howl/migrations/versions/0001_initial_schema.py
lorentz ecc6681432 Add web UI, sender profiles, purge rules, and infosec action
Extends the pipeline with infosec classification, sender profile tracking,
and configurable purge rules. Adds a web dashboard for managing rules and
monitoring email processing. Includes new migrations and seed script.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-04-02 14:12:56 -04:00

200 lines
9.2 KiB
Python

"""Initial schema
Revision ID: 0001
Revises:
Create Date: 2026-04-01
"""
from __future__ import annotations
from typing import Sequence, Union
import sqlalchemy as sa
from alembic import op
from sqlalchemy.dialects import postgresql
revision: str = "0001"
down_revision: Union[str, None] = None
branch_labels: Union[str, Sequence[str], None] = None
depends_on: Union[str, Sequence[str], None] = None
def upgrade() -> None:
# Enum types
sender_type = postgresql.ENUM(
"customer", "vendor", "whitelist", "unknown",
name="sender_type", create_type=True,
)
email_action = postgresql.ENUM(
"inbox_keep", "flag_follow_up",
"move_customer", "move_vendor", "move_whitelist",
"move_spam", "move_review", "escalate",
name="email_action", create_type=True,
)
processing_status = postgresql.ENUM(
"pending", "processing", "completed", "failed", "skipped",
name="processing_status", create_type=True,
)
sender_type.create(op.get_bind(), checkfirst=True)
email_action.create(op.get_bind(), checkfirst=True)
processing_status.create(op.get_bind(), checkfirst=True)
# updated_at trigger function
op.execute("""
CREATE OR REPLACE FUNCTION set_updated_at()
RETURNS TRIGGER AS $$
BEGIN
NEW.updated_at = NOW();
RETURN NEW;
END;
$$ LANGUAGE plpgsql;
""")
# customers
op.create_table(
"customers",
sa.Column("id", postgresql.UUID(as_uuid=True), primary_key=True, server_default=sa.text("gen_random_uuid()")),
sa.Column("name", sa.Text, nullable=False),
sa.Column("company", sa.Text),
sa.Column("phone", sa.Text),
sa.Column("notes", sa.Text),
sa.Column("is_active", sa.Boolean, nullable=False, server_default="TRUE"),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()")),
sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()")),
)
op.execute("""
CREATE TRIGGER trg_customers_updated_at
BEFORE UPDATE ON customers
FOR EACH ROW EXECUTE FUNCTION set_updated_at();
""")
# customer_emails
op.create_table(
"customer_emails",
sa.Column("id", postgresql.UUID(as_uuid=True), primary_key=True, server_default=sa.text("gen_random_uuid()")),
sa.Column("customer_id", postgresql.UUID(as_uuid=True), sa.ForeignKey("customers.id", ondelete="CASCADE"), nullable=False),
sa.Column("email_address", sa.Text, nullable=False),
sa.Column("label", sa.Text),
sa.Column("is_primary", sa.Boolean, nullable=False, server_default="FALSE"),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()")),
sa.UniqueConstraint("email_address", name="uq_customer_email"),
)
op.create_index("idx_customer_emails_address", "customer_emails", [sa.text("LOWER(email_address)")])
# vendors
op.create_table(
"vendors",
sa.Column("id", postgresql.UUID(as_uuid=True), primary_key=True, server_default=sa.text("gen_random_uuid()")),
sa.Column("name", sa.Text, nullable=False),
sa.Column("company", sa.Text),
sa.Column("service_category", sa.Text),
sa.Column("phone", sa.Text),
sa.Column("notes", sa.Text),
sa.Column("is_active", sa.Boolean, nullable=False, server_default="TRUE"),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()")),
sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()")),
)
op.execute("""
CREATE TRIGGER trg_vendors_updated_at
BEFORE UPDATE ON vendors
FOR EACH ROW EXECUTE FUNCTION set_updated_at();
""")
# vendor_emails
op.create_table(
"vendor_emails",
sa.Column("id", postgresql.UUID(as_uuid=True), primary_key=True, server_default=sa.text("gen_random_uuid()")),
sa.Column("vendor_id", postgresql.UUID(as_uuid=True), sa.ForeignKey("vendors.id", ondelete="CASCADE"), nullable=False),
sa.Column("email_address", sa.Text, nullable=False),
sa.Column("label", sa.Text),
sa.Column("is_primary", sa.Boolean, nullable=False, server_default="FALSE"),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()")),
sa.UniqueConstraint("email_address", name="uq_vendor_email"),
)
op.create_index("idx_vendor_emails_address", "vendor_emails", [sa.text("LOWER(email_address)")])
# whitelist
op.create_table(
"whitelist",
sa.Column("id", postgresql.UUID(as_uuid=True), primary_key=True, server_default=sa.text("gen_random_uuid()")),
sa.Column("email_address", sa.Text),
sa.Column("domain", sa.Text),
sa.Column("description", sa.Text),
sa.Column("added_by", sa.Text),
sa.Column("expires_at", sa.DateTime(timezone=True)),
sa.Column("is_active", sa.Boolean, nullable=False, server_default="TRUE"),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()")),
sa.CheckConstraint("email_address IS NOT NULL OR domain IS NOT NULL", name="chk_whitelist_has_target"),
)
op.create_index(
"idx_whitelist_email", "whitelist",
[sa.text("LOWER(email_address)")],
postgresql_where=sa.text("email_address IS NOT NULL"),
)
op.create_index(
"idx_whitelist_domain", "whitelist",
[sa.text("LOWER(domain)")],
postgresql_where=sa.text("domain IS NOT NULL"),
)
# email_log
op.create_table(
"email_log",
sa.Column("id", postgresql.UUID(as_uuid=True), primary_key=True, server_default=sa.text("gen_random_uuid()")),
sa.Column("graph_message_id", sa.Text, nullable=False, unique=True),
sa.Column("graph_conversation_id", sa.Text),
sa.Column("mailbox", sa.Text, nullable=False),
sa.Column("sender_address", sa.Text, nullable=False),
sa.Column("sender_name", sa.Text),
sa.Column("subject", sa.Text),
sa.Column("received_at", sa.DateTime(timezone=True)),
sa.Column("has_attachments", sa.Boolean, nullable=False, server_default="FALSE"),
sa.Column("sender_type", postgresql.ENUM("customer", "vendor", "whitelist", "unknown", name="sender_type", create_type=False), nullable=False, server_default="unknown"),
sa.Column("matched_entity_id", postgresql.UUID(as_uuid=True)),
sa.Column("matched_entity_table", sa.Text),
sa.Column("llm_model", sa.Text),
sa.Column("llm_input_tokens", sa.Integer),
sa.Column("llm_output_tokens", sa.Integer),
sa.Column("llm_raw_response", postgresql.JSONB),
sa.Column("llm_classification", sa.Text),
sa.Column("llm_confidence", sa.Numeric(4, 3)),
sa.Column("llm_reasoning", sa.Text),
sa.Column("llm_suggested_action", postgresql.ENUM("inbox_keep", "flag_follow_up", "move_customer", "move_vendor", "move_whitelist", "move_spam", "move_review", "escalate", name="email_action", create_type=False)),
sa.Column("final_action", postgresql.ENUM("inbox_keep", "flag_follow_up", "move_customer", "move_vendor", "move_whitelist", "move_spam", "move_review", "escalate", name="email_action", create_type=False), nullable=False, server_default="inbox_keep"),
sa.Column("action_overridden", sa.Boolean, nullable=False, server_default="FALSE"),
sa.Column("action_executed_at", sa.DateTime(timezone=True)),
sa.Column("action_error", sa.Text),
sa.Column("status", postgresql.ENUM("pending", "processing", "completed", "failed", "skipped", name="processing_status", create_type=False), nullable=False, server_default="pending"),
sa.Column("processing_started_at", sa.DateTime(timezone=True)),
sa.Column("processing_completed_at", sa.DateTime(timezone=True)),
sa.Column("error_message", sa.Text),
sa.Column("retry_count", sa.Integer, nullable=False, server_default="0"),
sa.Column("created_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()")),
sa.Column("updated_at", sa.DateTime(timezone=True), server_default=sa.text("NOW()")),
)
op.create_index("idx_email_log_sender", "email_log", [sa.text("LOWER(sender_address)")])
op.create_index(
"idx_email_log_status", "email_log", ["status"],
postgresql_where=sa.text("status IN ('pending', 'processing')"),
)
op.create_index("idx_email_log_received", "email_log", [sa.text("received_at DESC")])
op.execute("""
CREATE TRIGGER trg_email_log_updated_at
BEFORE UPDATE ON email_log
FOR EACH ROW EXECUTE FUNCTION set_updated_at();
""")
def downgrade() -> None:
op.execute("DROP TRIGGER IF EXISTS trg_email_log_updated_at ON email_log")
op.drop_table("email_log")
op.execute("DROP TRIGGER IF EXISTS trg_vendors_updated_at ON vendors")
op.drop_table("vendor_emails")
op.drop_table("vendors")
op.execute("DROP TRIGGER IF EXISTS trg_customers_updated_at ON customers")
op.drop_table("customer_emails")
op.drop_table("customers")
op.drop_table("whitelist")
op.execute("DROP TYPE IF EXISTS sender_type")
op.execute("DROP TYPE IF EXISTS email_action")
op.execute("DROP TYPE IF EXISTS processing_status")
op.execute("DROP FUNCTION IF EXISTS set_updated_at")