jevbooks

← All projects

pi-jev-compaction

MaxIvanyshen/pi-jev-compaction

Jev scores conversation turns for relevance before pi compacts context.

Scoring & Ranking0.90Runner-up: Data Labeling & CurationGhostwriter
Automated README summary

Automatically summarized from the README on 8 Oct 2026; not a run by jevbooks. Run instructions and author-reported outcomes still need verification.

What it is

A pi extension for developers using pi's session compaction. It filters conversation turns by relevance before summarization, so dead-end turns are dropped instead of blindly summarized.

How it uses Jev

On session_before_compact, each turn about to be summarized gets its own Jev call (four at a time) asking whether it should be kept. Turns with keep probability under 0.25 are removed from the compaction input; the first turn is always kept.

Primitives:choice

Technique worth stealing

Use a calibrated keep/drop probability per turn as a pre-filter before an LLM summarization pass.

Try it

pi install git:github.com/MaxIvanyshen/pi-jev-compaction

View on GitHub

Start using Jev: API key and your first request →

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 material0.88
  • Shows a System One patternFound in material0.83
  • Describes handling uncertaintyFound in material0.71
  • Reports measured numbersnot found in the excerpt0.05
  • Is a runnable toolFound in material0.98
  • Top-10 learning shortlist signalunclear0.49
  • Is a replica of the modelnot found in the excerpt0.03
  • Solves a common problem (0–2)score on a 0–2 scale1.14 / 2
  • About JevFound in material0.97
Signals
Jev is core to the project0.88Shows a System One pattern0.83Describes handling uncertainty0.71Reports measured numbers0.05Is a runnable tool0.98Top-10 learning shortlist signal0.49Is a replica of the model0.0300.51Solves a common problem (0–2)1.14 / 2012

no-judgment band (0.40–0.60)

Design patterns
Ghostwriter0.80Funnel0.69Fail open, fail closed0.68Viewfinder0.4500.51

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 8 Oct 2026.