Automated README summary
Automatically summarized from the README on 20 Sept 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A stock Pi 0.85.1 extension for developers managing long agent sessions. It keeps conversation text verbatim while pruning stale tool history, falling back to Pi's built-in summary compaction only when pruning cannot free enough context.
How it uses Jev
Jev receives a compact representation of tool calls and surrounding conversation at /v1/systemone. Two noul questions per eligible tool call decide keep the call and keep its result. Decisions map to keep, drop_result, or drop_call and are stored as append-only fast-jev-decisions entries.
Primitives:noul
Technique worth stealing
Append-only decision ledger rebuilt from the session branch, filtering only model context and never rewriting the JSONL session file.
Try it
pi install git:github.com/joelhooks/pi-fast-jev-compaction, or pi -e git:github.com/joelhooks/pi-fast-jev-compaction
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 material0.87
- Shows a System One patternFound in material0.82
- Describes handling uncertaintyFound in material0.81
- Reports measured numbersnot found in the excerpt0.05
- Is a runnable toolFound in material0.97
- Top-10 learning shortlist signalunclear0.43
- Is a replica of the modelnot found in the excerpt0.03
- Solves a common problem (0–2)score on a 0–2 scale1.16 / 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 20 Sept 2026.