- Apr 21, 2026
- Date parsed from source:Apr 21, 2026
- First seen by Releasebot:Apr 22, 2026
Bug Fixes and Improvements
Windsurf fixes OAuth authentication issues for some MCP servers.
- Fixed OAuth authentication issues for some MCP servers
- Apr 20, 2026
- Date parsed from source:Apr 20, 2026
- First seen by Releasebot:Apr 21, 2026
Bug Fixes and Improvements
Windsurf fixes OAuth regression for some MCP servers and improves Devin Cloud connection reliability.
Fixed a regression with OAuth integration for some MCP servers
Improved reliability of Devin Cloud connections in Windsurf
All of your release notes in one feed
Join Releasebot and get updates from Windsurf and hundreds of other software products.
- Apr 17, 2026
- Date parsed from source:Apr 17, 2026
- First seen by Releasebot:Feb 5, 2026
- Modified by Releasebot:Apr 18, 2026
Bug Fixes and Improvements
Windsurf improves performance with various bug fixes and reliability updates.
- Various bug fixes and performance improvements
- Apr 15, 2026
- Date parsed from source:Apr 15, 2026
- First seen by Releasebot:Apr 16, 2026
- Modified by Releasebot:Apr 16, 2026
Windsurf 2.0
Windsurf introduces Devin Cloud inside Windsurf, letting users delegate tasks from a local session to a cloud agent, review changes and test results in the editor, and manage work in a new Agent Command Center with task-level Spaces. It also brings browser, performance, and stability improvements.
Read the full announcement here.
Devin in Windsurf
- Devin cloud agent available directly inside Windsurf, included with every self-serve plan
- Delegate tasks from a local session to Devin with one click; Devin runs on its own VM
- Review Devin changes and test results without leaving the editor
- Billing is based on your existing quota and extra usage, with up to 50 USD in extra usage added for launching your first Devin Cloud session.
Note: Access to Devin Cloud is rolling out gradually. If you don't see it yet, try logging out of the website and IDE then logging back in.
Devin Cloud is disabled by default for enterprise accounts. Enterprise admins should enable Devin access in their organization settings if they have already purchased Cognition Platform.
Agent Command Center
- New Kanban-style view showing all local and cloud agent sessions, organized by status
- Group agent sessions, PRs, files, and context into task-level Spaces
- Switch between Spaces to switch between tasks
Additional Changes
- Refined Windsurf Browser with toolbar integration and Cascade tool for reading page contents
- Sped up initial load times for the Cascade sidebar
- Improved .gitignore and .codeiumignore handling across the product
- Stability improvements for remote extensions (WSL, SSH, Dev Containers)
- Performance improvements for typing in large active diff zones
- Apr 7, 2026
- Date parsed from source:Apr 7, 2026
- First seen by Releasebot:Apr 8, 2026
Adaptive Fix
Windsurf fixes an adaptive model router bug and restores quota for affected users.
We fixed a bug with the adaptive model router which prevented switching models after the first request.
All users who encountered the bug have had quota reset and overage restored.
Original source - Apr 6, 2026
- Date parsed from source:Apr 6, 2026
- First seen by Releasebot:Apr 7, 2026
Adaptive Model Visibility
Windsurf improves adaptive model visibility in the model picker.
We've improved the visibility of the adaptive model in the model picker.
Original source - Apr 6, 2026
- Date parsed from source:Apr 6, 2026
- First seen by Releasebot:Apr 7, 2026
Introducing Adaptive
Windsurf adds an Adaptive model option and a smarter model picker, helping users stretch quota with dynamic model selection and clearer pricing context. It also shows token rates, prompt cache timing, and token counts in response cards for more transparent usage tracking.
We've made several model packaging changes, with more info here.
Adaptive Model Router
A new Adaptive model option is now available in the model picker. Adaptive intelligently selects the best model for each task, helping you make your quota last longer by avoiding overuse of premium models.
- Availability: Now available to all self-serve users on Pro, Max, and Teams plans.
- Dynamic model selection - Automatically chooses the right underlying model for your task while drawing down quota at a fixed per-token rate.
- Extra usage promo - Beyond your quota, extra usage is offered at 0.50 USD per 1M input tokens, 2.00 USD per 1M output tokens, and 0.10 USD per 1M cache read tokens for the next 2 weeks.
Updated Model Picker with Pricing Context
The model picker now shows token pricing information directly, so you can see the exact rate extra usage is billed at.
- Token pricing display - Per-model input, output, and cache read token rates visible in the picker.
- Prompt cache timer - A new prompt cache timer is integrated into the context window indicator to help you track caching status.
- Token counts in response cards - Response cards after messages now include token counts so you can understand exactly how each message cost was calculated.
- Mar 19, 2026
- Date parsed from source:Mar 19, 2026
- First seen by Releasebot:Mar 27, 2026
Quota Billing
Windsurf adds support for the new quota billing system and shows daily and weekly quota usage in the IDE.
Added support for the new quota billing system
Daily and Weekly quota usage is now displayed directly in the IDE
- Mar 19, 2026
- Date parsed from source:Mar 19, 2026
- First seen by Releasebot:Mar 20, 2026
Bug Fixes and Improvements
Windsurf fixes Mac x64 build issue.
- Fix build for Mac x64
- Mar 17, 2026
- Date parsed from source:Mar 17, 2026
- First seen by Releasebot:Mar 18, 2026
GPT-5.4 Mini
Windsurf releases GPT-5.4 Mini now available starting at 1x credits promo.
GPT-5.4 Mini is now available in Windsurf, starting at 1x credits (promo).
Original source - Mar 12, 2026
- Date parsed from source:Mar 12, 2026
- First seen by Releasebot:Mar 13, 2026
Bug Fixes and Improvements
Windsurf updates with a fix for Apple M5, addressing a device-specific issue.
Fix for Apple M5
Original source - Mar 9, 2026
- Date parsed from source:Mar 9, 2026
- First seen by Releasebot:Mar 10, 2026
- Modified by Releasebot:Mar 13, 2026
Cascade
Windsurf announces a release with performance boosts and stability fixes across Jupyter on WSL, Cascade UI, and MCP, plus enhanced model price notifications, loading SKILL.md files from .windsurf/skills, and enterprise system‑level Skill definitions. Also improves autocomplete, SSH performance, and agent resilience.
Release Notes
- Fix dangling Diff Zones related to Jupyter Notebooks
- Improve Jupyter Notebook performance when running on WSL
- Improve Cascade UI rendering performance
- Fix Cascade agent panel crashes under certain conditions
- Improve notifications for model price changes
- Add support for loading SKILL.md files from the .windsurf/skills/ directory
- Fix AGENTS.md being ignored by Cascade in specific cases
MCP
- Add support for system-level Skill definitions via MDM-managed configs for Enterprise
- Improve context management for MCP servers
Stability & Performance
- Improve autocomplete error handling and performance
- Improve SSH & Remote performance
- Feb 26, 2026
- Date parsed from source:Feb 26, 2026
- First seen by Releasebot:Mar 6, 2026
GPT-5.4
GPT-5.4 arrives in Windsurf with limited-time self-serve pricing across reasoning tiers.
GPT-5.4 is now available in Windsurf with limited-time promotional pricing for self serve users:
- No Reasoning: 1x credits
- Low Reasoning: 1x credits
- Medium Reasoning: 2x credits
- High Reasoning: 3x credits
- Extra High Reasoning: 8x credits
- Feb 26, 2026
- Date parsed from source:Feb 26, 2026
- First seen by Releasebot:Feb 26, 2026
- Feb 25, 2026
- Date parsed from source:Feb 25, 2026
- First seen by Releasebot:Feb 26, 2026
New Model Picker
New model picker groups models by family with a hovercard to toggle variants like reasoning and speed, plus a pin models feature. Cascade, MCP, and platform updates boost reliability, config visibility, and onboarding with OAuth and ARM64 Linux binaries.
We introduced a new model picker that groups models by family and adds a hovercard with toggles for specific variants, like reasoning effort and speed. Separately, we also added the ability to pin models.
Cascade Improvements
- Added POST_CASCADE_RESPONSE_WITH_TRANSCRIPT cascade hook
- Added Cascade hooks configuration visibility on team settings page
- Reduced the priority of Git commits in @ mention search
- Added a windsurf.cascade.readClaudeCodeConfig flag to disable reading Claude configuration
MCP Improvements
- Added an MCP Refresh button
- Auto-trigger OAuth login when adding HTTP/SSE MCP servers
- Fix bugs with parsing on Windows and startup
Platform Improvements
- Merged changes from VS Code 1.108
- Improved startup reliability for Cascade
- Fixed Windows update initialization path that could block updates
- Released binaries for Linux ARM64