code-review-ai-cli 1.1.0

Automated AI-powered code review CLI for Azure DevOps / TFS Pull Requests

AI Code Review CLI

Automated code review tool with Pull Request integration for Azure DevOps/TFS and support for multiple LLM providers. Documentation where docs/index.md for complete guides on CLI usage, LLM configuration, and architecture.

Features

• AI Pull Request Review — Automated code analysis with configurable LLM providers
• Structured Comments — Inline suggestions + general summary comments
• Dry-run Mode — Validate reviews before posting
• Multiple LLM Providers — OpenAI, Azure OpenAI, Gemini, Claude, Ollama, GitHub Copilot, AWS Bedrock
• Smart Filtering — Filter by file extensions, limit diff size
• Project-aware PR Context — Sends repository and linked work item context while restricting findings to modified PR lines
• Customizable Prompts — Markdown-based review guidelines
• Usage Tracking — Store per-PR token usage and optional cost estimates
• Interactive CLI — Menu-driven selection and confirmation

Installation & Quick Start

1. Install Package

From PyPI:

pip install code-review-ai-cli

With optional LLM SDK extras:

pip install "code-review-ai-cli[bedrock]"    # AWS Bedrock
pip install "code-review-ai-cli[openai]"     # OpenAI SDK
pip install "code-review-ai-cli[gemini]"     # Google Gemini SDK
pip install "code-review-ai-cli[claude]"     # Anthropic Claude SDK
pip install "code-review-ai-cli[all]"        # All optional SDKs

For development:

pip install -r requirements.txt
pip install "code-review-ai-cli[dev]"        # Test suite + linting

2. Initialize Configuration

Generate config templates in your project directory:

ai-review init

Creates:

• config.yaml — LLM and review settings
• review_prompt.md — Customizable review guidelines

3. Run Your First Review

# List active PRs
ai-review list-prs

# Review a specific PR
ai-review pr-review 42

# Dry-run (preview without posting)
ai-review pr-review 42 --dry-run

# Check stored token/cost usage
ai-review usage

Configuration File

After ai-review init, edit config.yaml:

llm:
  provider: bedrock                    # or: openai, gemini, claude, etc.
  model: anthropic.claude-3-5-sonnet-20240620-v1:0

bedrock:
  region: us-east-1

tfs:
  base_url: https://dev.azure.com/your-org
  project: YourProject
  pat: xxxxxxxxx

review:
  language: pt
  verbosity: detailed                  # or: quick, security
  scope: diff_with_context             # diff_with_context, diff_only, full_code
  file_extensions_filter: [".cs", ".ts", ".py"]
  max_diff_files: 50
  project_context:
    enabled: true
    mode: on_demand                      # on_demand, full
    manifest_max_chars: 60000
    retrieval_max_rounds: 2
    retrieval_max_files: 20
    retrieval_max_chars: 120000
    retrieval_file_max_chars: 30000
  work_item_context:
    enabled: true
    max_items: 20

By default, repository context is loaded on demand: the prompt includes the PR diff, full changed-file contents, linked work item documentation, and a repository manifest, then the model requests any extra files it needs. Set review.project_context.mode: full to send the full eligible repository snapshot instead. Bedrock uses a default estimated prompt budget of 180000 tokens; override it with llm.max_prompt_tokens if your model supports more or less.

Development & Testing

This is a standard Python project with the following structure:

src/
  ai_review.py        # CLI entry point
  config.py           # Configuration management
  llm_client.py       # LLM provider abstraction
  tfs_client.py       # Azure DevOps integration
  git_utils.py        # Git diff processing
  formatter.py        # Output formatting (terminal, markdown, JSON)

tests/
  test_*.py           # Unit and integration tests

Run Tests

python -m pytest --cov=src --cov-report=term

Code Quality

Project follows PEP8 with Black formatter and Ruff linter:

# Format code
black src/ tests/

# Lint
ruff check src/ tests/

# Type checking (if using mypy)
mypy src/

VS Code Integration

Predefined tasks for quick execution in VS Code:

Available Tasks

1. AI Review: Pull Request (Interactive)

• Interactive mode with main menu
• Run with: Ctrl+Shift+B → Select task

2. AI Review: PR (Dry-Run)

• Dry-run for a specific PR
• Prompts for PR ID

3. AI Review: List Active PRs

• Lists active PRs
• Quick diagnostics

4. AI Review: Interactive Mode

• Full tool menu
• Runs in background

How to run tasks

In VS Code:

1. Ctrl+Shift+P → "Tasks: Run Task"
2. Select the desired task
3. Fill in parameters if needed