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	12495
title	pull-request decision-atom / compression pilot — or explicit deferral (#11605 AC5)
state	Closed
labels	enhancementairefactoringmodel-experience
assignees	neo-opus-ada
createdAt	Jun 4, 2026, 2:03 PM
updatedAt	Jun 4, 2026, 8:16 PM
githubUrl	https://github.com/neomjs/neo/issues/12495
author	neo-opus-ada
commentsCount	3
parentIssue	11605
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
blockedBy	[]
blocking	[]
closedAt	Jun 4, 2026, 8:16 PM

pull-request decision-atom / compression pilot — or explicit deferral (#11605 AC5)

Closed v13.0.0/archive-v13-0-0-chunk-16 enhancementairefactoringmodel-experience

neo-opus-ada commented on Jun 4, 2026, 2:03 PM

Sub of Epic #11605 (compress skill baggage → decision-atom maps). Fills the AC5 BLOCKER from @neo-gpt's epic-resolution review (2026-06-03): pull-request is the one hot-path skill not yet piloted-or-deferred — the author-side dual of the merged pr-review pilot (#11893 / #11904). (#11896 improved pull-request next-lane behavior but was not a compression pilot.)

Scope

Assess the pull-request hot-path runtime substrate (pull-request-workflow.md + references/review-response-protocol.md) via ai:skill-size-report, then either:

Pilot — compress incident-archaeology / tool-mechanics out of runtime substrate into Bias → Rule → Rationale → Trigger atoms + atlas pointers (tool-mechanics → tool-description SSOT per #12486); behavior-preserving.
Defer — if already lean post-#12486 / #12488, publicly defer with a byte-baseline + the deferral rationale.

Acceptance Criteria

pull-request substrate either compressed (net loaded-byte reduction, measured) OR explicitly publicly deferred with byte-baseline evidence.
Behavior-preserving — no rule loss; lint-skill-manifest + lint-agents green.
Decision (pilot vs defer) recorded with ai:skill-size-report before/after (or baseline).

Contract Ledger

Target Surface	Source of Authority	Proposed Behavior	Fallback	Docs	Evidence
`pull-request` skill substrate	#11605 AC5 + gpt resolution matrix	compress to decision-atoms OR explicit deferral	defer-with-evidence if already lean	yes	`ai:skill-size-report` before/after

tobiu referenced in commit d1e0d78 - "refactor(agentos): compress pull-request-workflow.md decision-atoms — strip archaeology + extract corrective-rotation behind trigger (#12495) (#12503) on Jun 4, 2026, 8:16 PM

tobiu closed this issue on Jun 4, 2026, 8:16 PM