fix: forward chat send run overrides

src/gateway/server-methods/chat.ts

@@ -2159,6 +2159,7 @@ export const chatHandlers: GatewayRequestHandlers = {
       sessionId?: string;
       message: string;
       thinking?: string;
+      fastMode?: boolean;
       deliver?: boolean;
       originatingChannel?: string;
       originatingTo?: string;
@@ -2822,6 +2823,8 @@ export const chatHandlers: GatewayRequestHandlers = {
               abortSignal: activeRunAbort.controller.signal,
               images: replyOptionImages,
               imageOrder: imageOrder.length > 0 ? imageOrder : undefined,
+              thinkingLevelOverride: p.thinking,
+              fastModeOverride: p.fastMode,
               onAgentRunStart: (runId) => {
                 agentRunStarted = true;
                 const connId = typeof client?.connId === "string" ? client.connId : undefined;

src/gateway/server.chat.gateway-server-chat-b.test.ts

@@ -851,6 +851,37 @@ describe("gateway server chat", () => {
     });
   });
 
+  test("chat.send forwards one-shot thinking and fast mode overrides", async () => {
+    await withGatewayChatHarness(async ({ ws, createSessionDir }) => {
+      const spy = getReplyFromConfig;
+      await connectOk(ws);
+
+      await createSessionDir();
+      await seedMainSessionEntry();
+      let capturedOpts: GetReplyOptions | undefined;
+      mockGetReplyFromConfigOnce(async (_ctx, opts) => {
+        capturedOpts = opts;
+        return undefined;
+      });
+
+      const sendRes = await rpcReq(ws, "chat.send", {
+        sessionKey: "main",
+        message: "hello",
+        thinking: "high",
+        fastMode: true,
+        idempotencyKey: "idem-thinking-fast",
+      });
+      expect(sendRes.ok).toBe(true);
+
+      await vi.waitFor(() => {
+        expect(spy.mock.calls.length).toBeGreaterThan(0);
+      }, FAST_WAIT_OPTS);
+
+      expect(capturedOpts?.thinkingLevelOverride).toBe("high");
+      expect(capturedOpts?.fastModeOverride).toBe(true);
+    });
+  });
+
   test("chat.history hard-caps single oversized nested payloads", async () => {
     await withGatewayChatHarness(async ({ ws, createSessionDir }) => {
       const historyMaxBytes = 64 * 1024;