dotnet__skills/.github/workflows/pr-triage-batch.yml

name: "PR Triage — Batch"

# Hourly orchestrator. Enumerates open PRs, computes a deterministic state
# for each, and dispatches the per-PR worker (pr-triage.yml) or the malicious-
# code scanner (pr-malicious-scan.agent.lock.yml) for PRs that need action.
# No model calls; no labels are applied here. The worker owns label and
# author-ping side effects. The orchestrator itself posts at most ONE comment
# per scanner dispatch — a deterministic
# `<!-- pr-malicious-scan:dispatched=<sha7> -->` idempotency marker — before
# triggering the scanner workflow. That marker is the source of truth that
# survives any scanner-side failure mode (PAT outage, integrity block,
# dropped HTML marker by the agent).
#
# This workflow also hosts the deterministic weekly stale-PR sweep (the
# `stale-sweep` job, cron `17 4 * * 1`), which replaces the former agentic
# `close-stale-prs.agent.md`. It warns about and closes PRs that have had no
# non-bot activity for 30 / 37 days. See .github/scripts/pr-stale-sweep.sh.

on:
  schedule:
    # Off-the-hour to avoid colliding with evaluation.yml's daily 00:00 UTC cron.
    - cron: "17 * * * *"
    # Weekly (Mon 04:17 UTC) deterministic stale-PR sweep — see the stale-sweep job.
    - cron: "17 4 * * 1"
  workflow_dispatch:
    inputs:
      dry_run:
        description: "If 'true', list states / stale decisions without making writes."
        required: false
        type: string
        default: "false"
      pr_number:
        description: "Optional: triage only this single PR (for ad-hoc smoke tests)."
        required: false
        type: string
      max_dispatches:
        description: "Hard cap on dispatched workers per run. Default 30."
        required: false
        type: string
        default: "30"
      stale_sweep:
        description: "If 'true', run the deterministic stale-PR sweep instead of the triage dispatch."
        required: false
        type: string
        default: "false"
      stale_max:
        description: "Hard cap on stale warn+close writes per sweep. Default 25."
        required: false
        type: string
        default: "25"

permissions:
  pull-requests: read
  issues: write
  statuses: read
  actions: write
  contents: read

concurrency:
  # Keep the hourly triage orchestrator and the weekly stale sweep in separate
  # concurrency groups so that when their crons overlap (Mon 04:17) neither run
  # blocks or queues the other. Runs within each group still serialize.
  group: "${{ (github.event.schedule == '17 4 * * 1' || inputs.stale_sweep == 'true') && 'pr-triage-batch-stale' || 'pr-triage-batch' }}"
  cancel-in-progress: false

run-name: "PR triage batch${{ inputs.stale_sweep == 'true' && ' — stale sweep' || '' }}${{ inputs.pr_number && format(' (PR #{0})', inputs.pr_number) || '' }}${{ inputs.dry_run == 'true' && ' [dry-run]' || '' }}"

jobs:
  dispatch:
    # Runs on the hourly cron and on manual dispatches (unless the dispatch asked
    # for a stale sweep). Skipped on the weekly stale-sweep cron.
    if: ${{ !github.event.repository.fork && (github.event_name != 'schedule' || github.event.schedule == '17 * * * *') && inputs.stale_sweep != 'true' }}
    runs-on: ubuntu-latest
    steps:
      - name: Enumerate open PRs and dispatch workers
        env:
          GH_TOKEN:       ${{ github.token }}
          DRY_RUN:        ${{ inputs.dry_run || 'false' }}
          ONLY_PR:        ${{ inputs.pr_number }}
          MAX_DISPATCHES: ${{ inputs.max_dispatches || '30' }}
        run: |
          set -euo pipefail
          REPO="${GITHUB_REPOSITORY}"
          MAX="${MAX_DISPATCHES}"

          if [ -n "${ONLY_PR:-}" ]; then
            PR_NUMBERS="${ONLY_PR}"
          else
            PR_NUMBERS=$(gh pr list --repo "$REPO" --state open --limit 200 \
              --json number,isDraft \
              --jq '.[] | select(.isDraft == false) | .number')
          fi

          if [ -z "$PR_NUMBERS" ]; then
            echo "No open PRs to triage."
            exit 0
          fi

          echo "## Triage plan" >> "$GITHUB_STEP_SUMMARY"
          echo "" >> "$GITHUB_STEP_SUMMARY"
          echo "| PR | author | author_assoc | mergeable_state | reviewDecision | eval_status | state | action |" >> "$GITHUB_STEP_SUMMARY"
          echo "|---:|---|---|---|---|---|---|---|" >> "$GITHUB_STEP_SUMMARY"

          DISPATCHED=0
          for PR in $PR_NUMBERS; do
            if [ "$DISPATCHED" -ge "$MAX" ]; then
              echo "Reached MAX_DISPATCHES=$MAX — stopping enumeration."
              break
            fi

            PR_JSON=$(gh api "repos/$REPO/pulls/$PR" 2>/dev/null) || { echo "PR #$PR: fetch failed — skipping"; continue; }
            HEAD_SHA=$(jq -r .head.sha <<<"$PR_JSON")
            AUTHOR=$(jq -r .user.login <<<"$PR_JSON")
            AUTHOR_TYPE=$(jq -r .user.type <<<"$PR_JSON")
            AUTHOR_ASSOC=$(jq -r .author_association <<<"$PR_JSON")
            IS_DRAFT=$(jq -r .draft <<<"$PR_JSON")
            MERGEABLE_STATE=$(jq -r .mergeable_state <<<"$PR_JSON")
            LABELS=$(jq -r '[.labels[].name] | join(",")' <<<"$PR_JSON")

            # Skip drafts unconditionally
            if [ "$IS_DRAFT" = "true" ]; then
              echo "| #$PR | $AUTHOR | $AUTHOR_ASSOC | $MERGEABLE_STATE | - | - | skip(draft) | none |" >> "$GITHUB_STEP_SUMMARY"
              continue
            fi
            # Skip PRs whose mergeable_state hasn't settled yet
            if [ "$MERGEABLE_STATE" = "unknown" ]; then
              echo "| #$PR | $AUTHOR | $AUTHOR_ASSOC | $MERGEABLE_STATE | - | - | skip(unsettled) | none |" >> "$GITHUB_STEP_SUMMARY"
              continue
            fi

            # GraphQL: review decision (cheap, one call)
            RV=$(gh api graphql -f query='
              query($owner:String!,$repo:String!,$num:Int!){
                repository(owner:$owner,name:$repo){
                  pullRequest(number:$num){
                    reviewDecision
                    reviewThreads(first:100){ nodes { isResolved } }
                  }
                }
              }' -F owner="${REPO%/*}" -F repo="${REPO#*/}" -F num="$PR" \
              --jq '.data.repository.pullRequest')
            REVIEW_DECISION=$(jq -r '.reviewDecision // ""' <<<"$RV")
            UNRESOLVED=$(jq -r '[.reviewThreads.nodes[] | select(.isResolved == false)] | length' <<<"$RV")

            # Eval status
            EVAL_STATE=$(gh api "repos/$REPO/statuses/$HEAD_SHA" \
              --jq '[.[] | select(.context == "evaluation-status")] | (sort_by(.created_at) | last) | .state // "pending"' 2>/dev/null || echo "pending")
            [ -z "$EVAL_STATE" ] && EVAL_STATE="pending"

            # Bot author?
            IS_BOT="false"
            if [ "$AUTHOR_TYPE" = "Bot" ] || [[ "$AUTHOR" == *"[bot]" ]]; then IS_BOT="true"; fi
            # Trusted contributor?
            IS_TRUSTED="false"
            case "$AUTHOR_ASSOC" in OWNER|MEMBER|COLLABORATOR) IS_TRUSTED="true" ;; esac

            # Compute state — same logic as worker, kept simple and deterministic.
            STATE=""
            if [ "$IS_BOT" = "false" ] && [ "$IS_TRUSTED" = "false" ]; then
              # Look for prior malicious-scan signal on this head. Match either:
              #   <!-- pr-malicious-scan:dispatched=SHORT --> (orchestrator-authored, posted
              #     just before `gh workflow run`; survives any agent-side failure mode), OR
              #   <!-- pr-malicious-scan:fingerprint=SHORT:DATE --> (agent-authored, posted by
              #     a successful scan run).
              # Either marker means "do not re-dispatch for this head SHA".
              SHORT="${HEAD_SHA:0:7}"
              # NB: --paginate runs --jq per page, so aggregations like 'length' would emit one
              # number per page. Emit one .id per matching comment and count lines in the shell.
              MARKER=$(gh api --paginate "repos/$REPO/issues/$PR/comments" \
                --jq ".[] | select(.user.login == \"github-actions[bot]\") | select((.body | contains(\"<!-- pr-malicious-scan:dispatched=$SHORT -->\")) or (.body | contains(\"<!-- pr-malicious-scan:fingerprint=$SHORT:\"))) | .id" \
                | wc -l | tr -d ' ')
              if [ "${MARKER:-0}" -eq 0 ]; then
                STATE="needs-malicious-scan"
              fi
            fi
            if [ -z "$STATE" ]; then
              if [ "$REVIEW_DECISION" = "CHANGES_REQUESTED" ] || [ "${UNRESOLVED:-0}" -gt 0 ] || [ "$MERGEABLE_STATE" = "dirty" ]; then
                STATE="needs-author-attention"
              elif [ "$EVAL_STATE" = "success" ] && [ "$REVIEW_DECISION" = "APPROVED" ]; then
                STATE="ready-for-merge"
              elif [ "$EVAL_STATE" = "success" ]; then
                if [ "$REVIEW_DECISION" = "" ] || [ "$REVIEW_DECISION" = "REVIEW_REQUIRED" ]; then
                  STATE="ready-for-review"
                else
                  STATE="in-review"
                fi
              else
                STATE="ready-for-eval"
              fi
            fi

            # Decide whether to dispatch. in-review and skip never dispatch the worker;
            # but we still dispatch the worker to reconcile the in-review label.
            ACTION="dispatch-worker"
            case "$STATE" in
              needs-malicious-scan) ACTION="dispatch-scanner" ;;
              skip)                  ACTION="none" ;;
            esac

            echo "| #$PR | $AUTHOR | $AUTHOR_ASSOC | $MERGEABLE_STATE | ${REVIEW_DECISION:-none} | $EVAL_STATE | $STATE | $ACTION |" >> "$GITHUB_STEP_SUMMARY"

            if [ "$DRY_RUN" = "true" ] || [ "$ACTION" = "none" ]; then
              continue
            fi

            case "$ACTION" in
              dispatch-worker)
                gh workflow run pr-triage.yml --repo "$REPO" \
                  -f pr_number="$PR" \
                  -f intended_state="$STATE" || echo "::warning::failed to dispatch worker for PR #$PR"
                DISPATCHED=$((DISPATCHED + 1))
                ;;
              dispatch-scanner)
                if gh workflow list --repo "$REPO" --json path --jq '.[].path' \
                    | grep -q 'pr-malicious-scan\.agent\.lock\.yml'; then
                  SHORT="${HEAD_SHA:0:7}"
                  # Post the pre-dispatch idempotency marker BEFORE triggering the scanner.
                  # This is the source of truth for "a scan has been initiated for this head SHA".
                  # Even if the scanner fails to start, never starts (e.g. missing PAT), drops
                  # its own fingerprint marker, or is blocked by an integrity filter, this marker
                  # prevents re-dispatch. A new push (= new SHA) creates no marker, so the
                  # scanner re-runs as expected.
                  PRE_DISPATCH_BODY=$(printf '%s\n%s\n\n%s\n' \
                    "<!-- pr-malicious-scan:dispatched=$SHORT -->" \
                    "🔍 Automated malicious-diff scan dispatched for \`$SHORT\`." \
                    "_Results will be posted as code-scanning alerts and a follow-up comment by github-actions[bot]._")
                  if ! gh api -X POST "repos/$REPO/issues/$PR/comments" \
                       -f body="$PRE_DISPATCH_BODY" >/dev/null 2>&1; then
                    echo "::warning::failed to post pre-dispatch marker for PR #$PR — skipping scanner dispatch"
                    continue
                  fi
                  if gh workflow run pr-malicious-scan.agent.lock.yml --repo "$REPO" \
                       -f pr_number="$PR"; then
                    DISPATCHED=$((DISPATCHED + 1))
                  else
                    echo "::warning::failed to dispatch scanner for PR #$PR"
                  fi
                else
                  echo "::notice::scanner workflow not yet present; would dispatch for PR #$PR"
                fi
                ;;
            esac
          done

          echo "Dispatched $DISPATCHED worker run(s)."

  # Deterministic stale-PR sweep. Runs on the weekly cron and on manual
  # dispatches that pass stale_sweep=true. Warns about / closes PRs with no
  # non-bot activity for 30 / 37 days. Replaces close-stale-prs.agent.md.
  stale-sweep:
    if: ${{ !github.event.repository.fork && ((github.event_name == 'schedule' && github.event.schedule == '17 4 * * 1') || (github.event_name == 'workflow_dispatch' && inputs.stale_sweep == 'true')) }}
    runs-on: ubuntu-latest
    permissions:
      contents: read
      pull-requests: write
      issues: write
    steps:
      - name: Checkout stale-sweep script
        uses: actions/checkout@3d3c42e5aac5ba805825da76410c181273ba90b1 # v6
        with:
          persist-credentials: false
          fetch-depth: 1
          sparse-checkout: |
            .github/scripts
          sparse-checkout-cone-mode: false

      - name: Run pr-stale-sweep.sh
        env:
          GH_TOKEN:  ${{ github.token }}
          DRY_RUN:   ${{ inputs.dry_run || 'false' }}
          STALE_MAX: ${{ inputs.stale_max || '25' }}
        run: |
          chmod +x .github/scripts/pr-stale-sweep.sh
          ./.github/scripts/pr-stale-sweep.sh