Consolidate benchmark workflows: drop benchmark.yml, add manual dispa…

.github/workflows/benchmark-external.yml

@@ -2,8 +2,12 @@ name: NAD Benchmark (label-triggered)
 
 # The active NAD benchmark gate. Policy: EVERY PR (internal or external fork) is
 # gated on demand — a maintainer reviews the PR and adds the `run-benchmark`
-# label to run it. (Automatic gating in benchmark.yml is disabled by policy;
-# this label gate is the one that runs.)
+# label to run it. This is the only NAD benchmark workflow.
+#
+# Maintainers can also run it MANUALLY from the Actions tab (Run workflow /
+# workflow_dispatch) against any branch, with optional subset/count/gate inputs.
+# Manual runs are trusted (only maintainers can trigger them), so they check out
+# the selected branch directly instead of an untrusted PR head.
 #
 # It uses pull_request_target so the run has access to KIRO_API_KEY even for fork
 # PRs (a plain pull_request gate can't — fork PRs receive no secrets), and is
@@ -28,33 +32,49 @@ on:
     # never auto-runs on push. A maintainer must (re-)apply the label each time.
     types: [labeled]
 
+  # Manual runs from the Actions tab. Only users with write access can dispatch
+  # this, so the run is trusted — it scores the selected branch's own code.
+  workflow_dispatch:
+    inputs:
+      subset:
+        description: "Subset(s): 'all', a single name, or a comma-separated list"
+        default: 'all'
+      count:
+        description: 'Pass@k attempts per scenario'
+        default: '1'
+      gate:
+        description: 'Required pass rate (0-100); job fails below this'
+        default: '90'
+
 # Least privilege: the base-context GITHUB_TOKEN is write-capable by default under
 # pull_request_target. Restrict it to read so untrusted code can't use it to push,
 # open releases, or modify the repo.
 permissions:
   contents: read
 
 concurrency:
-  group: nad-benchmark-external-${{ github.event.pull_request.number }}
+  group: nad-benchmark-external-${{ github.event.pull_request.number || github.ref }}
   cancel-in-progress: true
 
 jobs:
   gate:
-    # Run ONLY when a maintainer added the `run-benchmark` label. This `if` is the
-    # trust gate — without it, pull_request_target would run untrusted code with
-    # secrets on every PR event.
-    if: github.event.label.name == 'run-benchmark'
+    # Run on a manual dispatch, OR when a maintainer added the `run-benchmark`
+    # label. For the label path this `if` is the trust gate — without it,
+    # pull_request_target would run untrusted code with secrets on every PR event.
+    if: github.event_name == 'workflow_dispatch' || github.event.label.name == 'run-benchmark'
     name: NAD external benchmark (labeled)
     runs-on: ubuntu-latest
     timeout-minutes: 20
 
     steps:
-      # Check out the PR's HEAD — i.e. the contributor's UNTRUSTED code. This is
-      # required (we must score their skill) and is the crux of the risk above.
-      # The workflow FILE itself still comes from base (pull_request_target), so
-      # the contributor cannot alter these steps — only the skill/agent/test/
-      # grader content that the steps then run.
-      - name: Checkout PR head (untrusted)
+      # Label runs: check out the PR's HEAD — i.e. the contributor's UNTRUSTED
+      # code. This is required (we must score their skill) and is the crux of the
+      # risk above. The workflow FILE itself still comes from base
+      # (pull_request_target), so the contributor cannot alter these steps — only
+      # the skill/agent/test/grader content that the steps then run.
+      # Manual runs: head.sha is empty, so checkout falls back to the selected
+      # branch (trusted — only maintainers can dispatch).
+      - name: Checkout PR head (untrusted on label runs)
         uses: actions/checkout@v4
         with:
           ref: ${{ github.event.pull_request.head.sha }}
@@ -69,13 +89,14 @@ jobs:
           KIRO_API_KEY: ${{ secrets.KIRO_API_KEY }}
         run: |
           set -euo pipefail
+          # Inputs come from the manual dispatch form; label runs use the defaults.
           python benchmark/run_skill_tests.py \
             --nad-root=. \
-            --subset=all \
-            --count=1 \
+            --subset="${{ github.event.inputs.subset || 'all' }}" \
+            --count="${{ github.event.inputs.count || '1' }}" \
             --workers=4 \
             --judge \
-            --gate=90
+            --gate="${{ github.event.inputs.gate || '90' }}"
 
       - name: Upload results
         if: always()