Anthropic · Community reports
Jev + Claude Code: context compaction and user feedback
A plugin scores old tool calls before pruning context. Its implementation and a user report show both the approach and its limits.
We checked the cited posts and documentation. Measurements are attributed to their authors and have not been independently rerun by this site.
Selecting which tool history to keep
tamara’s fast-jev-compaction project applies Jev to Claude Code’s conversation history. It asks whether a tool call and its result still matter, then keeps, truncates or removes that material. User and assistant text remains verbatim in the resulting conversation.
The implementation pairs calls with results and protects recent messages. The state sent to Jev omits full tool-result bodies and can shorten other material to fit its budget. Preserving retained text does not mean the model sees an unlimited, unabridged transcript.
Sources:[6] tamara[8] tamaratran
What a Claude Code user reported
Alex Volkov reports that the plugin reduced a session from nearly one million tokens to about 86,000 in roughly one second. His post links to the project and describes an enthusiastic first-hand experience.
Those numbers belong to his session. The post does not establish a typical reduction ratio, a billing saving or unchanged performance on later coding tasks. The repository also describes its separate native demo app as scripted and making no API calls, so that animation cannot establish live API speed.
Sources:[7] Alex Volkov[8] tamaratran
Configuration and recovery behavior
The checked repository documents an early-access Claude Code function-hook integration, requiring Claude Code 2.1.274 or later and an opt-in setting. Installation and environment configuration belong to that project’s README; check those instructions against the version you run.
The hook falls back to Claude Code’s built-in summary when Jev fails or the reduction is too small. Token counts in the library are estimates. The author also warns that a probability is not proof that a tool result is safe to delete, even if the assistant can run the tool again.
Sources:[8] tamaratran
Questions about Jev + Claude
Does fast-jev-compaction summarize Claude messages?
Its documented approach selects and prunes tool calls and results while retaining user and assistant text verbatim in the output. The separate state sent to Jev can be shortened to fit its budget.
Sources:[8] tamaratran
Is the reported one-second compaction a guarantee?
No. It is Alex Volkov’s report about one session. The sources do not establish typical latency or unchanged downstream task accuracy.
Sources:[7] Alex Volkov[8] tamaratran
Sources and reading notes
The summaries below are paraphrases. Each link opens the original source, including its surrounding context.
tamara (@tamarajtran)
Published:
Source checked:
[6] Scoring tool calls for context compaction
The project author proposes using Jev to score tool calls and discard irrelevant material during compaction.
Project announcement. The repository says its native demo app is scripted and makes no API calls, so its animation is not timing evidence.
tamaratran
Source checked:
[8] fast-jev-compaction implementation and limitations
The plugin scores tool calls and results, preserves user and assistant text in its output, and keeps calls paired with their results. Its hook falls back to built-in compaction on errors or insufficient reduction.
The README documents early-access Claude Code function hooks, estimated token sizes and a scripted native demo. It explicitly warns that a probability does not prove a result is safe to delete.
Alex Volkov (@altryne)
Published:
Source checked:
[7] A user report of Claude context reduction
Volkov reports reducing a Claude session from nearly one million tokens to about 86,000 in roughly one second using fast-jev-compaction.
Individual experience, not a controlled benchmark or a measure of downstream task accuracy. The timestamp is the edited-post time shown by X.