[GH-ISSUE #4267] [FEAT]: support reasoning_content in LM Studio provider/connector #2716

Closed
opened 2026-02-22 18:30:55 -05:00 by yindo · 2 comments
Owner

Originally created by @willxy on GitHub (Aug 9, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4267

What would you like to see?

LM Studio (apparently as of version 0.3.9 2025-01-30) has an option to "separate reasoning_content and content in API responses". It looks like anything-llm includes support for reasoning_content in the Generic OpenAI connector, but it looks like it doesn't recognize reasoning_content when talking to an LM Studio provider. Currently, when I enable the option on LM Studio, then anything-llm does not show that reasoning output; and I have to uncheck that option in LM Studio in order to see that content from anything-llm. It would be great to enable this option on an LM Studio server, and see the reasoning output when connected from anything-llm.

Originally created by @willxy on GitHub (Aug 9, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4267 ### What would you like to see? LM Studio (apparently as of version 0.3.9 2025-01-30) has an option to "separate reasoning_content and content in API responses". It looks like anything-llm includes support for reasoning_content in the Generic OpenAI connector, but it looks like it doesn't recognize reasoning_content when talking to an LM Studio provider. Currently, when I enable the option on LM Studio, then anything-llm does not show that reasoning output; and I have to uncheck that option in LM Studio in order to see that content from anything-llm. It would be great to enable this option on an LM Studio server, and see the reasoning output when connected from anything-llm.
yindo added the enhancementfeature request labels 2026-02-22 18:30:55 -05:00
Author
Owner

@rhys-sharpe commented on GitHub (Aug 24, 2025):

I ran into the same thing. LM Studio (0.3.23) gives me reasoning_content over the API, but I can't figure out how to get Anything-LLM (1.8.5-r2) to show the reasoning (at all). I would love to be able to see reasoning output of LM Studio models in Anything-LLM.

@rhys-sharpe commented on GitHub (Aug 24, 2025): I ran into the same thing. LM Studio (0.3.23) gives me reasoning_content over the API, but I can't figure out how to get Anything-LLM (1.8.5-r2) to show the reasoning (at all). I would love to be able to see reasoning output of LM Studio models in Anything-LLM.
Author
Owner

@dev-rand commented on GitHub (Aug 26, 2025):

Same here, but for reasoning LLMs served by ollama (e.g. gpt-oss).

@dev-rand commented on GitHub (Aug 26, 2025): Same here, but for reasoning LLMs served by ollama (e.g. gpt-oss).
yindo changed title from [FEAT]: support reasoning_content in LM Studio provider/connector to [GH-ISSUE #4267] [FEAT]: support reasoning_content in LM Studio provider/connector 2026-06-05 14:48:09 -04:00
yindo closed this issue 2026-06-05 14:48:09 -04:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#2716