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 omp plugin that shrinks conversation context without rewriting it: tool calls and results are scored by Jev, and only low-scoring ones are truncated to a short head plus a recoverable note. All user and assistant text passes through unchanged.
How it uses Jev
Jev scores each tool call and result as a Noul decision over the conversation state (tool names, inputs, message text; outputs replaced by size notes first). Low-probability items are truncated to a head plus a spill-file note; the rest is passed through byte-identical. Decisions are cached and re-applied stickily between rare rewrites.
Primitives:noul
Technique worth stealing
Sticky decision reuse: remember tool_use_id to replacement mappings and re-apply them between rare rewrites so the cached prefix stays byte-identical.
Try it
omp plugin install jerryfane/omp-jev-compaction, then run omp; reduction is on by default.
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 material0.85
- Shows a System One patternnot found in the excerpt0.14
- Describes handling uncertaintynot found in the excerpt0.04
- Reports measured numbersnot found in the excerpt0.02
- Is a runnable toolFound in material0.87
- Top-10 learning shortlist signalnot found in the excerpt0.38
- Is a replica of the modelnot found in the excerpt0.17
- Solves a common problem (0–2)score on a 0–2 scale1.12 / 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.