User Info (NextGen Plugin)

⚠️ Deprecated in favour of MemoryPluginNextGen. This plugin keeps working unchanged; the memory plugin supersedes it with facts-over-KV, supersession-preserved history, LLM-synthesised profiles, three-principal permissions, and semantic recall.

Store user-specific preferences and context that persist across sessions and agents. Unlike other plugins, user info is user-scoped (not agent-scoped) — different agents share the same user's data.

User info entries are automatically injected into the LLM system message as markdown, so the LLM always knows the user's preferences without needing to call store_get("user_info") each turn.

Setup

typescript

import { Agent } from 'oneringai';

// Single-user app — no userId needed
const agent = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  context: {
    model: 'gpt-4.1',
    features: { userInfo: true },
  },
});

// Multi-user app — opt-in per-user isolation
const agentVariant2 = Agent.create({
  connector: 'openai',
  model: 'gpt-4.1',
  userId: 'alice',
  context: {
    model: 'gpt-4.1',
    features: { userInfo: true },
  },
});

How It Works

Lazy Loading — On first access (tool call or getContent()), entries are loaded from storage into an in-memory cache

Context Injection — getContent() renders entries as markdown in the system message. Regular user info and TODOs are shown in separate sections:

text

### theme
dark

### language
en

## Current TODOs
- [ ] todo_a1b2c3: Review PR for auth module (due: 2026-03-01, people: Alice) [work]
  Check the error handling changes
- [x] todo_d4e5f6: Buy groceries (due: 2026-02-25) [personal]

Write-Through — Tool mutations (set/remove/clear) update both the in-memory cache and persist to storage immediately
Session Persistence — getState()/restoreState() serialize/deserialize entries for session save/load

User Info Tools

Tool Call	Description	Permission
`store_set("user_info", key, { value, description? })`	Store/update entry by key	Always allowed
`store_get("user_info", key?)`	Retrieve one entry by key, or all entries (key optional)	Always allowed
`store_delete("user_info", key)`	Remove a specific entry by key	Always allowed
`store_action("user_info", "clear", { confirm: true })`	Clear all entries	Requires approval

TODO Tools

TODOs are stored as user info entries with a todo_ key prefix. They are rendered in a dedicated "Current TODOs" checklist section in context, separate from regular user info.

Tool	Description	Permission
`todo_add`	Create a TODO (`title`, `description?`, `people?`, `dueDate?`, `tags?`)	Always allowed
`todo_update`	Update a TODO — partial updates (`id`, `title?`, `description?`, `people?`, `dueDate?`, `tags?`, `status?`)	Always allowed
`todo_remove`	Delete a TODO by id	Always allowed

TODO fields:

title (required) — short description of the task
description (optional) — additional details
people (optional) — other people involved besides the current user
dueDate (optional) — deadline in YYYY-MM-DD format
tags (optional) — categorization tags (e.g. ["work", "urgent"])
status — 'pending' or 'done'

Agent behavior (built into plugin instructions):

Proactive creation — When conversation implies an action item, the agent suggests creating a TODO. Explicit requests like "remind me" or "track this" create one immediately.
Daily reminders — Once per day, the agent reminds about overdue and soon-due items (within 2 days). Uses a _todo_last_reminded internal entry to avoid repeating.
Auto-cleanup — Completed TODOs older than 48 hours are automatically removed. Pending TODOs overdue by more than 7 days prompt the user: "Still relevant or should I remove it?"

Storage

Default path: ~/.oneringai/users/<userId>/user_info.json (defaults to ~/.oneringai/users/default/user_info.json)
Custom storage: Implement IUserInfoStorage and pass via config or StorageRegistry

typescript

// Via StorageRegistry
StorageRegistry.set('userInfo', (context?: StorageContext) => {
  return new MongoUserInfoStorage(collection);
});

Configuration

typescript

interface UserInfoPluginConfig {
  storage?: IUserInfoStorage;    // Custom storage backend
  maxTotalSize?: number;         // Default: 100000 (~100KB)
  maxEntries?: number;           // Default: 100
  userId?: string;               // Auto-set from AgentContextNextGen._userId
}

Differences from Other Plugins

	PersistentInstructions	UserInfo	InContextMemory
Scope	Agent-scoped	User-scoped	Session only
Storage key	`agentId`	`userId`	None (in memory)
Persists to disk	Yes	Yes	No
In system message	Yes	Yes	Yes
Value type	`string`	`unknown` (any JSON)	`unknown` (any JSON)

Use Cases

User preferences: theme, language, timezone, notification settings
User context: role, location, department
Accumulated knowledge about the user
Profile information the LLM should always have access to
TODO tracking: tasks with deadlines, involved people, and tags — with proactive reminders and auto-cleanup

⚠️ Deprecated in favour of the Self-Learning Memory plugin below. UserInfoPluginNextGen keeps working unchanged; the memory plugin supersedes it with append-only facts (history preserved via supersession), LLM-synthesised profiles that evolve with new observations, three-principal permissions, and semantic recall.