Add dedicated quick question API

server/src/routes.ts

@@ -11,6 +11,7 @@ import { runMultiplex } from "./llm/multiplexer.js";
 import { runMultiplexStream, type StreamEvent } from "./llm/streaming.js";
 import { getAvailableChatTools, normalizeEnabledChatTools } from "./llm/chat-tools.js";
 import { getModelCatalogSnapshot } from "./llm/model-catalog.js";
+import { buildQuickQuestionMultiplexRequest } from "./llm/quick-question.js";
 import { openaiClient } from "./llm/providers.js";
 import { serializeProviderFields, toPrismaProvider } from "./llm/provider-ids.js";
 import { exaClient } from "./search/exa.js";
@@ -205,6 +206,16 @@ const CompletionStreamBody = z
     }
   });
 
+const QuickQuestionStreamBody = z.object({
+  provider: ProviderSchema,
+  model: z.string().min(1),
+  question: z.string().trim().min(1),
+  enabledTools: EnabledToolsSchema.optional(),
+  userLocation: z.string().trim().min(1).max(200).optional(),
+  temperature: z.number().min(0).max(2).optional(),
+  maxTokens: z.number().int().positive().optional(),
+});
+
 function mergeAttachmentsIntoMetadata(metadata: unknown, attachments?: ChatAttachment[]) {
   if (!attachments?.length) return metadata as any;
   if (!metadata || typeof metadata !== "object" || Array.isArray(metadata)) {
@@ -1564,7 +1575,28 @@ export async function registerRoutes(app: FastifyInstance) {
     };
   });
 
-  // Streaming SSE endpoint.
+  // One-shot, non-persistent Quick Question SSE endpoint.
+  app.post("/v1/quick-questions/stream", async (req, reply) => {
+    requireAdmin(req);
+
+    const parsed = QuickQuestionStreamBody.safeParse(req.body);
+    if (!parsed.success) return app.httpErrors.badRequest(parsed.error.message);
+    const body = withRequestUserLocation(parsed.data, req);
+
+    reply.raw.writeHead(200, buildSseHeaders(typeof req.headers.origin === "string" ? req.headers.origin : undefined));
+    reply.raw.flushHeaders();
+
+    for await (const ev of runMultiplexStream(buildQuickQuestionMultiplexRequest(body))) {
+      writeSseEvent(reply, mapChatStreamEvent(ev));
+    }
+
+    if (!reply.raw.destroyed && !reply.raw.writableEnded) {
+      reply.raw.end();
+    }
+    return reply;
+  });
+
+  // General chat completion SSE endpoint.
   app.post("/v1/chat-completions/stream", async (req, reply) => {
     requireAdmin(req);