feat(12-01): durable owner-scoped cloud metadata schema (migration 0006 + models)

- Migration 0006: cloud_items, cloud_item_topics, cloud_folder_states tables
- cloud_connections: add display_name_override column for same-provider disambiguation
- CloudItem, CloudItemTopic, CloudFolderState ORM models with owner/connection indexes
- Unique (connection_id, provider_item_id) boundary; no MinIO object_key field
- Root folder state representable as parent_ref='' without CloudItem parent row
- services/cloud_items.py: resolve_owned_connection, upsert, list, reconcile, folder state
- 17 unit/integration tests covering model fields, isolation, quota invariant, idempotency
This commit is contained in:
curo1305
2026-06-18 22:37:28 +02:00
parent 0a7273b9fe
commit 718fb2c2b5
4 changed files with 1156 additions and 0 deletions
@@ -0,0 +1,208 @@
"""Add cloud_items, cloud_item_topics, and cloud_folder_states tables.
Revision ID: 0006
Revises: 0005
Create Date: 2026-06-18
Changes:
1. cloud_connections: add display_name_override (nullable Text) for user-defined
display names distinct from the auto-generated default. Does NOT add a
(user_id, provider) unique constraint — multiple same-provider accounts must
remain permitted (D-02, D-03).
2. cloud_items: durable per-item metadata indexed by connection/provider item ID.
No MinIO object_key field — provider bytes are never mirrored here.
analysis_status, semantic_index_status, semantic_index_data reserved for
Phase 14 analysis and semantic search.
3. cloud_item_topics: association between cloud items and existing owner topics.
No local Document row required.
4. cloud_folder_states: per-connection/parent-ref folder freshness row.
Root folder represented with parent_ref = '' (empty string, not NULL) to
allow a unique constraint on (connection_id, parent_ref).
Design notes:
- Ownership boundary: every cloud row has user_id + connection_id.
- Uniqueness: (connection_id, provider_item_id) for items; (connection_id, parent_ref)
for folder states. Same provider_item_id can coexist across connections.
- CASCADE: deleting a user or connection cascades all child rows automatically.
- D-18 compliance: no quota_used / byte_size field that flows to quotas.used_bytes.
"""
from __future__ import annotations
import sqlalchemy as sa
from sqlalchemy.dialects.postgresql import UUID as PG_UUID, JSONB
from alembic import op
# revision identifiers, used by Alembic.
revision = "0006"
down_revision = "0005"
branch_labels = None
depends_on = None
def upgrade() -> None:
# 1. Extend cloud_connections with optional user-defined display name override
op.add_column(
"cloud_connections",
sa.Column("display_name_override", sa.Text, nullable=True),
)
# 2. cloud_items table
op.create_table(
"cloud_items",
sa.Column(
"id",
PG_UUID(as_uuid=True),
primary_key=True,
server_default=sa.text("gen_random_uuid()"),
),
sa.Column(
"user_id",
PG_UUID(as_uuid=True),
sa.ForeignKey("users.id", ondelete="CASCADE"),
nullable=False,
),
sa.Column(
"connection_id",
PG_UUID(as_uuid=True),
sa.ForeignKey("cloud_connections.id", ondelete="CASCADE"),
nullable=False,
),
# Opaque provider-assigned identifier (e.g. Drive file ID, OneDrive driveItem id)
sa.Column("provider_item_id", sa.Text, nullable=False),
# Opaque reference to the parent folder (empty string = root)
sa.Column("parent_ref", sa.Text, nullable=True),
# Provider-reported path snapshot — informational only, not used for lookup
sa.Column("path_snapshot", sa.Text, nullable=True),
sa.Column("name", sa.Text, nullable=False),
# "file" | "folder"
sa.Column("kind", sa.String(8), nullable=False),
sa.Column("content_type", sa.Text, nullable=True),
# Provider-reported size — never flows to quotas.used_bytes (D-18)
sa.Column("provider_size", sa.BigInteger, nullable=True),
sa.Column("etag", sa.Text, nullable=True),
sa.Column("version", sa.Text, nullable=True),
sa.Column("modified_at", sa.TIMESTAMP(timezone=True), nullable=True),
sa.Column(
"last_seen_at",
sa.TIMESTAMP(timezone=True),
nullable=False,
server_default=sa.text("now()"),
),
sa.Column("deleted_at", sa.TIMESTAMP(timezone=True), nullable=True),
# Phase 14: byte analysis fields (reserved)
sa.Column("extracted_text", sa.Text, nullable=True),
# "pending" | "processing" | "done" | "error" | "skipped"
sa.Column("analysis_status", sa.String(16), nullable=False, server_default="pending"),
# "none" | "pending" | "indexed" | "error"
sa.Column("semantic_index_status", sa.String(16), nullable=False, server_default="none"),
# Provider-independent semantic search artifacts (reserved for Phase 15)
sa.Column("semantic_index_data", JSONB, nullable=True),
sa.Column(
"created_at",
sa.TIMESTAMP(timezone=True),
nullable=False,
server_default=sa.text("now()"),
),
sa.Column(
"updated_at",
sa.TIMESTAMP(timezone=True),
nullable=False,
server_default=sa.text("now()"),
),
# Uniqueness: same provider item ID can exist in different connections only
sa.UniqueConstraint(
"connection_id", "provider_item_id",
name="uq_cloud_items_connection_provider_item",
),
)
# Indexes for ownership lookups
op.create_index("ix_cloud_items_user_id", "cloud_items", ["user_id"])
op.create_index("ix_cloud_items_connection_id", "cloud_items", ["connection_id"])
op.create_index(
"ix_cloud_items_connection_parent",
"cloud_items",
["connection_id", "parent_ref"],
)
# 3. cloud_item_topics association table
op.create_table(
"cloud_item_topics",
sa.Column(
"cloud_item_id",
PG_UUID(as_uuid=True),
sa.ForeignKey("cloud_items.id", ondelete="CASCADE"),
primary_key=True,
),
sa.Column(
"topic_id",
PG_UUID(as_uuid=True),
sa.ForeignKey("topics.id", ondelete="CASCADE"),
primary_key=True,
),
)
# 4. cloud_folder_states table
# parent_ref uses empty string '' for root (allows unique constraint)
op.create_table(
"cloud_folder_states",
sa.Column(
"id",
PG_UUID(as_uuid=True),
primary_key=True,
server_default=sa.text("gen_random_uuid()"),
),
sa.Column(
"user_id",
PG_UUID(as_uuid=True),
sa.ForeignKey("users.id", ondelete="CASCADE"),
nullable=False,
),
sa.Column(
"connection_id",
PG_UUID(as_uuid=True),
sa.ForeignKey("cloud_connections.id", ondelete="CASCADE"),
nullable=False,
),
# '' for root folder, provider ref string for non-root
sa.Column("parent_ref", sa.Text, nullable=False, server_default=""),
# "refreshing" | "fresh" | "warning"
sa.Column("refresh_state", sa.String(16), nullable=False, server_default="fresh"),
sa.Column("last_refreshed_at", sa.TIMESTAMP(timezone=True), nullable=True),
# Stable error code (e.g. "token_expired", "rate_limited") — never raw exception
sa.Column("error_code", sa.String(64), nullable=True),
# Safe human-readable message — never raw provider error text
sa.Column("error_message", sa.Text, nullable=True),
sa.Column(
"created_at",
sa.TIMESTAMP(timezone=True),
nullable=False,
server_default=sa.text("now()"),
),
sa.Column(
"updated_at",
sa.TIMESTAMP(timezone=True),
nullable=False,
server_default=sa.text("now()"),
),
sa.UniqueConstraint(
"connection_id", "parent_ref",
name="uq_cloud_folder_states_connection_parent",
),
)
op.create_index("ix_cloud_folder_states_connection", "cloud_folder_states", ["connection_id"])
def downgrade() -> None:
op.drop_index("ix_cloud_folder_states_connection", table_name="cloud_folder_states")
op.drop_table("cloud_folder_states")
op.drop_table("cloud_item_topics")
op.drop_index("ix_cloud_items_connection_parent", table_name="cloud_items")
op.drop_index("ix_cloud_items_connection_id", table_name="cloud_items")
op.drop_index("ix_cloud_items_user_id", table_name="cloud_items")
op.drop_table("cloud_items")
op.drop_column("cloud_connections", "display_name_override")