Remove inner message from thread M1 orchestrator #4611
Merged
Conversation
This file contains 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
victordibia
reviewed
Dec 9, 2024
...gentchat/src/autogen_agentchat/teams/_group_chat/_magentic_one/_magentic_one_orchestrator.py
Show resolved
Hide resolved
ekzhu
reviewed
Dec 9, 2024
There was a problem hiding this comment.
Approve as discussed.
Though we should consider unifying the way we treat message threads across group chats. Since tool calls are observed by application, and in SelectorGroupChat the application can specify custom selector function, I
still think it should be included.
ekzhu
approved these changes
Dec 9, 2024
rysweet
pushed a commit
that referenced
this pull request
Dec 10, 2024
remove inner message from thread
ekzhu
pushed a commit
that referenced
this pull request
Dec 10, 2024
remove inner message from thread
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Outdated suggestions cannot be applied.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.
M1 orchestrator does not rely on agent inner messages to decide it's execution. So they they should be ignored here. Each agent is supposed to return the relevant context in their final response.