Automated README summary
Automatically summarized from the README on 4 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A TypeScript Playwright end-to-end testing harness that runs against a local fixture site. Jev chooses which element to act on and whether the goal is done or the run is stuck; your test code makes the pass/fail call.
How it uses Jev
Each loop step, Playwright observes an element table (el_0, el_1, …), the goal, and visible text. Jev answers in one request: Choice for which element, Noul for goal-done and stuck. Code applies confidence/completion/stuck gates; a low-confidence choice aborts instead of clicking.
Primitives:choicenoul
Technique worth stealing
Map element handles to exact DOM nodes and gate on model confidence so the chosen action is the action that runs.
Try it
npm install; npx playwright install chromium; cp .env.example .env; npm test
Model judgments from README excerpts
Project signals use repository metadata, an existing summary and the first 700 README characters, not the full project. “Not found” means not detected in that material; it does not establish absence. These are the original judgments with recorded models and dates, not source audits or run results.
Models & evaluation dates
- Inclusion gate
jev-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
Evidence
These signals use repository metadata, an existing summary and at most 700 cleaned README characters. ≥ 0.60 means reported in that excerpt; ≤ 0.40 means not found there. The middle band is inconclusive. None is a source-code audit or a test result. The runnable-tool question excludes research experiments; the recommendation question asks for a learning shortlist, not a quality verdict.
- Jev is core to the projectFound in material0.96
- Shows a System One patternFound in material0.93
- Describes handling uncertaintynot found in the excerpt0.09
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolunclear0.48
- Top-10 learning shortlist signalunclear0.42
- Is a replica of the modelnot found in the excerpt0.09
- Solves a common problem (0–2)score on a 0–2 scale1.01 / 2
- About JevFound in material0.99
no-judgment band (0.40–0.60)
no-judgment band (0.40–0.60)
The Jev model and date for each judgment stage are listed above. Card written by DeepSeek V4.1 Flash from the README on 4 Nov 2026.