server + ui: ping silent SSE streams every 1s and kick only after 3s so slow prefill never drops healthy connections (#25241)

* server + ui: ping silent SSE streams every 1s and kick only after 3s so slow prefill never drops healthy connections

* server + ui: sse_ping_interval becomes a per-request body field

Address review from ngxson: the global default returns to 30 so API
clients see no behavior change, and the WebUI sends sse_ping_interval: 1
in the request body since it owns the 3s visibility-kick contract and
declares the cadence it needs. Positive values keep the existing > 0
gate, -1 keeps its disabled semantics.

* server: move sse_ping_interval into the request schema

Address review from ngxson: the field is now a typed field_num with
hard limits (-1, INT32_MAX) bound to task_params, seeded from the CLI
default alongside the other inherited parameters. The raw json_value
read and its redundant comment are gone, and schema evaluation brings
type and range validation for free.

tools/server/server-schema.cpp

@@ -37,6 +37,10 @@ std::vector<std::unique_ptr<field>> make_llama_cmpl_schema(const common_params &
     add((new field_bool("return_progress", params.return_progress))
         ->set_desc("Include prompt processing progress events in stream mode"));
 
+    add((new field_num("sse_ping_interval", params.sse_ping_interval))
+        ->set_hard_limits(-1, INT32_MAX)
+        ->set_desc("Interval in seconds between SSE comment pings emitted while the stream stays silent, -1 disables pings"));
+
     add((new field_num("n_predict", params.n_predict))
         ->set_hard_limits(-1, INT32_MAX)
         ->add_alias("max_completion_tokens")
@@ -504,6 +508,7 @@ task_params eval_llama_cmpl_schema(
     params.n_cache_reuse = params_base.n_cache_reuse;
     params.cache_prompt  = params_base.cache_prompt;
     params.antiprompt    = params_base.antiprompt;
+    params.sse_ping_interval = params_base.sse_ping_interval;
 
     // enabling this will output extra debug information in the HTTP responses from the server
     params.verbose       = params_base.verbosity > 9;