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	7901
title	Split Playwright tests into granular knowledge base chunks for better retrieval
state	Closed
labels	enhancementaitesting
assignees	tobiu
createdAt	Nov 25, 2025, 3:01 PM
updatedAt	Nov 25, 2025, 3:42 PM
githubUrl	https://github.com/neomjs/neo/issues/7901
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Nov 25, 2025, 3:42 PM

Split Playwright tests into granular knowledge base chunks for better retrieval

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

Closed v11.11.0 enhancementaitesting

tobiu commented on Nov 25, 2025, 3:01 PM

Currently, test/playwright files are indexed as single monolithic chunks. This dilutes the semantic signal of individual test cases, making it harder for the vector search to find specific testing patterns.

Goal: Decompose test files into smaller, semantically distinct chunks to improve search scoring and relevance.

Requirements:

File-Level Context Chunk:
- Create a dedicated chunk for the file's "header".
- Content: Top-level comments, imports, and outer test.describe descriptions.
- Purpose: Captures high-level intent (e.g., "Grid Filtering Tests") and shared context.
Test-Case Chunks:
- Parse individual test('description', ...) blocks.
- Create a separate chunk for each test case.
- Content: The test description + the full function body.
- Name: [RelativePath] - [Test Description].
Location Metadata (New):
- Calculate and store line_start and line_end for each test chunk.
- Benefit: Enables agents to pinpoint the exact location of a test within a large file, allowing for targeted read_file operations (using offset/limit) when safe to do so.
Source Mapping:
- All chunks must retain the exact source property pointing to the original .spec.mjs file.

tobiu added the enhancement label on Nov 25, 2025, 3:01 PM

tobiu added the ai label on Nov 25, 2025, 3:01 PM

tobiu added the testing label on Nov 25, 2025, 3:01 PM

tobiu assigned to @tobiu on Nov 25, 2025, 3:02 PM

tobiu referenced in commit 06c2c4a - "Split Playwright tests into granular chunks for improved Knowledge Base indexing #7901 on Nov 25, 2025, 3:33 PM

tobiu Nov 25, 2025, 3:41 PM

Input from Neo Agent:

◆ I have verified the implementation by performing a full rebuild of the Knowledge Base.

Verification Results:

Chunk Generation: The process successfully parsed Playwright test files, generating granular chunks for individual test cases and file-level headers.

Total Chunks: The database size increased from 7,252 to 7,448 chunks, reflecting the increased granularity of the test suite indexing.

Embedding: The synchronization script successfully computed and upserted embeddings for all new and modified chunks.

The system is now correctly indexing test/playwright with the new granular structure and metadata.

tobiu closed this issue on Nov 25, 2025, 3:42 PM