Using Tools

IMPORTANT

Tools are not supported for ACP adapters as they have their own set. Not all LLMs support function calling and the use of tools. Please see the compatibility section for more information.

As outlined by Andrew Ng in Agentic Design Patterns Part 3, Tool Use, LLMs can act as agents by leveraging external tools. Andrew notes some common examples such as web searching or code execution that have obvious benefits when using LLMs.

In the plugin, tools are simply context and actions that are shared with an LLM. The LLM can act as an agent by executing tools via the chat buffer which in turn orchestrates their use within Neovim. Tools can be added as a participant to the chat buffer by using the @ key.

IMPORTANT

The use of some tools in the plugin results in you, the developer, acting as the human-in-the-loop and approving their use.

How They Work

Tools make use of an LLM's function calling ability. All tools in CodeCompanion follow OpenAI's function calling specification, here.

When a tool is added to the chat buffer, the LLM is instructured by the plugin to return a structured JSON schema which has been defined for each tool. The chat buffer parses the LLMs response and detects the tool use before triggering the tools/init.lua file. The tool system triggers off a series of events, which sees tool's added to a queue and sequentially worked with their output being shared back to the LLM via the chat buffer. Depending on the tool, flags may be inserted on the chat buffer for later processing.

An outline of the architecture can be seen here.

Built-in Tools

CodeCompanion comes with a number of built-in tools which you can leverage, as long as your adapter and model are supported.

When calling a tool, CodeCompanion replaces the tool call in any prompt you send to the LLM with the value of a tool's opts.tool_replacement_message string. This is to ensure that you can call a tool efficiently whilst making the prompt readable to the LLM.

So calling a tool with:

Use @{lorem_ipsum} to generate a random paragraph

will yield:

Use the lorem_ipsum tool to generate a random paragraph

cmd_runner

The @cmd_runner tool enables an LLM to execute commands on your machine, subject to your authorization. For example:

Can you use @{cmd_runner} to run my test suite with `pytest`?

Use @{cmd_runner} to install any missing libraries in my project

Some commands do not write any data to stdout which means the plugin can't pass the output of the execution to the LLM. When this occurs, the tool will instead share the exit code.

The LLM is specifically instructed to detect if you're running a test suite, and if so, to insert a flag in its request. This is then detected and the outcome of the test is stored in the corresponding flag on the chat buffer. This makes it ideal for workflows to hook into.

Options:

• require_approval_before require approval before running a command? (Default: true)

create_file

NOTE

By default, this tool requires user approval before it can be executed

Create a file within the current working directory:

Can you create some test fixtures using @{create_file}?

Options:

• require_approval_before require approval before creating a file? (Default: true)

delete_file

NOTE

By default, this tool requires user approval before it can be executed

Delete a file within the current working directory:

Can you use @{delete_file} to delete the quotes.lua file?

Options:

• require_approval_before require approval before deleting a file? (Default: true)

fetch_webpage

This tools enables an LLM to fetch the content from a specific webpage. It will return the text in a text format, depending on which adapter you've configured for the tool.

Use @{fetch_webpage} to tell me what the latest version on neovim.io is

Options:

• adapter The adapter used to fetch, process and format the webpage's content (Default: jina)

file_search

This tool enables an LLM to search for files in the current working directory by glob pattern. It will return a list of relative paths for any matching files.

Use @{file_search} to list all the lua files in my project

Options:

• max_results limits the amount of results that can be sent to the LLM in the response (Default: 500)

get_changed_files

This tool enables an LLM to get git diffs of any file changes in the current working directory. It will return a diff which can contain staged, unstaged and merge-conflicts.

Use @{get_changed_files} see what's changed

Options:

• max_lines limits the amount of lines that can be sent to the LLM in the response (Default: 1000)

grep_search

IMPORTANT

This tool requires ripgrep to be installed

This tool enables an LLM to search for text, within files, in the current working directory. For every match, the output ({filename}:{line number} {relative filepath}) will be shared with the LLM:

Use @{grep_search} to find all occurrences of `buf_add_message`?

Options:

• max_files (number) limits the amount of files that can be sent to the LLM in the response (Default: 100)
• respect_gitignore (boolean) (Default: true)

insert_edit_into_file

NOTE

By default, when editing files, this tool requires user approval before it can be executed

This tool can edit buffers and files for code changes from an LLM:

Use @{insert_edit_into_file} to refactor the code in #buffer

Can you apply the suggested changes to the buffer with @{insert_edit_into_file}?

Options:

• patching_algorithm (string|table|function) The algorithm to use to determine how to edit files and buffers
• require_approval_before.buffer (boolean) Require approval before editng a buffer? (Default: false)
• require_approval_before.file (boolean) Require approval before editng a file? (Default: true)
• require_confirmation_after (boolean) require confirmation after the execution and before moving on in the chat buffer? (Default: true)

list_code_usages

NOTE

This tool requires LSP to be configured and active for optimal results

This tool enables an LLM to find all usages of a symbol (function, class, method, variable, etc.) throughout your codebase. It leverages LSP for accurate results and falls back to grep for broader text searching.

The tool provides comprehensive information about symbols including:

• References: All places where the symbol is used
• Definitions: Where the symbol is defined
• Implementations: Concrete implementations of interfaces/abstract methods
• Declarations: Forward declarations
• Type Definitions: Type aliases and definitions
• Documentation: Hover documentation when available

Use @{list_code_usages} to find all usages of the `create_file` function

Can you use @{list_code_usages} to show me how the `Tools` class is implemented and used?

memory

IMPORTANT

For security, all memory operations are restricted to the /memories directory

The memory tool enables LLMs to store and retrieve information across conversations through a memory file directory (/memories).

If you're using the Anthropic adapter, then this tool will act as its client implementation. Please refer to their documentation for more information.

The tool has the following commands that an LLM can use:

• view - Lists the contents in the /memories directory or displays file content with optional line ranges
• create - Creates a new file or overwrites an existing file with specified content
• str_replace - Replaces the first exact match of text in a file with new text
• insert - Inserts text at a specific line number in a file
• delete - Removes a file or recursively deletes a directory and all its contents
• rename - Moves or renames a file or directory to a new path

To use the tool:

Use @{memory} to carry on our conversation about streamlining my dotfiles

next_edit_suggestion

Inspired by Copilot Next Edit Suggestion, the tool gives the LLM the ability to show the user where the next edit is. The LLM can only suggest edits in files or buffers that have been shared with it as context.

Options:

• jump_action (string|function) Determines how a jump to the next edit is made (Default: tabnew)

read_file

This tool can read the contents of a specific file in the current working directory. This can be useful for an LLM to gain wider context of files that haven't been shared with it.

web_search

This tool enables an LLM to search the web for a specific query, enabling it to receive up to date information:

Use @{web_search} to find the latest version of Neovim?

Use @{web_search} to search neovim.io and explain how I can configure a new language server

Currently, the tool uses tavily and you'll need to ensure that an API key has been set accordingly, as per the adapter.

Tool Groups

Tool Groups are a convenient way to combine multiple built-in tools together in the chat buffer. CodeCompanion comes with two built-in ones, @{full_stack_dev} and @{files}.

When you include a tool group in the chat, all tools within that group become available to the LLM. By default, all the tools in the group will be shown as a single <group>name</group> reference in the chat buffer. If you want to show all tools as context items in the chat buffer, set the opts.collapse_tools option to false on the group itself.

Groups may also have a prompt field which is used to replace their reference in a message in the chat buffer. This ensures that the LLM receives a useful message rather than the name of the tools themselves.

For example, the following prompt:

@{full_stack_dev}. Can you create Snake for me, in Python?

Is replaced by:

I'm giving you access to the cmd_runner, create_file, file_search, get_changed_files, grep_search, insert_edit_into_file, list_code_usages, read_file tools to help you perform coding tasks. Can you create Snake for me, in Python?

This is because the @{full_stack_dev} group has the following prompt set in the config:

groups = {
  ["full_stack_dev"] = {
    -- ...
    prompt = "I'm giving you access to the ${tools} to help you perform coding tasks",
    -- ...
  }
},

full_stack_dev

The @{full_stack_dev} is a collection of tools which have been curated to enable an LLM to create applications and understand and refactor code bases.

It contains the following tools:

• cmd_runner
• create_file
• file_search
• get_changed_files
• grep_search
• insert_edit_into_file
• list_code_usages
• read_file

You can use it with:

@{full_stack_dev}. Can we create a todo list in Vue.js?

files

The @{files} tool is a collection of tools that allows an LLM to carry out file operations in your current working directory. It contains the following files:

• create_file
• file_search
• get_changed_files
• grep_search
• insert_edit_into_file
• read_file

You can use it with:

@{files}. Can you scaffold out the folder structure for a python package?

Adapter Tools

NOTE

Adapter tools are configured via the available_tools dictionary on the adapter itself

Prior to v17.30.0, tool use in CodeCompanion was only possible with the built-in tools. However, that release unlocked adapter tools. That is, tools that are owned by LLM providers such as Anthropic and OpenAI. This allows for remote tool execution of common tasks such as web searching and computer use.

From a UX perspective, there is no difference in using the built-in and adapter tools. However, please note that an adapter tool takes precedence over a built-in tool in the event of a name clash.

Anthropic

In the anthropic adapter, the following tools are available:

• code_execution - The code execution tool allows Claude to run Bash commands and manipulate files, including writing code, in a secure, sandboxed environment
• memory - Enables Claude to store and retrieve information across conversations through a memory file directory. Claude can create, read, update, and delete files that persist between sessions, allowing it to build knowledge over time without keeping everything in the context window
• web_fetch - The web fetch tool allows Claude to retrieve full content from specified web pages and PDF documents.
• web_search - The web search tool gives Claude direct access to real-time web content, allowing it to answer questions with up-to-date information beyond its knowledge cutoff

OpenAI

In the openai_responses adapter, the following tools are available:

• web_search - Allow models to search the web for the latest information before generating a response.

Useful Tips

YOLO mode

The plugin allows you to run tools on autopilot, with YOLO mode. This automatically approves any tool use instead of prompting the user, disables any diffs, submits errors and success messages and automatically saves any buffers that tools may have edited. In the chat buffer, the keymap gty will toggle YOLO mode on/off. Alternatively, set the global variable vim.g.codecompanion_yolo_mode to enable this or set it to nil to undo this.

Security and Approvals

CodeCompanion takes security very seriously, especially in a world of agentic code development. To that end, every effort is made to ensure that LLMs are only given the information that they need to execute a tool successfully. CodeCompanion will endeavour to make sure that the full disk path to your current working directory (cwd) in Neovim is never shared. The impact of this is that the LLM can only work within the cwd when executing tools but will minimize actions that are hard to recover from.

The plugin also puts approvals at the heart of its workflow. Some tools, such as the @cmd_runner, require the user to approve any actions before they can be executed. If the tool requires this a vim.fn.confirm dialog will prompt you for a response. You may also enforce an approval for any tool.

When using CodeCompanion's in-built tools, there are three choices:

1. Approve - The tool will be executed
2. Reject - The tool will NOT be executed
3. Cancel - All tools in the queue will NOT be executed

Compatibility

Below is the tool use status of various adapters and models in CodeCompanion:

Adapter	Model	Supported	Notes
Anthropic		✅	Dependent on the model
Azure OpenAI		✅	Dependent on the model
Copilot		✅	Dependent on the model
DeepSeek		✅	Dependent on the model
Gemini		✅	Dependent on the model
GitHub Models	All	❌	Not supported yet
Huggingface	All	❌	Not supported yet
Mistral		✅	Dependent on the model
Novita		✅	Dependent on the model
Ollama	Tested with Qwen3	✅	Dependent on the model
OpenAI		✅	Dependent on the model
xAI	All	❌	Not supported yet

IMPORTANT

When using Mistral, you will need to set strategies.chat.tools.opts.auto_submit_errors to true. See #2278 for more information.