fix: give backend healthcheck a 90s start_period

Backend startup needs ~30-60s (spaCy NLP models load, mem0 v2 init,
MCP session manager, 4 workers). The Dockerfile's 5s start-period was
too short, causing willfarrell/autoheal (running on the host with
AUTOHEAL_CONTAINER_LABEL=all) to kill the container before it finished
booting. Overriding the healthcheck in compose with a longer start_period
keeps failures from counting until the app is actually ready.

docker-compose.yml

@@ -47,6 +47,16 @@ services:
     depends_on:
       qdrant:
         condition: service_healthy
+    # Backend startup loads spaCy (NLP extra), initializes mem0 v2, mounts MCP,
+    # and warms 4 workers — needs ~30-60s. start_period below keeps healthcheck
+    # failures from counting (and from triggering willfarrell/autoheal) during
+    # boot.
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 5
+      start_period: 90s
     restart: unless-stopped
     volumes:
       - ./backend:/app