ksapi 2.5.0__tar.gz → 2.7.0__tar.gz

{ksapi-2.5.0 → ksapi-2.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ksapi
-Version: 2.5.0
+Version: 2.7.0
 Summary: Knowledge Stack API
 Home-page: 
 Author: OpenAPI Generator community

{ksapi-2.5.0 → ksapi-2.7.0}/ksapi/__init__.py

@@ -14,7 +14,7 @@
 """  # noqa: E501
 
 
-__version__ = "2.5.0"
+__version__ = "2.7.0"
 
 # Define package exports
 __all__ = [
@@ -197,6 +197,8 @@ __all__ = [
     "DocxParagraphAnchorOutput",
     "DownloadArtifact",
     "EditMemoryChunkRequest",
+    "EmailMetadata",
+    "EmailParty",
     "EmailSentResponse",
     "EmailVerificationRequest",
     "EnrichedCitation",
@@ -645,6 +647,8 @@ from ksapi.models.docx_paragraph_anchor_input import DocxParagraphAnchorInput as
 from ksapi.models.docx_paragraph_anchor_output import DocxParagraphAnchorOutput as DocxParagraphAnchorOutput
 from ksapi.models.download_artifact import DownloadArtifact as DownloadArtifact
 from ksapi.models.edit_memory_chunk_request import EditMemoryChunkRequest as EditMemoryChunkRequest
+from ksapi.models.email_metadata import EmailMetadata as EmailMetadata
+from ksapi.models.email_party import EmailParty as EmailParty
 from ksapi.models.email_sent_response import EmailSentResponse as EmailSentResponse
 from ksapi.models.email_verification_request import EmailVerificationRequest as EmailVerificationRequest
 from ksapi.models.enriched_citation import EnrichedCitation as EnrichedCitation

{ksapi-2.5.0 → ksapi-2.7.0}/ksapi/api/documents_api.py

@@ -2256,6 +2256,7 @@ class DocumentsApi:
         name: Annotated[Optional[StrictStr], Field(description="Document name (defaults to filename)")] = None,
         tag_ids: Annotated[Optional[List[UUID]], Field(description="Tag IDs applied to the created document.")] = None,
         idempotency_key: Annotated[Optional[StrictStr], Field(description="Opt-in key: a repeat with the same key at the same (parent, name) replays the existing document instead of a 409.")] = None,
+        email_nesting_depth: Annotated[Optional[Annotated[int, Field(le=10, strict=True, ge=0)]], Field(description="Internal: set by the email member fan-out when a nested email re-enters this endpoint. Leave at 0 for direct uploads.")] = None,
         ingestion_mode: Optional[IngestionMode] = None,
         chunk_type: Optional[ChunkType] = None,
         secondary_taxonomy: Optional[ImageTaxonomy] = None,
@@ -2289,6 +2290,8 @@ class DocumentsApi:
         :type tag_ids: List[UUID]
         :param idempotency_key: Opt-in key: a repeat with the same key at the same (parent, name) replays the existing document instead of a 409.
         :type idempotency_key: str
+        :param email_nesting_depth: Internal: set by the email member fan-out when a nested email re-enters this endpoint. Leave at 0 for direct uploads.
+        :type email_nesting_depth: int
         :param ingestion_mode:
         :type ingestion_mode: IngestionMode
         :param chunk_type:
@@ -2329,6 +2332,7 @@ class DocumentsApi:
             name=name,
             tag_ids=tag_ids,
             idempotency_key=idempotency_key,
+            email_nesting_depth=email_nesting_depth,
             ingestion_mode=ingestion_mode,
             chunk_type=chunk_type,
             secondary_taxonomy=secondary_taxonomy,
@@ -2364,6 +2368,7 @@ class DocumentsApi:
         name: Annotated[Optional[StrictStr], Field(description="Document name (defaults to filename)")] = None,
         tag_ids: Annotated[Optional[List[UUID]], Field(description="Tag IDs applied to the created document.")] = None,
         idempotency_key: Annotated[Optional[StrictStr], Field(description="Opt-in key: a repeat with the same key at the same (parent, name) replays the existing document instead of a 409.")] = None,
+        email_nesting_depth: Annotated[Optional[Annotated[int, Field(le=10, strict=True, ge=0)]], Field(description="Internal: set by the email member fan-out when a nested email re-enters this endpoint. Leave at 0 for direct uploads.")] = None,
         ingestion_mode: Optional[IngestionMode] = None,
         chunk_type: Optional[ChunkType] = None,
         secondary_taxonomy: Optional[ImageTaxonomy] = None,
@@ -2397,6 +2402,8 @@ class DocumentsApi:
         :type tag_ids: List[UUID]
         :param idempotency_key: Opt-in key: a repeat with the same key at the same (parent, name) replays the existing document instead of a 409.
         :type idempotency_key: str
+        :param email_nesting_depth: Internal: set by the email member fan-out when a nested email re-enters this endpoint. Leave at 0 for direct uploads.
+        :type email_nesting_depth: int
         :param ingestion_mode:
         :type ingestion_mode: IngestionMode
         :param chunk_type:
@@ -2437,6 +2444,7 @@ class DocumentsApi:
             name=name,
             tag_ids=tag_ids,
             idempotency_key=idempotency_key,
+            email_nesting_depth=email_nesting_depth,
             ingestion_mode=ingestion_mode,
             chunk_type=chunk_type,
             secondary_taxonomy=secondary_taxonomy,
@@ -2472,6 +2480,7 @@ class DocumentsApi:
         name: Annotated[Optional[StrictStr], Field(description="Document name (defaults to filename)")] = None,
         tag_ids: Annotated[Optional[List[UUID]], Field(description="Tag IDs applied to the created document.")] = None,
         idempotency_key: Annotated[Optional[StrictStr], Field(description="Opt-in key: a repeat with the same key at the same (parent, name) replays the existing document instead of a 409.")] = None,
+        email_nesting_depth: Annotated[Optional[Annotated[int, Field(le=10, strict=True, ge=0)]], Field(description="Internal: set by the email member fan-out when a nested email re-enters this endpoint. Leave at 0 for direct uploads.")] = None,
         ingestion_mode: Optional[IngestionMode] = None,
         chunk_type: Optional[ChunkType] = None,
         secondary_taxonomy: Optional[ImageTaxonomy] = None,
@@ -2505,6 +2514,8 @@ class DocumentsApi:
         :type tag_ids: List[UUID]
         :param idempotency_key: Opt-in key: a repeat with the same key at the same (parent, name) replays the existing document instead of a 409.
         :type idempotency_key: str
+        :param email_nesting_depth: Internal: set by the email member fan-out when a nested email re-enters this endpoint. Leave at 0 for direct uploads.
+        :type email_nesting_depth: int
         :param ingestion_mode:
         :type ingestion_mode: IngestionMode
         :param chunk_type:
@@ -2545,6 +2556,7 @@ class DocumentsApi:
             name=name,
             tag_ids=tag_ids,
             idempotency_key=idempotency_key,
+            email_nesting_depth=email_nesting_depth,
             ingestion_mode=ingestion_mode,
             chunk_type=chunk_type,
             secondary_taxonomy=secondary_taxonomy,
@@ -2575,6 +2587,7 @@ class DocumentsApi:
         name,
         tag_ids,
         idempotency_key,
+        email_nesting_depth,
         ingestion_mode,
         chunk_type,
         secondary_taxonomy,
@@ -2616,6 +2629,8 @@ class DocumentsApi:
             _form_params.append(('tag_ids', tag_ids))
         if idempotency_key is not None:
             _form_params.append(('idempotency_key', idempotency_key))
+        if email_nesting_depth is not None:
+            _form_params.append(('email_nesting_depth', email_nesting_depth))
         if ingestion_mode is not None:
             _form_params.append(('ingestion_mode', ingestion_mode))
         if chunk_type is not None:
@@ -3392,6 +3407,8 @@ class DocumentsApi:
         sort_dir: Annotated[Optional[SortDirection], Field(description="Sort direction; overrides the column's natural default")] = None,
         owner_id: Annotated[Optional[UUID], Field(description="Filter to documents owned by this user")] = None,
         document_type: Annotated[Optional[DocumentType], Field(description="Filter to documents of this type")] = None,
+        duration_min_ms: Annotated[Optional[Annotated[int, Field(strict=True, ge=0)]], Field(description="Only media whose active version is at least this long (milliseconds). Non-media documents have no duration and are excluded.")] = None,
+        duration_max_ms: Annotated[Optional[Annotated[int, Field(strict=True, ge=0)]], Field(description="Only media whose active version is at most this long.")] = None,
         with_tags: Annotated[Optional[StrictBool], Field(description="Include tags in the response (default: false)")] = None,
         limit: Annotated[Optional[Annotated[int, Field(le=100, strict=True, ge=1)]], Field(description="Number of items per page")] = None,
         offset: Annotated[Optional[Annotated[int, Field(strict=True, ge=0)]], Field(description="Number of items to skip")] = None,
@@ -3426,6 +3443,10 @@ class DocumentsApi:
         :type owner_id: UUID
         :param document_type: Filter to documents of this type
         :type document_type: DocumentType
+        :param duration_min_ms: Only media whose active version is at least this long (milliseconds). Non-media documents have no duration and are excluded.
+        :type duration_min_ms: int
+        :param duration_max_ms: Only media whose active version is at most this long.
+        :type duration_max_ms: int
         :param with_tags: Include tags in the response (default: false)
         :type with_tags: bool
         :param limit: Number of items per page
@@ -3468,6 +3489,8 @@ class DocumentsApi:
             sort_dir=sort_dir,
             owner_id=owner_id,
             document_type=document_type,
+            duration_min_ms=duration_min_ms,
+            duration_max_ms=duration_max_ms,
             with_tags=with_tags,
             limit=limit,
             offset=offset,
@@ -3504,6 +3527,8 @@ class DocumentsApi:
         sort_dir: Annotated[Optional[SortDirection], Field(description="Sort direction; overrides the column's natural default")] = None,
         owner_id: Annotated[Optional[UUID], Field(description="Filter to documents owned by this user")] = None,
         document_type: Annotated[Optional[DocumentType], Field(description="Filter to documents of this type")] = None,
+        duration_min_ms: Annotated[Optional[Annotated[int, Field(strict=True, ge=0)]], Field(description="Only media whose active version is at least this long (milliseconds). Non-media documents have no duration and are excluded.")] = None,
+        duration_max_ms: Annotated[Optional[Annotated[int, Field(strict=True, ge=0)]], Field(description="Only media whose active version is at most this long.")] = None,
         with_tags: Annotated[Optional[StrictBool], Field(description="Include tags in the response (default: false)")] = None,
         limit: Annotated[Optional[Annotated[int, Field(le=100, strict=True, ge=1)]], Field(description="Number of items per page")] = None,
         offset: Annotated[Optional[Annotated[int, Field(strict=True, ge=0)]], Field(description="Number of items to skip")] = None,
@@ -3538,6 +3563,10 @@ class DocumentsApi:
         :type owner_id: UUID
         :param document_type: Filter to documents of this type
         :type document_type: DocumentType
+        :param duration_min_ms: Only media whose active version is at least this long (milliseconds). Non-media documents have no duration and are excluded.
+        :type duration_min_ms: int
+        :param duration_max_ms: Only media whose active version is at most this long.
+        :type duration_max_ms: int
         :param with_tags: Include tags in the response (default: false)
         :type with_tags: bool
         :param limit: Number of items per page
@@ -3580,6 +3609,8 @@ class DocumentsApi:
             sort_dir=sort_dir,
             owner_id=owner_id,
             document_type=document_type,
+            duration_min_ms=duration_min_ms,
+            duration_max_ms=duration_max_ms,
             with_tags=with_tags,
             limit=limit,
             offset=offset,
@@ -3616,6 +3647,8 @@ class DocumentsApi:
         sort_dir: Annotated[Optional[SortDirection], Field(description="Sort direction; overrides the column's natural default")] = None,
         owner_id: Annotated[Optional[UUID], Field(description="Filter to documents owned by this user")] = None,
         document_type: Annotated[Optional[DocumentType], Field(description="Filter to documents of this type")] = None,
+        duration_min_ms: Annotated[Optional[Annotated[int, Field(strict=True, ge=0)]], Field(description="Only media whose active version is at least this long (milliseconds). Non-media documents have no duration and are excluded.")] = None,
+        duration_max_ms: Annotated[Optional[Annotated[int, Field(strict=True, ge=0)]], Field(description="Only media whose active version is at most this long.")] = None,
         with_tags: Annotated[Optional[StrictBool], Field(description="Include tags in the response (default: false)")] = None,
         limit: Annotated[Optional[Annotated[int, Field(le=100, strict=True, ge=1)]], Field(description="Number of items per page")] = None,
         offset: Annotated[Optional[Annotated[int, Field(strict=True, ge=0)]], Field(description="Number of items to skip")] = None,
@@ -3650,6 +3683,10 @@ class DocumentsApi:
         :type owner_id: UUID
         :param document_type: Filter to documents of this type
         :type document_type: DocumentType
+        :param duration_min_ms: Only media whose active version is at least this long (milliseconds). Non-media documents have no duration and are excluded.
+        :type duration_min_ms: int
+        :param duration_max_ms: Only media whose active version is at most this long.
+        :type duration_max_ms: int
         :param with_tags: Include tags in the response (default: false)
         :type with_tags: bool
         :param limit: Number of items per page
@@ -3692,6 +3729,8 @@ class DocumentsApi:
             sort_dir=sort_dir,
             owner_id=owner_id,
             document_type=document_type,
+            duration_min_ms=duration_min_ms,
+            duration_max_ms=duration_max_ms,
             with_tags=with_tags,
             limit=limit,
             offset=offset,
@@ -3723,6 +3762,8 @@ class DocumentsApi:
         sort_dir,
         owner_id,
         document_type,
+        duration_min_ms,
+        duration_max_ms,
         with_tags,
         limit,
         offset,
@@ -3772,6 +3813,14 @@ class DocumentsApi:
             
             _query_params.append(('document_type', document_type.value))
             
+        if duration_min_ms is not None:
+            
+            _query_params.append(('duration_min_ms', duration_min_ms))
+            
+        if duration_max_ms is not None:
+            
+            _query_params.append(('duration_max_ms', duration_max_ms))
+            
         if with_tags is not None:
             
             _query_params.append(('with_tags', with_tags))

{ksapi-2.5.0 → ksapi-2.7.0}/ksapi/api/system_jobs_api.py

@@ -1122,7 +1122,7 @@ class SystemJobsApi:
     ) -> ZipIngestionStatusResponse:
         """Get Zip Ingestion Status Handler
 
-        Get a ZIP fan-out's live status + per-member outcomes.  Tenant-scoped via the TenantId search attribute (no per-path can_read check — intentionally consistent with the sibling generic Temporal endpoints below; the opaque workflow_id is only handed to the uploader, who had can_write on the target). The per-member results come from the workflow's ``results`` query (served from retained history), so once Temporal retention expires this 404s.
+        Get a fan-out's live status + per-member outcomes.  Serves both container fan-outs: a ZIP archive's members and an email's attachments. Both expose the same ``results`` query, so one endpoint covers them rather than duplicating the tenant check and hydration.  Tenant-scoped via the TenantId search attribute (no per-path can_read check — intentionally consistent with the sibling generic Temporal endpoints below; the opaque workflow_id is only handed to the uploader, who had can_write on the target). The per-member results come from the workflow's ``results`` query (served from retained history), so once Temporal retention expires this 404s.
 
         :param workflow_id: (required)
         :type workflow_id: str
@@ -1190,7 +1190,7 @@ class SystemJobsApi:
     ) -> ApiResponse[ZipIngestionStatusResponse]:
         """Get Zip Ingestion Status Handler
 
-        Get a ZIP fan-out's live status + per-member outcomes.  Tenant-scoped via the TenantId search attribute (no per-path can_read check — intentionally consistent with the sibling generic Temporal endpoints below; the opaque workflow_id is only handed to the uploader, who had can_write on the target). The per-member results come from the workflow's ``results`` query (served from retained history), so once Temporal retention expires this 404s.
+        Get a fan-out's live status + per-member outcomes.  Serves both container fan-outs: a ZIP archive's members and an email's attachments. Both expose the same ``results`` query, so one endpoint covers them rather than duplicating the tenant check and hydration.  Tenant-scoped via the TenantId search attribute (no per-path can_read check — intentionally consistent with the sibling generic Temporal endpoints below; the opaque workflow_id is only handed to the uploader, who had can_write on the target). The per-member results come from the workflow's ``results`` query (served from retained history), so once Temporal retention expires this 404s.
 
         :param workflow_id: (required)
         :type workflow_id: str
@@ -1258,7 +1258,7 @@ class SystemJobsApi:
     ) -> RESTResponseType:
         """Get Zip Ingestion Status Handler
 
-        Get a ZIP fan-out's live status + per-member outcomes.  Tenant-scoped via the TenantId search attribute (no per-path can_read check — intentionally consistent with the sibling generic Temporal endpoints below; the opaque workflow_id is only handed to the uploader, who had can_write on the target). The per-member results come from the workflow's ``results`` query (served from retained history), so once Temporal retention expires this 404s.
+        Get a fan-out's live status + per-member outcomes.  Serves both container fan-outs: a ZIP archive's members and an email's attachments. Both expose the same ``results`` query, so one endpoint covers them rather than duplicating the tenant check and hydration.  Tenant-scoped via the TenantId search attribute (no per-path can_read check — intentionally consistent with the sibling generic Temporal endpoints below; the opaque workflow_id is only handed to the uploader, who had can_write on the target). The per-member results come from the workflow's ``results`` query (served from retained history), so once Temporal retention expires this 404s.
 
         :param workflow_id: (required)
         :type workflow_id: str

{ksapi-2.5.0 → ksapi-2.7.0}/ksapi/api_client.py

@@ -91,7 +91,7 @@ class ApiClient:
             self.default_headers[header_name] = header_value
         self.cookie = cookie
         # Set default User-Agent.
-        self.user_agent = 'OpenAPI-Generator/2.5.0/python'
+        self.user_agent = 'OpenAPI-Generator/2.7.0/python'
         self.client_side_validation = configuration.client_side_validation
 
     def __enter__(self):

{ksapi-2.5.0 → ksapi-2.7.0}/ksapi/configuration.py

@@ -562,7 +562,7 @@ conf = ksapi.Configuration(
                "OS: {env}\n"\
                "Python Version: {pyversion}\n"\
                "Version of the API: 0.1.0\n"\
-               "SDK Package Version: 2.5.0".\
+               "SDK Package Version: 2.7.0".\
                format(env=sys.platform, pyversion=sys.version)
 
     def get_host_settings(self) -> List[HostSetting]:

{ksapi-2.5.0 → ksapi-2.7.0}/ksapi/models/__init__.py

@@ -142,6 +142,8 @@ from ksapi.models.docx_paragraph_anchor_input import DocxParagraphAnchorInput
 from ksapi.models.docx_paragraph_anchor_output import DocxParagraphAnchorOutput
 from ksapi.models.download_artifact import DownloadArtifact
 from ksapi.models.edit_memory_chunk_request import EditMemoryChunkRequest
+from ksapi.models.email_metadata import EmailMetadata
+from ksapi.models.email_party import EmailParty
 from ksapi.models.email_sent_response import EmailSentResponse
 from ksapi.models.email_verification_request import EmailVerificationRequest
 from ksapi.models.enriched_citation import EnrichedCitation

{ksapi-2.5.0 → ksapi-2.7.0}/ksapi/models/chunk_metadata.py

@@ -38,6 +38,8 @@ class ChunkMetadata(BaseModel):
     secondary_taxonomy: Optional[ImageTaxonomy] = None
     start_ms: Optional[StrictInt] = Field(default=None, description="Start time of this chunk in the source media (ms from start).")
     end_ms: Optional[StrictInt] = Field(default=None, description="End time of this chunk in the source media (ms from start).")
+    speakers: Optional[List[StrictInt]] = Field(default=None, description="Every speaker label appearing in this chunk's segments, sorted. Lets a citation say which turn it came from. None when the provider does not diarize.")
+    languages: Optional[List[StrictStr]] = Field(default=None, description="Every language the ASR recognised across this chunk's segments, sorted. A meeting routinely code-switches, so a chunk can hold more than one; the document-level language is only the majority label and misreports a bilingual recording. None for non-media chunks and for media ingested before this field existed.")
     segments: Optional[List[SegmentSpan]] = Field(default=None, description="Per-ASR-segment spans inside this media chunk, in order, each carrying its char offset in the chunk content. Lets citation resolution narrow a chunk-level timeframe to the enclosing segment. None for non-media chunks and media ingested before this field existed.")
     sheet_name: Optional[StrictStr] = Field(default=None, description="Worksheet name this chunk was extracted from (XLSX only)")
     block_type: Optional[StrictStr] = Field(default=None, description="XLSXParser block type (e.g. table, calculation_block, chart_anchor)")
@@ -49,7 +51,7 @@ class ChunkMetadata(BaseModel):
     key_cells: Optional[List[StrictStr]] = Field(default=None, description="Notable output/header cells as A1 refs, e.g. 'Sheet1!A1' (XLSX only)")
     named_ranges: Optional[List[StrictStr]] = Field(default=None, description="Names of named ranges overlapping this chunk (XLSX only)")
     additional_properties: Dict[str, Any] = {}
-    __properties: ClassVar[List[str]] = ["polygons", "s3_urls", "summary", "summarize_for_embedding", "extracted_text_s3_uri", "secondary_taxonomy", "start_ms", "end_ms", "segments", "sheet_name", "block_type", "source_uri", "enriched_html", "cell_range", "dependency_summary", "formulas", "key_cells", "named_ranges"]
+    __properties: ClassVar[List[str]] = ["polygons", "s3_urls", "summary", "summarize_for_embedding", "extracted_text_s3_uri", "secondary_taxonomy", "start_ms", "end_ms", "speakers", "languages", "segments", "sheet_name", "block_type", "source_uri", "enriched_html", "cell_range", "dependency_summary", "formulas", "key_cells", "named_ranges"]
 
     model_config = ConfigDict(
         validate_by_name=True,
@@ -131,6 +133,16 @@ class ChunkMetadata(BaseModel):
         if self.end_ms is None and "end_ms" in self.model_fields_set:
             _dict['end_ms'] = None
 
+        # set to None if speakers (nullable) is None
+        # and model_fields_set contains the field
+        if self.speakers is None and "speakers" in self.model_fields_set:
+            _dict['speakers'] = None
+
+        # set to None if languages (nullable) is None
+        # and model_fields_set contains the field
+        if self.languages is None and "languages" in self.model_fields_set:
+            _dict['languages'] = None
+
         # set to None if segments (nullable) is None
         # and model_fields_set contains the field
         if self.segments is None and "segments" in self.model_fields_set:
@@ -201,6 +213,8 @@ class ChunkMetadata(BaseModel):
             "secondary_taxonomy": obj.get("secondary_taxonomy"),
             "start_ms": obj.get("start_ms"),
             "end_ms": obj.get("end_ms"),
+            "speakers": obj.get("speakers"),
+            "languages": obj.get("languages"),
             "segments": [SegmentSpan.from_dict(_item) for _item in obj["segments"]] if obj.get("segments") is not None else None,
             "sheet_name": obj.get("sheet_name"),
             "block_type": obj.get("block_type"),

{ksapi-2.5.0 → ksapi-2.7.0}/ksapi/models/create_upload_request.py

@@ -33,7 +33,10 @@ class CreateUploadRequest(BaseModel):
     filename: StrictStr = Field(description="Original filename; its extension selects the type + size cap")
     size_bytes: StrictInt = Field(description="Declared total size; fast-rejected against the type cap")
     tag_ids: Optional[List[UUID]] = Field(default=None, description="Tags applied to the document on completion (mirrors the buffered ingest endpoints so a mixed submit tags recordings too)")
-    __properties: ClassVar[List[str]] = ["parent_path_id", "name", "filename", "size_bytes", "tag_ids"]
+    workflow_run_id: Optional[UUID] = Field(default=None, description="Workflow run this upload belongs to; attributes the resulting document to the run in the audit log. Must be sent together with workflow_definition_id, and only by an assumed identity.")
+    workflow_definition_id: Optional[UUID] = Field(default=None, description="Workflow definition for workflow_run_id.")
+    idempotency_key: Optional[StrictStr] = Field(default=None, description="Replay key for callers that retry (e.g. the ZIP fan-out); completing twice with the same key replays the existing document instead of creating a duplicate.")
+    __properties: ClassVar[List[str]] = ["parent_path_id", "name", "filename", "size_bytes", "tag_ids", "workflow_run_id", "workflow_definition_id", "idempotency_key"]
 
     model_config = ConfigDict(
         validate_by_name=True,
@@ -74,6 +77,21 @@ class CreateUploadRequest(BaseModel):
             exclude=excluded_fields,
             exclude_none=True,
         )
+        # set to None if workflow_run_id (nullable) is None
+        # and model_fields_set contains the field
+        if self.workflow_run_id is None and "workflow_run_id" in self.model_fields_set:
+            _dict['workflow_run_id'] = None
+
+        # set to None if workflow_definition_id (nullable) is None
+        # and model_fields_set contains the field
+        if self.workflow_definition_id is None and "workflow_definition_id" in self.model_fields_set:
+            _dict['workflow_definition_id'] = None
+
+        # set to None if idempotency_key (nullable) is None
+        # and model_fields_set contains the field
+        if self.idempotency_key is None and "idempotency_key" in self.model_fields_set:
+            _dict['idempotency_key'] = None
+
         return _dict
 
     @classmethod
@@ -90,7 +108,10 @@ class CreateUploadRequest(BaseModel):
             "name": obj.get("name"),
             "filename": obj.get("filename"),
             "size_bytes": obj.get("size_bytes"),
-            "tag_ids": obj.get("tag_ids")
+            "tag_ids": obj.get("tag_ids"),
+            "workflow_run_id": obj.get("workflow_run_id"),
+            "workflow_definition_id": obj.get("workflow_definition_id"),
+            "idempotency_key": obj.get("idempotency_key")
         })
         return _obj
 

{ksapi-2.5.0 → ksapi-2.7.0}/ksapi/models/document_version_metadata.py

@@ -19,6 +19,7 @@ import json
 
 from pydantic import BaseModel, ConfigDict, Field, StrictBool, StrictInt, StrictStr
 from typing import Any, ClassVar, Dict, List, Optional
+from ksapi.models.email_metadata import EmailMetadata
 from ksapi.models.information_statistics import InformationStatistics
 from ksapi.models.pipeline_state import PipelineState
 from ksapi.models.xlsx_cell_anchor_output_or_docx_paragraph_anchor_output import XlsxCellAnchorOutputOrDocxParagraphAnchorOutput
@@ -44,6 +45,7 @@ class DocumentVersionMetadata(BaseModel):
     duration_ms: Optional[StrictInt] = Field(default=None, description="Media (audio/video) duration in milliseconds; null for non-media")
     language: Optional[StrictStr] = Field(default=None, description="ASR-detected language of the media transcript, as returned by the ASR provider; null for non-media or when the provider omits it")
     segment_count: Optional[StrictInt] = Field(default=None, description="Number of transcript segments produced by ASR; null for non-media")
+    email: Optional[EmailMetadata] = Field(default=None, description="Structured email headers; null for non-email documents")
     total_formulas: Optional[StrictInt] = Field(default=None, description="Total formula cells in the workbook (XLSX only)")
     xlsx_parse_result_s3: Optional[StrictStr] = Field(default=None, description="S3 URI to the full XLSX parse result JSON containing dependency graph, named ranges, and KPI catalog")
     xlsx_named_ranges: Optional[List[Dict[str, Any]]] = Field(default=None, description="Named ranges defined in the workbook (name, ref_string, scope)")
@@ -57,7 +59,7 @@ class DocumentVersionMetadata(BaseModel):
     file_md5: Optional[StrictStr] = Field(default='UNSET', description="MD5 of source bytes; 'UNSET' for pre-Phase-2 docs, real hex digest after first prep run")
     idempotency_key: Optional[StrictStr] = Field(default=None, description="Opt-in create key. A repeat ingest with the same key at the same (parent, name) replays this document instead of colliding — makes a ZIP fan-out member retry idempotent.")
     additional_properties: Dict[str, Any] = {}
-    __properties: ClassVar[List[str]] = ["source_s3", "cleaned_source_s3", "preconversion_source_s3", "cited_source_s3", "fast_plaintext_s3", "transcript_s3", "hash", "pipeline_state", "total_pages", "total_sections", "total_chunks", "duration_ms", "language", "segment_count", "total_formulas", "xlsx_parse_result_s3", "xlsx_named_ranges", "xlsx_kpi_catalog", "citation_anchors", "information_statistics", "quota_charged", "quota_page_count", "quota_media_minutes", "quota_idempotency_key", "file_md5", "idempotency_key"]
+    __properties: ClassVar[List[str]] = ["source_s3", "cleaned_source_s3", "preconversion_source_s3", "cited_source_s3", "fast_plaintext_s3", "transcript_s3", "hash", "pipeline_state", "total_pages", "total_sections", "total_chunks", "duration_ms", "language", "segment_count", "email", "total_formulas", "xlsx_parse_result_s3", "xlsx_named_ranges", "xlsx_kpi_catalog", "citation_anchors", "information_statistics", "quota_charged", "quota_page_count", "quota_media_minutes", "quota_idempotency_key", "file_md5", "idempotency_key"]
 
     model_config = ConfigDict(
         validate_by_name=True,
@@ -103,6 +105,9 @@ class DocumentVersionMetadata(BaseModel):
         # override the default output from pydantic by calling `to_dict()` of pipeline_state
         if self.pipeline_state:
             _dict['pipeline_state'] = self.pipeline_state.to_dict()
+        # override the default output from pydantic by calling `to_dict()` of email
+        if self.email:
+            _dict['email'] = self.email.to_dict()
         # override the default output from pydantic by calling `to_dict()` of each item in citation_anchors (list)
         _items = []
         if self.citation_anchors:
@@ -188,6 +193,11 @@ class DocumentVersionMetadata(BaseModel):
         if self.segment_count is None and "segment_count" in self.model_fields_set:
             _dict['segment_count'] = None
 
+        # set to None if email (nullable) is None
+        # and model_fields_set contains the field
+        if self.email is None and "email" in self.model_fields_set:
+            _dict['email'] = None
+
         # set to None if total_formulas (nullable) is None
         # and model_fields_set contains the field
         if self.total_formulas is None and "total_formulas" in self.model_fields_set:
@@ -249,6 +259,7 @@ class DocumentVersionMetadata(BaseModel):
             "duration_ms": obj.get("duration_ms"),
             "language": obj.get("language"),
             "segment_count": obj.get("segment_count"),
+            "email": EmailMetadata.from_dict(obj["email"]) if obj.get("email") is not None else None,
             "total_formulas": obj.get("total_formulas"),
             "xlsx_parse_result_s3": obj.get("xlsx_parse_result_s3"),
             "xlsx_named_ranges": obj.get("xlsx_named_ranges"),

{ksapi-2.5.0 → ksapi-2.7.0}/ksapi/models/document_version_metadata_update.py

@@ -19,6 +19,7 @@ import json
 
 from pydantic import BaseModel, ConfigDict, StrictBool, StrictInt, StrictStr
 from typing import Any, ClassVar, Dict, List, Optional
+from ksapi.models.email_metadata import EmailMetadata
 from ksapi.models.information_statistics import InformationStatistics
 from ksapi.models.pipeline_state import PipelineState
 from ksapi.models.xlsx_cell_anchor_input_or_docx_paragraph_anchor_input import XlsxCellAnchorInputOrDocxParagraphAnchorInput
@@ -47,6 +48,7 @@ class DocumentVersionMetadataUpdate(BaseModel):
     duration_ms: Optional[StrictInt] = None
     language: Optional[StrictStr] = None
     segment_count: Optional[StrictInt] = None
+    email: Optional[EmailMetadata] = None
     total_formulas: Optional[StrictInt] = None
     xlsx_parse_result_s3: Optional[StrictStr] = None
     xlsx_named_ranges: Optional[List[Dict[str, Any]]] = None
@@ -58,7 +60,7 @@ class DocumentVersionMetadataUpdate(BaseModel):
     quota_media_minutes: Optional[StrictInt] = None
     quota_idempotency_key: Optional[StrictStr] = None
     file_md5: Optional[StrictStr] = None
-    __properties: ClassVar[List[str]] = ["source_s3", "cleaned_source_s3", "preconversion_source_s3", "cited_source_s3", "standard_pipeline_json_s3", "fast_plaintext_s3", "transcript_s3", "high_accuracy_content_list_s3", "high_accuracy_middle_s3", "hash", "pipeline_state", "total_pages", "total_sections", "total_chunks", "duration_ms", "language", "segment_count", "total_formulas", "xlsx_parse_result_s3", "xlsx_named_ranges", "xlsx_kpi_catalog", "citation_anchors", "information_statistics", "quota_charged", "quota_page_count", "quota_media_minutes", "quota_idempotency_key", "file_md5"]
+    __properties: ClassVar[List[str]] = ["source_s3", "cleaned_source_s3", "preconversion_source_s3", "cited_source_s3", "standard_pipeline_json_s3", "fast_plaintext_s3", "transcript_s3", "high_accuracy_content_list_s3", "high_accuracy_middle_s3", "hash", "pipeline_state", "total_pages", "total_sections", "total_chunks", "duration_ms", "language", "segment_count", "email", "total_formulas", "xlsx_parse_result_s3", "xlsx_named_ranges", "xlsx_kpi_catalog", "citation_anchors", "information_statistics", "quota_charged", "quota_page_count", "quota_media_minutes", "quota_idempotency_key", "file_md5"]
 
     model_config = ConfigDict(
         validate_by_name=True,
@@ -102,6 +104,9 @@ class DocumentVersionMetadataUpdate(BaseModel):
         # override the default output from pydantic by calling `to_dict()` of pipeline_state
         if self.pipeline_state:
             _dict['pipeline_state'] = self.pipeline_state.to_dict()
+        # override the default output from pydantic by calling `to_dict()` of email
+        if self.email:
+            _dict['email'] = self.email.to_dict()
         # override the default output from pydantic by calling `to_dict()` of each item in citation_anchors (list)
         _items = []
         if self.citation_anchors:
@@ -197,6 +202,11 @@ class DocumentVersionMetadataUpdate(BaseModel):
         if self.segment_count is None and "segment_count" in self.model_fields_set:
             _dict['segment_count'] = None
 
+        # set to None if email (nullable) is None
+        # and model_fields_set contains the field
+        if self.email is None and "email" in self.model_fields_set:
+            _dict['email'] = None
+
         # set to None if total_formulas (nullable) is None
         # and model_fields_set contains the field
         if self.total_formulas is None and "total_formulas" in self.model_fields_set:
@@ -281,6 +291,7 @@ class DocumentVersionMetadataUpdate(BaseModel):
             "duration_ms": obj.get("duration_ms"),
             "language": obj.get("language"),
             "segment_count": obj.get("segment_count"),
+            "email": EmailMetadata.from_dict(obj["email"]) if obj.get("email") is not None else None,
             "total_formulas": obj.get("total_formulas"),
             "xlsx_parse_result_s3": obj.get("xlsx_parse_result_s3"),
             "xlsx_named_ranges": obj.get("xlsx_named_ranges"),