Automated README summary
Automatically summarized from the README on 13 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An OpenCode V2 plugin for coding agents that classifies each user prompt with TypeSafe Jev before the LLM starts reasoning, so the expensive model only handles requests that need it.
How it uses Jev
The plugin captures the prompt via the prompt hook, then on the first context step asks Jev whether the problem is deterministic. A deterministic verdict (noul >= JEV_THRESHOLD and confidence >= JEV_MIN_CONFIDENCE) injects [JEV PRE-ANALYSIS] with temperature 0 and maxTokens 400; otherwise it fails open.
Primitives:noulchoicescore
Technique worth stealing
Gate the LLM with a cheap typed classifier and fail open on any classifier error.
Try it
opencode plugin add github:murilogteixeira/opencode-jev-pre-llm, then set JEV_API_KEY in .env.
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 material0.72
- Shows a System One patternnot found in the excerpt0.12
- Describes handling uncertaintyFound in material0.93
- Reports measured numbersFound in material0.95
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalunclear0.40
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.10 / 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 13 Oct 2026.