From b76891a871dae21c71713fb8bc7cece32e4a08a6 Mon Sep 17 00:00:00 2001
From: Kpa-clawbot <259247574+Kpa-clawbot@users.noreply.github.com>
Date: Thu, 26 Mar 2026 22:35:41 -0700
Subject: [PATCH] ci: 5min staging health timeout, remove continue-on-error

The 185MB problematic DB needs time to load. Give staging up to 300s
to become healthy so we can find out if it starts at all vs hangs.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
---
 .github/workflows/deploy.yml | 9 ++++-----
 1 file changed, 4 insertions(+), 5 deletions(-)

diff --git a/.github/workflows/deploy.yml b/.github/workflows/deploy.yml
index 1b83b27f..e98a96b6 100644
--- a/.github/workflows/deploy.yml
+++ b/.github/workflows/deploy.yml
@@ -164,7 +164,6 @@ jobs:
           echo "Built $(git rev-parse --short HEAD)"
 
       - name: Deploy to staging
-        continue-on-error: true
         run: |
           set -e
 
@@ -209,15 +208,15 @@ jobs:
           # Run compose from the repo checkout (where docker-compose.yml lives)
           docker compose --profile staging up -d --force-recreate staging
 
-          # Wait for Docker healthcheck to report healthy
-          for i in $(seq 1 30); do
+          # Wait for Docker healthcheck — give it up to 5 minutes (big DB)
+          for i in $(seq 1 300); do
             HEALTH=$(docker inspect meshcore-staging --format '{{.State.Health.Status}}' 2>/dev/null || echo "starting")
             if [ "$HEALTH" = "healthy" ]; then
               echo "Staging healthy after ${i}s"
               break
             fi
-            if [ "$i" -eq 30 ]; then
-              echo "Staging failed health check after 30s"
+            if [ "$i" -eq 300 ]; then
+              echo "Staging failed health check after 300s"
               docker logs meshcore-staging --tail 50
               exit 1
             fi