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.

kab_ingestion/ports.py

@@ -0,0 +1,23 @@
+from __future__ import annotations
+from typing import Protocol
+from .models import Change, IngestionBatch, SyncCursor
+
+class Connector(Protocol):
+    name: str
+    def full(self, tenant_id: str) -> IngestionBatch: ...
+    def incremental(self, tenant_id: str, cursor: SyncCursor | None) -> IngestionBatch: ...
+    def changes_from_webhook(self, payload: dict) -> list[Change]: ...
+
+class HTTPClient(Protocol):
+    def get(self, url: str, *, headers: dict[str, str], params: dict | None = None): ...
+
+class SecretProvider(Protocol):
+    def get(self, ref: str) -> str: ...
+
+class CursorStore(Protocol):
+    def load(self, tenant_id: str, connector: str) -> SyncCursor | None: ...
+    def save(self, cursor: SyncCursor) -> None: ...
+
+class KnowledgeStore(Protocol):
+    def upsert(self, documents: list) -> None: ...
+    def delete(self, document_ids: list[str], tenant_id: str) -> None: ...