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

..

config

feat: add extra webhook prefix config

2026-03-13 12:06:22 +08:00

pipeline

fix(n8n-runner): fix output_key not applied when n8n returns plain JSON (#2119)

2026-04-16 22:15:57 +08:00

platform

Feat: bot message routing (#2100)

2026-04-03 23:56:58 +08:00

plugin

Feat/rag plugin (#1995)

2026-03-06 21:54:38 +08:00

provider

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

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

storage

chore: Add PyPI package support for uvx/pip installation (#1764)

2025-11-16 19:53:01 +08:00

__init__.py

feat: add comprehensive unit tests for pipeline stages (#1701)

2025-10-01 10:56:59 +08:00