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	11121
title	Migrate PR conversations data to hierarchical chunking (XXxx)
state	Closed
labels	enhancementai
assignees	neo-gemini-pro
createdAt	May 10, 2026, 5:23 PM
updatedAt	May 11, 2026, 2:09 AM
githubUrl	https://github.com/neomjs/neo/issues/11121
author	neo-gemini-pro
commentsCount	0
parentIssue	11120
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	May 11, 2026, 2:09 AM

Migrate PR conversations data to hierarchical chunking (XXxx)

Closed v13.0.0/archive-v13-0-0-chunk-10 enhancementai

neo-gemini-pro commented on May 10, 2026, 5:23 PM

Context

Per the Epic #11120, we are applying the hierarchical chunking (XXxx/) storage pattern to GitHub content directories. The code enablement for PR conversations has been handled in #11117.

The Problem

The resources/content/pulls/ directory holds over 700 files and is approaching the 1,000-file GitHub ceiling. If we don't migrate the data, future syncs will fail. We are separating this data migration from the code logic (per #11116) to prevent massive file-move diffs from obscuring logic review.

The Architectural Reality

The chunking algorithm (id.slice(0, -2) + 'xx') natively distributes these files into 100-file increments without breaking ingestion paths, now that the underlying code supports it.

The Fix

Physically move all .md files currently in resources/content/pulls/ and its corresponding archive into the newly required XXxx/ nested directory structure.

Acceptance Criteria

100% of PR conversation markdown files are located in XXxx subdirectories.
No flat .md files remain at the root of resources/content/pulls/ (excluding index/readme files if any).
Data-only PR is opened and cleanly passes review without logic changes.

tobiu closed this issue on May 11, 2026, 2:09 AM

tobiu referenced in commit 9213f9a - "feat(swarm,sync): codify Helpful-Assistant negative constraint in §15.6 (#11128) + chunked-content data migration (#11121) + fix JSDoc optional parsing (#11164) on May 11, 2026, 2:09 AM