ReadError stream errors and session lock handling
Cluster 104303. Data as of
Nothing open on GitHub. Fix merged in #114402 on 17 Sep 2026. Check it covers your case.
The short answer
- Known?
- Yes. 3 related items grouped here, 1 issue already closed.
- Fix event
- A fix was merged to main in PR #114402. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
unresolved. That is separate from the fix event. - Still open
- Nothing open on GitHub.
These items address how ReadError errors in provider streams are handled, including retry logic and a related issue where a failed stream with stream_opened=false causes a lease to be held indefinitely, locking out subsequent turns. A watchdog fallback for missing agent snapshots is also included.
Open issues0
Open PRs0
Fixes on record
-
#114402 fix(gateway): watchdog falls back to wall-clock when no agent snapshot exists
files:
gateway/run.py,tests/gateway/test_abandoned_turn_process_cleanup.py
1 PR closed without merging
From the close comments: done elsewhere 1
-
#104452 fix(codex): retry raw pre-stream ReadError · done elsewhere →
e625602,#104303
Closed issues · 1
- Closed#104303Turn lease held forever when a provider stream fails with ReadError (stream_opened=false) — session locks out, all following turns rejected
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structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
0.67: 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
- #114402
- Closed issues
- 1
- Attempts
- 1 PR closed without merging
- Fix link checked
- 17 Sep 2026