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	13746
title	feat(ai): CI-failure file-level dedup parser (pure) — slice 1 of #9888
state	Closed
labels	aiarchitecturemodel-experience
assignees	neo-opus-ada
createdAt	Jun 21, 2026, 12:01 PM
updatedAt	Jun 21, 2026, 9:41 PM
githubUrl	https://github.com/neomjs/neo/issues/13746
author	neo-opus-ada
commentsCount	1
parentIssue	null
subIssues	[]
subIssuesCompleted	0
subIssuesTotal	0
contentTrust
projected
quarantined	0
signals	[]
blockedBy	[]
blocking	[]
closedAt	Jun 21, 2026, 9:41 PM

feat(ai): CI-failure file-level dedup parser (pure) — slice 1 of #9888

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

neo-opus-ada commented on Jun 21, 2026, 12:01 PM

Slice 1 of #9888 (Autonomous CI Failure Triaging via Swarm Knowledge Graph)

The pure file-level-dedup parser — per the operator + Gemini (Antigravity) design refinement on #9888: dedup CI failures to the test-file level (one ticket per failing spec-file, not per it() / stack-trace), so a cascading failure (1 structural break → 10 failing tests across a file) yields ONE ticket, keeping the tracker's signal-to-noise clean.

Deltas

ai/services/ingestion/parseCiFailures.mjs (new): pure parseCiFailures(report) → string[] — extracts the failing spec-file paths from a Playwright JSON report (reporter: json; nested suites[].specs[], spec.ok === false = failing, spec.file = path), deduped to unique file paths (the file-level dedup keys the #9888 graph-check binds to). Accepts the parsed object OR a raw JSON string.

Out of scope (stays on #9888, the integration)

The graph-check ("does this file have an OPEN ticket bound?") + the ticket-create + the CI-log fetch (the I/O). Same pure-only carve as the RLAIF cores (#13724 / #13727).

Acceptance Criteria

pure parseCiFailures(report) export; extracts + dedupes failing spec-file paths to file-level from a Playwright JSON report; accepts the parsed object OR a raw JSON string; total (non-object / unparseable → []).
Unit tests: single failure, multi-failures-one-file (dedup → 1), multi-files, nested suites, raw-JSON-string, no-failures → [], malformed → [].

Slice of #9888. Surfaced by @neo-opus-ada.

tobiu referenced in commit 03893dc - "feat(ai): CI-failure file-level dedup parser (pure) — slice 1 of #9888 (#13746) (#13749) on Jun 21, 2026, 9:41 PM

tobiu closed this issue on Jun 21, 2026, 9:41 PM