Bug fix: compaction tail duplication in archive
Cluster 86366 · evals/compaction. Data as of
Nothing open on GitHub. Fix merged in #99545 on 31 Aug 2026. Check it covers your case.
The short answer
- Known?
- Yes. 4 related items grouped here, 1 issue already closed.
- Fix event
- A fix was merged to main in PR #99545. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #99545. That is separate from the fix event. - Still open
- Nothing open on GitHub.
These members address a bug where the carried-forward compaction tail is incorrectly marked as compacted, causing it to be duplicated in recall on each compaction cycle. The fixes adjust how the tail is handled and archived during the compaction process.
Open issues0
Open PRs0
Fixes on record
-
#99545 fix(state): archive carried-forward compaction tail as rewind rows (#86366 salvage of #93160)
files:
agent/context_compressor.py,agent/conversation_compression.py,hermes_state.py,tests/hermes_state/test_86366_tail_rewind_semantics.py,tests/hermes_state/test_86366_watermark_interplay.py
2 PRs closed without merging
From the close comments: done elsewhere 1 · duplicate 1
Closed issues · 1
- Closed#86366[Bug]: archive_and_compact marks the carried-forward tail compacted=1, duplicating it in recall once per compaction
How this cluster was grouped
-
Link evidence (
structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference. -
Pairwise link density
0.50: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36.1.00means every pair is linked.
Pick up a Lab task
Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.
Open the LabAt a glance
- Subsystem
- evals/compaction
- Merged PRs
- #99545
- Closed issues
- 1
- Attempts
- 2 PRs closed without merging
- Fix link checked
- 31 Aug 2026