fix(ci): retry Dagger engine probe and prune cache after check

The Dagger engine stopped responding (connection refused) after the
previous run exhausted disk space and crashed it. Two changes:

1. setup_dagger_remote.sh: retry the nc probe up to 5 times with 30 s
   delays so a transient crash/restart window doesn't immediately fail
   the job.

2. ci.yml: add a post-check prune step (if: always()) so the engine
   cache is cleaned up after every run, reducing the chance of disk
   exhaustion on the next run.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
This commit is contained in:
Thomas SharedInbox
2026-05-24 00:52:12 +02:00
co-authored by Claude Sonnet 4.6
parent e7d61e8ee1
commit 9eba422c67
2 changed files with 21 additions and 6 deletions
+6
View File
@@ -40,6 +40,12 @@ jobs:
DAGGER_NO_NAG: "1"
run: task check-dagger
- name: Prune Dagger cache after check
if: always()
env:
DAGGER_NO_NAG: "1"
run: dagger query '{ engine { localCache { prune } } }' 2>/dev/null || true
- name: Cleanup TLS credentials
if: always()
run: rm -rf /tmp/dagger-tls /tmp/stunnel-dagger.conf /tmp/stunnel.pid
+15 -6
View File
@@ -14,12 +14,21 @@ if [ "$host" == "$port" ]; then
port="8774"
fi
echo "Probing $host:$port..."
if ! nc -zw 3 "$host" "$port" 2>/dev/null; then
echo "Error: No Dagger server responded on $host:$port"
exit 1
fi
echo "Found active Dagger server on $host:$port"
MAX_PROBE_ATTEMPTS=5
PROBE_DELAY=30
for attempt in $(seq 1 $MAX_PROBE_ATTEMPTS); do
echo "Probing $host:$port (attempt $attempt/$MAX_PROBE_ATTEMPTS)..."
if nc -zw 5 "$host" "$port" 2>/dev/null; then
echo "Found active Dagger server on $host:$port"
break
fi
if [ "$attempt" -eq "$MAX_PROBE_ATTEMPTS" ]; then
echo "Error: No Dagger server responded on $host:$port after $MAX_PROBE_ATTEMPTS attempts"
exit 1
fi
echo "Dagger server not responding, waiting ${PROBE_DELAY}s before retry..."
sleep $PROBE_DELAY
done
# 2. Setup TLS credentials (passed as env vars from secrets)
mkdir -p /tmp/dagger-tls