tdd-llm 0.7.0

Deploy TDD workflow templates for Claude and Gemini AI assistants

tdd-llm

AI-Powered TDD Workflows for Claude and Gemini

Deploy structured Test-Driven Development workflows to your AI coding assistants. Guide Claude and Gemini through the RED-GREEN-REFACTOR cycle with consistent, reproducible prompts.

Features

• Deploy .claude/ and .gemini/ configuration directories
• Automatic conversion from Claude (.md) to Gemini (.toml) format
• Language-specific placeholders (Python, C#, TypeScript)
• Backend support for local files or Jira (via REST API)
• Migrate existing projects from files to Jira
• Global and project-level configuration (project overrides global)
• Configurable coverage thresholds per project
• Cross-platform (Linux, macOS, Windows)
• Update templates from GitHub without reinstalling the package

Installation

pip install tdd-llm

Quick Start

# Initialize project config (creates .tdd-llm.yaml)
tdd-llm init --lang python --backend files

# Deploy TDD templates to current project
tdd-llm deploy

# Deploy to user-level directories
tdd-llm deploy --target user --lang csharp --backend jira

# Preview changes without writing
tdd-llm deploy --lang typescript --dry-run

# List available languages and backends
tdd-llm list

# Show configuration (merged global + project)
tdd-llm config --show

# Update templates from GitHub (without reinstalling)
tdd-llm update

Configuration

tdd-llm supports two configuration levels:

• Global (user-level): Applies to all projects
• Project (local): Overrides global settings for a specific project

Global Configuration

Location:

• Linux/macOS: ~/.config/tdd-llm/config.yaml
• Windows: %APPDATA%\tdd-llm\config.yaml

default_target: "project"  # or "user"
default_language: "python"
default_backend: "files"   # or "jira"
platforms:
  - claude
  - gemini
coverage:
  line: 80      # Line coverage threshold (%)
  branch: 70    # Branch coverage threshold (%)

Project Configuration

Create a .tdd-llm.yaml file in your project root to override global settings:

# Initialize project config with custom settings
tdd-llm init --lang typescript --coverage-line 90

# Or modify existing project config
tdd-llm config --project --set-lang csharp

Project config file: .tdd-llm.yaml

default_language: "typescript"
coverage:
  line: 90      # Override only what you need

Configuration Commands

# Show effective configuration (merged global + project)
tdd-llm config --show

# Modify global config
tdd-llm config --set-coverage-line 80

# Modify project config
tdd-llm config --project --set-lang typescript

Coverage thresholds are applied to the generated TDD templates and enforced during the review phase.

Updating Templates

Templates can be updated from GitHub without reinstalling the package:

# Update to latest templates
tdd-llm update

# Force re-download all templates
tdd-llm update --force

# Update and deploy in one command
tdd-llm deploy --update

# Force re-download and overwrite existing files
tdd-llm deploy --update --force

# Deploy using package templates (ignore cached updates)
tdd-llm deploy --no-cache

Updated templates are cached in:

• Linux/macOS: ~/.config/tdd-llm/templates/
• Windows: %APPDATA%\tdd-llm\templates\

Supported Languages

Language	Placeholders
Python	pytest, coverage, architecture/integration/perf tests
C#	dotnet test, xUnit, architecture/integration/perf tests
TypeScript	Jest, Vitest, architecture/integration/perf tests

Backends

Files (default)

Uses local markdown files for epic/story management:

• docs/epics/*.md - Epic definitions with tasks
• docs/state.json - Progress tracking
• .tdd-state.local.json - Session state (gitignored)

Jira

Uses Jira REST API for epic/story management. Supports OAuth 2.0 (recommended) or API token authentication.

OAuth 2.0 Authentication (Recommended)

OAuth provides secure, token-based authentication with automatic refresh. Credentials are stored encrypted locally.

# Login with OAuth (interactive setup on first run)
tdd-llm jira login

# Check authentication status
tdd-llm jira status

# Logout (remove stored tokens and credentials)
tdd-llm jira logout

First-time setup:

1. Create an OAuth app at https://developer.atlassian.com/console/myapps/
2. Configure your app:
   • Callback URL: http://localhost:8089/callback
   • Permissions: Jira API > read:jira-work, write:jira-work, read:jira-user
3. Run tdd-llm jira login and enter your Client ID and Client Secret when prompted
4. Complete authorization in your browser

Credentials and tokens are encrypted and stored in:

• Linux/macOS: ~/.config/tdd-llm/
• Windows: %APPDATA%\tdd-llm\

API Token Authentication (Alternative)

For simpler setups or environments where OAuth isn't available:

# Set API token
export JIRA_API_TOKEN=your-api-token

Generate an API token at: https://id.atlassian.com/manage-profile/security/api-tokens

Configuration

# In config.yaml
default_backend: "jira"
jira:
  base_url: "https://company.atlassian.net"
  email: "[e-mail]"
  project_key: "PROJ"

  # Optional: custom field mappings
  fields:
    acceptance_criteria: "customfield_10001"

  # Optional: status mapping (adapt to your Jira language/workflow)
  status_map:
    "To Do": "not_started"
    "In Progress": "in_progress"
    "Done": "completed"
  # French example:
  # status_map:
  #   "À faire": "not_started"
  #   "En cours": "in_progress"
  #   "Terminé": "completed"

Environment variables (override config):

• JIRA_API_TOKEN - API token for basic auth
• JIRA_BASE_URL - Jira instance URL
• JIRA_EMAIL - User email
• JIRA_PROJECT_KEY - Default project key

Backend Commands

Commands for AI assistants to interact with Jira:

# Get current workflow state
tdd-llm backend status

# Get epic with all tasks
tdd-llm backend get-epic PROJ-100

# Get task details
tdd-llm backend get-task PROJ-1234

# Get next incomplete task
tdd-llm backend next-task PROJ-100

# Update task status
tdd-llm backend update-status PROJ-1234 Done

# Set TDD phase (adds label tdd:test, tdd:dev, etc.)
tdd-llm backend set-phase PROJ-1234 test

# Set current task
tdd-llm backend set-current PROJ-100 PROJ-1234

# Add comment to task
tdd-llm backend add-comment PROJ-1234 "Task completed"

Migration: Files to Jira

Migrate existing epics and tasks from files backend to Jira:

# Preview what will be created (dry run)
tdd-llm migrate --dry-run

# Run migration
tdd-llm migrate

# Custom output path for mapping file
tdd-llm migrate --output my-mapping.json

The migration:

1. Reads epics from docs/epics/*.md
2. Creates epics in Jira with format E1: Epic Name
3. Creates tasks linked to epics with format T1: Task Title
4. Marks completed tasks as "Done" in Jira
5. Generates docs/jira-mapping.json:

{
  "E1": "PROJ-100",
  "E1/T1": "PROJ-101",
  "E1/T2": "PROJ-102",
  "E2": "PROJ-200"
}

TDD Workflow Commands

After deployment, use these commands with Claude or Gemini:

Flow Commands

Command	Phase	Description
/tdd:flow:1-analyze	Plan	Analyze task, write specs
/tdd:flow:2-test	RED	Write failing tests
/tdd:flow:3-dev	GREEN+REFACTOR	Implement, then refactor
/tdd:flow:4-docs	Document	Update docs, CHANGELOG
/tdd:flow:5-review	Review	Code review, create PR
/tdd:flow:6-done	Done	Commit, update state
/tdd:flow:status	-	Show current progress

Init Commands

Command	Description
/tdd:init:1-project	Initialize project structure
/tdd:init:2-architecture	Define architecture
/tdd:init:3-standards	Define code standards
/tdd:init:4-readme	Generate README

Development

# Clone and install in dev mode
git clone https://github.com/mxdumas/tdd-llm-workflow
cd tdd-llm-workflow
python -m venv .venv
source .venv/bin/activate  # Linux/macOS
# .venv\Scripts\activate   # Windows
pip install -e ".[dev]"
pre-commit install

# Run tests
pytest

# Run linter
ruff check src/

# Format code
ruff format src/

License

MIT