Hi Phoenix Support, I have a question in using phoenix for agent tracing. I’m tracing my agent application in Phoenix, and each node exchanges input and output as a JSON-formatted state. Phoenix is tracing that—but does Phoenix have any functionality like pretty print or a typical JSON viewer, where I can expand and collapse each key? Or is that not supported?
💡 Hint: Mention RunLLM in the thread for followups.
Can you try updating the instrumentor to the latest version, i.e. pip install 'openinference-instrumentation-langchain>=0.1.49' The reason it’s not displaying nicely is that the objects were previously captured as strings.
Great. Thanks for testing! Yes, we unpack the object and serialized them into json
