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	14236
title	Data-integrity sweep config comment asserts the DELETED escalate/operator-gated model (substrate-scent)
state	Closed
labels	ai
assignees	neo-opus-vega
createdAt	Jun 27, 2026, 3:23 PM
updatedAt	Jun 27, 2026, 4:04 PM
githubUrl	https://github.com/neomjs/neo/issues/14236
author	neo-opus-vega
commentsCount	0
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Jun 27, 2026, 4:04 PM

Data-integrity sweep config comment asserts the DELETED escalate/operator-gated model (substrate-scent)

Closed v13.1.0/archive-v13-1-0-chunk-7 ai

neo-opus-vega commented on Jun 27, 2026, 3:23 PM

Problem

The data-integrity sweep config leaf comment (ai/config.mjs + ai/config.template.mjs) described the DELETED escalate/operator-gated model: "escalates a data-integrity diagnosis (operator page) on drift ... Detect-only; data mutation stays operator-gated." That is the smoke-detector anti-pattern #14132 deletes and Epic #14039 now forbids — and it re-seeds the wrong mental model for any peer reading the config. Operator-flagged 2026-06-27 ("the OPPOSITE of our self healing goal").

The data runner (DataIntegrityDiagnosisService) already routes every diagnosis to applyHeal autonomously (the cutover landed) — only this comment lagged.

Fix

Correct the comment to the autonomous-heal model: the sweep emits a data-integrity diagnosis routed to the autonomous data-recovery actuator — the store is HEALED, not paged (no operator in cloud).

Acceptance Criteria

ai/config.mjs + ai/config.template.mjs data-integrity sweep comment carries no operator-gated / operator-page / "detect-only; data mutation stays operator-gated" framing.
config↔template SSOT lint passes (in sync).

Part of #14132 (the escalate/operator deletion). Operator-directed.

Authored by Vega (@neo-opus-vega · Claude Opus 4.8); filed via the gh relay (gh-author neo-opus-ada = shared-token artifact).

tobiu referenced in commit 66c9930 - "docs(ai): data-integrity sweep config comment → autonomous-heal model, drop operator-gated/detect-only framing (#14236) (#14237) on Jun 27, 2026, 4:04 PM

tobiu closed this issue on Jun 27, 2026, 4:04 PM