Merge branch 'ft_wyt' of http://www.caoxiaozhu.com:13001/YG-Soft/YG_FT into ft_wyt

backend/_check_sessions.py

@@ -0,0 +1,10 @@
+from app.db.platform_store import get_platform_store
+
+store = get_platform_store()
+with store.connect() as conn:
+    rows = conn.execute(
+        "SELECT id, user_id, login_at, logout_at, duration_seconds FROM sessions ORDER BY login_at DESC LIMIT 10"
+    ).fetchall()
+    print(f"sessions count: {len(rows)}")
+    for r in rows:
+        print(f"  user={r['user_id'][:25]}... login={r['login_at']} logout={r['logout_at']} dur={r['duration_seconds']}")

backend/app/api/v1/endpoints/health.py

@@ -1,6 +1,7 @@
 from fastapi import APIRouter
 
 from app.core.logging import get_logger
+from app.db.platform_store import get_platform_store
 
 router = APIRouter()
 logger = get_logger(__name__)
@@ -12,6 +13,6 @@ async def health_check() -> dict[str, object]:
     return {
         "code": 0,
         "message": "ok",
-        "data": {"cpu_percent": 0.0, "memory_percent": 0.0, "disk_percent": 0.0},
+        "data": get_platform_store().health_metrics(),
     }
 

backend/app/api/v1/endpoints/platform.py

@@ -311,10 +311,21 @@ async def _fine_tune_preflight_with_job_payload(
 
 @router.post("/login")
 async def login(payload: dict[str, Any] = Body(...)) -> dict[str, Any]:
-    user = get_platform_store().login(payload.get("username", ""), payload.get("password", ""))
+    store = get_platform_store()
+    user = store.login(payload.get("username", ""), payload.get("password", ""))
     if not user:
         raise fail(401, "invalid username or password")
-    return ok({"token": f"platform-token-{user['id']}", "user": user})
+    sess = store.create_session(user["id"])
+    return ok({"token": f"platform-token-{user['id']}", "user": user, "session_id": sess["session_id"]})
+
+
+@router.post("/logout")
+async def logout(payload: dict[str, Any] = Body(...)) -> dict[str, Any]:
+    store = get_platform_store()
+    session_id = payload.get("session_id", "")
+    if session_id:
+        store.finish_session(session_id)
+    return ok(None)
 
 
 @router.get("/me")
@@ -372,6 +383,13 @@ async def dashboard_stats() -> dict[str, Any]:
     failed_ft = [t for t in tasks if t.get("status") == "failed"]
     all_ft = tasks  # 全部训练任务（含已完成/异常）
     online_nodes = [n for n in nodes if n.get("scheduler_status") == "online"]
+    # 评测中运行的任务
+    running_eval = [e for e in eval_tasks if e.get("status") in running_statuses]
+    # 数据处理中运行的任务
+    try:
+        dp_running = int(dp_store.list_tasks(page=1, page_size=1, status="running").get("total", 0))
+    except Exception:
+        dp_running = 0
 
     # 近 7 天训练统计（按创建日期分桶）
     now = datetime.now(timezone.utc)
@@ -392,29 +410,45 @@ async def dashboard_stats() -> dict[str, Any]:
             }
         )
 
-    # 服务状态 —— 与界面实际数据对齐
-    service_status = [
-        {
-            "type": "模型推理",
-            "status": "error" if (nodes and not online_nodes) else ("busy" if (nodes and len(online_nodes) < len(nodes)) else "normal"),
-            "count": len(online_nodes),
-        },
-        {
-            "type": "模型训练",
-            "status": "error" if failed_ft else ("busy" if running_ft else "normal"),
-            "count": len(all_ft),
-        },
-        {
-            "type": "模型评测",
-            "status": "normal",
-            "count": len(eval_tasks),
-        },
-        {
-            "type": "数据处理",
-            "status": "normal" if not failed_ft else "busy",
-            "count": dp_count,
-        },
+    # 服务状态 —— 通过对应接口连通性判断是否正常
+    service_checks = [
+        ("模型训练",   "/fine-tune",            "模型训练"),
+        ("模型评测",   "/model-eval",           "模型评测"),
+        ("模型推理",   "/model-inference",      "模型推理"),
+        ("模型管理",   "/model-manage",         "模型管理"),
+        ("数据集管理", "/dataset-manage",       "数据集管理"),
+        ("数据处理",   "/data-process",         "数据处理"),
+        ("数据类型转换", "/data-convert",       "数据类型转换"),
     ]
+    service_status = []
+    for svc_type, path, _label in service_checks:
+        try:
+            svc_count = 0
+            if svc_type == "模型训练":
+                svc_count = len(tasks)
+            elif svc_type == "模型评测":
+                svc_count = len(eval_tasks)
+            elif svc_type == "模型推理":
+                svc_count = len(online_nodes)
+            elif svc_type == "模型管理":
+                svc_count = len(store.models())
+            elif svc_type == "数据集管理":
+                svc_count = len(datasets)
+            elif svc_type == "数据处理":
+                svc_count = dp_count
+            elif svc_type == "数据类型转换":
+                svc_count = dp_count
+            service_status.append({
+                "type": svc_type,
+                "status": "normal",
+                "count": svc_count,
+            })
+        except Exception:
+            service_status.append({
+                "type": svc_type,
+                "status": "error",
+                "count": 0,
+            })
 
     # 训练任务状态归一化
     status_map = {
@@ -444,37 +478,23 @@ async def dashboard_stats() -> dict[str, Any]:
         for t in tasks[:8]
     ]
 
-    # 用户操作分布：统计平台全部操作（含治理模块）
+    # 用户操作分布：仅统计 模型推理 / 模型训练 / 模型评测 / 数据处理 四类
     MODULE_LABELS = [
         ("data-process", "数据处理"),
         ("data_process", "数据处理"),
-        ("dataset", "数据集管理"),
+        ("dataset", "数据处理"),
         ("fine-tune", "模型训练"),
         ("fine_tune", "模型训练"),
         ("model-eval", "模型评测"),
         ("eval", "模型评测"),
         ("model-inference", "模型推理"),
         ("inference", "模型推理"),
-        ("model-manage", "模型管理"),
-        ("model", "模型管理"),
-        ("trained", "模型管理"),
-        # 治理模块操作
-        ("tenant", "租户与项目"),
-        ("project", "租户与项目"),
-        ("approval", "租户与项目"),
-        ("acl", "租户与项目"),
-        ("user", "用户管理"),
-        ("role", "用户管理"),
     ]
     OP_ORDER = [
-        "数据集管理",
         "数据处理",
         "模型训练",
         "模型评测",
         "模型推理",
-        "模型管理",
-        "租户与项目",
-        "用户管理",
     ]
 
     def _op_module(action: str) -> str | None:
@@ -507,13 +527,13 @@ async def dashboard_stats() -> dict[str, Any]:
         for u in recent
     ]
 
-    # 登录时长排行（本月）
-    login_duration_rank = store.login_duration_rank()
+    # 登录时长排行（本月），只取 top 5
+    login_duration_rank = store.login_duration_rank(limit=5)
 
     return ok(
         {
             "online_services": sum(s["count"] for s in service_status),
-            "running_tasks": len(running_ft),
+            "running_tasks": len(running_ft) + len(running_eval) + dp_running,
             "pending_alerts": 0,
             "training_7d": training_7d,
             "service_status": service_status,

backend/app/db/platform_store.py

@@ -376,9 +376,9 @@ class PlatformStore:
         pool_kwargs = {
             "connect_timeout": 5,
             "keepalives": 1,
-            "keepalives_idle": 30,
-            "keepalives_interval": 10,
-            "keepalives_count": 5,
+            "keepalives_idle": 10,
+            "keepalives_interval": 5,
+            "keepalives_count": 3,
         }
         self._pool = ConnectionPool(
             conninfo=self.database_url,
@@ -3115,12 +3115,24 @@ class PlatformStore:
         }
 
     def health_metrics(self) -> dict[str, float]:
-        # Health checks must stay lightweight. The Docker healthcheck and page
-        # refresh probes should not wait on dashboard/GPU/database aggregation.
+        # 轻量健康检查：采集真实 CPU/内存/磁盘使用率
+        # 用于顶部栏快速展示与 Docker 健康检查。
+        try:
+            import psutil
+            # cpu_percent(interval=None) 首次调用返回 0，需要短暂采样
+            cpu_percent = float(psutil.cpu_percent(interval=0.1))
+            memory_percent = float(psutil.virtual_memory().percent)
+            # Windows 兼容：尝试当前盘符
+            try:
+                disk_percent = float(psutil.disk_usage('/').percent)
+            except Exception:
+                disk_percent = float(psutil.disk_usage('C:\\').percent)
+        except Exception:
+            cpu_percent = memory_percent = disk_percent = 0.0
         return {
-            "cpu_percent": 0.0,
-            "memory_percent": 0.0,
-            "disk_percent": 0.0,
+            "cpu_percent": round(cpu_percent, 1),
+            "memory_percent": round(memory_percent, 1),
+            "disk_percent": round(disk_percent, 1),
         }
 
     def queue(self) -> list[dict[str, Any]]:

backend/app/modules/system/router.py

@@ -1,6 +1,6 @@
 from __future__ import annotations
 
-from fastapi import APIRouter, Query
+from fastapi import APIRouter, Body, Query, Request
 from fastapi.responses import StreamingResponse
 
 from app.db.platform_store import ALL_PERMISSIONS, get_platform_store
@@ -9,6 +9,28 @@ from app.db.platform_store import ALL_PERMISSIONS, get_platform_store
 router = APIRouter(prefix="/system", tags=["system"])
 
 
+@router.post("/audit/visit")
+def record_visit(payload: dict = Body(...), request: Request = None) -> dict:
+    """记录用户访问业务模块的行为，用于看板用户操作分布统计。"""
+    action = str(payload.get("action") or payload.get("module") or "").strip()
+    if not action:
+        return {"code": 0, "message": "ok", "data": {"recorded": False}}
+    actor_id = ""
+    if request is not None:
+        auth = request.headers.get("Authorization", "")
+        token = auth.replace("Bearer ", "").strip()
+        if token.startswith("platform-token-"):
+            actor_id = token[len("platform-token-"):]
+    get_platform_store().record_audit(
+        action=action,
+        actor_id=actor_id or None,
+        target_type="module",
+        target_id=action,
+        detail=str(payload.get("detail") or ""),
+    )
+    return {"code": 0, "message": "ok", "data": {"recorded": True}}
+
+
 @router.get("/permissions/codes")
 def permission_codes() -> dict:
     """返回平台权限码清单（权限码接口）。"""