[Feature] Together AI provider, Synthetic datasets, and QPS-based Traffic Pattern #95
Conversation
waitong94
changed the title
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
ℹ️ About Codex in GitHub
Codex has been enabled to automatically review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
When you sign up for Codex through ChatGPT, Codex can also answer questions or update the PR, like "@codex address that feedback".
| self.headers = None | ||
| if auth_provider and hasattr(auth_provider, "get_credentials"): | ||
| token = auth_provider.get_credentials() | ||
| if token: | ||
| self.headers = { | ||
| "Authorization": f"Bearer {token}", | ||
| "Content-Type": "application/json", |
There was a problem hiding this comment.
Open-loop mode unconditionally builds headers as {"Authorization": f"Bearer {token}"} using whatever get_credentials() returns. For providers where get_credentials() returns a dict or uses non-bearer headers (e.g., Azure OpenAI returns { "api_key": ... }, AWS Bedrock returns AWS credential dict), this sends an invalid Authorization header like Bearer {'api_key': ...} and omits the provider-specific header (api-key, SigV4, etc.), so every request in non-locust mode will be rejected with 401/403. This makes the new open-loop runner unusable for any backend that isn't plain bearer-token auth.
Useful? React with 👍 / 👎.
4 participants
Description
Please provide a brief description of the changes in this PR.
What type of PR is this?
Related Issue
Fixes #<issue_number>
Changes Made in this PR
How Has This Been Tested?
Checklist
git pull origin main)make checkto ensure code is properly formatted and passes all lint checksmake testormake test_changedto verify test coverage (~90% required)Additional Information
Add any other context, screenshots, or information about the PR here.