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	7864
title	Refactor SessionService for better error handling and config management
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Nov 22, 2025, 8:03 PM
updatedAt	Nov 22, 2025, 8:17 PM
githubUrl	https://github.com/neomjs/neo/issues/7864
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 22, 2025, 8:17 PM

Refactor SessionService for better error handling and config management

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

Closed v11.9.0 enhancementai

tobiu commented on Nov 22, 2025, 8:03 PM

During a self-review of ai/mcp/server/memory-core/services/SessionService.mjs, the following potential improvements were identified:

Error Handling: findSessionsToSummarize performs multiple database calls (memory fetch loop, summary fetch loop) without internal try/catch blocks. While the caller (summarizeSessions -> initAsync) likely handles errors, a failure in the memory fetch loop (e.g., partial network failure) currently causes the entire process to abort. Consider if granular error handling or retry logic is needed here.
Hardcoded Configuration: The batch limit (const limit = 2000;) is hardcoded inside the method. This should be moved to ai/mcp/server/memory-core/config.mjs to allow for environment-based tuning (e.g., smaller batches for memory-constrained environments).
Loop Safety: While hasMore is controlled by batch.ids.length < limit, adding a safety break (max iterations) could prevent infinite loops in case of weird driver behavior where it keeps returning full pages of the same data (though unlikely with offset).

Goal: Refactor SessionService.mjs to address these code quality and robustness points.

tobiu assigned to @tobiu on Nov 22, 2025, 8:05 PM

tobiu added the enhancement label on Nov 22, 2025, 8:05 PM

tobiu added the ai label on Nov 22, 2025, 8:05 PM

tobiu referenced in commit a2b3480 - "Refactor SessionService for better error handling and config management #7864" on Nov 22, 2025, 8:16 PM

tobiu Nov 22, 2025, 8:16 PM

Input from Gemini:

✦ Refactoring completed.

Summary of Changes:

Config Management: Added summarizationBatchLimit to config.mjs (default: 2000) to control database fetch sizes.

Robust Database Scanning:

Updated findSessionsToSummarize to use pagination loops with safety breaks (maxIterations: 1000).

Ensured database queries use dynamically built configuration objects to avoid where: undefined errors.

Removed internal try/catch from findSessionsToSummarize to allow errors to propagate correctly.

Tool Error Handling:

Updated summarizeSessions (the public tool method) to wrap logic in a try/catch block.

On failure, it now returns a structured error object ({ error, message, code }) instead of crashing or returning misleading empty results.

The service is now consistent with the project's error handling patterns and safe for large-scale deployments.

tobiu closed this issue on Nov 22, 2025, 8:17 PM