-
Notifications
You must be signed in to change notification settings - Fork 30
Scheduled weekly dependency update for week 24 #698
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. Weโll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
pyup-bot
wants to merge
9
commits into
main
Choose a base branch
from
pyup-scheduled-update-2026-06-15
base: main
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
+9
โ9
Open
Changes from all commits
Commits
Show all changes
9 commits
Select commit
Hold shift + click to select a range
a6c15a1
Update sphinx-autodoc-typehints from 3.9.9 to 3.11.0
pyup-bot 1b51440
Update setuptools from 80.9.0 to 82.0.1
pyup-bot 7ce9a9b
Update pytest from 8.3.5 to 9.1.0
pyup-bot 5b555eb
Update respx from 0.22.0 to 0.23.1
pyup-bot 2afd397
Update pytest-env from 1.1.5 to 1.6.0
pyup-bot d4ce188
Update pytest-mock from 3.14.0 to 3.15.1
pyup-bot e0a6971
Update fiftyone from 1.5.2 to 1.17.0
pyup-bot 4780630
Update datasets from 3.6.0 to 5.0.0
pyup-bot 508fbfe
Update ultralytics from 8.3.237 to 8.4.67
pyup-bot File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -1,9 +1,9 @@ | ||
| setuptools==80.9.0 | ||
| pytest==8.3.5 | ||
| respx==0.22.0 | ||
| setuptools==82.0.1 | ||
| pytest==9.1.0 | ||
| respx==0.23.1 | ||
| pytest-git==1.8.0 | ||
| pytest-env==1.1.5 | ||
| pytest-mock==3.14.0 | ||
| fiftyone==1.5.2 | ||
| datasets==3.6.0 | ||
| ultralytics==8.3.237 | ||
| pytest-env==1.6.0 | ||
| pytest-mock==3.15.1 | ||
| fiftyone==1.17.0 | ||
| datasets==5.0.0 | ||
| ultralytics==8.4.67 | ||
Oops, something went wrong.
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
๐งฉ Analysis chain
๐ Script executed:
Repository: DagsHub/client
Length of output: 2472
๐ Web query:
What are the breaking changes in datasets 5.0.0 compared to 3.6.0?๐ก Result:
Breaking changes introduced in datasets 5.0.0 (vs 3.6.0) that are explicitly called out as BREAKING in the 5.0.0 release notes: 1) Streaming IterableDataset.shuffle: default shuffling behavior changed (BREAKING) - In datasets 5.0.0, the default shuffling mechanism in streaming mode now uses multiple input shards, changing the effective shuffle behavior/performance characteristics. - The release notes state this is a BREAKING CHANGE and that you can recover the old behavior by passing max_buffer_input_shards=1 to IterableDataset.shuffle. [1][2] Notes: - The 5.0.0 release notes page excerpt we found shows this single explicit BREAKING change (the other items listed are described as improvements/bug fixes rather than as breaking). [1] - Therefore, based on the sources available from the official 5.0.0 release notes, the only clearly documented breaking change we can substantiate is the streaming shuffle behavior default. [1][2] If you want, I can do a second pass specifically looking for other 5.0.0 changes that may be breaking but not labeled โBREAKINGโ in the release notes (e.g., API signature changes), but that would require additional targeted source collection.
Citations:
๐ Web query:
What are the breaking changes in fiftyone 1.17.0 compared to 1.5.2?๐ก Result:
FiftyOne 1.17.0 includes several breaking changes compared to version 1.5.2, reflecting updates accumulated over the releases between them. The primary breaking changes include: Python Support: Support for Python 3.9 has been removed; FiftyOne 1.17.0 now requires Python 3.10 or higher [1][2]. Indexing Defaults: The default behavior for several view stages was changed to not automatically create an index [3]. Specifically, for the
sort_by(),group_by(),geo_within(), andgeo_near()view stages, thecreate_indexparameter now defaults toFalse[3]. Users who require indexing for these operations must now explicitly setcreate_index=True[3]. App Server Security: The App serverโs CORS (Cross-Origin Resource Sharing) policy is now configurable viaallowed_origins, and the default has been changed tosame-origin[1]. These changes, particularly the requirement for Python 3.10+ and the shift to opt-in indexing for specific view stages, may require updates to existing codebases and deployment environments [1][2][3]. Users are encouraged to review their dataset operations and infrastructure requirements when upgrading [3].Citations:
Resolve Python version conflicts before merging: pytest and fiftyone both require Python 3.10+, but project declares support for Python 3.9.
The PR bumps two dependencies with Python version conflicts:
python_requires=">=3.9", so this breaks compatibility for Python 3.9 users.Additionally, fiftyone 1.17.0 changes default indexing behavior for
sort_by(),group_by(),geo_within(), andgeo_near()โ these now default tocreate_index=False. Review usage in tests and code to ensure explicitly settingcreate_index=Truewhere needed.datasets 5.0.0 introduces only one documented breaking change: streaming
IterableDataset.shuffle()default behavior now uses multiple input shards. If the project uses streaming shuffle, verify compatibility or passmax_buffer_input_shards=1to recover old behavior.Update
python_requiresto>=3.10or pin pytest and fiftyone to older versions compatible with Python 3.9.