Automated README summary
Automatically summarized from the README on 19 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
el-jev v2 is a local daemon and GitHub Copilot CLI extension that gives fast typed System-1 verdicts (intent, deep-analysis need, execution tier) and compiles them into execution constraints, for developers routing agent turns cheaply.
How it uses Jev
Jev (Microsoft-Decision-1, or Cohere via --engine) evaluates state text in one pass: intent as choice, needs_deep_analysis as noul, execution_tier as choice. The gate compiles probabilities into an imperative contract injected via onUserPromptSubmitted; onPreToolUse denies task/run_dynamic_workflow on enforceable fast_direct turns.
Primitives:choicenoulscore
Technique worth stealing
Compile numeric gate probabilities into imperative RLHF-native execution constraints, then enforce them deterministically at the harness tool boundary.
Try it
pip install -e ., az login, python -m eljev configure --engine md1, then python -m eljev daemon start and install-extension.
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 projectnot found in the excerpt0.21
- Shows a System One patternFound in material0.77
- Describes handling uncertaintynot found in the excerpt0.08
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalnot found in the excerpt0.31
- Is a replica of the modelnot found in the excerpt0.08
- Solves a common problem (0–2)score on a 0–2 scale1.26 / 2
- About JevFound in material0.77
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 19 Oct 2026.