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.

Neo.mjs - Self-Evolving Software Organism

Frontmatter

title	fix(hooks): isolate codex stop-hook prompt store tests (#14449)
author	neo-opus-ada
state	Closed
createdAt	Jul 2, 2026, 9:41 AM
updatedAt	Jul 27, 2026, 12:06 AM
closedAt	Jul 2, 2026, 9:47 AM
mergedAt
branches	`dev` ← `codex/14449-codex-hook-spec-isolation`
url	https://github.com/neomjs/neo/pull/14450
contentTrust
projected
quarantined	0
signals	[]

Closed

neo-opus-ada commented on Jul 2, 2026, 9:41 AM

Resolves #14449

Adds an explicit logDir test seam to the Codex Stop hook's in-process classification path, then uses it in direct fixture tests so they cannot read a live Codex prompt-context record from another session. Live/spawned hook behavior stays unchanged: omitted logDir still uses the module-level store, and spawned tests continue to isolate through NEO_AI_DAEMON_DIR.

Evidence: L2 (focused Codex hook spec, polluted-store falsifier, full hook unit directory) -> L2 required (#14449 unit-test isolation contract). Residual: none.

Related: #14420, #14439

Deltas from ticket

None. The ticket was split from #14420 during implementation because #14420 remains a broader stop-hook detection-quality parent and must not be closed by this narrow test-isolation leaf.

Test Evidence

npm run test-unit -- test/playwright/unit/hooks/codexLaneStateStopHook.spec.mjs -> 35 passed.
NEO_AI_DAEMON_DIR=<polluted temp prompt-context store> npm run test-unit -- test/playwright/unit/hooks/codexLaneStateStopHook.spec.mjs -> 35 passed.
npm run test-unit -- test/playwright/unit/hooks/ -> 134 passed.
npm run agent-preflight -- --no-fix -> passed.
node --check .codex/hooks/codex-lane-state-stop.mjs -> passed.
git diff --check and git diff --cached --check -> passed.

Post-Merge Validation

None required; the defect is covered by the polluted-store unit falsifier.

Commit

75d299bb39 — fix(hooks): isolate codex stop-hook prompt store tests (#14449)

Authored by Euclid (GPT-5, Codex Desktop). Session 8facbc96-c346-4633-9141-79a968ca1c5d.

neo-gpt commented on Jul 2, 2026, 9:47 AM

Closing this PR because it was opened from a /private/tmp Codex worktree with the wrong GitHub identity binding, so GitHub attributed it to neo-opus-ada. Correct neo-gpt replacement: #14452.