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	9767
title	Investigate 'Viewer has null permission' bug in manage_issue_assignees MCP tool
state	Closed
labels	bugaiagent-role:dev
assignees	tobiu
createdAt	Apr 7, 2026, 10:30 PM
updatedAt	Apr 7, 2026, 10:42 PM
githubUrl	https://github.com/neomjs/neo/issues/9767
author	tobiu
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Apr 7, 2026, 10:42 PM

Investigate 'Viewer has null permission' bug in manage_issue_assignees MCP tool

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

Closedbugaiagent-role:dev

tobiu commented on Apr 7, 2026, 10:30 PM

The manage_issue_assignees MCP tool fails when attempting to assign a ticket to a valid user despite valid auth credentials.

Details:

Target login: tobiu
CLI validation: gh auth status shows successful connection with repo scope and active GH_TOKEN.
Internal check: get_viewer_permission returns ADMIN.
Error Output: Tool Error: Permission Denied. Message: Permission denied. Viewer has 'null' permission, but one of [ADMIN, MAINTAIN, WRITE] is required to assign issues.

Suspected Issue: The GraphQL mutation payload or the viewer scope dynamically executed inside the Node.js MCP server logic appears to be incorrectly failing to attach or resolve the permission level from the token, passing null directly into the mutation, causing an explicit block. Needs internal debugging of the MCP server's GraphQL dispatch mechanism.

tobiu added the bug label on Apr 7, 2026, 10:30 PM

tobiu added the ai label on Apr 7, 2026, 10:30 PM

tobiu added the agent-role:dev label on Apr 7, 2026, 10:30 PM

tobiu Apr 7, 2026, 10:41 PM

Input from Antigravity (Gemini 3.1 Pro):

✦ I have investigated and resolved the manage_issue_assignees MCP tool permission bug and execution bug in IssueService.

Two independent root causes were addressed:

Synchronous Permission Checking Cache Miss: When the MCP server initialized, RepositoryService.viewerPermission fetched the GitHub token capabilities. If the networking was slow or authentication wasn’t completely mounted, this fetch failed cleanly returning null. However, IssueService.hasWritePermission() was evaluating this null state synchronously. It has been updated to be asynchronous (async), where it awaits RepositoryService.getViewerPermission() which has logic to lazily re-fetch the permission if the cache yields a miss or null.

GH CLI Context: The operations string passed to the gh shell sub-process didn’t target a particular repo, causing fatal: not a git repository. gh issue edit {number} --repo {owner}/{repo} syntax injection guarantees absolute targeting capabilities.

As these fixes require server reboot mapping to .agent, they will be fully available sequentially when MCP server node processes respawn. I will proceed to close this investigation ticket.

tobiu assigned to @tobiu on Apr 7, 2026, 10:42 PM

tobiu closed this issue on Apr 7, 2026, 10:42 PM

tobiu referenced in commit 6aaa996 - "fix(ai): Resolve MCP tool issue mapping to gh cli & update OpenAiCompatible to ES6 (#9767) (#9766)" on Apr 7, 2026, 10:42 PM