feat: Added support for new task type Tag Detection for Workflows

[ronpal]

Description

Added new task type to Workflows based on spec

https://pr-2871.specs.preview.cogniteapp.com/20230101-internal.json.html#tag/Workflow-versions/operation/CreateOrUpdateWorkflowVersion

Checklist:

• Tests added/updated.
• Documentation updated. Documentation is generated from docstrings - these must be updated according to your change.
  If a new method has been added it should be referenced in cognite.rst in order to generate docs based on its docstring.
• The PR title follows the Conventional Commit spec.

[gemini-code-assist]

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description

Customization

To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here.

[codecov]

Codecov Report

❌ Patch coverage is 93.75000% with 5 lines in your changes missing coverage. Please review.
✅ Project coverage is 90.98%. Comparing base (489c703) to head (16d9738).
⚠️ Report is 17 commits behind head on master.

Files with missing lines	Patch %	Lines
cognite/client/data_classes/workflows.py	93.75%	5 Missing ⚠️

Additional details and impacted files

@@            Coverage Diff             @@
##           master    #2342      +/-   ##
==========================================
+ Coverage   90.96%   90.98%   +0.01%     
==========================================
  Files         192      192              
  Lines       26138    26217      +79     
==========================================
+ Hits        23777    23853      +76     
- Misses       2361     2364       +3     

Files with missing lines	Coverage Δ
cognite/client/data_classes/workflows.py	96.12% <93.75%> (+0.17%)	⬆️

... and 4 files with indirect coverage changes

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[doctrino]

This seems to not be completed. Lots of the spec is missing.

[doctrino]

Description

Added new task type to Workflows based on spec

https://pr-2871.specs.preview.cogniteapp.com/20230101-internal.json.html#tag/Workflow-versions/operation/CreateOrUpdateWorkflowVersion

Checklist:

• Tests added/updated.
• Documentation updated. Documentation is generated from docstrings - these must be updated according to your change.
  If a new method has been added it should be referenced in cognite.rst in order to generate docs based on its docstring.
• The PR title follows the Conventional Commit spec.

Seems the taskType is not updated in the API docs:

[doctrino]

Good job. There are a few minor fixes that are necessary.

[doctrino]

Good stuff :)

[doctrino]

One thing to consider, should we have raise an alpha warning everytime a TagDetectionParameter is initialized? I assume this feature is in alpha?

[ronpal]

One thing to consider, should we have raise an alpha warning everytime a TagDetectionParameter is initialized? I assume this feature is in alpha?

It is in private beta, does the same apply?

[arnels]

This looks good. Could you please add unit tests for the new classes? Since they contain custom logic for serialization/deserialization in methods like _load and dump, it's important to ensure that logic is covered.

[haakonvt]

This looks good. Could you please add unit tests for the new classes? Since they contain custom logic for serialization/deserialization in methods like _load and dump, it's important to ensure that logic is covered.

Just to narrow this a bit, any object inheriting from e.g. CogniteObject or -Resource are automatically picked up and tested in a variety of ways.

Other class hierarchies must be tested, e.g. subclasses of WorkflowTaskOutput which just inherits from ABC.

[VerstraeteBert]

Sorry for the late review, was on vacation.

Making some last changes to the API spec before the testing is commencing (out-of-sync updates and some small breaking changes). Will write a summary here when ready.

Waiting for this PR to be merged on the Jazz side:
https://github.com/cognitedata/jazz-api/pull/1913

[queCognite]

The pr above has been merged. @ronpal @VerstraeteBert

[VerstraeteBert]

@ronpal
Summary of changes:

• More possible statuses for a Tag Detection Job:

                  [
                   "Queued",
                   "Distributing",
                   "Distributed",
                   "Loading Entities",
                   "Loaded Entities",
                   "Running",
                   "Detected",
                   "Annotated",
                   "Collecting",
                   "Completed",
                   "Failed",
                   "Timeout",
                 ]

• An errorMessage (str | null) is added to both the Job and SubJobs.
• A minimum of 1 file is expected for the fileInstanceIds
• entityFilters takes [1; 10] filters.

[ronpal]

@ronpal Summary of changes:

• More possible statuses for a Tag Detection Job:

                  [
                   "Queued",
                   "Distributing",
                   "Distributed",
                   "Loading Entities",
                   "Loaded Entities",
                   "Running",
                   "Detected",
                   "Annotated",
                   "Collecting",
                   "Completed",
                   "Failed",
                   "Timeout",
                 ]

• An errorMessage (str | null) is added to both the Job and SubJobs.
• A minimum of 1 file is expected for the fileInstanceIds
• entityFilters takes [1; 10] filters.

@VerstraeteBert can you please review again? These are the commits that address these changes 👆

94c1801
8f15c0a
cbc7008

[thorkildcognite]

/gemini review

[gemini-code-assist]

Code Review

This pull request adds support for the new tagDetection task type in Workflows. The changes include new data classes for the task parameters and output, as well as integrating it into the existing workflow structure. The implementation is mostly solid, but I've identified a critical issue with loading optional parameters that could lead to runtime errors, and some inconsistencies with the project's naming conventions and API consistency. Addressing these points will improve the robustness and maintainability of the new feature.

[gemini-code-assist]

The _load method should handle optional fields gracefully. Accessing minTokens, partialMatch, and writeAnnotations with [] will raise a KeyError if they are not present in the API response. Since these are optional in __init__, you should use the .get() method to avoid potential runtime errors.

Suggested change

	min_tokens=tag_detection["minTokens"],
	partial_match=tag_detection["partialMatch"],
	write_annotations=tag_detection["writeAnnotations"],
	min_tokens=tag_detection.get("minTokens"),
	partial_match=tag_detection.get("partialMatch"),
	write_annotations=tag_detection.get("writeAnnotations", False),

[gemini-code-assist]

The parameter instanceId and attribute self.instanceId should be instance_id to adhere to the snake_case naming convention specified in the style guide.¹ You will also need to update the dump method to use self.instance_id.

Suggested change

	def __init__(self, instanceId: NodeId, page_range: PageRange, error_message: str | None) -> None:
	self.instanceId = instanceId
	self.page_range = page_range
	self.error_message = error_message
	def __init__(self, instance_id: NodeId, page_range: PageRange, error_message: str | None) -> None:
	self.instance_id = instance_id
	self.page_range = page_range
	self.error_message = error_message

Style Guide References

Footnotes

1. The style guide requires snake_case for variable and function names. ↩

[gemini-code-assist]

The parameters jobId, filePageRanges, and errorMessage and their corresponding attributes should be job_id, file_page_ranges, and error_message to follow the snake_case naming convention from the style guide.¹ You will also need to update the _load and dump methods to use these new attribute names.

Suggested change

	def __init__(
	self,
	jobId: int,
	status: TagDetectionStatus,
	filePageRanges: list[TagDetectionJobFilePageRange],
	errorMessage: str | None,
	) -> None:
	self.jobId = jobId
	self.status = status
	self.filePageRanges = filePageRanges
	self.errorMessage = errorMessage
	def __init__(
	self,
	job_id: int,
	status: TagDetectionStatus,
	file_page_ranges: list[TagDetectionJobFilePageRange],
	error_message: str | None,
	) -> None:
	self.job_id = job_id
	self.status = status
	self.file_page_ranges = file_page_ranges
	self.error_message = error_message

Style Guide References

Footnotes

1. The style guide requires snake_case for variable and function names. ↩

[gemini-code-assist]

The default value for camel_case in the dump method is False, which is inconsistent with most other WorkflowTaskOutput subclasses that default to True. For consistency across the SDK, it's better to use True as the default.

Suggested change

	def dump(self, camel_case: bool = False) -> dict[str, Any]:
	def dump(self, camel_case: bool = True) -> dict[str, Any]:

[thorkildcognite]

@ronpal Going through old PRs that have been "stuck", this seems like it needs a team-review, and potentially some follow-ups of the Gemini feedback (I haven't looked at whether it is sensible things it raises). Could you please help us figure out if this PR is still relevant to risk-review? And get a team-review so it is ready?