JevMade hello@JevMade.com
← Back to guides

JevMade field notes / Technical critique

The case against Jev compaction

Theo Browne argues that independently scoring and deleting tool calls loses thread-level context, can break access to encrypted reasoning, and may cost more by invalidating prompt-cache prefixes.

Original by Theo BrowneAgent workflowsX postOriginal published Source reviewed

Before you dive in

What you’ll find in the original

  1. Compaction should preserve a coherent account of what the agent tried and learned; judging each tool call without its result or surrounding thread can make the agent repeat failed work.
  2. Some providers require an intact history to reuse encrypted reasoning data, so deleting earlier messages can remove information a separate classifier cannot inspect.
  3. Changing an early message invalidates cached content after it; when cache writes cost more than reads, deleting text can increase rather than reduce total spend.
Worth knowing

This is a critique of one fast-jev-compaction design, not evidence that every classifier-assisted context strategy fails. The cost observations come from the author's personal Claude Code and Codex usage.