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 #3708] [BUG]: When using KoboldCPP, the max response length is always 512, regardless of context size. #2391

New Issue
Closed
opened 2026-02-22 18:29:28 -05:00 by yindo · 1 comment
yindo commented 2026-02-22 18:29:28 -05:00
Owner
Copy Link
Copy Source

Originally created by @SafentisFox on GitHub (Apr 23, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3708

Originally assigned to: @shatfield4 on GitHub.

How are you running AnythingLLM?

AnythingLLM desktop app

What happened?

I'm attempting to use AnythingLLM with KoboldCPP as the provider. No matter what I tried, the max response length is always 512 tokens. No matter the context size.

This, combined with the lack of a "Continue" button makes certain tasks hard, annoying or borderline impossible.

Are there known steps to reproduce?

Connect KoboldCPP. Do any kind of chat. Look at the KoboldCPP console to confirm that the requested response has a maximum of 512 tokens.

Originally created by @SafentisFox on GitHub (Apr 23, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/3708 Originally assigned to: @shatfield4 on GitHub. ### How are you running AnythingLLM? AnythingLLM desktop app ### What happened? I'm attempting to use AnythingLLM with KoboldCPP as the provider. No matter what I tried, the max response length is always 512 tokens. No matter the context size. This, combined with the lack of a "Continue" button makes certain tasks hard, annoying or borderline impossible. ### Are there known steps to reproduce? Connect KoboldCPP. Do any kind of chat. Look at the KoboldCPP console to confirm that the requested response has a maximum of 512 tokens.
yindo added the possible buginvestigating labels 2026-02-22 18:29:28 -05:00
yindo closed this issue 2026-02-22 18:29:28 -05:00
yindo commented 2026-02-22 18:29:28 -05:00
Author
Owner
Copy Link
Copy Source

@staltux commented on GitHub (Oct 3, 2025):

if i chat normal, the context is the defined in the UI (like 4096 in my case), but if i use a agent, the context is limited to 512, this is a bug or is the intended feature?

@staltux commented on GitHub (Oct 3, 2025): if i chat normal, the context is the defined in the UI (like 4096 in my case), but if i use a agent, the context is limited to 512, this is a bug or is the intended feature?
yindo changed title from [BUG]: When using KoboldCPP, the max response length is always 512, regardless of context size. to [GH-ISSUE #3708] [BUG]: When using KoboldCPP, the max response length is always 512, regardless of context size. 2026-06-05 14:46:17 -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 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#2391
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?