v0.14.1

This is primarily a bugfix release with one quality-of-life feature. First, the fun stuff:

Mux now supports enabling notifications for all final responses in a workspace, toggleable in the workspace header and defaulting to off:

See docs here.

🛠️ Fixes

• Fixed bug where /fork on a local workspace would create a broken worktree workspace
• Fixed two bugs related to previousResponseId handling with OpenAI models over Mux Gateway
  • gpt-5.2-codex should now be usable over Gateway
• Fixed incorrect context window stats for gpt-5.2-codex, removing "output reserve" indication which was added with bad underlying reasoning
• Improved New Project flow
  • If project directory doesn't exist, Mux will transparently create it for you
  • If you enter a project name like "cool-vibe-project", Mux will place it into "~/.mux/projects/cool-vibe-project" instead of "/cool-vibe-project"
    • Psychos out there can still place projects at the root by entering "/cool-vibe-project" in the New Project flow

v0.14.0

🌃 Highlights

You can now use slash commands with skills.

For example, if you have a skill called pull-requests, you can run:

/pull-requests open PR

Mux will automatically load that skill into the prompt before sending your message:

---

We now warn when the auto-compact threshold is higher than the model’s output reserve, helping you avoid “context exceeded” errors:

Additionally, if compaction fails on GPT-5.2 or Sonnet 4.5, we automatically retry once with more permissive options:

• GPT-5.2: Auto Truncate enabled
• Sonnet 4.5: 1M context enabled

No configuration required—this should work well out of the box.

---

We made several improvements to the review flow, including:

• Highlighted lines stay highlighted when the review is staged
• You can add review comments from the FileViewer (not just diffs)

Misc.

• Minor improvements to the mobile layout (more coming soon)
• Fixed a thinking-level persistence bug when using XHIGH
• New /debug-llm-request command to show the full, unmodified payload of the most recent model request for debugging and analysis

v0.13.1

This release is a hotfix primarily for improved Windows support.

It also:

• Improves compaction performance for GPT-5.2/Gemini
• Adds onboarding wizard
• Implements /fork for Local workspaces

v0.13.0

Highlights

• PR status and link now available in real-time in the workspace chat view:
  
  (requires authenticated gh CLI)

• Added file explorer and minimal file viewer:
  

• We now support a first-class Coder Workspaces runtime (docs)

• Built-in support for Codex 5.2 now available (/model codex)

• Fixed a variety of Windows bugs

v0.12.2

This release is a hotfix to restore terminal input functionality (see #1586)

v0.12.1

Features

• Login with Mux Gateway is now live!
  If you have a coupon code you can still redeem them at https://gateway.mux.coder.com/
  When launching mux you can login to the gateway to automatically use the vouchers.

You can also join our discord to talk mux and request some tokens for testing!

Fixes

• improvements to review pane - file status, CRLF handling and inline review comments
• revamp of the provider menu for easier management of custom models

Full Changelog: v0.12.0...v0.12.1

v0.12.0

🏙️ Highlights

We now support integrated terminals in the right sidebar, with drag-and-drop tiling and resizing:

Terminals persist on the backend, so mux server users can leave a tab, come back later, and resume the session exactly where they left off.

---

New runtime: Docker!

---

mux run has been given a makeover to make it useful for automation and CI. See:

• mux run docs
• Example GitHub Actions workflow

🛠️ Fixes

• Unified handling of environment variables (docs)
• Better default $PATH on macOS using common shell profiles (49176ed39)

v0.11.1

Primarily a hotfix for 5dd8529 — fixing a rare bug where Anthropic reasoning would be effectively disabled sometimes on long-running chats.

Also, sneaks in e4e41f7 which embeds the Mux docs as a built-in skill. So, users can ask Mux about itself for support.

v0.11.0

🌃 Highlights

Project now support customizable sections for organization:

You can share plans and other assistant outputs from Mux via the e2e encrypted mux.md:

Idle-compaction settings moved next to usage-based auto-compact slider:

When reaching a context exceeded error, we now give you a more useful retry operation if you have a model available with a higher context limit:

See also:

• Fully customizable Agents (docs)
• Mux can notify via new notify tool, just instruct via prompt (docs)
• Tool hooks! (docs)
• You can tag files with "@" in the chat which will include them in your context

🛠️ Fixes

• Fixed bug where SSH workspace sub-agents had unexpected git state (b4125da)
• Fixed thundering herd issue where enabling idle compaction could lead to dozens of old workspaces undergoing simultaneous compaction
  • New behavior: only one idle compaction runs at a time (f24db30)
• Many performance improvements all around the app

v0.10.1

What’s Changed

🚀 Features

• Add a Keybinds section to Settings (improves discoverability of shortcuts).
• Add simulateFileModifyingToolEnd for UI testing.
• Add model-only TODO reminder notifications.
• Add VS Code secondary sidebar mux chat view (better VS Code integration).
• Add PTC subagent support plus compatibility improvements.

⚡ Performance

• Prevent sidebar re-renders during streaming (reduces UI churn / improves responsiveness).

🐛 Fixes

• Bug fixes around PTC, UI, etc.