Files
hermes-agent/agent
Teknium 765933299d fix(compression): a prepared summary is never redone over a moved tail cut
With compression.prepare_ahead, compress() re-planned the tail cut and threw the
completed background summary away whenever the fresh cut landed before the
summary's boundary (the no-LLM prune made tail rows cheaper, tool-group
alignment moved the cut), then wrote a second summary inline while the user
waited. That breaks the one-summary rule: once the background summary exists it
is used, and everything after its boundary is the tail.

The splice check no longer consults the fresh cut at all. A summary is still
discarded only when the messages it covers changed (rewind, shape change, other
session, moved head). The pass planned its own window with a full tail, so the
tail is never empty. The now-unreachable inside_tail reason leaves the
(unreleased) prepared-compaction metric contract.
2026-10-26 00:10:23 -07:00
..
2026-10-09 17:34:38 +02:00
2026-10-09 17:34:38 +02:00
2026-10-09 17:34:38 +02:00
2026-10-21 23:05:11 -04:00
2026-10-09 17:34:38 +02:00
2026-10-09 17:34:38 +02:00
2026-10-08 19:28:23 +02:00
2026-10-20 21:04:30 -04:00
2026-10-20 21:04:30 -04:00
2026-10-21 23:05:11 -04:00
2026-10-09 17:34:38 +02:00
2026-10-09 17:34:38 +02:00
2026-10-09 17:34:36 +02:00
2026-10-09 17:34:38 +02:00
…
2026-10-09 17:34:36 +02:00
2026-10-09 17:34:38 +02:00
2026-10-08 19:54:07 +02:00
2026-10-08 19:54:07 +02:00
2026-10-09 17:34:38 +02:00
2026-10-09 17:34:36 +02:00
2026-10-09 17:34:36 +02:00
2026-10-09 17:34:38 +02:00
2026-10-09 17:34:38 +02:00
2026-10-09 17:34:38 +02:00
2026-10-20 22:18:49 -04:00
2026-10-09 17:34:38 +02:00
2026-10-09 17:34:38 +02:00
2026-10-08 19:54:07 +02:00
2026-10-09 17:34:38 +02:00
2026-10-09 17:34:38 +02:00
2026-10-08 21:29:48 +02:00
2026-10-09 17:34:38 +02:00
2026-10-20 21:04:30 -04:00
2026-10-08 21:29:48 +02:00
2026-10-08 19:54:07 +02:00
2026-10-21 23:05:11 -04:00
2026-10-09 17:34:38 +02:00
2026-10-08 21:29:48 +02:00