fix(deepseek): exclude WebSocket turns from the HTTP SSE synthesis (#875)

Author: lidge-jun

src/server/responses/core.ts

@@ -2251,6 +2251,7 @@ async function handleResponsesInner(
       // terminal → [DONE]) so Codex commits the turn instead of hanging on a
       // stream that never closes. Non-streaming clients keep the plain JSON.
       if (clientRequestedStream === true
+        && options.inboundTransport !== "websocket"
         && providerModelResponsesUpstreamStreaming(route.providerName, route.provider, route.modelId) === false
         && route.provider.adapter === "openai-responses") {
         try {

tests/deepseek-inbound-wire.test.ts

@@ -132,6 +132,27 @@ describe("the inbound scope survives the handleResponses replay", () => {
     expect(request.body.stream).toBe(false);
   });
 
+  test("a Codex WebSocket turn keeps plain JSON downstream (no SSE synthesis)", async () => {
+    globalThis.fetch = (async () => Response.json({
+      id: "resp_deepseek",
+      object: "response",
+      status: "completed",
+      output: [],
+    })) as typeof fetch;
+    const config = { providers: { deepseek: deepseekProvider() } } as unknown as OcxConfig;
+    const response = await handleResponses(
+      new Request("http://localhost/v1/responses", {
+        method: "POST",
+        headers: { "content-type": "application/json" },
+        body: JSON.stringify({ model: MODEL, input: "ping", stream: true }),
+      }),
+      config,
+      { model: "", provider: "" },
+      { inboundTransport: "websocket" },
+    );
+    expect(response.headers.get("content-type")).not.toContain("text/event-stream");
+  });
+
   test("ordinary HTTP Responses requests also use bounded JSON upstream (#875)", async () => {
     // The reliability policy is transport-neutral: DeepSeek's Responses stream can
     // deliver output without a terminal, so HTTP turns get the same bounded JSON