Performance Issues

Typical bottlenecks

• Slow model responses
• Overlapping scheduled tasks
• Large command outputs
• Long conversation context

Optimization checklist

1. Use faster models for high-frequency interactions.

2. Reduce task frequency to avoid overlaps.

3. Keep command output focused by narrowing the command scope and avoiding large noisy logs.

4. Conversation compaction is built in. If a session still feels slow, prioritize:

• a smaller working prompt
• less noisy tool output
• a faster model binding

Observe performance signals

grep -Ei "timeout|slow|context|compact" .downcity/logs/$(date +%F).jsonl