Skip to content

Conversation

@mrubens
Copy link
Collaborator

@mrubens mrubens commented Aug 19, 2025

Important

Add changeset for v3.25.18 with fixes for reasoning usage and model deduplication, and new features including Sonic model support.

  • Fixes:
    • Respect enableReasoningEffort setting for reasoning usage.
    • Prevent duplicate LM Studio models with case-insensitive deduplication.
  • Features:
    • Add support for Sonic model.
    • Simplify ask_followup_question prompt documentation.
    • Add read_file tool for single-file-only models.

This description was created by Ellipsis for 4d731bc. You can customize this summary. It will automatically update as commits are pushed.

@mrubens mrubens merged commit 5d54ce9 into main Aug 19, 2025
7 of 8 checks passed
@mrubens mrubens deleted the release/v3.25.18 branch August 19, 2025 18:04
@github-project-automation github-project-automation bot moved this from New to Done in Roo Code Roadmap Aug 19, 2025
@github-project-automation github-project-automation bot moved this from PR [Needs Review] to Done in Roo Code Roadmap Aug 19, 2025
@dosubot dosubot bot added size:XS This PR changes 0-9 lines, ignoring generated files. changelog-ready labels Aug 19, 2025
Copy link
Contributor

@roomote roomote bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Thank you for your contribution! I've reviewed the changeset and have some suggestions for improvement to enhance consistency and traceability.

"roo-cline": patch
---

- Fix: respect enableReasoningEffort setting when determining reasoning usage (#7048 by @ikbencasdoei, PR by @app/roomote)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I noticed the attribution format varies between entries. The first two use "by @username, PR by @app/roomote" while the last three use "thanks @username!". Would it be better to standardize this for consistency?

For example, all entries could follow either:

What do you think?


- Fix: respect enableReasoningEffort setting when determining reasoning usage (#7048 by @ikbencasdoei, PR by @app/roomote)
- Fix: prevent duplicate LM Studio models with case-insensitive deduplication (#6954 by @fbuechler, PR by @daniel-lxs)
- Add support for Sonic model (thanks @mrubens!)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

These feature entries don't include issue or PR references like the fixes above do. Including references (if they exist) would help with traceability. For instance:

  • Add support for Sonic model (#XXXX, thanks @mrubens!)
  • Feat: simplify ask_followup_question prompt documentation (#XXXX, thanks @daniel-lxs!)
  • Feat: simple read_file tool for single-file-only models (#XXXX, thanks @daniel-lxs!)

- Fix: prevent duplicate LM Studio models with case-insensitive deduplication (#6954 by @fbuechler, PR by @daniel-lxs)
- Add support for Sonic model (thanks @mrubens!)
- Feat: simplify ask_followup_question prompt documentation (thanks @daniel-lxs!)
- Feat: simple read_file tool for single-file-only models (thanks @daniel-lxs!)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Consider adding more context to this feature description? For example, what specific use case does this enable or what problem does it solve for single-file-only models? This would help users understand the value of this addition.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

changelog-ready size:XS This PR changes 0-9 lines, ignoring generated files.

Projects

Archived in project

Development

Successfully merging this pull request may close these issues.

2 participants