Automated README summary
Automatically summarized from the README on 7 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An OpenCode V2 plugin that lets an agent evaluate text with Jev or text and images with OpenAI Decisions. Both APIs answer typed questions with probabilities instead of generating prose, and the calling agent chooses categories and interprets answers.
How it uses Jev
The decisions_evaluate tool defaults to Jev and forwards provider-native questions to OpenCode Console Jev. The agent supplies the taxonomy and final labels; Jev returns answers keyed by question ID. The legacy jev_jev_evaluate tool keeps the original state and question-map format.
Primitives:choicescorenoul
Technique worth stealing
Ask every question in a single call: Jev evaluates them in parallel and in isolation, so adding questions barely changes latency.
Try it
opencode plugin add github:matthewpetela/opencode-decisions-plugin
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 excerpt0.25
- Shows a System One patternnot found in the excerpt0.20
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.95
- Top-10 learning shortlist signalnot found in the excerpt0.25
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.03 / 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 7 Oct 2026.