Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-19 14:13:35 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #5711] [BUG]: erratic deepseek-v4-flash (The agent model failed to respond: 400 The reasoning_content) #5249

New Issue
Closed
opened 2026-06-05 14:52:55 -04:00 by yindo · 1 comment
yindo commented 2026-06-05 14:52:55 -04:00
Owner
Copy Link
Copy Source

Originally created by @ohromeo on GitHub (May 27, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5711

Originally assigned to: @shatfield4 on GitHub.

How are you running AnythingLLM?

Docker (local)

What happened?

throwing different commands at v4-flash return erratic results: (these all work with the -chat model)

the "s;lash" commands are now executing..
simple commands it struggles? (not sure if its my restrictive prompt), complex questions appear be working ("explain in layman's terms the Accessibility_Policy_Final.pdf", /explain , /persuade /grammar /translate -etc all good)

Image Image Image Image Image Image

Are there known steps to reproduce?

see above examples

LLM Provider & Model (if applicable)

deepseek - deekseek-v4-flash

Embedder Provider & Model (if applicable)

default

Originally created by @ohromeo on GitHub (May 27, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/5711 Originally assigned to: @shatfield4 on GitHub. ### How are you running AnythingLLM? Docker (local) ### What happened? throwing different commands at v4-flash return erratic results: (these all work with the -chat model) the "s;lash" commands are now executing.. simple commands it struggles? (not sure if its my restrictive prompt), complex questions appear be working ("explain in layman's terms the Accessibility_Policy_Final.pdf", /explain , /persuade /grammar /translate -etc all good) <img width="978" height="371" alt="Image" src="https://github.com/user-attachments/assets/835a00cc-0c15-4e70-b02c-be67fa3ebf19" /> <img width="1067" height="462" alt="Image" src="https://github.com/user-attachments/assets/05353890-c767-4f19-8e70-0bf16e64f31a" /> <img width="948" height="435" alt="Image" src="https://github.com/user-attachments/assets/55effe62-1454-41f6-83e8-e2f794ed3b99" /> <img width="978" height="377" alt="Image" src="https://github.com/user-attachments/assets/79473789-e181-4454-88a1-25048c335a49" /> <img width="973" height="378" alt="Image" src="https://github.com/user-attachments/assets/ab6c7136-40e6-49fb-b1b4-73180f726e65" /> <img width="1031" height="567" alt="Image" src="https://github.com/user-attachments/assets/aebbacb3-d478-4946-be2d-0aacf78ab71e" /> ### Are there known steps to reproduce? see above examples ### LLM Provider & Model (if applicable) deepseek - deekseek-v4-flash ### Embedder Provider & Model (if applicable) default
yindo added the possible buginvestigating labels 2026-06-05 14:52:55 -04:00
yindo closed this issue 2026-06-05 14:52:55 -04:00
yindo commented 2026-06-05 14:52:55 -04:00
Author
Owner
Copy Link
Copy Source

@shatfield4 commented on GitHub (May 27, 2026):

I'm still unable to reproduce this bug. We are aware that multiple users are having this problem with multi-turn agent tool calls but I still am not seeing any crash at all. Are you able to provide exact instructions on what steps you took to consistently reproduce this bug?

I see that you are on the docker version of AnythingLLM using the Deepseek LLM provider with deepseek-v4-flash model (which is what I was throughly testing with as well).

Make sure you are on the latest release and please also provide OS as well since this may help us narrow down where this problem is coming from.

<!-- gh-comment-id:4559843662 --> @shatfield4 commented on GitHub (May 27, 2026): I'm still unable to reproduce this bug. We are aware that multiple users are having this problem with multi-turn agent tool calls but I still am not seeing any crash at all. Are you able to provide exact instructions on what steps you took to consistently reproduce this bug? I see that you are on the docker version of AnythingLLM using the Deepseek LLM provider with `deepseek-v4-flash` model (which is what I was throughly testing with as well). Make sure you are on the latest release and please also provide OS as well since this may help us narrow down where this problem is coming from.
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 investigating 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#5249
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?