Automated README summary
Automatically summarized from the README on 29 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Adds meaning-based matchers to Playwright Test so tests check what a page says rather than exact wording, for teams whose copy changes, translates, or is A/B tested.
How it uses Jev
Jev answers noul, choice, and score questions about a locator's text, page body, or JSON value. The matcher compares the returned probability against a threshold (0.8 default) and yields yes, no, or ambiguous; ambiguity and unverified answers fail closed.
Primitives:noulchoicescore
Technique worth stealing
Three-valued verdicts with fail-closed handling of ambiguity, missing keys, and missing fixtures, plus record/replay fixtures keyed by sha256 of model, redacted state, and question.
Try it
npm i -D github:criguex/playwright-jev, set TYPESAFE_API_KEY, then run npx playwright 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 material0.95
- Shows a System One patternunclear0.59
- Describes handling uncertaintyFound in material0.91
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.86
- Top-10 learning shortlist signalunclear0.55
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.13 / 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 29 Oct 2026.