Fix web_extract URL-to-result positional matching bug
Cluster 97378. Data as of
Nothing open on GitHub. Fix merged in #112245 on 16 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 #112245. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #112245. That is separate from the fix event. - Still open
- Nothing open on GitHub.
A bug caused web_extract to associate provider results with requested URLs by position rather than by URL, meaning reordering or partial failures could poison the cache with mismatched content. These changes fix the matching logic to use URL identity instead of positional order.
Open issues0
Open PRs0
Fixes on record
-
#112245 fix(web): web_extract caches each page under its own requested URL, never by batch position (#111803, #97378, salvage #111806)
files:
plugins/web/tavily/provider.py,tests/tools/test_web_tools_tavily.py,tools/web_tools_extract.py,website/docs/user-guide/features/web-search.md
2 PRs closed without merging
From the close comments: merged via another change 2
Closed issues · 1
- Closed#97378[Bug]: web_extract associates provider results with requested URLs by position — reorder/failure poisons the extract cache
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structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
- #112245
- Closed issues
- 1
- Attempts
- 2 PRs closed without merging
- Fix link checked
- 16 Sep 2026