Fix insights undercounting mixed tool usage sources
Cluster 9814 · agent. Data as of
Nothing open on GitHub. Fix merged in #109132 on 12 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 #109132. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #109132. That is separate from the fix event. - Still open
- Nothing open on GitHub.
These items address a bug where insights undercount tool usage when both tool_name and tool_calls data sources coexist within or across sessions. The work involves identifying and correcting the counting logic to handle mixed tool usage accurately.
Open issues0
Open PRs0
Fixes on record
-
#109132 Insights count tool usage across mixed tool_name / tool_calls sessions (#9814, salvage #9896)
files:
agent/insights.py,contributors/emails/[redacted:email],tests/agent/test_insights.py
1 PR closed without merging
From the close comments: other 1
-
#9896 fix(insights): count mixed tool usage across sessions · other →
#9990,#9814
Closed issues · 1
- Closed#9814Insights undercount tool usage when tool_name and tool_calls sources coexist
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structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
- #109132
- Closed issues
- 1
- Attempts
- 1 PR closed without merging
- Fix link checked
- 12 Sep 2026