From 6ac4b31dfa89b44e58acbfaadecaaa53220ddf71 Mon Sep 17 00:00:00 2001 From: Dennis Thiessen Date: Mon, 7 Sep 2026 19:53:12 +0200 Subject: [PATCH] fix(ci): poll the health endpoint instead of sleeping a fixed 3s The deploy failed with "curl: (7) Failed to connect to 127.0.0.1 port 8998 after 0 ms" on a service that was in fact running. "after 0 ms" is connection-refused, not a timeout: the check fired before uvicorn had bound the port. A fixed "sleep 3" followed by a single curl has no retry, so it fails the whole deploy whenever startup runs a second long. Raising the sleep would slow every deploy and still race on a bad day. This polls once a second for up to 60s and exits as soon as the app answers, so a fast start costs nothing and a slow one no longer fails. On a genuine failure it now dumps systemctl status and the last 80 journal lines, so the cause is visible without running a second deploy to go looking. The heredoc is quoted so the loop's $i and $(seq) expand on the remote host rather than in the runner's shell; that block has no local variables or ${{ }} expressions, so quoting is safe here. Co-Authored-By: Claude Opus 5 Claude-Session: https://claude.ai/code/session_01HAH7vVtn7qbcn1EVheecHQ --- .gitea/workflows/deploy.yml | 28 +++++++++++++++++++++++----- 1 file changed, 23 insertions(+), 5 deletions(-) diff --git a/.gitea/workflows/deploy.yml b/.gitea/workflows/deploy.yml index 5ba7ef0..2dc654d 100644 --- a/.gitea/workflows/deploy.yml +++ b/.gitea/workflows/deploy.yml @@ -166,13 +166,31 @@ jobs: - name: Restart service & health check run: | - ssh $SSH_OPTS "${DEPLOY_USER}@${DEPLOY_HOST}" << REMOTE_SCRIPT + # Quoted heredoc: the loop's $i / $(seq) must be expanded on the + # REMOTE host, not by this runner's shell before it is sent. + ssh $SSH_OPTS "${DEPLOY_USER}@${DEPLOY_HOST}" << 'REMOTE_SCRIPT' set -e sudo systemctl restart signalplatform.service - sleep 3 - curl -fsS http://127.0.0.1:8998/api/v1/health > /dev/null \ - || { echo "✗ health check failed after restart"; exit 1; } - echo "✓ signalplatform deployed" + + # Poll instead of guessing how long startup takes. The old fixed + # "sleep 3" then single curl raced whenever startup ran long, and + # failed the deploy with a bare "connection refused" on a service + # that came up healthy a second later. This exits as soon as the app + # answers, so a fast start costs nothing. + for i in $(seq 1 60); do + if curl -fsS http://127.0.0.1:8998/api/v1/health > /dev/null 2>&1; then + echo "✓ signalplatform deployed — healthy after ${i}s" + exit 0 + fi + sleep 1 + done + + # Still down after a minute: this is a real failure, so leave enough + # behind to diagnose it without a second deploy. + echo "✗ health check failed: no response on :8998 after 60s" + sudo systemctl status signalplatform.service --no-pager -l || true + journalctl -u signalplatform.service -n 80 --no-pager || true + exit 1 REMOTE_SCRIPT - name: Clean up SSH key