Automated README summary
Automatically summarized from the README on 9 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A DeepSeek Harness plugin that registers a `jev` tool and a Settings page, letting coding agents batch typed judgements over many items — log lines, tool outputs, failing tests, search results — without loading them into model context.
How it uses Jev
The `jev` tool sends a `state` string plus `questions` (each `noul`, `choice` or `score`) to a configured provider and returns typed answers, probabilities and confidence. Jev evaluates all questions in parallel against the same state, so 50 questions cost about the same as one.
Primitives:choicescorenoul
Technique worth stealing
Batch many atomic questions against one shared state block in a single request instead of spawning a subagent per item.
Try it
dsh plugin --profile web add dsh-jev-plugin, then restart the harness and set the API key in Settings → Plugins → Jev.
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 material0.83
- Shows a System One patternFound in material0.89
- Describes handling uncertaintynot found in the excerpt0.06
- Reports measured numbersnot found in the excerpt0.13
- Is a runnable toolFound in material0.89
- Top-10 learning shortlist signalunclear0.50
- Is a replica of the modelnot found in the excerpt0.06
- Solves a common problem (0–2)score on a 0–2 scale1.22 / 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 9 Oct 2026.