✨ Features

• ✅ Docker-based action with pre-installed Node.js 22, npm, go, cargo, and uv
• ✅ Configurable authentication with iFlow API
• ✅ Support for MCP servers
• ✅ Agent Client Protocol: use Rust ACP Websocket client to communicate with iFlow CLI
• ✅ Support for custom models and API endpoints
• ✅ Flexible command execution with timeout control
• ✅ Works in any working directory
• ✅ Built with Rust for fast, reliable execution
• ✅ GitHub Actions Summary integration: Rich execution reports in PR summaries
• ✅ PR/Issue Integration: Works seamlessly with GitHub comments and PR reviews

📦 Installation & Setup

Basic Usage

Add to your GitHub workflow:

- name: Run iFlow CLI
  uses: iflow-ai/iflow-cli-action@v2.0.0
  with:
    prompt: "Analyze this codebase"
    api_key: ${{ secrets.IFLOW_API_KEY }}

Authentication

1. Register for an iFlow account at iflow.cn
2. Go to your profile settings or get your API key
3. Click "Reset" in the pop-up dialog to generate a new API key
4. Add the API key to your GitHub repository secrets as IFLOW_API_KEY

💡 Usage Example

Issue Triage with iFLOW CLI

name: '🏷️ iFLOW CLI Automated Issue Triage'

on:
  issues:
    types: ['opened', 'reopened']
  issue_comment:
    types: ['created']
  workflow_dispatch:
    inputs:
      issue_number:
        description: 'issue number to triage'
        required: true
        type: 'number'

concurrency:
  group: '${{ github.workflow }}-${{ github.event.issue.number }}'
  cancel-in-progress: true

defaults:
  run:
    shell: 'bash'

permissions:
  contents: 'read'
  issues: 'write'
  statuses: 'write'

jobs:
  triage-issue:
    if: |-
      github.event_name == 'issues' ||
      github.event_name == 'workflow_dispatch' ||
      (
        github.event_name == 'issue_comment' &&
        contains(github.event.comment.body, '@iflow-cli /triage') &&
        contains(fromJSON('["OWNER", "MEMBER", "COLLABORATOR"]'), github.event.comment.author_association)
      )
    runs-on: 'ubuntu-latest'
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4

      - name: 'Run iFlow CLI Issue Triage'
        uses: iflow-ai/iflow-cli-action@v2.0.0
        id: 'iflow_cli_issue_triage'
        env:
          GITHUB_TOKEN: '${{ secrets.GITHUB_TOKEN }}'
          ISSUE_TITLE: '${{ github.event.issue.title }}'
          ISSUE_BODY: '${{ github.event.issue.body }}'
          ISSUE_NUMBER: '${{ github.event.issue.number }}'
          REPOSITORY: '${{ github.repository }}'
        with:
          api_key: ${{ secrets.IFLOW_API_KEY }}
          timeout: "3600"
          debug: "true"
          prompt: |
            ## Role

            You are an issue triage assistant. Analyze the current GitHub issue
            and apply the most appropriate existing labels. Use the available
            tools to gather information; do not ask for information to be
            provided.

            ## Steps

            1. Run: `gh label list` to get all available labels.
            2. Review the issue title and body provided in the environment
               variables: "${ISSUE_TITLE}" and "${ISSUE_BODY}".
            3. Classify issues by their kind (bug, enhancement, documentation,
               cleanup, etc) and their priority (p0, p1, p2, p3). Set the
               labels according to the format `kind/*` and `priority/*` patterns.
            4. Apply the selected labels to this issue using:
               `gh issue edit "${ISSUE_NUMBER}" --add-label "label1,label2"`
            5. If the "status/needs-triage" label is present, remove it using:
               `gh issue edit "${ISSUE_NUMBER}" --remove-label "status/needs-triage"`

            ## Guidelines

            - Only use labels that already exist in the repository
            - Do not add comments or modify the issue content
            - Triage only the current issue
            - Assign all applicable labels based on the issue content
            - Reference all shell variables as "${VAR}" (with quotes and braces)

🔧 Inputs

📤 Outputs

⚡ Advanced Features

Pre-Execution Commands

- name: iFlow with Pre-Execution Commands
  uses: iflow-ai/iflow-cli-action@v2.0.0
  with:
    prompt: "Analyze this codebase after installing dependencies"
    api_key: ${{ secrets.IFLOW_API_KEY }}
    precmd: |
      npm install
      git fetch origin main

Custom Settings

- name: Custom iFlow Configuration
  uses: iflow-ai/iflow-cli-action@v2.0.0
  with:
    prompt: "Analyze this codebase with custom configuration"
    api_key: ${{ secrets.IFLOW_API_KEY }}  # Still required for basic validation
    settings_json: |
      {
        "theme": "Dark",
        "selectedAuthType": "iflow",
        "apiKey": "${{ secrets.IFLOW_API_KEY }}",
        "baseUrl": "https://custom-api.example.com/v1",
        "modelName": "custom-model",
        "searchApiKey": "${{ secrets.SEARCH_API_KEY }}",
        "customField": "customValue"
      }

🌐 MCP Servers

[MCP (Model Context Protocol)](https://modelcontextprotocol.io) allows iFlow CLI to connect to external tools and services, extending its capabilities beyond just AI model interactions.

Example: Using DeepWiki MCP Server

- name: iFlow CLI with MCP Server
  uses: iflow-ai/iflow-cli-action@v2.0.0
  with:
    prompt: "use @deepwiki to search how to use Skynet to build a game"
    api_key: ${{ secrets.IFLOW_API_KEY }}
    settings_json: |
      {
        "selectedAuthType": "iflow",
        "apiKey": "${{ secrets.IFLOW_API_KEY }}",
        "baseUrl": "https://apis.iflow.cn/v1",
        "modelName": "qwen3-coder-plus",
        "searchApiKey": "${{ secrets.IFLOW_API_KEY }}",
        "mcpServers": {
          "deepwiki": {
            "command": "npx",
            "args": ["-y", "mcp-deepwiki@latest"]
          }
        }
      }
    model: "qwen3-coder-plus"
    timeout: "1800"
    debug: "true"

When to Use MCP Servers

• Enhanced code search and documentation lookup capabilities
• Integration with external tools and services
• Access to specialized knowledge bases or databases
• Custom tooling that extends the iFlow CLI functionality

🎯 Common Use Cases

Code Analysis and Review

• Code Review on Pull Requests - Automatically reviews PRs when opened/reopened or when triggered by comment
• PR Review Killer - Implements changes to PRs based on comments

Documentation Generation

• Documentation Generation - Automatically generates technical documentation from codebase

Issue Management

• Issue Killer - Automatically implements features based on GitHub issues
• Issue Triage - Automatically labels new GitHub issues

🛠️ Troubleshooting

Common Issues

Command timeout: Increase the timeout value for complex operations

timeout: "900"  # 15 minutes

API authentication failed: Verify your API key is correctly set in repository secrets

Working directory not found: Ensure the path exists and checkout action is used

Debug Mode

Enable verbose logging by setting environment variables:

env:
  ACTIONS_STEP_DEBUG: true