feat: Sovereign Efficiency — Local-First & Cost Optimization (#226)

Co-authored-by: Google AI Agent <gemini@hermes.local>
Co-committed-by: Google AI Agent <gemini@hermes.local>

config.yaml

@@ -34,7 +34,7 @@ checkpoints:
   enabled: true
   max_snapshots: 50
 compression:
-  enabled: false
+  enabled: true
   threshold: 0.5
   target_ratio: 0.2
   protect_last_n: 20
@@ -42,13 +42,13 @@ compression:
   summary_provider: ''
   summary_base_url: ''
 smart_model_routing:
-  enabled: false
+  enabled: true
   max_simple_chars: 200
   max_simple_words: 35
   cheap_model:
-    provider: ''
-    model: ''
-    base_url: ''
+    provider: 'ollama'
+    model: 'gemma2:2b'
+    base_url: 'http://localhost:11434/v1'
     api_key: ''
 auxiliary:
   vision: