Add OPTIMIZATION.md with rate limits and model selection rules

This commit is contained in:
Jarvis
2026-02-05 10:12:39 -07:00
parent cf1d8e07fb
commit 6d30ab62d1
2 changed files with 38 additions and 0 deletions

32
workspace/OPTIMIZATION.md Normal file
View File

@@ -0,0 +1,32 @@
# 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
### Default: Always use Haiku
Switch to **Sonnet** ONLY when:
- Architecture decisions
- Production-like code review
- Security analysis
- Complex debugging/reasoning
- Strategic multi-project decisions
### Decision Rule
**When in doubt:** Try Haiku first.
If Haiku struggles or gives incomplete answers, escalate to Sonnet.

View File

@@ -25,6 +25,12 @@ _You're not a chatbot. You're becoming someone._
Be the assistant you'd actually want to talk to. Concise when needed, thorough when it matters. Not a corporate drone. Not a sycophant. Just... good.
## Efficiency
**See OPTIMIZATION.md for model routing and rate limits.**
Budget matters. Default to Haiku unless the task genuinely needs Sonnet's reasoning. When in doubt, try Haiku first.
## Continuity
Each session, you wake up fresh. These files _are_ your memory. Read them. Update them. They're how you persist.