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	14215
title	#14130 slice-1: dimensionConsistencyGatherer function (live-Chroma audit→producer, off dev)
state	Closed
labels	enhancementaiarchitecture
assignees	neo-opus-ada
createdAt	Jun 27, 2026, 8:36 AM
updatedAt	Jun 27, 2026, 9:35 AM
githubUrl	https://github.com/neomjs/neo/issues/14215
author	neo-opus-ada
commentsCount	0
parentIssue	14130
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Jun 27, 2026, 9:35 AM

#14130 slice-1: dimensionConsistencyGatherer function (live-Chroma audit→producer, off dev)

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

neo-opus-ada commented on Jun 27, 2026, 8:36 AM

Slice 1 of #14130 (Slice B's gatherer). The primitive-first half — buildable off dev because both inputs are already there.

Scope (this ticket)

gatherDimensionConsistencyDiagnosis({collections, expectedDimension, serviceId, observedAt, sampleSize, auditFn}) (ai/daemons/orchestrator/services/dimensionConsistencyGatherer.mjs): runs auditCollectionVectorDimensions (#14113, pure/embedder-free) across the supplied live collections → per-collection samples → buildDimensionConsistencyDiagnosis (#14104, detect-only/samples-injected) → a recovery-diagnosis (null when all match). auditFn injectable for tests. Degrade-not-throw; not embed-canary-gated. + 4 unit tests.

Why off-dev / interface-stable

The gatherer emits a standard recovery-diagnosis regardless of the runner's escalate-vs-heal routing, and both auditCollectionVectorDimensions + buildDimensionConsistencyDiagnosis are on dev with exactly-matching sample shapes — so the FUNCTION needs nothing from #14184.

Out of scope (#14130 slice-2)

The runner injection — wiring this gatherer into DataIntegrityDiagnosisService's evidence seam — targets #14184's post-cutover runner and is gated on its 8am merge.

Refs #14130 (parent), #14113 (the audit primitive), #14104 (the producer), #14184 (the runner cutover, slice-2 gate). Self-assigned. Authored by Ada (@neo-opus-ada · Claude Opus 4.8, Claude Code).

tobiu closed this issue on Jun 27, 2026, 9:35 AM