What is the Neural Link?

The Neural Link is a bi-directional bridge that connects AI agents directly to the Neo.mjs runtime. It lets agents inspect the Scene Graph, component state, event listeners, computed styles, and DOM rectangles, and mutate the running application in real time.

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

Neo.mjs maintains persistent application objects in a worker-backed Scene Graph instead of compiling application state away into ephemeral DOM nodes. That architecture enables multi-window orchestration, runtime permutation, and deep AI introspection.

What is Context Engineering?

Context Engineering shapes the information and tool environment around AI agents. Neo.mjs implements it through Knowledge Base, Memory Core, GitHub Workflow, and Neural Link MCP servers for frontier harnesses, plus a File System MCP server for internal Neo.ai.Agent local loops.

What is the Neo.mjs Agent OS?

The Neo.mjs Agent OS is the repository Brain: source code and services for Memory Core, Knowledge Base, Active Hybrid GraphRAG, DreamService, Golden Path synthesis, A2A coordination, and Neural Link tooling.

Frontmatter

id	8172
title	Implement Neural Link Drag & Drop Inspection
state	Closed
labels	enhancementai
assignees	tobiu
createdAt	Dec 28, 2025, 2:37 PM
updatedAt	Dec 28, 2025, 6:17 PM
githubUrl	https://github.com/neomjs/neo/issues/8172
author	tobiu
commentsCount	1
parentIssue	8169
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Dec 28, 2025, 6:17 PM

Implement Neural Link Drag & Drop Inspection

Closed v11.18.0/archive-v11-18-0-chunk-1 enhancementai

tobiu commented on Dec 28, 2025, 2:37 PM

Create a specialized tool to expose the internal state of the Neo.manager.DragCoordinator.

Tool: get_drag_state()

Goal: meaningful debug info for "Infinite Canvas" scenarios.
Return Data:
- isDragging: Boolean
- dragProxy: ID and WindowID of the current proxy.
- source: ID and WindowID of the source component.
- activeMonitors: List of active drop zones and their coordinates.
- currentWindow: The windowId where the mouse currently is.

tobiu Dec 28, 2025, 6:17 PM

Input from Gemini 3:

✦ Implementation Complete

I have implemented the Drag & Drop inspection tool for the Neural Link.

Changes:

OpenAPI & Tools (openapi.yaml, toolService.mjs):

Added /drag/state endpoint (get_drag_state).

Used sessionId as the target parameter, aligning with the new routing standard.

Server (ConnectionService.mjs):

Implemented getDragState routing.

Client (src/ai/Client.mjs):

Implemented get_drag_state handler.

Logic: Queries Neo.manager.DragCoordinator (if available) to retrieve:

activeTargetZone: The remote zone currently receiving the drag (with windowId and sortGroup).

sortZones: A flattened list of all registered sort zones across all windows, grouped by sortGroup.

Verification:

Verified static analysis of Client.mjs logic.

Verified server startup.

Ready for review.

2026-06-23T03:46:30Z @neo-gpt cross-referenced by #8166