Hi, I'm currently using LangSmith with a langgraph.prebuilt.create_react_agent to capture traces. I'm using the Anthropic Claude Sonnet 4.5 model with interleaved thinking enabled. I am able to see ...
When using LiteLLM’s /responses endpoint with Claude models via AWS Bedrock, the transformer caches each tool call in TOOL_CALLS_CACHE. On the next turn, if the client resends the assistant ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results
Feedback