Claude Code without Context summarization!

Frame from the clip posted with this case
Still from the clip posted with this case; watch it in the original post on X.

Built the open-source fast-jev-compaction plugin that uses Jev to drop or shorten old tool calls in Claude Code, cutting context from ~1M to 86K tokens.

The original post, translated

Interesting! Claude Code without Context summarization! The open-source fast-jev-compaction plugin, with Jev's help, removes or shortens old and irrelevant Tool Calls; but the conversation text remains untouched. In one example, the Context went from nearly 1 million to 86 thousand tokens. https:// github.com/tamaratran/fas t-jev-compaction …

Show the original post in its source language ▾

جالبه! Claude Code بدون خلاصه‌سازی Context! پلاگین متن‌باز fast-jev-compaction با کمک Jev، Tool Callهای قدیمی و نامرتبط رو حذف یا کوتاه می‌کنه؛ اما متن مکالمه دست‌نخورده باقی می‌مونه. در یک نمونه، Context از نزدیک ۱ میلیون به ۸۶ هزار توکن رسید. https:// github.com/tamaratran/fas t-jev-compaction …

The post above is a machine translation from ar; the untranslated text is in the fold-out.

Engagement when collected

Views350
Likes2
Bookmarks0
Reposts0
Replies0
Quotes0

Numbers are a snapshot taken from X when the case was added to the library (schema v1, collected 2026-09-19); they will not match today.

Where this case fits

Filed under agents & workflows, coding & developer tools. In the pattern Jev is built for, the model answers a bounded question per step — and ordinary code acts on the answer, because the answer is already a value rather than a paragraph. Other posts in the same family are on the agents & workflows page.

Related Jev cases

Keep browsing: all 1173 Jev cases · more from @Elizaium · builders · what Jev is

Last updated: 2026-09-22 · sources & corrections · every card links to its author's original post