Repository navigation
Conversation
Member
|
Thank you! We have a rudimentary agent-shell integration I slopped together for a demo yesterday here: It's ultra barebones, but it might help :) I would love to merge your (definitely better) integration to this repo, if you are up for it |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
I am currently writing an integration with agent-shell, the most popular acp client for GNU Emacs. One of the first problems I encountered was the fact that model thinking is separated into hundreds (or thousands) of separate thought blocks, each only containing a single token. This is caused by the ACP-integration sending a blank
agent_message_chunkbetween eachagent_thought_chunk. This adds a filter (and corresponding test) to remove such blank messages.There might be a more elegant fix for this if anyone can find the source for the empty messages, but I am not all that familiar with this codebase.