astream lose when useing deep-Thinking model

### Checked other resources - [x] This is a bug, not a usage question. - [x] I added a clear and descriptive title that summarizes this issue. - [x] I used the GitHub search to find a similar question and didn't find it. - [x] I am sure that this is a bug in LangChain rather than my code. - [x] The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package). - [x] This is not related to the langchain-community package. - [x] I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS. ### Package (Required) - [x] langchain - [ ] langchain-openai - [ ] langchain-anthropic - [ ] langchain-classic - [ ] langchain-core - [ ] langchain-cli - [ ] langchain-model-profiles - [ ] langchain-tests - [ ] langchain-text-splitters - [ ] langchain-chroma - [ ] langchain-deepseek - [ ] langchain-exa - [ ] langchain-fireworks - [ ] langchain-groq - [ ] langchain-huggingface - [ ] langchain-mistralai - [ ] langchain-nomic - [ ] langchain-ollama - [ ] langchain-perplexity - [ ] langchain-prompty - [ ] langchain-qdrant - [ ] langchain-xai - [ ] Other / not sure / general ### Example Code (Python) ```python import asyncio from langchain.agents import create_agent from langchain_openai import ChatOpenAI agent = create_agent( model= ChatOpenAI( model = settings.openai_model, # replace it with yours (A deep‑thinking model — I’m using Qwen3‑4B.) base_url = settings.openai_base_url, # replace it with yours api_key = settings.openai_api_key, # replace it with yours temperature = 0, max_tokens = 1024, ), system_prompt="You are a smart AI assistant.", ) async def main(): async for token, metadata in agent.astream( input={"input": "who are you"}, stream_mode="messages" ): content_blocks = token.content_blocks target_text = content_blocks[0].get('text', '').strip() if targe…