fix: 算力节点任务/GPU 统计纳入评测与推理占用，补充测试依赖

- compute_nodes() 的 current_running_jobs 纳入运行中的评测任务（eval_tasks）
  与已加载的推理模型（compare_tasks 持久化状态 + 内存标记兜底），
  多节点时 GPU 被评测/推理占用不再显示 0/1
- gpus() 直接按 eval_tasks / compare_tasks 派生 GPU busy/reserved 状态，
  修复 gpu_id=0 时 or -1 导致匹配失败；删除评测后 GPU 不再残留 busy
- 评测不再复用 mark_inference_loaded 内存标记，GPU 占用由任务数据驱动
- requirements.txt 补充 pytest / ruff（此前仅声明在 pyproject dev 可选依赖）

Co-Authored-By: Claude <noreply@anthropic.com>

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

@@ -1537,8 +1537,8 @@ async def model_eval_start(payload: dict[str, Any] = Body(...)) -> dict[str, Any
             "compute_node_id": node["id"],
             "output_dir": output_dir,
         })
-        if job.get("status") in {"queued", "running"}:
-            store.mark_inference_loaded(node["id"])
+        # 评测占用 GPU 由 eval_tasks 派生（gpus()/compute_nodes() 直接统计），
+        # 不再复用 mark_inference_loaded 内存标记，避免删除评测后 GPU 状态残留 busy
         return ok({"task_id": task["id"], "status": "running", "job": job})
     except Exception as exc:
         store.update_eval_task(task["id"], {"status": "failed", "error": str(exc)})

backend/app/db/platform_store.py

@@ -2837,6 +2837,28 @@ class PlatformStore:
                 "SELECT compute_node_id, COUNT(*) AS cnt FROM fine_tune_tasks WHERE status IN ('syncing','queued','running') GROUP BY compute_node_id"
             ).fetchall()
             running_map = {r["compute_node_id"]: r["cnt"] for r in running}
+            # 评测任务同样占用算力节点，纳入运行任务统计
+            for row in conn.execute(
+                "SELECT payload FROM eval_tasks WHERE status IN ('syncing','queued','running')"
+            ).fetchall():
+                node_id = json_loads(row["payload"], {}).get("compute_node_id")
+                if node_id:
+                    running_map[node_id] = running_map.get(node_id, 0) + 1
+            # 推理模型占用算力节点同样计入：优先从 compare_tasks 持久化状态派生
+            # （重启后仍准确），并用内存标记兜底（直接 preload 的模型无 compare 记录）
+            inference_node_ids = set(self._inference_nodes)
+            for ctr in conn.execute("SELECT payload FROM compare_tasks").fetchall():
+                ls = json_loads(ctr["payload"], {}).get("load_status") or {}
+                if isinstance(ls, str):
+                    try:
+                        ls = json.loads(ls)
+                    except (json.JSONDecodeError, TypeError):
+                        ls = {}
+                for m in ls.get("loaded_models") or []:
+                    if m.get("status") in {"ready", "running"} and m.get("node_id"):
+                        inference_node_ids.add(m["node_id"])
+            for nid in inference_node_ids:
+                running_map[nid] = running_map.get(nid, 0) + 1
             rows = conn.execute("SELECT * FROM compute_nodes ORDER BY scheduler_weight DESC, code").fetchall()
             return [
                 {
@@ -3054,6 +3076,26 @@ class PlatformStore:
                     "SELECT * FROM fine_tune_tasks WHERE status IN ('syncing','queued','running')"
                 ).fetchall()
             ]
+            # 评测任务同样占用节点 GPU
+            eval_running = [
+                json_loads(row["payload"], {})
+                for row in conn.execute(
+                    "SELECT payload FROM eval_tasks WHERE status IN ('syncing','queued','running')"
+                ).fetchall()
+            ]
+            # 推理模型占用的节点：优先从 compare_tasks 持久化状态派生（重启后仍准确），
+            # 内存标记兜底（直接 preload 的模型无 compare 记录）
+            inference_node_ids = set(self._inference_nodes)
+            for ctr in conn.execute("SELECT payload FROM compare_tasks").fetchall():
+                ls = json_loads(ctr["payload"], {}).get("load_status") or {}
+                if isinstance(ls, str):
+                    try:
+                        ls = json.loads(ls)
+                    except (json.JSONDecodeError, TypeError):
+                        ls = {}
+                for m in ls.get("loaded_models") or []:
+                    if m.get("status") in {"ready", "running"} and m.get("node_id"):
+                        inference_node_ids.add(m["node_id"])
             items = []
             for row in rows:
                 task = next(
@@ -3064,11 +3106,21 @@ class PlatformStore:
                     ),
                     None,
                 )
-                busy = task is not None and task.get("status") == "running"
-                reserved = task is not None and task.get("status") in {"syncing", "queued"}
+                eval_task = next(
+                    (
+                        t
+                        for t in eval_running
+                        if t.get("compute_node_id") == row["node_id"]
+                        and row["gpu_index"] == (int(t["gpu_id"]) if t.get("gpu_id") is not None else -1)
+                    ),
+                    None,
+                )
+                busy = (task is not None and task.get("status") == "running") or eval_task is not None
+                reserved = (task is not None and task.get("status") in {"syncing", "queued"}) or (
+                    eval_task is not None and eval_task.get("status") in {"syncing", "queued"}
+                )
                 # Also mark GPU as busy if an inference model is loaded on this node
-                inference_busy = self.is_inference_loaded(row["node_id"])
-                if inference_busy and not busy:
+                if row["node_id"] in inference_node_ids and not busy:
                     busy = True
                     reserved = False
                 memory_used = round(row["memory_total_gb"] * (0.72 if busy else 0.18 if reserved else 0.04), 1)
@@ -3100,6 +3152,16 @@ class PlatformStore:
                             }
                         ]
                         if task
+                        else [
+                            {
+                                "pid": int(eval_task.get("process_id") or 0),
+                                "name": "eval_runner",
+                                "memory_used_gb": memory_used,
+                                "task_name": eval_task.get("eval_task_name") or eval_task.get("name") or "评测任务",
+                                "user": "admin",
+                            }
+                        ]
+                        if eval_task
                         else [],
                     }
                 )

backend/app/modules/compute_gateway/sync.py

@@ -174,9 +174,7 @@ async def poll_compute_jobs_once() -> dict[str, Any]:
                 except Exception:
                     pass
             store.apply_eval_job_result(eval_task["id"], job, result_content)
-            # If job completed, un-mark inference loaded
-            if job.get("status") in {"completed", "failed", "stopped"}:
-                store.mark_inference_unloaded(node["id"])
+            # 评测 GPU 占用由 eval_tasks 状态派生，无需维护推理内存标记
             eval_synced += 1
         except Exception as exc:  # noqa: BLE001
             failed.append({"eval_task_id": eval_task["id"], "error": str(exc)})