Arcane OS Docs Development only

Reference

Arcane.ollama

Admitted native Ollama inference, inventory, policy, and model-management operations.

  • Reference

This focused page is derived from the mechanically checked full member inventory.

Syntax

Arcane.ollama

Member kind

Namespace

Description

Admitted native Ollama inference, inventory, policy, and model-management operations.

Overview

Arcane.ollama exposes admitted Ollama inference, raw diagnostic inventory, managed selection and settings, and policy-controlled model management. Raw provider inventory is not an application's model-admission catalog. Streaming calls can deliver correlated ollama.chunk events or an onChunk callback.

Availability and security

Inference requires ai.inference; diagnostic inventory requires ai.models.read and is limited to Settings, Shell, and Terminal. Mutations use ai.models.manage or Settings-only ai.settings.manage, frequently behind an exclusive mutation boundary. Android user-managed loopback admission exposes chat only and does not grant managed model lifecycle authority.

Example

const access = await globalThis.Arcane.capabilities.list();
const canUseOllamaChat = access.methods.includes('ollama.chat');

console.log('Native Ollama chat admitted:', canUseOllamaChat);

Members

Reference group

Namespace, constructor, and values

Repository and reviewed source access