fix: remaining template YAML and topology table corrections

- hermes-config-template: Template YAML compression model gemma→ornith.
  Context guidance updated (qwen=256K, only gemma limited to 131K).
- litellm-self-heal: GPU topology table fixed (RTX 3090: 128K→256K, parallel 2→1)

hermes-config-template.prose.md

@@ -99,8 +99,8 @@ model:
   base_url: http://192.168.68.116/v1
   api_key_env: LITELLM_API_KEY    # Injected via infisical run -- wrapper
   max_tokens: 4096                # ⚠️ CRITICAL: Prevents unbounded generation
-  context_length: 262144          # For syslog-auto (ornith route supports 256K).
-                                  # Set 131072 if using qwen3.6-27B-code or gemma-4-12b directly.
+  context_length: 262144          # For syslog-auto (all GPUs support 256K).
+                                  # Set 131072 if using gemma-4-12b directly (12GB VRAM constraint).
 
 fallback_providers:
   provider: deepseek
@@ -129,10 +129,10 @@ mcp_servers:
 # ─── Compression ───
 compression:
   enabled: true
-  model: gemma-4-12b              # ⚠️ Must match auxiliary.compression.model
+  model: ornith-1.0-35b           # ⚠️ Must match auxiliary.compression.model
   provider: harness
-  max_context_window: 262144      # For syslog-auto (ornith supports 256K).
-                                  # Set 131072 if using qwen or gemma directly.
+  max_context_window: 262144      # For Strix Halo compression (256K ctx).
+                                  # Set 131072 if using gemma directly.
   threshold: 0.65                 # Fires at ~170K for 262K window, ~85K for 128K
   target_ratio: 0.30
   protect_last_n: 40
@@ -164,7 +164,7 @@ auxiliary:
     timeout: 30
   compression:
     provider: harness
-    model: gemma-4-12b
+    model: ornith-1.0-35b
     base_url: http://192.168.68.116/v1
     api_key_env: LITELLM_API_KEY
     timeout: 60