server: support Vertex AI compatible API (#22545)

* server: support Vertex AI compatible API

* a bit safer

* support other AIP_* env var

* various fixes

* if AIP_MODE is unset, do nothing

* fix test case

* fix windows build

tools/server/server-http.h

@@ -67,6 +67,10 @@ struct server_http_context {
     std::thread thread; // server thread
     std::atomic<bool> is_ready = false;
 
+    // note: the handler should never throw exceptions
+    using handler_t = std::function<server_http_res_ptr(const server_http_req & req)>;
+    mutable std::unordered_map<std::string, handler_t> handlers;
+
     std::string path_prefix;
     std::string hostname;
     int port;
@@ -78,12 +82,13 @@ struct server_http_context {
     bool start();
     void stop() const;
 
-    // note: the handler should never throw exceptions
-    using handler_t = std::function<server_http_res_ptr(const server_http_req & req)>;
-
     void get(const std::string & path, const handler_t & handler) const;
     void post(const std::string & path, const handler_t & handler) const;
 
+    // Register the Google Cloud Platform (Vertex AI) compat (AIP_PREDICT_ROUTE env var, or /predict)
+    // Must be called AFTER all other API routes are registered
+    void register_gcp_compat();
+
     // for debugging
     std::string listening_address;
 };