fix: triple litellm_settings merged into one + add /ui/, /sso/, /litellm-asset-prefix/ to port 80 nginx

litellm_config.yaml

@@ -70,22 +70,7 @@ litellm_settings:
   request_timeout: 600               # Match 10-min llama-server timeout
   set_verbose: true
   failure_callback: ["prometheus"]   # Export metrics to Prometheus
-
-router_settings:
-  routing_strategy: "usage-based-routing"  # For external models only
-  enable_loadbalancing_on_proxy: false     # Disable LiteLLM internal LB
-  allowed_fails: 100                       # Router returns 503 on saturated GPUs
-  # Fallback chains: LiteLLM retries down the chain when router returns saturated.
-  # This gives accurate per-model metrics because router no longer silently reroutes.
-  # The router's circuit breaker prevents cascading failures to dead GPUs.
-  fallbacks:
-    - syslog-auto: ["qwen3.6-35B-A3B", "qwen3.6-27B-code", "gemma-4-12b"]
-    - qwen3.6-35B-A3B: ["qwen3.6-27B-code", "gemma-4-12b"]
-    - qwen3.6-27B-code: ["qwen3.6-35B-A3B", "gemma-4-12b"]
-    - gemma-4-12b: ["qwen3.6-27B-code", "qwen3.6-35B-A3B"]
-
-# Cost tracking for spend analytics (local GPUs at $0, symbolic rates optional)
-litellm_settings:
+  sso_callback: "/sso/callback"
   model_cost:
     syslog-auto:
       input_cost_per_token: 0.0
@@ -99,9 +84,16 @@ litellm_settings:
     gemma-4-12b:
       input_cost_per_token: 0.0
       output_cost_per_token: 0.0
-    # For internal cost allocation, set symbolic rates:
-    # e.g., MoE = $2/M tokens, Dense = $1/M tokens, VLM = $0.50/M tokens
 
-# SSO/OIDC Configuration
-litellm_settings:
-  sso_callback: "/sso/callback"
+router_settings:
+  routing_strategy: "usage-based-routing"  # For external models only
+  enable_loadbalancing_on_proxy: false     # Disable LiteLLM internal LB
+  allowed_fails: 100                       # Router returns 503 on saturated GPUs
+  # Fallback chains: LiteLLM retries down the chain when router returns saturated.
+  # This gives accurate per-model metrics because router no longer silently reroutes.
+  # The router's circuit breaker prevents cascading failures to dead GPUs.
+  fallbacks:
+    - syslog-auto: ["qwen3.6-35B-A3B", "qwen3.6-27B-code", "gemma-4-12b"]
+    - qwen3.6-35B-A3B: ["qwen3.6-27B-code", "gemma-4-12b"]
+    - qwen3.6-27B-code: ["qwen3.6-35B-A3B", "gemma-4-12b"]
+    - gemma-4-12b: ["qwen3.6-27B-code", "qwen3.6-35B-A3B"]