ci: janitor cancels jobs no runner can ever take

windy-pro alone left ~4 jobs per run waiting forever (build-electron on
macos/windows/ubuntu-latest, deploy if:false): Gitea evaluates job if:
only at pick time, the labels do not exist here, and waiting jobs are
invisible in /actions/tasks. 37 such jobs across 10 runs today. After
30 min they are cancelled and the run status recomputed. Runs each sync,
non-fatal.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

scripts/cancel_unrunnable.sh

@@ -0,0 +1,6 @@
+#!/usr/bin/env bash
+# Cancel jobs no runner can ever take (see cancel_unrunnable.sql). Run on Veron as root.
+set -euo pipefail
+n=$(docker exec -i windy-git-db-1 sh -c 'psql -U "$POSTGRES_USER" -d gitea -At -v ON_ERROR_STOP=1' \
+      < "$(dirname "$0")/cancel_unrunnable.sql" | grep -cE '^[0-9]+$' || true)
+echo "[janitor] cancelled unrunnable jobs in ${n} run(s)"

scripts/cancel_unrunnable.sql

@@ -0,0 +1,29 @@
+-- Cancel CI jobs that can never run (called by scripts/cancel_unrunnable.sh).
+--
+-- A job whose runs-on names a label no Windy Git runner offers (ubuntu-latest,
+-- macos-latest, windows-latest …) waits forever: Gitea evaluates a job's `if:`
+-- only when a runner picks it, so even `if: false` / tag-only jobs sit in the
+-- queue, invisible to /actions/tasks, and keep their run "waiting" for good.
+-- After 30 minutes they are cancelled here; the run's status is then recomputed
+-- (failure > still-active > cancelled > success), the same precedence Gitea uses.
+-- Keep RUNNER_LABELS in step with deploy/runner/config.yaml.
+BEGIN;
+WITH dead AS (
+  UPDATE action_run_job j
+     SET status = 3, stopped = extract(epoch from now())::bigint, updated = extract(epoch from now())::bigint
+   WHERE j.status IN (5, 7)
+     AND to_timestamp(j.created) < now() - interval '30 minutes'
+     AND EXISTS (SELECT 1 FROM jsonb_array_elements_text(j.runs_on::jsonb) l
+                 WHERE l NOT IN ('veron-1', 'linux-x64', 'self-hosted', 'linux', 'x64'))
+  RETURNING j.run_id
+)
+UPDATE action_run r
+   SET status = CASE
+         WHEN EXISTS (SELECT 1 FROM action_run_job x WHERE x.run_id = r.id AND x.status = 2) THEN 2
+         WHEN EXISTS (SELECT 1 FROM action_run_job x WHERE x.run_id = r.id AND x.status IN (5, 6, 7)) THEN r.status
+         WHEN EXISTS (SELECT 1 FROM action_run_job x WHERE x.run_id = r.id AND x.status = 3) THEN 3
+         ELSE 1 END,
+       stopped = CASE WHEN r.stopped = 0 THEN extract(epoch from now())::bigint ELSE r.stopped END
+ WHERE r.id IN (SELECT DISTINCT run_id FROM dead)
+RETURNING r.id;
+COMMIT;

scripts/sync_from_github.sh

@@ -80,6 +80,10 @@ for r in $REPOS; do
   fi
 done
 
+# Jobs that name labels no runner has (ubuntu/macos/windows-latest) would wait
+# forever and invisibly; cancel them after 30 min. Never fails the sync.
+bash "$(dirname "$0")/cancel_unrunnable.sh" || log "janitor failed (non-fatal)"
+
 # Private repos can't run GitHub Actions; mirror their open PRs here so CI
 # fires, and post the verdicts back to GitHub as commit statuses.
 if ! python3 "$(dirname "$0")/pr_status_bridge.py"; then