github-starred/ollama
2
0
Fork 0
mirror of https://github.com/ollama/ollama.git synced 2026-05-07 00:22:43 -05:00
Code Issues 14.5k Packages Projects Releases 120 Wiki Activity

[GH-ISSUE #12363] Feature Request: Edit Assistant Messages #8214

New Issue
Open
opened 2026-04-12 20:41:37 -05:00 by GiteaMirror · 1 comment
GiteaMirror commented 2026-04-12 20:41:37 -05:00
Owner
Copy Link

Originally created by @willmorong on GitHub (Sep 21, 2025).
Original GitHub issue: https://github.com/ollama/ollama/issues/12363

Recently, I've been using the Ollama app for macOS and noticed there's no option for editing Assistant responses or the system prompt.

I use this feature all the time when models will get some fact or piece of code wrong, and fixing the response manually is a great way to keep future responses correct and on-task. Otherwise, it's pretty useless to continue a conversation once you have to start sending messages hoping to correct the Assistant on something without it forgetting or playing the role of "Assistant who keeps messing up in the same way".

These features are supported by pretty much every other open-source LLM text generation app, and it's quick to implement because nothing new has to be changed in the Ollama API.
OpenRouter (the largest and most popular LLM aggregated service) also has this feature, and combined with branching it makes for a much better dev user-facing experience.

Thanks!

Originally created by @willmorong on GitHub (Sep 21, 2025). Original GitHub issue: https://github.com/ollama/ollama/issues/12363 Recently, I've been using the Ollama app for macOS and noticed there's no option for editing Assistant responses or the system prompt. I use this feature all the time when models will get some fact or piece of code wrong, and fixing the response manually is a great way to keep future responses correct and on-task. Otherwise, it's pretty useless to continue a conversation once you have to start sending messages hoping to correct the Assistant on something without it forgetting or playing the role of "Assistant who keeps messing up in the same way". These features are supported by pretty much every other open-source LLM text generation app, and it's quick to implement because nothing new has to be changed in the Ollama API. OpenRouter (the largest and most popular LLM aggregated service) also has this feature, and combined with branching it makes for a much better dev user-facing experience. Thanks!
GiteaMirror added the appfeature request labels 2026-04-12 20:41:37 -05:00
GiteaMirror commented 2026-04-12 20:41:39 -05:00
Author
Owner
Copy Link

@Zamy846692 commented on GitHub (Jan 18, 2026):

Want this to!

<!-- gh-comment-id:3765750478 --> @Zamy846692 commented on GitHub (Jan 18, 2026): Want this to!
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
amd
api
app
bug
build
cli
cloud
compatibility
context-length
create
docker
documentation
embeddings
feature request
feedback wanted
good first issue
gpt-oss
gpu
harmony
help wanted
image
install
intel
js
launch
linux
macos
memory
mlx
model
needs more info
networking
nvidia
ollama.com
performance
pull-request
Mirrored from GitHub Pull Request
 python
question
registry
rendering
thinking
tools
top
vulkan
windows
wsl
No Label app feature request
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
GiteaMirror ninjasurge
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#8214
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?