Automated README summary
Automatically summarized from the README on 9 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.
What it is
A Pi extension for Pi users that decides when to compact a session. Once a run settles with a final answer and the session is idle, it asks a Jev System One judge whether the work sits at a finished checkpoint, then starts Pi's compaction. It does not change how history is compacted.
How it uses Jev
After agent_settled, the judge receives a bounded, redacted snapshot (user messages, recent messages with clipped tool output, previous summary, edited file paths). It answers two choice questions, done and shape, producing score = P(finished) × (0.5 + 0.5 × P(hands_on)). Compaction starts when score ≥ a usage-dependent floor and the session is still idle.
Primitives:choice
Technique worth stealing
Gate compaction timing on a calibrated finished-checkpoint score rather than a fixed token threshold.
Try it
pi install git:github.com/YanzuoLu/pi-compact-timing
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 material0.86
- Shows a System One patternunclear0.50
- Describes handling uncertaintynot found in the excerpt0.33
- Reports measured numbersnot found in the excerpt0.04
- Is a runnable toolFound in material0.96
- Top-10 learning shortlist signalnot found in the excerpt0.35
- Is a replica of the modelnot found in the excerpt0.05
- Solves a common problem (0–2)score on a 0–2 scale1.03 / 2
- About JevFound in material0.97
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 9 Oct 2026.