Skip to content

Conversation

@ashwinb
Copy link
Owner

@ashwinb ashwinb commented Oct 27, 2025

Summary

  • reset contextvars after async generator yields to avoid leaking values across SSE requests
  • add regression test verifying provider data context is cleared between streaming requests

Testing

  • python3.12 -m pytest tests/test_provider_data_context.py -q

https://chatgpt.com/codex/tasks/task_e_68951153acec8321a56ae15125fb07be

Copy link

@cursor cursor bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This PR is being reviewed by Cursor Bugbot

Details

You are on the Bugbot Free tier. On this plan, Bugbot will review limited PRs each billing cycle.

To receive Bugbot reviews on all of your PRs, visit the Cursor dashboard to activate Pro and start your 14-day free trial.

build_hf_repo_model_entry(provider_model_id, model_descriptor)
for provider_model_id, model_descriptor in RUNPOD_SUPPORTED_MODELS.items()
] + SAFETY_MODELS_ENTRIES

Copy link

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Bug: Incorrect Parameter Usage in ModelRegistryHelper

The ModelRegistryHelper.init is called with incorrect parameters. It uses the old parameter name stack_to_provider_models_map and passes RUNPOD_SUPPORTED_MODELS (a dict), but ModelRegistryHelper.init expects model_entries (a list of ProviderModelEntry objects). The code creates the correct MODEL_ENTRIES list on lines 48-51 but doesn't use it. The call should be: ModelRegistryHelper.__init__(self, model_entries=MODEL_ENTRIES).

Fix in Cursor Fix in Web

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants