name: Regression Test Check

on:
  pull_request:

jobs:
  regression-test:
    name: Regression test enforcement
    runs-on: ubuntu-latest
    steps:
      - name: Checkout repository
        uses: actions/checkout@v4
        with:
          fetch-depth: 0

      - name: Fetch PR head and base
        run: |
          git fetch origin ${{ github.event.pull_request.base.ref }}
          git fetch origin pull/${{ github.event.pull_request.number }}/head:pr-head

      - name: Check for regression tests
        env:
          PR_TITLE: ${{ github.event.pull_request.title }}
          PR_LABELS: ${{ join(github.event.pull_request.labels.*.name, ',') }}
        run: |
          set -euo pipefail

          BASE_REF="origin/${{ github.event.pull_request.base.ref }}"
          # Use the actual PR head, not the merge commit that actions/checkout checks out
          HEAD_REF="pr-head"

          # --- 1. Is this a fix PR? Check title first, then commit messages ---
          IS_FIX=false

          if grep -qiE '^(fix(\(.*\))?|hotfix|bugfix):' <<< "$PR_TITLE"; then
            IS_FIX=true
          fi

          if [ "$IS_FIX" = false ]; then
            COMMITS=$(git log --format='%s' "${BASE_REF}..${HEAD_REF}")
            if grep -qiE '^(fix(\(.*\))?|hotfix|bugfix):' <<< "$COMMITS"; then
              IS_FIX=true
            fi
          fi

          # --- 1b. Does this PR touch high-risk state machine or resilience code? ---
          CHANGED_FILES=$(git diff --name-only "${BASE_REF}...${HEAD_REF}")

          TOUCHES_HIGH_RISK=false
          HIGH_RISK_PATTERNS=(
            "src/context/state.rs"
            "src/agent/session.rs"
            "src/llm/circuit_breaker.rs"
            "src/llm/retry.rs"
            "src/llm/failover.rs"
            "src/agent/self_repair.rs"
            "src/agent/agentic_loop.rs"
            "src/tools/execute.rs"
            "crates/optimclaw_safety/src/"
          )

          for pattern in "${HIGH_RISK_PATTERNS[@]}"; do
            if echo "$CHANGED_FILES" | grep -q "$pattern"; then
              TOUCHES_HIGH_RISK=true
              echo "High-risk file matched: $pattern"
              break
            fi
          done

          # Skip only if NEITHER condition holds — no double-firing on fix PRs
          if [ "$IS_FIX" = false ] && [ "$TOUCHES_HIGH_RISK" = false ]; then
            echo "Not a fix PR and no high-risk files changed — skipping."
            exit 0
          fi

          if [ "$IS_FIX" = true ]; then
            echo "Fix PR detected."
          fi
          if [ "$TOUCHES_HIGH_RISK" = true ]; then
            echo "High-risk state machine or resilience code modified."
          fi

          # --- 2. Skip label or commit message marker ---
          if grep -qF ',skip-regression-check,' <<< ",$PR_LABELS,"; then
            echo "skip-regression-check label present — skipping."
            exit 0
          fi

          COMMIT_BODIES=$(git log --format='%B' "${BASE_REF}..${HEAD_REF}")
          if grep -qF '[skip-regression-check]' <<< "$COMMIT_BODIES"; then
            echo "[skip-regression-check] found in commit message — skipping."
            exit 0
          fi

          # --- 3. Exempt static-only / docs-only changes ---
          if [ -z "$CHANGED_FILES" ]; then
            echo "No changed files — skipping."
            exit 0
          fi

          ALL_EXEMPT=true
          while IFS= read -r file; do
            case "$file" in
              src/channels/web/static/*) ;;
              *.md) ;;
              *) ALL_EXEMPT=false; break ;;
            esac
          done <<< "$CHANGED_FILES"

          if [ "$ALL_EXEMPT" = true ]; then
            echo "All changes are static assets or docs — skipping."
            exit 0
          fi

          # --- 4. Look for test changes ---

          # Fast path: new test attributes or test modules in added lines.
          if git diff "${BASE_REF}...${HEAD_REF}" -U0 -- '*.rs' | grep -qE '^\+.*(#\[test\]|#\[tokio::test\]|#\[cfg\(test\)\]|mod tests)'; then
            echo "Test changes found in .rs files."
            exit 0
          fi

          # Whole-function context: detect edits inside existing test functions.
          # Uses -W (whole function) which works when git recognises function boundaries.
          if git diff "${BASE_REF}...${HEAD_REF}" -W -- '*.rs' | awk '
            /^@@/           { if (has_test && has_add) { found=1; exit } has_test=0; has_add=0 }
            /^ .*#\[test\]/ || /^ .*#\[tokio::test\]/ || /^ .*#\[cfg\(test\)\]/ || /^ .*mod tests/ { has_test=1 }
            /^\+.*#\[test\]/ || /^\+.*#\[tokio::test\]/ || /^\+.*#\[cfg\(test\)\]/ || /^\+.*mod tests/ { has_test=1 }
            /^\+[^+]/       { has_add=1 }
            END             { if (has_test && has_add) found=1; exit !found }
          '; then
            echo "Test changes found in existing test functions."
            exit 0
          fi

          # Line-level check: detect changes inside #[cfg(test)] mod blocks.
          # git -W relies on function boundary detection which misses Rust mod blocks,
          # so this fallback checks whether changed line numbers fall within test modules.
          # We specifically match #[cfg(test)] that is followed by `mod` (same or next
          # line) to avoid false positives from standalone #[cfg(test)] items like
          # individual statics or functions.
          CHANGED_RS=$(echo "$CHANGED_FILES" | grep '\.rs$' || true)
          if [ -n "$CHANGED_RS" ]; then
            while IFS= read -r rs_file; do
              [ -f "$rs_file" ] || continue

              # Find the line where #[cfg(test)] precedes a `mod` declaration.
              # Handles both `#[cfg(test)] mod tests` (same line) and the two-line form.
              TEST_MOD_START=$(awk '
                /^[[:space:]]*#\[cfg\(test\)\].*mod / { print NR; exit }
                /^[[:space:]]*#\[cfg\(test\)\][[:space:]]*$/ { pending=NR; next }
                pending && /^[[:space:]]*mod / { print pending; exit }
                { pending=0 }
              ' "$rs_file")
              [ -n "$TEST_MOD_START" ] || continue

              # Get changed line numbers in this file from the diff hunk headers.
              # Each @@ line looks like: @@ -old,count +new,count @@
              while IFS= read -r hunk_line; do
                line_no=$(echo "$hunk_line" | sed -E 's/^@@ -[0-9,]+ \+([0-9]+).*/\1/')
                [ -n "$line_no" ] || continue
                if [ "$line_no" -ge "$TEST_MOD_START" ]; then
                  echo "Test changes found: $rs_file has changes at line $line_no inside #[cfg(test)] mod block (starts at line $TEST_MOD_START)."
                  exit 0
                fi
              done < <(git diff "${BASE_REF}...${HEAD_REF}" -U0 -- "$rs_file" | grep -E '^@@')
            done <<< "$CHANGED_RS"
          fi

          if grep -qE '^tests/' <<< "$CHANGED_FILES"; then
            echo "Test file changes found under tests/."
            exit 0
          fi

          # --- 5. No tests found ---
          if [ "$IS_FIX" = true ]; then
            echo "::warning::This PR looks like a bug fix but contains no test changes."
          fi
          if [ "$TOUCHES_HIGH_RISK" = true ]; then
            echo "::warning::This PR modifies high-risk state machine or resilience code but includes no test changes."
          fi
          echo "::warning::Please add tests exercising the changed behavior, or apply the 'skip-regression-check' label if not feasible."
          exit 1