# Copyright (c) Microsoft Corporation. All rights reserved.
#
# Validates that Copilot configuration files stay in sync with the codebase.
# Runs on changes to Copilot config or docs/knowledge/, and weekly to catch drift.

name: Copilot Config Validation

on:
  pull_request:
    paths:
      - '.github/copilot-instructions.md'
      - '.github/copilot-code-review-instructions.md'
      - '.github/skills/**'
      - '.github/workflows/copilot-setup-steps.yml'
      - 'docs/knowledge/**'
  push:
    branches: ["main"]
    paths:
      - '.github/copilot-instructions.md'
      - '.github/copilot-code-review-instructions.md'
      - '.github/skills/**'
      - '.github/workflows/copilot-setup-steps.yml'
      - 'docs/knowledge/**'
  schedule:
    # Weekly on Monday at 7:00 AM UTC — catch drift from codebase changes
    - cron: "0 7 * * 1"
  workflow_dispatch:

permissions:
  contents: read

jobs:
  validate-copilot-config:
    name: Validate Copilot Configuration
    runs-on: ubuntu-latest

    steps:
      - name: Checkout repository
        uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2

      - name: Validate YAML syntax
        run: |
          echo "Checking copilot-setup-steps.yml..."
          python3 -c "
          import yaml, sys
          with open('.github/workflows/copilot-setup-steps.yml') as f:
              yaml.safe_load(f)
          print('  ✓ Valid YAML')
          "

      - name: Validate knowledge file references
        run: |
          echo "Checking that all knowledge files referenced in instructions exist..."
          # Extract knowledge file references from the table (lines starting with | `...` |)
          grep -P '^\| `[a-z-]+\.md`' .github/copilot-instructions.md | grep -oP '`[a-z-]+\.md`' | tr -d '`' | sort -u > /tmp/referenced.txt

          # List actual knowledge files
          ls docs/knowledge/*.md 2>/dev/null | xargs -I{} basename {} | sort -u > /tmp/actual.txt

          # Check for references to non-existent files
          missing=$(comm -23 /tmp/referenced.txt /tmp/actual.txt || true)
          if [ -n "$missing" ]; then
            echo "❌ Instructions reference non-existent knowledge files:"
            echo "$missing"
            exit 1
          fi
          echo "  ✓ All referenced knowledge files exist"

          # Check for knowledge files not referenced in instructions
          unreferenced=$(comm -13 /tmp/referenced.txt /tmp/actual.txt || true)
          if [ -n "$unreferenced" ]; then
            echo "⚠ Knowledge files not referenced in instructions (may be intentional):"
            echo "$unreferenced"
          fi

      - name: Validate skill files
        run: |
          echo "Checking skill SKILL.md files..."
          errors=0
          for skill_dir in .github/skills/*/; do
            skill_name=$(basename "$skill_dir")
            skill_file="$skill_dir/SKILL.md"

            if [ ! -f "$skill_file" ]; then
              echo "❌ $skill_dir missing SKILL.md"
              errors=$((errors + 1))
              continue
            fi

            # Check frontmatter has required fields
            if ! head -20 "$skill_file" | grep -q "^name:"; then
              echo "❌ $skill_file missing 'name' in frontmatter"
              errors=$((errors + 1))
            fi
            if ! head -20 "$skill_file" | grep -q "^description:"; then
              echo "❌ $skill_file missing 'description' in frontmatter"
              errors=$((errors + 1))
            fi

            echo "  ✓ $skill_name"
          done

          if [ $errors -gt 0 ]; then
            echo "❌ $errors skill validation error(s)"
            exit 1
          fi
          echo "  ✓ All skills valid"

      - name: Check knowledge file freshness indicators
        run: |
          echo "Checking for potential staleness..."
          warnings=0

          # Check if key source files changed more recently than their knowledge files
          check_freshness() {
            knowledge_file="$1"
            shift
            for src in "$@"; do
              if [ -f "$src" ] && [ -f "$knowledge_file" ]; then
                src_commit=$(git log -1 --format=%ct -- "$src" 2>/dev/null || echo 0)
                doc_commit=$(git log -1 --format=%ct -- "$knowledge_file" 2>/dev/null || echo 0)
                if [ "$src_commit" -gt "$doc_commit" ] 2>/dev/null; then
                  echo "⚠ $knowledge_file may be stale — $src changed more recently"
                  warnings=$((warnings + 1))
                fi
              fi
            done
          }

          check_freshness docs/knowledge/value-semantics.md src/value.rs
          check_freshness docs/knowledge/rvm-architecture.md src/rvm/vm/mod.rs
          check_freshness docs/knowledge/builtin-system.md src/builtins/mod.rs
          check_freshness docs/knowledge/ffi-boundary.md bindings/ffi/src/lib.rs
          check_freshness docs/knowledge/engine-api.md src/engine.rs
          check_freshness docs/knowledge/interpreter-architecture.md src/interpreter.rs
          check_freshness docs/knowledge/rego-compiler.md src/languages/rego/compiler/mod.rs
          check_freshness docs/knowledge/compilation-pipeline.md src/scheduler.rs

          if [ $warnings -gt 0 ]; then
            echo ""
            echo "⚠ $warnings knowledge file(s) may need updating"
            echo "  This is informational — not a build failure"
          else
            echo "  ✓ No obvious staleness detected"
          fi