feat: track crawl run employee changes and verify dismissals

2026-05-06 15:13:15 +03:00
parent 2331c7a28d
commit d0459a2c30
16 changed files with 517 additions and 27 deletions
--- a/app/admin.py
+++ b/app/admin.py
@@ -8,7 +8,14 @@ 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.version import BACKEND_VERSION, FRONTEND_VERSION

@@ -150,6 +157,20 @@ 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,
--- a/app/api.py
+++ b/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,
--- a/app/mcp.py
+++ b/app/mcp.py
@@ -8,6 +8,8 @@ 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()
@@ -47,6 +49,15 @@ 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"],
+        },
+    },
 ]


@@ -66,7 +77,7 @@ 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":
@@ -95,6 +106,9 @@ 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}")


--- a/app/models.py
+++ b/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"
--- a/app/services/admin_data.py
+++ b/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,
@@ -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:
--- a/app/services/crawler.py
+++ b/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"
@@ -107,6 +107,9 @@ 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 +120,16 @@ 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 +154,70 @@ 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()
--- a/app/templates/run_detail.html
+++ b/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">
+  <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 %}
--- a/app/templates/runs.html
+++ b/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><td class="table__cell"><a class="admin__link" href="/admin/runs/{{ run.id }}">{{ run.id }}</a></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>
--- a/app/version.py
+++ b/app/version.py
@@ -1,3 +1,3 @@
-APP_VERSION = "0.3.0"
-FRONTEND_VERSION = "0.3.0"
-BACKEND_VERSION = "0.3.0"
+APP_VERSION = "0.4.0"
+FRONTEND_VERSION = "0.4.0"
+BACKEND_VERSION = "0.4.0"