Refactor/role based prompt injection #195
Merged
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
…e for non-reasoning Restore user-role injections for thinking/reasoning models while keeping assistant-role injections for non-reasoning models. This improves prompt effectiveness by matching the injection style to the model's capabilities. Changes: - Organize prompts into user/ and assistant/ subdirectories - User prompts use second-person language (for reasoning models) - Assistant prompts use first-person language (for non-reasoning models) - Update prune.ts to select injection role based on isReasoningModel - Remove synthetic user message workaround (no longer needed) Reverts behavior changed in 16b86c7 for reasoning models only.
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Outdated suggestions cannot be applied.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.
use user role for thinking models
use assistant role for non thinking models