feat: add detailed employee publications storage and MCP docs

This commit is contained in:
Anton
2026-05-15 17:39:41 +03:00
parent 2819a6c334
commit dbaf3af468
14 changed files with 677 additions and 26 deletions

View File

@@ -41,6 +41,7 @@ class Employee(Base):
snapshots: Mapped[list["EmployeeSnapshot"]] = relationship(back_populates="employee")
tabs: Mapped[list["ProfileTab"]] = relationship(back_populates="employee", cascade="all, delete-orphan")
publications: Mapped[list["EmployeePublication"]] = relationship(back_populates="employee", cascade="all, delete-orphan")
crawl_run_changes: Mapped[list["CrawlRunEmployeeChange"]] = relationship(back_populates="employee")
@@ -60,6 +61,42 @@ class EmployeeSnapshot(Base):
employee: Mapped[Employee] = relationship(back_populates="snapshots")
class EmployeePublication(Base):
__tablename__ = "employee_publications"
__table_args__ = (
UniqueConstraint("employee_id", "publication_id", name="uq_employee_publications_employee_publication"),
UniqueConstraint("employee_id", "source_hash", name="uq_employee_publications_employee_source_hash"),
Index("ix_employee_publications_employee_id", "employee_id"),
Index("ix_employee_publications_publication_id", "publication_id"),
Index("ix_employee_publications_doi_url", "doi_url"),
Index("ix_employee_publications_year", "year"),
Index("ix_employee_publications_publication_type", "publication_type"),
)
id: Mapped[int] = mapped_column(Integer, primary_key=True)
employee_id: Mapped[int] = mapped_column(ForeignKey("employees.id", ondelete="CASCADE"), nullable=False)
publication_id: Mapped[str | None] = mapped_column(String(64))
title: Mapped[str] = mapped_column(Text, nullable=False)
year: Mapped[int | None] = mapped_column(Integer)
publication_type: Mapped[str | None] = mapped_column(String(64))
language: Mapped[str | None] = mapped_column(String(16))
status: Mapped[int | None] = mapped_column(Integer)
url: Mapped[str | None] = mapped_column(Text)
doi_url: Mapped[str | None] = mapped_column(Text)
other_url: Mapped[str | None] = mapped_column(Text)
document_url: Mapped[str | None] = mapped_column(Text)
citation_text: Mapped[str | None] = mapped_column(Text)
annotation: Mapped[dict | None] = mapped_column(json_type)
description: Mapped[dict | None] = mapped_column(json_type)
authors: Mapped[list | None] = mapped_column(json_type)
raw_data: Mapped[dict | None] = mapped_column(json_type)
source_hash: Mapped[str] = mapped_column(String(64), nullable=False)
created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, nullable=False)
updated_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, onupdate=utcnow, nullable=False)
employee: Mapped[Employee] = relationship(back_populates="publications")
class CrawlRun(Base):
__tablename__ = "crawl_runs"