Automated README summary
Automatically summarized from the README on 27 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An OpenCode v1 and v2 plugin that prunes stale tool calls and truncates bulky tool results from the outgoing request, keeping everything else word for word. Aimed at OpenCode users who want smaller requests without summarization.
How it uses Jev
For each candidate tool call, the plugin sends Jev one three-way choice question (keep/truncate/drop) with a head/tail excerpt of the output. Jev returns probabilities compared against keepCallThreshold and keepResultThreshold; the outgoing request is rewritten accordingly. Transcript-provable stale calls are dropped without asking Jev.
Primitives:choicenoul
Technique worth stealing
Ask one three-way choice question per candidate tool call with a head/tail excerpt, so pruning is decided on content rather than byte count.
Try it
opencode plugin add fast-jev-opencode, set TYPESAFE_API_KEY, restart; starts in dryRun until fast-jev.json sets dryRun false.
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 material0.88
- Shows a System One patternnot found in the excerpt0.23
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.03
- Is a runnable toolFound in material0.98
- Top-10 learning shortlist signalunclear0.41
- Is a replica of the modelnot found in the excerpt0.04
- Solves a common problem (0–2)score on a 0–2 scale1.05 / 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 27 Sept 2026.