name: Skill Quality Report — Nightly Scan

on:
  schedule:
    - cron: "0 3 * * *" # 3:00 AM UTC daily
  workflow_dispatch: # allow manual trigger

permissions:
  contents: read
  discussions: write
  issues: write # fallback if Discussions are not enabled

jobs:
  nightly-scan:
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4.3.1
        with:
          fetch-depth: 0 # full history for git-log author fallback

      # ── Download & cache skill-validator ──────────────────────────
      - name: Get cache key date
        id: cache-date
        run: echo "date=$(date +%Y-%m-%d)" >> "$GITHUB_OUTPUT"

      - name: Restore skill-validator from cache
        id: cache-sv
        uses: actions/cache/restore@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
        with:
          path: .skill-validator
          key: skill-validator-linux-x64-${{ steps.cache-date.outputs.date }}
          restore-keys: |
            skill-validator-linux-x64-

      - name: Download skill-validator
        if: steps.cache-sv.outputs.cache-hit != 'true'
        run: |
          mkdir -p .skill-validator
          curl -fsSL \
            "https://github.com/dotnet/skills/releases/download/skill-validator-nightly/skill-validator-linux-x64.tar.gz" \
            -o .skill-validator/skill-validator-linux-x64.tar.gz
          tar -xzf .skill-validator/skill-validator-linux-x64.tar.gz -C .skill-validator
          rm .skill-validator/skill-validator-linux-x64.tar.gz
          chmod +x .skill-validator/skill-validator

      - name: Save skill-validator to cache
        if: steps.cache-sv.outputs.cache-hit != 'true'
        uses: actions/cache/save@cdf6c1fa76f9f475f3d7449005a359c84ca0f306 # v5.0.3
        with:
          path: .skill-validator
          key: skill-validator-linux-x64-${{ steps.cache-date.outputs.date }}

      # ── Run full scan ─────────────────────────────────────────────
      - name: Run skill-validator check on all skills
        id: check-skills
        run: |
          set +e
          set -o pipefail
          .skill-validator/skill-validator check \
            --skills ./skills \
            --verbose \
            2>&1 | tee sv-skills-output.txt
          echo "exit_code=${PIPESTATUS[0]}" >> "$GITHUB_OUTPUT"
          set +o pipefail
          set -e

      - name: Run skill-validator check on all agents
        id: check-agents
        run: |
          set +e
          set -o pipefail
          AGENT_FILES=$(find agents -name '*.agent.md' -type f 2>/dev/null | tr '\n' ' ')
          if [ -n "$AGENT_FILES" ]; then
            .skill-validator/skill-validator check \
              --agents $AGENT_FILES \
              --verbose \
              2>&1 | tee sv-agents-output.txt
            echo "exit_code=${PIPESTATUS[0]}" >> "$GITHUB_OUTPUT"
          else
            echo "No agent files found."
            echo "" > sv-agents-output.txt
            echo "exit_code=0" >> "$GITHUB_OUTPUT"
          fi
          set +o pipefail
          set -e

      # ── Build report with author attribution ──────────────────────
      - name: Build quality report
        id: report
        uses: actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b # v7.1.0
        with:
          script: |
            const fs = require('fs');
            const path = require('path');
            const { execSync } = require('child_process');

            // ── Parse CODEOWNERS ──────────────────────────────────
            function parseCodeowners() {
              const map = new Map();
              try {
                const raw = fs.readFileSync('CODEOWNERS', 'utf8');
                for (const line of raw.split('\n')) {
                  const trimmed = line.trim();
                  if (!trimmed || trimmed.startsWith('#')) continue;
                  const parts = trimmed.split(/\s+/);
                  if (parts.length >= 2) {
                    const filePath = parts[0].replace(/^\//, '').replace(/\/$/, '');
                    const owners = parts.slice(1).filter(p => p.startsWith('@'));
                    if (owners.length > 0) {
                      map.set(filePath, owners);
                    }
                  }
                }
              } catch (e) {
                console.log('Could not parse CODEOWNERS:', e.message);
              }
              return map;
            }

            // ── Resolve author for a path ─────────────────────────
            function resolveAuthor(resourcePath, codeowners) {
              // CODEOWNERS semantics: last matching rule wins.
              // Also treat "*" as a match-all default rule.
              let matchedOwners = null;
              for (const [pattern, owners] of codeowners) {
                if (
                  pattern === '*' ||
                  resourcePath === pattern ||
                  resourcePath.startsWith(pattern + '/')
                ) {
                  matchedOwners = owners;
                }
              }
              if (matchedOwners && matchedOwners.length > 0) {
                return matchedOwners.join(', ');
              }
              // Fallback: git log
              try {
                const author = execSync(
                  `git log --format='%aN' --follow -1 -- "${resourcePath}"`,
                  { encoding: 'utf8' }
                ).trim();
                return author || 'unknown';
              } catch {
                return 'unknown';
              }
            }

            // ── Parse skill-validator output ──────────────────────
            // The output is a text report; we preserve it as-is and
            // augment it with author info in the summary.
            const skillsOutput = fs.readFileSync('sv-skills-output.txt', 'utf8').trim();
            const agentsOutput = fs.existsSync('sv-agents-output.txt')
              ? fs.readFileSync('sv-agents-output.txt', 'utf8').trim()
              : '';

            const codeowners = parseCodeowners();

            // Count findings
            const combined = skillsOutput + '\n' + agentsOutput;
            const errorCount = (combined.match(/\bError\b/gi) || []).length;
            const warningCount = (combined.match(/\bWarning\b/gi) || []).length;
            const advisoryCount = (combined.match(/\bAdvisory\b/gi) || []).length;

            // Count total skills & agents checked
            let skillDirs = [];
            try {
              skillDirs = fs.readdirSync('skills', { withFileTypes: true })
                .filter(d => d.isDirectory())
                .map(d => d.name);
            } catch {}

            let agentFiles = [];
            try {
              agentFiles = fs.readdirSync('agents')
                .filter(f => f.endsWith('.agent.md'));
            } catch {}

            // ── Build author-attributed summary ───────────────────
            // Extract per-resource blocks from output.  The validator
            // prints skill names as headers — we annotate them with
            // the resolved owner.
            function annotateWithAuthors(output, kind) {
              if (!output) return '_No findings._';
              const lines = output.split('\n');
              const annotated = [];
              for (const line of lines) {
                // Skill names appear as headers, e.g. "## skill-name" or "skill-name:"
                const headerMatch = line.match(/^(?:#{1,3}\s+)?([a-z0-9][a-z0-9-]+(?:\.[a-z0-9.-]+)?)\b/);
                if (headerMatch) {
                  const name = headerMatch[1];
                  const resourcePath = kind === 'skill'
                    ? `skills/${name}`
                    : `agents/${name}.agent.md`;
                  const author = resolveAuthor(resourcePath, codeowners);
                  annotated.push(`${line}  — ${author}`);
                } else {
                  annotated.push(line);
                }
              }
              return annotated.join('\n');
            }

            const today = new Date().toISOString().split('T')[0];

            const title = `Skill Quality Report — ${today}`;

            const body = [
              `# ${title}`,
              '',
              `**${skillDirs.length} skills** and **${agentFiles.length} agents** scanned.`,
              '',
              `| Severity | Count |`,
              `|----------|-------|`,
              `| ⛔ Errors | ${errorCount} |`,
              `| ⚠️ Warnings | ${warningCount} |`,
              `| ℹ️ Advisories | ${advisoryCount} |`,
              '',
              '---',
              '',
              '## Skills',
              '',
              '<details>',
              '<summary>Full skill-validator output for skills</summary>',
              '',
              '```',
              annotateWithAuthors(skillsOutput, 'skill'),
              '```',
              '',
              '</details>',
              '',
              '## Agents',
              '',
              '<details>',
              '<summary>Full skill-validator output for agents</summary>',
              '',
              '```',
              annotateWithAuthors(agentsOutput, 'agent'),
              '```',
              '',
              '</details>',
              '',
              '---',
              '',
              `_Generated by the [Skill Validator nightly scan](https://github.com/${context.repo.owner}/${context.repo.repo}/actions/workflows/skill-quality-report.yml)._`,
            ].join('\n');

            core.setOutput('title', title);
            core.setOutput('body_file', 'report-body.md');

            // GitHub Issues/Discussions enforce a body size limit on the
            // UTF-8 payload (~65536 bytes). Use byte-based limits and prefer
            // shrinking verbose <details> sections to keep markdown valid.
            const MAX_BODY_BYTES = 65000; // leave some margin

            function shrinkDetailsSections(markdown) {
              return markdown.replace(
                /<details([\s\S]*?)>[\s\S]*?<\/details>/g,
                (match, attrs) => {
                  const placeholder = '\n<summary>Details truncated</summary>\n\n' +
                    "> Full output was truncated to fit GitHub's body size limit. " +
                    'See the workflow run for complete output.\n';
                  return `<details${attrs}>${placeholder}</details>`;
                }
              );
            }

            function trimToByteLimit(str, maxBytes) {
              const buf = Buffer.from(str, 'utf8');
              if (buf.length <= maxBytes) return str;
              // Slice bytes and decode, which safely handles multi-byte chars
              return buf.slice(0, maxBytes).toString('utf8').replace(/\uFFFD$/, '');
            }

            const truncNote = '\n\n> **Note:** Output was truncated to fit GitHub\'s body size limit. See the [workflow run](https://github.com/' + context.repo.owner + '/' + context.repo.repo + '/actions/workflows/skill-quality-report.yml) for full output.\n';
            const truncNoteBytes = Buffer.byteLength(truncNote, 'utf8');

            let finalBody = body;

            if (Buffer.byteLength(finalBody, 'utf8') > MAX_BODY_BYTES) {
              // First try: collapse <details> sections to reduce size
              finalBody = shrinkDetailsSections(finalBody);
            }

            if (Buffer.byteLength(finalBody, 'utf8') > MAX_BODY_BYTES) {
              // Last resort: hard byte-trim + truncation note
              finalBody = trimToByteLimit(finalBody, MAX_BODY_BYTES - truncNoteBytes);
            }

            if (Buffer.byteLength(finalBody, 'utf8') < Buffer.byteLength(body, 'utf8')) {
              finalBody += truncNote;
            }

            fs.writeFileSync('report-body.md', finalBody);

      # ── Create Discussion (preferred) or Issue (fallback) ────────
      - name: Create Discussion
        id: create-discussion
        continue-on-error: true
        uses: actions/github-script@f28e40c7f34bde8b3046d885e986cb6290c5673b # v7.1.0
        with:
          script: |
            const fs = require('fs');
            const title = '${{ steps.report.outputs.title }}'.replace(/'/g, "\\'");
            const body = fs.readFileSync('report-body.md', 'utf8');

            // Find the "Skill Quality Reports" category
            const categoriesResult = await github.graphql(`
              query($owner: String!, $repo: String!) {
                repository(owner: $owner, name: $repo) {
                  id
                  discussionCategories(first: 25) {
                    nodes { id name }
                  }
                }
              }
            `, {
              owner: context.repo.owner,
              repo: context.repo.repo,
            });

            const repo = categoriesResult.repository;
            const categories = repo.discussionCategories.nodes;
            const category = categories.find(c =>
              c.name === 'Skill Quality Reports'
            );

            if (!category) {
              core.setFailed('Discussion category "Skill Quality Reports" not found. Falling back to issue.');
              return;
            }

            await github.graphql(`
              mutation($repoId: ID!, $categoryId: ID!, $title: String!, $body: String!) {
                createDiscussion(input: {
                  repositoryId: $repoId,
                  categoryId: $categoryId,
                  title: $title,
                  body: $body
                }) {
                  discussion { url }
                }
              }
            `, {
              repoId: repo.id,
              categoryId: category.id,
              title: title,
              body: body,
            });

            console.log('Discussion created successfully.');

      - name: Fallback — Create Issue
        if: steps.create-discussion.outcome == 'failure'
        env:
          GH_TOKEN: ${{ github.token }}
        run: |
          # Create label if it doesn't exist (ignore errors if it already exists)
          gh label create "skill-quality" --description "Automated skill quality reports" --color "d4c5f9" 2>/dev/null || true
          gh issue create \
            --title "${{ steps.report.outputs.title }}" \
            --body-file report-body.md \
            --label "skill-quality"