What is the 'Neural Link'?

The Neural Link is a bi-directional bridge that connects AI agents (like Gemini or Claude) directly to the Neo.mjs runtime. It allows agents to 'see' the application's Scene Graph, inspect component state, verify event listeners, and even mutate the running application in real-time. This turns the application into a 'glass box' for AI, enabling autonomous debugging and feature development.

Why is Neo.mjs called an 'Application Engine' instead of a framework?

Traditional frameworks are general-purpose libraries (like a Toyota) that help you organize code, but they compile away into ephemeral DOM nodes. Neo.mjs is a precision-engineered runtime (like an F1 car), similar to Unreal Engine for games. It maintains a persistent 'Scene Graph' of objects in a separate worker thread. These objects retain their identity, state, and relationships, allowing for advanced capabilities like multi-window orchestration, runtime permutation, and deep AI introspection that are impossible with 'melted plastic' DOM-based frameworks.

What is 'Context Engineering'?

Context Engineering is the practice of curating the environment and information flow for AI agents to maximize their autonomy. In Neo.mjs, this is implemented via three Model Context Protocol (MCP) servers: a Knowledge Base for semantic code understanding, a Memory Core for learning from past sessions, and a GitHub Workflow server for project management. This ecosystem allows agents to work as fully integrated members of the development team.

What is 'Object Permanence' in the context of Neo.mjs?

In Neo.mjs, UI components are persistent JavaScript objects living in the App Worker, not just transient rendering results. This 'Object Permanence' means a component (like a Dashboard) maintains its state (scroll position, user input, internal logic) even if it is detached from the DOM or moved to a different browser window. This is the 'Lego Technic' approach versus the 'Duplo' approach of traditional frameworks.

What is an 'Agent Operating System'?

Neo.mjs v11 introduced the concept of an Agent OS, where the platform itself provides the tools and interfaces for AI agents to operate. It combines a standalone, type-safe AI SDK for autonomous 'Code Execution' with the Neural Link for runtime control. This enables agents to monitor, debug, and heal the application autonomously, effectively acting as an operating system for synthetic intelligence.

How does Neo.mjs handle multi-window applications?

Neo.mjs uses shared web workers to run a single application instance across multiple browser windows. All windows share the same application state and data in real-time. Components can even move between windows while retaining their JavaScript instances. This enables desktop-class experiences like multi-window IDEs, browser-based email clients, and multi-screen control rooms.

What makes Neo.mjs different from React, Angular, or Vue?

Neo.mjs is fundamentally different in its architecture: (1) It uses True Multithreading via web workers to prevent UI jank, (2) It is an AI-Native Application Engine with built-in bridges for AI collaboration, and (3) It treats components as persistent objects in a Scene Graph, enabling native multi-window support and runtime permutation.

Frontmatter

id	9430
title	TreeModel: Introduce childCount to decouple isLeaf state from emptiness
state	Closed
labels	enhancementaiarchitecturecore
assignees	tobiu
createdAt	Mar 10, 2026, 2:25 PM
updatedAt	Mar 10, 2026, 2:34 PM
githubUrl	https://github.com/neomjs/neo/issues/9430
author	tobiu
commentsCount	1
parentIssue	9404
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Mar 10, 2026, 2:34 PM

TreeModel: Introduce childCount to decouple isLeaf state from emptiness

Name: Neo.mjs Application Engine
Author: Neo.mjs

Closed v12.1.0 enhancementaiarchitecturecore

tobiu commented on Mar 10, 2026, 2:25 PM

Goal

Introduce a childCount field to TreeModel to decouple a node's intrinsic type (isLeaf) from its current structural state (empty vs populated) and ensure O(1) read access for UI components.

Context

Currently, isLeaf is conceptually overloaded. If a folder (branch node) loses its last child via drag-and-drop or deletion, naively reverting it to isLeaf: true would cause the UI to render it as a file, potentially breaking drag-and-drop logic. A folder should remain isLeaf: false forever, even when empty. However, the UI still needs to know if a branch node is empty so it can hide or disable the expand/collapse arrow.

We choose childCount over a boolean hasChildren because, while it requires slightly more frequent mutations (O(1) updates on the parent during TreeStore.splice()), it provides maximum data availability for the grid.Row hot-path. Developers can render badges like "Folder (5 items)" directly from record.childCount without expensive store.get() or #childrenMap lookups during 120fps virtual scrolling.

Acceptance Criteria

Add childCount (Integer, default 0) to Neo.data.TreeModel.
Update TreeStore.splice() (likely within updateSiblingStats or the mutation loops) to dynamically calculate and mutate childCount on parent nodes during additions, moves, and removals.
Ensure "Turbo Mode" (lazy instantiation) supports childCount directly on raw data objects.
Add a Playwright unit test verifying childCount updates correctly when children are added or removed, while the parent's isLeaf state remains unchanged.

tobiu added the enhancement label on Mar 10, 2026, 2:25 PM

tobiu added the ai label on Mar 10, 2026, 2:25 PM

tobiu added the architecture label on Mar 10, 2026, 2:25 PM

tobiu added the core label on Mar 10, 2026, 2:25 PM

tobiu added parent issue #9404 on Mar 10, 2026, 2:25 PM

tobiu referenced in commit 6bc5aa9 - "feat(data): Introduce childCount to TreeModel to decouple isLeaf state (#9430)" on Mar 10, 2026, 2:33 PM

tobiu Mar 10, 2026, 2:34 PM

Input from Gemini 3.1 Pro:

✦ I have successfully implemented childCount on TreeModel and updated the TreeStore mutation logic.

Implementation Details:

Model: Added childCount (Integer, default 0) to Neo.data.TreeModel.

Mutation Logic: Updated TreeStore.updateSiblingStats(parentId). Since this method is already called during every structural mutation (add, remove, move) and already iterates over all children to update ARIA sibling stats, I hooked the childCount calculation into this exact loop. This ensures we update the parent's childCount (and fire recordChange events) optimally with O(1) overhead on an existing O(N) loop.

Soft Hydration: Updated the initialization loop in TreeStore.splice() to inject childCount: 0 into raw data objects if it's missing, ensuring full compatibility with "Turbo Mode".

Unit Tests Added: I added a new test block to test/playwright/unit/data/TreeStore.spec.mjs:

childCount should accurately reflect the number of children and decouple from isLeaf: Verifies that adding children increases childCount, and removing all children drops childCount to 0 while keeping isLeaf: false.

Updated the existing Turbo Mode test to verify childCount is accurately calculated for raw objects during initial ingest.

All tests are passing. I have committed the changes (feat(data): Introduce childCount to TreeModel to decouple isLeaf state (#9430)) and will close this issue.

tobiu assigned to @tobiu on Mar 10, 2026, 2:34 PM

tobiu closed this issue on Mar 10, 2026, 2:34 PM