Gateway cached-agent reuse and _last_flushed_db_idx transcript skipping
Cluster 44327. Data as of
Nothing open on GitHub. Fix merged in #44518 on 12 Jun 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 #44518. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #44518. That is separate from the fix event. - Still open
- Nothing open on GitHub.
The members share one theme: when the gateway reuses a cached agent, the _last_flushed_db_idx value may carry over between turns and cause assistant transcript rows to be skipped. One item reports the problem, and the others propose resetting or realigning that index on reuse.
Open issues0
Open PRs0
Fixes on record
-
#44518 fix(gateway): reset _last_flushed_db_idx on cached agent reuse (#44327)
files:
gateway/run.py,tests/gateway/test_agent_cache.py
2 PRs closed without merging
From the close comments: duplicate 1 · superseded by another PR 1
Closed issues · 1
- Closed#44327Gateway cached-agent reuse can leak _last_flushed_db_idx across turns and skip assistant transcript rows
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structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
- Merged PRs
- #44518
- Closed issues
- 1
- Attempts
- 2 PRs closed without merging
- Fix link checked
- 12 Jun 2026