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	13724
title	feat(ai): PR-outcome reward-computation core (pure) — slice 1 of #9962
state	Closed
labels	aiarchitecturemodel-experience
assignees	[]
createdAt	Jun 21, 2026, 8:46 AM
updatedAt	Jun 21, 2026, 11:42 AM
githubUrl	https://github.com/neomjs/neo/issues/13724
author	neo-opus-ada
commentsCount	0
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Jun 21, 2026, 11:42 AM

feat(ai): PR-outcome reward-computation core (pure) — slice 1 of #9962

Closed v13.1.0/archive-v13-1-0-chunk-5 aiarchitecturemodel-experience

neo-opus-ada commented on Jun 21, 2026, 8:46 AM

Slice 1 of #9962 (PR Outcome Tracker — RLAIF reward signal).

Scope

The PURE PR-outcome → reward mapping core (no I/O, no ChromaDB write), per #9962's reward table:

outcome	reward	rationale
merged clean	1.0	merge-ready code
merged with requested changes	0.7	good, minor polish
closed unmerged	0.0	wasted effort
reverted after merge	-1.0	actively harmful

Deliverable: a pure, fully-tested classifyPrOutcome + computeOutcomeReward module — the testable foundation the rest of #9962 consumes.

Out of scope (tracked on #9962, @neo-opus-grace's RLAIF/memory-core domain)

The PR-outcome SCAN (gh I/O), session-linking, the ChromaDB retroactive-tag WRITE (RLS + dry-run-first per #13722/#13517), and DreamService/runSandman integration. This slice is deliberately pure so it lands independently while the integration is designed.

Refs #9962.

tobiu referenced in commit c666c27 - "feat(ai): pure PR-outcome reward-computation core (#13724) (#13725) on Jun 21, 2026, 11:42 AM

tobiu closed this issue on Jun 21, 2026, 11:42 AM

tobiu referenced in commit efc47d1 - "feat(ai): pure PR-outcome revert-detection core (#13727) (#13729) on Jun 21, 2026, 11:48 AM