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

nginx/nginx.conf

@@ -0,0 +1,79 @@
+worker_processes auto;
+error_log /var/log/nginx/error.log warn;
+pid /var/run/nginx.pid;
+
+events { worker_connections 1024; }
+
+http {
+    include /etc/nginx/mime.types;
+    default_type application/octet-stream;
+
+    log_format main  launching rt=;
+    access_log /var/log/nginx/access.log main;
+    error_log /var/log/nginx/error.log;
+    sendfile on;
+    keepalive_timeout 65;
+
+    upstream router_api { server router:9000; }
+    upstream dashboard_ui { server dashboard:3000; }
+    upstream litellm_backend { server litellm:4000; }
+
+    server {
+        listen 80;
+
+        # Disable buffering for SSE streams
+        proxy_buffering off;
+
+        # API — through router
+        location /v1/ {
+            proxy_pass http://router_api;
+            proxy_http_version 1.1;
+            proxy_set_header Host $host;
+            proxy_set_header X-Real-IP $remote_addr;
+            proxy_set_header Authorization $http_authorization;
+            proxy_connect_timeout 10s;
+            proxy_read_timeout 300s;
+            proxy_buffering off;
+        }
+
+        # SSE streaming endpoint
+        location /stream {
+            proxy_pass http://router_api;
+            proxy_http_version 1.1;
+            proxy_set_header Host $host;
+            proxy_set_header Connection "";
+            proxy_buffering off;
+            chunked_transfer_encoding off;
+        }
+
+        # Dashboard API proxy for SSE
+        location /api/ {
+            proxy_pass http://dashboard_ui;
+            proxy_http_version 1.1;
+            proxy_set_header Host $host;
+            proxy_buffering off;
+        }
+
+        # LiteLLM debug
+        location /litellm/ {
+            rewrite ^/litellm/(.*) /$1 break;
+            proxy_pass http://litellm_backend;
+            proxy_http_version 1.1;
+            proxy_set_header Host $host;
+            proxy_set_header Authorization $http_authorization;
+        }
+
+        # Dashboard
+        location / {
+            proxy_pass http://dashboard_ui;
+            proxy_http_version 1.1;
+            proxy_set_header Host $host;
+            proxy_buffering off;
+        }
+
+        location /health {
+            return 200 "{\"status\":\"healthy\"}";
+            add_header Content-Type application/json;
+        }
+    }
+}