1.0.94-5

Fixed

• copilot mcp add recovers cleanly after interrupted MCP config initialization

1.0.94-4

Fixed

• MCP enable/disable now works before server discovery without starting MCP servers
• Assisted permissions send visible shell code to the permission judge instead of requiring unnecessary manual approval

1.0.94-3

Added

• Add Claude Haiku 5.5 to model selection and --model completions

Fixed

• Show a policy warning when startup bypass-permission flags are suppressed by managed settings

1.0.94-2

Fixes and changes

1.0.94-1

Fixed

• Clicking a Sessions sidebar row now reliably switches sessions during split-view reconciliation

1.0.94-0

Improved

• Show update guidance when managed settings request a newer CLI version without blocking normal prompts
• Managed policy can disable Assisted Permissions and keep sessions in Manual Approval mode.

1.0.93

2026-10-07

• Add enterprise permissions.limitTo to enforce managed domain boundaries for network requests
• Run safe /user commands immediately during active turns, reject unsafe remote commands during active turns without opening dialogs, and queue commands advertised by relay hosts
• Plugin skill commands stay available after reloading enabled plugins
• Sandbox local-network allowlists now include localhost and loopback hosts.
• GitHub.com Connector users can expand GitHub CLI permissions in place and retry connections without switching sign-in methods.
• Honor --context long_context at startup and show accurate context allowance in /context
• Connecting a Connector without the required GitHub scope now prompts to update your authorization instead of failing with an authentication error
• Warmed language servers stay running across LSP requests when sandboxing is disabled
• Clicking a truncated compact shell command expands it
• Command sandboxing is available to all users via /sandbox and --sandbox.
• MCP server configuration changes apply between turns without restarting the session.
• Model picker updates the recommended list to prioritize GPT-6.1 Sol, GPT-6 Astra/Luna, and Claude 5.5 models.
• Read user settings only from ~/.copilot/settings.json; user-setting keys in ~/.copilot/config.json are ignored.

1.0.93-4

Improved

• Command sandboxing is available to all users via /sandbox and --sandbox.

Fixed

• Run safe /user commands immediately during active turns, reject unsafe remote commands during active turns without opening dialogs, and queue commands advertised by relay hosts
• Plugin skill commands stay available after reloading enabled plugins
• Sandbox local-network allowlists now include localhost and loopback hosts.

1.0.93-3

Improved

• MCP server configuration changes apply between turns without restarting the session.

1.0.93-2

Added

• Add enterprise permissions.limitTo to enforce managed domain boundaries for network requests

Improved

• Model picker updates the recommended list to prioritize GPT-6.1 Sol, GPT-6 Astra/Luna, and Claude 5.5 models.

Fixed

• GitHub.com Connector users can expand GitHub CLI permissions in place and retry connections without switching sign-in methods.
• Honor --context long_context at startup and show accurate context allowance in /context
• Connecting a Connector without the required GitHub scope now prompts to update your authorization instead of failing with an authentication error

Removed

• Read user settings only from ~/.copilot/settings.json; user-setting keys in ~/.copilot/config.json are ignored.