docs: add FAQ section for common questions#3030
Conversation
![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.
Reviewed commit: b4cd2195f3
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".
|
|
||
| ### How do I handle rate limits? | ||
|
|
||
| The SDK includes built-in retry logic with exponential backoff. You can customize retry behavior via the `RunConfig` by setting `max_retries` and configuring the underlying HTTP client. For high-throughput scenarios, consider implementing request queuing or batching. |
There was a problem hiding this comment.
This guidance points users to RunConfig(max_retries=...), but RunConfig does not expose a max_retries field (see src/agents/run_config.py), so following it will raise a constructor error instead of configuring retries. Retry tuning is currently done through model retry settings (for example ModelSettings/ModelRetrySettings) and provider client configuration, so this FAQ answer sends users to a non-functional API path.
Useful? React with 👍 / 👎.
|
|
Thanks for the suggestion, but we prefer covering topics like these on the documentation side rather than README. |
|
Frequently Asked Questions (FAQ)
|
3 participants
Summary
Add a Frequently Asked Questions section to the README to help new users quickly find answers to common setup and usage questions.
Changes
Motivation
New users frequently ask about provider support, rate limits, sandbox agents, and debugging. A FAQ section in the README reduces friction and directs users to the right resources.
Checklist