Hua/nanobot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: preserve reasoning_content in message sanitization for thinking models

Browse Source 
_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
This commit is contained in:
haosenwang1018
2026-02-24 04:21:55 +08:00
parent 30361c9307
commit 8de2f8d588
1 changed files with 3 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
nanobot/providers/litellm_provider.py
View File

@@ -12,8 +12,9 @@ from nanobot.providers.base import LLMProvider, LLMResponse, ToolCallRequest
from nanobot.providers.registry import find_by_model, find_gateway
# Standard OpenAI chat-completion message keys; extras (e.g. reasoning_content) are stripped for strict providers.
_ALLOWED_MSG_KEYS = frozenset({"role", "content", "tool_calls", "tool_call_id", "name"})
# Standard OpenAI chat-completion message keys plus reasoning_content for
# thinking-enabled models (Kimi k2.5, DeepSeek-R1, etc.).
_ALLOWED_MSG_KEYS = frozenset({"role", "content", "tool_calls", "tool_call_id", "name", "reasoning_content"})
class LiteLLMProvider(LLMProvider):