omp: drop static model lists, use proxy discovery only

- Remove static model lists from llama-swap.byte and llama-swap.miche
  (discovery: type: proxy fetches live models from /v1/models)
- Update byte model IDs in config.yml to current roster:
  qwen3.6-35b-heretic-mtp -> qwen36-35b-genesis
  gemma-4-12b-heretic -> gemma4-12b-hauhau
  qwen3.6-35b-a3b-mtp -> qwen36-35b-genesis

dot_omp/private_agent/config.yml

@@ -8,13 +8,13 @@ theme:
   light: light
 setupVersion: 1
 modelRoles: 
-  default: zai-coding/glm-5.2:high
+  default: deepseek/deepseek-v4-flash:high
   task: llama-swap.miche/qwen3.6-27b-mtp
-  smol: llama-swap.byte/qwen3.6-35b-heretic-mtp
+  smol: llama-swap.byte/qwen36-35b-genesis
   plan: zai-coding/glm-5.2:xhigh
   slow: minimax-code/MiniMax-M3:high
   vision: llama-swap.miche/gemma4-12b
-  tiny: llama-swap.byte/qwen3.6-35b-heretic-mtp
+  tiny: llama-swap.byte/qwen36-35b-genesis
 retry: 
   fallbackChains: 
     default: 
@@ -30,7 +30,7 @@ retry:
       - minimax-code/MiniMax-M3
     smol: 
       - llama-swap.miche/qwen3.6-35b-a3b-mtp-rocmfp4
-      - llama-swap.byte/qwen3.6-35b-a3b-mtp
+      - llama-swap.byte/qwen36-35b-genesis
       - llama-swap.miche/qwen3.6-27b-mtp-rocmfp4-turbo
       - zai-coding/glm-5.2
       - minimax-code/MiniMax-M3
@@ -46,7 +46,7 @@ retry:
       - llama-swap.miche/step-3.7-flash
     vision: 
       - llama-swap.miche/gemma4-12b
-      - llama-swap.byte/gemma-4-12b-heretic
+      - llama-swap.byte/gemma4-12b-hauhau
       - llama-swap.miche/qwen3.6-27b-mtp-rocmfp4-turbo
 tools: 
   approvalMode: yolo