Scheduled weekly dependency update for week 24#698
Conversation
📝 WalkthroughWalkthroughBumps pinned dependency versions in two requirement files: ChangesDependency Version Bumps
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~2 minutes Poem
🚥 Pre-merge checks | ✅ 4✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
ℹ️ Review info
⚙️ Run configuration
Configuration used: Organization UI
Review profile: CHILL
Plan: Pro
Run ID: f6e262d2-aa3b-48a7-9424-a3e01c8992e1
📒 Files selected for processing (2)
docs/requirements-docs.txtrequirements-dev.txt
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (6)
- GitHub Check: build (3.13)
- GitHub Check: build (3.12)
- GitHub Check: build (3.11)
- GitHub Check: Build documentation
- GitHub Check: build (3.10)
- GitHub Check: check-licenses
🔇 Additional comments (2)
requirements-dev.txt (1)
3-3: LGTM!docs/requirements-docs.txt (1)
7-7: LGTM!
| 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 |
There was a problem hiding this comment.
🧩 Analysis chain
🏁 Script executed:
#!/bin/bash
# Verify Python version requirements declared in the project.
# Expected: minimum Python version >= 3.10 if pytest 9.1.0 is acceptable.
echo "=== Checking Python version requirements ==="
find . -maxdepth 2 -type f \( -name 'setup.py' -o -name 'pyproject.toml' -o -name '.python-version' -o -name 'setup.cfg' \) \
-exec echo "File: {}" \; -exec cat {} \; 2>/dev/null
echo ""
echo "=== Checking for pkg_resources imports ==="
# Expected: no results if setuptools pkg_resources removal is safe
rg -n "from pkg_resources|import pkg_resources" --type py
echo ""
echo "=== Checking test compatibility with pytest 9.1.0 ==="
# List pytest-deprecated APIs in use (if any)
rg -n "pytest\.deprecated|pytest\.fail|pytest\.warns.*deprecated" --type py tests/Repository: DagsHub/client
Length of output: 2472
🌐 Web query:
What are the breaking changes in datasets 5.0.0 compared to 3.6.0?
💡 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 “BREAKING” in the release notes (e.g., API signature changes), but that would require additional targeted source collection.
Citations:
- 1: https://github.com/huggingface/datasets/releases/tag/5.0.0
- 2: Use multiple input shards for shuffle buffer huggingface/datasets#8194
🌐 Web query:
What are the breaking changes in fiftyone 1.17.0 compared to 1.5.2?
💡 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(), and geo_near() view stages, the create_index parameter now defaults to False [3]. Users who require indexing for these operations must now explicitly set create_index=True [3]. App Server Security: The App server’s CORS (Cross-Origin Resource Sharing) policy is now configurable via allowed_origins, and the default has been changed to same-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:
- 1: https://docs.voxel51.com/release-notes.html
- 2: https://pypi.org/project/fiftyone/1.17.0/
- 3: Don't create indexes by default in view stages voxel51/fiftyone#6344
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:
- pytest 9.1.0 (line 2): Drops Python 3.9 support. Project declares
python_requires=">=3.9", so this breaks compatibility for Python 3.9 users. - fiftyone 1.17.0 (line 7): Requires Python 3.10+ (dropped 3.9 support). Project still supports Python 3.9, creating a compatibility gap.
Additionally, fiftyone 1.17.0 changes default indexing behavior for sort_by(), group_by(), geo_within(), and geo_near() — these now default to create_index=False. Review usage in tests and code to ensure explicitly setting create_index=True where 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 pass max_buffer_input_shards=1 to recover old behavior.
Update python_requires to >=3.10 or pin pytest and fiftyone to older versions compatible with Python 3.9.
1 participant
Update sphinx-autodoc-typehints from 3.9.9 to 3.11.0.
Changelog
3.11.0
3.10.6
3.10.5
3.10.4
3.10.3
3.10.2
3.10.1
3.10.0
3.9.11
3.9.10
Links
Update setuptools from 80.9.0 to 82.0.1.
Changelog
82.0.1
82.0.0
81.0.0
80.10.2
80.10.1
80.10.0
Links
Update pytest from 8.3.5 to 9.1.0.
Changelog
9.0.3
9.0.2
9.0.1
9.0.0
8.4.2
8.4.1
8.4.0
Links
Update respx from 0.22.0 to 0.23.1.
Changelog
0.23.1
0.23.0
Links
Update pytest-env from 1.1.5 to 1.6.0.
The bot wasn't able to find a changelog for this release. Got an idea?
Links
Update pytest-mock from 3.14.0 to 3.15.1.
Changelog
3.15.1
3.15.0
3.14.1
Links
Update fiftyone from 1.5.2 to 1.17.0.
Changelog
1.17.0
1.16.0
1.15.0
1.14.2
1.14.1
1.14.0
1.13.5
1.13.4
1.13.3
1.13.2
1.13.1
1.13.0
1.12.0
1.11.1
1.11.0
1.10.0
1.9.0
1.8.1
1.8.0
1.7.2
1.7.1
1.7.0
1.6.0
Links
Update datasets from 3.6.0 to 5.0.0.
Changelog
5.0.0