Add count_tokens api proxying (#476)

README.md

@@ -27,6 +27,7 @@ Built in Go for performance and simplicity, llama-swap has zero dependencies and
   - `v1/images/edits`
 - ✅ Anthropic API supported endpoints:
   - `v1/messages`
+  - `v1/messages/count_tokens`
 - ✅ llama-server (llama.cpp) supported endpoints
   - `v1/rerank`, `v1/reranking`, `/rerank`
   - `/infill` - for code infilling

proxy/proxymanager.go

@@ -282,6 +282,8 @@ func (pm *ProxyManager) setupGinEngine() {
 	pm.ginEngine.POST("/v1/completions", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 	// Support anthropic /v1/messages (added https://github.com/ggml-org/llama.cpp/pull/17570)
 	pm.ginEngine.POST("/v1/messages", pm.apiKeyAuth(), pm.proxyInferenceHandler)
+	// Support anthropic count_tokens API (Also added in the above PR)
+	pm.ginEngine.POST("/v1/messages/count_tokens", pm.apiKeyAuth(), pm.proxyInferenceHandler)
 
 	// Support embeddings and reranking
 	pm.ginEngine.POST("/v1/embeddings", pm.apiKeyAuth(), pm.proxyInferenceHandler)