Initial commit: CT 116 inference harness — nginx, LiteLLM, router, dashboard, Redis

- Complexity-based routing (MoE default, Dense heavy, Gemma light)
- Per-agent API keys with metrics tracking
- Time-series usage graphs (24h/7d/30d)
- Streaming support (SSE passthrough)
- Unicode cleanup (ASCII-only output)
- Vision support (gemma-4-E4B)
- Tier enforcement (starter/professional/enterprise)
- GPU health monitoring via sidecar polling
- Unified dashboard with line graph

litellm_config.yaml

@@ -0,0 +1,25 @@
+model_list:
+  - model_name: qwen3.6-35B-A3B
+    litellm_params:
+      model: openai/qwen3.6-35B-A3B
+      api_base: http://192.168.68.15:8080/v1
+      api_key: "not-needed"
+
+  - model_name: qwen3.6-27B-code
+    litellm_params:
+      model: openai/qwen3.6-27B-code-text
+      api_base: http://192.168.68.8:8080/v1
+      api_key: "not-needed"
+
+  - model_name: gemma-4-E4B
+    litellm_params:
+      model: openai/gemma-4-E4B
+      api_base: http://192.168.68.110:8080/v1
+      api_key: "not-needed"
+
+general_settings:
+  master_key: sk-syslog-local-master-key
+
+litellm_settings:
+  drop_params: true
+  request_timeout: 120