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/ui/src/lib/constants/stream.ts

@@ -1,3 +1,3 @@
 // grace window after a visibilitychange before we kick a reader whose socket likely died
 // while the tab was hidden. covers brief background pauses without thrashing live streams
-export const STREAM_VISIBILITY_KICK_MS = 1000;
+export const STREAM_VISIBILITY_KICK_MS = 3000;

tools/ui/src/lib/services/chat.service.ts

@@ -255,6 +255,7 @@ export class ChatService {
 			}),
 			stream,
 			return_progress: stream ? true : undefined,
+			sse_ping_interval: stream ? 1 : undefined,
 			tools: tools && tools.length > 0 ? tools : undefined
 		};
 

tools/ui/src/lib/types/api.d.ts

@@ -265,6 +265,7 @@ export interface ApiChatCompletionRequest {
 	stream?: boolean;
 	model?: string;
 	return_progress?: boolean;
+	sse_ping_interval?: number;
 	tools?: ApiChatCompletionTool[];
 	// Reasoning parameters
 	reasoning_format?: string;