chengyongru 0334fa9944 feat(provider): show cache hit rate in /status (#2645)

2026-03-31 10:57:39 +08:00

..

__init__.py

refactor: replace litellm with native openai + anthropic SDKs

2026-03-25 01:58:48 +08:00

anthropic_provider.py

feat(provider): show cache hit rate in /status (#2645)

2026-03-31 10:57:39 +08:00

azure_openai_provider.py

feat: add streaming channel support with automatic fallback

2026-03-23 10:20:41 +08:00

base.py

refactor(provider): preserve extra_content verbatim for Gemini thought_signature round-trip

2026-03-25 10:00:29 +08:00

openai_codex_provider.py

feat: add streaming channel support with automatic fallback

2026-03-23 10:20:41 +08:00

openai_compat_provider.py

feat(provider): show cache hit rate in /status (#2645)

2026-03-31 10:57:39 +08:00

registry.py

fix(providers): make max_tokens and max_completion_tokens mutually exclusive (#2491)

2026-03-27 21:19:23 +08:00

transcription.py

style: unify code formatting and import order

2026-02-28 20:55:43 +08:00