Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 22:23:50 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #3762] [BUG]: LiteLLM Preference and agent configuration. #2421

New Issue
Closed
opened 2026-02-22 18:29:37 -05:00 by yindo · 2 comments
yindo commented 2026-02-22 18:29:37 -05:00
Owner
Copy Link
Copy Source

Originally created by @zuicis on GitHub (May 3, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3762

How are you running AnythingLLM?

Docker (remote machine)

What happened?

If I specify the provider in the LLM Preference section, for example, LiteLLM with the GPT-4.1 model, and in one workspace I indicate that agents should use LiteLLM Claude Haiku, while in another workspace I specify LiteLLM with LiteLLM Claude Sonnet, then the workspaces still use the model specified in the preferences.

  • According to my understanding, the agent’s specified configuration should be effective regardless of what is set in the preferences

Are there known steps to reproduce?

On the LiteLLM side connect multiple API providers with their models (Claude - Haiku/Sonnet, OpenAI - GPT-4.1 Mini / O1-Min, xAi - Grok-2). The connected API models are grouped together, and one virtual API key is assigned, which will be used by Anything LLM.

Originally created by @zuicis on GitHub (May 3, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3762 ### How are you running AnythingLLM? Docker (remote machine) ### What happened? If I specify the provider in the LLM Preference section, for example, LiteLLM with the GPT-4.1 model, and in one workspace I indicate that agents should use LiteLLM Claude Haiku, while in another workspace I specify LiteLLM with LiteLLM Claude Sonnet, then the workspaces still use the model specified in the preferences. - According to my understanding, the agent’s specified configuration should be effective regardless of what is set in the preferences ### Are there known steps to reproduce? On the LiteLLM side connect multiple API providers with their models (Claude - Haiku/Sonnet, OpenAI - GPT-4.1 Mini / O1-Min, xAi - Grok-2). The connected API models are grouped together, and one virtual API key is assigned, which will be used by Anything LLM.
yindo added the possible bugneeds info / can't replicate labels 2026-02-22 18:29:37 -05:00
yindo closed this issue 2026-02-22 18:29:37 -05:00
yindo commented 2026-02-22 18:29:37 -05:00
Author
Owner
Copy Link
Copy Source

@timothycarambat commented on GitHub (May 3, 2025):

Can you screenshot where you are defining a workspace should be using a specific model for agents? You may be setting the wrong configuration. Whatever you set in the workspace's agent config is the model/provider that will be used when calling @agent but it may not be the model used when just running regular chats.

@timothycarambat commented on GitHub (May 3, 2025): Can you screenshot where you are defining a workspace should be using a specific model for agents? You may be setting the wrong configuration. Whatever you set in the workspace's agent config is the model/provider that will be used when calling `@agent` but it may not be the model used when just running regular chats.
yindo commented 2026-02-22 18:29:37 -05:00
Author
Owner
Copy Link
Copy Source

@zuicis commented on GitHub (May 6, 2025):

I apologize, it looks like everything is as it should be. - changes take effect on new threads and after the /reset command

Image
Image
Image

.

@zuicis commented on GitHub (May 6, 2025): I apologize, it looks like everything is as it should be. - changes take effect on new threads and after the /reset command ![Image](https://github.com/user-attachments/assets/cb4ada78-9142-4ab9-8f5e-41fae794b456) ![Image](https://github.com/user-attachments/assets/3bb2c3ad-dd7b-419d-b149-cf55a3b1021d) ![Image](https://github.com/user-attachments/assets/f5523187-4407-45e2-8153-24bb75e7aa11) .
yindo changed title from [BUG]: LiteLLM Preference and agent configuration. to [GH-ISSUE #3762] [BUG]: LiteLLM Preference and agent configuration. 2026-06-05 14:46:26 -04:00
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Desktop
Docker
Integration Request
Integration Request
OS: Linux
OS: Mobile
OS: Windows
UI/UX
blocked
bug
bug
core-team-only
documentation
duplicate
embed-widget
enhancement
feature request
github_actions
good first issue
investigating
needs info / can't replicate
possible bug
pull-request
Mirrored from GitHub Pull Request
 question
stage: specifications
wontfix
No Label needs info / can't replicate possible bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: Mintplex-Labs/anything-llm#2421
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?