fix: strip <think> tags from chat responses

Add thinking content cleaning to notebook and source chat graphs.
Previously, models that output <think>...</think> tags (like DeepSeek)
or malformed variants without opening tags (like Nemotron) would leak
reasoning content into user-visible responses.

Changes:
- chat.py: Clean AI response content before returning messages
- source_chat.py: Same fix for source-specific chat
- text_utils.py: Handle malformed output where opening <think> tag
  is missing but </think> is present

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

open_notebook/graphs/chat.py

@@ -3,8 +3,10 @@ import sqlite3
 from typing import Annotated, Optional
 
 from ai_prompter import Prompter
-from langchain_core.messages import SystemMessage
+from langchain_core.messages import AIMessage, SystemMessage
 from langchain_core.runnables import RunnableConfig
+
+from open_notebook.utils import clean_thinking_content
 from langgraph.checkpoint.sqlite import SqliteSaver
 from langgraph.graph import END, START, StateGraph
 from langgraph.graph.message import add_messages
@@ -66,7 +68,13 @@ def call_model_with_messages(state: ThreadState, config: RunnableConfig) -> dict
         )
 
     ai_message = model.invoke(payload)
-    return {"messages": ai_message}
+
+    # Clean thinking content from AI response (e.g., <think>...</think> tags)
+    content = ai_message.content if isinstance(ai_message.content, str) else str(ai_message.content)
+    cleaned_content = clean_thinking_content(content)
+    cleaned_message = AIMessage(content=cleaned_content)
+
+    return {"messages": cleaned_message}
 
 
 conn = sqlite3.connect(