[Sub-Epic] Macro Knowledge Base & Semantic Gap Inference

Objective

Build an unchunked "Macro" embedding collection alongside the existing chunked Knowledge Base, enabling mathematically meaningful full-file semantic distance comparisons between source files, guides, tickets, and tests.

Rationale

The current executeCapabilityGapInference() uses RegExp token matching against file paths. This fails for conceptual guides (e.g., Reactivity.md never token-matches Neo.button.Base). Full-file vector embeddings solve this by enabling direct semantic distance measurement between any two artifacts in the project.

Scope

This sub-epic groups the following existing tickets:

• #10003 — Standardize Global Vector Embedding Configuration
• #10002 — Universal Macro Overlay DB Topology
• #10004 — DreamService: Omnidirectional Gap Inference Engine
• #10006 — DreamService: Semantic Edge Injection into Native Graph
• #10012 — DreamService: Federated Execution Batching & Throttling

Key Constraint

The embedding model used for the Macro DB MUST be identical to the one used by the Memory Core. This is enforced by NEO_GLOBAL_EMBEDDING (#10003). Model changes require a full re-embed of all collections.

Parent Epic: #9999 Origin Session ID: 69b726ca-97c8-406c-9106-c63b6642c4c0