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	8560
title	Replace hardcoded timeout in MainContainerController with deterministic wait
state	Closed
labels	airefactoringperformance
assignees	tobiu
createdAt	Jan 11, 2026, 11:45 PM
updatedAt	Jan 11, 2026, 11:55 PM
githubUrl	https://github.com/neomjs/neo/issues/8560
author	tobiu
commentsCount	1
parentIssue	8398
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jan 11, 2026, 11:55 PM

Replace hardcoded timeout in MainContainerController with deterministic wait

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

Closed v11.20.0 airefactoringperformance

tobiu commented on Jan 11, 2026, 11:45 PM

In apps/portal/view/news/tickets/MainContainerController.mjs, onRouteItem uses a hardcoded delay:

            if (!oldValue?.hashString?.startsWith('/news/tickets')) {
                await me.timeout(100);
                tree.scrollToItem(itemId)
            }

This delay is intended to wait for the tree to expand and render before scrolling. However, 100ms is arbitrary and can be flaky or wasteful.

Proposed Solution: Replace await me.timeout(100) with a deterministic wait, likely await tree.promiseUpdate(), which ensures that the VDOM updates (triggered by tree.expandParents(itemId)) have been processed and applied to the DOM.

We need to verify if promiseUpdate() is sufficient for scrollToItem to work (which relies on document.getElementById).

tobiu added the ai label on Jan 11, 2026, 11:45 PM

tobiu added the refactoring label on Jan 11, 2026, 11:45 PM

tobiu added the performance label on Jan 11, 2026, 11:45 PM

tobiu referenced in commit 5eb836d - "refactor: Replace timeouts with robust DOM waits in TreeList logic (#8560)" on Jan 11, 2026, 11:54 PM

tobiu assigned to @tobiu on Jan 11, 2026, 11:54 PM

tobiu Jan 11, 2026, 11:54 PM

Input from Gemini 3 Pro:

✦ I have replaced the hardcoded timeout(100) in MainContainerController.mjs with a robust waitForDomRect check.

Changes:

Replaced await me.timeout(100) with await tree.waitForDomRect({id, attempts: 20, delay: 20}).

This ensures the code waits for the tree item to be truly rendered, visible, and laid out (expanded) before attempting to scroll to it.

This addresses the flakiness of fixed timeouts while ensuring scrolling only happens when the target is ready.

I also removed the arbitrary 20ms delay in TreeList.afterSetCurrentPageRecord as discussed, assuming the reactive update cycle should handle selection state correctly.

tobiu added parent issue #8398 on Jan 11, 2026, 11:54 PM

tobiu closed this issue on Jan 11, 2026, 11:55 PM

tobiu cross-referenced by #8561 on Jan 11, 2026, 11:56 PM