feat: implement /v1/messages/count_tokens endpoint

Add Anthropic-compatible token counting endpoint using hybrid approach:
- Local estimation with gpt-tokenizer for text content (~95% accuracy)
- API-based counting for complex content (images, documents)
- Automatic fallback to local estimation on API errors

This resolves warnings in LiteLLM and other clients that rely on
pre-request token counting.

package.json

@@ -60,7 +60,8 @@
     "async-mutex": "^0.5.0",
     "better-sqlite3": "^12.5.0",
     "cors": "^2.8.5",
-    "express": "^4.18.2"
+    "express": "^4.18.2",
+    "gpt-tokenizer": "^2.5.0"
   },
   "devDependencies": {
     "@tailwindcss/forms": "^0.5.7",