🥮 mooncakes.io
    Sign in

    genmit

    Generate AI-assisted commit messages from staged Git changes

    git
    commit-message
    llm
    ai
    cli
    Download zip
    Author
    Version
    0.2.0
    License
    Apache-2.0
    Repository
    Last updated
    4 hours ago
    Downloads
    5

    Dependencies

    #genmit

    genmit generates a commit message from the changes already staged in Git. It never stages files and never creates the commit: the CLI prints a message for you to review, while the VS Code extension places it in the Source Control input.

    The default provider is Codex CLI, so an existing ChatGPT/Codex login is enough to get started. OpenAI Responses, OpenAI-compatible Chat Completions, Anthropic Messages, and custom command-line harnesses are also supported.

    #Quick start

    Install the CLI from Mooncakes with an up-to-date MoonBit toolchain:

    moon install klaseca/genmit

    Install Codex CLI, sign in once, then stage the changes you want described:

    codex login
git add <files>
genmit

    genmit prints the generated message. Review it and create the commit normally. Configure the model and reasoning effort through genmit's TOML configuration.

    #CLI

    Running genmit without a command is the same as genmit generate.

    genmit [options]
genmit generate [options] [--json]
genmit prompt [options]
genmit providers [options] [--json]

    Commands:

    • generate generates and prints a commit message.
    • prompt prints the direct prompt without contacting the provider.
    • providers lists the providers available in the active configuration and marks the selected one with *.

    providers only reads configuration and does not require a Git repository.

    Options:

    • -C, --cwd <directory> selects the Git repository and the base for a relative config path.
    • -c, --config <file> uses one TOML file instead of automatic user-config discovery.
    • -p, --provider <name> selects a configured provider without changing the config file.
    • --json returns machine-readable output from generate or providers.
    • -v, --verbose shows generation progress and timings on standard error.
    • -V, --version prints the version.
    • -h, --help prints help. Use genmit <command> --help for command-specific options.

    The --cwd, --config, and --provider options may appear before or after a command. For example, these are equivalent:

    genmit --provider openai generate
genmit generate --provider openai

    Only staged changes are used. Unstaged and untracked content is not collected by genmit.

    Use --verbose to follow progress or investigate slow or failed generation:

    genmit --verbose
genmit generate --json --verbose

    Logs go to stderr, leaving stdout ready for redirection or JSON parsing. They include stages and timings without recording staged content or credentials.

    genmit generate --json returns a stable result for scripts and editor integrations:

    {
  "protocol_version": 1,
  "message": "feat: improve the CLI",
  "provider": "codex",
  "files": ["src/cli.mbt"]
}

    #Configuration

    Without --config, genmit starts with built-in defaults and then looks for one user config:

    1. $GENMIT_HOME/config.toml, when GENMIT_HOME is set;
    2. otherwise <home>/.config/genmit/config.toml.

    On Windows, USERPROFILE is used as the home directory, with HOME as a fallback. If no file exists, the built-in configuration is ready to use with Codex CLI.

    Passing --config <file> disables discovery and applies that file over the built-in defaults. Configuration files are not combined with each other. Relative paths are resolved from --cwd, or from the current directory when --cwd is omitted.

    A small user config can contain only the settings being changed:

    provider = "codex"
language = "en"
style = "conventional"
include_body = true
max_subject_length = 72

[generation]
max_provider_calls = 32
timeout_ms = 600000

[prompt]
extra = ""

    The main generation settings are:

    • language: the language requested for the message;
    • style: conventional, plain, or gitmoji;
    • include_body: whether a body is allowed after the subject;
    • max_subject_length: subject limit from 20 to 200 characters;
    • prompt.extra: additional instructions;
    • providers.<name>.max_input_chars: maximum prepared input size per request in characters, including instructions and context;
    • generation.max_provider_calls and generation.timeout_ms: whole-generation safety limits.

    The built-in providers are:

    NameKindConnection
    codexcodexCodex CLI with the existing login
    openaiopenai-responsesOpenAI Responses API
    anthropicanthropic-messagesAnthropic Messages API

    The built-in codex and openai providers use gpt-6-luna; anthropic uses claude-sonnet-5. Their default reasoning effort is low. Their input budgets are 222,500 and 210,000 characters respectively. New providers use 32,000 characters unless max_input_chars is set explicitly. Changing a provider's model or kind preserves its input budget. A user config may override individual settings without repeating the whole built-in provider:

    [providers.codex]
max_input_chars = 64000

[providers.codex.config]
model = "gpt-6-luna"
reasoning_effort = "low"

    To use the built-in OpenAI provider, select it and expose the API key to the process:

    provider = "openai"

    $env:OPENAI_API_KEY = "..."
genmit

    New API providers require an explicit kind, endpoint, and model. Supported API kinds are openai-responses, openai-compatible, and anthropic-messages. Custom command-line integrations are defined as reusable harnesses, then referenced by name from a provider. See genmit.example.toml for both forms.

    API keys are read from the environment variable named by api_key_env; the key itself should not be written to TOML. reasoning_effort is optional and its valid values depend on the selected model.

    Each provider's max_input_chars sets genmit's input budget. The nested config table contains backend options: typed API fields or string values for parameters declared by a harness.

    #Large staged changes

    Large staged diffs may require several provider requests. By default, generation is limited to 32 requests and 10 minutes. If it exceeds those limits, genmit reports an error instead of silently omitting part of the diff.

    #VS Code extension

    The VS Code extension adds generation and provider selection to Source Control. The standalone CLI is not required.

    See the extension README for installation, usage, configuration, cancellation, and troubleshooting.

    #Security

    Review git diff --cached before generation. A staged diff can contain secrets and is sent to the selected provider. API keys belong in environment variables, not TOML.

    The built-in Codex integration uses a read-only sandbox and ignores Codex user configuration, rules, and project instructions. Custom command-line tools run with their own permissions and may access files beyond the staged changes.

    #Development

    Build and test the MoonBit module:

    moon check
moon test
moon build src --release
moon build src --target wasm

    Install the CLI from the current checkout:

    moon install ./src

    Build and test the extension:

    cd apps/vscode-extension
npm install
npm test
npm run package

    For an overview of the project structure, see docs/architecture.md.

    Action

    source

    CliOptions

    source
    type CliOptions derive(
    Debug    )

    Source Files

    Powered by MoonBit

    Site sourceReport issuePackagesBuild queueSkillsStatistics

    © 2026 mooncakes.io