next-ai-draw-io/.github/workflows/claude-code.yml

name: Claude Code

on:
  issue_comment:
    types: [created]
  pull_request_review_comment:
    types: [created]
  issues:
    types: [opened, assigned]
  pull_request_review:
    types: [submitted]
  pull_request_target:
    types: [opened, synchronize, reopened]

jobs:
  claude:
    if: |
      (github.event_name == 'issue_comment' && contains(github.event.comment.body, '@claude')) ||
      (github.event_name == 'pull_request_review_comment' && contains(github.event.comment.body, '@claude')) ||
      (github.event_name == 'pull_request_review' && contains(github.event.review.body, '@claude')) ||
      (github.event_name == 'issues' && contains(github.event.issue.body, '@claude'))
    runs-on: ubuntu-latest
    permissions:
      contents: write
      pull-requests: write
      issues: write
      id-token: write
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Configure AWS Credentials
        uses: aws-actions/configure-aws-credentials@v4
        with:
          role-to-assume: ${{ secrets.AWS_ROLE_TO_ASSUME }}
          aws-region: us-east-1

      - name: Run Claude Code
        uses: anthropics/claude-code-action@v1
        with:
          use_bedrock: "true"
          github_token: ${{ secrets.GITHUB_TOKEN }}

  pr-review:
    if: github.event_name == 'pull_request_target'
    runs-on: ubuntu-latest
    permissions:
      contents: read
      pull-requests: write
      id-token: write
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Configure AWS Credentials
        uses: aws-actions/configure-aws-credentials@v4
        with:
          role-to-assume: ${{ secrets.AWS_ROLE_TO_ASSUME }}
          aws-region: us-east-1

      - name: Run Claude Code PR Review
        uses: anthropics/claude-code-action@v1
        with:
          use_bedrock: "true"
          github_token: ${{ secrets.GITHUB_TOKEN }}
          allowed_non_write_users: "*"
          prompt: |
            REPO: ${{ github.repository }}
            PR NUMBER: ${{ github.event.pull_request.number }}

            This is a personal project - an AI-powered draw.io diagram generator built with:
            - Next.js 15 with React 19
            - Vercel AI SDK (streamText, useChat, tool calling)
            - Multiple AI providers: Bedrock, Anthropic, OpenAI, Google, Azure, OpenRouter, Ollama

            STEP 1: Check existing comments to avoid duplicates.
            Run: `gh api repos/${{ github.repository }}/pulls/${{ github.event.pull_request.number }}/comments`

            Build a list of files and line numbers that already have comments. For each existing comment:
            - If the issue is FIXED in current code, resolve the thread using:
              `gh api graphql -f query='mutation { resolveReviewThread(input: {threadId: "THREAD_ID"}) { thread { isResolved } } }'`
            - If the issue still exists, remember this file:line - DO NOT create a new comment for it

            STEP 2: Review the diff for issues, but SKIP any file:line that already has a comment.

            Review this PR for these issues (report ALL that apply):
            1. Bugs that would cause runtime errors or broken functionality
            2. Security issues (exposed secrets, API key leaks)
            3. AI SDK misuse - specifically check for:
               - Client-side: Should use useChat/useCompletion/useObject hooks, NOT raw fetch()
               - Server-side: Should use streamText/generateText/streamObject/generateObject
               - Message handling: Access message.parts array, not legacy content property
               - Tool definitions: Must use Zod schemas for inputSchema
               - Status handling: Check status (submitted/streaming/ready/error) before actions
               - Stream cleanup: Call stop() when aborting streams
            4. Unrelated changes that should be in separate PRs (scope creep)
            5. Suspicious .gitignore additions or accidentally committed files
            6. UI/UX inconsistencies (e.g., alignment issues)

            When reviewing AI SDK usage, fetch https://ai-sdk.dev/docs/ to verify correct patterns.
            Key doc pages: /docs/ai-sdk-ui/chatbot, /docs/ai-sdk-core/generating-text, /docs/ai-sdk-core/tools-and-tool-calling

            DO NOT comment on:
            - Minor performance optimizations
            - Code style preferences (unless clearly wrong)
            - Type annotations that don't affect functionality

            IMPORTANT:
            - NEVER create a comment on a file:line that already has a comment - this causes duplicates
            - For each NEW issue, use `mcp__github_inline_comment__create_inline_comment` to comment on the specific line
            - ALWAYS include a suggested fix using GitHub's suggestion syntax: ```suggestion\n<fixed code>\n```
            - Only say "LGTM" if there are truly ZERO new issues to report
          claude_args: |
            --allowedTools "mcp__github_inline_comment__create_inline_comment,Bash(gh pr diff:*),Bash(gh pr view:*),Bash(gh api:*),WebFetch(domain:ai-sdk.dev)"