upload: set size_bytes=0 at early log creation to satisfy NOT NULL

alembic.ini

@@ -5,7 +5,7 @@
 # this is typically a path given in POSIX (e.g. forward slashes)
 # format, relative to the token %(here)s which refers to the location of this
 # ini file
-script_location = %(here)s/dev/alembic
+script_location = alembic
 
 # template used to generate migration file names; The default value is %%(rev)s_%%(slug)s
 # Uncomment the line below if you want the files to be prepended with date and time

alembic/README

@@ -0,0 +1 @@
+Generic single-database configuration.

alembic/env.py

@@ -0,0 +1,61 @@
+from logging.config import fileConfig
+import os
+import sys
+from sqlalchemy import engine_from_config
+from sqlalchemy import pool
+from alembic import context
+
+# Add the project root to the Python path
+sys.path.insert(0, os.path.dirname(os.path.dirname(__file__)))
+
+# Import your SQLAlchemy models and engine
+from models import SQLModel
+from database import engine
+
+# this is the Alembic Config object, which provides
+# access to the values within the .ini file in use.
+config = context.config
+
+# Interpret the config file for Python logging.
+# This line sets up loggers basically.
+if config.config_file_name is not None:
+    fileConfig(config.config_file_name)
+
+# Import all your SQLModel models here so that Alembic can detect them
+from models import User, DBSession
+
+# Set the target metadata to SQLModel.metadata
+target_metadata = SQLModel.metadata
+
+def run_migrations_offline() -> None:
+    """Run migrations in 'offline' mode."""
+    url = config.get_main_option("sqlalchemy.url")
+    context.configure(
+        url=url,
+        target_metadata=target_metadata,
+        literal_binds=True,
+        dialect_opts={"paramstyle": "named"},
+        compare_type=True,
+    )
+
+    with context.begin_transaction():
+        context.run_migrations()
+
+def run_migrations_online() -> None:
+    """Run migrations in 'online' mode."""
+    connectable = engine
+    
+    with connectable.connect() as connection:
+        context.configure(
+            connection=connection, 
+            target_metadata=target_metadata,
+            compare_type=True,
+        )
+
+        with context.begin_transaction():
+            context.run_migrations()
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

alembic/legacy_versions/0df481ee920b_add_publicstream_model.py

@@ -0,0 +1,71 @@
+"""Add PublicStream model
+
+Revision ID: 0df481ee920b
+Revises: f86c93c7a872
+Create Date: 2025-07-19 10:02:22.902696
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '0df481ee920b'
+down_revision: Union[str, Sequence[str], None] = 'f86c93c7a872'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    # First create the new publicstream table
+    op.create_table('publicstream',
+    sa.Column('uid', sa.String(), nullable=False),
+    sa.Column('size', sa.Integer(), nullable=False),
+    sa.Column('mtime', sa.Integer(), nullable=False),
+    sa.Column('created_at', sa.DateTime(), nullable=False),
+    sa.Column('updated_at', sa.DateTime(), nullable=False),
+    sa.PrimaryKeyConstraint('uid')
+    )
+    
+    # Drop the foreign key constraint first
+    op.drop_constraint('dbsession_user_id_fkey', 'dbsession', type_='foreignkey')
+    
+    # Then drop the unique constraint
+    op.drop_constraint(op.f('uq_user_username'), 'user', type_='unique')
+    
+    # Create the new index
+    op.create_index(op.f('ix_user_username'), 'user', ['username'], unique=True)
+    
+    # Recreate the foreign key constraint
+    op.create_foreign_key(
+        'dbsession_user_id_fkey', 'dbsession', 'user',
+        ['user_id'], ['username'], ondelete='CASCADE'
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    # Drop the foreign key constraint first
+    op.drop_constraint('dbsession_user_id_fkey', 'dbsession', type_='foreignkey')
+    
+    # Drop the index
+    op.drop_index(op.f('ix_user_username'), table_name='user')
+    
+    # Recreate the unique constraint
+    op.create_unique_constraint(op.f('uq_user_username'), 'user', ['username'])
+    
+    # Recreate the foreign key constraint
+    op.create_foreign_key(
+        'dbsession_user_id_fkey', 'dbsession', 'user',
+        ['user_id'], ['username'], ondelete='CASCADE'
+    )
+    
+    # Drop the publicstream table
+    op.drop_table('publicstream')
+    # ### end Alembic commands ###

alembic/legacy_versions/1ab2db0e4b5e_make_username_unique.py

@@ -0,0 +1,86 @@
+"""make username unique
+
+Revision ID: 1ab2db0e4b5e
+Revises: 
+Create Date: 2025-06-27 13:04:10.085253
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+import sqlmodel
+
+# revision identifiers, used by Alembic.
+revision: str = '1ab2db0e4b5e'
+down_revision: Union[str, Sequence[str], None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # 1. First, add the unique constraint to the username column
+    with op.batch_alter_table('user', schema=None) as batch_op:
+        batch_op.create_unique_constraint('uq_user_username', ['username'])
+    
+    # 2. Now create the dbsession table with the foreign key
+    op.create_table('dbsession',
+        sa.Column('token', sqlmodel.sql.sqltypes.AutoString(), nullable=False),
+        sa.Column('user_id', sqlmodel.sql.sqltypes.AutoString(), nullable=False),
+        sa.Column('ip_address', sqlmodel.sql.sqltypes.AutoString(), nullable=False),
+        sa.Column('user_agent', sqlmodel.sql.sqltypes.AutoString(), nullable=False),
+        sa.Column('created_at', sa.DateTime(), nullable=False),
+        sa.Column('expires_at', sa.DateTime(), nullable=False),
+        sa.Column('is_active', sa.Boolean(), nullable=False),
+        sa.Column('last_activity', sa.DateTime(), nullable=False),
+        sa.ForeignKeyConstraint(['user_id'], ['user.username'], ),
+        sa.PrimaryKeyConstraint('token')
+    )
+    
+    # 3. Drop old tables if they exist
+    if op.get_bind().engine.dialect.has_table(op.get_bind(), 'session'):
+        op.drop_index(op.f('ix_session_token'), table_name='session')
+        op.drop_index(op.f('ix_session_user_id'), table_name='session')
+        op.drop_table('session')
+    
+    if op.get_bind().engine.dialect.has_table(op.get_bind(), 'publicstream'):
+        op.drop_table('publicstream')
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # 1. First drop the dbsession table
+    op.drop_table('dbsession')
+    
+    # 2. Recreate the old tables
+    op.create_table('publicstream',
+        sa.Column('uid', sa.VARCHAR(), autoincrement=False, nullable=False),
+        sa.Column('size', sa.INTEGER(), autoincrement=False, nullable=False),
+        sa.Column('mtime', sa.INTEGER(), autoincrement=False, nullable=False),
+        sa.Column('updated_at', postgresql.TIMESTAMP(), autoincrement=False, nullable=False),
+        sa.PrimaryKeyConstraint('uid', name=op.f('publicstream_pkey'))
+    )
+    
+    op.create_table('session',
+        sa.Column('id', sa.INTEGER(), autoincrement=True, nullable=False),
+        sa.Column('user_id', sa.VARCHAR(), autoincrement=False, nullable=False),
+        sa.Column('token', sa.TEXT(), autoincrement=False, nullable=True),
+        sa.Column('ip_address', sa.VARCHAR(), autoincrement=False, nullable=False),
+        sa.Column('user_agent', sa.VARCHAR(), autoincrement=False, nullable=True),
+        sa.Column('created_at', postgresql.TIMESTAMP(), autoincrement=False, nullable=False),
+        sa.Column('expires_at', postgresql.TIMESTAMP(), autoincrement=False, nullable=False),
+        sa.Column('last_used_at', postgresql.TIMESTAMP(), autoincrement=False, nullable=False),
+        sa.Column('is_active', sa.BOOLEAN(), autoincrement=False, nullable=False),
+        sa.PrimaryKeyConstraint('id', name=op.f('session_pkey'))
+    )
+    
+    op.create_index(op.f('ix_session_user_id'), 'session', ['user_id'], unique=False)
+    op.create_index(op.f('ix_session_token'), 'session', ['token'], unique=True)
+    
+    # 3. Finally, remove the unique constraint from username
+    with op.batch_alter_table('user', schema=None) as batch_op:
+        batch_op.drop_constraint('uq_user_username', type_='unique')
+    # ### end Alembic commands ###

alembic/legacy_versions/8be4811023d8_add_display_name_to_user.py

@@ -0,0 +1,49 @@
+"""add_display_name_to_user
+
+Revision ID: 8be4811023d8
+Revises: 0df481ee920b
+Create Date: 2025-07-19 19:46:01.129412
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+import sqlmodel
+
+
+# revision identifiers, used by Alembic.
+revision: str = '8be4811023d8'
+down_revision: Union[str, Sequence[str], None] = '0df481ee920b'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_constraint(op.f('dbsession_user_id_fkey'), 'dbsession', type_='foreignkey')
+    op.create_foreign_key(None, 'dbsession', 'user', ['user_id'], ['username'])
+    op.alter_column('publicstream', 'storage_bytes',
+               existing_type=sa.INTEGER(),
+               nullable=False,
+               existing_server_default=sa.text('0'))
+    op.create_index(op.f('ix_publicstream_username'), 'publicstream', ['username'], unique=False)
+    op.drop_column('publicstream', 'size')
+    op.add_column('user', sa.Column('display_name', sqlmodel.sql.sqltypes.AutoString(), nullable=True))
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_column('user', 'display_name')
+    op.add_column('publicstream', sa.Column('size', sa.INTEGER(), autoincrement=False, nullable=False))
+    op.drop_index(op.f('ix_publicstream_username'), table_name='publicstream')
+    op.alter_column('publicstream', 'storage_bytes',
+               existing_type=sa.INTEGER(),
+               nullable=True,
+               existing_server_default=sa.text('0'))
+    op.drop_constraint(None, 'dbsession', type_='foreignkey')
+    op.create_foreign_key(op.f('dbsession_user_id_fkey'), 'dbsession', 'user', ['user_id'], ['username'], ondelete='CASCADE')
+    # ### end Alembic commands ###

alembic/legacy_versions/f86c93c7a872_add_processed_filename_to_uploadlog.py

@@ -0,0 +1,30 @@
+"""add_processed_filename_to_uploadlog
+
+Revision ID: f86c93c7a872
+Revises: 1ab2db0e4b5e
+Create Date: 2025-06-28 15:56:29.169668
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = 'f86c93c7a872'
+down_revision: Union[str, Sequence[str], None] = '1ab2db0e4b5e'
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    op.add_column('uploadlog', 
+                 sa.Column('processed_filename', sa.String(), nullable=True),
+                 schema=None)
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    op.drop_column('uploadlog', 'processed_filename', schema=None)

alembic/script.py.mako

@@ -0,0 +1,28 @@
+"""${message}
+
+Revision ID: ${up_revision}
+Revises: ${down_revision | comma,n}
+Create Date: ${create_date}
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+${imports if imports else ""}
+
+# revision identifiers, used by Alembic.
+revision: str = ${repr(up_revision)}
+down_revision: Union[str, Sequence[str], None] = ${repr(down_revision)}
+branch_labels: Union[str, Sequence[str], None] = ${repr(branch_labels)}
+depends_on: Union[str, Sequence[str], None] = ${repr(depends_on)}
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    ${upgrades if upgrades else "pass"}
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    ${downgrades if downgrades else "pass"}

alembic/versions/5f0b37b50730_initial_base_schema.py

@@ -0,0 +1,85 @@
+"""initial base schema
+
+Revision ID: 5f0b37b50730
+Revises: 
+Create Date: 2025-08-08 08:42:06.859256
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+
+
+# revision identifiers, used by Alembic.
+revision: str = '5f0b37b50730'
+down_revision: Union[str, Sequence[str], None] = None
+branch_labels: Union[str, Sequence[str], None] = None
+depends_on: Union[str, Sequence[str], None] = None
+
+
+def upgrade() -> None:
+    """Upgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.create_table('publicstream',
+    sa.Column('uid', sa.String(), nullable=False),
+    sa.Column('username', sa.String(), nullable=True),
+    sa.Column('storage_bytes', sa.Integer(), nullable=False),
+    sa.Column('mtime', sa.Integer(), nullable=False),
+    sa.Column('last_updated', sa.DateTime(), nullable=True),
+    sa.Column('created_at', sa.DateTime(), nullable=False),
+    sa.Column('updated_at', sa.DateTime(), nullable=False),
+    sa.PrimaryKeyConstraint('uid')
+    )
+    op.create_index(op.f('ix_publicstream_username'), 'publicstream', ['username'], unique=False)
+    op.create_table('uploadlog',
+    sa.Column('id', sa.Integer(), nullable=False),
+    sa.Column('uid', sa.String(), nullable=False),
+    sa.Column('ip', sa.String(), nullable=False),
+    sa.Column('filename', sa.String(), nullable=True),
+    sa.Column('processed_filename', sa.String(), nullable=True),
+    sa.Column('size_bytes', sa.Integer(), nullable=False),
+    sa.Column('created_at', sa.DateTime(), nullable=False),
+    sa.PrimaryKeyConstraint('id')
+    )
+    op.create_table('user',
+    sa.Column('token_created', sa.DateTime(), nullable=False),
+    sa.Column('email', sa.String(), nullable=False),
+    sa.Column('username', sa.String(), nullable=False),
+    sa.Column('token', sa.String(), nullable=False),
+    sa.Column('confirmed', sa.Boolean(), nullable=False),
+    sa.Column('ip', sa.String(), nullable=False),
+    sa.PrimaryKeyConstraint('email')
+    )
+    op.create_index(op.f('ix_user_username'), 'user', ['username'], unique=True)
+    op.create_table('userquota',
+    sa.Column('uid', sa.String(), nullable=False),
+    sa.Column('storage_bytes', sa.Integer(), nullable=False),
+    sa.PrimaryKeyConstraint('uid')
+    )
+    op.create_table('dbsession',
+    sa.Column('token', sa.String(), nullable=False),
+    sa.Column('uid', sa.String(), nullable=False),
+    sa.Column('ip_address', sa.String(), nullable=False),
+    sa.Column('user_agent', sa.String(), nullable=False),
+    sa.Column('created_at', sa.DateTime(), nullable=False),
+    sa.Column('expires_at', sa.DateTime(), nullable=False),
+    sa.Column('is_active', sa.Boolean(), nullable=False),
+    sa.Column('last_activity', sa.DateTime(), nullable=False),
+    sa.ForeignKeyConstraint(['uid'], ['user.email'], ),
+    sa.PrimaryKeyConstraint('token')
+    )
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.drop_table('dbsession')
+    op.drop_table('userquota')
+    op.drop_index(op.f('ix_user_username'), table_name='user')
+    op.drop_table('user')
+    op.drop_table('uploadlog')
+    op.drop_index(op.f('ix_publicstream_username'), table_name='publicstream')
+    op.drop_table('publicstream')
+    # ### end Alembic commands ###

gunicorn.conf.py

@@ -1,4 +1,4 @@
-bind = "0.0.0.0:8000"
+bind = "0.0.0.0:8100"
 workers = 2  # Tune based on available CPU cores
 worker_class = "uvicorn.workers.UvicornWorker"
 timeout = 300  # Increased from 60 to 300 seconds (5 minutes)

requirements.in

@@ -12,3 +12,5 @@ uvicorn==0.34.2
 uvloop==0.21.0
 watchfiles==1.0.5
 websockets==15.0.1
+alembic
+gunicorn

requirements.txt

@@ -4,6 +4,8 @@
 #
 #    pip-compile requirements.in
 #
+alembic==1.16.4
+    # via -r requirements.in
 annotated-types==0.6.0
     # via pydantic
 anyio==4.2.0
@@ -18,6 +20,8 @@ fastapi==0.115.12
     # via -r requirements.in
 greenlet==3.2.1
     # via sqlalchemy
+gunicorn==23.0.0
+    # via -r requirements.in
 h11==0.14.0
     # via uvicorn
 httptools==0.6.4
@@ -26,8 +30,14 @@ idna==3.4
     # via anyio
 limits==3.2.0
     # via slowapi
+mako==1.3.10
+    # via alembic
+markupsafe==3.0.2
+    # via mako
 packaging==23.0
-    # via limits
+    # via
+    #   gunicorn
+    #   limits
 psycopg2-binary==2.9.10
     # via -r requirements.in
 pydantic==2.6.0
@@ -47,13 +57,16 @@ slowapi==0.1.9
 sniffio==1.3.0
     # via anyio
 sqlalchemy==2.0.40
-    # via sqlmodel
+    # via
+    #   alembic
+    #   sqlmodel
 sqlmodel==0.0.24
     # via -r requirements.in
 starlette==0.46.1
     # via fastapi
 typing-extensions==4.13.2
     # via
+    #   alembic
     #   fastapi
     #   limits
     #   pydantic

upload.py

@@ -97,7 +97,7 @@ def upload(request: Request, uid: str = Form(...), file: UploadFile = Form(...))
                         ip=request.client.host,
                         filename=file.filename,  # original filename from user
                         processed_filename=None, # not yet processed
-                        size_bytes=None          # not yet known
+                        size_bytes=0            # placeholder to satisfy NOT NULL; updated after processing
                     )
                     db.add(early_log)
                     log_violation("UPLOAD_DEBUG", request.client.host, uid, f"[FORCE FLUSH] Before db.flush() after early_log add")