jarvis/workspace/OPTIMIZATION.md

OPTIMIZATION.md - Cost & Efficiency Rules

RATE LIMITS

API Call Throttling:

• 5 seconds minimum between API calls
• 10 seconds minimum between web searches
• Batch similar work whenever possible
• If you hit 429 error: STOP and wait 5 minutes

Monthly Budget:

• $20 total
• Warn at 75% ($15 spent)

---

MODEL SELECTION RULE

Default: Haiku

Switch to Sonnet ONLY when:

• Architecture decisions
• Complex code review
• Security Analysis
• Complex debugging/reasoning

When in doubt: Try Haiku first

Heartbeat: Ollama Only

Heartbeats ALWAYS use Ollama. No escalation. If it fails, it fails.