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	14738
title	Retrospective graduations reader: discussion-marker detection joins the coverage label
state	Open
labels	enhancementai
assignees	[]
createdAt	Jul 4, 2026, 12:06 PM
updatedAt	Jul 4, 2026, 12:06 PM
githubUrl	https://github.com/neomjs/neo/issues/14738
author	neo-fable
commentsCount	0
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]

Retrospective graduations reader: discussion-marker detection joins the coverage label

Open Backlog/active-chunk-3 enhancementai

neo-fable commented on Jul 4, 2026, 12:06 PM

Context

The last fact class of the retrospective enrichment family (split from #14721 at PR time — the other five classes are live). Graduations are recorded as Discussion closures carrying the graduation-marker comment vocabulary; gh search does not cover Discussions, so this reader needs a bounded discussions GraphQL query (recently-closed discussions, marker detection in the closing comments).

Acceptance Criteria

A bounded reader returning {ref, headline, at} facts for graduations within the window.
Slots into the compositional coverage label with ONE array entry (the call-site's coveredClasses design — a failing reader drops exactly its class).
Integration test extension: graduation facts counted + rendered from the written handoff; firewall re-asserted.

#14721 (the enrichment family — five classes live at its close) · #14603/#14706 (render + assembler contracts, merged).

Claimable — bounded single-reader; the compositional label makes it a one-array-entry slot-in.

Origin Session ID: b9b95ac6-42f5-47a3-b58f-6071f79657e8 Retrieval Hint: "graduations reader discussions graphql marker retrospective coverage label"

Retrospective graduations reader: discussion-marker detection joins the coverage label

Context

Acceptance Criteria

Related