feat: add migration export and write fencing

src/core_hub/migration.py

@@ -1,6 +1,7 @@
 import hashlib
 import json
 from collections.abc import Iterable
+from datetime import datetime, timezone
 from typing import Any
 
 from sqlalchemy import select
@@ -34,10 +35,179 @@ def encode_body(payload: dict[str, Any]) -> str:
 
 
 def bundle_digest(bundle: dict[str, Any]) -> str:
-    canonical = json.dumps(bundle, sort_keys=True, separators=(",", ":"))
+    digestable = {key: value for key, value in bundle.items() if key != "bundleSha256"}
+    canonical = json.dumps(digestable, sort_keys=True, separators=(",", ":"))
     return hashlib.sha256(canonical.encode("utf-8")).hexdigest()
 
 
+def _timestamp(value: datetime) -> str:
+    if value.tzinfo is None:
+        value = value.replace(tzinfo=timezone.utc)
+    return value.astimezone(timezone.utc).isoformat().replace("+00:00", "Z")
+
+
+def _decoded(raw: str | None) -> dict[str, Any]:
+    value = json.loads(raw or "{}")
+    return value if isinstance(value, dict) else {}
+
+
+def _with_timestamps(
+    body: str | None,
+    *,
+    created_at: datetime,
+    updated_at: datetime | None = None,
+) -> dict[str, Any]:
+    value = _decoded(body)
+    value["createdAt"] = _timestamp(created_at)
+    if updated_at is not None:
+        value["updatedAt"] = _timestamp(updated_at)
+    return value
+
+
+async def export_bundle(
+    session: AsyncSession, *, source_revision: str | None = None
+) -> dict[str, Any]:
+    """Export all seven durable Core Hub tables without raw credential material."""
+    hubs = list((await session.execute(select(Hub).order_by(Hub.id))).scalars())
+    manifests = list(
+        (await session.execute(select(HubCapabilityManifest).order_by(HubCapabilityManifest.id)))
+        .scalars()
+    )
+    consumers = list(
+        (await session.execute(select(ApiConsumer).order_by(ApiConsumer.id))).scalars()
+    )
+    keys = list((await session.execute(select(ApiKey).order_by(ApiKey.id))).scalars())
+    widgets = list((await session.execute(select(Widget).order_by(Widget.id))).scalars())
+    events = list(
+        (await session.execute(select(InteractionEvent).order_by(InteractionEvent.id))).scalars()
+    )
+    runs = list(
+        (await session.execute(select(MigrationRun).order_by(MigrationRun.id))).scalars()
+    )
+
+    records: dict[str, list[dict[str, Any]]] = {
+        "hubs": [],
+        "hubCapabilityManifests": [],
+        "apiConsumers": [],
+        "apiKeys": [],
+        "widgets": [],
+        "interactionEvents": [],
+        "migrationRuns": [],
+    }
+    for row in hubs:
+        value = _with_timestamps(
+            row.body_json, created_at=row.created_at, updated_at=row.updated_at
+        )
+        value.update(
+            id=row.id,
+            slug=row.slug,
+            name=row.name,
+            domain=row.domain,
+            hubKind=row.hub_kind,
+            hubFamily=row.hub_family,
+            vsmFunction=row.vsm_function,
+            vsmSystem=row.vsm_system,
+            status=row.status,
+            description=row.description,
+        )
+        records["hubs"].append({key: child for key, child in value.items() if child is not None})
+    for row in manifests:
+        value = _with_timestamps(
+            row.body_json, created_at=row.created_at, updated_at=row.updated_at
+        )
+        value.update(
+            id=row.id,
+            hubId=row.hub_id,
+            hubSlug=row.hub_slug,
+            manifestVersion=row.manifest_version,
+            status=row.status,
+        )
+        records["hubCapabilityManifests"].append(
+            {key: child for key, child in value.items() if child is not None}
+        )
+    for row in consumers:
+        value = _with_timestamps(row.body_json, created_at=row.created_at)
+        value.update(
+            id=row.id,
+            slug=row.slug,
+            name=row.name,
+            description=row.description,
+            hubCapabilityManifestId=row.hub_capability_manifest_id,
+            rateLimitPerMinute=row.rate_limit_per_minute,
+            quotaPerDay=row.quota_per_day,
+            keyPrefix=row.key_prefix,
+            status=row.status,
+        )
+        records["apiConsumers"].append(
+            {key: child for key, child in value.items() if child is not None}
+        )
+    records["apiKeys"] = [
+        {
+            "id": row.id,
+            "apiConsumerId": row.api_consumer_id,
+            "keyPrefix": row.key_prefix,
+            "keyHash": row.key_hash,
+            "scopes": row.scopes,
+            "status": row.status,
+            "createdAt": _timestamp(row.created_at),
+        }
+        for row in keys
+    ]
+    for row in widgets:
+        value = _with_timestamps(row.body_json, created_at=row.created_at)
+        value.update(
+            id=row.id,
+            hubId=row.hub_id,
+            name=row.name,
+            widgetType=row.widget_type,
+            capabilityRef=row.capability_ref,
+            viewContext=row.view_context,
+            policyScope=row.policy_scope,
+            status=row.status,
+        )
+        records["widgets"].append(
+            {key: child for key, child in value.items() if child is not None}
+        )
+    for row in events:
+        value = _with_timestamps(row.body_json, created_at=row.created_at)
+        value.update(
+            id=row.id,
+            widgetId=row.widget_id,
+            eventType=row.event_type,
+            viewContext=row.view_context,
+            metadata=_decoded(row.metadata_json),
+        )
+        records["interactionEvents"].append(
+            {key: child for key, child in value.items() if child is not None}
+        )
+    records["migrationRuns"] = [
+        {
+            "id": row.id,
+            "source": row.source,
+            "schemaVersion": row.schema_version,
+            "bundleSha256": row.bundle_sha256,
+            "dryRun": row.dry_run,
+            "status": row.status,
+            "counts": _decoded(row.counts_json),
+            "diagnostics": _decoded(row.diagnostics_json),
+            "createdAt": _timestamp(row.created_at),
+        }
+        for row in runs
+    ]
+    high_water = max((_timestamp(row.created_at) for row in events), default=None)
+    bundle: dict[str, Any] = {
+        "schemaVersion": MIGRATION_SCHEMA_VERSION,
+        "source": "core-hub",
+        "exportedAt": _timestamp(datetime.now(timezone.utc)),
+        "highWaterMark": high_water,
+        "records": records,
+    }
+    if source_revision:
+        bundle["sourceRevision"] = source_revision
+    bundle["bundleSha256"] = bundle_digest(bundle)
+    return bundle
+
+
 def records_for(bundle: dict[str, Any], collection: str) -> list[dict[str, Any]]:
     records = bundle.get("records", {})
     if not isinstance(records, dict):