### Install and Configure AICommit2 CLI (Quick Start)

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Provides a rapid guide to globally installing AICommit2, setting up an API key for an AI provider like OpenAI, and using the tool within a Git repository to generate commit messages.

```sh
# Install globally
npm install -g aicommit2
# Set up at least one AI provider
aicommit2 config set OPENAI.key=<your-key>
# Use in your git repository
git add .
aicommit2
```

--------------------------------

### Install project dependencies with pnpm

Source: https://github.com/tak-bro/aicommit2/blob/main/CONTRIBUTING.md

This command installs all required project dependencies using the pnpm package manager, ensuring the project has all necessary modules.

```sh
pnpm i
```

--------------------------------

### Install AICommit2 with Nix Package Manager

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Provides commands for installing AICommit2 temporarily or permanently using the Nix package manager, leveraging its flake for easy setup and management within a Nix environment.

```sh
# Install temporarily in your current shell
nix run github:tak-bro/aicommit2

# Install permanently to your profile
nix profile install github:tak-bro/aicommit2

# Use the shorter alias
nix run github:tak-bro/aic2 -- --help
```

--------------------------------

### Install AICommit2 from Source

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Outlines the steps to clone the AICommit2 repository, build the project, and install it globally from the source code, useful for development, custom modifications, or specific build environments.

```sh
git clone https://github.com/tak-bro/aicommit2.git
cd aicommit2
npm run build
npm install -g .
```

--------------------------------

### Example Configurations for OpenAI API-Compatible Services in INI Format

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/compatible.md

This snippet provides various example configurations in INI format for different OpenAI API-compatible services, including Together AI, Gemini, Ollama, and OpenRouter. It illustrates how to set `compatible`, `key`, `url`, `path`, `model`, and `envKey` for each provider.

```ini
[TOGETHER]
compatible=true
key=<your-api-key>
url=https://api.together.xyz/v1
model=meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo

[GEMINI_COMPATIBILITY]
compatible=true
key=<your-api-key>
url=https://generativelanguage.googleapis.com
path=/v1beta/openai/
model=gemini-1.5-flash

[OLLAMA_COMPATIBILITY]
compatible=true
key=ollama
url=http://localhost:11434/v1
model=llama3.2

[OR_DEEPSEEK_R1]
compatible=true
url=https://openrouter.ai/api/v1
envKey=OPENROUTER_API_KEY
model=deepseek/deepseek-r1:free

[OR_QWEN3_235B_A22B]
compatible=true
url=https://openrouter.ai/api/v1
envKey=OPENROUTER_API_KEY
model=qwen/qwen3-235b-a22b:free
```

--------------------------------

### Manage aicommit2 Configurations via Command Line

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Shows how to read, set, and delete configuration settings using `aicommit2 config get`, `aicommit2 config set`, and `aicommit2 config del` commands. Includes examples for general, specific, and array-like settings.

```sh
# Get all configurations
aicommit2 config get

# Get specific configuration
aicommit2 config get OPENAI
aicommit2 config get GEMINI.key

# Set configurations
aicommit2 config set OPENAI.generate=3 GEMINI.temperature=0.5

# Delete a configuration setting or section
aicommit2 config del OPENAI.key
aicommit2 config del GEMINI
aicommit2 config del timeout
```

--------------------------------

### Run project tests

Source: https://github.com/tak-bro/aicommit2/blob/main/CONTRIBUTING.md

These commands show how to run the project's tests. The first includes an OpenAI API key for full functionality testing, while the second runs tests that do not require the key.

```sh
OPENAI_KEY=<your OPENAI key> pnpm test
```

```sh
pnpm test
```

--------------------------------

### Install Node.js version with nvm

Source: https://github.com/tak-bro/aicommit2/blob/main/CONTRIBUTING.md

This command uses nvm to install the Node.js version specified in the project's .nvmrc file, ensuring compatibility for development.

```sh
nvm i
```

--------------------------------

### Run project in development watch mode

Source: https://github.com/tak-bro/aicommit2/blob/main/CONTRIBUTING.md

Starts the build process in watch mode, automatically rebuilding the package on file changes for continuous development and immediate feedback.

```sh
pnpm build -w
```

--------------------------------

### Build the project package

Source: https://github.com/tak-bro/aicommit2/blob/main/CONTRIBUTING.md

Executes the build script defined in package.json to compile and bundle the project using pkgroll, preparing it for distribution or local execution.

```sh
pnpm build
```

--------------------------------

### Publish current branch to GitHub for testing

Source: https://github.com/tak-bro/aicommit2/blob/main/CONTRIBUTING.md

Uses `git-publish` to publish the current branch to a `npm/*` branch on the GitHub repository, making it available for installation and testing in other projects.

```sh
$ pnpm dlx git-publish

✔ Successfully published branch! Install with command:
→ npm i 'tak-bro/aicommit2#npm/develop'
```

--------------------------------

### Example Custom Template for AI Commit Message Generation

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Illustrates a sample custom template demonstrating how placeholders are integrated to guide the AI in generating commit messages. It also includes specific guidelines for the AI to follow regarding message style and content, ensuring desired output quality.

```template
Generate a {type} commit message in {locale}.
The message should not exceed {maxLength} characters.
Please provide {generate} messages.

Remember to follow these guidelines:
1. Use the imperative mood
2. Be concise and clear
3. Explain the 'why' behind the change
```

--------------------------------

### Ollama Authentication Methods Examples

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/ollama.md

This table illustrates various authentication methods supported by Ollama, detailing the corresponding values for `OLLAMA.auth` and `OLLAMA.key`. It provides examples for Bearer, Basic, JWT, OAuth 2.0, and HMAC-SHA256 authentication.

```APIDOC
Authentication Method: Bearer
  OLLAMA.auth: Bearer
  OLLAMA.key: <API key>

Authentication Method: Basic
  OLLAMA.auth: Basic
  OLLAMA.key: <Base64 Encoded username:password>

Authentication Method: JWT
  OLLAMA.auth: Bearer
  OLLAMA.key: <JWT Token>

Authentication Method: OAuth 2.0
  OLLAMA.auth: Bearer
  OLLAMA.key: <Access Token>

Authentication Method: HMAC-SHA256
  OLLAMA.auth: HMAC
  OLLAMA.key: <Base64 Encoded clientId:signature>
```

--------------------------------

### Manual Installation of aicommit2 Git Hook Script

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

This snippet provides the content for manually setting up the `prepare-commit-msg` Git hook for aicommit2. Place this script in `.git/hooks/prepare-commit-msg` to enable aicommit2 to run in hook mode.

```sh
#!/bin/sh
# your-other-hook "$@"
aicommit2 --hook-mode "$@"
```

--------------------------------

### Run published GitHub branch locally

Source: https://github.com/tak-bro/aicommit2/blob/main/CONTRIBUTING.md

Executes the package directly from the published GitHub branch using `pnpm dlx`, allowing for local testing of changes made in a fork or branch.

```sh
$ pnpm dlx 'tak-bro/aicommit2#npm/develop' # same as running `npx aicommit2`
```

--------------------------------

### Run aicommit2 with API Keys from Environment Variables

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Provides an example of running the `aicommit2` command while simultaneously setting multiple API keys via environment variables, demonstrating their precedence over configuration file settings.

```sh
OPENAI_API_KEY="your-openai-key" ANTHROPIC_API_KEY="your-anthropic-key" aicommit2
```

--------------------------------

### Install AICommit2 Globally via npm

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Details the command to install the AICommit2 CLI tool globally using npm, making it accessible from any directory in the system. This is the primary installation method for Node.js environments.

```sh
npm install -g aicommit2
```

--------------------------------

### Run compiled package locally

Source: https://github.com/tak-bro/aicommit2/blob/main/CONTRIBUTING.md

These commands demonstrate how to execute the bundled CLI script locally. The first is for UNIX-like environments, directly running the executable. The second uses Node.js, suitable for non-UNIX environments.

```sh
./dist/cli.mjs
```

```sh
node ./dist/cli.mjs
```

--------------------------------

### OpenAI API-Compatible Service Configuration Settings

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/compatible.md

This section documents the available settings for configuring OpenAI API-compatible services. It details each setting's description, whether it is required, and its default value, providing a comprehensive reference for setup.

```APIDOC
Setting: compatible
  Description: Enable OpenAI API compatibility mode
  Required: ✓ (must be true)
  Default: false
Setting: url
  Description: Base URL of the API endpoint
  Required: ✓
  Default: -
Setting: path
  Description: API path for chat completions
  Required:
  Default: -
Setting: key
  Description: API key for authentication
  Required: ✓
  Default: -
Setting: envKey
  Description: Custom environment variable name for the API key
  Required:
  Default: -
Setting: model
  Description: Model identifier to use
  Required: ✓
  Default: -
```

--------------------------------

### Basic CLI Usage for aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

This example shows the fundamental way to use aicommit2 from the command line. After staging your changes with `git add`, simply run `aicommit2` to generate and apply an AI-suggested commit message.

```sh
git add <files...>
aicommit2
```

--------------------------------

### Configure Perplexity AI Basic Settings with aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/perplexity.md

This snippet demonstrates how to set the essential Perplexity API key and default model using the `aicommit2 config set` command for a basic setup.

```sh
aicommit2 config set PERPLEXITY.key="your-api-key"
aicommit2 config set PERPLEXITY.model="sonar-pro"
```

--------------------------------

### Example of aicommit2 CLI with Multiple Options

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

This example demonstrates how to combine several `aicommit2` command-line options in a single invocation. It configures the locale, stages all changes, sets the commit type, generates multiple messages, copies to clipboard, and excludes specific file types from AI analysis.

```sh
aicommit2 --locale "jp" --all --type "conventional" --generate 3 --clipboard --exclude "*.json" --exclude "*.ts"
```

--------------------------------

### Configure Basic Mistral API Settings

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/mistral.md

This snippet demonstrates how to set the essential API key and model for Mistral using `aicommit2`'s configuration command. It's a quick way to get started with the Mistral integration.

```sh
aicommit2 config set MISTRAL.key="your-api-key"
aicommit2 config set MISTRAL.model="codestral-latest"
```

--------------------------------

### Configure Anthropic API Key and Model (Basic)

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/anthropic.md

Demonstrates the fundamental commands to set the Anthropic API key and a default model using `aicommit2 config set`. This is the minimum required setup to use Anthropic services.

```sh
aicommit2 config set ANTHROPIC.key="your-api-key"
aicommit2 config set ANTHROPIC.model="claude-3-5-haiku-20241022"
```

--------------------------------

### Automatic Installation of aicommit2 Git Hook

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

This command automatically installs the `aicommit2` Git hook within the current Git repository. It configures aicommit2 to run as part of the `prepare-commit-msg` hook, streamlining the commit message generation process.

```sh
aicommit2 hook install
```

--------------------------------

### Check Installed Version of aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Displays the current version of the aicommit2 tool installed on the system. This command is useful for verifying the installed software version before considering an upgrade to the latest release.

```sh
aicommit2 --version
```

--------------------------------

### Run Ollama with a Specific Model

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/ollama.md

This command starts the Ollama server and loads a specified large language model, such as `llama3.2`, `codellama`, or `deepseek-coder`. It's the initial step to make a model available for use.

```shell
ollama run llama3.2 # model you want use. ex) codellama, deepseek-coder
```

--------------------------------

### Configure aicommit2 Settings via INI Configuration File

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Illustrates the structure and syntax for configuring `aicommit2` using a `config.ini` file. It includes examples for general settings, model-specific parameters, and handling array-like values such as multiple models.

```ini
# General Settings
logging=true
generate=2
temperature=1.0

# Model-Specific Settings
[OPENAI]
key="<your-api-key>"
temperature=0.8
generate=1
model="gpt-4o,gpt-3.5-turbo"
systemPromptPath="<your-prompt-path>"

[GEMINI]
key="<your-api-key>"
generate=5
includeBody=true
model="gemini-pro,gemini-flash"

[OLLAMA]
temperature=0.7
model[]=llama3.2
model[]=codestral
```

--------------------------------

### Execute aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/ollama.md

This command runs aicommit2 after it has been configured. Ensure Ollama version 0.1.33+ and aicommit2 version 1.9.5+ are installed for multi-model support.

```shell
aicommit2
```

--------------------------------

### Upgrade aicommit2 Global Installation via npm

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Updates the globally installed aicommit2 package to its latest available version using the npm package manager. This ensures users benefit from the newest features, bug fixes, and performance improvements.

```sh
npm update -g aicommit2
```

--------------------------------

### Set Specific Groq Model for aicommit2 Configuration

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/groq.md

Provides an example of how to explicitly configure the `GROQ.model` setting to 'llama-3.3-70b-versatile' using the `aicommit2 config set` command, overriding the default model.

```sh
aicommit2 config set GROQ.model="llama-3.3-70b-versatile"
```

--------------------------------

### Get Current aicommit2 Configuration File Path

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Demonstrates how to use the `aicommit2 config path` command to display the location of the currently loaded configuration file, following the XDG Base Directory Specification.

```sh
aicommit2 config path
```

--------------------------------

### Set Specific Anthropic Model via Command Line

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/anthropic.md

Provides a command-line example for explicitly setting the Anthropic model to be used. This allows users to switch between different supported Claude models.

```sh
aicommit2 config set ANTHROPIC.model="claude-3-5-sonnet-20240620"
```

--------------------------------

### Launch Ollama Server with Model Limit

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/ollama.md

This command launches the Ollama server, setting the maximum number of models that can be loaded simultaneously using the OLLAMA_MAX_LOADED_MODELS environment variable. For example, setting it to 3 allows up to three models to be loaded.

```shell
OLLAMA_MAX_LOADED_MODELS=3 ollama serve
```

--------------------------------

### Mistral API Configuration Settings Reference

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/mistral.md

This section provides a reference for available configuration settings for the Mistral API. It lists parameters like API key and model, along with their descriptions and default values, guiding users on how to customize their Mistral integration.

```APIDOC
Mistral Configuration:
  key:
    Type: string
    Description: The Mistral API key. Sign up and subscribe in Mistral Console (https://console.mistral.ai/).
    Default: -
  model:
    Type: string
    Description: The model to use for Mistral API calls.
    Default: pixtral-12b-2409
    Supported Values:
      - codestral-latest
      - mistral-large-latest
      - pixtral-large-latest
      - ministral-8b-latest
      - mistral-small-latest
      - mistral-embed
      - mistral-moderation-latest
```

--------------------------------

### Add aicommit2 to VSCode Devcontainer Features

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

This snippet demonstrates how to integrate aicommit2 into a VSCode Devcontainer setup. By adding the specified feature to your `devcontainer.json` file, aicommit2 will be automatically available within your development container environment.

```json
{
    "features": {
        "ghcr.io/kvokka/features/aicommit2:1": {}
    }
}
```

--------------------------------

### aicommit2 CLI Usage with Git Commit Flags

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Illustrates how aicommit2 can forward unknown flags directly to the underlying `git commit` command. This specific example uses the `--all` (or `-a`) flag to automatically stage all changes in tracked files before generating the commit message.

```sh
aicommit2 --all # or -a
```

--------------------------------

### Required JSON Output Format for AI Commit Messages

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Specifies the mandatory JSON array format for AI-generated commit messages, which is always appended to custom prompts. It defines the 'subject', 'body', and 'footer' keys and provides an example to ensure consistent parsing and data structure.

```text
Lastly, Provide your response as a JSON array containing exactly {generate} object, each with the following keys:
- "subject": The main commit message using the {type} style. It should be a concise summary of the changes.
- "body": An optional detailed explanation of the changes. If not needed, use an empty string.
- "footer": An optional footer for metadata like BREAKING CHANGES. If not needed, use an empty string.
The array must always contain {generate} element, no more and no less.
Example response format:
[
  {
    "subject": "fix: fix bug in user authentication process",
    "body": "- Update login function to handle edge cases\n- Add additional error logging for debugging",
    "footer": ""
  }
]
Ensure you generate exactly {generate} commit message, even if it requires creating slightly varied versions for similar changes.
The response should be valid JSON that can be parsed without errors.
```

```json
[
  {
    "subject": "fix: fix bug in user authentication process",
    "body": "- Update login function to handle edge cases\n- Add additional error logging for debugging",
    "footer": ""
  }
]
```

--------------------------------

### Set up AICommit2 Nix Development Environment

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Explains how to enter a development shell with all necessary dependencies for AICommit2 using Nix, facilitating contributions or deeper exploration of the project's source code and functionality.

```sh
nix develop github:tak-bro/aicommit2
```

--------------------------------

### Configure Groq Basic API Key and Model for aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/groq.md

Demonstrates how to set the fundamental Groq API key and preferred model using simple `aicommit2 config set` commands, essential for initial integration.

```sh
aicommit2 config set GROQ.key="your-api-key"
aicommit2 config set GROQ.model="gemma2-9b-it"
```

--------------------------------

### Groq API Configuration Settings Reference for aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/groq.md

Comprehensive documentation of Groq API configuration settings available in aicommit2, detailing parameters like `key` and `model`, their descriptions, default values, and a complete list of supported models.

```APIDOC
Settings Table:
| Setting | Description | Default |
| ------- | ----------- | ------- |
| `key`   | API key     | -       |
| `model` | Model to use| `llama-3.3-70b-versatile` |

Detailed Configuration:
GROQ.key:
  Description: The Groq API key. If you don't have one, please sign up and get the API key in Groq Console.
  Link: https://console.groq.com

GROQ.model:
  Default: `llama-3.3-70b-versatile`
  Supported Models:
    - `allam-2-7b`
    - `compound-beta`
    - `compound-beta-mini`
    - `deepseek-r1-distill-llama-70b`
    - `distil-whisper-large-v3-en`
    - `gemma2-9b-it`
    - `llama-3.1-8b-instant`
    - `llama-3.3-70b-versatile`
    - `llama-guard-3-8b`
    - `llama3-70b-8192`
    - `llama3-8b-8192`
    - `meta-llama/llama-4-maverick-17b-128e-instruct`
    - `meta-llama/llama-4-scout-17b-16e-instruct`
    - `mistral-saba-24b`
    - `playai-tts`
    - `playai-tts-arabic`
    - `qwen-qwq-32b`
    - `whisper-large-v3`
    - `whisper-large-v3-turbo`
```

--------------------------------

### Configure AICommit2 API Keys

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Explains how to set up API keys for various AI providers using the 'aicommit2 config set' command, which is essential for the tool's operation. At least one key must be configured for AI services to function.

```sh
aicommit2 config set OPENAI.key=<your key>
aicommit2 config set ANTHROPIC.key=<your key>
# ... (similar commands for other providers)
```

--------------------------------

### aicommit2 General Settings Compatibility by AI Model

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

This table outlines which general configuration settings are supported by various AI models within aicommit2. It helps users understand the available options for each specific AI provider.

```APIDOC
Available General Settings by Model:
  - OpenAI: timeout, temperature, maxTokens, topP
  - Anthropic Claude: timeout, temperature, maxTokens, topP
  - Gemini: temperature, maxTokens, topP
  - Mistral AI: timeout, temperature, maxTokens, topP
  - Codestral: timeout, temperature, maxTokens, topP
  - Cohere: timeout, temperature, maxTokens, topP
  - Groq: timeout, temperature, maxTokens, topP
  - Perplexity: timeout, temperature, maxTokens, topP
  - DeepSeek: timeout, temperature, maxTokens, topP
  - Ollama: timeout, temperature, topP
  - OpenAI API-Compatible: timeout, temperature, maxTokens, topP

All AI support the following options in General Settings:
  - systemPrompt
  - systemPromptPath
  - codeReview
  - codeReviewPromptPath
  - exclude
  - type
  - locale
  - generate
  - logging
  - includeBody
  - maxLength
```

--------------------------------

### Configure aicommit2 for Ollama Host, Model, and Context

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/ollama.md

These commands configure `aicommit2` to connect to the Ollama server, specify the model to use, and set the context window size (`numCtx`). A higher `numCtx` value like `4096` is recommended for better performance.

```sh
aicommit2 config set OLLAMA.host=<your host>
aicommit2 config set OLLAMA.model=<your model>
aicommit2 config set OLLAMA.numCtx=4096
```

--------------------------------

### aicommit2 OpenAI Provider Configuration Settings

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/openai.md

Detailed documentation for configuring the OpenAI provider within aicommit2, including descriptions, default values, and usage notes for each setting.

```APIDOC
Settings:
  key:
    Description: API key
    Default: -
  model:
    Description: Model to use
    Default: gpt-4o-mini
  url:
    Description: API endpoint URL
    Default: https://api.openai.com
  path:
    Description: API path
    Default: /v1/chat/completions
  proxy:
    Description: Proxy settings
    Default: -
Detailed Configuration:
  OPENAI.key:
    Description: The OpenAI API key. You can retrieve it from OpenAI API Keys page.
  OPENAI.model:
    Default: gpt-4o-mini
    Description: The Chat Completions (/v1/chat/completions) model to use. Consult the list of models available in the OpenAI Documentation.
  OPENAI.url:
    Default: https://api.openai.com
    Description: The OpenAI URL. Both https and http protocols supported. It allows to run local OpenAI-compatible server.
  OPENAI.path:
    Default: /v1/chat/completions
    Description: The OpenAI Path.
  OPENAI.topP:
    Default: 0.9
    Description: The `top_p` parameter selects tokens whose combined probability meets a threshold. Please see detail.
    Note: If `topP` is less than 0, it does not deliver the `top_p` parameter to the request.
```

--------------------------------

### Configure Together AI with aicommit2 CLI

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/compatible.md

This snippet demonstrates how to configure Together AI as an OpenAI API-compatible service using the `aicommit2` command-line interface. It shows the necessary commands to enable compatibility mode, set the API URL, path, model, and API key.

```sh
aicommit2 config set TOGETHER.compatible=true
aicommit2 config set TOGETHER.url=https://api.together.xyz
aicommit2 config set TOGETHER.path=/v1
aicommit2 config set TOGETHER.model=meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
aicommit2 config set TOGETHER.key="your-api-key"
```

--------------------------------

### Configure aicommit2 AI Model Parameters

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

This command demonstrates how to set various configuration options for aicommit2, including the number of generations, topP, maxTokens, and temperature. It also shows how to configure API keys and specific model settings for different AI providers like OpenAI, Anthropic, Mistral, and Ollama.

```sh
aicommit2 config set \
  generate=2 \
  topP=0.8 \
  maxTokens=1024 \
  temperature=0.7 \
  OPENAI.key="sk-..." OPENAI.model="gpt-4o" OPENAI.temperature=0.5 \
  ANTHROPIC.key="sk-..." ANTHROPIC.model="claude-3-haiku" ANTHROPIC.maxTokens=2000 \
  MISTRAL.key="your-key" MISTRAL.model="codestral-latest"  \
  OLLAMA.model="llama3.2" OLLAMA.numCtx=4096 OLLAMA.watchMode=true
```

--------------------------------

### aicommit2 Application Logging Configuration (Winston)

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Details the configuration options for aicommit2's general application logging system, powered by Winston. It explains `logLevel`, `logFilePath`, and `exceptionLogFilePath` settings, including their descriptions, default values, and supported levels for controlling log verbosity and file locations.

```APIDOC
Application Logging (Winston) Configuration:
  logLevel:
    Description: Specifies the minimum level for logs to be recorded. Messages with a level equal to or higher than the configured logLevel will be captured.
    Default: info
    Supported Levels: error, warn, info, http, verbose, debug, silly
  logFilePath:
    Description: Defines the path to the main application log file. This setting supports date patterns (e.g., %DATE%) to automatically rotate log files daily.
    Default: logs/aicommit2-%DATE%.log (relative to the application's state directory, typically ~/.local/state/aicommit2/logs on Linux or ~/Library/Application Support/aicommit2/logs on macOS).
  exceptionLogFilePath:
    Description: Specifies the path to a dedicated log file for recording exceptions. Similar to logFilePath, it supports date patterns for daily rotation.
    Default: logs/exceptions-%DATE%.log (relative to the application's state directory, typically ~/.local/state/aicommit2/logs on Linux or ~/Library/Application Support/aicommit2/logs on macOS).
```

--------------------------------

### Configure Custom System Prompt Text

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Shows how to set a custom system prompt directly via the configuration, which takes precedence over a system prompt file path. This allows users to define the AI's initial instructions.

```shell
aicommit2 config set systemPrompt="Generate git commit message."
```

--------------------------------

### Gemini Configuration Settings API Reference

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/gemini.md

Detailed reference for available configuration settings for Gemini API integration with `aicommit2`, including descriptions, default values, supported models, and unsupported options.

```APIDOC
Settings:
  key:
    Description: API key
    Default: -
  model:
    Description: Model to use
    Default: gemini-2.0-flash
    Supported Models:
      - gemini-2.5-flash-preview-04-17
      - gemini-2.5-flash-preview-05-20
      - gemini-2.5-pro-preview-05-06
      - gemini-2.0-flash
      - gemini-2.0-flash-lite
      - gemini-2.0-flash-preview-image-generation
      - gemini-1.5-pro
      - gemini-1.5-flash
      - gemini-1.5-flash-8b
Unsupported Options:
  - timeout
```

--------------------------------

### Configure General Settings for AI Models

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Demonstrates how to apply general settings to specific AI models using the `aicommit2 config set` command, allowing per-model customization of parameters like locale, commit type, and body inclusion.

```shell
aicommit2 config set OPENAI.locale="jp"
aicommit2 config set CODESTRAL.type="gitmoji"
aicommit2 config set GEMINI.includeBody=true
```

--------------------------------

### Configure OpenAI Basic Settings with aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/openai.md

Sets the essential OpenAI API key and model for aicommit2 using the `config set` command.

```sh
aicommit2 config set OPENAI.key="your-api-key"
aicommit2 config set OPENAI.model="gpt-4o"
```

--------------------------------

### Configure Basic Gemini API Settings with aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/gemini.md

Sets the essential Gemini API key and model using `aicommit2` for basic integration.

```sh
aicommit2 config set GEMINI.key="your-api-key"
aicommit2 config set GEMINI.model="gemini-2.0-flash"
```

--------------------------------

### aicommit2 CLI Options Reference

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

A comprehensive reference for all available command-line options for the `aicommit2` CLI tool. Each option controls a specific aspect of the AI commit message generation process, including locale, staging behavior, message format, and output handling.

```APIDOC
CLI Options:
- --locale (-l): Locale to use for the generated commit messages (default: en)
- --all (-a): Automatically stage changes in tracked files for the commit (default: false)
- --type (-t): Git commit message format (conventional, gitmoji) (default: conventional)
- --confirm (-y): Skip confirmation when committing after message generation (default: false)
- --clipboard (-c): Copy the selected message to the clipboard (disables commit) (default: false)
- --generate (-g): Number of messages to generate (default: 1)
- --exclude (-x): Files to exclude from AI analysis
- --hook-mode: Run as a Git hook, typically used with prepare-commit-msg hook (default: false)
- --pre-commit: Run in pre-commit framework mode (default: false)
```

--------------------------------

### Anthropic API Configuration Reference

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/anthropic.md

Comprehensive documentation of the available configuration settings for the Anthropic API within aicommit2. It details the `key` and `model` parameters, including their descriptions, default values, and a list of all supported Anthropic Claude models.

```APIDOC
ANTHROPIC.key:
  Description: The Anthropic API key. To get started with Anthropic Claude, request access to their API at anthropic.com/earlyaccess.
  Default: -
ANTHROPIC.model:
  Description: The specific Anthropic model to use for AI operations.
  Default: claude-3-5-haiku-20241022
  Supported Models:
    - claude-opus-4-20250514
    - claude-sonnet-4-20250514
    - claude-3-7-sonnet-20250219
    - claude-3-5-sonnet-20241022
    - claude-3-5-haiku-20241022
    - claude-3-opus-20240229
    - claude-3-sonnet-20240229
    - claude-3-haiku-20240307
```

--------------------------------

### Configure AI Service API Keys with Environment Variables

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Illustrates how to set API keys for various AI services (OpenAI, Anthropic, Google, Mistral AI, Cohere, Groq, Perplexity, Deepseek) using environment variables. This method is useful for CI/CD or avoiding storing keys in config files.

```bash
# OpenAI
OPENAI_API_KEY="your-openai-key"
# Anthropic
ANTHROPIC_API_KEY="your-anthropic-key"
# Google
GEMINI_API_KEY="your-gemini-key"
# Mistral AI
MISTRAL_API_KEY="your-mistral-key"
CODESTRAL_API_KEY="your-codestral-key"
# Other Providers
COHERE_API_KEY="your-cohere-key"
GROQ_API_KEY="your-groq-key"
PERPLEXITY_API_KEY="your-perplexity-key"
DEEPSEEK_API_KEY="your-deepseek-key"
```

--------------------------------

### Ollama Configuration Settings Reference

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/ollama.md

This table provides a comprehensive reference for various Ollama configuration settings available in `aicommit2`. It details each setting's purpose, default value, and impact on model behavior, such as context length and output limits.

```APIDOC
Setting: model
  Description: Model(s) to use (comma-separated list)
  Default: -

Setting: host
  Description: Ollama host URL
  Default: http://localhost:11434

Setting: auth
  Description: Authentication type
  Default: Bearer

Setting: key
  Description: Authentication key
  Default: -

Setting: numCtx
  Description: The maximum number of tokens the model can process at once
  Default: 2048

Setting: maxTokens
  Description: The maximum number of output tokens (maps to num_predict)
  Default: -1 (infinite generation)
```

--------------------------------

### Cohere API Configuration Settings Reference

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/cohere.md

Details the available configuration settings for integrating Cohere with aicommit2, including the API key, model selection, and a list of supported models.

```APIDOC
Cohere Configuration Settings:
  COHERE.key:
    Description: The Cohere API key. If you don't have one, please sign up and get the API key in Cohere Dashboard (https://dashboard.cohere.com/).
    Default: -
  COHERE.model:
    Description: The model to use for Cohere API calls.
    Default: command
    Supported Models:
      - command-r7b-12-2024
      - command-r-plus-08-2024
      - command-r-plus-04-2024
      - command-r-plus
      - command-r-08-2024
      - command-r-03-2024
      - command-r
      - command
      - command-nightly
      - command-light
      - command-light-nightly
      - c4ai-aya-expanse-8b
      - c4ai-aya-expanse-32b
```

--------------------------------

### Advanced aicommit2 Ollama Configuration

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/ollama.md

This command demonstrates how to set multiple advanced Ollama parameters simultaneously, including the model, context window, temperature, locale, generation count, top-p sampling, and maximum output tokens. These settings allow fine-tuning of the model's behavior.

```sh
aicommit2 config set OLLAMA.model="codellama" \
    OLLAMA.numCtx=4096 \
    OLLAMA.temperature=0.7 \
    OLLAMA.locale="en" \
    OLLAMA.generate=3 \
    OLLAMA.topP=0.9 \
    OLLAMA.maxTokens=4000
```

--------------------------------

### Configure Groq Advanced API Parameters for aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/groq.md

Illustrates setting multiple Groq API parameters, including key, model, temperature, max tokens, locale, generation count, and top-P, to fine-tune AI behavior within aicommit2.

```sh
aicommit2 config set GROQ.key="your-api-key" \
    GROQ.model="gemma2-9b-it" \
    GROQ.temperature=0.7 \
    GROQ.maxTokens=4000 \
    GROQ.locale="en" \
    GROQ.generate=3 \
    GROQ.topP=0.9
```

--------------------------------

### Configure Perplexity AI Advanced Settings with aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/perplexity.md

This snippet shows how to configure advanced parameters for Perplexity AI, including API key, model, temperature, max tokens, locale, generate count, and topP, using a single `aicommit2 config set` command.

```sh
aicommit2 config set PERPLEXITY.key="your-api-key" \
    PERPLEXITY.model="sonar-pro" \
    PERPLEXITY.temperature=0.7 \
    PERPLEXITY.maxTokens=4000 \
    PERPLEXITY.locale="en" \
    PERPLEXITY.generate=3 \
    PERPLEXITY.topP=0.9
```

--------------------------------

### Integrate aicommit2 with pre-commit Framework

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

This YAML configuration snippet shows how to integrate aicommit2 into your `.pre-commit-config.yaml` file. It defines a local hook that runs `aicommit2` in `--pre-commit` mode, ensuring compatibility and proper execution within the pre-commit framework.

```yaml
repos:
    - repo: local
      hooks:
          - id: aicommit2
            name: AI Commit Message Generator
            entry: aicommit2 --pre-commit
            language: node
            stages: [prepare-commit-msg]
            always_run: true
```

--------------------------------

### Perplexity AI Configuration Settings Reference

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/perplexity.md

This section provides a reference for available configuration settings for Perplexity AI within aicommit2, including descriptions, default values, and supported models.

```APIDOC
Settings:
  key: API key (Default: -)
  model: Model to use (Default: sonar)

PERPLEXITY.key:
  Description: The Perplexity API key. Sign up at Perplexity to obtain one.

PERPLEXITY.model:
  Default: sonar
  Supported Models:
    - sonar-pro
    - sonar
    - llama-3.1-sonar-small-128k-online
    - llama-3.1-sonar-large-128k-online
    - llama-3.1-sonar-huge-128k-online
  Note: Models are subject to change.
```

--------------------------------

### Integrate AICommit2 into Nix Flake Project

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Shows how to add AICommit2 as an input to a Nix flake and include it in system or home packages, enabling its use within a Nix-managed project environment and ensuring reproducible builds.

```nix
{
  # flake.nix configuration file
  inputs = {
    nixpkgs.url = "github:NixOS/nixpkgs/nixos-unstable";
    aicommit2.url = "github:tak-bro/aicommit2";
  };
  # Rest of your flake.nix file
}

  # Somewhere where you define your packages
  {pkgs, inputs, ...}:{

  environment.systemPackages = [inputs.aicommit2.packages.x86_64-linux.default];
  # Or home packages
  home.packages = [inputs.aicommit2.packages.x86_64-linux.default];
  }
```

--------------------------------

### Configure Deepseek API Key and Model (Basic)

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/deepseek.md

This snippet demonstrates the basic configuration for Deepseek, setting the API key and the default chat model using `aicommit2`.

```sh
aicommit2 config set DEEPSEEK.key="your-api-key"
aicommit2 config set DEEPSEEK.model="deepseek-chat"
```

--------------------------------

### Specify Custom System Prompt File Path

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Demonstrates how to configure a path to a custom system prompt template file. Paths can be absolute or relative to the configuration file, enabling external management of prompt content.

```shell
aicommit2 config set systemPromptPath="/path/to/user/prompt.txt"
```

--------------------------------

### Configure Custom Prompt Templates for aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

This command demonstrates how to set a custom prompt template file path for aicommit2 using the `systemPromptPath` option. It shows both a global setting and an override for a specific AI service (OpenAI), allowing tailored prompt structures for commit message generation.

```sh
aicommit2 config set systemPromptPath="/path/to/user/prompt.txt"
aicommit2 config set OPENAI.systemPromptPath="/path/to/another-prompt.txt"
```

--------------------------------

### Configure OpenAI Advanced Settings with aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/openai.md

Sets multiple advanced OpenAI parameters including API key, model, temperature, max tokens, locale, generate count, and topP for fine-grained control.

```sh
aicommit2 config set OPENAI.key="your-api-key" \
    OPENAI.model="gpt-4o" \
    OPENAI.temperature=0.7 \
    OPENAI.maxTokens=4000 \
    OPENAI.locale="en" \
    OPENAI.generate=3 \
    OPENAI.topP=0.9
```

--------------------------------

### Instruct ChatGPT to act as Git CLI

Source: https://github.com/tak-bro/aicommit2/blob/main/tests/fixtures/README.md

This prompt configures ChatGPT to simulate a git command-line interface, allowing it to generate random git diffs based on subsequent user input specifying the type of change.

```Natural Language
I want you to act as a git cli
I will give you the type of content and you will generate a random git diff based on that
```

--------------------------------

### Configure Basic Cohere API Settings for aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/cohere.md

Sets the essential API key and default model for Cohere integration with aicommit2. This is the minimum configuration required to use Cohere.

```sh
aicommit2 config set COHERE.key="your-api-key"
aicommit2 config set COHERE.model="command"
```

--------------------------------

### Configure Deepseek with Advanced Settings

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/deepseek.md

This snippet shows how to configure Deepseek with additional parameters like temperature, max tokens, locale, generate count, and topP, providing more control over the model's behavior.

```sh
aicommit2 config set DEEPSEEK.key="your-api-key" \
    DEEPSEEK.model="deepseek-chat" \
    DEEPSEEK.temperature=0.7 \
    DEEPSEEK.maxTokens=4000 \
    DEEPSEEK.locale="en" \
    DEEPSEEK.generate=3 \
    DEEPSEEK.topP=0.9
```

--------------------------------

### Configure aicommit2 Settings via Command-Line Arguments

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Shows how to override or set `aicommit2` configuration parameters directly through command-line arguments, including specifying multiple models using a comma-separated format. Command-line arguments have the highest precedence.

```sh
aicommit2 --OPENAI.locale="jp" --GEMINI.temperature="0.5" --OPENAI.model="gpt-4o,gpt-3.5-turbo"
```

--------------------------------

### Make Manual Git Hook Executable for aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

After manually creating or editing the `prepare-commit-msg` Git hook file, this command is necessary to make it executable. This ensures the Git hook system can properly invoke the aicommit2 script.

```sh
chmod +x .git/hooks/prepare-commit-msg
```

--------------------------------

### Configure Advanced Gemini API Settings with aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/gemini.md

Sets comprehensive Gemini API parameters including key, model, temperature, max tokens, locale, generate count, and topP for fine-tuned control.

```sh
aicommit2 config set GEMINI.key="your-api-key" \
    GEMINI.model="gemini-2.0-flash" \
    GEMINI.temperature=0.7 \
    GEMINI.maxTokens=4000 \
    GEMINI.locale="en" \
    GEMINI.generate=3 \
    GEMINI.topP=0.9
```

--------------------------------

### Use AICommit2 in a Git Repository

Source: https://github.com/tak-bro/aicommit2/blob/main/README.md

Demonstrates the basic workflow for using AICommit2 within a Git repository, involving staging files and then running the 'aicommit2' command to generate commit messages based on the staged changes.

```sh
git add <files...>
aicommit2
```

--------------------------------

### Set Perplexity AI Model with aicommit2

Source: https://github.com/tak-bro/aicommit2/blob/main/docs/providers/perplexity.md

This snippet demonstrates how to specifically set the Perplexity AI model using the `aicommit2 config set` command.

```sh
aicommit2 config set PERPLEXITY.model="sonar-pro"
```