feat: add detailed employee publications storage and MCP docs

app/mcp.py

@@ -5,7 +5,7 @@ from sqlalchemy import desc, or_, select
 from sqlalchemy.orm import Session
 
 from app.db import get_db
-from app.models import CrawlRun, Employee
+from app.models import CrawlRun, Employee, EmployeePublication
 from app.services.admin_data import run_detail_payload
 from app.services.dataset_versions import service_info_payload, sync_employees_payload
 from app.version import BACKEND_VERSION
@@ -52,7 +52,10 @@ TOOLS = [
     },
     {
         "name": "list_employee_publications",
-        "description": "List publications parsed from an employee profile.",
+        "description": (
+            "List employee publications with detailed fields when available: authors, DOI URL, annotation, "
+            "description, citation text, year, publication type, language, status, and HSE Publications URL."
+        ),
         "inputSchema": {"type": "object", "properties": {"profile_id_or_url": {"type": "string"}}, "required": ["profile_id_or_url"]},
     },
     {
@@ -171,8 +174,14 @@ def _find_employee(db: Session, value: str) -> Employee | None:
 
 
 def _collect_section_items(employee: Employee | None, section_type: str) -> dict:
-    if not employee or not employee.current_data:
+    if not employee:
         return {"items": []}
+    if section_type == "publications":
+        publications = _stored_publications(employee)
+        if publications:
+            return {"employee": _employee_payload(employee, include_data=False), "items": publications}
+    if not employee.current_data:
+        return {"employee": _employee_payload(employee, include_data=False), "items": []}
     items = []
     for section in employee.current_data.get("sections") or []:
         if section.get("type") != section_type:
@@ -184,6 +193,41 @@ def _collect_section_items(employee: Employee | None, section_type: str) -> dict
     return {"employee": _employee_payload(employee, include_data=False), "items": items}
 
 
+def _stored_publications(employee: Employee) -> list[dict]:
+    return [_publication_payload(publication) for publication in sorted(employee.publications, key=_publication_sort_key)]
+
+
+def _publication_sort_key(publication: EmployeePublication) -> tuple:
+    return (publication.year or 0, publication.title or "", publication.id)
+
+
+def _publication_payload(publication: EmployeePublication) -> dict:
+    text = publication.citation_text or publication.title
+    payload = {
+        "id": publication.publication_id,
+        "publication_id": publication.publication_id,
+        "title": publication.title,
+        "text": text,
+        "url": publication.url,
+    }
+    optional = {
+        "year": publication.year,
+        "type": publication.publication_type,
+        "publication_type": publication.publication_type,
+        "language": publication.language,
+        "status": publication.status,
+        "doi_url": publication.doi_url,
+        "other_url": publication.other_url,
+        "document_url": publication.document_url,
+        "citation_text": publication.citation_text,
+        "annotation": publication.annotation,
+        "description": publication.description,
+        "authors": publication.authors,
+    }
+    payload.update({key: value for key, value in optional.items() if value not in (None, [], {})})
+    return payload
+
+
 def _employee_payload(employee: Employee, include_data: bool = True) -> dict:
     payload = {
         "profile_key": employee.profile_key,