Back
developer-toolsagentsOpen source

fast-jev-compaction

Prune stale coding-agent tool history without rewriting the context that remains.

What Jev decides

Whether each old tool call and its result should remain available.

The library asks two Noul questions for each eligible tool call and result, then local policy keeps, truncates, or removes the pair while preserving ordinary conversation text verbatim.

NOUL
Jev role
Judge whether older tool activity is still relevant to the active coding task.
Input
The current goal, fitted conversation history, tool inputs, and compact result previews.
Output
Two Noul probabilities per eligible tool call.
Decision frequency
When manual or automatic context compaction runs.
Fallback
Use the host agent's built-in compaction when Jev fails or reduction is too small.
Author reported · Source reviewed

How it works

Input
The current goal, fitted conversation history, tool inputs, and compact result previews.
Jev
NOUL
Output
Two Noul probabilities per eligible tool call.

Reported performance

GitHub stars

5.3k

Repository adoption snapshot

Author reported · Source reviewed

Captured Sep 21, 2026

Overview

fast-jev-compaction replaces summary-based compaction with selective pruning. Recent activity is protected, the conversation is fitted into Jev's request budget, and each older tool call is judged for whether the call and its full result still matter.

Keep, truncate, and drop are application actions derived from two Noul probabilities; they are not a Jev Choice response. Failures and insufficient reduction fall back to the host agent's normal compaction path.

Language
TypeScript
License
MIT
Author
tamaratran
Sources checked Sep 21, 2026

Sources

Related projects