Automated README summary
Automatically summarized from the README on 22 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
An OpenCode plugin that prunes a session's tool history with Noul judgments instead of a model-written summary, keeping relevant calls verbatim and shortening stale outputs. Ships reproducible measurement scripts for any /v1/systemone endpoint.
How it uses Jev
Jev answers Noul questions about each tool output and narration, given the session state. The ranking decides how much to remove (targetReduction budget); the score only chooses between shortening and removing, with a dropFloor. Results drive which outputs are truncated or dropped in the checkpoint.
Primitives:noul
Technique worth stealing
Let the ranking set the removal budget and use the absolute score only to pick between two conservative actions, so calibration drift cannot flip the outcome.
Try it
Add the plugin to opencode.json with baseUrl and model, then run /jev-compact; use dryRun to preview.
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 material0.87
- Shows a System One patternnot found in the excerpt0.28
- Describes handling uncertaintynot found in the excerpt0.13
- Reports measured numbersFound in material0.75
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalFound in material0.71
- Is a replica of the modelnot found in the excerpt0.12
- Solves a common problem (0–2)score on a 0–2 scale1.29 / 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 22 Oct 2026.