Remove PythonInterpreter from Space prompt; note offline-only usage

README.md

@@ -19,9 +19,14 @@ models through the shared HF Inference API.
 Supported tools:
 - `search` (DuckDuckGo, multi-query)
 - `visit` (HTTP fetch + text extraction, multi-URL)
+- `google_scholar` (Serper, multi-query)
 - lightweight research-state summary to cut repeated work
 - `<answer>` extraction for the final response
 
+`PythonInterpreter` is **not** available in this Space (no sandbox service).
+To try it, use [offline inference](https://github.com/OSU-NLP-Group/QUEST)
+from the GitHub repo with `ENABLE_PYTHON_TOOL=true`.
+
 ---
 
 ## 1) Use our own `osunlp/QUEST-35B` model (recommended)

app.py

@@ -41,9 +41,10 @@ MODEL_URL = os.getenv("MODEL_URL", "https://huggingface.co/osunlp/QUEST-35B-RL")
 
 
 # --- System prompt ---------------------------------------------------------
-# Full QUEST SYSTEM_PROMPT (mirrors inference/prompt.py in the research repo)
-# so that QUEST-35B sees the exact tool schema it was trained with. Other
-# models still follow this schema just fine in practice.
+# Hosted Space prompt (based on inference/prompt.py in the GitHub repo).
+# PythonInterpreter is intentionally omitted here: this Space has no Python
+# sandbox backend. To try PythonInterpreter, run offline inference from
+# https://github.com/OSU-NLP-Group/QUEST with ENABLE_PYTHON_TOOL=true.
 QUEST_SYSTEM_PROMPT = """You are a deep research assistant. Your core function is to conduct thorough, multi-source investigations into any topic. You must handle both broad, open-domain inquiries and queries within specialized academic fields. For every request, synthesize information from credible, diverse sources to deliver a comprehensive, accurate, and objective response. When you have gathered sufficient information and are ready to provide the definitive response, you must enclose the entire final answer within <answer></answer> tags.
 
 # Tools