Automated README summary
Automatically summarized from the README on 21 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
Sedum lets teams write browser end-to-end tests as plain-English steps inside TypeScript or YAML files, while keeping Playwright for actions and assertions. It targets teams that want selector-free tests runnable on every pull request at low cost.
How it uses Jev
Jev is the default decision model. For each plain-English step it picks the element the sentence refers to; in goal mode it picks the next browser action and target; for verify claims it judges whether the claim holds or is contradicted. Playwright performs actions, and code turns probabilities into pass, low-confidence pass, or fail.
Primitives:choicescore
Technique worth stealing
Use a bounded decision model returning calibrated probabilities for element choice and claim verification, then threshold and contradiction-check the scores deterministically.
Try it
npx sedum init, set TYPESAFE_API_KEY in .env, then npx sedum run tests/example.test.ts --headed
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-1.13.0- Project signals
jev-1.13.0- Category
jev-1.13.0- Pattern tags
jev-1.13.0
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 material0.90
- Shows a System One patternFound in material0.86
- Describes handling uncertaintynot found in the excerpt0.37
- Reports measured numbersnot found in the excerpt0.08
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalunclear0.45
- Is a replica of the modelnot found in the excerpt0.10
- Solves a common problem (0–2)score on a 0–2 scale1.74 / 2
- About JevFound in material0.97
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 21 Oct 2026.