Automated README summary
Automatically summarized from the README on 27 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A standalone DeepSeek Harness (DSH) plugin, installed via dsh.bundle, that lets DSH agents call TypeSafe Jev for structured judgments instead of conversational text. It also adds configurable guardrails, caching, routing and Web UI result cards.
How it uses Jev
Jev's three primitives are exposed as tools: noul returns a 0–1 probability for yes/no judgments, choice returns a selected label with distribution and confidence, score returns a score with distribution and confidence. Optional guardrails use Jev on tool calls (pre-execute risk gate, post-execute review) and confidence thresholds drive verdictFor acceptance/escalation.
Primitives:choicescorenoul
Technique worth stealing
Use calibrated probabilities plus confidence thresholds to gate or escalate agent tool calls rather than trusting generated text.
Try it
Run npm ci --legacy-peer-deps, then dsh plugin --profile jev-dev add /path/to/dsh-jev-plugin and start dsh.
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 material0.81
- Shows a System One patternnot found in the excerpt0.27
- Describes handling uncertaintynot found in the excerpt0.03
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalnot found in the excerpt0.37
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.04 / 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 27 Oct 2026.