Automated README summary
Automatically summarized from the README on 24 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A TypeScript CLI that categorizes Playwright test failures using System 1 decision models, produces an HTML dashboard and PR summary, enforces CI exit-code gates, and includes an AI QA calibration benchmark for teams running Playwright in CI.
How it uses Jev
When Laya's confidence is below τ=0.78 or its top-2 margin is too small, the cascade escalates the extracted failure state (error, stack, HTTP 4xx/5xx, console) to Jev. Jev returns typed probabilities for root_cause (choice), retryable (noul), and release_blocker (score), which feed the CI gate and report.
Primitives:choicenoulscore
Technique worth stealing
Confidence-gated cascade: cheap local model handles clear failures, escalating only low-confidence compound cases to a calibrated cloud decision API.
Try it
npm run demo (zero-config, Node.js 22.6+); npm run eval for the calibration benchmark.
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 material0.74
- Shows a System One patternnot found in the excerpt0.36
- Describes handling uncertaintynot found in the excerpt0.05
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.61
- Top-10 learning shortlist signalnot found in the excerpt0.11
- Is a replica of the modelnot found in the excerpt0.15
- Solves a common problem (0–2)score on a 0–2 scale1.12 / 2
- About JevFound in material0.98
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 24 Oct 2026.