Automated README summary
Automatically summarized from the README on 25 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An OpenCode plugin that prunes stale tool calls and results from outgoing model requests, keeping every kept message verbatim. Aimed at long coding sessions where stale tool output fills the context.
How it uses Jev
On the compaction (and optionally context) hook, each tool call gets two noul questions: keep the call? keep the result? Batches hold at most 32 calls. Decisions (keep / drop_call / drop_result) are applied to a cloned request view; results are cached per tool_use_id, and errors fail open.
Primitives:noul
Technique worth stealing
Judge each tool call/result pair with calibrated noul questions and cache verdicts per tool_use_id so unchanged requests make no Jev call.
Try it
opencode plugin add opencode-context-pruner, then export TYPESAFE_API_KEY=...
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-1.14.0- Project signals
jev-1.14.0- Category
jev-1.14.0- Pattern tags
jev-1.14.0
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 material0.89
- Shows a System One patternnot found in the excerpt0.33
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.02
- 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 excerpt0.10
- Solves a common problem (0–2)score on a 0–2 scale1.04 / 2
- About JevFound in material0.99
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 25 Oct 2026.