haosenwang1018 8de2f8d588 fix: preserve reasoning_content in message sanitization for thinking models ...

_sanitize_messages strips all non-standard keys from messages, including
reasoning_content. Thinking-enabled models like Moonshot Kimi k2.5
require reasoning_content to be present in assistant tool call messages
when thinking mode is on, causing a BadRequestError (#1014).

Add reasoning_content to _ALLOWED_MSG_KEYS so it passes through
sanitization when present.

Fixes #1014

2026-02-24 04:21:55 +08:00

..

__init__.py

feat: implement OpenAI Codex OAuth login and provider integration

2026-02-05 17:39:18 +08:00

base.py

refactor(providers): move empty content sanitization to base class

2026-02-22 18:26:42 +00:00

custom_provider.py

refactor(providers): move empty content sanitization to base class

2026-02-22 18:26:42 +00:00

litellm_provider.py

fix: preserve reasoning_content in message sanitization for thinking models

2026-02-24 04:21:55 +08:00

openai_codex_provider.py

fix: complete ensure_ascii=False and UTF-8 encoding migration

2026-02-20 07:59:32 +00:00

registry.py

fix: change VolcEngine litellm prefix from openai to volcengine

2026-02-22 00:42:41 +08:00

transcription.py

fix: complete loguru native formatting migration across all files

2026-02-20 07:55:34 +00:00