Automated README summary
Automatically summarized from the README on 1 Nov 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A runnable JavaScript demo comparing decision models (TypeSafe Jev, Microsoft-Decision-1) with a regular LLM (GPT-6 Luna) on four everyday coding-agent decisions: issue triage, tool-call gating, fix ranking, and task routing.
How it uses Jev
Jev answers typed questions (choice, score, yes/no) over issue text or candidate fixes. Code reads each answer's probability and confidence: paging a maintainer at P(needs human) ≥ 0.5, allowing/asking/blocking tool calls by thresholds, and routing low-confidence tasks to a human.
Primitives:choicescorenoul
Technique worth stealing
Send state plus typed questions in one request and gate downstream actions on the returned per-option probabilities.
Try it
npm run demo (offline mock, no keys); npm run triage, gate, rank or route for one scenario.
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 projectnot found in the excerpt0.07
- Shows a System One patternunclear0.60
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolunclear0.47
- Top-10 learning shortlist signalnot found in the excerpt0.27
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale0.60 / 2
- About JevFound in material0.92
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 1 Nov 2026.