first ingestion/normalization slice

src/kontextual_engine/adapters/sqlite/asset_registry.py

@@ -15,6 +15,8 @@ from kontextual_engine.core import (
     ContextEntity,
     CoreRelationship,
     IdempotencyRecord,
+    IngestionJob,
+    IngestionJobStatus,
     KnowledgeAsset,
     LifecycleState,
     MetadataRecord,
@@ -381,6 +383,51 @@ class SQLiteAssetRegistryRepository:
             return None
         return IdempotencyRecord.from_dict(_loads(row["payload"]))
 
+    def save_ingestion_job(self, job: IngestionJob) -> IngestionJob:
+        with self._connect() as conn:
+            conn.execute(
+                """
+                insert into ingestion_jobs (id, status, actor_id, correlation_id, created_at, updated_at, payload)
+                values (?, ?, ?, ?, ?, ?, ?)
+                on conflict(id) do update set
+                  status=excluded.status,
+                  actor_id=excluded.actor_id,
+                  correlation_id=excluded.correlation_id,
+                  updated_at=excluded.updated_at,
+                  payload=excluded.payload
+                """,
+                (
+                    job.job_id,
+                    job.status.value,
+                    job.actor_id,
+                    job.correlation_id,
+                    job.created_at,
+                    job.updated_at,
+                    _json(job.to_dict()),
+                ),
+            )
+        return job
+
+    def get_ingestion_job(self, job_id: str) -> IngestionJob:
+        row = self._one("select payload from ingestion_jobs where id = ?", (job_id,))
+        if row is None:
+            raise NotFoundError("Ingestion job not found", details={"job_id": job_id})
+        return IngestionJob.from_dict(_loads(row["payload"]))
+
+    def list_ingestion_jobs(
+        self,
+        *,
+        status: IngestionJobStatus | None = None,
+    ) -> list[IngestionJob]:
+        if status is None:
+            rows = self._all("select payload from ingestion_jobs order by created_at, id", ())
+        else:
+            rows = self._all(
+                "select payload from ingestion_jobs where status = ? order by created_at, id",
+                (status.value,),
+            )
+        return [IngestionJob.from_dict(_loads(row["payload"])) for row in rows]
+
     def _initialize(self) -> None:
         with self._connect() as conn:
             conn.executescript(
@@ -449,6 +496,15 @@ class SQLiteAssetRegistryRepository:
                   status text not null,
                   payload text not null
                 );
+                create table if not exists ingestion_jobs (
+                  id text primary key,
+                  status text not null,
+                  actor_id text not null,
+                  correlation_id text not null,
+                  created_at text not null,
+                  updated_at text not null,
+                  payload text not null
+                );
                 create index if not exists idx_assets_lifecycle on assets(lifecycle);
                 create index if not exists idx_representations_asset on representations(asset_id);
                 create index if not exists idx_metadata_asset on metadata_records(asset_id);
@@ -458,6 +514,8 @@ class SQLiteAssetRegistryRepository:
                 create index if not exists idx_versions_asset on asset_versions(asset_id);
                 create index if not exists idx_audit_target on audit_events(target);
                 create index if not exists idx_audit_correlation on audit_events(correlation_id);
+                create index if not exists idx_ingestion_jobs_status on ingestion_jobs(status);
+                create index if not exists idx_ingestion_jobs_correlation on ingestion_jobs(correlation_id);
                 """
             )