feat(returnPrompt)+fix(task): add custom return instructions to the task tool - fix agent conservation in main session on result #4527
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
spoons-and-mirrors
force-pushed
the
feat/task-return-instruction
branch
2 times, most recently
from
3127d71 to
aed55d7
Compare
github-actions
bot
force-pushed
the
dev
branch
3 times, most recently
from
f1dc981 to
3e15a39
Compare
github-actions
bot
force-pushed
the
dev
branch
2 times, most recently
from
df8bdf9 to
0dd5039
Compare
spoons-and-mirrors
force-pushed
the
feat/task-return-instruction
branch
from
409e66d to
6534665
Compare
github-actions
bot
force-pushed
the
dev
branch
from
f8ee907 to
6a9856d
Compare
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Outdated suggestions cannot be applied.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.
the returnPrompt is like a continuation prompt - the subtask can tell the parent session what to do next with its results and keep the agent loop going. it's a more automated command
It makes commands more powerful and augments it with a 2 step workflow capability with a single subtask command which uses the main session agent as a judge of the subtask or w/e you want to make it with the return instructions
This PR also fixes the subtask result message to use the main session agent instead of the child session agent.