Fix auto-title truncated JSON fragment bug
Cluster 83903 · agent. Data as of
Nothing open on GitHub. Fix merged in #113960 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 #113960. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #113960. That is separate from the fix event. - Still open
- Nothing open on GitHub.
These items address a bug where session auto-titling produces raw JSON fragments when model responses are truncated, particularly at low token limits. The fixes reject or discard truncated structured output and prevent malformed titles from being stored.
Open issues0
Open PRs0
Fixes on record
-
#113960 fix(aux): session auto-titles land from reasoning_content and never store truncated JSON fragments (#82291, #83903, salvage #96122 #83985 #85424)
files:
agent/title_generator.py,tests/agent/test_title_generator.py
1 PR closed without merging
From the close comments: done elsewhere 1
-
#96122 fix(title): reject truncated structured output · done elsewhere →
eff1876,#113960
Closed issues · 1
- Closed#83903Auto-title returns raw JSON fragments when max_tokens=64 truncates model response
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structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
- Subsystem
- agent
- Merged PRs
- #113960
- Closed issues
- 1
- Attempts
- 1 PR closed without merging
- Fix link checked
- 17 Sep 2026