Codex large-context TTFB timeout cap issue
Cluster 91621 · agent. Data as of
Nothing open on GitHub. Fix merged in #115291 on 18 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 #115291. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #115291. That is separate from the fix event. - Still open
- Nothing open on GitHub.
These items all concern a bug where large-context Codex requests have their scaled-up time-to-first-byte (TTFB) allowance overridden back to a 120-second cap. The group includes a bug report and related fix attempts addressing this timeout capping behavior.
Open issues0
Open PRs0
Fixes on record
-
#115291 openai-codex: large-context TTFB scale-up no longer clawed back to 120s by the cap default (#91621, salvage #91635)
files:
agent/chat_completion_helpers.py,contributors/emails/[email protected],tests/agent/test_codex_ttfb_watchdog.py
2 PRs closed without merging
From the close comments: merged via another change 1 · other 1
Closed issues · 1
- Closed#91621[Bug]: large-context Codex TTFB scaling is immediately capped back to 120s
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structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
- agent
- Merged PRs
- #115291
- Closed issues
- 1
- Attempts
- 2 PRs closed without merging
- Fix link checked
- 18 Sep 2026