Skip to main content
Catalyst instruments the OpenAI SDK in both TypeScript and Python. Initialize tracing before constructing clients so the OpenAI prototypes are patched before application calls start.

What Is Captured

  • Chat Completions request and response messages
  • Responses API input and output text
  • Tool call names, IDs, and JSON arguments
  • Tool result messages passed back into later turns
  • JSON schema response format in invocation parameters
  • Model name, finish reason, usage, and token counts

Install

Basic Chat

OpenAI Inside An Agent

Tool Calling

The first model call records the assistant tool call. The second model call records the tool result message and the final answer.
The capture below is the model-side view of tool calling — the request/response the LLM saw. To also capture the caller-side view (the actual function that ran, its input, output, and duration), wrap the tool function in a TOOL span using Manual spans. For a full agent loop, see the Production Agent Example.

Structured Outputs

response_format is included in invocation parameters, so you can inspect which schema constrained the model call.
TypeScript

Responses API

Responses API calls are traced with the same OpenInference attribute families as Chat Completions.
TypeScript