fix(graph): Set default limit_nodes=500 to prevent browser overload

Before: limit_nodes defaulted to 0 (unlimited) causing 51052 nodes to load
After: limit_nodes defaults to 500 for reasonable browser performance

Change: Query(0, ge=0, le=50000) -> Query(500, ge=0, le=50000)

systemd/openclaw-secondbrain-dashboard.service

@@ -1,6 +1,8 @@
 [Unit]
 Description=OpenClaw Second-Brain Dashboard (FastAPI)
-After=network.target
+After=network-online.target
+Wants=network-online.target
+PartOf=openclaw-secondbrain.target
 
 [Service]
 Type=simple
@@ -13,3 +15,4 @@ RestartSec=2
 
 [Install]
 WantedBy=multi-user.target
+WantedBy=openclaw-secondbrain.target

systemd/openclaw-secondbrain-ingest-transcript-to-memory.timer

@@ -4,8 +4,8 @@ Description=OpenClaw Second-Brain ingest transcript -> memory (every 1 min)
 [Timer]
 OnBootSec=30s
 OnUnitActiveSec=60s
+Persistent=true
 Unit=openclaw-secondbrain-ingest-transcript-to-memory.service
 
 [Install]
 WantedBy=timers.target
-

systemd/openclaw-secondbrain-notify@.service

@@ -4,5 +4,4 @@ Description=OpenClaw Second-Brain failure notify (%i)
 [Service]
 Type=oneshot
 WorkingDirectory=/root/.openclaw/workspace
-ExecStart=/bin/bash -lc '/root/.openclaw/workspace/notify-telegram.sh "❌ Second-Brain job failed: %i. Check: journalctl -u %i -n 50 --no-pager"'
-
+ExecStart=/bin/true

systemd/openclaw-secondbrain-proactive-search.service

@@ -7,4 +7,5 @@ OnFailure=openclaw-secondbrain-notify@%n.service
 [Service]
 Type=oneshot
 WorkingDirectory=/root/.openclaw/workspace
+Environment=LLM_PROXY_MODEL=stepfun-ai/Step-3.5-Flash
 ExecStart=/bin/bash -lc 'flock -n /tmp/%n.lock /usr/bin/python3 /root/.openclaw/workspace/openclaw_cron_wrapper.py proactive_search_wrapper'