Mintplex-Labs/anything-llm
1
0
Fork 0
mirror of https://github.com/Mintplex-Labs/anything-llm.git synced 2026-07-21 01:25:28 -04:00
Code Issues 328 Packages Projects Releases 10 Wiki Activity

[GH-ISSUE #4905] [BUG]: @Agent Context Windows Resets from 96000 to 8192 after request to sumarize large PDF #3086

New Issue
Closed
opened 2026-02-22 18:32:33 -05:00 by yindo · 0 comments
yindo commented 2026-02-22 18:32:33 -05:00
Owner
Copy Link
Copy Source

Originally created by @ABrauser on GitHub (Jan 27, 2026).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4905

How are you running AnythingLLM?

Docker (local)

What happened?

Hello,

i noticed a bug. i have set my Context windows for Ollama to Max Token 96000 in Performance Mode Maximum.
when i now ask @agent to sumarize a specific file he has in his workspace. he starts -> ollama ps -> with gpt-oss:120b and a context window of 96000. after several seconds the context window drops down ot 8192 and the agant does not seem to react anymore and replies after 2-3 minutes that there is a fetchfailed. and i should be sure that the file is there. when i ask @agent "What for files do you have" he list all the files including the one he should sumarize.

does someone have a clue what im doing wrong?

for a test i have set the following parameter to the ollama service:

[Service]
Environment="OLLAMA_NUM_CTX=32768"

but that doesnt avoid that gpt-oss:120b get reloaded with a too small context window.

btw. im using the Dell Pro Max GB10 - aka. DGX Spark

Are there known steps to reproduce?

No response

Originally created by @ABrauser on GitHub (Jan 27, 2026). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4905 ### How are you running AnythingLLM? Docker (local) ### What happened? Hello, i noticed a bug. i have set my Context windows for Ollama to Max Token 96000 in Performance Mode Maximum. when i now ask @agent to sumarize a specific file he has in his workspace. he starts -> ollama ps -> with gpt-oss:120b and a context window of 96000. after several seconds the context window drops down ot 8192 and the agant does not seem to react anymore and replies after 2-3 minutes that there is a fetchfailed. and i should be sure that the file is there. when i ask @agent "What for files do you have" he list all the files including the one he should sumarize. does someone have a clue what im doing wrong? for a test i have set the following parameter to the ollama service: [Service] Environment="OLLAMA_NUM_CTX=32768" but that doesnt avoid that gpt-oss:120b get reloaded with a too small context window. btw. im using the Dell Pro Max GB10 - aka. DGX Spark ### Are there known steps to reproduce? _No response_
yindo added the possible bug label 2026-02-22 18:32:33 -05:00
yindo closed this issue 2026-02-22 18:32:33 -05:00
yindo changed title from [BUG]: @Agent Context Windows Resets from 96000 to 8192 after request to sumarize large PDF to [GH-ISSUE #4905] [BUG]: @Agent Context Windows Resets from 96000 to 8192 after request to sumarize large PDF 2026-06-05 14:50:13 -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 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#3086
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?