Studio: forward parallel_tool_calls through /v1/responses bridge

Round 3 reviewer feedback:

- studio/backend/routes/inference.py: _build_chat_request (the
  /v1/responses → /v1/chat/completions translator) was dropping
  parallel_tool_calls on the floor. A Responses-API caller that set
  `parallel_tool_calls=false` saw the flag accepted at the schema
  layer but never reach llama-server because the translated
  ChatCompletionRequest had no first-class field for it. Now that
  parallel_tool_calls IS a first-class field on ChatCompletionRequest
  (added by this PR's earlier commits), translate it through the
  bridge so the preference actually fires.

- studio/frontend/src/features/chat/utils/chat-settings-storage.ts:
  the stop sanitizer silently dropped `stop: []` instead of persisting
  the empty array. That meant a user could not clear the last chip —
  on reload, the previously-persisted stops came back. Persist empty
  arrays explicitly so the cleared state round-trips.

- studio/backend/tests/test_sampling_params_routing.py: pin both with
  the raw reproductions reviewers cited.

studio/backend/routes/inference.py

@@ -3780,6 +3780,14 @@ def _build_chat_request(
         chat_kwargs["top_p"] = payload.top_p
     if payload.max_output_tokens is not None:
         chat_kwargs["max_tokens"] = payload.max_output_tokens
+    # `parallel_tool_calls` is now a first-class field on
+    # ChatCompletionRequest (PR #5711) and the OpenAI-compat
+    # passthrough builder forwards it. Translate it here so a Responses
+    # API caller (e.g. OpenAI Codex SDK) that sets
+    # `parallel_tool_calls=false` actually sees the preference reach
+    # llama-server instead of getting silently dropped at the bridge.
+    if payload.parallel_tool_calls is not None:
+        chat_kwargs["parallel_tool_calls"] = payload.parallel_tool_calls
 
     chat_tools = _translate_responses_tools_to_chat(payload.tools)
     if chat_tools is not None:
@@ -3789,13 +3797,7 @@ def _build_chat_request(
     if chat_tool_choice is not None:
         chat_kwargs["tool_choice"] = chat_tool_choice
 
-    req = ChatCompletionRequest(**chat_kwargs)
-    # `parallel_tool_calls` is not a first-class field on ChatCompletionRequest,
-    # but the model allows extras and _build_openai_passthrough_body forwards
-    # only explicitly-known fields. Llama-server does not currently implement
-    # parallel_tool_calls semantics, so we accept-and-ignore it on the
-    # Responses side to avoid breaking SDK clients that always send it.
-    return req
+    return ChatCompletionRequest(**chat_kwargs)
 
 
 def _chat_tool_calls_to_responses_output(tool_calls: list[dict]) -> list[dict]:

studio/backend/tests/test_sampling_params_routing.py

@@ -547,6 +547,51 @@ def test_local_openai_passthrough_forwards_new_sampling_fields():
     assert body["parallel_tool_calls"] is False, body
 
 
+# ── Responses → ChatCompletions bridge preserves parallel_tool_calls ──
+
+
+def test_responses_to_chat_bridge_preserves_parallel_tool_calls():
+    """Round 3 reviewers flagged that `_build_chat_request` (the
+    /v1/responses → /v1/chat/completions translator) dropped
+    `parallel_tool_calls`, so a Responses-API caller that set
+    `parallel_tool_calls=false` never saw the flag reach llama-server.
+    Pin the translation."""
+    from models.inference import ChatMessage, ResponsesRequest
+    from routes.inference import _build_chat_request, _build_openai_passthrough_body
+
+    payload = ResponsesRequest(
+        input = "hi",
+        stream = True,
+        parallel_tool_calls = False,
+    )
+    chat_req = _build_chat_request(
+        payload,
+        [ChatMessage(role = "user", content = "hi")],
+        stream = True,
+    )
+    assert chat_req.parallel_tool_calls is False, chat_req
+    body = _build_openai_passthrough_body(chat_req, backend_ctx = 4096)
+    assert body["parallel_tool_calls"] is False, body
+
+
+def test_responses_to_chat_bridge_omits_unset_parallel_tool_calls():
+    """Unset `parallel_tool_calls` (None) must not appear on the
+    translated body — the upstream default is `true` everywhere, so
+    forwarding `parallel_tool_calls=None` would over-specify."""
+    from models.inference import ChatMessage, ResponsesRequest
+    from routes.inference import _build_chat_request, _build_openai_passthrough_body
+
+    payload = ResponsesRequest(input = "hi", stream = True)
+    chat_req = _build_chat_request(
+        payload,
+        [ChatMessage(role = "user", content = "hi")],
+        stream = True,
+    )
+    assert chat_req.parallel_tool_calls is None, chat_req
+    body = _build_openai_passthrough_body(chat_req, backend_ctx = 4096)
+    assert "parallel_tool_calls" not in body, body
+
+
 # ── Backend ChatInferenceSettings schema accepts new fields ────────────
 
 

studio/frontend/src/features/chat/utils/chat-settings-storage.ts

@@ -171,10 +171,13 @@ function sanitizeInferenceParams(
   // re-truncates to the wire cap (4 for OpenAI Chat, 16 for Anthropic,
   // dropped entirely for OpenAI Responses) before the request hits the
   // network. Capping to 4 here would defeat Anthropic's UI cap of 16
-  // for users who switch providers between sessions.
+  // for users who switch providers between sessions. An EMPTY array
+  // must persist as an empty array (not be sanitized away) so the user
+  // can clear the last chip and have the change saved — otherwise the
+  // previously stored stops come back on reload.
   if (Array.isArray(value.stop)) {
     const stops = value.stop.filter((s): s is string => typeof s === "string");
-    if (stops.length > 0) params.stop = stops.slice(0, 16);
+    params.stop = stops.slice(0, 16);
   }
   // serviceTier: nullable enum string.
   if (value.serviceTier === null) {