From a029790483bf9f1c0514fc61690ad493590a7f28 Mon Sep 17 00:00:00 2001 From: Jarvis Date: Thu, 5 Feb 2026 10:36:52 -0700 Subject: [PATCH] Simplify model tiers: Basic=Ollama, Normal=Haiku, Complex=Sonnet --- workspace/OPTIMIZATION.md | 32 +++++++++++++++----------------- 1 file changed, 15 insertions(+), 17 deletions(-) diff --git a/workspace/OPTIMIZATION.md b/workspace/OPTIMIZATION.md index 67a2a6e..5c78d09 100644 --- a/workspace/OPTIMIZATION.md +++ b/workspace/OPTIMIZATION.md @@ -14,36 +14,34 @@ --- -## MODEL SELECTION +## MODEL SELECTION - Three Tiers -### System Default: Haiku - -Haiku is your primary model. It decides routing internally: - -**Haiku routes to Ollama when:** +### Basic → Ollama - File checking and organization - Simple templating/formatting - Log review and cleanup - Non-critical analysis - Routine status checks -**Haiku handles directly when:** -- Most tasks fit within Haiku's capability -- Reasoning is needed but not deeply complex +**Cost:** Free (local) + +### Normal → Haiku (Default) +- Most tasks - Code review (non-production) - Documentation and writing +- General problem solving +- Straightforward reasoning -**Haiku escalates to Sonnet when:** +**Cost:** ~$0.30-1.50 per 1M tokens + +### Complex → Sonnet - Architecture decisions -- Production-like code review +- Production code review - Security analysis - Complex debugging/reasoning - Strategic multi-project decisions +**Cost:** ~$3-15 per 1M tokens + ### Heartbeat: Ollama Only - -Heartbeats ALWAYS use Ollama. No escalation. If Ollama fails, the heartbeat fails. - -### Decision Rule - -Let Haiku decide. It's smart enough to route to Ollama when appropriate and escalate to Sonnet when needed. You only override when you know you need Sonnet upfront. +Heartbeats ALWAYS use Ollama. No escalation. If it fails, it fails.