feat: enable interrupt for long-running commands in textual UI (mini -v) #568
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
… mode Implements immediate interrupt functionality for interactive textual mode, matching the behavior of interactive.py. When the user presses 'i', the agent now interrupts immediately, even during long-running commands. Changes: - Modified execute_action() to use subprocess.Popen() with polling instead of env.execute(), enabling process termination on interrupt - Added _current_process tracking to _TextualAgent - Modified action_interrupt() to terminate running subprocess before injecting KeyboardInterrupt - Added KeyboardInterrupt handlers in query() and execute_action() - Added tests for interrupt during command execution The interrupt now works immediately for: - Long-running commands (e.g., sleep) - LLM queries - Any point in the agent loop Fixes SWE-agent#332
Codecov Report❌ Patch coverage is
🚀 New features to boost your workflow:
|
Documents the new 'i' keybinding that allows users to interrupt the agent immediately during execution, including long-running commands.
klieret
requested changes
Oct 9, 2025
| if result: # Non-empty string means rejection | ||
| raise NonTerminatingException(f"Command not executed: {result}") | ||
| return super().execute_action(action) | ||
|
|
Member
There was a problem hiding this comment.
no, we can't do this like that,this completely bypasses the environment setup (we might not be running locally but in a docker container for example). I thought it might be possible to just catch the keyboardinterrupt at the same place? Take a look at how this is done for the non-visual interactive mode
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.
Summary
Implements immediate interrupt functionality for interactive textual mode, matching the behavior of interactive.py. When the user presses 'i', the agent now interrupts immediately, even during long-running commands.
Changes:
The interrupt now works for:
Closes #332