Positron Settings
When running inside Positron, Posit Assistant is configured through VS Code settings in addition to the shared config file. These settings are accessed via Settings (Cmd+, / Ctrl+,) and use the assistant.* prefix.
Settings Reference
| Key | Type | Default | Description |
|---|---|---|---|
assistant.preferredModel | string | "" | The preferred language model to use by default. If specified and available, this model is selected automatically when Posit Assistant starts. |
assistant.modelRouting | string | "prefer-direct" | Controls how Posit Assistant accesses language models. See below for options. |
assistant.sidebarView | boolean | false | Show the Posit Assistant sidebar view in the activity bar. |
assistant.experimentalFeatures | boolean | false | Enable experimental features. |
assistant.mcpServers | object | {} | MCP server configuration. Same format as the mcpServers key in the config file. |
assistant.aiExcludes | string[] | [] | Glob patterns for files excluded from AI access. For example, ["*.env", "secrets/**"] prevents the assistant from reading matching files. Admin policies can enforce non-overridable patterns. |
AI Excludes
In Positron, you can exclude files from AI access using glob patterns via the assistant.aiExcludes setting. Matching files are blocked from being read, written, or edited by the assistant. Patterns without a / are matched against filenames in any directory (e.g., *.env matches all .env files).
Admin policies can enforce non-overridable exclude patterns that users cannot override during a session.
MCP Servers in Positron
MCP servers can be configured either in the VS Code settings (assistant.mcpServers) or in the shared config file (mcpServers key). The format is the same in both locations. See the MCP Servers guide for configuration details.
Model Routing
The assistant.modelRouting setting controls how the assistant connects to language models:
| Value | Description |
|---|---|
prefer-direct | (Default) Use direct API access when available, fill in remaining providers from Positron’s language model API. |
direct | Only use direct API access via configured credentials. |
vscode-lm | Only use Positron’s built-in language model API. |
prefer-vscode-lm | Prefer Positron’s language model API, fill in remaining providers from direct access. |
Most users should leave this at the default (prefer-direct).
Custom Base URLs
Posit Assistant respects custom base URLs configured in Positron’s language model provider settings. This is useful for enterprise proxies, custom API gateways, or local development servers.
When you register a model provider in Positron with a custom base URL (via the model provider configuration UI), Posit Assistant automatically routes API requests through that URL. These are Positron authentication settings (authentication.*), not assistant.* settings — they are set at model registration time and apply to all extensions that use the provider.
The supported settings are:
| Provider | Setting Key |
|---|---|
| Anthropic | authentication.anthropic.baseUrl |
| OpenAI | authentication.openai-api.baseUrl |
| Google / Gemini | authentication.google.baseUrl |
| OpenAI Compatible | authentication.openai-compatible.baseUrl |
| Microsoft Foundry | authentication.foundry.baseUrl |
For non-Positron platforms, custom base URLs are configured via
providers.{provider}.baseUrl in the config file.
Relationship to Config File
Positron reads settings from both VS Code settings and the shared config file (~/.positai/settings.json). VS Code settings handle Positron-specific behavior like model routing and sidebar visibility. The config file handles shared settings like runtime paths, permissions, and storage — these apply across all platforms.
Model preferences like thinking effort and web search are set as defaults in the config file (model.thinkingEffort, model.webSearch) and applied when starting new conversations. During a conversation, these preferences are adjusted via the UI and stored per-conversation — they are not written back to the config file.