huanghuoguoguo de61b5d368 refactor(provider): use LiteLLM as unified LLM requester backend ...

- Replace 23+ individual requester implementations with unified litellmchat.py
  - Add litellm_provider field to 27 YAML manifests for provider routing
  - Delete redundant requester subclasses
  - Add unit tests for LiteLLMRequester (29 tests)
  - Fix num_retries parameter name (was max_retries)
  - Fix exception handling order for subclass exceptions

  LiteLLM provides unified API for 100+ providers, eliminating need for
  provider-specific requesters.

2026-04-24 22:32:33 +08:00

23 KiB

Raw Blame History

View Raw