Merge pull request 'fix: separate news from publications and add employee refresh' (#22) from fix/publications-news-refresh into main

Reviewed-on: #22

.env.example

@@ -14,7 +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
-
 API_PORT=8000
 MCP_PORT=8001

.gitignore

@@ -4,6 +4,7 @@ __pycache__/
 *.py[cod]
 *.db
 .pytest_cache/
+pytest-cache-files-*/
 .coverage
 htmlcov/
 postgres_data/

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 bearer token.
+- `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`.
@@ -27,7 +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`: bearer token для `/mcp`.
 - `PARSER_USE_PLAYWRIGHT`: включение Playwright-рендера динамических вкладок.
 
 ## Локальный запуск
@@ -82,7 +81,7 @@ curl -X POST http://localhost:8000/api/crawl-runs --cookie "miem_admin_session=.
 
 ## MCP
 
-Endpoint: `POST /mcp`, авторизация `Authorization: Bearer <MCP_TOKEN>`.
+Endpoint: `POST /mcp`, без авторизации на уровне приложения.
 
 Поддерживаемые tools:
 
@@ -92,15 +91,16 @@ Endpoint: `POST /mcp`, авторизация `Authorization: Bearer <MCP_TOKEN>
 - `list_employee_courses(profile_id_or_url)`
 - `get_crawl_status()`
 
-Пример:
+Пример локального legacy-режима со статическим токеном:
 
 ```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":{}}'
 ```
 
+Если MCP нужно ограничить, делайте это на сетевом уровне: localhost binding, VPN, firewall, reverse proxy или другой внешний контур доступа.
+
 ## Обслуживание
 
 ```bash
@@ -110,4 +110,4 @@ docker compose exec postgres pg_dump -U miem miem_workers > backup.sql
 docker compose down
 ```
 
-Версия сервиса: `0.2.6`. 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

@@ -8,8 +8,16 @@ from app.config import Settings, get_settings
 from app.db import SessionLocal, get_db
 from app.models import CrawlError, CrawlRun, Employee
 from app.security import SESSION_COOKIE, require_admin, sign_session, verify_admin
-from app.services.admin_data import employee_detail_payload, format_admin_datetime, list_employees_page, run_payload, stats_payload
+from app.services.admin_data import (
+    employee_detail_payload,
+    format_admin_datetime,
+    list_employees_page,
+    run_detail_payload,
+    run_payload,
+    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")
@@ -22,7 +30,7 @@ def dashboard(request: Request, db: Session = Depends(get_db), settings: Setting
     counts = stats_payload(db)
     counts["runs"] = db.scalar(select(func.count()).select_from(CrawlRun)) or 0
     counts["errors"] = db.scalar(select(func.count()).select_from(CrawlError)) or 0
-    run_models = db.scalars(select(CrawlRun).order_by(desc(CrawlRun.started_at)).limit(10)).all()
+    run_models = db.scalars(select(CrawlRun).order_by(desc(CrawlRun.started_at)).limit(5)).all()
     runs = [run_payload(run) for run in run_models]
     return _render(request, "dashboard.html", {"counts": counts, "runs": runs, "latest_run": runs[0] if runs else None})
 
@@ -108,7 +116,7 @@ def directory(
                 "has_email": has_email or "",
                 "sort": sort,
                 "direction": direction,
-                "limit": limit,
+                "limit": page["limit"],
                 "offset": offset,
             },
         },
@@ -137,10 +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)
@@ -150,6 +179,20 @@ def runs(request: Request, db: Session = Depends(get_db), settings: Settings = D
     return _render(request, "runs.html", {"runs": items, "errors": errors})
 
 
+@router.get("/runs/{run_id}", response_class=HTMLResponse)
+def run_detail(
+    run_id: int,
+    request: Request,
+    db: Session = Depends(get_db),
+    settings: Settings = Depends(get_settings),
+):
+    require_admin(request, settings)
+    run = db.get(CrawlRun, run_id)
+    if not run:
+        return RedirectResponse("/admin/runs", status_code=303)
+    return _render(request, "run_detail.html", {"run": run_detail_payload(db, run)})
+
+
 @router.post("/runs")
 def trigger_run(
     request: Request,

app/api.py

@@ -8,7 +8,7 @@ from app.config import Settings, get_settings
 from app.db import SessionLocal, get_db
 from app.models import CrawlRun, Employee
 from app.security import require_admin
-from app.services.admin_data import employee_display_payload, list_employees_page, run_payload, stats_payload
+from app.services.admin_data import employee_display_payload, list_employees_page, run_detail_payload, run_payload, stats_payload
 from app.services.crawl_control import get_running_run, run_crawl_if_idle
 from app.version import BACKEND_VERSION, FRONTEND_VERSION
 
@@ -88,6 +88,20 @@ def latest_crawl_run(
     return {"running": run_payload(running), "latest": run_payload(latest)}
 
 
+@router.get("/crawl-runs/{run_id}")
+def get_crawl_run(
+    run_id: int,
+    request: Request,
+    db: Session = Depends(get_db),
+    settings: Settings = Depends(get_settings),
+) -> dict:
+    require_admin(request, settings)
+    run = db.get(CrawlRun, run_id)
+    if not run:
+        return {"error": "not_found"}
+    return run_detail_payload(db, run) or {"error": "not_found"}
+
+
 @router.post("/crawl-runs")
 def trigger_crawl(
     request: Request,

app/config.py

@@ -1,5 +1,5 @@
 from functools import lru_cache
-from pydantic import Field
+from pydantic import Field, field_validator
 from pydantic_settings import BaseSettings, SettingsConfigDict
 
 
@@ -17,8 +17,13 @@ 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"
 
+    @field_validator("crawl_limit", mode="before")
+    @classmethod
+    def empty_crawl_limit_as_none(cls, value):
+        if value == "":
+            return None
+        return value
 
 @lru_cache
 def get_settings() -> Settings:

app/mcp.py

@@ -4,10 +4,10 @@ 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 require_mcp_token
+from app.services.admin_data import run_detail_payload
+from app.version import BACKEND_VERSION
 
 router = APIRouter(prefix="/mcp")
 
@@ -46,6 +46,15 @@ TOOLS = [
         "description": "Return the latest crawl run status.",
         "inputSchema": {"type": "object", "properties": {}},
     },
+    {
+        "name": "get_crawl_run_details",
+        "description": "Return detailed employee changes and errors for one crawl run.",
+        "inputSchema": {
+            "type": "object",
+            "properties": {"run_id": {"type": "integer"}},
+            "required": ["run_id"],
+        },
+    },
 ]
 
 
@@ -53,9 +62,7 @@ TOOLS = [
 async def mcp_http(
     request: Request,
     db: Session = Depends(get_db),
-    settings: Settings = Depends(get_settings),
 ) -> dict:
-    require_mcp_token(request, settings)
     payload = await request.json()
     method = payload.get("method")
     request_id = payload.get("id")
@@ -65,7 +72,7 @@ async def mcp_http(
         if method == "initialize":
             result = {
                 "protocolVersion": "2024-11-05",
-                "serverInfo": {"name": "miem-employees", "version": "0.1.0"},
+                "serverInfo": {"name": "miem-employees", "version": BACKEND_VERSION},
                 "capabilities": {"tools": {}},
             }
         elif method == "tools/list":
@@ -94,6 +101,9 @@ def _call_tool(db: Session, name: str, arguments: dict) -> dict:
     if name == "get_crawl_status":
         run = db.scalar(select(CrawlRun).order_by(desc(CrawlRun.started_at)).limit(1))
         return _tool_response(_run_payload(run) if run else {"status": "never_run"})
+    if name == "get_crawl_run_details":
+        run = db.get(CrawlRun, int(arguments["run_id"]))
+        return _tool_response(run_detail_payload(db, run) if run else {"error": "not_found"})
     raise ValueError(f"Unknown tool: {name}")
 
 

app/models.py

@@ -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")
+    crawl_run_changes: Mapped[list["CrawlRunEmployeeChange"]] = relationship(back_populates="employee")
 
 
 class EmployeeSnapshot(Base):
@@ -74,6 +75,31 @@ class CrawlRun(Base):
     dismissed_count: Mapped[int] = mapped_column(Integer, default=0, nullable=False)
     message: Mapped[str | None] = mapped_column(Text)
 
+    employee_changes: Mapped[list["CrawlRunEmployeeChange"]] = relationship(back_populates="crawl_run")
+
+
+class CrawlRunEmployeeChange(Base):
+    __tablename__ = "crawl_run_employee_changes"
+    __table_args__ = (
+        Index("ix_crawl_run_employee_changes_run_id", "crawl_run_id"),
+        Index("ix_crawl_run_employee_changes_employee_id", "employee_id"),
+        Index("ix_crawl_run_employee_changes_change_type", "change_type"),
+    )
+
+    id: Mapped[int] = mapped_column(Integer, primary_key=True)
+    crawl_run_id: Mapped[int] = mapped_column(ForeignKey("crawl_runs.id"), nullable=False)
+    employee_id: Mapped[int | None] = mapped_column(ForeignKey("employees.id"))
+    profile_key: Mapped[str] = mapped_column(String(255), nullable=False)
+    profile_url: Mapped[str] = mapped_column(Text, nullable=False)
+    full_name: Mapped[str | None] = mapped_column(Text)
+    change_type: Mapped[str] = mapped_column(String(32), nullable=False)
+    profile_available: Mapped[bool | None] = mapped_column()
+    message: Mapped[str | None] = mapped_column(Text)
+    created_at: Mapped[datetime] = mapped_column(DateTime(timezone=True), default=utcnow, nullable=False)
+
+    crawl_run: Mapped[CrawlRun] = relationship(back_populates="employee_changes")
+    employee: Mapped[Employee | None] = relationship(back_populates="crawl_run_changes")
+
 
 class CrawlError(Base):
     __tablename__ = "crawl_errors"

app/parser/profile.py

@@ -164,6 +164,7 @@ def parse_person_profile(
     header = extract_person_header(soup, normalized_url)
     tabs = extract_person_tabs(soup, normalized_url)
     sections = extract_sections(soup, normalized_url)
+    sections = enrich_sections_from_hse_widgets(session, soup, normalized_url, headers, timeout, sections)
     internal_links = [tab["href"] for tab in tabs if tab.get("href")]
 
     return {
@@ -183,6 +184,25 @@ def parse_person_profile(
     }
 
 
+def enrich_sections_from_hse_widgets(
+    session: Session,
+    soup: BeautifulSoup,
+    source_url: str,
+    headers: dict[str, str],
+    timeout: int,
+    sections: list[dict],
+) -> list[dict]:
+    enriched = list(sections)
+    publications = _load_widget_publications(session, soup, headers, timeout)
+    if publications:
+        enriched = _upsert_publications_section(enriched, publications)
+
+    theses = _load_widget_graduation_theses(session, soup, source_url, headers, timeout)
+    if theses:
+        enriched = _upsert_graduation_theses_section(enriched, theses)
+    return enriched
+
+
 def _render_with_playwright(source_url: str, fallback_html: str) -> str:
     try:
         from playwright.sync_api import sync_playwright
@@ -206,6 +226,117 @@ def _render_with_playwright(source_url: str, fallback_html: str) -> str:
         return fallback_html
 
 
+def _load_widget_publications(session: Session, soup: BeautifulSoup, headers: dict[str, str], timeout: int) -> list[dict]:
+    script = soup.select_one('script[data-widget-name="AuthorSearch"][data-author]')
+    if not script:
+        return []
+    author_id = normalize_ws(script.get("data-author"))
+    if not author_id:
+        return []
+
+    publications = []
+    page_id = 1
+    per_page = 100
+    while page_id <= 20:
+        payload = {
+            "type": "ANY",
+            "filterParams": (
+                f'"acceptLanguage":"ru"|"fullTextPublicEnabled": 1|'
+                f'"pubsAuthor": {author_id}|"widgetName": "AuthorSearch"'
+            ),
+            "paginationParams": {
+                "publsSort": ["TITLE_ASC"],
+                "publsCount": per_page,
+                "pageId": page_id,
+            },
+        }
+        try:
+            response = session.post(
+                "https://publications.hse.ru/api/searchPubs",
+                json=payload,
+                headers=headers,
+                timeout=timeout,
+            )
+            response.raise_for_status()
+            data = response.json()
+        except Exception:
+            return publications
+
+        result = data.get("result") if isinstance(data, dict) else {}
+        items = _extract_publication_items(result)
+        if not items:
+            break
+        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:
+            break
+        page_id += 1
+    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,
+    source_url: str,
+    headers: dict[str, str],
+    timeout: int,
+) -> list[dict]:
+    script = soup.select_one('script[src*="/n/stat/vkr/app.js"][data-person-id]')
+    if not script:
+        return []
+    person_id = normalize_ws(script.get("data-person-id"))
+    api_url = normalize_ws(script.get("data-api-url")) or "/n/vkr/api/"
+    if not person_id:
+        return []
+
+    request_headers = {**headers, "x-portal-language": "ru"}
+    try:
+        response = session.get(
+            urljoin(source_url, api_url),
+            params={"supervisorId": person_id},
+            headers=request_headers,
+            timeout=timeout,
+        )
+        response.raise_for_status()
+        data = response.json()
+    except Exception:
+        return []
+
+    items = data.get("data") if isinstance(data, dict) else []
+    if not isinstance(items, list):
+        return []
+    return [_normalize_vkr_item(item, source_url) for item in items if isinstance(item, dict)]
+
+
 def _collect_between_h2(start_h2: Tag) -> list[Tag | NavigableString | str]:
     nodes = []
     for sibling in start_h2.next_siblings:
@@ -256,7 +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"
@@ -267,6 +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)
 
@@ -353,6 +488,122 @@ def _parse_vkr_items(nodes: list) -> list[str]:
     return [item for item in dict.fromkeys(items) if item]
 
 
+def _normalize_publication_item(item: dict) -> dict:
+    publication_id = str(item.get("id") or "").strip()
+    title = _html_to_text(item.get("title"))
+    year = item.get("year")
+    publication_type = str(item.get("type") or "").strip() or None
+    description = item.get("description") if isinstance(item.get("description"), dict) else {}
+    short_description = _localized_value(description.get("short")) or _localized_value(description.get("shortLeft"))
+    text = normalize_ws(" ".join(part for part in [title, str(year or ""), short_description] if part))
+    return {
+        "id": publication_id or None,
+        "title": title or publication_id,
+        "year": year,
+        "type": publication_type,
+        "url": f"https://publications.hse.ru/view/{publication_id}" if publication_id else None,
+        "text": text or title or publication_id,
+    }
+
+
+def _normalize_vkr_item(item: dict, source_url: str) -> dict:
+    thesis_id = item.get("id")
+    program = item.get("learnProgram") if isinstance(item.get("learnProgram"), dict) else {}
+    org_unit = item.get("orgUnit") if isinstance(item.get("orgUnit"), dict) else {}
+    supervisors = []
+    for supervisor in item.get("supervisors") or []:
+        if not isinstance(supervisor, dict):
+            continue
+        name = normalize_ws(supervisor.get("name"))
+        url = normalize_ws(supervisor.get("url"))
+        if name or url:
+            supervisors.append({"name": name or url, "url": url or None})
+    return {
+        "id": thesis_id,
+        "student": normalize_ws(item.get("student")),
+        "title": normalize_ws(item.get("title")),
+        "defense_year": item.get("year"),
+        "level": normalize_ws(item.get("level")),
+        "rating": item.get("rating"),
+        "project_url": urljoin(source_url, f"/edu/vkr/{thesis_id}") if thesis_id else None,
+        "program": normalize_ws(program.get("title")),
+        "program_url": urljoin(source_url, program.get("url")) if program.get("url") else None,
+        "org_unit": normalize_ws(org_unit.get("title")),
+        "org_unit_url": urljoin(source_url, org_unit.get("url")) if org_unit.get("url") else None,
+        "supervisors": supervisors,
+        "text": normalize_ws(" ".join(str(part) for part in [item.get("student"), item.get("title"), item.get("year")] if part)),
+    }
+
+
+def _upsert_publications_section(sections: list[dict], publications: list[dict]) -> list[dict]:
+    merged = []
+    inserted = False
+    for section in sections:
+        if section.get("type") != "publications":
+            merged.append(section)
+            continue
+        existing = section.get("publications") or []
+        section = {
+            **section,
+            "publications_count": max(section.get("publications_count") or 0, len(publications)),
+            "publications": _dedupe_publications([*existing, *publications]),
+        }
+        section["items"] = [item["text"] for item in section["publications"] if item.get("text")]
+        merged.append(section)
+        inserted = True
+    if not inserted:
+        merged.append(
+            {
+                "title": "Публикации и исследования",
+                "slug": "publikacii_i_issledovaniya",
+                "type": "publications",
+                "raw_text": "",
+                "paragraphs": [],
+                "items": [item["text"] for item in publications if item.get("text")],
+                "links": [],
+                "publications_count": len(publications),
+                "publications": publications,
+            }
+        )
+    return merged
+
+
+def _upsert_graduation_theses_section(sections: list[dict], theses: list[dict]) -> list[dict]:
+    section = {
+        "title": "Выпускные квалификационные работы студентов НИУ ВШЭ",
+        "slug": "vypusknye_kvalifikacionnye_raboty_studentov_niu_vshe",
+        "type": "graduation_theses",
+        "raw_text": "",
+        "paragraphs": [],
+        "items": [item["text"] for item in theses if item.get("text")],
+        "links": [{"text": item["title"], "url": item["project_url"]} for item in theses if item.get("title") and item.get("project_url")],
+        "theses_count": len(theses),
+        "theses": theses,
+    }
+    return [item for item in sections if item.get("type") != "graduation_theses"] + [section]
+
+
+def _dedupe_publications(items: list[dict]) -> list[dict]:
+    seen = set()
+    unique = []
+    for item in items:
+        key = item.get("id") or item.get("url") or item.get("title")
+        if key and key not in seen:
+            seen.add(key)
+            unique.append(item)
+    return unique
+
+
+def _html_to_text(value: object) -> str:
+    return normalize_ws(BeautifulSoup(str(value or ""), "html.parser").get_text(" ", strip=True))
+
+
+def _localized_value(value: object) -> str:
+    if isinstance(value, dict):
+        return normalize_ws(value.get("ru") or value.get("publ") or value.get("en"))
+    return normalize_ws(str(value or ""))
+
+
 def _slugify(value: str) -> str:
     cleaned = re.sub(r"[^\w\s-]", "", value.lower(), flags=re.UNICODE)
     return re.sub(r"[-\s]+", "_", cleaned).strip("_") or "section"

app/security.py

@@ -44,9 +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_token(request: Request, settings: Settings) -> None:
-    auth = request.headers.get("authorization", "")
-    if not auth.startswith("Bearer ") or not hmac.compare_digest(auth.removeprefix("Bearer ").strip(), settings.mcp_token):
-        raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="Invalid MCP token")

app/services/admin_data.py

@@ -8,7 +8,7 @@ from zoneinfo import ZoneInfo
 from sqlalchemy import Select, Text, and_, desc, func, or_, select
 from sqlalchemy.orm import Session
 
-from app.models import CrawlRun, Employee
+from app.models import CrawlError, CrawlRun, CrawlRunEmployeeChange, Employee
 
 EMPLOYEE_SORTS = {
     "full_name": Employee.full_name,
@@ -112,7 +112,7 @@ def list_employees_page(
     limit: int = 50,
     offset: int = 0,
 ) -> dict[str, Any]:
-    limit = max(1, min(limit, 200))
+    limit = limit if limit in {25, 50, 100} else 50
     offset = max(0, offset)
     base_stmt = build_employee_query(
         status=status,
@@ -175,6 +175,26 @@ def run_payload(run: CrawlRun | None) -> dict[str, Any] | None:
     }
 
 
+def run_detail_payload(db: Session, run: CrawlRun | None) -> dict[str, Any] | None:
+    if not run:
+        return None
+    changes = db.scalars(
+        select(CrawlRunEmployeeChange)
+        .where(CrawlRunEmployeeChange.crawl_run_id == run.id)
+        .order_by(CrawlRunEmployeeChange.created_at, CrawlRunEmployeeChange.id)
+    ).all()
+    errors = db.scalars(select(CrawlError).where(CrawlError.crawl_run_id == run.id).order_by(CrawlError.created_at)).all()
+    grouped_changes = {"new": [], "missing_from_source": [], "dismissed": []}
+    for change in changes:
+        grouped_changes.setdefault(change.change_type, []).append(_change_payload(change))
+    return {
+        **(run_payload(run) or {}),
+        "changes_detail_available": bool(changes),
+        "changes": grouped_changes,
+        "errors": [_crawl_error_payload(error) for error in errors],
+    }
+
+
 def format_admin_datetime(value: Any) -> str:
     if not value:
         return "Не указано"
@@ -200,6 +220,52 @@ def _run_status_display(status: str | None) -> str:
     return labels.get(status or "", status or "Не указано")
 
 
+def _change_payload(change: CrawlRunEmployeeChange) -> dict[str, Any]:
+    return {
+        "id": change.id,
+        "employee_id": change.employee_id,
+        "profile_key": change.profile_key,
+        "profile_url": change.profile_url,
+        "full_name": change.full_name,
+        "change_type": change.change_type,
+        "change_type_display": _change_type_display(change.change_type),
+        "profile_available": change.profile_available,
+        "profile_available_display": _profile_available_display(change.profile_available),
+        "message": change.message,
+        "created_at": change.created_at.isoformat() if change.created_at else None,
+        "created_display": format_admin_datetime(change.created_at),
+    }
+
+
+def _crawl_error_payload(error: CrawlError) -> dict[str, Any]:
+    return {
+        "id": error.id,
+        "crawl_run_id": error.crawl_run_id,
+        "profile_url": error.profile_url,
+        "error_type": error.error_type,
+        "message": error.message,
+        "created_at": error.created_at.isoformat() if error.created_at else None,
+        "created_display": format_admin_datetime(error.created_at),
+    }
+
+
+def _change_type_display(change_type: str | None) -> str:
+    labels = {
+        "new": "Новый",
+        "missing_from_source": "Потеряшка",
+        "dismissed": "Уволен",
+    }
+    return labels.get(change_type or "", change_type or "Не указано")
+
+
+def _profile_available_display(value: bool | None) -> str:
+    if value is True:
+        return "Профиль доступен"
+    if value is False:
+        return "Профиль недоступен"
+    return "Не проверялось"
+
+
 def _count_section_items(sections: list[dict[str, Any]], section_type: str) -> int:
     total = 0
     for section in sections:
@@ -281,6 +347,8 @@ def _normalize_section(section: Any) -> dict[str, Any]:
         "year_entries": _normalize_year_entries(section.get("year_entries")),
         "publications": _normalize_publications(section.get("publications")),
         "publications_count": section.get("publications_count"),
+        "theses": _normalize_theses(section.get("theses")),
+        "theses_count": section.get("theses_count"),
         "academic_year": section.get("academic_year"),
         "courses": _normalize_courses(section.get("courses")),
         "table": _normalize_table(section.get("table")),
@@ -349,6 +417,35 @@ def _normalize_courses(items: Any) -> list[dict[str, str | None]]:
     return normalized
 
 
+def _normalize_theses(items: Any) -> list[dict[str, Any]]:
+    normalized = []
+    if not isinstance(items, list):
+        return normalized
+    for item in items:
+        if not isinstance(item, dict):
+            continue
+        title = str(item.get("title") or "").strip()
+        student = str(item.get("student") or "").strip()
+        if not title and not student:
+            continue
+        normalized.append(
+            {
+                "id": item.get("id"),
+                "student": student,
+                "title": title,
+                "defense_year": item.get("defense_year") or item.get("year"),
+                "level": str(item.get("level") or "").strip(),
+                "rating": item.get("rating"),
+                "project_url": str(item.get("project_url") or "").strip() or None,
+                "program": str(item.get("program") or "").strip(),
+                "program_url": str(item.get("program_url") or "").strip() or None,
+                "org_unit": str(item.get("org_unit") or "").strip(),
+                "org_unit_url": str(item.get("org_unit_url") or "").strip() or None,
+            }
+        )
+    return normalized
+
+
 def _normalize_table(table: Any) -> dict[str, Any] | None:
     if not isinstance(table, dict):
         return None

app/services/crawler.py

@@ -9,7 +9,7 @@ from sqlalchemy import select
 from sqlalchemy.orm import Session
 
 from app.config import Settings
-from app.models import CrawlError, CrawlRun, Employee, EmployeeSnapshot, ParserSource, ProfileTab
+from app.models import CrawlError, CrawlRun, CrawlRunEmployeeChange, Employee, EmployeeSnapshot, ParserSource, ProfileTab
 from app.parser.collector import collect_profile_links
 from app.parser.profile import parse_person_profile
 from app.parser.profile_url import profile_key
@@ -68,7 +68,7 @@ def run_crawl(db: Session, settings: Settings) -> CrawlRun:
                 finally:
                     time.sleep(settings.request_delay_seconds)
 
-        run.dismissed_count = _mark_dismissed(db, found_keys)
+        run.dismissed_count = _mark_dismissed(db, run, found_keys, session, settings.request_timeout)
         run.status = "completed"
     except Exception as exc:
         run.status = "failed"
@@ -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:
@@ -107,6 +153,9 @@ def _upsert_employee(db: Session, run: CrawlRun, parsed: dict) -> Employee:
         )
         db.add(employee)
         run.new_count += 1
+        is_new = True
+    else:
+        is_new = False
 
     employee.full_name = parsed.get("full_name")
     employee.status = "active"
@@ -117,6 +166,16 @@ def _upsert_employee(db: Session, run: CrawlRun, parsed: dict) -> Employee:
     employee.current_checksum = checksum
     db.flush()
 
+    if is_new:
+        _record_employee_change(
+            db,
+            run,
+            employee,
+            "new",
+            profile_available=True,
+            message="Сотрудник впервые найден в источнике.",
+        )
+
     db.query(ProfileTab).filter(ProfileTab.employee_id == employee.id).delete()
     for tab in parsed.get("tabs") or []:
         db.add(
@@ -141,20 +200,70 @@ def _upsert_employee(db: Session, run: CrawlRun, parsed: dict) -> Employee:
     return employee
 
 
-def _mark_dismissed(db: Session, found_keys: set[str]) -> int:
+def _mark_dismissed(db: Session, run: CrawlRun, found_keys: set[str], session: requests.Session, timeout: int) -> int:
     dismissed = 0
     active = db.scalars(select(Employee).where(Employee.status == "active")).all()
     now = datetime.now(timezone.utc)
     for employee in active:
         if employee.profile_key in found_keys:
             continue
+        profile_available = _profile_is_available(session, employee.canonical_url, timeout)
+        if profile_available:
+            _record_employee_change(
+                db,
+                run,
+                employee,
+                "missing_from_source",
+                profile_available=True,
+                message="Профиль доступен, но ссылка отсутствует в исходном списке.",
+            )
+            continue
         employee.status = "dismissed"
         employee.dismissed_at = now
+        _record_employee_change(
+            db,
+            run,
+            employee,
+            "dismissed",
+            profile_available=False,
+            message="Сотрудник отсутствует в исходном списке, профиль не подтвердился как доступный.",
+        )
         dismissed += 1
     db.commit()
     return dismissed
 
 
+def _profile_is_available(session: requests.Session, url: str, timeout: int) -> bool:
+    try:
+        response = session.get(url, headers=HEADERS, timeout=timeout, allow_redirects=True)
+        return response.status_code < 400
+    except requests.RequestException:
+        return False
+
+
+def _record_employee_change(
+    db: Session,
+    run: CrawlRun,
+    employee: Employee,
+    change_type: str,
+    *,
+    profile_available: bool | None,
+    message: str,
+) -> None:
+    db.add(
+        CrawlRunEmployeeChange(
+            crawl_run_id=run.id,
+            employee_id=employee.id,
+            profile_key=employee.profile_key,
+            profile_url=employee.canonical_url,
+            full_name=employee.full_name,
+            change_type=change_type,
+            profile_available=profile_available,
+            message=message,
+        )
+    )
+
+
 def _checksum(data: dict) -> str:
     payload = json.dumps(data, ensure_ascii=False, sort_keys=True, separators=(",", ":"))
     return hashlib.sha256(payload.encode("utf-8")).hexdigest()

app/static/admin.css

@@ -1,6 +1,8 @@
 .admin {
   margin: 0;
   min-height: 100vh;
+  display: flex;
+  flex-direction: column;
   color: #1f2937;
   background: #f6f7f9;
   font-family: Arial, sans-serif;
@@ -21,6 +23,11 @@
   font-size: 20px;
 }
 
+.admin__brand-link {
+  color: inherit;
+  text-decoration: none;
+}
+
 .admin__nav {
   display: flex;
   align-items: center;
@@ -34,6 +41,7 @@
 }
 
 .admin__main {
+  flex: 1;
   width: min(1180px, calc(100% - 32px));
   margin: 28px auto;
 }
@@ -52,18 +60,30 @@
 }
 
 .metric {
+  display: block;
   padding: 18px;
   background: #ffffff;
   border: 1px solid #d9dee7;
   border-radius: 8px;
 }
 
+.metric--link {
+  color: inherit;
+  text-decoration: none;
+}
+
+.metric--link:hover {
+  border-color: #0f766e;
+}
+
 .metric__label {
+  display: block;
   color: #6b7280;
   font-size: 13px;
 }
 
 .metric__value {
+  display: block;
   margin-top: 8px;
   font-size: 28px;
   font-weight: 700;
@@ -87,6 +107,14 @@
   border-collapse: collapse;
 }
 
+.table__row {
+  cursor: pointer;
+}
+
+.table__row:hover {
+  background: #f0fdfa;
+}
+
 .table__cell,
 .table__head {
   padding: 10px 8px;
@@ -143,6 +171,10 @@
   background: transparent;
 }
 
+.button--compact {
+  padding: 8px 12px;
+}
+
 .code {
   overflow-x: auto;
   padding: 14px;
@@ -173,11 +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;
@@ -270,6 +325,18 @@
   line-height: 1.55;
 }
 
+.employee-section__meta {
+  display: flex;
+  flex-wrap: wrap;
+  gap: 8px 12px;
+  color: #4b5563;
+  font-size: 13px;
+}
+
+.employee-section__meta-item {
+  line-height: 1.4;
+}
+
 .employee-section__table-wrap {
   overflow-x: auto;
 }
@@ -319,12 +386,22 @@
 }
 
 .stats-strip__item {
+  display: block;
   padding: 14px 16px;
   background: #ffffff;
   border: 1px solid #d9dee7;
   border-radius: 8px;
 }
 
+.stats-strip__item--link {
+  color: inherit;
+  text-decoration: none;
+}
+
+.stats-strip__item--link:hover {
+  border-color: #0f766e;
+}
+
 .stats-strip__label {
   display: block;
   color: #6b7280;

app/static/admin.js

@@ -59,10 +59,23 @@
         applyColumns(columns);
       });
     });
+  }
+
+  function setupClickableRows() {
+    const openRow = (row) => {
+      window.location.href = row.dataset.rowHref;
+    };
+
     document.querySelectorAll("[data-row-href]").forEach((row) => {
       row.addEventListener("click", (event) => {
         if (event.target.closest("a, button, input, select, label")) return;
-        window.location.href = row.dataset.rowHref;
+        openRow(row);
+      });
+      row.addEventListener("keydown", (event) => {
+        if (!["Enter", " "].includes(event.key)) return;
+        if (event.target.closest("a, button, input, select, label")) return;
+        event.preventDefault();
+        openRow(row);
       });
     });
   }
@@ -107,5 +120,6 @@
   }
 
   setupColumns();
+  setupClickableRows();
   setupProgress();
 })();

app/templates/base.html

@@ -8,7 +8,7 @@
   </head>
   <body class="admin">
     <header class="admin__header">
-      <h1 class="admin__brand">MIEM Employees</h1>
+      <h1 class="admin__brand"><a class="admin__brand-link" href="/admin">MIEM Employees</a></h1>
       <nav class="admin__nav">
         <a class="admin__link" href="/admin">Обзор</a>
         <a class="admin__link" href="/admin/directory">Сотрудники</a>

app/templates/dashboard.html

@@ -2,10 +2,10 @@
 {% block title %}Обзор · MIEM Employees{% endblock %}
 {% block content %}
 <section class="admin__grid">
-  <div class="metric"><div class="metric__label">Всего в базе</div><div class="metric__value">{{ counts.total }}</div></div>
+  <a class="metric metric--link" href="/admin/directory"><span class="metric__label">Всего в базе</span><span class="metric__value">{{ counts.total }}</span></a>
-  <div class="metric"><div class="metric__label">Работают</div><div class="metric__value">{{ counts.active }}</div></div>
+  <a class="metric metric--link" href="/admin/directory?status=active"><span class="metric__label">Работают</span><span class="metric__value">{{ counts.active }}</span></a>
-  <div class="metric"><div class="metric__label">Новые за запуск</div><div class="metric__value">{{ counts.new_in_last_run }}</div></div>
+  <a class="metric metric--link" href="{% if latest_run %}/admin/runs/{{ latest_run.id }}#new-employees{% else %}/admin/runs{% endif %}"><span class="metric__label">Новые за запуск</span><span class="metric__value">{{ counts.new_in_last_run }}</span></a>
-  <div class="metric"><div class="metric__label">Уволены</div><div class="metric__value">{{ counts.dismissed }}</div></div>
+  <a class="metric metric--link" href="/admin/directory?status=dismissed"><span class="metric__label">Уволены</span><span class="metric__value">{{ counts.dismissed }}</span></a>
 </section>
 <section class="stats-strip">
   <div class="stats-strip__item">
@@ -16,10 +16,10 @@
     <span class="stats-strip__value">Сотрудников пока нет</span>
     {% endif %}
   </div>
-  <div class="stats-strip__item">
+  <a class="stats-strip__item stats-strip__item--link" href="/admin/runs">
     <span class="stats-strip__label">Запуски</span>
     <span class="stats-strip__value">{{ counts.runs }}</span>
-  </div>
+  </a>
   <div class="stats-strip__item">
     <span class="stats-strip__label">Ошибки</span>
     <span class="stats-strip__value">{{ counts.errors }}</span>
@@ -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><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/directory.html

@@ -33,6 +33,12 @@
       <option value="asc" {% if filters.direction == "asc" %}selected{% endif %}>По возрастанию</option>
       <option value="desc" {% if filters.direction == "desc" %}selected{% endif %}>По убыванию</option>
     </select>
+    <select class="directory__input" name="limit" onchange="this.form.offset.value = 0; this.form.submit()">
+      {% for value in [25, 50, 100] %}
+      <option value="{{ value }}" {% if filters.limit == value %}selected{% endif %}>На странице: {{ value }}</option>
+      {% endfor %}
+    </select>
+    <input type="hidden" name="offset" value="{{ filters.offset }}">
     <button class="button" type="submit">Применить</button>
   </form>
 

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>
-    <a class="admin__link" href="{{ employee_view.canonical_url }}">{{ employee_view.canonical_url }}</a>
+    <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>
@@ -138,6 +148,34 @@
           </li>
           {% endfor %}
         </ul>
+        {% elif section.type == "graduation_theses" and section.theses %}
+        {% if section.theses_count %}<p class="employee-section__note">Всего: {{ section.theses_count }}</p>{% endif %}
+        <ul class="employee-card__list">
+          {% for thesis in section.theses %}
+          <li class="employee-card__list-item">
+            {% if thesis.student %}<strong>{{ thesis.student }}</strong>{% endif %}
+            {% if thesis.title %}
+            <div class="employee-section__text">
+              {% if thesis.project_url %}
+              <a class="admin__link" href="{{ thesis.project_url }}">{{ thesis.title }}</a>
+              {% else %}
+              {{ thesis.title }}
+              {% endif %}
+            </div>
+            {% endif %}
+            <div class="employee-section__meta">
+              {% if thesis.defense_year %}<span class="employee-section__meta-item">Год защиты: {{ thesis.defense_year }}</span>{% endif %}
+              {% if thesis.level %}<span class="employee-section__meta-item">{{ thesis.level }}</span>{% endif %}
+              {% if thesis.rating is not none %}<span class="employee-section__meta-item">Оценка: {{ thesis.rating }}</span>{% endif %}
+              {% if thesis.program %}
+              <span class="employee-section__meta-item">
+                {% if thesis.program_url %}<a class="admin__link" href="{{ thesis.program_url }}">{{ thesis.program }}</a>{% else %}{{ thesis.program }}{% endif %}
+              </span>
+              {% endif %}
+            </div>
+          </li>
+          {% endfor %}
+        </ul>
         {% elif section.type == "table" and section.table %}
         <div class="employee-section__table-wrap">
           <table class="employee-section__table">
@@ -170,7 +208,7 @@
         {% endif %}
         {% endif %}
 
-        {% if section.links and section.type not in ["courses_by_year"] %}
+        {% if section.links and section.type not in ["courses_by_year", "graduation_theses"] %}
         <div class="employee-section__links">
           {% for link in section.links %}
           <a class="employee-section__link" href="{{ link.url }}">{{ link.text }}</a>

app/templates/run_detail.html

@@ -0,0 +1,64 @@
+{% extends "base.html" %}
+{% block title %}Запуск {{ run.id }} · MIEM Employees{% endblock %}
+{% block content %}
+<section class="panel">
+  <div class="progress-panel__header">
+    <div>
+      <h2 class="panel__title">Запуск {{ run.id }}</h2>
+      <p class="progress-panel__empty">{{ run.started_display }} · {{ run.status_display }}</p>
+    </div>
+    <a class="admin__link" href="/admin/runs">Все запуски</a>
+  </div>
+  <div class="stats-strip">
+    <div class="stats-strip__item"><span class="stats-strip__label">Найдено</span><span class="stats-strip__value">{{ run.found_count }}</span></div>
+    <div class="stats-strip__item"><span class="stats-strip__label">Обработано</span><span class="stats-strip__value">{{ run.parsed_count }}</span></div>
+    <div class="stats-strip__item"><span class="stats-strip__label">Новые</span><span class="stats-strip__value">{{ run.new_count }}</span></div>
+    <div class="stats-strip__item"><span class="stats-strip__label">Потеряшки</span><span class="stats-strip__value">{{ run.changes.missing_from_source | length }}</span></div>
+    <div class="stats-strip__item"><span class="stats-strip__label">Уволены</span><span class="stats-strip__value">{{ run.dismissed_count }}</span></div>
+    <div class="stats-strip__item"><span class="stats-strip__label">Ошибки</span><span class="stats-strip__value">{{ run.error_count }}</span></div>
+  </div>
+  {% if not run.changes_detail_available %}
+  <p class="progress-panel__empty">Детализация сотрудников для этого запуска недоступна. Она сохраняется только для новых запусков после обновления.</p>
+  {% endif %}
+</section>
+
+{% for group, title in [("new", "Новые сотрудники"), ("missing_from_source", "Потеряшки"), ("dismissed", "Уволенные")] %}
+<section class="panel"{% if group == "new" %} id="new-employees"{% endif %}>
+  <h2 class="panel__title">{{ title }}</h2>
+  {% set items = run.changes[group] %}
+  {% if items %}
+  <table class="table">
+    <thead><tr><th class="table__head">ФИО</th><th class="table__head">Профиль</th><th class="table__head">Проверка</th><th class="table__head">Комментарий</th></tr></thead>
+    <tbody>
+      {% for item in items %}
+      <tr>
+        <td class="table__cell">{% if item.employee_id %}<a class="admin__link" href="/admin/employees/{{ item.employee_id }}">{{ item.full_name or item.profile_key }}</a>{% else %}{{ item.full_name or item.profile_key }}{% endif %}</td>
+        <td class="table__cell"><a class="admin__link" href="{{ item.profile_url }}">{{ item.profile_url }}</a></td>
+        <td class="table__cell">{{ item.profile_available_display }}</td>
+        <td class="table__cell">{{ item.message or "" }}</td>
+      </tr>
+      {% endfor %}
+    </tbody>
+  </table>
+  {% else %}
+  <p class="progress-panel__empty">Нет записей.</p>
+  {% endif %}
+</section>
+{% endfor %}
+
+<section class="panel">
+  <h2 class="panel__title">Ошибки запуска</h2>
+  {% if run.errors %}
+  <table class="table">
+    <thead><tr><th class="table__head">Профиль</th><th class="table__head">Ошибка</th><th class="table__head">Время</th></tr></thead>
+    <tbody>
+      {% for error in run.errors %}
+      <tr><td class="table__cell">{{ error.profile_url or "" }}</td><td class="table__cell">{{ error.error_type }}: {{ error.message }}</td><td class="table__cell">{{ error.created_display }}</td></tr>
+      {% endfor %}
+    </tbody>
+  </table>
+  {% else %}
+  <p class="progress-panel__empty">Ошибок нет.</p>
+  {% endif %}
+</section>
+{% endblock %}

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><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 = "0.2.6"
+APP_VERSION = "0.4.7"
-FRONTEND_VERSION = "0.2.6"
+FRONTEND_VERSION = "0.4.7"
-BACKEND_VERSION = "0.2.6"
+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
@@ -42,7 +42,7 @@ services:
     environment:
       DATABASE_URL: postgresql+psycopg://${POSTGRES_USER:-miem}:${POSTGRES_PASSWORD:-miem_password}@postgres:5432/${POSTGRES_DB:-miem_workers}
     ports:
-      - "127.0.0.1:8001:8000"
+      - "127.0.0.1:${MCP_PORT:-8001}:8000"
     depends_on:
       postgres:
         condition: service_healthy

migrations/003_crawl_run_employee_changes.sql

@@ -0,0 +1,21 @@
+CREATE TABLE IF NOT EXISTS crawl_run_employee_changes (
+  id SERIAL PRIMARY KEY,
+  crawl_run_id INTEGER NOT NULL REFERENCES crawl_runs(id),
+  employee_id INTEGER REFERENCES employees(id),
+  profile_key VARCHAR(255) NOT NULL,
+  profile_url TEXT NOT NULL,
+  full_name TEXT,
+  change_type VARCHAR(32) NOT NULL,
+  profile_available BOOLEAN,
+  message TEXT,
+  created_at TIMESTAMPTZ NOT NULL DEFAULT now()
+);
+
+CREATE INDEX IF NOT EXISTS ix_crawl_run_employee_changes_run_id
+  ON crawl_run_employee_changes (crawl_run_id);
+
+CREATE INDEX IF NOT EXISTS ix_crawl_run_employee_changes_employee_id
+  ON crawl_run_employee_changes (employee_id);
+
+CREATE INDEX IF NOT EXISTS ix_crawl_run_employee_changes_change_type
+  ON crawl_run_employee_changes (change_type);

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "miem-workers"
-version = "0.2.6"
+version = "0.4.7"
 description = "MIEM employees parser, admin API, and MCP server"
 requires-python = ">=3.11"
 dependencies = [

tests/test_admin_data.py

@@ -1,11 +1,12 @@
 from datetime import datetime, timezone
 
-from app.models import CrawlRun, Employee
+from app.models import CrawlError, CrawlRun, CrawlRunEmployeeChange, Employee
 from app.services.admin_data import (
     employee_detail_payload,
     employee_display_payload,
     format_admin_datetime,
     list_employees_page,
+    run_detail_payload,
     run_payload,
     stats_payload,
 )
@@ -85,6 +86,19 @@ def test_employee_detail_payload_normalizes_human_readable_sections(db_session):
                     "academic_year": "2025/2026",
                     "courses": [{"title": "Course", "url": "https://example.test/course"}],
                 },
+                {
+                    "title": "ВКР",
+                    "type": "graduation_theses",
+                    "theses_count": 1,
+                    "theses": [
+                        {
+                            "student": "Student Name",
+                            "title": "Thesis title",
+                            "defense_year": 2025,
+                            "project_url": "https://www.hse.ru/edu/vkr/1",
+                        }
+                    ],
+                },
                 {
                     "title": "Fallback",
                     "type": "generic",
@@ -102,7 +116,8 @@ def test_employee_detail_payload_normalizes_human_readable_sections(db_session):
     assert payload["sections"][0]["year_entries"][0]["text"] == "Master degree"
     assert payload["sections"][1]["publications"][0]["title"] == "Paper"
     assert payload["sections"][2]["courses"][0]["title"] == "Course"
-    assert payload["sections"][3]["paragraphs"] == ["Fallback text"]
+    assert payload["sections"][3]["theses"][0]["student"] == "Student Name"
+    assert payload["sections"][4]["paragraphs"] == ["Fallback text"]
 
 
 def test_employee_payloads_tolerate_malformed_current_data(db_session):
@@ -155,6 +170,7 @@ def test_list_employees_page_filters_sorts_and_paginates(db_session):
 
     assert page["total"] == 1
     assert page["employees"][0]["full_name"] == "Alpha"
+    assert page["limit"] == 50
 
 
 def test_stats_payload_uses_latest_run_new_count(db_session):
@@ -192,3 +208,43 @@ def test_run_payload_calculates_progress():
     assert payload["processed_count"] == 5
     assert payload["progress_percent"] == 50.0
     assert payload["status_display"] == "Выполняется"
+
+
+def test_run_detail_payload_groups_changes_and_handles_old_runs(db_session):
+    old_run = CrawlRun(source_url="https://miem.hse.ru/persons", status="completed")
+    run = CrawlRun(source_url="https://miem.hse.ru/persons", status="completed", new_count=1)
+    employee = Employee(
+        profile_key="staff:new",
+        canonical_url="https://www.hse.ru/staff/new",
+        full_name="New Person",
+        status="active",
+        first_seen_at=datetime.now(timezone.utc),
+        last_seen_at=datetime.now(timezone.utc),
+    )
+    db_session.add_all([old_run, run, employee])
+    db_session.commit()
+    db_session.add(
+        CrawlRunEmployeeChange(
+            crawl_run_id=run.id,
+            employee_id=employee.id,
+            profile_key=employee.profile_key,
+            profile_url=employee.canonical_url,
+            full_name=employee.full_name,
+            change_type="new",
+            profile_available=True,
+            message="added",
+        )
+    )
+    db_session.add(
+        CrawlError(crawl_run_id=run.id, profile_url=employee.canonical_url, error_type="ValueError", message="bad")
+    )
+    db_session.commit()
+
+    payload = run_detail_payload(db_session, run)
+    old_payload = run_detail_payload(db_session, old_run)
+
+    assert payload["changes_detail_available"] is True
+    assert payload["changes"]["new"][0]["full_name"] == "New Person"
+    assert payload["errors"][0]["error_type"] == "ValueError"
+    assert old_payload["changes_detail_available"] is False
+    assert old_payload["changes"]["new"] == []

tests/test_admin_templates.py

@@ -8,6 +8,7 @@ def test_base_navigation_is_russian_and_has_no_legacy_employees_link():
     assert "Сотрудники" in template
     assert "Запуски" in template
     assert "Выйти" in template
+    assert '<a class="admin__brand-link" href="/admin">MIEM Employees</a>' in template
     assert ">Employees<" not in template
     assert "/admin/employees" not in template
 
@@ -18,6 +19,8 @@ def test_directory_template_is_russian_and_uses_display_dates():
     assert "Сотрудники" in template
     assert "Колонки" in template
     assert "Применить" in template
+    assert "На странице: {{ value }}" in template
+    assert "{% for value in [25, 50, 100] %}" in template
     assert "Найдено:" in template
     assert "employee.first_seen_display" in template
     assert "employee.last_seen_display" in template
@@ -30,3 +33,61 @@ def test_admin_employees_route_redirects_to_directory():
     source = Path("app/admin.py").read_text(encoding="utf-8")
 
     assert 'RedirectResponse("/admin/directory", status_code=303)' in source
+
+
+def test_dashboard_limits_latest_runs_to_five():
+    source = Path("app/admin.py").read_text(encoding="utf-8")
+
+    assert "order_by(desc(CrawlRun.started_at)).limit(5)" in source
+    assert "order_by(desc(CrawlRun.started_at)).limit(10)" not in source
+
+
+def test_runs_template_links_to_run_detail():
+    template = Path("app/templates/runs.html").read_text(encoding="utf-8")
+
+    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
+
+
+def test_run_detail_template_extends_base_and_shows_change_groups():
+    template = Path("app/templates/run_detail.html").read_text(encoding="utf-8")
+
+    assert '{% extends "base.html" %}' in template
+    assert 'id="new-employees"' in template
+    assert "Новые сотрудники" in template
+    assert "Потеряшки" in template
+    assert "Уволенные" in template
+    assert "Детализация сотрудников для этого запуска недоступна" in template
+
+
+def test_dashboard_metric_cards_link_to_admin_targets():
+    template = Path("app/templates/dashboard.html").read_text(encoding="utf-8")
+
+    assert 'href="/admin/directory"' in template
+    assert 'href="/admin/directory?status=active"' in template
+    assert '/admin/runs/{{ latest_run.id }}#new-employees' in template
+    assert 'href="/admin/directory?status=dismissed"' in template
+    assert 'href="/admin/runs"' in template
+
+
+def test_dashboard_latest_run_rows_link_to_run_detail():
+    template = Path("app/templates/dashboard.html").read_text(encoding="utf-8")
+
+    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
+
+
+def test_admin_js_supports_keyboard_activation_for_clickable_rows():
+    source = Path("app/static/admin.js").read_text(encoding="utf-8")
+
+    assert 'addEventListener("keydown"' in source
+    assert '"Enter"' in source
+    assert '" "' in source

tests/test_api_mcp.py

@@ -1,14 +1,15 @@
 from datetime import datetime, timezone
+from types import SimpleNamespace
 
 from fastapi.testclient import TestClient
-from sqlalchemy import create_engine
+from sqlalchemy import create_engine, select
 from sqlalchemy.orm import sessionmaker
 from sqlalchemy.pool import StaticPool
 
 from app.config import Settings, get_settings
 from app.db import Base, get_db
 from app.main import app
-from app.models import CrawlRun, Employee
+from app.models import CrawlRun, CrawlRunEmployeeChange, Employee
 from app.security import SESSION_COOKIE, sign_session
 
 
@@ -18,10 +19,10 @@ def test_health_returns_versions():
     response = client.get("/api/health")
 
     assert response.status_code == 200
-    assert response.json()["backend_version"] == "0.2.6"
+    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},
@@ -38,19 +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_token="secret", session_secret="session-secret")
     client = TestClient(app)
 
-    unauthorized = client.post("/mcp", json={"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}})
+    without_auth = client.post("/mcp", json={"jsonrpc": "2.0", "id": 1, "method": "tools/list", "params": {}})
-    authorized = client.post(
+    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 without_auth.status_code == 200
-    assert authorized.status_code == 200
+    assert with_auth.status_code == 200
-    assert authorized.json()["result"]["tools"][0]["name"] == "search_employees"
+    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()
 
@@ -88,12 +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_token="secret", session_secret="session-secret")
     client = TestClient(app)
 
     response = client.post(
         "/mcp",
-        headers={"Authorization": "Bearer secret"},
         json={
             "jsonrpc": "2.0",
             "id": 1,
@@ -108,6 +108,80 @@ def test_mcp_search_employees_returns_matching_employee():
     app.dependency_overrides.clear()
 
 
+def test_mcp_get_crawl_run_details_returns_changes():
+    engine = create_engine(
+        "sqlite:///:memory:",
+        connect_args={"check_same_thread": False},
+        poolclass=StaticPool,
+    )
+    Base.metadata.create_all(engine)
+    Session = sessionmaker(bind=engine)
+    session = Session()
+    run = CrawlRun(source_url="https://miem.hse.ru/persons", status="completed", new_count=1)
+    employee = Employee(
+        profile_key="staff:new",
+        profile_type="staff",
+        profile_id="new",
+        canonical_url="https://www.hse.ru/staff/new",
+        full_name="New Person",
+        status="active",
+        first_seen_at=datetime.now(timezone.utc),
+        last_seen_at=datetime.now(timezone.utc),
+    )
+    session.add_all([run, employee])
+    session.commit()
+    session.add(
+        CrawlRunEmployeeChange(
+            crawl_run_id=run.id,
+            employee_id=employee.id,
+            profile_key=employee.profile_key,
+            profile_url=employee.canonical_url,
+            full_name=employee.full_name,
+            change_type="new",
+            profile_available=True,
+            message="added",
+        )
+    )
+    session.commit()
+    run_id = run.id
+    session.close()
+
+    def override_db():
+        db = Session()
+        try:
+            yield db
+        finally:
+            db.close()
+
+    app.dependency_overrides[get_db] = override_db
+    client = TestClient(app)
+
+    response = client.post(
+        "/mcp",
+        json={
+            "jsonrpc": "2.0",
+            "id": 1,
+            "method": "tools/call",
+            "params": {"name": "get_crawl_run_details", "arguments": {"run_id": run_id}},
+        },
+    )
+
+    assert response.status_code == 200
+    text = response.json()["result"]["content"][0]["text"]
+    assert "New Person" in text
+    assert "changes_detail_available" in text
+
+    app.dependency_overrides.clear()
+
+
+def test_mcp_protected_resource_metadata_route_is_removed():
+    client = TestClient(app)
+
+    response = client.get("/.well-known/oauth-protected-resource")
+
+    assert response.status_code == 404
+
+
 def test_api_employees_and_stats_require_admin_session():
     engine = create_engine(
         "sqlite:///:memory:",
@@ -130,8 +204,23 @@ def test_api_employees_and_stats_require_admin_session():
             current_data={"contacts": {"emails": ["alpha@hse.ru"]}, "sections": []},
         )
     )
-    db.add(CrawlRun(source_url="https://miem.hse.ru/persons", status="completed", new_count=1))
+    run = CrawlRun(source_url="https://miem.hse.ru/persons", status="completed", new_count=1)
+    db.add(run)
     db.commit()
+    db.add(
+        CrawlRunEmployeeChange(
+            crawl_run_id=run.id,
+            employee_id=1,
+            profile_key="staff:alpha",
+            profile_url="https://www.hse.ru/staff/alpha",
+            full_name="Alpha Person",
+            change_type="new",
+            profile_available=True,
+            message="added",
+        )
+    )
+    db.commit()
+    run_id = run.id
     db.close()
 
     settings = Settings(admin_username="admin", admin_password="password", session_secret="session-secret")
@@ -150,10 +239,66 @@ def test_api_employees_and_stats_require_admin_session():
 
     employees = client.get("/api/employees", params={"q": "Alpha", "has_email": True})
     stats = client.get("/api/stats")
+    run_details = client.get(f"/api/crawl-runs/{run_id}")
 
     assert employees.status_code == 200
     assert employees.json()["total"] == 1
     assert stats.status_code == 200
     assert stats.json()["new_in_last_run"] == 1
+    assert run_details.status_code == 200
+    assert run_details.json()["changes"]["new"][0]["full_name"] == "Alpha Person"
+
+    app.dependency_overrides.clear()
+
+
+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 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

@@ -0,0 +1,13 @@
+from app.config import Settings
+
+
+def test_empty_crawl_limit_is_treated_as_none():
+    settings = Settings(crawl_limit="")
+
+    assert settings.crawl_limit is None
+
+
+def test_numeric_crawl_limit_is_parsed():
+    settings = Settings(crawl_limit="25")
+
+    assert settings.crawl_limit == 25

tests/test_crawler.py

@@ -1,10 +1,25 @@
 from datetime import datetime, timezone
 
-from app.models import CrawlRun, Employee
+from app.models import CrawlRun, CrawlRunEmployeeChange, Employee
 from app.services.crawler import _mark_dismissed, _upsert_employee
 
 
-def test_mark_dismissed_only_marks_missing_active_employees(db_session):
+class FakeResponse:
+    def __init__(self, status_code):
+        self.status_code = status_code
+
+
+class FakeSession:
+    def __init__(self, statuses):
+        self.statuses = statuses
+
+    def get(self, url, **_kwargs):
+        return FakeResponse(self.statuses[url])
+
+
+def test_mark_dismissed_records_missing_source_when_profile_is_available(db_session):
+    run = CrawlRun(source_url="https://miem.hse.ru/persons", status="running")
+    db_session.add(run)
     db_session.add(
         Employee(
             profile_key="staff:kept",
@@ -16,8 +31,8 @@ def test_mark_dismissed_only_marks_missing_active_employees(db_session):
     )
     db_session.add(
         Employee(
-            profile_key="staff:gone",
+            profile_key="staff:missing",
-            canonical_url="https://www.hse.ru/staff/gone",
+            canonical_url="https://www.hse.ru/staff/missing",
             status="active",
             first_seen_at=datetime.now(timezone.utc),
             last_seen_at=datetime.now(timezone.utc),
@@ -25,16 +40,53 @@ def test_mark_dismissed_only_marks_missing_active_employees(db_session):
     )
     db_session.commit()
 
-    dismissed = _mark_dismissed(db_session, {"staff:kept"})
+    dismissed = _mark_dismissed(
+        db_session,
+        run,
+        {"staff:kept"},
+        FakeSession({"https://www.hse.ru/staff/missing": 200}),
+        30,
+    )
+
+    assert dismissed == 0
+    assert db_session.query(Employee).filter_by(profile_key="staff:kept").one().status == "active"
+    missing = db_session.query(Employee).filter_by(profile_key="staff:missing").one()
+    assert missing.status == "active"
+    assert missing.dismissed_at is None
+    change = db_session.query(CrawlRunEmployeeChange).one()
+    assert change.change_type == "missing_from_source"
+    assert change.profile_available is True
+
+
+def test_mark_dismissed_marks_missing_employee_when_profile_is_unavailable(db_session):
+    run = CrawlRun(source_url="https://miem.hse.ru/persons", status="running")
+    employee = Employee(
+        profile_key="staff:gone",
+        canonical_url="https://www.hse.ru/staff/gone",
+        status="active",
+        first_seen_at=datetime.now(timezone.utc),
+        last_seen_at=datetime.now(timezone.utc),
+    )
+    db_session.add_all([run, employee])
+    db_session.commit()
+
+    dismissed = _mark_dismissed(
+        db_session,
+        run,
+        set(),
+        FakeSession({"https://www.hse.ru/staff/gone": 404}),
+        30,
+    )
 
     assert dismissed == 1
-    assert db_session.query(Employee).filter_by(profile_key="staff:kept").one().status == "active"
+    assert employee.status == "dismissed"
-    gone = db_session.query(Employee).filter_by(profile_key="staff:gone").one()
+    assert employee.dismissed_at is not None
-    assert gone.status == "dismissed"
+    change = db_session.query(CrawlRunEmployeeChange).one()
-    assert gone.dismissed_at is not None
+    assert change.change_type == "dismissed"
+    assert change.profile_available is False
 
 
-def test_upsert_employee_increments_new_count_for_new_employee(db_session):
+def test_upsert_employee_increments_new_count_and_records_change_for_new_employee(db_session):
     run = CrawlRun(source_url="https://miem.hse.ru/persons", status="running")
     db_session.add(run)
     db_session.commit()
@@ -56,3 +108,6 @@ def test_upsert_employee_increments_new_count_for_new_employee(db_session):
     db_session.commit()
 
     assert run.new_count == 1
+    change = db_session.query(CrawlRunEmployeeChange).one()
+    assert change.change_type == "new"
+    assert change.full_name == "New Person"

tests/test_employee_detail_template.py

@@ -14,6 +14,8 @@ def test_employee_detail_template_is_human_readable():
     assert "Основная информация" in template
     assert "Контакты" in template
     assert "Разделы профиля" in template
+    assert "graduation_theses" in template
+    assert "Год защиты" in template
     assert "Parser version" not in template
     assert "First seen" not in template
     assert "Last seen" not in template
@@ -25,4 +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

@@ -1,9 +1,110 @@
 from bs4 import BeautifulSoup
 
-from app.parser.profile import 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
 
 
+class FakeResponse:
+    def __init__(self, payload):
+        self.payload = payload
+
+    def raise_for_status(self):
+        return None
+
+    def json(self):
+        return self.payload
+
+
+class FakeSession:
+    def __init__(self):
+        self.posts = []
+        self.gets = []
+
+    def post(self, url, **kwargs):
+        self.posts.append((url, kwargs))
+        return FakeResponse(
+            {
+                "status": "ok",
+                "result": {
+                    "more": False,
+                    "total": 1,
+                    "items": [
+                        {
+                            "id": "888959076",
+                            "type": "ARTICLE",
+                            "title": "Дублирование пакетов",
+                            "year": 2023,
+                            "description": {"short": {"ru": "Информационные процессы. 2023."}},
+                        }
+                    ],
+                },
+            }
+        )
+
+    def get(self, url, **kwargs):
+        self.gets.append((url, kwargs))
+        return FakeResponse(
+            {
+                "lang": "ru",
+                "success": True,
+                "data": [
+                    {
+                        "id": 1045750164,
+                        "year": 2025,
+                        "level": "Бакалавриат",
+                        "title": "Аппаратно-программный комплекс защиты сети",
+                        "rating": 8,
+                        "student": "Лесняк Владислав Евгеньевич",
+                        "learnProgram": {"title": "Информатика и вычислительная техника", "url": "https://hse.ru/ba/isct/"},
+                        "orgUnit": {"title": "МИЭМ", "url": "https://www.hse.ru/org/url/59315150"},
+                        "supervisors": [{"url": "https://www.hse.ru/org/persons/803294906", "name": "Борисов Сергей Петрович"}],
+                    }
+                ],
+            }
+        )
+
+
+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"
@@ -26,3 +127,91 @@ def test_extract_person_tabs_prefers_person_menu_addition():
 
     assert [tab["title"] for tab in tabs] == ["Домашняя страница", "Публикации"]
     assert tabs[1]["href"] == "https://www.hse.ru/staff/avsergeev#sci"
+
+
+def test_enrich_sections_from_hse_widgets_loads_publications_and_vkr():
+    soup = BeautifulSoup(
+        """
+        <script src="/n/stat/publications/dist-w/publs.js" data-author="568398853" data-widget-name="AuthorSearch"></script>
+        <script src="/n/stat/vkr/app.js" data-api-url="/n/vkr/api/" data-person-id="803294906"></script>
+        """,
+        "html.parser",
+    )
+    session = FakeSession()
+
+    sections = enrich_sections_from_hse_widgets(
+        session,
+        soup,
+        "https://www.hse.ru/org/persons/803294906",
+        {"User-Agent": "test"},
+        10,
+        [],
+    )
+
+    publications = next(section for section in sections if section["type"] == "publications")
+    theses = next(section for section in sections if section["type"] == "graduation_theses")
+
+    assert publications["publications_count"] == 1
+    assert publications["publications"][0]["url"] == "https://publications.hse.ru/view/888959076"
+    assert theses["theses_count"] == 1
+    assert theses["theses"][0]["student"] == "Лесняк Владислав Евгеньевич"
+    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