AI Features Settings (Preferences)

Studio AI has three separate configuration surfaces, and it is easy to confuse them:

This article covers the third surface: a large set of preferences under the AI Features category of Studio's standard Settings UI, most of which are not exposed anywhere in the AI Configuration panel.

Opening AI Features Settings

1. Open the command palette (F1) and run Preferences: Open Settings (UI), or press Ctrl+,.
2. In the left navigation, expand AI Features. It contains sub-sections such as Agent Mode, Agent Settings, AI Enablement, Anthropic, Chat, Code Completion, and more. Selecting a sub-section shows only its settings.
3. Alternatively, type a keyword (for example, "compaction" or "token usage") into the Search settings box at the top; matching settings from any category are shown directly.

Settings here apply to your Studio user or workspace (not only to one chat session, unlike the per-session overrides in article 03). They are not a central policy: each Studio has its own settings, and its user can change them. See Security and Privacy.

AI Enablement and LLM Providers

Turning AI on and connecting a provider is covered in Getting Started with Studio AI. The same AI Enablement section lives under AI Features in this Settings UI.

Each supported LLM provider has its own sub-section here for API keys and provider-specific options.

From V8.5.2, Anthropic, OpenAI and Google no longer have a model-list setting: the settings ai-features.anthropic.AnthropicModels, ai-features.openAiOfficial.officialOpenAiModels and ai-features.google.models were removed. Studio reads the available models from each provider, and you choose which appear in the chat in the Providers & Models category of AI Configuration. Two new settings per provider (anthropic, openAiOfficial, google) control this:

The models chosen in AI Configuration are stored in ai-features.modelSettings.favoriteModels and ai-features.modelSettings.hiddenModels.

Model Selection and Language Model Aliases also appear here, but both are thin pointers into the AI Configuration panel's Agents and Model Aliases categories (see article 06) rather than separate editors. Model Settings does add two standalone knobs: maxRetries (retry attempts on a failed model call) and requestSettings (provider request tuning).

Server-Side Compaction

When a conversation grows past a model's context limit, server-side compaction has the provider itself summarize older turns so the session keeps working, instead of the request failing outright. It is a genuine safeguard against the kind of hard failure some users have hit ("prompt is too long: N tokens > maximum"), but it only works when the model/provider supports it, and only if it is actually enabled for that session.

Support is currently limited to Anthropic (recent Opus/Sonnet models, via a Beta Messages API) and OpenAI official models using the Responses API (Chat Completions is not supported). Unsupported models and providers silently ignore the setting.

Activation is layered, each level overriding the one before it:

When compaction fires, an inline marker appears in the chat and the token-usage tooltip shows a "compacted N×" count; this is persisted with the session and restored on reload. If you see a hard token-limit error despite compaction being enabled, check that the session's model is actually one of the supported ones (Anthropic Opus/Sonnet or an OpenAI Responses-API model); on any other model, compaction has no effect and the raw context limit still applies.

Token Usage Visibility (Experimental)

Separately from compaction, three experimental settings control whether you get any visibility into approaching a token limit at all:

This is the closest equivalent Studio AI currently has to a "your session is getting long, consider starting fresh" warning. It is off by default in some deployments and marked experimental, so if you want a proactive nearing-the-limit warning rather than relying on compaction alone, check that both tokenUsageIndicator.enabled and tokenUsageWarning.enabled are turned on.

Chat Behavior

Because the Studio ships with tool confirmations set to Always Allow, most agent tool calls - including file writes - proceed without a per-action prompt. Review that default with your security team, and consider requiring confirmation for more tools with toolConfirmation. Shell commands are also governed by the allow and deny lists below. See Security and Privacy.

Agent Mode and Agent Settings

Agent Mode: Enabled (ai-features.agentMode.enabled) is the global default for whether @Coder's Agent Mode is available without an extra first-use confirmation dialog. See Code Editing with @Coder (Legacy).

Agent Settings is a pointer, not a separate editor: it directs you to the AI Configuration view's Agents category for enablement, LLM selection, prompt customization, and custom agent creation (articles 06 and 09).

Code Completion

Prompt Templates and Skills

These settings back the file-location behavior described in Customizing Agent Prompts and Skills and Slash Commands. Live-checked in this project:

Skills therefore resolve from both a workspace-level .agents/skills folder and a user-home-level ~/.agents/skills folder, with workspace taking precedence. Custom agents do not follow this convention: they are read from the workspace only - see Creating Custom Agents.

MCP, Notifications, Reasoning, Orchestrator

Security-Relevant Settings

These directly affect what AI agents and tools can access or execute without your explicit per-action approval; see also Security and Privacy.

API keys and tokens entered in these fields are stored in clear text on the machine running Studio unless you use the corresponding environment variable instead (for example, SCANOSS_API_KEY). Prefer environment variables for anything sensitive.