Skip to content

Show reasoning tokens in telemetry #1328

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Closed
bruffridge opened this issue May 14, 2025 · 1 comment
Closed

Show reasoning tokens in telemetry #1328

bruffridge opened this issue May 14, 2025 · 1 comment
Labels
enhancement New feature or request

Comments

@bruffridge
Copy link

bruffridge commented May 14, 2025 •
edited
Loading

I want to be able to see the reasoning tokens generated by Claude 3.7. This is supported by LiteLLM.

How I setup the model used by CodeAgent:

model_params = {"thinking": {
    "type": "enabled",
    "budget_tokens": 4000
}}
model = LiteLLMModel(model_id="bedrock/us.anthropic.claude-3-7-sonnet-20250219-v1:0", **model_params)

Output in Phoenix
Image
@bruffridge bruffridge added the enhancement New feature or request label May 14, 2025
@bruffridge bruffridge changed the title Verbose mode for debugging LLM calls and outputs (including reasoning tokens) Show reasoning tokens in telemetry May 14, 2025
@bruffridge
Copy link
Author

Moved issue to the right repository: Arize-ai/openinference#1641

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
enhancement New feature or request
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
1 participant
@bruffridge