pi-ts-aperture

Route Pi LLM providers and connector tools through Tailscale Aperture, a managed AI gateway on your tailnet.

Aperture handles API key injection and request routing server-side, so Pi never needs upstream provider credentials. This extension offers three capabilities:

• Dedicated (default): a standalone aperture provider whose models come from the gateway.
• Proxy: reroute existing Pi providers (anthropic, openai, openai-codex, …) through Aperture.
• Connectors: expose MCP tools from the gateway to Pi as discovery meta-tools or pinned first-class tools.

Install

pi install npm:@aliou/pi-ts-aperture

First run

After installing, run the onboarding wizard:

/aperture:onboarding

The wizard asks for your Aperture URL (with a health check), lets you pick capabilities and providers, then saves and reloads Pi. You can change everything later with /aperture:settings.

Capabilities

Dedicated provider (default)

Registers a standalone aperture provider listing the models your gateway exposes. Include all gateway providers or filter to specific ones, and each model is routed through the Pi API that matches its Aperture compatibility.

Capabilities (context window, vision input, reasoning, thinking levels) come from the first source that knows the model: ~/.pi/agent/models.json, then Pi’s model registry, then models.dev, then safe defaults. Costs come from the gateway. The resolved catalog is cached in Pi’s models store, so models load instantly on startup, even offline.

Proxy existing providers

Reroutes existing Pi providers through Aperture. Each provider keeps its own model definitions and settings; only the base URL, API key, and headers are overridden. Use this when you want Pi’s native per-provider model configuration but want requests to go through Aperture for server-side credentials.

Provider selection matches your local Pi providers against the providers enabled on the gateway. Optional per-provider verification warns when configured local models are missing from the gateway. Set keepGatewayModelsOnly: true on a provider to go further and filter those models out of the model picker entirely, so it only shows models the gateway can actually serve.

Connectors

Aperture can expose MCP connectors (GitHub, your own internal tools, …) at /v1/mcp. When enabled, this extension surfaces gateway tools to Pi in one of two ways:

• Discovery meta-tools (default): aperture_connector_list, aperture_connector_tool_search, aperture_connector_tool_describe, and aperture_connector_tool_call let the model find and call connector tools on demand, keeping individual tool schemas out of the system prompt.
• Pinned tools: an allow-list of gateway tools that register as first-class Pi tools. Pin a small set you use every session; each pin adds its full schema to the system prompt.

Enable connectors in /aperture:settings. Pin changes take effect on the next Pi restart (Pi cannot unregister tools at runtime).

Commands

Command	Description
/aperture:onboarding	Onboarding wizard. Only available while onboarding is enabled.
/aperture:settings	Edit connection, capabilities, providers, and pinned connector tools.

Configuration

Configuration is saved globally to ~/.pi/agent/extensions/aperture.json. The settings UI covers everything, but you can also edit the file directly. The APERTURE_BASE_URL environment variable, when set, overrides the configured baseUrl (it is not written back to the config file):

{
  "baseUrl": "http://ai.your-tailnet.ts.net",
  "proxy": {
    "enabled": true,
    "upstreamProviders": [
      { "id": "anthropic", "shouldCheckGatewayModels": true }
    ]
  },
  "dedicated": {
    "enabled": true,
    "providers": [
      { "id": "anthropic", "name": "Anthropic", "enabled": true },
      { "id": "openrouter", "name": "OpenRouter", "enabled": true, "api": "anthropic-messages" },
      { "id": "google", "name": "Google", "enabled": false }
    ]
  },
  "connectors": {
    "enabled": false,
    "discoveryTools": true,
    "pinnedTools": [
      { "connectorId": "github", "toolName": "github_list_repos" }
    ]
  }
}

Notes:

• keepGatewayModelsOnly (per proxy provider, default false) hides that provider’s local models the gateway doesn’t serve instead of letting them fail at request time. Also editable per provider from the Proxy tab in /aperture:settings.
• api (per provider, unset by default) routes that provider’s models through a specific Pi API (openai-completions, anthropic-messages, openai-responses, google-generative-ai, google-vertex, bedrock-converse-stream) instead of the one auto-picked from the gateway’s compatibility map. Useful for providers Aperture serves through more than one API. Only values the provider reports as supported are offered in /aperture:settings; an override the gateway stops serving falls back to auto with a warning.
• An empty dedicated.providers list means all gateway providers are included. Passthrough providers are excluded: the dedicated provider never forwards a client credential.
• Model metadata belongs in ~/.pi/agent/models.json, not in the extension config.
• Requests include Referer and x-session-id (the live Pi session id, injected per-request via the before_provider_headers hook) for grouping requests in the Aperture dashboard. Turn them off with "shouldSendProvenanceHeaders": false or the Provenance headers toggle in /aperture:settings. Independent of that setting, the headers are skipped whenever Pi telemetry is disabled (PI_TELEMETRY=0 or enableInstallTelemetry: false in Pi settings) — the same gate Pi uses for its own provider attribution headers.
• No API keys are stored: Aperture injects upstream credentials server-side. Pi OAuth credentials still take precedence when available.

Requirements

• A Tailscale tailnet with Aperture configured.
• The device running Pi must be able to reach your Aperture endpoint.
• Use the URL/scheme that matches your deployment (http:// or https://).