@presencelearning/ai

AI integration library for Presence Learning. Provides chat functionality, background job management, and UI components for AI-powered features using the Vercel AI SDK.

Install

npm install @presencelearning/ai

Peer Dependencies

@angular/core >= 18.0.0
@angular/common >= 18.0.0
@ai-sdk/angular ^2.0.0
ai ^6.0.0
rxjs ^7.0.0
marked ^15.0.0

Setup

Configure the AI module in your application:

import { PRESENCE_AI_CONFIG } from '@presencelearning/ai';

bootstrapApplication(AppComponent, {
  providers: [
    {
      provide: PRESENCE_AI_CONFIG,
      useFactory: () => ({
        chiron: { baseUrl: environment.apps.chiron.url },
        workplace: { baseUrl: environment.apps.apiWorkplace.url },
        auth: {
          getToken: () => inject(AuthStore).getCurrentToken(),
        },
      }),
    },
  ],
});

Features

Feature	Description
Chat	`PresenceChatFactory` for streaming chat with tool call tracking
Jobs	`AIJobManager` for background AI job polling and status tracking
Sessions	`AISessionService` for managing chat session lifecycle
Feedback	`AIFeedbackService` for collecting user feedback on AI responses

Components

Component	Description
`AIMarkdownComponent`	Renders AI-generated markdown safely via `marked` (bold, italic, code, lists, links, blockquotes, tables)
`AIToolStatusComponent`	Displays tool invocation status during streaming
`AIToolProgressComponent`	Streaming tool progress with step descriptions and summaries
`SparkleLoaderComponent`	Animated loading indicator with therapy-themed status messages
`UserPromptDialogComponent`	Material dialog for chiron `ask_user` tool prompts (radio options + optional free text)

Utilities

Export	Description
`createAskUserHandler`	Creates a reactive handler for the `ask_user` tool lifecycle — provides a `pendingPrompt` signal and a `respond()` method

Key Types

Type	Description
`PresenceChat`	Chat instance with Angular signals for messages, status, streaming, and tool calls
`ChironToolResult`	Tool result from the chiron SSE stream
`UserPrompt`	Pending `ask_user` prompt data (question, options, allowCustom, toolCallId)
`UserPromptDialogData`	Input data for `UserPromptDialogComponent` (adds optional `title`)
`UserPromptDialogResult`	Dialog return value (`response` string + `isCustom` flag)
`ToolDescriptionMap`	Maps tool names to user-friendly descriptions for `AIToolProgressComponent`
`ToolSummarizer`	Function that extracts a summary string from a `ChironToolResult`