From f9fe77e35c9f8b281049f253b4f4fb2f85fe9059 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Wed, 24 Sep 2025 12:33:42 +0200
Subject: [PATCH 01/19] Added support for new task type Tag Detection for
 Workflows

---
 cognite/client/data_classes/workflows.py | 73 +++++++++++++++++++++++-
 1 file changed, 72 insertions(+), 1 deletion(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index fa35416476..4278795145 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -19,6 +19,7 @@
     WriteableCogniteResource,
     WriteableCogniteResourceList,
 )
+from cognite.client.data_classes.data_modeling import NodeId
 from cognite.client.data_classes.data_modeling.query import Query, ResultSetExpression, Select
 from cognite.client.data_classes.simulators.runs import (
     SimulationInputOverride,
@@ -136,7 +137,7 @@ def as_write(self) -> WorkflowUpsertList:
         return WorkflowUpsertList([workflow.as_write() for workflow in self.data])
 
 
-ValidTaskType = Literal["function", "transformation", "cdf", "dynamic", "subworkflow", "simulation"]
+ValidTaskType = Literal["function", "transformation", "cdf", "dynamic", "subworkflow", "simulation", "tagDetection"]
 
 
 class WorkflowTaskParameters(CogniteObject, ABC):
@@ -166,6 +167,8 @@ def load_parameters(cls, data: dict) -> WorkflowTaskParameters:
             return SubworkflowReferenceParameters._load(parameters)
         elif type_ == "simulation":
             return SimulationTaskParameters._load(parameters)
+        elif type_ == "tagDetection":
+            return TagDetectionTaskParameters._load(parameters)
         else:
             raise ValueError(f"Unknown task type: {type_}. Expected {ValidTaskType}")
 
@@ -513,6 +516,57 @@ def dump(self, camel_case: bool = True) -> dict[str, Any]:
         }
 
 
+class TagDetectionTaskParameters(WorkflowTaskParameters):
+    """
+    The tag detection task parameters are used to specify a tag detection task.
+
+    Args:
+        file_instance_ids (list[NodeId] | str): List of files to detect tags in. Can be a reference.
+        entity_filters (str): The DMS filter query to fetch entities to match on
+        min_tokens (int): Each detected item must match the detected entity on at least this number of tokens. A token is a substring of consecutive letters or digits.
+        partial_match (bool): Allow partial (fuzzy) matching of entities in the engineering diagrams. Creates a match only when it is possible to do so unambiguously.
+        write_annotations (bool): Whether annotations should be automatically be written for the files
+
+    """
+
+    task_type = "tagDetection"
+
+    def __init__(
+        self,
+        file_instance_ids: list[NodeId] | str,
+        entity_filters: str,
+        min_tokens: int,
+        partial_match: bool,
+        write_annotations: bool = False,
+    ) -> None:
+        self.file_instance_ids = file_instance_ids
+        self.entity_filters = entity_filters
+        self.min_tokens = min_tokens
+        self.partial_match = partial_match
+        self.write_annotations = write_annotations
+
+    @classmethod
+    def _load(cls, resource: dict, cognite_client: CogniteClient | None = None) -> Self:
+        return cls(
+            file_instance_ids=resource["fileInstanceIds"],
+            entity_filters=resource["entityFilters"],
+            min_tokens=resource["minTokens"],
+            partial_match=resource["partialMatch"],
+            write_annotations=resource["writeAnnotations"],
+        )
+
+    def dump(self, camel_case: bool = True) -> dict[str, Any]:
+        return {
+            self.task_type: {
+                "fileInstanceIds": self.file_instance_ids,
+                "entityFilters": self.entity_filters,
+                "minTokens": self.min_tokens,
+                "partialMatch": self.partial_match,
+                "writeAnnotations": self.write_annotations,
+            }
+        }
+
+
 class WorkflowTask(CogniteResource):
     """
     This class represents a workflow task.
@@ -779,6 +833,23 @@ def dump(self, camel_case: bool = False) -> dict[str, Any]:
         return {}
 
 
+class TagDetectionTaskOutput(WorkflowTaskOutput):
+    """
+    The tag detection task output is used to specify the output of a tag detection task.
+    """
+
+    task_type: ClassVar[str] = "tagDetection"
+
+    def __init__(self) -> None: ...
+
+    @classmethod
+    def load(cls, data: dict[str, Any]) -> TagDetectionTaskOutput:
+        return cls()
+
+    def dump(self, camel_case: bool = False) -> dict[str, Any]:
+        return {}
+
+
 class WorkflowTaskExecution(CogniteObject):
     """
     This class represents a task execution.

From ffa9c535dfd73376ce1fd9fd92418d3066e8b40b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Thu, 25 Sep 2025 09:13:06 +0200
Subject: [PATCH 02/19] Fixed dump/load

---
 cognite/client/data_classes/workflows.py | 33 +++++++++++++++++++-----
 1 file changed, 27 insertions(+), 6 deletions(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 4278795145..412573605f 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -527,6 +527,12 @@ class TagDetectionTaskParameters(WorkflowTaskParameters):
         partial_match (bool): Allow partial (fuzzy) matching of entities in the engineering diagrams. Creates a match only when it is possible to do so unambiguously.
         write_annotations (bool): Whether annotations should be automatically be written for the files
 
+    Note:
+        A Reference is an expression that allows dynamically injecting input to a task during execution.
+        References can be used to reference the input of the Workflow, the output of a previous task in the Workflow,
+        or the input of a previous task in the Workflow. Note that the injected value must be valid in the context of
+        the property it is injected into. Example Task reference: ${myTaskExternalId.output.someKey} Example Workflow input reference: ${workflow.input.myKey}
+
     """
 
     task_type = "tagDetection"
@@ -547,18 +553,31 @@ def __init__(
 
     @classmethod
     def _load(cls, resource: dict, cognite_client: CogniteClient | None = None) -> Self:
+        tag_detection = resource[cls.task_type]
+        file_instance_ids: list[NodeId] | str
+        if isinstance(tag_detection["fileInstanceIds"], str):
+            file_instance_ids = tag_detection["fileInstanceIds"]
+        else:
+            file_instance_ids = [NodeId.load(file_instance_id) for file_instance_id in tag_detection["fileInstanceIds"]]
+
         return cls(
-            file_instance_ids=resource["fileInstanceIds"],
-            entity_filters=resource["entityFilters"],
-            min_tokens=resource["minTokens"],
-            partial_match=resource["partialMatch"],
-            write_annotations=resource["writeAnnotations"],
+            file_instance_ids=file_instance_ids,
+            entity_filters=tag_detection["entityFilters"],
+            min_tokens=tag_detection["minTokens"],
+            partial_match=tag_detection["partialMatch"],
+            write_annotations=tag_detection["writeAnnotations"],
         )
 
     def dump(self, camel_case: bool = True) -> dict[str, Any]:
+        fileInstanceIds: list[dict[str, str]] | str
+        if isinstance(self.file_instance_ids, str):
+            fileInstanceIds = self.file_instance_ids
+        else:
+            fileInstanceIds = [file_instance_id.dump(camel_case) for file_instance_id in self.file_instance_ids]
+
         return {
             self.task_type: {
-                "fileInstanceIds": self.file_instance_ids,
+                "fileInstanceIds": fileInstanceIds,
                 "entityFilters": self.entity_filters,
                 "minTokens": self.min_tokens,
                 "partialMatch": self.partial_match,
@@ -669,6 +688,8 @@ def load_output(cls, data: dict) -> WorkflowTaskOutput:
             return SubworkflowTaskOutput.load(data)
         elif task_type == "simulation":
             return SimulationTaskOutput.load(data)
+        elif task_type == "tagDetection":
+            return TagDetectionTaskOutput.load(data)
         else:
             raise ValueError(f"Unknown task type: {task_type}")
 

From 931e450889e5f9f92ab78c408b59614c85288073 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Thu, 25 Sep 2025 14:20:58 +0200
Subject: [PATCH 03/19] separate class for filter property

---
 cognite/client/data_classes/workflows.py | 47 +++++++++++++++++++++---
 1 file changed, 41 insertions(+), 6 deletions(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 412573605f..3acf271fe4 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -19,8 +19,9 @@
     WriteableCogniteResource,
     WriteableCogniteResourceList,
 )
-from cognite.client.data_classes.data_modeling import NodeId
+from cognite.client.data_classes.data_modeling import NodeId, ViewId
 from cognite.client.data_classes.data_modeling.query import Query, ResultSetExpression, Select
+from cognite.client.data_classes.filters import Filter
 from cognite.client.data_classes.simulators.runs import (
     SimulationInputOverride,
 )
@@ -516,13 +517,39 @@ def dump(self, camel_case: bool = True) -> dict[str, Any]:
         }
 
 
+class TagDetectionTaskEntityFilter(CogniteObject):
+    view: ViewId
+    filters: Filter
+    search_field: str
+
+    def __init__(self, view: ViewId, filters: Filter, search_field: str) -> None:
+        self.view = view
+        self.filters = filters
+        self.search_field = search_field
+
+    @classmethod
+    def _load(cls, resource: dict, cognite_client: CogniteClient | None = None) -> Self:
+        return cls(
+            view=ViewId.load(resource["view"]),
+            filters=Filter.load(resource["filters"]),
+            search_field=resource["searchField"],
+        )
+
+    def dump(self, camel_case: bool = True) -> dict[str, Any]:
+        return {
+            "view": self.view.dump(camel_case=camel_case, include_type=False),
+            "filters": self.filters.dump(),
+            "searchField": self.search_field,
+        }
+
+
 class TagDetectionTaskParameters(WorkflowTaskParameters):
     """
     The tag detection task parameters are used to specify a tag detection task.
 
     Args:
         file_instance_ids (list[NodeId] | str): List of files to detect tags in. Can be a reference.
-        entity_filters (str): The DMS filter query to fetch entities to match on
+        entity_filters (list[TagDetectionTaskEntityFilter]): Entity search specification(s) used to fetch DMS entities to match on.
         min_tokens (int): Each detected item must match the detected entity on at least this number of tokens. A token is a substring of consecutive letters or digits.
         partial_match (bool): Allow partial (fuzzy) matching of entities in the engineering diagrams. Creates a match only when it is possible to do so unambiguously.
         write_annotations (bool): Whether annotations should be automatically be written for the files
@@ -540,7 +567,7 @@ class TagDetectionTaskParameters(WorkflowTaskParameters):
     def __init__(
         self,
         file_instance_ids: list[NodeId] | str,
-        entity_filters: str,
+        entity_filters: list[TagDetectionTaskEntityFilter],
         min_tokens: int,
         partial_match: bool,
         write_annotations: bool = False,
@@ -557,12 +584,18 @@ def _load(cls, resource: dict, cognite_client: CogniteClient | None = None) -> S
         file_instance_ids: list[NodeId] | str
         if isinstance(tag_detection["fileInstanceIds"], str):
             file_instance_ids = tag_detection["fileInstanceIds"]
-        else:
+        elif isinstance(tag_detection["fileInstanceIds"], list):
             file_instance_ids = [NodeId.load(file_instance_id) for file_instance_id in tag_detection["fileInstanceIds"]]
+        else:
+            raise ValueError(f"Invalid file instance ids: {tag_detection['fileInstanceIds']}")
+
+        entity_filters: list[TagDetectionTaskEntityFilter] = [
+            TagDetectionTaskEntityFilter.load(item) for item in tag_detection["entityFilters"]
+        ]
 
         return cls(
             file_instance_ids=file_instance_ids,
-            entity_filters=tag_detection["entityFilters"],
+            entity_filters=entity_filters,
             min_tokens=tag_detection["minTokens"],
             partial_match=tag_detection["partialMatch"],
             write_annotations=tag_detection["writeAnnotations"],
@@ -575,10 +608,12 @@ def dump(self, camel_case: bool = True) -> dict[str, Any]:
         else:
             fileInstanceIds = [file_instance_id.dump(camel_case) for file_instance_id in self.file_instance_ids]
 
+        entityFilters = [ef.dump(camel_case) for ef in self.entity_filters]
+
         return {
             self.task_type: {
                 "fileInstanceIds": fileInstanceIds,
-                "entityFilters": self.entity_filters,
+                "entityFilters": entityFilters,
                 "minTokens": self.min_tokens,
                 "partialMatch": self.partial_match,
                 "writeAnnotations": self.write_annotations,

From a24148df3595324b2b24e299fb4eefe2297097a9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Thu, 25 Sep 2025 14:53:33 +0200
Subject: [PATCH 04/19] added task output classes

---
 cognite/client/data_classes/workflows.py | 78 ++++++++++++++++++++++--
 1 file changed, 72 insertions(+), 6 deletions(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 3acf271fe4..0c1d5c7662 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -889,21 +889,87 @@ def dump(self, camel_case: bool = False) -> dict[str, Any]:
         return {}
 
 
-class TagDetectionTaskOutput(WorkflowTaskOutput):
+class TagDetectionJobFilePageRange(CogniteObject):
     """
-    The tag detection task output is used to specify the output of a tag detection task.
+    A list of file page ranges that is being processed or was processed by the job.
+
+    Args:
+        instanceId (NodeId): The identifier of the instance.
+        begin (int): The beginning of the page range.
+        end (int): The end of the page range.
     """
 
-    task_type: ClassVar[str] = "tagDetection"
+    def __init__(self, instanceId: NodeId, begin: int, end: int) -> None:
+        self.instanceId = instanceId
+        self.begin = begin
+        self.end = end
 
-    def __init__(self) -> None: ...
+    @classmethod
+    def _load(cls, resource: dict, cognite_client: CogniteClient | None = None) -> Self:
+        return cls(
+            NodeId.load(resource["instanceId"]),
+            resource["pageRange"]["begin"],
+            resource["pageRange"]["end"],
+        )
+
+    def dump(self, camel_case: bool = True) -> dict[str, Any]:
+        return {
+            "instanceId": self.instanceId.dump(camel_case=camel_case),
+            "pageRange": {
+                "begin": self.begin,
+                "end": self.end,
+            },
+        }
+
+
+class TagDetectionJob(CogniteObject):
+    """
+        A tag detection job.
+
+        Args:
+            jobId (int): The identifier of the tag detection job
+            status (str): Enum: "Queued" "Distributing" "Running" "Collecting" "Completed" "Failed" "Timeout"
+    The last observed status of the job.
+            filePageRanges (list[TagDetectionJobFilePageRange]): A list of file page ranges that is being processed or was processed by the job.
+    """
+
+    def __init__(self, jobId: int, status: str, filePageRanges: list[TagDetectionJobFilePageRange]) -> None:
+        self.jobId = jobId
+        self.status = status
+        self.filePageRanges = filePageRanges
+
+    @classmethod
+    def _load(cls, resource: dict, cognite_client: CogniteClient | None = None) -> Self:
+        filePageRanges = [
+            TagDetectionJobFilePageRange.load(filePageRange) for filePageRange in resource["filePageRanges"]
+        ]
+
+        return cls(resource["jobId"], resource["status"], filePageRanges)
+
+    def dump(self, camel_case: bool = True) -> dict[str, Any]:
+        return {
+            "jobId": self.jobId,
+            "status": self.status,
+            "filePageRanges": [filePageRange.dump(camel_case) for filePageRange in self.filePageRanges],
+        }
+
+
+class TagDetectionTaskOutput(WorkflowTaskOutput):
+    """
+    The tag detection task output is used to specify the output of tag detection task.
+    """
+
+    def __init__(self, jobs: list[TagDetectionJob]) -> None:
+        self.jobs = jobs
 
     @classmethod
     def load(cls, data: dict[str, Any]) -> TagDetectionTaskOutput:
-        return cls()
+        return cls([TagDetectionJob.load(tagDetectionJob) for tagDetectionJob in data["jobs"]])
 
     def dump(self, camel_case: bool = False) -> dict[str, Any]:
-        return {}
+        return {
+            "jobs": [tagDetectionJob.dump(camel_case) for tagDetectionJob in self.jobs],
+        }
 
 
 class WorkflowTaskExecution(CogniteObject):

From e70a9bd659cce309b41466e9d958de3a6dd6c25d Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Fri, 26 Sep 2025 08:05:10 +0200
Subject: [PATCH 05/19] Housekeeping

---
 cognite/client/data_classes/workflows.py | 13 ++++++-------
 1 file changed, 6 insertions(+), 7 deletions(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 0c1d5c7662..69035aa882 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -923,14 +923,13 @@ def dump(self, camel_case: bool = True) -> dict[str, Any]:
 
 
 class TagDetectionJob(CogniteObject):
-    """
-        A tag detection job.
+    """A tag detection job.
 
-        Args:
-            jobId (int): The identifier of the tag detection job
-            status (str): Enum: "Queued" "Distributing" "Running" "Collecting" "Completed" "Failed" "Timeout"
-    The last observed status of the job.
-            filePageRanges (list[TagDetectionJobFilePageRange]): A list of file page ranges that is being processed or was processed by the job.
+    Args:
+        jobId (int): The identifier of the tag detection job.
+        status (str): The last observed status of the job. One of ``"Queued"``, ``"Distributing"``, ``"Running"``,
+            ``"Collecting"``, ``"Completed"``, ``"Failed"``, ``"Timeout"``.
+        filePageRanges (list[TagDetectionJobFilePageRange]): File page ranges that are or were processed by the job.
     """
 
     def __init__(self, jobId: int, status: str, filePageRanges: list[TagDetectionJobFilePageRange]) -> None:

From 90c4f87da303dbd8bea70c84d3809374f5723d06 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Fri, 26 Sep 2025 09:07:41 +0200
Subject: [PATCH 06/19] Update cognite/client/data_classes/workflows.py

Co-authored-by: Anders Albert <60234212+doctrino@users.noreply.github.com>
---
 cognite/client/data_classes/workflows.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 69035aa882..8db42f621a 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -568,8 +568,8 @@ def __init__(
         self,
         file_instance_ids: list[NodeId] | str,
         entity_filters: list[TagDetectionTaskEntityFilter],
-        min_tokens: int,
-        partial_match: bool,
+        min_tokens: int | None = None,
+        partial_match: bool | None = None,
         write_annotations: bool = False,
     ) -> None:
         self.file_instance_ids = file_instance_ids

From 4e72ff20ce8d37e9f959a0c09d93cdeb0f656a77 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Fri, 26 Sep 2025 09:08:16 +0200
Subject: [PATCH 07/19] Update cognite/client/data_classes/workflows.py

Co-authored-by: Anders Albert <60234212+doctrino@users.noreply.github.com>
---
 cognite/client/data_classes/workflows.py | 4 ----
 1 file changed, 4 deletions(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 8db42f621a..16dd7fcaeb 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -518,10 +518,6 @@ def dump(self, camel_case: bool = True) -> dict[str, Any]:
 
 
 class TagDetectionTaskEntityFilter(CogniteObject):
-    view: ViewId
-    filters: Filter
-    search_field: str
-
     def __init__(self, view: ViewId, filters: Filter, search_field: str) -> None:
         self.view = view
         self.filters = filters

From fc78eb25b658d90a08029bbf2f5d5721c741aeb3 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Fri, 26 Sep 2025 09:15:50 +0200
Subject: [PATCH 08/19] Docstring and snake_case

---
 cognite/client/data_classes/workflows.py | 16 ++++++++--------
 1 file changed, 8 insertions(+), 8 deletions(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 16dd7fcaeb..8e1a5fd407 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -546,8 +546,8 @@ class TagDetectionTaskParameters(WorkflowTaskParameters):
     Args:
         file_instance_ids (list[NodeId] | str): List of files to detect tags in. Can be a reference.
         entity_filters (list[TagDetectionTaskEntityFilter]): Entity search specification(s) used to fetch DMS entities to match on.
-        min_tokens (int): Each detected item must match the detected entity on at least this number of tokens. A token is a substring of consecutive letters or digits.
-        partial_match (bool): Allow partial (fuzzy) matching of entities in the engineering diagrams. Creates a match only when it is possible to do so unambiguously.
+        min_tokens (int | None): Each detected item must match the detected entity on at least this number of tokens. A token is a substring of consecutive letters or digits.
+        partial_match (bool | None): Allow partial (fuzzy) matching of entities in the engineering diagrams. Creates a match only when it is possible to do so unambiguously.
         write_annotations (bool): Whether annotations should be automatically be written for the files
 
     Note:
@@ -598,18 +598,18 @@ def _load(cls, resource: dict, cognite_client: CogniteClient | None = None) -> S
         )
 
     def dump(self, camel_case: bool = True) -> dict[str, Any]:
-        fileInstanceIds: list[dict[str, str]] | str
+        file_instance_ids: list[dict[str, str]] | str
         if isinstance(self.file_instance_ids, str):
-            fileInstanceIds = self.file_instance_ids
+            file_instance_ids = self.file_instance_ids
         else:
-            fileInstanceIds = [file_instance_id.dump(camel_case) for file_instance_id in self.file_instance_ids]
+            file_instance_ids = [file_instance_id.dump(camel_case) for file_instance_id in self.file_instance_ids]
 
-        entityFilters = [ef.dump(camel_case) for ef in self.entity_filters]
+        entity_filters = [ef.dump(camel_case) for ef in self.entity_filters]
 
         return {
             self.task_type: {
-                "fileInstanceIds": fileInstanceIds,
-                "entityFilters": entityFilters,
+                "fileInstanceIds": file_instance_ids,
+                "entityFilters": entity_filters,
                 "minTokens": self.min_tokens,
                 "partialMatch": self.partial_match,
                 "writeAnnotations": self.write_annotations,

From 270e56f992ba54fe6124af219d33afae7c5e9030 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Fri, 26 Sep 2025 09:17:14 +0200
Subject: [PATCH 09/19] Update cognite/client/data_classes/workflows.py

Co-authored-by: Anders Albert <60234212+doctrino@users.noreply.github.com>
---
 cognite/client/data_classes/workflows.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 8e1a5fd407..0d30cb8cda 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -928,7 +928,7 @@ class TagDetectionJob(CogniteObject):
         filePageRanges (list[TagDetectionJobFilePageRange]): File page ranges that are or were processed by the job.
     """
 
-    def __init__(self, jobId: int, status: str, filePageRanges: list[TagDetectionJobFilePageRange]) -> None:
+    def __init__(self, jobId: int, status: TagDetectionStatus, filePageRanges: list[TagDetectionJobFilePageRange]) -> None:
         self.jobId = jobId
         self.status = status
         self.filePageRanges = filePageRanges

From c144e21a6887a6ab35e4faefcb0f218f158e84a9 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Fri, 26 Sep 2025 09:20:08 +0200
Subject: [PATCH 10/19] Update cognite/client/data_classes/workflows.py

Co-authored-by: Anders Albert <60234212+doctrino@users.noreply.github.com>
---
 cognite/client/data_classes/workflows.py | 24 +++++++++++++++---------
 1 file changed, 15 insertions(+), 9 deletions(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 0d30cb8cda..17a330ed81 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -885,6 +885,16 @@ def dump(self, camel_case: bool = False) -> dict[str, Any]:
         return {}
 
 
+@dataclass
+class PageRange(CogniteObject):
+    begin: int
+    end: int
+    
+    @classmethod
+    def _load(cls, resource: dict, cognite_client: CogniteClient | None = None) -> Self:
+        return cls(resource["begin"], resource["end"])
+
+
 class TagDetectionJobFilePageRange(CogniteObject):
     """
     A list of file page ranges that is being processed or was processed by the job.
@@ -895,29 +905,25 @@ class TagDetectionJobFilePageRange(CogniteObject):
         end (int): The end of the page range.
     """
 
-    def __init__(self, instanceId: NodeId, begin: int, end: int) -> None:
+    def __init__(self, instanceId: NodeId, page_range: PageRange) -> None:
         self.instanceId = instanceId
-        self.begin = begin
-        self.end = end
+        self.page_range = page_range
 
     @classmethod
     def _load(cls, resource: dict, cognite_client: CogniteClient | None = None) -> Self:
         return cls(
             NodeId.load(resource["instanceId"]),
-            resource["pageRange"]["begin"],
-            resource["pageRange"]["end"],
+            PageRange._load(resource["pageRange"]),
         )
 
     def dump(self, camel_case: bool = True) -> dict[str, Any]:
         return {
             "instanceId": self.instanceId.dump(camel_case=camel_case),
-            "pageRange": {
-                "begin": self.begin,
-                "end": self.end,
-            },
+            "pageRange": self.page_range.dump(camel_case=camel_case),
         }
 
 
+
 class TagDetectionJob(CogniteObject):
     """A tag detection job.
 

From b28005de904999c6acd34fdf234ff38718c61187 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Fri, 26 Sep 2025 09:20:48 +0200
Subject: [PATCH 11/19] following suggestions

---
 cognite/client/data_classes/workflows.py | 17 ++++++++++++++---
 1 file changed, 14 insertions(+), 3 deletions(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 0d30cb8cda..de932121c3 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -45,6 +45,16 @@
 
 WorkflowStatus: TypeAlias = Literal["completed", "failed", "running", "terminated", "timed_out"]
 
+TagDetectionStatus: TypeAlias = Literal[
+    "Queued",
+    "Distributing",
+    "Running",
+    "Collecting",
+    "Completed",
+    "Failed",
+    "Timeout",
+]
+
 
 class WorkflowCore(WriteableCogniteResource["WorkflowUpsert"], ABC):
     def __init__(self, external_id: str, description: str | None = None, data_set_id: int | None = None) -> None:
@@ -923,12 +933,13 @@ class TagDetectionJob(CogniteObject):
 
     Args:
         jobId (int): The identifier of the tag detection job.
-        status (str): The last observed status of the job. One of ``"Queued"``, ``"Distributing"``, ``"Running"``,
-            ``"Collecting"``, ``"Completed"``, ``"Failed"``, ``"Timeout"``.
+        status (TagDetectionStatus): The last observed status of the job.
         filePageRanges (list[TagDetectionJobFilePageRange]): File page ranges that are or were processed by the job.
     """
 
-    def __init__(self, jobId: int, status: TagDetectionStatus, filePageRanges: list[TagDetectionJobFilePageRange]) -> None:
+    def __init__(
+        self, jobId: int, status: TagDetectionStatus, filePageRanges: list[TagDetectionJobFilePageRange]
+    ) -> None:
         self.jobId = jobId
         self.status = status
         self.filePageRanges = filePageRanges

From e1d5db2412a8c9ec6f245f55cfd4a0192b61eed1 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Fri, 26 Sep 2025 09:44:02 +0200
Subject: [PATCH 12/19] Docstring

---
 cognite/client/data_classes/workflows.py | 12 +++++-------
 1 file changed, 5 insertions(+), 7 deletions(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 8654b4a82e..648529d38a 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -895,11 +895,11 @@ def dump(self, camel_case: bool = False) -> dict[str, Any]:
         return {}
 
 
-@dataclass
 class PageRange(CogniteObject):
-    begin: int
-    end: int
-    
+    def __init__(self, begin: int, end: int) -> None:
+        self.begin = begin
+        self.end = end
+
     @classmethod
     def _load(cls, resource: dict, cognite_client: CogniteClient | None = None) -> Self:
         return cls(resource["begin"], resource["end"])
@@ -911,8 +911,7 @@ class TagDetectionJobFilePageRange(CogniteObject):
 
     Args:
         instanceId (NodeId): The identifier of the instance.
-        begin (int): The beginning of the page range.
-        end (int): The end of the page range.
+        page_range (PageRange): No description.
     """
 
     def __init__(self, instanceId: NodeId, page_range: PageRange) -> None:
@@ -933,7 +932,6 @@ def dump(self, camel_case: bool = True) -> dict[str, Any]:
         }
 
 
-
 class TagDetectionJob(CogniteObject):
     """A tag detection job.
 

From ca1205eeb9387d734cd0532cccff06c2f46f8c53 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Thu, 9 Oct 2025 09:51:29 +0200
Subject: [PATCH 13/19] Added new error message property to the TagDetectionJob
 class

---
 cognite/client/data_classes/workflows.py | 10 ++++++++--
 1 file changed, 8 insertions(+), 2 deletions(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 648529d38a..44ce97ba9c 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -939,14 +939,20 @@ class TagDetectionJob(CogniteObject):
         jobId (int): The identifier of the tag detection job.
         status (TagDetectionStatus): The last observed status of the job.
         filePageRanges (list[TagDetectionJobFilePageRange]): File page ranges that are or were processed by the job.
+        errorMessage (str | None): Describes the job failure reason in case of job failure.
     """
 
     def __init__(
-        self, jobId: int, status: TagDetectionStatus, filePageRanges: list[TagDetectionJobFilePageRange]
+        self,
+        jobId: int,
+        status: TagDetectionStatus,
+        filePageRanges: list[TagDetectionJobFilePageRange],
+        errorMessage: str | None,
     ) -> None:
         self.jobId = jobId
         self.status = status
         self.filePageRanges = filePageRanges
+        self.errorMessage = errorMessage
 
     @classmethod
     def _load(cls, resource: dict, cognite_client: CogniteClient | None = None) -> Self:
@@ -954,7 +960,7 @@ def _load(cls, resource: dict, cognite_client: CogniteClient | None = None) -> S
             TagDetectionJobFilePageRange.load(filePageRange) for filePageRange in resource["filePageRanges"]
         ]
 
-        return cls(resource["jobId"], resource["status"], filePageRanges)
+        return cls(resource["jobId"], resource["status"], filePageRanges, resource.get("errorMessage"))
 
     def dump(self, camel_case: bool = True) -> dict[str, Any]:
         return {

From 48724ffcb39d993109b728938e593294970aa73c Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Thu, 9 Oct 2025 10:01:06 +0200
Subject: [PATCH 14/19] Fixed docstring precision

---
 cognite/client/data_classes/workflows.py | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 44ce97ba9c..160e6881ff 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -554,8 +554,8 @@ class TagDetectionTaskParameters(WorkflowTaskParameters):
     The tag detection task parameters are used to specify a tag detection task.
 
     Args:
-        file_instance_ids (list[NodeId] | str): List of files to detect tags in. Can be a reference.
-        entity_filters (list[TagDetectionTaskEntityFilter]): Entity search specification(s) used to fetch DMS entities to match on.
+        file_instance_ids (list[NodeId] | str): List of files to detect tags in. A minimum of 1 file is expected. Can be a reference.
+        entity_filters (list[TagDetectionTaskEntityFilter]): Entity search specification(s) used to fetch DMS entities to match on. Must contain between 1 and 10 filters.
         min_tokens (int | None): Each detected item must match the detected entity on at least this number of tokens. A token is a substring of consecutive letters or digits.
         partial_match (bool | None): Allow partial (fuzzy) matching of entities in the engineering diagrams. Creates a match only when it is possible to do so unambiguously.
         write_annotations (bool): Whether annotations should be automatically be written for the files

From 322aac22d45046d13da783dd2d4795863fa2528b Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Thu, 9 Oct 2025 09:38:19 +0200
Subject: [PATCH 15/19] Added additional TagDetectionStatus statuses

---
 cognite/client/data_classes/workflows.py | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 160e6881ff..669f291eea 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -48,7 +48,12 @@
 TagDetectionStatus: TypeAlias = Literal[
     "Queued",
     "Distributing",
+    "Distributed",
+    "Loading Entities",
+    "Loaded Entities",
     "Running",
+    "Detected",
+    "Annotated",
     "Collecting",
     "Completed",
     "Failed",

From 1f1dadb3ebc29aff8f0c5d278f5a69bc80d0fb05 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Thu, 9 Oct 2025 10:24:27 +0200
Subject: [PATCH 16/19] Added errormessage to dump method

---
 cognite/client/data_classes/workflows.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index 669f291eea..d7723834b8 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -972,6 +972,7 @@ def dump(self, camel_case: bool = True) -> dict[str, Any]:
             "jobId": self.jobId,
             "status": self.status,
             "filePageRanges": [filePageRange.dump(camel_case) for filePageRange in self.filePageRanges],
+            "errorMessage": self.errorMessage,
         }
 
 

From d7cf8ac99b09e5731037282bc9470065b20ec059 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Thu, 9 Oct 2025 11:49:50 +0200
Subject: [PATCH 17/19] Added rountrip load/dump for ABC dataclasses in
 workflows

---
 cognite/client/data_classes/workflows.py      |  3 +-
 .../test_data_classes/test_workflows.py       | 43 +++++++++++++++++++
 2 files changed, 45 insertions(+), 1 deletion(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index d7723834b8..d6a990655d 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -986,7 +986,8 @@ def __init__(self, jobs: list[TagDetectionJob]) -> None:
 
     @classmethod
     def load(cls, data: dict[str, Any]) -> TagDetectionTaskOutput:
-        return cls([TagDetectionJob.load(tagDetectionJob) for tagDetectionJob in data["jobs"]])
+        output = data["output"]
+        return cls([TagDetectionJob.load(tagDetectionJob) for tagDetectionJob in output["jobs"]])
 
     def dump(self, camel_case: bool = False) -> dict[str, Any]:
         return {
diff --git a/tests/tests_unit/test_data_classes/test_workflows.py b/tests/tests_unit/test_data_classes/test_workflows.py
index 840a45ad58..c45c9add3f 100644
--- a/tests/tests_unit/test_data_classes/test_workflows.py
+++ b/tests/tests_unit/test_data_classes/test_workflows.py
@@ -12,6 +12,7 @@
     FunctionTaskParameters,
     SimulationInputOverride,
     SimulationTaskParameters,
+    TagDetectionTaskOutput,
     TransformationTaskOutput,
     TransformationTaskParameters,
     WorkflowDefinition,
@@ -49,6 +50,48 @@ class TestWorkflowTaskOutput:
     def test_serialization(self, output: WorkflowTaskOutput, expected: dict):
         assert output.dump(camel_case=True) == expected
 
+    @pytest.mark.parametrize(
+        ["data", "cls"],
+        [
+            (
+                {
+                    "taskType": "function",
+                    "output": {"callId": 123, "functionId": 3456, "response": {"test": 1}},
+                },
+                FunctionTaskOutput,
+            ),
+            ({"taskType": "dynamic", "output": {}}, DynamicTaskOutput),
+            ({"taskType": "cdf", "output": {"response": {"test": 1}, "statusCode": 200}}, CDFTaskOutput),
+            ({"taskType": "transformation", "output": {"jobId": 789}}, TransformationTaskOutput),
+            (
+                {
+                    "taskType": "tagDetection",
+                    "output": {
+                        "jobs": [
+                            {
+                                "jobId": 321,
+                                "status": "Completed",
+                                "filePageRanges": [
+                                    {
+                                        "instanceId": {"space": "sp", "externalId": "id", "type": "node"},
+                                        "pageRange": {"begin": 1, "end": 5},
+                                    }
+                                ],
+                                "errorMessage": None,
+                            }
+                        ]
+                    },
+                },
+                TagDetectionTaskOutput,
+            ),
+        ],
+        ids=["function", "dynamic", "cdf", "transformation", "tagDetection"],
+    )
+    def test_serialization_roundtrip(self, data: dict, cls: type[WorkflowTaskOutput]):
+        task_output = WorkflowTaskOutput.load_output(data)
+        assert isinstance(task_output, cls)
+        assert task_output.dump(camel_case=True) == data["output"]
+
 
 class TestWorkflowId:
     @pytest.mark.parametrize(

From 7c70f7fbf36b816b9c6d75b9b114d628ab7442d5 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Mon, 20 Oct 2025 15:23:20 +0200
Subject: [PATCH 18/19] added errorMessage to filePageRange dataclass

---
 cognite/client/data_classes/workflows.py | 6 +++++-
 1 file changed, 5 insertions(+), 1 deletion(-)

diff --git a/cognite/client/data_classes/workflows.py b/cognite/client/data_classes/workflows.py
index d6a990655d..f485f4fcbd 100644
--- a/cognite/client/data_classes/workflows.py
+++ b/cognite/client/data_classes/workflows.py
@@ -917,23 +917,27 @@ class TagDetectionJobFilePageRange(CogniteObject):
     Args:
         instanceId (NodeId): The identifier of the instance.
         page_range (PageRange): No description.
+        error_message (str | None): Describes why the page range failed to be processed in case of page range processing failure.
     """
 
-    def __init__(self, instanceId: NodeId, page_range: PageRange) -> None:
+    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
 
     @classmethod
     def _load(cls, resource: dict, cognite_client: CogniteClient | None = None) -> Self:
         return cls(
             NodeId.load(resource["instanceId"]),
             PageRange._load(resource["pageRange"]),
+            resource.get("errorMessage"),
         )
 
     def dump(self, camel_case: bool = True) -> dict[str, Any]:
         return {
             "instanceId": self.instanceId.dump(camel_case=camel_case),
             "pageRange": self.page_range.dump(camel_case=camel_case),
+            "errorMessage": self.error_message,
         }
 
 

From 16d973891058240caff9f76ab571926114a89346 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?P=C3=A5l=20R=C3=B8nning?= <ronpal@users.noreply.github.com>
Date: Mon, 20 Oct 2025 15:28:12 +0200
Subject: [PATCH 19/19] Updated test

---
 tests/tests_unit/test_data_classes/test_workflows.py | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tests/tests_unit/test_data_classes/test_workflows.py b/tests/tests_unit/test_data_classes/test_workflows.py
index c45c9add3f..4a39eb3356 100644
--- a/tests/tests_unit/test_data_classes/test_workflows.py
+++ b/tests/tests_unit/test_data_classes/test_workflows.py
@@ -75,6 +75,7 @@ def test_serialization(self, output: WorkflowTaskOutput, expected: dict):
                                     {
                                         "instanceId": {"space": "sp", "externalId": "id", "type": "node"},
                                         "pageRange": {"begin": 1, "end": 5},
+                                        "errorMessage": None,
                                     }
                                 ],
                                 "errorMessage": None,