Jev Compaction: scoring old tool calls instead of summarizing agent context
Jev Compaction scores old tool call pairs against the current goal and keeps, trims, or drops them by threshold, so a lossy summary can't turn "maxAttempts = 2" into "fix retry handling".
Jev Engineering: your agent's context summary can quietly delete the one rule it needs the pattern is Jev Compaction: stop summarizing agent context. decide what survives long agent runs pile up old tool calls and results a lossy summary can turn "maxAttempts = 2" into "fix retry handling" the exact limit is gone in this pattern, Jev scores old tool pairs against the current goal call needed? full result needed? your app sets the threshold and owns the policy keep: the failing test, exactly as seen. expected 2 calls, received 5 trim: the old file read. call + original head + "[… 8,360 chars omitted]" drop: the dead-end search. call and results leave together, no orphan result goal, rule and exact failure all reach the next model call. the noise doesn't bookmark & watch now ↓
This post quotes another post: “Jev single-choice selection breaks the agent wrong-tool loop”