feat: chat setting to prevent agents ending or declining to respond - #1185
Open
jacyanthis wants to merge 3 commits into
Open
feat: chat setting to prevent agents ending or declining to respond#1185jacyanthis wants to merge 3 commits into
jacyanthis wants to merge 3 commits into
Conversation
…p-style turn-based chats
# Conflicts: # docs/assets/api/schemas.json # frontend/src/components/stages/group_chat_editor.ts # scripts/deliberate_lab/types.py # utils/src/stages/chat_stage.ts # utils/src/stages/chat_stage.validation.ts
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
This setting prevents LLM agents from ending the chat. When on, agents are not asked for
readyToEndChat(the field is dropped from their structured output), and the backend ignores it if a model returns it anyway. In a turn-based private chat, the agent is also not asked forshouldRespondbecause respondingfalseto that would end the chat.Manual testing as per template
Set up an experiment with (i) a chat stage with
Prevent agents from ending chatchecked and (ii) an agent mediator. Ask the mediator to end the chat (e.g., "We are done now. Please end the chat.").readyToEndChatfield.