fix(web): keep long streams responsive (#1643)

* fix(web): keep long streams responsive

* fix(web): drop queued events for archived sessions

Author: wbxl2000

.changeset/fix-web-long-stream-backlog.md

@@ -0,0 +1,5 @@
+---
+"@moonshot-ai/kimi-code": patch
+---
+
+web: Prevent long streaming responses from stalling after a tab is backgrounded.

apps/kimi-web/src/api/daemon/client.ts

@@ -1434,14 +1434,26 @@ export class DaemonKimiWebApi implements KimiWebApi {
         const { type, seq, session_id: sessionId, payload, offset } = frame;
         const appEvents = projector.project(type, payload, sessionId, { offset });
         for (const appEvent of appEvents) {
+          const turnId = (payload as { turnId?: unknown } | null)?.turnId;
+          const stream =
+            appEvent.type === 'assistantDelta' &&
+            typeof turnId === 'number' &&
+            typeof offset === 'number' &&
+            (type === 'assistant.delta' || type === 'thinking.delta')
+              ? {
+                  turnId,
+                  offset,
+                  kind: type === 'assistant.delta' ? ('text' as const) : ('thinking' as const),
+                }
+              : undefined;
           // historyCompacted from the projector is either a compaction signal
           // (reason auto_compact — no reload, the divider marker handles it) or
           // a delta-gap recovery (reason delta_gap — a real resync, routed to
           // onResync with the real frame.seq, mirroring the protocol path).
           if (appEvent.type === 'historyCompacted' && !isCompactionReason(appEvent.reason)) {
             handlers.onResync(sessionId, seq);
           }
-          handlers.onEvent(appEvent, { sessionId, seq });
+          handlers.onEvent(appEvent, { sessionId, seq, stream });
         }
       },
 

apps/kimi-web/src/api/types.ts

@@ -507,14 +507,26 @@ export interface AppSessionSnapshot {
 }
 
 export interface KimiEventHandlers {
-  onEvent(event: AppEvent, meta: { sessionId: string; seq: number }): void;
+  onEvent(event: AppEvent, meta: KimiEventMeta): void;
   onResync(sessionId: string, currentSeq: number, epoch?: string): void;
   onError(code: number, msg: string, fatal: boolean): void;
   onConnectionChange(connected: boolean): void;
   onTerminalOutput?(sessionId: string, terminalId: string, data: string, seq: number): void;
   onTerminalExit?(sessionId: string, terminalId: string, exitCode: number | null): void;
 }
 
+/** Raw stream coordinates are present only for kap-server assistant/thinking
+    deltas. They let the render queue merge chunks without guessing continuity. */
+export interface KimiEventMeta {
+  sessionId: string;
+  seq: number;
+  stream?: {
+    turnId: number;
+    offset: number;
+    kind: 'text' | 'thinking';
+  };
+}
+
 export interface KimiEventConnection {
   subscribe(sessionId: string, cursor?: AppSessionCursor): void;
   unsubscribe(sessionId: string): void;