Add dedicated quick question API

server/src/llm/quick-question.ts

@@ -0,0 +1,30 @@
+import type { MultiplexRequest, Provider } from "./types.js";
+
+export const QUICK_QUESTION_SYSTEM_PROMPT =
+  "You are answering a quick question in a one-shot experience intended to replace a quick Google search. " +
+  "Give a succinct, direct, self-contained answer. Do not ask follow-up questions, invite the user to continue, " +
+  "or offer additional help. If the question is ambiguous, make the most reasonable assumption and state it briefly only when needed.";
+
+export type QuickQuestionRequest = {
+  provider: Provider;
+  model: string;
+  question: string;
+  enabledTools?: string[];
+  userLocation?: string;
+  temperature?: number;
+  maxTokens?: number;
+};
+
+export function buildQuickQuestionMultiplexRequest({
+  question,
+  ...request
+}: QuickQuestionRequest): MultiplexRequest {
+  return {
+    ...request,
+    persist: false,
+    messages: [
+      { role: "system", content: QUICK_QUESTION_SYSTEM_PROMPT },
+      { role: "user", content: question },
+    ],
+  };
+}

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);
 

server/tests/quick-question.test.ts

@@ -0,0 +1,27 @@
+import assert from "node:assert/strict";
+import test from "node:test";
+import {
+  buildQuickQuestionMultiplexRequest,
+  QUICK_QUESTION_SYSTEM_PROMPT,
+} from "../src/llm/quick-question.js";
+
+test("quick question requests receive the server-owned one-shot system prompt", () => {
+  const request = buildQuickQuestionMultiplexRequest({
+    provider: "openai",
+    model: "gpt-4.1-mini",
+    question: "How do I reset my password?",
+    enabledTools: ["web_search"],
+    userLocation: "Los Angeles, CA",
+  });
+
+  assert.equal(request.persist, false);
+  assert.equal(request.chatId, undefined);
+  assert.deepEqual(request.messages, [
+    { role: "system", content: QUICK_QUESTION_SYSTEM_PROMPT },
+    { role: "user", content: "How do I reset my password?" },
+  ]);
+  assert.deepEqual(request.enabledTools, ["web_search"]);
+  assert.equal(request.userLocation, "Los Angeles, CA");
+  assert.match(QUICK_QUESTION_SYSTEM_PROMPT, /succinct, direct, self-contained answer/i);
+  assert.match(QUICK_QUESTION_SYSTEM_PROMPT, /do not ask follow-up questions/i);
+});