server: in SSE mode, send HTTP headers when slot starts (#23884)

* server: in SSE mode, send HTTP headers when slot starts

* ref to pr

* stream should be false by default

tools/server/server-task.h

@@ -47,7 +47,7 @@ enum stop_type {
 };
 
 struct task_params {
-    bool stream          = true;
+    bool stream          = false;
     bool include_usage   = false;
     bool cache_prompt    = true; // remember the prompt to avoid reprocessing all prompt
     bool return_tokens   = false;
@@ -418,6 +418,8 @@ struct server_task_result_cmpl_partial : server_task_result {
 
     bool post_sampling_probs;
     bool is_progress = false;
+    bool is_begin = false; // whether to send 200 status to HTTP client (begin of SSE stream)
+                           // ref: https://github.com/ggml-org/llama.cpp/pull/23884
     completion_token_output prob_output;
     result_timings timings;
     result_prompt_progress progress;