Living doc. Last reviewed 2026-10-31, against main at b38c622 (Phase 39
complete). Reviewed at every phase completion
(WORKING_AGREEMENTS.md). Point new readers here
first; README.md is the how-to, docs/decisions/product-roadmap.md the
phase-by-phase ledger, docs/test-plan/ the case-by-case status (indexed
from TEST_PLAN.md).
Mr Onion is a test automation assistant for websites. Give it a base URL and it crawls the site, groups its pages into page types, inspects one page of each type, writes a Playwright TypeScript suite from what it actually found, runs it in Chromium, and returns a report that says what was tested, how, and — just as prominently — what wasn’t tested and why. The suite is plain Playwright you can keep and run without Mr Onion. The core needs no AI and no API key. It is a local, single-user tool today: a Next.js app on the tester’s machine, not a hosted service.
npm run check:template-unchanged, nightly).benchmarks/ (docs/QUALITY_GATES.md).docs/decisions/deferred-work-register.md).Measured: on the local Toolshop copies, with 37 known bugs in reach, Standard alone finds 30 (TFP-207, 2026-10-16); Standard plus Comprehensive security and accessibility finds 33 (Phase 41 Gate B).
src/lib/library/), applied to any site with that pattern.Site suites, run history and candidates hold one site’s details, so they
live in Mr Onion’s local data folder (%LOCALAPPDATA%\MrOnion on
Windows; MRONION_DATA_DIR overrides), never in the repo.
Browser UI (src/app/page.tsx)
│ fetch
▼
Next.js API routes (src/app/api/*) one Node process, loopback only
crawl · introspect · generate · run · runs · runs/diff · candidates
site-settings · site-ownership · save-suite · health
│
├─ src/lib/introspect, selection crawl, page types, inspection (Playwright)
├─ src/lib/generate template generator, Comprehensive sets
├─ src/lib/gap-writer, candidates, gap tests, candidate pool, promotion
│ library, site-suites
├─ src/lib/run job queue, gates, request guard, host limits,
│ child Playwright runs with a minimal environment
├─ src/lib/report coverage, summary, diff, HTML export
└─ src/lib/storage data folder: runs/, site-suites/, candidates/
│
▼
Chromium (Playwright) ──► target site optional: Ollama (local model),
Claude Code CLI (gap writer)
run.json, the executed
suite.spec.ts, evidence/), written atomically; one Mr Onion process
per data folder.POST /api/run returns a job (202); the UI polls
GET /api/run. Concurrency is by worker count with per-host request caps
(Phase 39)./api/run executes generated code with the user’s
privileges. That is accepted under the local-only model (Phase 16) and is
why Mr Onion must never be bound to a non-loopback interface or tunnelled
(README.md, Security model). Model-written code is restricted to the page
and expect and runs with no keys in its environment — not a sandbox; the
Docker sandbox is Phase 45..github/workflows/).In order (product-roadmap.md, deferred-work-register.md):
v0.2.0 (2026-10-31, the first
tagged version); then Phase 47, Mr Onion as a step in a
target’s CI pipeline (docs/decisions/phase-47-ci-integration-decision-record.md),
with the application’s rename (D39, “Mr Onion” proposed) before its
Docker image is published.saas-prerequisites.md); the OpenAI path (Phase 28, parked).skills/A parallel track, not a replacement: skills/ packages the testing and
engineering judgment behind Mr Onion as an installable Claude Code plugin
(mr-onion-skills, 12 skills under skills/testing/ and
skills/engineering/), usable without the app. skills/proposed/ holds
SRE and DORA skills under review, four of them being adopted (TFP-236).
Rewriting TestForge as skills only was considered and declined
(docs/REIMAGINING.md, REIMAGINING-RESPONSE.md).