decomposer: generate deliverable files for Define the normalized ingestion contract and pluggable source-connector interface for SCM, CMS, and other content sources.; Implement a GitHub SCM connector that conforms to the normalized ingestion contract and supports scoped full and incremental ingestion of Markdown, plain-text, and source files with webhook and revision metadata.; Implement a SharePoint CMS connector that conforms to the normalized ingestion contract and supports scoped full and incremental ingestion of PDF, DOCX, and HTML files with webhook and revision metadata.; Implement ingestion orchestration and triggers; Normalize, govern, and publish ingested content to the shared knowledge store.; Add deployment/configuration, tests, and documentation for the ingestion agent.; Validate end-to-end ingestion and downstream content availability.

tests/test_connectors.py

@@ -0,0 +1,17 @@
+from datetime import datetime, timezone
+from kab_ingestion.github import GitHubConnector
+from kab_ingestion.sharepoint import SharePointConnector
+class Secrets:
+ def get(self, ref): return 'token'
+class GH:
+ def list_files(self,*a): return [{'path':'docs/a.md','content':'hello','mime_type':'text/markdown','sha':'1','html_url':'u'}]
+ def list_changed(self,*a): return self.list_files()
+class SP:
+ def list_files(self,*a): return [{'id':'1','name':'a.html','text':'x','mime_type':'text/html','web_url':'u','last_modified':datetime.now(timezone.utc)}]
+ def delta(self,*a): return self.list_files(), 'next'
+def test_github_scope_and_normalization():
+ c=GitHubConnector(GH(),Secrets(),{'owner':'o','repo':'r','path_prefix':'docs/','credential_ref':'s'})
+ assert c.full('t').documents[0].document_id == 'github:1'
+def test_sharepoint_normalization():
+ c=SharePointConnector(SP(),Secrets(),{'site_id':'s','drive_id':'d','credential_ref':'x'})
+ assert c.full('t').documents[0].mime_type == 'text/html'

tests/test_contract.py

@@ -0,0 +1,6 @@
+from datetime import datetime, timezone
+from kab_ingestion.models import ACL, NormalizedDocument
+
+def test_document_requires_tenant_and_acl():
+    d = NormalizedDocument(document_id='x', tenant_id='t', title='a', body='b', mime_type='text/plain', source_path='a', content_hash='h', updated_at=datetime.now(timezone.utc), acl=ACL(), provenance={'connector':'x','source_uri':'u','source_id':'s','retrieved_at':datetime.now(timezone.utc)})
+    assert d.tenant_id == 't' and not d.acl.public

tests/test_governance.py

@@ -0,0 +1,9 @@
+import pytest
+from kab_ingestion.governance import GovernedPublisher
+class Store:
+ def upsert(self,d): self.docs=d
+ def delete(self,*a): pass
+def test_tenant_isolation():
+ class D: tenant_id='other'
+ class B: tenant_id='acme'; documents=[D()]
+ with pytest.raises(PermissionError): GovernedPublisher(Store(),[]).publish(B())

tests/test_orchestration.py

@@ -0,0 +1,12 @@
+from kab_ingestion.orchestrator import Orchestrator
+class C:
+ def incremental(self,t,c): return type('B',(),{'next_cursor':None})()
+ def full(self,t): return self.incremental(t,None)
+class Cur:
+ def load(self,*a): return None
+ def save(self,*a): pass
+class Pub:
+ def publish(self,b): pass
+def test_run_success():
+ r=Orchestrator({'x':C()},Cur(),Pub()).run('x','t')
+ assert r.status == 'succeeded'