refactor: remove assistant message injection support #204
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
Remove the ability to inject synthetic assistant messages for context pruning nudges. This simplifies the codebase to only use user message injection. Reasoning: Injecting assistant messages is risky because it's unknown how different providers handle edge cases like missing reasoning blocks or malformed assistant content. User message injection is safer and more predictable across all providers. Removed: - getLastAssistantMessage() helper - createSyntheticAssistantMessage() function - isReasoningModel state property - chat.params hook for model detection - wrapPrunableToolsAssistant() function - All assistant prompt files (nudge and system)
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Outdated suggestions cannot be applied.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.
Injecting assistant messages is too risky because it's unknown how different providers handle edge cases like missing reasoning blocks or malformed assistant content. User message injection is safer and more predictable across all providers. Seems like all SOTA models are reasoning so this is almost always default behavior anyway with less risk.