fix: separate news from publications and add employee refresh

Reviewed-on: #21

.env.example

@@ -14,13 +14,5 @@ PARSER_USE_PLAYWRIGHT=false
 ADMIN_USERNAME=admin
 ADMIN_PASSWORD=change-me
 SESSION_SECRET=change-me-session-secret
-MCP_TOKEN=change-me-mcp-token
-MCP_AUTH_MODE=oauth
-MCP_RESOURCE_URL=http://localhost:8001/mcp
-MCP_OAUTH_ISSUER=
-MCP_OAUTH_AUDIENCE=
-MCP_OAUTH_JWKS_URL=
-MCP_OAUTH_REQUIRED_SCOPE=mcp:tools
-
 API_PORT=8000
 MCP_PORT=8001

README.md

@@ -6,7 +6,7 @@
 
 - `api`: FastAPI, REST API, HTML-админка, healthcheck.
 - `worker`: weekly scheduler, который запускает парсинг по `CRAWL_CRON`.
-- `mcp`: HTTP MCP endpoint с OAuth/OIDC access token для внешних агентов или legacy static token для локального режима.
+- `mcp`: открытый HTTP MCP endpoint для ИИ-агентов.
 - `postgres`: основная БД.
 
 Парсер использует фиксированный источник сотрудников, по умолчанию `https://miem.hse.ru/persons`. Для каждой карточки сохраняются ФИО, должности, год начала работы, контакты, идентификаторы, вкладки профиля, секции, публикации, курсы, ВКР, JSON-снапшот и сжатый HTML-снапшот. Ссылки обходятся только из меню профиля самого сотрудника (`person-menu`), например `#sci`, `#teaching`, `#main`.
@@ -27,13 +27,6 @@ cp .env.example .env
 - `CRAWL_LIMIT`: опциональный лимит профилей для тестового запуска.
 - `ADMIN_USERNAME`, `ADMIN_PASSWORD`: логин и пароль админки.
 - `SESSION_SECRET`: секрет подписи cookie.
-- `MCP_TOKEN`: статический bearer token для legacy/local режима `MCP_AUTH_MODE=token`.
-- `MCP_AUTH_MODE`: режим авторизации MCP: `oauth` для внешних агентов или `token` для локальной отладки.
-- `MCP_RESOURCE_URL`: публичный URL MCP endpoint, например `https://example.com/mcp`.
-- `MCP_OAUTH_ISSUER`: issuer внешнего OIDC-провайдера.
-- `MCP_OAUTH_AUDIENCE`: ожидаемый `aud` в OAuth access token.
-- `MCP_OAUTH_JWKS_URL`: JWKS endpoint; если не задан, используется `<issuer>/.well-known/jwks.json`.
-- `MCP_OAUTH_REQUIRED_SCOPE`: scope для доступа к MCP tools, по умолчанию `mcp:tools`.
 - `PARSER_USE_PLAYWRIGHT`: включение Playwright-рендера динамических вкладок.
 
 ## Локальный запуск
@@ -88,9 +81,7 @@ curl -X POST http://localhost:8000/api/crawl-runs --cookie "miem_admin_session=.
 
 ## MCP
 
-Endpoint: `POST /mcp`, авторизация `Authorization: Bearer <token>`.
-
-Для внешних ИИ-агентов используйте `MCP_AUTH_MODE=oauth`. В этом режиме статический `MCP_TOKEN` не принимается: клиент должен передать OAuth/OIDC access token с нужным scope.
+Endpoint: `POST /mcp`, без авторизации на уровне приложения.
 
 Поддерживаемые tools:
 
@@ -104,23 +95,11 @@ Endpoint: `POST /mcp`, авторизация `Authorization: Bearer <token>`.
 
 ```bash
 curl http://localhost:8001/mcp \
-  -H "Authorization: Bearer change-me-mcp-token" \
   -H "Content-Type: application/json" \
   -d '{"jsonrpc":"2.0","id":1,"method":"tools/list","params":{}}'
 ```
 
-Для production OAuth/OIDC настройте внешний authorization server и включите режим `oauth`:
-
-```env
-MCP_AUTH_MODE=oauth
-MCP_RESOURCE_URL=https://example.com/mcp
-MCP_OAUTH_ISSUER=https://auth.example.com
-MCP_OAUTH_AUDIENCE=miem-mcp
-MCP_OAUTH_JWKS_URL=https://auth.example.com/.well-known/jwks.json
-MCP_OAUTH_REQUIRED_SCOPE=mcp:tools
-```
-
-MCP server работает как OAuth protected resource: он не выдает токены, а проверяет JWT access token по JWKS, `issuer`, `audience`, сроку действия и scope. Metadata для MCP-клиентов доступна по `GET /.well-known/oauth-protected-resource`.
+Если MCP нужно ограничить, делайте это на сетевом уровне: localhost binding, VPN, firewall, reverse proxy или другой внешний контур доступа.
 
 ## Обслуживание
 
@@ -131,4 +110,4 @@ docker compose exec postgres pg_dump -U miem miem_workers > backup.sql
 docker compose down
 ```
 
-Версия сервиса: `0.4.0`. Админка всегда показывает версии backend и frontend в footer.
+Версия сервиса: `0.4.5`. Админка всегда показывает версии backend и frontend в footer.

app/admin.py

@@ -17,6 +17,7 @@ from app.services.admin_data import (
     stats_payload,
 )
 from app.services.crawl_control import get_running_run, run_crawl_if_idle
+from app.services.crawler import refresh_employee
 from app.version import BACKEND_VERSION, FRONTEND_VERSION
 
 router = APIRouter(prefix="/admin")
@@ -144,10 +145,31 @@ def employee_detail(
     return _render(
         request,
         "employee_detail.html",
-        {"employee": employee, "employee_view": employee_detail_payload(employee), "snapshots": snapshots},
+        {
+            "employee": employee,
+            "employee_view": employee_detail_payload(employee),
+            "snapshots": snapshots,
+            "refresh_status": request.query_params.get("refresh_status"),
+        },
     )
 
 
+@router.post("/employees/{employee_id}/refresh")
+def refresh_employee_detail(
+    employee_id: int,
+    request: Request,
+    db: Session = Depends(get_db),
+    settings: Settings = Depends(get_settings),
+):
+    require_admin(request, settings)
+    employee = db.get(Employee, employee_id)
+    if not employee:
+        return RedirectResponse("/admin/directory", status_code=303)
+    run = refresh_employee(db, employee, settings)
+    status = "success" if run.status == "completed" else "error"
+    return RedirectResponse(f"/admin/employees/{employee_id}?refresh_status={status}", status_code=303)
+
+
 @router.get("/runs", response_class=HTMLResponse)
 def runs(request: Request, db: Session = Depends(get_db), settings: Settings = Depends(get_settings)):
     require_admin(request, settings)

app/config.py

@@ -1,6 +1,4 @@
 from functools import lru_cache
-from typing import Literal
-
 from pydantic import Field, field_validator
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
@@ -19,13 +17,6 @@ class Settings(BaseSettings):
     admin_username: str = "admin"
     admin_password: str = "admin"
     session_secret: str = Field(default="dev-session-secret", min_length=8)
-    mcp_token: str = "dev-mcp-token"
-    mcp_auth_mode: Literal["token", "oauth"] = "oauth"
-    mcp_resource_url: str = "http://localhost:8001/mcp"
-    mcp_oauth_issuer: str = ""
-    mcp_oauth_audience: str = ""
-    mcp_oauth_jwks_url: str = ""
-    mcp_oauth_required_scope: str = "mcp:tools"
 
     @field_validator("crawl_limit", mode="before")
     @classmethod
@@ -34,15 +25,6 @@ class Settings(BaseSettings):
             return None
         return value
 
-    def oauth_jwks_url(self) -> str:
-        if self.mcp_oauth_jwks_url:
-            return self.mcp_oauth_jwks_url
-        issuer = self.mcp_oauth_issuer.rstrip("/")
-        if not issuer:
-            return ""
-        return f"{issuer}/.well-known/jwks.json"
-
-
 @lru_cache
 def get_settings() -> Settings:
     return Settings()

app/main.py

@@ -4,7 +4,6 @@ from fastapi.staticfiles import StaticFiles
 from app.admin import router as admin_router
 from app.api import router as api_router
 from app.db import init_db
-from app.mcp import metadata_router as mcp_metadata_router
 from app.mcp import router as mcp_router
 from app.version import BACKEND_VERSION
 
@@ -13,7 +12,6 @@ app.mount("/static", StaticFiles(directory="app/static"), name="static")
 app.include_router(api_router)
 app.include_router(admin_router)
 app.include_router(mcp_router)
-app.include_router(mcp_metadata_router)
 
 
 @app.on_event("startup")

app/mcp.py

@@ -4,15 +4,12 @@ from fastapi import APIRouter, Depends, Request
 from sqlalchemy import desc, or_, select
 from sqlalchemy.orm import Session
 
-from app.config import Settings, get_settings
 from app.db import get_db
 from app.models import CrawlRun, Employee
-from app.security import mcp_protected_resource_metadata, require_mcp_auth
 from app.services.admin_data import run_detail_payload
 from app.version import BACKEND_VERSION
 
 router = APIRouter(prefix="/mcp")
-metadata_router = APIRouter()
 
 
 TOOLS = [
@@ -65,9 +62,7 @@ TOOLS = [
 async def mcp_http(
     request: Request,
     db: Session = Depends(get_db),
-    settings: Settings = Depends(get_settings),
 ) -> dict:
-    require_mcp_auth(request, settings)
     payload = await request.json()
     method = payload.get("method")
     request_id = payload.get("id")
@@ -183,8 +178,3 @@ def _run_payload(run: CrawlRun) -> dict:
 
 def _tool_response(data: object) -> dict:
     return {"content": [{"type": "text", "text": json.dumps(data, ensure_ascii=False, default=str)}]}
-
-
-@metadata_router.get("/.well-known/oauth-protected-resource")
-def oauth_protected_resource(settings: Settings = Depends(get_settings)) -> dict:
-    return mcp_protected_resource_metadata(settings)

app/parser/profile.py

@@ -263,10 +263,10 @@ def _load_widget_publications(session: Session, soup: BeautifulSoup, headers: di
             return publications
 
         result = data.get("result") if isinstance(data, dict) else {}
-        items = result.get("items") if isinstance(result, dict) else []
-        if not isinstance(items, list) or not items:
+        items = _extract_publication_items(result)
+        if not items:
             break
-        publications.extend(_normalize_publication_item(item) for item in items if isinstance(item, dict))
+        publications.extend(_normalize_publication_item(item) for item in items)
 
         total = int(result.get("total") or 0)
         if not result.get("more") and len(publications) >= total:
@@ -275,6 +275,34 @@ def _load_widget_publications(session: Session, soup: BeautifulSoup, headers: di
     return _dedupe_publications(publications)
 
 
+def _extract_publication_items(result: object) -> list[dict]:
+    if not isinstance(result, dict):
+        return []
+    return _flatten_publication_items(result.get("items"))
+
+
+def _flatten_publication_items(value: object) -> list[dict]:
+    if isinstance(value, list):
+        return [item for item in value if _is_publication_item(item)]
+    if not isinstance(value, dict):
+        return []
+
+    nested_items = value.get("items")
+    if isinstance(nested_items, list):
+        return [item for item in nested_items if _is_publication_item(item)]
+    if isinstance(nested_items, dict):
+        return _flatten_publication_items(nested_items)
+
+    publications = []
+    for child in value.values():
+        publications.extend(_flatten_publication_items(child))
+    return publications
+
+
+def _is_publication_item(value: object) -> bool:
+    return isinstance(value, dict) and ("id" in value or "title" in value)
+
+
 def _load_widget_graduation_theses(
     session: Session,
     soup: BeautifulSoup,
@@ -359,7 +387,7 @@ def _infer_section_type(title: str, nodes: list) -> str:
     lowered = title.lower()
     if _has_table(nodes):
         return "table"
-    if "публикац" in lowered:
+    if _is_publications_title(lowered):
         return "publications"
     if "учебные курсы" in lowered:
         return "courses_by_year"
@@ -370,6 +398,10 @@ def _infer_section_type(title: str, nodes: list) -> str:
     return "generic"
 
 
+def _is_publications_title(lowered_title: str) -> bool:
+    return lowered_title.startswith("публикац")
+
+
 def _has_table(nodes: list) -> bool:
     return any(isinstance(node, Tag) and (node.name == "table" or node.find("table")) for node in nodes)
 

app/security.py

@@ -3,10 +3,7 @@ import hashlib
 import hmac
 import json
 import time
-from functools import lru_cache
 
-import jwt
-from jwt import PyJWKClient, PyJWTError
 from fastapi import HTTPException, Request, status
 
 from app.config import Settings
@@ -47,93 +44,3 @@ def require_admin(request: Request, settings: Settings) -> str:
     if not username:
         raise HTTPException(status_code=status.HTTP_303_SEE_OTHER, headers={"Location": "/admin/login"})
     return username
-
-
-def require_mcp_auth(request: Request, settings: Settings) -> None:
-    auth = request.headers.get("authorization", "")
-    if not auth.startswith("Bearer "):
-        raise _mcp_unauthorized(settings, "Missing bearer token")
-
-    token = auth.removeprefix("Bearer ").strip()
-    if _mcp_static_token_allowed(settings) and hmac.compare_digest(token, settings.mcp_token):
-        return
-    if _mcp_oauth_allowed(settings):
-        _validate_mcp_oauth_token(token, settings)
-        return
-    raise _mcp_unauthorized(settings, "Invalid MCP token")
-
-
-def require_mcp_token(request: Request, settings: Settings) -> None:
-    require_mcp_auth(request, settings)
-
-
-def mcp_protected_resource_metadata(settings: Settings) -> dict:
-    authorization_servers = [settings.mcp_oauth_issuer.rstrip("/")] if settings.mcp_oauth_issuer else []
-    return {
-        "resource": settings.mcp_resource_url,
-        "authorization_servers": authorization_servers,
-        "bearer_methods_supported": ["header"],
-        "scopes_supported": [settings.mcp_oauth_required_scope],
-        "resource_documentation": settings.mcp_resource_url,
-    }
-
-
-def _mcp_static_token_allowed(settings: Settings) -> bool:
-    return settings.mcp_auth_mode == "token"
-
-
-def _mcp_oauth_allowed(settings: Settings) -> bool:
-    return settings.mcp_auth_mode == "oauth"
-
-
-def _validate_mcp_oauth_token(token: str, settings: Settings) -> None:
-    if not settings.mcp_oauth_issuer or not settings.mcp_oauth_audience or not settings.oauth_jwks_url():
-        raise _mcp_unauthorized(settings, "MCP OAuth is not configured")
-    try:
-        signing_key = _get_mcp_oauth_signing_key(token, settings).key
-        claims = jwt.decode(
-            token,
-            signing_key,
-            algorithms=["RS256", "RS384", "RS512", "ES256", "ES384", "ES512"],
-            audience=settings.mcp_oauth_audience,
-            issuer=settings.mcp_oauth_issuer.rstrip("/"),
-        )
-    except PyJWTError as exc:
-        raise _mcp_unauthorized(settings, "Invalid OAuth access token") from exc
-    if not _claims_have_scope(claims, settings.mcp_oauth_required_scope):
-        raise HTTPException(status_code=status.HTTP_403_FORBIDDEN, detail="Missing required MCP OAuth scope")
-
-
-def _claims_have_scope(claims: dict, required_scope: str) -> bool:
-    scopes: set[str] = set()
-    scope = claims.get("scope")
-    if isinstance(scope, str):
-        scopes.update(scope.split())
-    scp = claims.get("scp")
-    if isinstance(scp, str):
-        scopes.update(scp.split())
-    elif isinstance(scp, list):
-        scopes.update(str(item) for item in scp)
-    return required_scope in scopes
-
-
-@lru_cache(maxsize=16)
-def _get_jwk_client(jwks_url: str) -> PyJWKClient:
-    return PyJWKClient(jwks_url)
-
-
-def _get_mcp_oauth_signing_key(token: str, settings: Settings):
-    return _get_jwk_client(settings.oauth_jwks_url()).get_signing_key_from_jwt(token)
-
-
-def _mcp_unauthorized(settings: Settings, detail: str) -> HTTPException:
-    headers = {}
-    if _mcp_oauth_allowed(settings):
-        headers["WWW-Authenticate"] = f'Bearer resource_metadata="{_mcp_metadata_url(settings)}"'
-    return HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail=detail, headers=headers)
-
-
-def _mcp_metadata_url(settings: Settings) -> str:
-    resource_url = settings.mcp_resource_url.rstrip("/")
-    base_url = resource_url[: -len("/mcp")] if resource_url.endswith("/mcp") else resource_url
-    return f"{base_url}/.well-known/oauth-protected-resource"

app/services/crawler.py

@@ -80,6 +80,48 @@ def run_crawl(db: Session, settings: Settings) -> CrawlRun:
     return run
 
 
+def refresh_employee(db: Session, employee: Employee, settings: Settings) -> CrawlRun:
+    run = CrawlRun(source_url=employee.canonical_url, status="running", found_count=1)
+    db.add(run)
+    db.commit()
+    db.refresh(run)
+
+    try:
+        with requests.Session() as session:
+            parsed = parse_person_profile(
+                session,
+                employee.canonical_url,
+                HEADERS,
+                settings.request_timeout,
+                settings.parser_use_playwright,
+            )
+        if not parsed:
+            raise ValueError("Профиль не удалось распарсить.")
+        if _parsed_profile_key(parsed) != employee.profile_key:
+            raise ValueError("Распарсенный профиль не совпадает с обновляемым сотрудником.")
+
+        _upsert_employee(db, run, parsed)
+        run.parsed_count = 1
+        run.status = "completed"
+    except Exception as exc:
+        run.status = "failed"
+        run.error_count = 1
+        run.message = str(exc)
+        db.add(
+            CrawlError(
+                crawl_run_id=run.id,
+                profile_url=employee.canonical_url,
+                error_type=type(exc).__name__,
+                message=str(exc),
+            )
+        )
+    finally:
+        run.finished_at = datetime.now(timezone.utc)
+        db.commit()
+        db.refresh(run)
+    return run
+
+
 def _ensure_source(db: Session, source_url: str) -> ParserSource:
     source = db.scalar(select(ParserSource).where(ParserSource.source_url == source_url))
     if source:
@@ -91,10 +133,14 @@ def _ensure_source(db: Session, source_url: str) -> ParserSource:
     return source
 
 
+def _parsed_profile_key(parsed: dict) -> str:
+    return f"{parsed.get('profile_type')}:{parsed.get('profile_id')}"
+
+
 def _upsert_employee(db: Session, run: CrawlRun, parsed: dict) -> Employee:
     html = parsed.pop("_html", None)
     checksum = _checksum(parsed)
-    key = f"{parsed.get('profile_type')}:{parsed.get('profile_id')}"
+    key = _parsed_profile_key(parsed)
     employee = db.scalar(select(Employee).where(Employee.profile_key == key))
     now = datetime.now(timezone.utc)
     if not employee:

app/static/admin.css

@@ -171,6 +171,10 @@
   background: transparent;
 }
 
+.button--compact {
+  padding: 8px 12px;
+}
+
 .code {
   overflow-x: auto;
   padding: 14px;
@@ -201,11 +205,34 @@
   gap: 10px;
 }
 
+.employee-card__actions {
+  display: grid;
+  justify-items: end;
+  gap: 10px;
+}
+
 .employee-card__title {
   margin: 0;
   font-size: 24px;
 }
 
+.employee-card__notice {
+  margin: 0;
+  padding: 12px 14px;
+  border-radius: 8px;
+  font-weight: 700;
+}
+
+.employee-card__notice--success {
+  color: #065f46;
+  background: #d1fae5;
+}
+
+.employee-card__notice--error {
+  color: #991b1b;
+  background: #fee2e2;
+}
+
 .employee-card__section {
   padding: 20px;
   background: #ffffff;

app/templates/dashboard.html

@@ -51,7 +51,7 @@
     <thead><tr><th class="table__head">ID</th><th class="table__head">Статус</th><th class="table__head">Обработано</th><th class="table__head">Ошибки</th><th class="table__head">Старт</th></tr></thead>
     <tbody>
       {% for run in runs %}
-      <tr class="table__row" data-row-href="/admin/runs/{{ run.id }}" role="link" tabindex="0"><td class="table__cell">{{ run.id }}</td><td class="table__cell">{{ run.status_display }}</td><td class="table__cell">{{ run.parsed_count }}</td><td class="table__cell">{{ run.error_count }}</td><td class="table__cell">{{ run.started_display }}</td></tr>
+      <tr class="table__row" onclick="window.location.href='/admin/runs/{{ run.id }}'" onkeydown="if (event.key === 'Enter' || event.key === ' ') { event.preventDefault(); window.location.href='/admin/runs/{{ run.id }}'; }" role="link" tabindex="0"><td class="table__cell">{{ run.id }}</td><td class="table__cell">{{ run.status_display }}</td><td class="table__cell">{{ run.parsed_count }}</td><td class="table__cell">{{ run.error_count }}</td><td class="table__cell">{{ run.started_display }}</td></tr>
       {% endfor %}
     </tbody>
   </table>

app/templates/employee_detail.html

@@ -7,8 +7,18 @@
       <h2 class="employee-card__title">{{ employee_view.full_name or employee.profile_key }}</h2>
       <span class="badge {% if employee_view.status == "dismissed" %}badge--dismissed{% endif %}">{{ employee_view.status_display }}</span>
     </div>
+    <div class="employee-card__actions">
+      <form method="post" action="/admin/employees/{{ employee.id }}/refresh">
+        <button class="button button--compact" type="submit">Обновить данные</button>
+      </form>
       <a class="admin__link" href="{{ employee_view.canonical_url }}">{{ employee_view.canonical_url }}</a>
     </div>
+  </div>
+  {% if refresh_status == "success" %}
+  <p class="employee-card__notice employee-card__notice--success">Данные сотрудника обновлены.</p>
+  {% elif refresh_status == "error" %}
+  <p class="employee-card__notice employee-card__notice--error">Не удалось обновить данные сотрудника.</p>
+  {% endif %}
 
   <section class="employee-card__section">
     <h3 class="employee-section__title">Основная информация</h3>

app/templates/runs.html

@@ -38,7 +38,7 @@
     <thead><tr><th class="table__head">ID</th><th class="table__head">Статус</th><th class="table__head">Найдено</th><th class="table__head">Обработано</th><th class="table__head">Новые</th><th class="table__head">Ошибки</th><th class="table__head">Уволены</th><th class="table__head">Старт</th></tr></thead>
     <tbody>
       {% for run in runs %}
-      <tr class="table__row" data-row-href="/admin/runs/{{ run.id }}" role="link" tabindex="0"><td class="table__cell">{{ run.id }}</td><td class="table__cell">{{ run.status_display }}</td><td class="table__cell">{{ run.found_count }}</td><td class="table__cell">{{ run.parsed_count }}</td><td class="table__cell">{{ run.new_count }}</td><td class="table__cell">{{ run.error_count }}</td><td class="table__cell">{{ run.dismissed_count }}</td><td class="table__cell">{{ run.started_display }}</td></tr>
+      <tr class="table__row" onclick="window.location.href='/admin/runs/{{ run.id }}'" onkeydown="if (event.key === 'Enter' || event.key === ' ') { event.preventDefault(); window.location.href='/admin/runs/{{ run.id }}'; }" role="link" tabindex="0"><td class="table__cell">{{ run.id }}</td><td class="table__cell">{{ run.status_display }}</td><td class="table__cell">{{ run.found_count }}</td><td class="table__cell">{{ run.parsed_count }}</td><td class="table__cell">{{ run.new_count }}</td><td class="table__cell">{{ run.error_count }}</td><td class="table__cell">{{ run.dismissed_count }}</td><td class="table__cell">{{ run.started_display }}</td></tr>
       {% endfor %}
     </tbody>
   </table>

app/version.py

@@ -1,3 +1,3 @@
-APP_VERSION = "0.4.3"
-FRONTEND_VERSION = "0.4.3"
-BACKEND_VERSION = "0.4.3"
+APP_VERSION = "0.4.7"
+FRONTEND_VERSION = "0.4.7"
+BACKEND_VERSION = "0.4.7"

docker-compose.yml

@@ -20,7 +20,7 @@ services:
     environment:
       DATABASE_URL: postgresql+psycopg://${POSTGRES_USER:-miem}:${POSTGRES_PASSWORD:-miem_password}@postgres:5432/${POSTGRES_DB:-miem_workers}
     ports:
-      - "127.0.0.1:8000:8000"
+      - "127.0.0.1:${API_PORT:-8000}:8000"
     depends_on:
       postgres:
         condition: service_healthy
@@ -42,33 +42,7 @@ services:
     environment:
       DATABASE_URL: postgresql+psycopg://${POSTGRES_USER:-miem}:${POSTGRES_PASSWORD:-miem_password}@postgres:5432/${POSTGRES_DB:-miem_workers}
     ports:
-      - "127.0.0.1:8001:8000"
-    depends_on:
-      postgres:
-        condition: service_healthy
-
-  keycloak:
-    image: quay.io/keycloak/keycloak:latest
-    container_name: keycloak
-    restart: unless-stopped
-    environment:
-      KC_DB: postgres
-      KC_DB_URL: jdbc:postgresql://postgres:5432/${KEYCLOAK_DB_NAME}
-      KC_DB_USERNAME: ${KEYCLOAK_DB_USER}
-      KC_DB_PASSWORD: ${KEYCLOAK_DB_PASSWORD}
-
-      KEYCLOAK_ADMIN: ${KEYCLOAK_ADMIN}
-      KEYCLOAK_ADMIN_PASSWORD: ${KEYCLOAK_ADMIN_PASSWORD}
-
-      KC_HTTP_ENABLED: true
-      KC_PROXY_HEADERS: xforwarded
-      KC_HOSTNAME: ${KEYCLOAK_HOSTNAME}
-
-      KC_HEALTH_ENABLED: true
-      KC_METRICS_ENABLED: true
-    command: start
-    ports:
-      - "127.0.0.1:8080:8080"
+      - "127.0.0.1:${MCP_PORT:-8001}:8000"
     depends_on:
       postgres:
         condition: service_healthy

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "miem-workers"
-version = "0.4.0"
+version = "0.4.7"
 description = "MIEM employees parser, admin API, and MCP server"
 requires-python = ">=3.11"
 dependencies = [
@@ -12,7 +12,6 @@ dependencies = [
   "lxml>=5.2.0",
   "psycopg[binary]>=3.2.0",
   "pydantic-settings>=2.4.0",
-  "PyJWT[crypto]>=2.9.0",
   "python-multipart>=0.0.9",
   "requests>=2.32.0",
   "sqlalchemy>=2.0.32",

requirements.txt

@@ -6,7 +6,6 @@ jinja2>=3.1.4
 lxml>=5.2.0
 psycopg[binary]>=3.2.0
 pydantic-settings>=2.4.0
-PyJWT[crypto]>=2.9.0
 python-multipart>=0.0.9
 requests>=2.32.0
 sqlalchemy>=2.0.32

tests/test_admin_templates.py

@@ -45,9 +45,11 @@ def test_dashboard_limits_latest_runs_to_five():
 def test_runs_template_links_to_run_detail():
     template = Path("app/templates/runs.html").read_text(encoding="utf-8")
 
-    assert 'data-row-href="/admin/runs/{{ run.id }}"' in template
+    assert 'onclick="window.location.href=\'/admin/runs/{{ run.id }}\'"' in template
+    assert "onkeydown=\"if (event.key === 'Enter' || event.key === ' ')" in template
     assert 'role="link"' in template
     assert 'tabindex="0"' in template
+    assert 'data-row-href="/admin/runs/{{ run.id }}"' not in template
     assert '<a class="admin__link" href="/admin/runs/{{ run.id }}">' not in template
 
 
@@ -75,9 +77,11 @@ def test_dashboard_metric_cards_link_to_admin_targets():
 def test_dashboard_latest_run_rows_link_to_run_detail():
     template = Path("app/templates/dashboard.html").read_text(encoding="utf-8")
 
-    assert 'data-row-href="/admin/runs/{{ run.id }}"' in template
+    assert 'onclick="window.location.href=\'/admin/runs/{{ run.id }}\'"' in template
+    assert "onkeydown=\"if (event.key === 'Enter' || event.key === ' ')" in template
     assert 'role="link"' in template
     assert 'tabindex="0"' in template
+    assert 'data-row-href="/admin/runs/{{ run.id }}"' not in template
     assert '<a class="admin__link" href="/admin/runs/{{ run.id }}">' not in template
 
 

tests/test_api_mcp.py

@@ -1,15 +1,11 @@
-import time
 from datetime import datetime, timezone
 from types import SimpleNamespace
 
-import jwt
 from fastapi.testclient import TestClient
-from cryptography.hazmat.primitives.asymmetric import rsa
-from sqlalchemy import create_engine
+from sqlalchemy import create_engine, select
 from sqlalchemy.orm import sessionmaker
 from sqlalchemy.pool import StaticPool
 
-import app.security as security
 from app.config import Settings, get_settings
 from app.db import Base, get_db
 from app.main import app
@@ -23,10 +19,10 @@ def test_health_returns_versions():
     response = client.get("/api/health")
 
     assert response.status_code == 200
-    assert response.json()["backend_version"] == "0.4.3"
+    assert response.json()["backend_version"] == "0.4.7"
 
 
-def test_mcp_requires_token_and_lists_tools():
+def test_mcp_lists_tools_without_auth_and_ignores_auth_header():
     engine = create_engine(
         "sqlite:///:memory:",
         connect_args={"check_same_thread": False},
@@ -43,22 +39,20 @@ def test_mcp_requires_token_and_lists_tools():
             session.close()
 
     app.dependency_overrides[get_db] = override_db
-    app.dependency_overrides[get_settings] = lambda: Settings(
-        mcp_auth_mode="token", mcp_token="secret", session_secret="session-secret"
-    )
     client = TestClient(app)
 
-    unauthorized = client.post("/mcp", json={"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}})
-    authorized = client.post(
+    without_auth = client.post("/mcp", json={"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}})
+    with_auth = client.post(
         "/mcp",
-        headers={"Authorization": "Bearer secret"},
+        headers={"Authorization": "Bearer anything"},
         json={"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}},
     )
 
-    assert unauthorized.status_code == 401
-    assert authorized.status_code == 200
-    assert authorized.json()["result"]["tools"][0]["name"] == "search_employees"
-    assert any(tool["name"] == "get_crawl_run_details" for tool in authorized.json()["result"]["tools"])
+    assert without_auth.status_code == 200
+    assert with_auth.status_code == 200
+    assert without_auth.json()["result"]["tools"][0]["name"] == "search_employees"
+    assert any(tool["name"] == "get_crawl_run_details" for tool in without_auth.json()["result"]["tools"])
+    assert with_auth.json()["result"]["tools"] == without_auth.json()["result"]["tools"]
 
     app.dependency_overrides.clear()
 
@@ -96,14 +90,10 @@ def test_mcp_search_employees_returns_matching_employee():
             db.close()
 
     app.dependency_overrides[get_db] = override_db
-    app.dependency_overrides[get_settings] = lambda: Settings(
-        mcp_auth_mode="token", mcp_token="secret", session_secret="session-secret"
-    )
     client = TestClient(app)
 
     response = client.post(
         "/mcp",
-        headers={"Authorization": "Bearer secret"},
         json={
             "jsonrpc": "2.0",
             "id": 1,
@@ -164,14 +154,10 @@ def test_mcp_get_crawl_run_details_returns_changes():
             db.close()
 
     app.dependency_overrides[get_db] = override_db
-    app.dependency_overrides[get_settings] = lambda: Settings(
-        mcp_auth_mode="token", mcp_token="secret", session_secret="session-secret"
-    )
     client = TestClient(app)
 
     response = client.post(
         "/mcp",
-        headers={"Authorization": "Bearer secret"},
         json={
             "jsonrpc": "2.0",
             "id": 1,
@@ -188,146 +174,12 @@ def test_mcp_get_crawl_run_details_returns_changes():
     app.dependency_overrides.clear()
 
 
-def test_mcp_oauth_rejects_static_token():
-    engine = create_engine(
-        "sqlite:///:memory:",
-        connect_args={"check_same_thread": False},
-        poolclass=StaticPool,
-    )
-    Base.metadata.create_all(engine)
-    Session = sessionmaker(bind=engine)
-
-    def override_db():
-        session = Session()
-        try:
-            yield session
-        finally:
-            session.close()
-
-    settings = Settings(
-        mcp_auth_mode="oauth",
-        mcp_token="secret",
-        session_secret="session-secret",
-        mcp_oauth_issuer="https://auth.example.com",
-        mcp_oauth_audience="miem-mcp",
-        mcp_oauth_jwks_url="https://auth.example.com/.well-known/jwks.json",
-    )
-    app.dependency_overrides[get_db] = override_db
-    app.dependency_overrides[get_settings] = lambda: settings
-    client = TestClient(app)
-
-    response = client.post(
-        "/mcp",
-        headers={"Authorization": "Bearer secret"},
-        json={"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}},
-    )
-
-    assert response.status_code == 401
-    assert response.headers["www-authenticate"] == (
-        'Bearer resource_metadata="http://localhost:8001/.well-known/oauth-protected-resource"'
-    )
-
-    app.dependency_overrides.clear()
-
-
-def test_mcp_oauth_missing_auth_returns_metadata_challenge():
-    settings = Settings(
-        mcp_auth_mode="oauth",
-        mcp_resource_url="https://api.example.com/mcp",
-        mcp_oauth_issuer="https://auth.example.com",
-        mcp_oauth_audience="miem-mcp",
-        mcp_oauth_jwks_url="https://auth.example.com/.well-known/jwks.json",
-    )
-    app.dependency_overrides[get_settings] = lambda: settings
-    client = TestClient(app)
-
-    response = client.post("/mcp", json={"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}})
-
-    assert response.status_code == 401
-    assert response.headers["www-authenticate"] == (
-        'Bearer resource_metadata="https://api.example.com/.well-known/oauth-protected-resource"'
-    )
-
-    app.dependency_overrides.clear()
-
-
-def test_mcp_accepts_valid_oauth_jwt(monkeypatch):
-    public_key, token = _oauth_key_and_token()
-    monkeypatch.setattr(security, "_get_mcp_oauth_signing_key", lambda _token, _settings: SimpleNamespace(key=public_key))
-    app.dependency_overrides[get_settings] = lambda: _oauth_settings()
-    client = TestClient(app)
-
-    response = client.post(
-        "/mcp",
-        headers={"Authorization": f"Bearer {token}"},
-        json={"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}},
-    )
-
-    assert response.status_code == 200
-    assert response.json()["result"]["tools"][0]["name"] == "search_employees"
-
-    app.dependency_overrides.clear()
-
-
-def test_mcp_rejects_invalid_oauth_jwts(monkeypatch):
-    public_key, expired_token = _oauth_key_and_token(exp=int(time.time()) - 60)
-    _, wrong_issuer_token = _oauth_key_and_token(issuer="https://other.example.com")
-    _, wrong_audience_token = _oauth_key_and_token(audience="other-audience")
-    _, bad_signature_token = _oauth_key_and_token(public_key=public_key)
-    monkeypatch.setattr(security, "_get_mcp_oauth_signing_key", lambda _token, _settings: SimpleNamespace(key=public_key))
-    app.dependency_overrides[get_settings] = lambda: _oauth_settings()
-    client = TestClient(app)
-
-    for token in [expired_token, wrong_issuer_token, wrong_audience_token, bad_signature_token]:
-        response = client.post(
-            "/mcp",
-            headers={"Authorization": f"Bearer {token}"},
-            json={"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}},
-        )
-
-        assert response.status_code == 401
-
-    app.dependency_overrides.clear()
-
-
-def test_mcp_rejects_oauth_jwt_without_required_scope(monkeypatch):
-    public_key, token = _oauth_key_and_token(scope="profile")
-    monkeypatch.setattr(security, "_get_mcp_oauth_signing_key", lambda _token, _settings: SimpleNamespace(key=public_key))
-    app.dependency_overrides[get_settings] = lambda: _oauth_settings()
-    client = TestClient(app)
-
-    response = client.post(
-        "/mcp",
-        headers={"Authorization": f"Bearer {token}"},
-        json={"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}},
-    )
-
-    assert response.status_code == 403
-
-    app.dependency_overrides.clear()
-
-
-def test_mcp_protected_resource_metadata_uses_settings():
-    settings = Settings(
-        mcp_resource_url="https://api.example.com/mcp",
-        mcp_oauth_issuer="https://auth.example.com/",
-        mcp_oauth_required_scope="mcp:tools",
-    )
-    app.dependency_overrides[get_settings] = lambda: settings
+def test_mcp_protected_resource_metadata_route_is_removed():
     client = TestClient(app)
 
     response = client.get("/.well-known/oauth-protected-resource")
 
-    assert response.status_code == 200
-    assert response.json() == {
-        "resource": "https://api.example.com/mcp",
-        "authorization_servers": ["https://auth.example.com"],
-        "bearer_methods_supported": ["header"],
-        "scopes_supported": ["mcp:tools"],
-        "resource_documentation": "https://api.example.com/mcp",
-    }
-
-    app.dependency_overrides.clear()
+    assert response.status_code == 404
 
 
 def test_api_employees_and_stats_require_admin_session():
@@ -399,33 +251,54 @@ def test_api_employees_and_stats_require_admin_session():
     app.dependency_overrides.clear()
 
 
-def _oauth_settings() -> Settings:
-    return Settings(
-        mcp_auth_mode="oauth",
-        mcp_resource_url="https://api.example.com/mcp",
-        mcp_oauth_issuer="https://auth.example.com",
-        mcp_oauth_audience="miem-mcp",
-        mcp_oauth_jwks_url="https://auth.example.com/.well-known/jwks.json",
-        session_secret="session-secret",
+def test_admin_refresh_employee_route_updates_only_requested_employee(monkeypatch):
+    engine = create_engine(
+        "sqlite:///:memory:",
+        connect_args={"check_same_thread": False},
+        poolclass=StaticPool,
     )
+    Base.metadata.create_all(engine)
+    Session = sessionmaker(bind=engine)
+    db = Session()
+    db.add(
+        Employee(
+            profile_key="org_person:133709486",
+            profile_type="org_person",
+            profile_id="133709486",
+            canonical_url="https://www.hse.ru/org/persons/133709486",
+            full_name="Будков Юрий Алексеевич",
+            status="active",
+        )
+    )
+    db.commit()
+    employee_id = db.scalar(select(Employee.id))
+    db.close()
 
+    settings = Settings(admin_username="admin", admin_password="password", session_secret="session-secret")
 
-def _oauth_key_and_token(
-    *,
-    issuer: str = "https://auth.example.com",
-    audience: str = "miem-mcp",
-    scope: str = "mcp:tools",
-    exp: int | None = None,
-    public_key=None,
-):
-    private_key = rsa.generate_private_key(public_exponent=65537, key_size=2048)
-    claims = {
-        "iss": issuer,
-        "aud": audience,
-        "scope": scope,
-        "sub": "mcp-client",
-        "iat": int(time.time()),
-        "exp": exp or int(time.time()) + 300,
-    }
-    token = jwt.encode(claims, private_key, algorithm="RS256", headers={"kid": "test-key"})
-    return public_key or private_key.public_key(), token
+    def override_db():
+        session = Session()
+        try:
+            yield session
+        finally:
+            session.close()
+
+    calls = []
+
+    def fake_refresh_employee(db, refreshed_employee, route_settings):
+        calls.append((refreshed_employee.id, route_settings))
+        return SimpleNamespace(status="completed")
+
+    app.dependency_overrides[get_db] = override_db
+    app.dependency_overrides[get_settings] = lambda: settings
+    monkeypatch.setattr("app.admin.refresh_employee", fake_refresh_employee)
+    client = TestClient(app)
+    client.cookies.set(SESSION_COOKIE, sign_session("admin", settings))
+
+    response = client.post(f"/admin/employees/{employee_id}/refresh", follow_redirects=False)
+
+    assert response.status_code == 303
+    assert response.headers["location"] == f"/admin/employees/{employee_id}?refresh_status=success"
+    assert calls == [(employee_id, settings)]
+
+    app.dependency_overrides.clear()

tests/test_config.py

@@ -1,6 +1,3 @@
-import pytest
-from pydantic import ValidationError
-
 from app.config import Settings
 
 
@@ -14,8 +11,3 @@ def test_numeric_crawl_limit_is_parsed():
     settings = Settings(crawl_limit="25")
 
     assert settings.crawl_limit == 25
-
-
-def test_mcp_auth_mode_rejects_oauth_or_token_fallback():
-    with pytest.raises(ValidationError):
-        Settings(mcp_auth_mode="oauth_or_token")

tests/test_employee_detail_template.py

@@ -27,4 +27,6 @@ def test_employee_detail_template_is_human_readable():
     assert "Дата увольнения" in template
     assert "Тип профиля" in template
     assert "ID профиля" in template
+    assert "Обновить данные" in template
+    assert 'action="/admin/employees/{{ employee.id }}/refresh"' in template
     assert "Снапшоты" in template

tests/test_parser.py

@@ -1,6 +1,6 @@
 from bs4 import BeautifulSoup
 
-from app.parser.profile import enrich_sections_from_hse_widgets, extract_person_tabs
+from app.parser.profile import enrich_sections_from_hse_widgets, extract_person_tabs, extract_sections
 from app.parser.profile_url import normalize_profile_url, parse_profile_identity
 
 
@@ -64,6 +64,47 @@ class FakeSession:
         )
 
 
+class GroupedPublicationsSession(FakeSession):
+    def post(self, url, **kwargs):
+        self.posts.append((url, kwargs))
+        return FakeResponse(
+            {
+                "status": "ok",
+                "result": {
+                    "more": False,
+                    "total": 1,
+                    "groupType": 2,
+                    "items": {
+                        "year": {
+                            "header": {"ru": "по году", "en": "by year"},
+                            "criteria": {"year": []},
+                            "items": {
+                                "2011": [
+                                    {
+                                        "id": "146366790",
+                                        "type": "ARTICLE",
+                                        "title": "Развитие теории самосогласованного поля",
+                                        "year": 2011,
+                                        "description": {"short": {"ru": "Журнал физической химии 2011."}},
+                                    }
+                                ],
+                                "2012": [
+                                    {
+                                        "id": "146367323",
+                                        "type": "ARTICLE",
+                                        "title": "Self-consistent field theory investigation",
+                                        "year": 2012,
+                                        "description": {"short": {"en": "Russian Journal of Physical Chemistry A 2012."}},
+                                    }
+                                ],
+                            },
+                        }
+                    },
+                },
+            }
+        )
+
+
 def test_normalize_profile_url_supports_staff_and_org_persons():
     assert normalize_profile_url("/staff/avsergeev#sci") == "https://www.hse.ru/staff/avsergeev"
     assert normalize_profile_url("https://www.hse.ru/org/persons/123/") == "https://www.hse.ru/org/persons/123"
@@ -117,3 +158,60 @@ def test_enrich_sections_from_hse_widgets_loads_publications_and_vkr():
     assert theses["theses"][0]["project_url"] == "https://www.hse.ru/edu/vkr/1045750164"
     assert session.posts[0][0] == "https://publications.hse.ru/api/searchPubs"
     assert session.gets[0][1]["params"] == {"supervisorId": "803294906"}
+
+
+def test_enrich_sections_from_hse_widgets_loads_grouped_publications():
+    soup = BeautifulSoup(
+        """
+        <script src="/n/stat/publications/dist-w/publs.js" data-author="133709486" data-widget-name="AuthorSearch"></script>
+        """,
+        "html.parser",
+    )
+    session = GroupedPublicationsSession()
+
+    sections = enrich_sections_from_hse_widgets(
+        session,
+        soup,
+        "https://www.hse.ru/org/persons/133709486",
+        {"User-Agent": "test"},
+        10,
+        [],
+    )
+
+    publications = next(section for section in sections if section["type"] == "publications")
+
+    assert publications["publications_count"] == 2
+    assert [item["id"] for item in publications["publications"]] == ["146366790", "146367323"]
+    assert publications["publications"][0]["url"] == "https://publications.hse.ru/view/146366790"
+    assert publications["publications"][1]["url"] == "https://publications.hse.ru/view/146367323"
+
+
+def test_news_heading_with_publications_word_does_not_absorb_widget_publications():
+    soup = BeautifulSoup(
+        """
+        <h2>Статья профессора МИЭМ вошла в число самых популярных публикаций на портале SpringerLink</h2>
+        <div class="post__text">
+          <p>Первоначально статья профессора вышла в российском журнале.</p>
+        </div>
+        <script src="/n/stat/publications/dist-w/publs.js" data-author="133709486" data-widget-name="AuthorSearch"></script>
+        """,
+        "html.parser",
+    )
+    session = FakeSession()
+
+    sections = extract_sections(soup, "https://www.hse.ru/org/persons/133709486")
+    sections = enrich_sections_from_hse_widgets(
+        session,
+        soup,
+        "https://www.hse.ru/org/persons/133709486",
+        {"User-Agent": "test"},
+        10,
+        sections,
+    )
+
+    assert sections[0]["type"] == "paragraphs"
+    assert sections[0]["title"].startswith("Статья профессора")
+    publications = [section for section in sections if section["type"] == "publications"]
+    assert len(publications) == 1
+    assert publications[0]["title"] == "Публикации и исследования"
+    assert publications[0]["publications_count"] == 1