Workspace Settings
Frontend RefactorGeneral Settings
Configure the basic settings for your workspace.
Workspace Information
Basic details about this workspace
The directory where the agent will operate
Behavior
Control how the workspace behaves
Agent
The coding agent and model for this workspace. To use a different agent or model, create a new workspace.
Agent & model
Read only — chosen when this workspace was created
Skills
Enable skills for this workspace — same layout as when creating a workspace.
Skills
6 skillsMCP Servers
Choose MCP servers for this workspace — same layout as when creating a workspace.
MCP Servers
6 serversKnowledge
Attach knowledge bases so the agent can retrieve context from your indexed documents.
Knowledge bases
5 collectionsFile system
Host file access for this workspace — same presets as the create-workspace flow. The first table picks the scope; when Custom Paths is selected, the second table lists every allowed directory (edit paths, access mode, add or remove rows).
File system
Same layout as Models — pick one scope for agent read/write on the host.
| Status | Name | Access | Notes | Use |
|---|---|---|---|---|
|
No host filesystem access
The agent cannot read or write files on your host. Use for API-only or fully remote workflows.
Recommended
|
None | Strict isolation | ||
|
Home Directory
Agent can access your entire home directory (~/) and all subdirectories.
|
Home (~) | Local development | ||
|
Custom Paths
Specify exact directories the agent can access.
|
Listed paths | Table below | ||
|
Full System Access
Agent can access the entire filesystem. Use with caution.
|
Full host | High privilege |
Custom allowed paths
Directories the agent may read or write on the host. Use absolute paths; tilde (~) is expanded when the workspace starts.
| Path | Access | Actions |
|---|---|---|
Changes apply when you save workspace settings.
Networking
Outbound network for this workspace sandbox — same presets as the create-workspace flow. Separate from file system access.
Network policy
Same layout as Models — click a row or use Use.
| Status | Name | Egress | Notes | Use |
|---|---|---|---|---|
|
Deny All
No outbound HTTP/HTTPS from the sandbox.
|
None | Strict | ||
|
Developer Preset
Allow npm, PyPI, and similar registries — not arbitrary public hosts.
Recommended
|
Registries | Balanced default | ||
|
Agent mode
The agent requests each outbound access; you approve before traffic leaves the sandbox.
|
Per request | Human in the loop | ||
|
Unrestricted
Permit all outbound traffic. Best for trusted dev setups.
|
All hosts | Trusted setups |
Allowlists and more — Fine-grained host allowlists and static egress rules live in project settings when you need them.
Advanced Settings
Advanced configuration options and danger zone.
Context Management
Manage the agent's context window
Danger Zone
Irreversible and destructive actions