feat: 添加 SQLAlchemy 模型 + Alembic 数据库迁移

alembic.ini

@@ -0,0 +1,149 @@
+# A generic, single database configuration.
+
+[alembic]
+# path to migration scripts.
+# 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/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
+# see https://alembic.sqlalchemy.org/en/latest/tutorial.html#editing-the-ini-file
+# for all available tokens
+# file_template = %%(year)d_%%(month).2d_%%(day).2d_%%(hour).2d%%(minute).2d-%%(rev)s_%%(slug)s
+# Or organize into date-based subdirectories (requires recursive_version_locations = true)
+# file_template = %%(year)d/%%(month).2d/%%(day).2d_%%(hour).2d%%(minute).2d_%%(second).2d_%%(rev)s_%%(slug)s
+
+# sys.path path, will be prepended to sys.path if present.
+# defaults to the current working directory.  for multiple paths, the path separator
+# is defined by "path_separator" below.
+prepend_sys_path = .
+
+
+# timezone to use when rendering the date within the migration file
+# as well as the filename.
+# If specified, requires the tzdata library which can be installed by adding
+# `alembic[tz]` to the pip requirements.
+# string value is passed to ZoneInfo()
+# leave blank for localtime
+# timezone =
+
+# max length of characters to apply to the "slug" field
+# truncate_slug_length = 40
+
+# set to 'true' to run the environment during
+# the 'revision' command, regardless of autogenerate
+# revision_environment = false
+
+# set to 'true' to allow .pyc and .pyo files without
+# a source .py file to be detected as revisions in the
+# versions/ directory
+# sourceless = false
+
+# version location specification; This defaults
+# to <script_location>/versions.  When using multiple version
+# directories, initial revisions must be specified with --version-path.
+# The path separator used here should be the separator specified by "path_separator"
+# below.
+# version_locations = %(here)s/bar:%(here)s/bat:%(here)s/alembic/versions
+
+# path_separator; This indicates what character is used to split lists of file
+# paths, including version_locations and prepend_sys_path within configparser
+# files such as alembic.ini.
+# The default rendered in new alembic.ini files is "os", which uses os.pathsep
+# to provide os-dependent path splitting.
+#
+# Note that in order to support legacy alembic.ini files, this default does NOT
+# take place if path_separator is not present in alembic.ini.  If this
+# option is omitted entirely, fallback logic is as follows:
+#
+# 1. Parsing of the version_locations option falls back to using the legacy
+#    "version_path_separator" key, which if absent then falls back to the legacy
+#    behavior of splitting on spaces and/or commas.
+# 2. Parsing of the prepend_sys_path option falls back to the legacy
+#    behavior of splitting on spaces, commas, or colons.
+#
+# Valid values for path_separator are:
+#
+# path_separator = :
+# path_separator = ;
+# path_separator = space
+# path_separator = newline
+#
+# Use os.pathsep. Default configuration used for new projects.
+path_separator = os
+
+# set to 'true' to search source files recursively
+# in each "version_locations" directory
+# new in Alembic version 1.10
+# recursive_version_locations = false
+
+# the output encoding used when revision files
+# are written from script.py.mako
+# output_encoding = utf-8
+
+# database URL.  This is consumed by the user-maintained env.py script only.
+# other means of configuring database URLs may be customized within the env.py
+# file.
+sqlalchemy.url = driver://user:pass@localhost/dbname
+
+
+[post_write_hooks]
+# post_write_hooks defines scripts or Python functions that are run
+# on newly generated revision scripts.  See the documentation for further
+# detail and examples
+
+# format using "black" - use the console_scripts runner, against the "black" entrypoint
+# hooks = black
+# black.type = console_scripts
+# black.entrypoint = black
+# black.options = -l 79 REVISION_SCRIPT_FILENAME
+
+# lint with attempts to fix using "ruff" - use the module runner, against the "ruff" module
+# hooks = ruff
+# ruff.type = module
+# ruff.module = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Alternatively, use the exec runner to execute a binary found on your PATH
+# hooks = ruff
+# ruff.type = exec
+# ruff.executable = ruff
+# ruff.options = check --fix REVISION_SCRIPT_FILENAME
+
+# Logging configuration.  This is also consumed by the user-maintained
+# env.py script only.
+[loggers]
+keys = root,sqlalchemy,alembic
+
+[handlers]
+keys = console
+
+[formatters]
+keys = generic
+
+[logger_root]
+level = WARNING
+handlers = console
+qualname =
+
+[logger_sqlalchemy]
+level = WARNING
+handlers =
+qualname = sqlalchemy.engine
+
+[logger_alembic]
+level = INFO
+handlers =
+qualname = alembic
+
+[handler_console]
+class = StreamHandler
+args = (sys.stderr,)
+level = NOTSET
+formatter = generic
+
+[formatter_generic]
+format = %(levelname)-5.5s [%(name)s] %(message)s
+datefmt = %H:%M:%S

alembic/README

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

alembic/env.py

@@ -0,0 +1,34 @@
+from alembic import context
+from sqlalchemy import engine_from_config, pool
+from app.models.announcement import Base
+
+config = context.config
+
+target_metadata = Base.metadata
+
+
+def run_migrations_offline():
+    from app.config import settings
+    url = settings.database_url
+    context.configure(url=url, target_metadata=target_metadata, literal_binds=True)
+    with context.begin_transaction():
+        context.run_migrations()
+
+
+def run_migrations_online():
+    from app.config import settings
+    connectable = engine_from_config(
+        {"sqlalchemy.url": settings.database_url},
+        prefix="sqlalchemy.",
+        poolclass=pool.NullPool,
+    )
+    with connectable.connect() as connection:
+        context.configure(connection=connection, target_metadata=target_metadata)
+        with context.begin_transaction():
+            context.run_migrations()
+
+
+if context.is_offline_mode():
+    run_migrations_offline()
+else:
+    run_migrations_online()

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/567cd83d63c2_create_announcements_table.py

@@ -0,0 +1,194 @@
+"""create_announcements_table
+
+Revision ID: 567cd83d63c2
+Revises: 
+Create Date: 2026-05-09 13:33:26.593143
+
+"""
+from typing import Sequence, Union
+
+from alembic import op
+import sqlalchemy as sa
+from sqlalchemy.dialects import postgresql
+
+# revision identifiers, used by Alembic.
+revision: str = '567cd83d63c2'
+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.drop_table('auto_announcements')
+    op.drop_table('announcement_sources')
+    op.drop_index(op.f('idx_dahuagov_content_hash'), table_name='dahuagov_announcements')
+    op.drop_index(op.f('idx_dahuagov_created_at'), table_name='dahuagov_announcements')
+    op.drop_index(op.f('idx_dahuagov_publish_date'), table_name='dahuagov_announcements')
+    op.drop_table('dahuagov_announcements')
+    op.drop_index(op.f('idx_crawl_results_crawled_at'), table_name='crawl_results')
+    op.drop_table('crawl_results')
+    op.drop_table('manual_announcements')
+    op.add_column('announcements', sa.Column('is_sent', sa.Boolean(), nullable=False))
+    op.alter_column('announcements', 'purchase_name',
+               existing_type=sa.VARCHAR(length=200),
+               nullable=False)
+    op.alter_column('announcements', 'content_url',
+               existing_type=sa.TEXT(),
+               nullable=False)
+    op.alter_column('announcements', 'content_hash',
+               existing_type=sa.VARCHAR(length=32),
+               type_=sa.String(length=64),
+               nullable=False)
+    op.alter_column('announcements', 'crawl_mode',
+               existing_type=sa.VARCHAR(length=20),
+               nullable=False,
+               existing_server_default=sa.text("'auto'::character varying"))
+    op.alter_column('announcements', 'is_new',
+               existing_type=sa.BOOLEAN(),
+               nullable=False,
+               existing_server_default=sa.text('true'))
+    op.alter_column('announcements', 'keyword_matched',
+               existing_type=sa.BOOLEAN(),
+               nullable=False,
+               existing_server_default=sa.text('false'))
+    op.alter_column('announcements', 'created_at',
+               existing_type=postgresql.TIMESTAMP(),
+               nullable=False,
+               existing_server_default=sa.text('CURRENT_TIMESTAMP'))
+    op.alter_column('announcements', 'updated_at',
+               existing_type=postgresql.TIMESTAMP(),
+               nullable=False,
+               existing_server_default=sa.text('CURRENT_TIMESTAMP'))
+    op.drop_index(op.f('idx_announcements_content_hash'), table_name='announcements')
+    op.drop_index(op.f('idx_announcements_created_at'), table_name='announcements')
+    op.drop_index(op.f('idx_announcements_publish_date'), table_name='announcements')
+    op.drop_index(op.f('idx_announcements_source_code'), table_name='announcements')
+    op.drop_column('announcements', 'date_filtered')
+    op.drop_column('announcements', 'is_today')
+    op.drop_column('announcements', 'crawled_at')
+    # ### end Alembic commands ###
+
+
+def downgrade() -> None:
+    """Downgrade schema."""
+    # ### commands auto generated by Alembic - please adjust! ###
+    op.add_column('announcements', sa.Column('crawled_at', postgresql.TIMESTAMP(), autoincrement=False, nullable=True))
+    op.add_column('announcements', sa.Column('is_today', sa.BOOLEAN(), server_default=sa.text('false'), autoincrement=False, nullable=True))
+    op.add_column('announcements', sa.Column('date_filtered', sa.BOOLEAN(), server_default=sa.text('true'), autoincrement=False, nullable=True))
+    op.create_index(op.f('idx_announcements_source_code'), 'announcements', ['source_code'], unique=False)
+    op.create_index(op.f('idx_announcements_publish_date'), 'announcements', [sa.literal_column('publish_date DESC')], unique=False)
+    op.create_index(op.f('idx_announcements_created_at'), 'announcements', [sa.literal_column('created_at DESC')], unique=False)
+    op.create_index(op.f('idx_announcements_content_hash'), 'announcements', ['content_hash'], unique=False)
+    op.alter_column('announcements', 'updated_at',
+               existing_type=postgresql.TIMESTAMP(),
+               nullable=True,
+               existing_server_default=sa.text('CURRENT_TIMESTAMP'))
+    op.alter_column('announcements', 'created_at',
+               existing_type=postgresql.TIMESTAMP(),
+               nullable=True,
+               existing_server_default=sa.text('CURRENT_TIMESTAMP'))
+    op.alter_column('announcements', 'keyword_matched',
+               existing_type=sa.BOOLEAN(),
+               nullable=True,
+               existing_server_default=sa.text('false'))
+    op.alter_column('announcements', 'is_new',
+               existing_type=sa.BOOLEAN(),
+               nullable=True,
+               existing_server_default=sa.text('true'))
+    op.alter_column('announcements', 'crawl_mode',
+               existing_type=sa.VARCHAR(length=20),
+               nullable=True,
+               existing_server_default=sa.text("'auto'::character varying"))
+    op.alter_column('announcements', 'content_hash',
+               existing_type=sa.String(length=64),
+               type_=sa.VARCHAR(length=32),
+               nullable=True)
+    op.alter_column('announcements', 'content_url',
+               existing_type=sa.TEXT(),
+               nullable=True)
+    op.alter_column('announcements', 'purchase_name',
+               existing_type=sa.VARCHAR(length=200),
+               nullable=True)
+    op.drop_column('announcements', 'is_sent')
+    op.create_table('manual_announcements',
+    sa.Column('id', sa.INTEGER(), autoincrement=True, nullable=False),
+    sa.Column('title', sa.VARCHAR(length=500), autoincrement=False, nullable=False),
+    sa.Column('publish_date', postgresql.TIMESTAMP(), autoincrement=False, nullable=False),
+    sa.Column('purchase_name', sa.VARCHAR(length=200), autoincrement=False, nullable=True),
+    sa.Column('content_url', sa.TEXT(), autoincrement=False, nullable=True),
+    sa.Column('source_code', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.Column('source_name', sa.VARCHAR(length=100), autoincrement=False, nullable=False),
+    sa.Column('announcement_type', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.Column('crawled_at', postgresql.TIMESTAMP(), autoincrement=False, nullable=True),
+    sa.Column('created_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('updated_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('content_hash', sa.VARCHAR(length=32), autoincrement=False, nullable=True),
+    sa.Column('keyword_matched', sa.BOOLEAN(), server_default=sa.text('false'), autoincrement=False, nullable=True),
+    sa.Column('date_filtered', sa.BOOLEAN(), server_default=sa.text('true'), autoincrement=False, nullable=True),
+    sa.Column('is_new', sa.BOOLEAN(), server_default=sa.text('true'), autoincrement=False, nullable=True),
+    sa.Column('is_today', sa.BOOLEAN(), server_default=sa.text('false'), autoincrement=False, nullable=True),
+    sa.PrimaryKeyConstraint('id', name=op.f('manual_announcements_pkey'))
+    )
+    op.create_table('crawl_results',
+    sa.Column('id', sa.INTEGER(), autoincrement=True, nullable=False),
+    sa.Column('source_code', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.Column('status', sa.VARCHAR(length=20), autoincrement=False, nullable=False),
+    sa.Column('total_count', sa.INTEGER(), server_default=sa.text('0'), autoincrement=False, nullable=True),
+    sa.Column('new_count', sa.INTEGER(), server_default=sa.text('0'), autoincrement=False, nullable=True),
+    sa.Column('error_message', sa.TEXT(), autoincrement=False, nullable=True),
+    sa.Column('crawled_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('duration', sa.DOUBLE_PRECISION(precision=53), server_default=sa.text('0.0'), autoincrement=False, nullable=True),
+    sa.ForeignKeyConstraint(['source_code'], ['announcement_sources.code'], name=op.f('crawl_results_source_code_fkey')),
+    sa.PrimaryKeyConstraint('id', name=op.f('crawl_results_pkey'))
+    )
+    op.create_index(op.f('idx_crawl_results_crawled_at'), 'crawl_results', [sa.literal_column('crawled_at DESC')], unique=False)
+    op.create_table('dahuagov_announcements',
+    sa.Column('id', sa.INTEGER(), autoincrement=True, nullable=False),
+    sa.Column('title', sa.VARCHAR(length=500), autoincrement=False, nullable=False),
+    sa.Column('publish_date', postgresql.TIMESTAMP(), autoincrement=False, nullable=False),
+    sa.Column('purchase_name', sa.VARCHAR(length=200), autoincrement=False, nullable=True),
+    sa.Column('content_url', sa.TEXT(), autoincrement=False, nullable=True),
+    sa.Column('source_code', sa.VARCHAR(length=50), server_default=sa.text("'dahuagov'::character varying"), autoincrement=False, nullable=False),
+    sa.Column('source_name', sa.VARCHAR(length=100), server_default=sa.text("'大化县政府网采购公告'::character varying"), autoincrement=False, nullable=False),
+    sa.Column('announcement_type', sa.VARCHAR(length=50), server_default=sa.text("'purchase'::character varying"), autoincrement=False, nullable=False),
+    sa.Column('crawled_at', postgresql.TIMESTAMP(), autoincrement=False, nullable=True),
+    sa.Column('created_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('updated_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('content_hash', sa.VARCHAR(length=32), autoincrement=False, nullable=True),
+    sa.Column('is_new', sa.BOOLEAN(), server_default=sa.text('true'), autoincrement=False, nullable=True),
+    sa.PrimaryKeyConstraint('id', name=op.f('dahuagov_announcements_pkey')),
+    sa.UniqueConstraint('content_hash', name=op.f('dahuagov_announcements_content_hash_key'), postgresql_include=[], postgresql_nulls_not_distinct=False)
+    )
+    op.create_index(op.f('idx_dahuagov_publish_date'), 'dahuagov_announcements', [sa.literal_column('publish_date DESC')], unique=False)
+    op.create_index(op.f('idx_dahuagov_created_at'), 'dahuagov_announcements', [sa.literal_column('created_at DESC')], unique=False)
+    op.create_index(op.f('idx_dahuagov_content_hash'), 'dahuagov_announcements', ['content_hash'], unique=False)
+    op.create_table('announcement_sources',
+    sa.Column('code', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.Column('category_id', sa.INTEGER(), autoincrement=False, nullable=False),
+    sa.Column('name', sa.VARCHAR(length=100), autoincrement=False, nullable=False),
+    sa.Column('type', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.PrimaryKeyConstraint('code', name=op.f('announcement_sources_pkey'))
+    )
+    op.create_table('auto_announcements',
+    sa.Column('id', sa.INTEGER(), autoincrement=True, nullable=False),
+    sa.Column('title', sa.VARCHAR(length=500), autoincrement=False, nullable=False),
+    sa.Column('publish_date', postgresql.TIMESTAMP(), autoincrement=False, nullable=False),
+    sa.Column('purchase_name', sa.VARCHAR(length=200), autoincrement=False, nullable=True),
+    sa.Column('content_url', sa.TEXT(), autoincrement=False, nullable=True),
+    sa.Column('source_code', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.Column('source_name', sa.VARCHAR(length=100), autoincrement=False, nullable=False),
+    sa.Column('announcement_type', sa.VARCHAR(length=50), autoincrement=False, nullable=False),
+    sa.Column('crawled_at', postgresql.TIMESTAMP(), autoincrement=False, nullable=True),
+    sa.Column('created_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('updated_at', postgresql.TIMESTAMP(), server_default=sa.text('CURRENT_TIMESTAMP'), autoincrement=False, nullable=True),
+    sa.Column('content_hash', sa.VARCHAR(length=32), autoincrement=False, nullable=True),
+    sa.Column('keyword_matched', sa.BOOLEAN(), server_default=sa.text('false'), autoincrement=False, nullable=True),
+    sa.Column('date_filtered', sa.BOOLEAN(), server_default=sa.text('true'), autoincrement=False, nullable=True),
+    sa.Column('is_new', sa.BOOLEAN(), server_default=sa.text('true'), autoincrement=False, nullable=True),
+    sa.Column('is_today', sa.BOOLEAN(), server_default=sa.text('false'), autoincrement=False, nullable=True),
+    sa.PrimaryKeyConstraint('id', name=op.f('auto_announcements_pkey')),
+    sa.UniqueConstraint('content_hash', name=op.f('auto_announcements_content_hash_key'), postgresql_include=[], postgresql_nulls_not_distinct=False)
+    )
+    # ### end Alembic commands ###

app/main.py

@@ -1,7 +1,17 @@
 import logging
 from contextlib import asynccontextmanager
 from fastapi import FastAPI
+from sqlalchemy.ext.asyncio import create_async_engine, async_sessionmaker, AsyncSession
 from app.config import settings
+from app.models.announcement import Base
+
+engine = create_async_engine(settings.database_url, echo=settings.debug)
+async_session = async_sessionmaker(engine, class_=AsyncSession, expire_on_commit=False)
+
+
+async def get_db() -> AsyncSession:
+    async with async_session() as session:
+        yield session
 
 
 @asynccontextmanager
@@ -11,6 +21,7 @@ async def lifespan(app: FastAPI):
         format="%(asctime)s [%(levelname)s] %(name)s: %(message)s",
     )
     yield
+    await engine.dispose()
 
 
 app = FastAPI(

app/models/announcement.py

@@ -0,0 +1,40 @@
+import hashlib
+from datetime import datetime, date
+from sqlalchemy import String, Boolean, DateTime, Integer, Text, func
+from sqlalchemy.orm import DeclarativeBase, Mapped, mapped_column
+
+
+class Base(DeclarativeBase):
+    pass
+
+
+class Announcement(Base):
+    __tablename__ = "announcements"
+
+    id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
+    title: Mapped[str] = mapped_column(String(500), nullable=False)
+    publish_date: Mapped[datetime] = mapped_column(DateTime, nullable=False)
+    purchase_name: Mapped[str] = mapped_column(String(200), default="")
+    content_url: Mapped[str] = mapped_column(Text, default="")
+    source_code: Mapped[str] = mapped_column(String(50), nullable=False)
+    source_name: Mapped[str] = mapped_column(String(100), nullable=False)
+    announcement_type: Mapped[str] = mapped_column(String(50), default="purchase")
+    content_hash: Mapped[str] = mapped_column(String(64), unique=True, nullable=False)
+    crawl_mode: Mapped[str] = mapped_column(String(20), default="auto")
+    is_new: Mapped[bool] = mapped_column(Boolean, default=True)
+    is_sent: Mapped[bool] = mapped_column(Boolean, default=False)
+    keyword_matched: Mapped[bool] = mapped_column(Boolean, default=False)
+    created_at: Mapped[datetime] = mapped_column(DateTime, server_default=func.now())
+    updated_at: Mapped[datetime] = mapped_column(DateTime, server_default=func.now(), onupdate=func.now())
+
+    @staticmethod
+    def generate_hash(title: str, publish_date: str, purchase_name: str,
+                      content_url: str, source_code: str) -> str:
+        content = f"{title}|{publish_date}|{purchase_name}|{content_url}|{source_code}"
+        return hashlib.sha256(content.encode("utf-8")).hexdigest()
+
+    @staticmethod
+    def source_map() -> dict:
+        import json
+        from app.config import settings
+        return json.loads(settings.announcement_sources)

app/models/schemas.py

@@ -0,0 +1,56 @@
+from datetime import datetime
+from typing import Optional
+from pydantic import BaseModel
+
+
+class AnnouncementResponse(BaseModel):
+    id: int
+    title: str
+    publish_date: datetime
+    purchase_name: str
+    content_url: str
+    source_code: str
+    source_name: str
+    announcement_type: str
+    crawl_mode: str
+    is_new: bool
+    is_sent: bool
+    keyword_matched: bool
+    created_at: datetime
+
+    model_config = {"from_attributes": True}
+
+
+class AnnouncementListResponse(BaseModel):
+    total: int
+    page: int
+    page_size: int
+    items: list[AnnouncementResponse]
+
+
+class CrawlTriggerRequest(BaseModel):
+    keywords: Optional[list[str]] = None
+    sources: Optional[list[str]] = None
+    manual: bool = False
+
+
+class CrawlStatusResponse(BaseModel):
+    running: bool
+    last_crawl_time: Optional[datetime] = None
+    total_sources: int
+
+
+class SourceInfo(BaseModel):
+    code: str
+    name: str
+    type: str
+
+
+class SourcesResponse(BaseModel):
+    sources: list[SourceInfo]
+
+
+class JobResponse(BaseModel):
+    id: str
+    name: str
+    next_run_time: Optional[str] = None