Fix mv read loop hardcoding 4 instead of nnode #873
Workflow file for this run
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| name: Claude Code Review | |
| on: | |
| pull_request_target: | |
| types: [opened, synchronize, ready_for_review, reopened, labeled] | |
| issue_comment: | |
| types: [created] | |
| jobs: | |
| claude-review: | |
| if: > | |
| ( | |
| github.event_name == 'pull_request_target' && | |
| ( | |
| github.event.action == 'opened' || | |
| github.event.action == 'ready_for_review' || | |
| github.event.action == 'reopened' || | |
| github.event.action == 'synchronize' || | |
| ( | |
| github.event.action == 'labeled' && | |
| github.event.label.name == 'claude-full-review' | |
| ) | |
| ) | |
| ) || | |
| ( | |
| github.event_name == 'issue_comment' && | |
| github.event.issue.pull_request != null && | |
| contains(github.event.comment.body, '@claude full review') | |
| ) | |
| runs-on: ubuntu-latest | |
| permissions: | |
| contents: read | |
| pull-requests: write | |
| issues: write | |
| actions: read | |
| id-token: write | |
| steps: | |
| - name: Install unzip (required by bun setup) | |
| run: | | |
| sudo apt-get update | |
| sudo apt-get install -y unzip | |
| # Base checkout only | |
| - name: Checkout base repo (safe) | |
| uses: actions/checkout@v4 | |
| with: | |
| fetch-depth: 1 | |
| - name: Determine PR number and review mode | |
| id: mode | |
| shell: bash | |
| run: | | |
| if [[ "${{ github.event_name }}" == "pull_request_target" ]]; then | |
| PR_NUMBER="${{ github.event.pull_request.number }}" | |
| if [[ "${{ github.event.action }}" == "opened" || "${{ github.event.action }}" == "ready_for_review" || "${{ github.event.action }}" == "reopened" ]]; then | |
| REVIEW_MODE="full" | |
| elif [[ "${{ github.event.action }}" == "synchronize" ]]; then | |
| REVIEW_MODE="incremental" | |
| elif [[ "${{ github.event.action }}" == "labeled" && "${{ github.event.label.name }}" == "claude-full-review" ]]; then | |
| REVIEW_MODE="full" | |
| else | |
| REVIEW_MODE="full" | |
| fi | |
| elif [[ "${{ github.event_name }}" == "issue_comment" ]]; then | |
| PR_NUMBER="${{ github.event.issue.number }}" | |
| REVIEW_MODE="full" | |
| else | |
| REVIEW_MODE="full" | |
| fi | |
| echo "pr_number=$PR_NUMBER" >> "$GITHUB_OUTPUT" | |
| echo "review_mode=${REVIEW_MODE:-full}" >> "$GITHUB_OUTPUT" | |
| - name: Run Claude Code Review | |
| uses: anthropics/claude-code-action@v1 | |
| with: | |
| claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }} | |
| github_token: ${{ github.token }} | |
| plugin_marketplaces: "https://github.com/anthropics/claude-code.git" | |
| plugins: "code-review@claude-code-plugins" | |
| claude_args: > | |
| --dangerously-skip-permissions | |
| --max-turns 90 | |
| --allowedTools | |
| "Bash" | |
| prompt: | | |
| You are running in pull_request_target / issue_comment automation. | |
| REVIEW MODE: ${{ steps.mode.outputs.review_mode }} | |
| PR NUMBER: ${{ steps.mode.outputs.pr_number }} | |
| DO NOT read or inspect any checked-out PR/fork code. Review ONLY using GitHub API/gh commands. | |
| You may read local guidance ONLY from: | |
| - ./CLAUDE.md (root) if present | |
| - ./.claude/rules/*.md if present (max 10 files) | |
| Keep tool calls minimal and in this order: | |
| Phase 1 — Local guidance (base branch only, safe): | |
| 1) ls -1 .claude/rules 2>/dev/null || true | |
| 2) cat CLAUDE.md 2>/dev/null || true | |
| 3) find .claude/rules -maxdepth 1 -name "*.md" -print | head -n 10 | xargs -I{} cat "{}" 2>/dev/null || true | |
| Phase 2 — PR metadata and diff: | |
| 4) gh pr view ${{ steps.mode.outputs.pr_number }} --repo ${{ github.repository }} --json title,body,files,changedFiles,additions,deletions,headRefOid,comments | |
| 5) gh pr diff ${{ steps.mode.outputs.pr_number }} --repo ${{ github.repository }} | |
| Phase 3 — Full file context (read via GitHub API, NOT local checkout): | |
| After reviewing the diff, fetch full contents of changed files to understand | |
| surrounding context. This is critical for catching issues the diff alone hides | |
| (e.g., duplicate code, broken callers, missing cleanup, variable shadowing). | |
| Use this pattern to fetch file contents at the PR head SHA: | |
| gh api repos/${{ github.repository }}/contents/{path}?ref={head_sha} --jq '.content' | base64 -d | |
| Rules for Phase 3: | |
| - Get the head SHA from step 4's headRefOid field. | |
| - Fetch up to 15 changed files (skip files >500 lines or binary files). | |
| - Prioritize: source code (.fpp, .f90, .py, .yml) over docs/config. | |
| - For Fortran/Fypp files: also fetch files that the changed file imports | |
| (look for "use m_<name>" or "#:include" in the fetched content) if they | |
| seem relevant to the review. Limit to 5 additional related files. | |
| - Do NOT fetch files that are unchanged and unrelated to the diff. | |
| - If a file fetch fails (404, too large), skip it and continue. | |
| Review policy: | |
| - FULL mode: | |
| - Review the current PR normally. | |
| - Post or update ONE top-level PR comment titled "Claude Code Review". | |
| - INCREMENTAL mode: | |
| - Find the most recent prior Claude review comment on this PR. | |
| - Look for a hidden marker in the form: | |
| <!-- claude-review: reviewed_sha=<sha>; mode=<mode> --> | |
| - Compare the prior reviewed SHA to the current head SHA. | |
| - Review ONLY for newly introduced issues since the previous Claude-reviewed SHA. | |
| - DO NOT repeat earlier findings. | |
| - DO NOT restate the full PR summary. | |
| - If there are no new high-confidence findings, DO NOT post a new comment. STOP. | |
| - If there are new findings, update the existing Claude review comment if possible; otherwise post one new top-level comment. | |
| Re-review policy: | |
| - A full review is explicitly requested only when: | |
| - the workflow was triggered by PR label "claude-full-review", or | |
| - the workflow was triggered by an issue comment containing "@claude full review" | |
| Output format for FULL mode: | |
| Claude Code Review | |
| Head SHA: <sha> | |
| Files changed: | |
| - <count> | |
| - <up to 10 paths> | |
| Summary: | |
| - <3-6 minimal bullets> | |
| Findings: | |
| - <file + line numbers when possible> | |
| - <minimal, high-confidence only> | |
| Output format for INCREMENTAL mode: | |
| Claude Code Review | |
| Incremental review from: <previous_sha> | |
| Head SHA: <current_sha> | |
| New findings since last Claude review: | |
| - <only genuinely new issues, file + line numbers when possible> | |
| When posting a comment, include this hidden marker at the end: | |
| <!-- claude-review: reviewed_sha=<current_head_sha>; mode=${{ steps.mode.outputs.review_mode }} --> | |
| If posting is blocked, write the full review to the GitHub Actions job summary instead, then STOP. | |
| additional_permissions: | | |
| actions: read |