Bharat Sinha

Add no-store, no-cache in Cache-Control headers

23

### Changes - Removed the logic to never use cache if either of `no-cache`/`no-store` was present - Instead they work as follows - `no-cache`: doesn't use cache even if the...

Handle large resource spec being annotated to `last-handled-configuration`

3

### Keywords annotation, spec, last-handled-configuration, finalizers ### Problem When dealing with a resource that has a large `spec`, the operator is throwing an error ``` APIClientError('Pod \"\" is invalid: metadata.annotations:...

Library should handle unexpected exception related to backend

5

## Description When using Redis as a backend, the code doesn't handle any exceptions caused by the backend, i.e., Network/Connectivity related, which results in a 5xx `internal server error`. ###...

Add handling for backend error

4

### Changes - Add a new `exception` folder to store all the custom exception classes - update `core.py` to catch `BaseBackendException` - Add new argument `on_backend_error` to `RateLimitMiddleware` , defaults...

Honor `include` block when loading config from bucket

2

## Title Honor include block when loading config from S3/GCS bucket https://docs.litellm.ai/docs/proxy/config_management#examples-using-include ## Relevant issues Fixes [#10632](https://github.com/BerriAI/litellm/issues/10632) ## Pre-Submission checklist **Please complete all items before asking a LiteLLM maintainer to...

Context overwritten on non-async API route

1

I am using this in fastAPI and when I use this in a route that doesn't use `async` keyword the context is overwitten by the call that responded faster. ```python...