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_orchestration.py

@@ -1,12 +1,16 @@
 from kab_ingestion.orchestrator import Orchestrator
+from kab_ingestion.models import *
 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'
+ def full(self,c): return [],SyncCursor(c.connector_id,"full")
+ def incremental(self,c,cur,changes=None): return [],cur
+ def webhook(self,c,p,h): return []
+class P:
+ def upsert(self,d): self.d=list(d)
+ def delete(self,i,t): pass
+def test_run_is_idempotent_shape():
+ p=P(); r=Orchestrator({"x":C()},p).run(ConnectorConfig("x","t","s",{}),mode="full",run_id="fixed")
+ assert r.status=="succeeded" and r.run_id=="fixed"
+def test_validation_rejects_cross_tenant():
+ from kab_ingestion.validation import validate_documents
+ d=Document("i","other","x","x","text/plain","h",None,Provenance("x","i","u"),ACL("other"))
+ assert not validate_documents([d],"t")["passed"]