Skip to content

Conversation

@Tarquinen
Copy link
Collaborator

@Tarquinen Tarquinen commented Dec 26, 2025

Revert assistant message injections, too scary and not well supported by all oauth providers
clean up distillation UI

Tarquinen and others added 7 commits December 25, 2025 21:36
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)
…essage-injection

refactor: remove assistant message injection support
…lation-notification

refactor: consolidate distillation into unified notification
@Tarquinen Tarquinen merged commit a5731e6 into master Dec 26, 2025
1 check passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants