simulation-theory/.github/workflows/pr-agent.yml

name: PR Agent

on:
  pull_request_target:
    types: [opened, reopened]

permissions:
  pull-requests: write
  contents: read
  models: read

jobs:
  analyze-pr:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Collect changed files
        id: changed
        run: |
          # Ensure the base branch ref is available locally (important for fork-based PRs)
          git fetch origin "${{ github.event.pull_request.base.ref }}" --no-tags --prune --depth=1

          BASE="${{ github.event.pull_request.base.sha }}"
          HEAD="${{ github.event.pull_request.head.sha }}"

          # Compute the list of changed files between base and head; fail explicitly on error
          if ! ALL_FILES=$(git diff --name-only "$BASE" "$HEAD"); then
            echo "Error: failed to compute git diff between $BASE and $HEAD" >&2
            exit 1
          fi

          # Count total changed files robustly, even when there are zero files
          TOTAL=$(printf '%s\n' "$ALL_FILES" | sed '/^$/d' | wc -l | tr -d ' ')
          FILES=$(echo "$ALL_FILES" | head -50 | tr '\n' ', ')
          FILES="${FILES%, }"
          if [ "$TOTAL" -gt 50 ]; then
            REMAINING=$(( TOTAL - 50 ))
            FILES="${FILES} (and ${REMAINING} more files)"
          fi
          {
            echo 'files<<EOF'
            echo "$FILES"
            echo 'EOF'
          } >> "$GITHUB_OUTPUT"

      - name: Analyze PR and post comment
        uses: actions/github-script@v7
        env:
          CHANGED_FILES: ${{ steps.changed.outputs.files }}
        with:
          github-token: ${{ secrets.GITHUB_TOKEN }}
          script: |
            const prNumber    = context.payload.pull_request.number;
            const prTitle     = context.payload.pull_request.title;
            const prBody      = context.payload.pull_request.body || '(no description provided)';
            const prUser      = context.payload.pull_request.user.login;
            const baseBranch  = context.payload.pull_request.base.ref;
            const headBranch  = context.payload.pull_request.head.ref;
            const changedFiles = process.env.CHANGED_FILES || 'unknown';
            const additions   = context.payload.pull_request.additions ?? '?';
            const deletions   = context.payload.pull_request.deletions ?? '?';

            // Call GitHub Models API for AI-powered analysis
            let response;
            try {
              response = await fetch('https://models.inference.ai.azure.com/chat/completions', {
                method: 'POST',
                headers: {
                  'Content-Type': 'application/json',
                  'Authorization': `Bearer ${process.env.GITHUB_TOKEN}`
                },
                body: JSON.stringify({
                  model: 'gpt-4o-mini',
                  messages: [
                    {
                      role: 'system',
                      content: `You are a rigorous code and content review agent for the "simulation-theory" repository — a research project on simulation theory, mathematics, quantum mechanics, and philosophy. Your job is to carefully examine each pull request and provide a thorough, structured review.

For each PR produce:
1. **Summary** — a concise one-paragraph summary of the proposed changes.
2. **Changed Files Analysis** — observations about the files being modified and why they matter.
3. **Potential Concerns** — any risks, conflicts, or issues the reviewer should check.
4. **Relevance to Project Goals** — how these changes align with (or diverge from) simulation-theory research.
5. **Suggested Actions** — specific things the PR author or reviewers should do before merging.

Be rigorous, constructive, and precise. Keep the tone academic and professional.`
                  },
                  {
                    role: 'user',
                    content: `Please analyze this pull request:\n\n**Title:** ${prTitle}\n**Author:** ${prUser}\n**Base branch:** ${baseBranch} ← **Head branch:** ${headBranch}\n**Changes:** +${additions} / -${deletions} lines\n**Changed files:** ${changedFiles}\n\n**Description:**\n${prBody}`
                  }
                ],
                max_tokens: 1500,
                temperature: 0.4
              })
            });

            let analysisText;
            if (response.ok) {
              try {
                const data = await response.json();
                if (data.choices && data.choices.length > 0 && data.choices[0].message) {
            try {
              if (response.ok) {
                const data = await response.json();
                if (data.choices && data.choices.length > 0 && data.choices[0].message) {
                  analysisText = data.choices[0].message.content;
                } else {
                  console.log('Unexpected response structure from GitHub Models API:', JSON.stringify(data));
                }
              } else {
                console.log(`GitHub Models API returned ${response.status}: ${await response.text()}`);
              }
            } catch (error) {
              console.log('Error while calling or parsing response from GitHub Models API, falling back to templated analysis:', error);
            }

            // Fallback: structured analysis without AI
            if (!analysisText) {
              let changedFilesSection;
              if (!changedFiles || changedFiles === 'unknown') {
                changedFilesSection = 'No changed file list is available for this PR.';
              } else {
                const files = changedFiles.split(',').map(f => f.trim()).filter(f => f.length > 0);
                if (files.length === 0) {
                  changedFilesSection = 'No files listed.';
                } else {
                  changedFilesSection = files.map(f => `- ${f}`).join('\n');
                }
              }
              analysisText = `**Summary**\nPR #${prNumber} titled *"${prTitle}"* was submitted by @${prUser} merging \`${headBranch}\` into \`${baseBranch}\`.\n\n**Changed Files**\n${changedFilesSection}\n\n**Stats:** +${additions} additions / -${deletions} deletions\n\n**Suggested Actions**\n- Review all changed files for correctness and consistency.\n- Ensure the description clearly explains the motivation for each change.\n- Verify no unintended files are included in this PR.`;
            }

            // Sanitize and limit the AI-generated analysis text before posting as a comment.
            const MAX_COMMENT_LENGTH = 5000;
            const sanitizeAnalysisText = (text) => {
              if (typeof text !== 'string') {
                return '';
              }
              // Remove script-like tags and generic HTML tags as a defense-in-depth measure.
              let cleaned = text
                .replace(/<\s*\/?\s*script[^>]*>/gi, '')
                .replace(/<[^>]+>/g, '')
                .trim();
              if (cleaned.length > MAX_COMMENT_LENGTH) {
                cleaned = cleaned.slice(0, MAX_COMMENT_LENGTH) +
                  '\n\n*Note: Output truncated to fit comment length limits.*';
              }
              return cleaned;
            };

            const safeAnalysisText = sanitizeAnalysisText(analysisText);

            const comment = `## 🤖 Agent Review\n\n${safeAnalysisText}\n\n---\n*This comment was generated automatically by the PR Agent workflow.*`;
            // Try to find an existing PR Agent comment to update, to avoid spamming the thread
            const { data: existingComments } = await github.rest.issues.listComments({
              owner: context.repo.owner,
              repo: context.repo.repo,
              issue_number: prNumber
            });

            const existingAgentComment = existingComments.find(c =>
              c &&
              c.body &&
              c.body.includes('This comment was generated automatically by the PR Agent workflow.')
            );

            if (existingAgentComment) {
              await github.rest.issues.updateComment({
                owner: context.repo.owner,
                repo: context.repo.repo,
                comment_id: existingAgentComment.id,
                body: comment
              });
            } else {
              await github.rest.issues.createComment({
                owner: context.repo.owner,
                repo: context.repo.repo,
                issue_number: prNumber,
                body: comment
              });
            }