From 961720c1b17d31bc28fca6abadcdb149fb3bcb4f Mon Sep 17 00:00:00 2001
From: Daniel Han <danielhanchen@gmail.com>
Date: Sat, 14 Mar 2026 08:08:34 +0000
Subject: [PATCH] studio: handle reasoning_content in GGUF streaming

llama-server sends thinking/reasoning tokens as "reasoning_content"
in the SSE delta (separate from "content"). The studio was only
reading delta.content, so all reasoning tokens from models like
Qwen3.5, Qwen3-Thinking, DeepSeek-R1, etc. were silently dropped.

This caused "replies with nothing" for thinking models: the model
would spend its entire token budget on reasoning, produce zero
content tokens, and the user would see an empty response.

Fix: read reasoning_content from the delta and wrap it in
<think>...</think> tags. The frontend already has full support
for these tags (parse-assistant-content.ts splits them into
reasoning parts, reasoning.tsx renders a collapsible "Thinking..."
indicator).

Verified with Qwen3.5-27B-GGUF (UD-Q4_K_XL):
  - Before: "What is 2+2?" -> empty response (all tokens in reasoning)
  - After: shows collapsible thinking + answer "4"
---
 studio/backend/core/inference/llama_cpp.py | 19 +++++++++++++++++++
 1 file changed, 19 insertions(+)

diff --git a/studio/backend/core/inference/llama_cpp.py b/studio/backend/core/inference/llama_cpp.py
index 21a25d51b2..2f68958bbd 100644
--- a/studio/backend/core/inference/llama_cpp.py
+++ b/studio/backend/core/inference/llama_cpp.py
@@ -592,6 +592,7 @@ class LlamaCppBackend:
 
         url = f"{self.base_url}/v1/chat/completions"
         cumulative = ""
+        in_thinking = False
 
         try:
             with httpx.Client(timeout = None) as client:
@@ -615,6 +616,9 @@ class LlamaCppBackend:
                             if not line:
                                 continue
                             if line == "data: [DONE]":
+                                if in_thinking:
+                                    cumulative += "</think>"
+                                    yield cumulative
                                 return
                             if not line.startswith("data: "):
                                 continue
@@ -624,8 +628,23 @@ class LlamaCppBackend:
                                 choices = data.get("choices", [])
                                 if choices:
                                     delta = choices[0].get("delta", {})
+
+                                    # Handle reasoning/thinking tokens
+                                    # llama-server sends these as "reasoning_content"
+                                    # Wrap in <think> tags for the frontend parser
+                                    reasoning = delta.get("reasoning_content", "")
+                                    if reasoning:
+                                        if not in_thinking:
+                                            cumulative += "<think>"
+                                            in_thinking = True
+                                        cumulative += reasoning
+                                        yield cumulative
+
                                     token = delta.get("content", "")
                                     if token:
+                                        if in_thinking:
+                                            cumulative += "</think>"
+                                            in_thinking = False
                                         cumulative += token
                                         yield cumulative
                             except json.JSONDecodeError: