Merge pull request 'fix: add runtime schema guard for skipped count' (#26) from fix/runtime-schema-skipped-count into main

Reviewed-on: #26

.gitignore

@@ -8,3 +8,4 @@ pytest-cache-files-*/
 .coverage
 htmlcov/
 postgres_data/
+MCP_DESCRIPTION.md

README.md

@@ -58,7 +58,7 @@ docker compose up --build
 - MCP: `http://localhost:8001/mcp`
 - Postgres: `localhost:5432`
 
-Таблицы создаются приложением при старте. SQL-миграция для ручного применения лежит в `migrations/001_init.sql`.
+Таблицы создаются приложением при старте. При обновлении существующей базы приложение также добавляет недостающие runtime-колонки, например `crawl_runs.skipped_count`. SQL-миграции для ручного применения лежат в `migrations/`.
 
 ## Парсинг
 
@@ -115,4 +115,4 @@ docker compose exec postgres pg_dump -U miem miem_workers > backup.sql
 docker compose down
 ```
 
-Версия сервиса: `0.6.0`. Админка всегда показывает версии backend и frontend в footer.
+Версия сервиса: `0.6.1`. Админка всегда показывает версии backend и frontend в footer.

app/db.py

@@ -1,6 +1,6 @@
 from collections.abc import Generator
 
-from sqlalchemy import create_engine
+from sqlalchemy import create_engine, inspect, text
 from sqlalchemy.orm import DeclarativeBase, Session, sessionmaker
 
 from app.config import get_settings
@@ -25,6 +25,17 @@ def init_db() -> None:
     import app.models  # noqa: F401
 
     Base.metadata.create_all(bind=engine)
+    _ensure_runtime_schema()
+
+
+def _ensure_runtime_schema() -> None:
+    inspector = inspect(engine)
+    if "crawl_runs" not in inspector.get_table_names():
+        return
+    crawl_run_columns = {column["name"] for column in inspector.get_columns("crawl_runs")}
+    if "skipped_count" not in crawl_run_columns:
+        with engine.begin() as connection:
+            connection.execute(text("ALTER TABLE crawl_runs ADD COLUMN skipped_count INTEGER NOT NULL DEFAULT 0"))
 
 
 def get_db() -> Generator[Session, None, None]:

app/version.py

@@ -1,3 +1,3 @@
-APP_VERSION = "0.6.0"
-FRONTEND_VERSION = "0.6.0"
-BACKEND_VERSION = "0.6.0"
+APP_VERSION = "0.6.1"
+FRONTEND_VERSION = "0.6.1"
+BACKEND_VERSION = "0.6.1"

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "miem-workers"
-version = "0.6.0"
+version = "0.6.1"
 description = "MIEM employees parser, admin API, and MCP server"
 requires-python = ">=3.11"
 dependencies = [

tests/test_api_mcp.py

@@ -20,7 +20,7 @@ def test_health_returns_versions():
     response = client.get("/api/health")
 
     assert response.status_code == 200
-    assert response.json()["backend_version"] == "0.6.0"
+    assert response.json()["backend_version"] == "0.6.1"
 
 
 def test_mcp_lists_tools_without_auth_and_ignores_auth_header():
@@ -154,7 +154,7 @@ def test_mcp_service_info_returns_tools_and_dataset_hash():
     assert response.status_code == 200
     payload = json.loads(response.json()["result"]["content"][0]["text"])
     assert payload["service_name"] == "miem-employees"
-    assert payload["backend_version"] == "0.6.0"
+    assert payload["backend_version"] == "0.6.1"
     assert payload["dataset"]["hash"]
     assert any(tool["name"] == "sync_employees" for tool in payload["tools"])
 

tests/test_db_schema.py

@@ -0,0 +1,27 @@
+from sqlalchemy import create_engine, inspect, text
+
+from app.db import _ensure_runtime_schema
+
+
+def test_runtime_schema_adds_skipped_count_to_existing_crawl_runs_table(monkeypatch):
+    engine = create_engine("sqlite:///:memory:")
+    with engine.begin() as connection:
+        connection.execute(
+            text(
+                """
+                CREATE TABLE crawl_runs (
+                  id INTEGER PRIMARY KEY,
+                  source_url TEXT NOT NULL,
+                  status VARCHAR(32) NOT NULL DEFAULT 'running',
+                  found_count INTEGER NOT NULL DEFAULT 0,
+                  parsed_count INTEGER NOT NULL DEFAULT 0
+                )
+                """
+            )
+        )
+    monkeypatch.setattr("app.db.engine", engine)
+
+    _ensure_runtime_schema()
+
+    columns = {column["name"] for column in inspect(engine).get_columns("crawl_runs")}
+    assert "skipped_count" in columns