feat: add render_turn callback for dynamic agent configuration - #527
Open
dheerapat wants to merge 7 commits into
Open
feat: add render_turn callback for dynamic agent configuration#527dheerapat wants to merge 7 commits into
dheerapat wants to merge 7 commits into
Conversation
dheerapat
changed the title
dheerapat
marked this pull request as ready for review
August 1, 2026 20:57
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Agent loops currently lock the model, system prompt, and tool set for the entire run. There's no way to change what an agent can see or use between turns of a single conversation.
Workflows that need conditional capabilities, a support agent that only gets escalation tools after verifying a customer, or a triage agent that switches models mid-task, have to rebuild the harness between messages or reload it entirely.