Parsing and retrying model output-cap errors
Cluster 72281 · agent. Data as of
Nothing open on GitHub. Fix merged in #90563 on 20 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 #90563. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #90563. That is separate from the fix event. - Still open
- Nothing open on GitHub.
These issues and fixes address cases where output token limit errors from OpenAI-compatible relays and vLLM were not being parsed correctly, preventing proper retry behavior in the agent.
Open issues0
Open PRs0
Fixes on record
-
#90563 fix(agent): converge vLLM output-cap retries and recover relay 'maximum output tokens' rejections
files:
agent/conversation_loop.py,agent/model_metadata.py,contributors/emails/[redacted:email],contributors/emails/[redacted:email],tests/run_agent/test_run_agent.py,tests/test_output_cap_parsing.py
2 PRs closed without merging
From the close comments: duplicate 1 · merged via another change 1
Closed issues · 1
- Closed#72281[Bug]: Output-cap 400 from OpenAI-compatible relays is not parsed for retry
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structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
- #90563
- Closed issues
- 1
- Attempts
- 2 PRs closed without merging
- Fix link checked
- 20 Aug 2026