Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension


Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
5 changes: 0 additions & 5 deletions .changeset/nine-cameras-applaud.md

This file was deleted.

5 changes: 0 additions & 5 deletions .changeset/shiny-mugs-care.md

This file was deleted.

5 changes: 0 additions & 5 deletions .changeset/tame-carpets-bake.md

This file was deleted.

5 changes: 0 additions & 5 deletions .changeset/wise-bats-perform.md

This file was deleted.

5 changes: 0 additions & 5 deletions .changeset/wise-pears-join.md

This file was deleted.

5 changes: 0 additions & 5 deletions .changeset/young-wolves-add.md

This file was deleted.

19 changes: 19 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
@@ -1,5 +1,24 @@
# Roo Code Changelog

## [3.8.0]

- Add opt-in telemetry to help us improve Roo Code faster (thanks Cline!)
- Fix terminal overload / gray screen of death, and other terminal issues
- Add a new experimental diff editing strategy that applies multiple diff edits at once (thanks @qdaxb!)
- Add support for a .rooignore to prevent Roo Code from read/writing certain files, with a setting to also exclude them from search/lists (thanks Cline!)
- Update the new_task tool to return results to the parent task on completion, supporting better orchestration (thanks @shaybc!)
- Support running Roo in multiple editor windows simultaneously (thanks @samhvw8!)
- Make checkpoints asynchronous and exclude more files to speed them up
- Redesign the settings page to make it easier to navigate
- Add credential-based authentication for Vertex AI, enabling users to easily switch between Google Cloud accounts (thanks @eonghk!)
- Update the DeepSeek provider with the correct baseUrl and track caching correctly (thanks @olweraltuve!)
- Add a new “Human Relay” provider that allows you to manually copy information to a Web AI when needed, and then paste the AI's response back into Roo Code (thanks @NyxJae)!
- Add observability for OpenAI providers (thanks @refactorthis!)
- Support speculative decoding for LM Studio local models (thanks @adamwlarson!)
- Improve UI for mode/provider selectors in chat
- Improve styling of the task headers (thanks @monotykamary!)
- Improve context mention path handling on Windows (thanks @samhvw8!)

## [3.7.12]

- Expand max tokens of thinking models to 128k, and max thinking budget to over 100k (thanks @monotykamary!)
Expand Down
4 changes: 2 additions & 2 deletions package-lock.json

Some generated files are not rendered by default. Learn more about how customized files appear on GitHub.

2 changes: 1 addition & 1 deletion package.json
Original file line number Diff line number Diff line change
Expand Up @@ -3,7 +3,7 @@
"displayName": "Roo Code (prev. Roo Cline)",
"description": "A whole dev team of AI agents in your editor.",
"publisher": "RooVeterinaryInc",
"version": "3.7.12",
"version": "3.8.0",
"icon": "assets/icons/rocket.png",
"galleryBanner": {
"color": "#617A91",
Expand Down
Loading