feature: add an "interject" response option to the "ask" permission's modal (implements #4822) #4844
Conversation
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
- Resolved conflict in processor.ts by preserving interjection logic while adopting shouldBreak config - Interjections will continue to allow model processing - Non-interjection denials will respect the continue_loop_on_deny config flag
… into feat/interjections
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Outdated suggestions cannot be applied.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.
Closes #4822.
This PR adds a new fourth response option to the options presented in the modal dialog produced by the "ask" permission in the TUI: "interject" ("i" key).
When the user hits the "i" key to select the "interject" option, they're prompted to enter their advice for how the model should proceed.
If the user hits enter after entering their advice, the user's interjection is formatted into the error message received by the model, after which it continues processing.
If the user instead hits escape, it behaves as if they'd denied the tool cool.
Step 1: display the option to interject
Step 2: allow the user to enter their interjection/advice
Step 3: model receives the user's advice and continues