name: Online search for vulns

on:
  schedule:
    - cron: '42 8 * * *'
  workflow_dispatch: {}   # allow manual trigger

permissions:
  contents: read
  actions: read           # needed to list/download previous run artifacts
  id-token: write         # needed by claude-code-action for OIDC auth

concurrency:
  group: vuln-watch
  cancel-in-progress: true

jobs:
  watch:
    runs-on: ubuntu-latest
    timeout-minutes: 20

    steps:
      # The scripts driving this workflow live on the `vuln-watch` branch so
      # they don't clutter master (which is what ships to production). The
      # workflow file itself MUST stay on the default branch, as GitHub only
      # honors `schedule:` triggers on the default branch.
      - name: Checkout vuln-watch branch (scripts + prompt)
        uses: actions/checkout@v5
        with:
          ref: vuln-watch
          fetch-depth: 1
          persist-credentials: false

      - name: Set up Python
        uses: actions/setup-python@v5
        with:
          python-version: '3.12'

      - name: Install Python dependencies
        run: python -m pip install --quiet feedparser

      # ---- Load previous state ---------------------------------------------
      # Find the most recent successful run of THIS workflow (other than the
      # current one) and pull its `vuln-watch-state` artifact. On the very
      # first run there will be none — that's fine, we start empty.
      - name: Find previous successful run id
        id: prev
        env:
          GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
        run: |
          set -e
          run_id=$(gh run list \
            --workflow="${{ github.workflow }}" \
            --status=success \
            --limit 1 \
            --json databaseId \
            --jq '.[0].databaseId // empty')
          echo "run_id=${run_id}" >> "$GITHUB_OUTPUT"
          if [ -n "$run_id" ]; then
            echo "Found previous successful run: $run_id"
          else
            echo "No previous successful run — starting from empty state."
          fi

      - name: Download previous state artifact
        if: steps.prev.outputs.run_id != ''
        uses: actions/download-artifact@v5
        continue-on-error: true   # tolerate retention expiry
        with:
          name: vuln-watch-state
          path: state/
          run-id: ${{ steps.prev.outputs.run_id }}
          github-token: ${{ secrets.GITHUB_TOKEN }}

      # ---- Fetch + diff (token-free; runs every time) ---------------------
      # Performs conditional GETs (ETag / If-Modified-Since) against every
      # source, parses RSS/Atom/HTML, dedups against state.seen + state.aliases,
      # applies the time-window filter, and emits new_items.json.
      # Updates state.sources (HTTP cache metadata + per-source high-water
      # marks) in place so the cache survives even when Claude doesn't run.
      - name: Fetch + diff all sources
        id: diff
        env:
          SCAN_DATE: ${{ github.run_started_at }}
        run: python -m scripts.vuln_watch.fetch_and_diff

      # ---- Fetch checker code so Claude can grep it for coverage ---------
      # The orphan vuln-watch branch has none of the actual checker code,
      # so we pull the `test` branch (the dev branch where coded-but-
      # unreleased CVE checks live) into ./checker/. The prompt tells
      # Claude this is the canonical source of truth for "is CVE-X already
      # implemented?". Only fetched on days with something to classify.
      - name: Checkout checker code (test branch) for coverage grep
        if: steps.diff.outputs.new_count != '0'
        uses: actions/checkout@v5
        with:
          ref: test
          path: checker
          fetch-depth: 1
          persist-credentials: false

      # ---- Classify new items with Claude (skipped when nothing is new) ---
      - name: Run classifier with Claude Opus
        id: classify
        if: steps.diff.outputs.new_count != '0'
        uses: anthropics/claude-code-action@v1
        env:
          SCAN_DATE: ${{ github.run_started_at }}
        with:
          prompt: |
            Read the full task instructions from scripts/daily_vuln_watch_prompt.md
            and execute them end-to-end. Your input is new_items.json (already
            deduped, windowed, and pre-filtered — do NOT re-fetch sources).
            Write the three watch_${TODAY}_*.md files and classifications.json.
            Use $SCAN_DATE as the canonical timestamp.
          claude_code_oauth_token: ${{ secrets.CLAUDE_CODE_OAUTH_TOKEN }}
          # model + tool allowlist now pass through claude_args (v1 dropped
          # the dedicated `model:` and `allowed_tools:` inputs). Job-level
          # `timeout-minutes: 20` above bounds total runtime.
          claude_args: |
            --model claude-opus-4-7
            --allowedTools "Read,Write,Edit,Bash,Grep,Glob,WebFetch"

      - name: Upload Claude execution log
        if: ${{ always() && steps.classify.outputs.execution_file != '' }}
        uses: actions/upload-artifact@v5
        with:
          name: claude-execution-log-${{ github.run_id }}
          path: ${{ steps.classify.outputs.execution_file }}
          retention-days: 30
          if-no-files-found: warn

      # ---- Merge classifications back into state --------------------------
      # Also writes stub watch_*.md files if the classify step was skipped, so
      # the report artifact is consistent across runs.
      - name: Merge classifications into state
        if: always()
        env:
          SCAN_DATE: ${{ github.run_started_at }}
        run: python -m scripts.vuln_watch.merge_state

      - name: Upload new state artifact
        if: always()
        uses: actions/upload-artifact@v5
        with:
          name: vuln-watch-state
          path: state/seen.json
          retention-days: 90
          if-no-files-found: error

      - name: Upload daily report
        if: always()
        uses: actions/upload-artifact@v5
        with:
          name: vuln-watch-report-${{ github.run_id }}
          path: |
            watch_*.md
            current_toimplement.md
            current_tocheck.md
            new_items.json
            classifications.json
          retention-days: 90
          if-no-files-found: warn