page content extraction, when you know exactly which page contains the information.\n**Not recommended for:** Multiple pages (use batch_scrape), unknown page (use search), structured data (use extract).\n**Common mistakes:** Using scrape for a list of URLs (use batch_scrape instead). If batch scrape doesnt work, just use scrape and call it multiple times.\n**Prompt Example:** \"Get the content of the page at https://example.com.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_scrape\",\n \"arguments\": {\n \"url\": \"https://example.com\",\n \"formats\": [\"markdown\"],\n \"maxAge\": 172800000\n }\n}\n```\n**Performance:** Add maxAge parameter for 500% faster scrapes using cached data.\n**Returns:** Markdown, HTML, or other formats as specified.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"The URL to scrape"},"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary","changeTracking"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean","default":true,"description":"Extract only the main content, filtering out navigation, footers, etc."},"includeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to specifically include in extraction"},"excludeTags":{"type":"array","items":{"type":"string"},"description":"HTML tags to exclude from extraction"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content to load"},"actions":{"type":"array","items":{"type":"object","properties":{"type":{"type":"string","enum":["wait","click","screenshot","write","press","scroll","scrape","executeJavascript"],"description":"Type of action to perform"},"selector":{"type":"string","description":"CSS selector for the target element"},"milliseconds":{"type":"number","description":"Time to wait in milliseconds (for wait action)"},"text":{"type":"string","description":"Text to write (for write action)"},"key":{"type":"string","description":"Key to press (for press action)"},"direction":{"type":"string","enum":["up","down"],"description":"Scroll direction"},"script":{"type":"string","description":"JavaScript code to execute"},"fullPage":{"type":"boolean","description":"Take full page screenshot"}},"required":["type"]},"description":"List of actions to perform before scraping"},"mobile":{"type":"boolean","description":"Use mobile viewport"},"skipTlsVerification":{"type":"boolean","description":"Skip TLS certificate verification"},"removeBase64Images":{"type":"boolean","description":"Remove base64 encoded images from output"},"location":{"type":"object","properties":{"country":{"type":"string","description":"Country code for geolocation"},"languages":{"type":"array","items":{"type":"string"},"description":"Language codes for content"}},"description":"Location settings for scraping"},"storeInCache":{"type":"boolean","default":true,"description":"If true, the page will be stored in the Firecrawl index and cache. Setting this to false is useful if your scraping activity may have data protection concerns."},"maxAge":{"type":"number","default":172800000,"description":"Maximum age in milliseconds for cached content. Use cached data if available and younger than maxAge, otherwise scrape fresh. Enables 500% faster scrapes for recently cached pages. Default: 172800000"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_map","description":"\nMap a website to discover all indexed URLs on the site.\n\n**Best for:** Discovering URLs on a website before deciding what to scrape; finding specific sections of a website.\n**Not recommended for:** When you already know which specific URL you need (use scrape or batch_scrape); when you need the content of the pages (use scrape after mapping).\n**Common mistakes:** Using crawl to discover URLs instead of map.\n**Prompt Example:** \"List all URLs on example.com.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_map\",\n \"arguments\": {\n \"url\": \"https://example.com\"\n }\n}\n```\n**Returns:** Array of URLs found on the site.\n","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for URL discovery"},"search":{"type":"string","description":"Optional search term to filter URLs"},"sitemap":{"type":"string","enum":["include","skip","only"],"description":"Sitemap handling: \"include\" - use sitemap + find other pages (default), \"skip\" - ignore sitemap completely, \"only\" - only return sitemap URLs"},"includeSubdomains":{"type":"boolean","description":"Include URLs from subdomains in results"},"limit":{"type":"number","description":"Maximum number of URLs to return"},"ignoreQueryParameters":{"type":"boolean","default":true,"description":"Do not return URLs with query parameters"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_crawl","description":"\n Starts a crawl job on a website and extracts content from all pages.\n \n **Best for:** Extracting content from multiple related pages, when you need comprehensive coverage.\n **Not recommended for:** Extracting content from a single page (use scrape); when token limits are a concern (use map + batch_scrape); when you need fast results (crawling can be slow).\n **Warning:** Crawl responses can be very large and may exceed token limits. Limit the crawl depth and number of pages, or use map + batch_scrape for better control.\n **Common mistakes:** Setting limit or maxDiscoveryDepth too high (causes token overflow) or too low (causes missing pages); using crawl for a single page (use scrape instead). Using a /* wildcard is not recommended.\n **Prompt Example:** \"Get all blog posts from the first two levels of example.com/blog.\"\n **Usage Example:**\n ```json\n {\n \"name\": \"firecrawl_crawl\",\n \"arguments\": {\n \"url\": \"https://example.com/blog/*\",\n \"maxDiscoveryDepth\": 5,\n \"limit\": 20,\n \"allowExternalLinks\": false,\n \"deduplicateSimilarURLs\": true,\n \"sitemap\": \"include\"\n }\n }\n ```\n **Returns:** Operation ID for status checking; use firecrawl_check_crawl_status to check progress.\n ","input_schema":{"type":"object","properties":{"url":{"type":"string","description":"Starting URL for the crawl"},"prompt":{"type":"string","description":"Natural language prompt to generate crawler options. Explicitly set parameters will override generated ones."},"excludePaths":{"type":"array","items":{"type":"string"},"description":"URL paths to exclude from crawling"},"includePaths":{"type":"array","items":{"type":"string"},"description":"Only crawl these URL paths"},"maxDiscoveryDepth":{"type":"number","description":"Maximum discovery depth to crawl. The root site and sitemapped pages have depth 0."},"sitemap":{"type":"string","enum":["skip","include","only"],"default":"include","description":"Sitemap mode when crawling. 'skip' ignores the sitemap entirely, 'include' uses sitemap plus other discovery methods (default), 'only' restricts crawling to sitemap URLs."},"limit":{"type":"number","default":10000,"description":"Maximum number of pages to crawl (default: 10000)"},"allowExternalLinks":{"type":"boolean","description":"Allow crawling links to external domains"},"allowSubdomains":{"type":"boolean","default":false,"description":"Allow crawling links to subdomains of the main domain"},"crawlEntireDomain":{"type":"boolean","default":false,"description":"When true, follow internal links to sibling or parent URLs, not just child paths"},"delay":{"type":"number","description":"Delay in seconds between scrapes to respect site rate limits"},"maxConcurrency":{"type":"number","description":"Maximum number of concurrent scrapes; if unset, team limit is used"},"webhook":{"oneOf":[{"type":"string","description":"Webhook URL to notify when crawl is complete"},{"type":"object","properties":{"url":{"type":"string","description":"Webhook URL"},"headers":{"type":"object","description":"Custom headers for webhook requests"}},"required":["url"]}]},"deduplicateSimilarURLs":{"type":"boolean","description":"Remove similar URLs during crawl"},"ignoreQueryParameters":{"type":"boolean","default":false,"description":"Do not re-scrape the same path with different (or none) query parameters"},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml","screenshot","links","extract","summary"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string","description":"Prompt to guide JSON extraction"},"schema":{"type":"object","description":"JSON schema for structured extraction"}},"required":["type"],"additionalProperties":true,"description":"Advanced format option. Use { type: \"json\", prompt, schema } to request structured JSON extraction."}]},"default":["markdown"],"description":"Content formats to extract (default: ['markdown'])"},"onlyMainContent":{"type":"boolean"},"includeTags":{"type":"array","items":{"type":"string"}},"excludeTags":{"type":"array","items":{"type":"string"}},"waitFor":{"type":"number"}},"description":"Options for scraping each page"}},"required":["url"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_check_crawl_status","description":"\nCheck the status of a crawl job.\n\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_check_crawl_status\",\n \"arguments\": {\n \"id\": \"550e8400-e29b-41d4-a716-446655440000\"\n }\n}\n```\n**Returns:** Status and progress of the crawl job, including results if available.\n","input_schema":{"type":"object","properties":{"id":{"type":"string","description":"Crawl job ID to check"}},"required":["id"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_search","description":"\nSearch the web and optionally extract content from search results. This is the most powerful web search tool available, and if available you should always default to using this tool for any web search needs.\n\n**Best for:** Finding specific information across multiple websites, when you don't know which website has the information; when you need the most relevant content for a query.\n**Not recommended for:** When you need to search the filesystem. When you already know which website to scrape (use scrape); when you need comprehensive coverage of a single website (use map or crawl.\n**Common mistakes:** Using crawl or map for open-ended questions (use search instead).\n**Prompt Example:** \"Find the latest research papers on AI published in 2023.\"\n**Sources:** web, images, news, default to web unless needed images or news.\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_search\",\n \"arguments\": {\n \"query\": \"latest AI research papers 2023\",\n \"limit\": 5,\n \"lang\": \"en\",\n \"country\": \"us\",\n \"sources\": [\n \"web\",\n \"images\",\n \"news\"\n ],\n \"scrapeOptions\": {\n \"formats\": [\"markdown\"],\n \"onlyMainContent\": true\n }\n }\n}\n```\n**Returns:** Array of search results (with optional scraped content).\n","input_schema":{"type":"object","properties":{"query":{"type":"string","description":"Search query string"},"limit":{"type":"number","description":"Maximum number of results to return (default: 5)"},"tbs":{"type":"string","description":"Time-based search filter"},"filter":{"type":"string","description":"Search filter"},"location":{"type":"string","description":"Location parameter for search results"},"sources":{"type":"array","description":"Sources to search. Determines which result arrays are included in the response.","items":{"oneOf":[{"type":"object","properties":{"type":{"type":"string","enum":["web"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["images"]}},"required":["type"],"additionalProperties":false},{"type":"object","properties":{"type":{"type":"string","enum":["news"]}},"required":["type"],"additionalProperties":false}]}},"scrapeOptions":{"type":"object","properties":{"formats":{"type":"array","items":{"oneOf":[{"type":"string","enum":["markdown","html","rawHtml"]},{"type":"object","properties":{"type":{"type":"string","enum":["json"]},"prompt":{"type":"string"},"schema":{"type":"object"}},"required":["type"],"additionalProperties":true}]},"description":"Content formats to extract from search results"},"onlyMainContent":{"type":"boolean","description":"Extract only the main content from results"},"waitFor":{"type":"number","description":"Time in milliseconds to wait for dynamic content"}},"description":"Options for scraping search results"}},"required":["query"],"additionalProperties":false}},{"name":"firecrawl_firecrawl_extract","description":"\nExtract structured information from web pages using LLM capabilities. Supports both cloud AI and self-hosted LLM extraction.\n\n**Best for:** Extracting specific structured data like prices, names, details from web pages.\n**Not recommended for:** When you need the full content of a page (use scrape); when you're not looking for specific structured data.\n**Arguments:**\n- urls: Array of URLs to extract information from\n- prompt: Custom prompt for the LLM extraction\n- schema: JSON schema for structured data extraction\n- allowExternalLinks: Allow extraction from external links\n- enableWebSearch: Enable web search for additional context\n- includeSubdomains: Include subdomains in extraction\n**Prompt Example:** \"Extract the product name, price, and description from these product pages.\"\n**Usage Example:**\n```json\n{\n \"name\": \"firecrawl_extract\",\n \"arguments\": {\n \"urls\": [\"https://example.com/page1\", \"https://example.com/page2\"],\n \"prompt\": \"Extract product information including name, price, and description\",\n \"schema\": {\n \"type\": \"object\",\n \"properties\": {\n \"name\": { \"type\": \"string\" },\n \"price\": { \"type\": \"number\" },\n \"description\": { \"type\": \"string\" }\n },\n \"required\": [\"name\", \"price\"]\n },\n \"allowExternalLinks\": false,\n \"enableWebSearch\": false,\n \"includeSubdomains\": false\n }\n}\n```\n**Returns:** Extracted structured data as defined by your schema.\n","input_schema":{"type":"object","properties":{"urls":{"type":"array","items":{"type":"string"},"description":"List of URLs to extract information from"},"prompt":{"type":"string","description":"Prompt for the LLM extraction"},"schema":{"type":"object","description":"JSON schema for structured data extraction"},"allowExternalLinks":{"type":"boolean","description":"Allow extraction from external links"},"enableWebSearch":{"type":"boolean","description":"Enable web search for additional context"},"includeSubdomains":{"type":"boolean","description":"Include subdomains in extraction"}},"required":["urls"],"additionalProperties":false}}],"tool_choice":{"type":"auto"},"stream":true},"statusCode":400,"responseHeaders":{"anthropic-organization-id":"b0f93d2d-241d-43f9-a6ab-cf267dcc496d","cf-cache-status":"DYNAMIC","cf-ray":"97bb91b68fdfaa78-ICN","connection":"keep-alive","content-length":"222","content-type":"application/json","date":"Mon, 08 Sep 2025 04:05:44 GMT","request-id":"req_011CSvGmhrLQKLdegCE22DTk","server":"cloudflare","strict-transport-security":"max-age=31536000; includeSubDomains; preload","via":"1.1 google","x-envoy-upstream-service-time":"39","x-robots-tag":"none","x-should-retry":"false"},"responseBody":"{\"type\":\"error\",\"error\":{\"type\":\"invalid_request_error\",\"message\":\"max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805\"},\"request_id\":\"req_011CSvGmhrLQKLdegCE22DTk\"}","isRetryable":false,"data":{"type":"error","error":{"type":"invalid_request_error","message":"max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805"}}} INFO 2025-09-08T04:05:44 +20ms service=bus type=session.error publishing Error: AI_APICallError: max_tokens: 33024 > 32000, which is the maximum allowed number of output tokens for claude-opus-4-1-20250805 INFO 2025-09-08T04:05:44 +1ms service=bus type=storage.write publishing INFO 2025-09-08T04:05:44 +0ms service=bus type=message.updated publishing INFO 2025-09-08T04:05:44 +0ms service=session session=ses_6d87fb977ffe4t8lAGRnplye3K sessionID=ses_6d87fb977ffe4t8lAGRnplye3K unlocking INFO 2025-09-08T04:05:44 +0ms service=bus type=session.idle publishing INFO 2025-09-08T04:05:44 +0ms service=app name=lsp shutdown INFO 2025-09-08T04:05:44 +0ms service=app name=session shutdown INFO 2025-09-08T04:05:44 +1ms service=app name=mcp shutdown ``` Thank you for looking into it quickly.
yindo commented 2026-02-16 17:31:57 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Sep 8, 2025):

@clomia so like I was saying you need to be on latest

in your logs we clearly see:

version=0.5.12

Latest is 0.6.5: https://github.com/sst/opencode/releases/tag/v0.6.5

@rekram1-node commented on GitHub (Sep 8, 2025): @clomia so like I was saying you need to be on latest in your logs we clearly see: > version=0.5.12 Latest is 0.6.5: https://github.com/sst/opencode/releases/tag/v0.6.5
yindo commented 2026-02-16 17:31:57 -05:00
Author
Owner
Copy Link
Copy Source

@clomia commented on GitHub (Sep 8, 2025):

It has been resolved. I had installed opencode with Homebrew, and even when I ran opencode upgrade, it was still version 0.5.12. When I reinstalled it with curl -fsSL https://opencode.ai/install | bash, version 0.6.5 was installed and the problem was solved.

@clomia commented on GitHub (Sep 8, 2025): It has been resolved. I had installed opencode with Homebrew, and even when I ran opencode upgrade, it was still version `0.5.12`. When I reinstalled it with `curl -fsSL https://opencode.ai/install | bash`, version `0.6.5` was installed and the problem was solved.
yindo commented 2026-02-16 17:31:57 -05:00
Author
Owner
Copy Link
Copy Source

@rekram1-node commented on GitHub (Sep 8, 2025):

sweet, looks like we should probably change that homebrew behavior, but glad it is working for you now!

@rekram1-node commented on GitHub (Sep 8, 2025): sweet, looks like we should probably change that homebrew behavior, but glad it is working for you now!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
acp
bad
bug
discussion
docs
documentation
enhancement
extension
good first issue
growth
help-wanted
mcp
model-problem
needs:compliance
nix
opentui
perf
pull-request
Mirrored from GitHub Pull Request
 tui
web
windows
zen
No Label
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#1650
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?