Skip to content

Conversation

@Tarquinen
Copy link
Collaborator

@Tarquinen Tarquinen commented Dec 25, 2025

Summary

  • Refactor prompt injection to use user role for reasoning models and assistant role for non-reasoning models
  • Add line range info to read tool display for better context visibility
  • Reorganize prompts into assistant/user subdirectories with improved structure

Full Changelog: v1.0.3...v1.1.0

Tarquinen and others added 9 commits December 23, 2025 23:08
…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.
…injection

Refactor/role based prompt injection
@Tarquinen Tarquinen changed the title Dev v1.1.0 - Role-based prompt injection and read tool improvements Dec 25, 2025
@Tarquinen Tarquinen merged commit 4cb7f98 into master Dec 25, 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