Repository navigation
fix(chat): return scrubbed command output to the agent under every capture policy - #90
Merged
Merged
Conversation
…pture policy Under the default capture_text = "titles", Chat discarded the output of commands the user approved before it reached the agent, so run_command answered with only an exit code. The agent could run a command but never read what it printed, and could not finish the task it asked to run it for. The agent now gets the scrubbed head and tail of the output under every policy. Storage still follows capture_text: titles keeps no command output and no result text in the action log. The chat guide says what is sent.
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Under the default capture_text = "titles", Chat discarded the output of
commands the user approved before it reached the agent, so run_command
answered with only an exit code. The agent could run a command but never
read what it printed, and could not finish the task it asked to run it for.
The agent now gets the scrubbed head and tail of the output under every
policy. Storage still follows capture_text: titles keeps no command output
and no result text in the action log. The chat guide says what is sent.