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 #4160] [FEAT]: Ability to turn off @agent directive or inject system prompt into @agent workflow #2646

New Issue
Closed
opened 2026-02-22 18:30:35 -05:00 by yindo · 0 comments
yindo commented 2026-02-22 18:30:35 -05:00
Owner
Copy Link
Copy Source

Originally created by @Toddie40 on GitHub (Jul 16, 2025).
Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4160

What would you like to see?

Context

I've been using AnythingLLM for about 6 months now and have been superbly impressed.

I limit the topic of discussion using the workspace system prompt so that discussion remains relevant and the endpoint isn't used for anything other than its purpose.

In testing, we have discovered the following problem...

Problem:

When a user enters the @agent directive, the system prompt is no longer obeyed and so the endpoint can go rogue and discuss anything it wants.

Requests

It would be ace if either:

  • We could disable the @agent directive from specific workspaces, or
  • We could inject the workspace system prompt into the agent system prompt to maintain the system-prompt level guardrails.
Originally created by @Toddie40 on GitHub (Jul 16, 2025). Original GitHub issue: https://github.com/Mintplex-Labs/anything-llm/issues/4160 ### What would you like to see? ## Context I've been using AnythingLLM for about 6 months now and have been superbly impressed. I limit the topic of discussion using the workspace system prompt so that discussion remains relevant and the endpoint isn't used for anything other than its purpose. In testing, we have discovered the following problem... ## Problem: When a user enters the `@agent` directive, the system prompt is no longer obeyed and so the endpoint can go rogue and discuss anything it wants. ## Requests It would be ace if either: - We could disable the `@agent` directive from specific workspaces, **or** - We could inject the workspace system prompt into the agent system prompt to maintain the system-prompt level guardrails.
yindo added the enhancementfeature request labels 2026-02-22 18:30:35 -05:00
yindo closed this issue 2026-02-22 18:30:36 -05:00
yindo changed title from [FEAT]: Ability to turn off @agent directive or inject system prompt into @agent workflow to [GH-ISSUE #4160] [FEAT]: Ability to turn off @agent directive or inject system prompt into @agent workflow 2026-06-05 14:47:43 -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 enhancement feature request
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#2646
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?