Codex image-too-large error triggers shrink retry
Cluster 106337. Data as of
Nothing open on GitHub. Fix merged in #106525 on 9 Sep 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 #106525. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #106525. That is separate from the fix event. - Still open
- Nothing open on GitHub.
A bug where OpenAI Codex patch-budget 400 errors were not classified as image-too-large, causing automatic image shrink recovery to be bypassed. These issues and fixes address classifying and handling those errors so the shrink-and-retry path runs correctly.
Open issues0
Open PRs0
Fixes on record
-
#106525 fix(agent): Codex patch-budget image 400 now shrinks and retries the image (#106337, salvage #106345)
files:
agent/error_classifier.py,agent/turn_recovery.py,tests/run_agent/test_image_shrink_recovery.py
2 PRs closed without merging
From the close comments: merged via another change 1 · superseded by another PR 1
Closed issues · 1
- Closed#106337[Bug] OpenAI Codex patch-limit error bypasses automatic image shrink recovery
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structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
- #106525
- Closed issues
- 1
- Attempts
- 2 PRs closed without merging
- Fix link checked
- 9 Sep 2026