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>

.gitignore

@@ -12,8 +12,6 @@ __pycache__/
 build/
 develop-eggs/
 dist/
-!frontend/dist/
-!frontend/dist/**
 node_modules/
 *.tsbuildinfo
 downloads/
@@ -159,6 +157,8 @@ backend/config.yaml
 .codex-backups/
 .pnpm-store/
 .zcode/
+.claude/
+CLAUDE.md
 
 # Spyder project settings
 .spyderproject

README.md

@@ -134,12 +134,45 @@ npm run dev
 
 ## 算力服务启动
 
+算力服务是一个 FastAPI 应用，同时承载 Compute API（模型训练/推理/GPU 管理）和 File Gateway（文件上传下载）路由。Docker 部署时对外暴露两个端口（19100 和 19101）均指向同一服务，方便应用平台分别配置 `api_base_url` 和 `file_gateway_url`。本地开发只需启动一个进程。
+
+### 方式一：Docker 启动（推荐）
+
 ```bash
-cd compute
-uvicorn api.main:app --reload --port 19100
+cd docker/compute
+cp .env.example .env
+docker compose up -d
 ```
 
-默认 `COMPUTE_MODE=real`。真实 GPU 接入时，在每台算力服务器上部署 Compute API、Agent、File Gateway 和 LLaMA-Factory，应用平台通过 `compute_nodes.api_base_url` 和 `compute_nodes.file_gateway_url` 主动轮询。仅在隔离联调环境可显式设置 `COMPUTE_MODE=simulator` 或 `COMPUTE_EXECUTION_MODE=simulator`。
+### 方式二：本地开发启动
+
+**Windows (cmd)：**
+
+```cmd
+cd /d E:\yg_ft\compute
+set PYTHONPATH=E:\yg_ft
+.\.venv\Scripts\python.exe -m uvicorn api.main:app --reload --port 19100
+```
+
+> `PYTHONPATH=E:\yg_ft` 是必需的，因为代码使用 `from compute.agent...` 绝对导入。
+
+**Linux / macOS：**
+
+```bash
+cd compute
+PYTHONPATH=.. uvicorn api.main:app --reload --port 19100
+```
+
+### 环境变量说明
+
+| 变量 | 默认值 | 说明 |
+|---|---|---|
+| `COMPUTE_MODE` | `real` | `real` / `simulator`，仅隔离联调用 simulator |
+| `COMPUTE_EXECUTION_MODE` | `real` | 训练执行模式 |
+| `COMPUTE_SERVICE_TOKEN` | `change_me` | 服务间认证 token |
+| `MODELTF_ROUTE_PREFIX` | `/modelTF` | API 路由前缀 |
+
+应用平台通过数据库 `compute_nodes` 表中的 `api_base_url` 和 `file_gateway_url` 主动轮询算力节点状态。
 
 ## 日志
 

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

@@ -10,5 +10,9 @@ logger = get_logger(__name__)
 @router.get("/health")
 async def health_check() -> dict[str, object]:
     logger.info("health check requested")
-    return {"code": 0, "message": "ok", "data": get_platform_store().health_metrics()}
+    return {
+        "code": 0,
+        "message": "ok",
+        "data": get_platform_store().health_metrics(),
+    }
 

backend/app/api/v1/router.py

@@ -3,8 +3,20 @@
 from app.api.v1.endpoints.data_process import router as data_process_router
 from app.api.v1.endpoints.platform import router as platform_router
 from app.api.v1.endpoints.health import router as health_router
+from app.modules.tenant.router import router as tenant_router
+from app.modules.project.router import router as project_router
+from app.modules.approval.router import router as approval_router
+from app.modules.system.router import router as system_router
+from app.modules.retention.router import router as retention_router
+from app.modules.resource.router import router as resource_router
 
 api_router = APIRouter()
 api_router.include_router(health_router, tags=["health"])
 api_router.include_router(data_process_router, tags=["data-process"])
 api_router.include_router(platform_router, tags=["platform"])
+api_router.include_router(system_router, tags=["system"])
+api_router.include_router(tenant_router, tags=["tenant"])
+api_router.include_router(project_router, tags=["project"])
+api_router.include_router(approval_router, tags=["approval"])
+api_router.include_router(retention_router, tags=["retention"])
+api_router.include_router(resource_router, tags=["resource"])

backend/app/core/auth.py

@@ -0,0 +1,138 @@
+"""鉴权依赖：从 Authorization header 解析当前用户，提供权限校验。"""
+from __future__ import annotations
+
+from typing import Any
+
+from fastapi import Depends, HTTPException, Query, Request, status
+
+from app.db.platform_store import get_platform_store
+
+# 无需鉴权的路径前缀（健康检查、登录等）
+PUBLIC_PATHS = ("/health", "/login", "/system-info")
+
+
+def _extract_token(request: Request) -> str | None:
+    """从 Authorization header 提取 token（格式: Bearer platform-token-{user_id}）。"""
+    auth = request.headers.get("Authorization", "")
+    token = auth.replace("Bearer ", "").strip()
+    if token.startswith("platform-token-"):
+        return token[len("platform-token-"):]
+    return None
+
+
+def get_current_user(request: Request) -> dict[str, Any]:
+    """
+    FastAPI 依赖：解析当前登录用户。
+    - 公开路径（/health, /login 等）直接放行，返回匿名用户。
+    - 无 token 或 token 无效时抛 401。
+    - admin 用户标记为超级管理员，拥有全部权限。
+    """
+    path = request.url.path
+    # 去掉路由前缀后判断
+    for prefix in PUBLIC_PATHS:
+        if path.endswith(prefix):
+            return {"id": None, "username": "anonymous", "role": "viewer", "permissions": [], "protected": False}
+
+    user_id = _extract_token(request)
+    if not user_id:
+        raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="missing or invalid token")
+
+    store = get_platform_store()
+    for u in store.users():
+        if u.get("id") == user_id:
+            return u
+    raise HTTPException(status_code=status.HTTP_401_UNAUTHORIZED, detail="user not found")
+
+
+def require_admin(current_user: dict[str, Any] = Depends(get_current_user)) -> dict[str, Any]:
+    """FastAPI 依赖：要求当前用户是管理员（role=admin 或 protected）。"""
+    if current_user.get("role") == "admin" or current_user.get("protected"):
+        return current_user
+    raise HTTPException(status_code=status.HTTP_403_FORBIDDEN, detail="admin permission required")
+
+
+def is_admin(user: dict[str, Any]) -> bool:
+    """判断用户是否为管理员（admin 角色或 protected 标记）。"""
+    return user.get("role") == "admin" or user.get("protected", False)
+
+
+def has_resource_access(
+    resource_type: str,
+    resource_id: str,
+    user: dict[str, Any],
+    permission: str = "read",
+) -> bool:
+    """
+    检查用户对某资源是否有指定权限。
+    - admin/protected 用户直接放行（旁路）。
+    - 其他用户检查 acls 表中是否有对应授权。
+    """
+    if user.get("role") == "admin" or user.get("protected"):
+        return True
+
+    store = get_platform_store()
+    acls = store.get_acl(resource_type, resource_id)
+    user_id = user.get("id")
+    user_role = user.get("role")
+
+    for entry in acls:
+        # 按 user 授权
+        if entry.get("principal_type") == "user" and entry.get("principal_id") == user_id:
+            if _permission_covers(entry.get("permission"), permission):
+                return True
+        # 按 role 授权
+        if entry.get("principal_type") == "role" and entry.get("principal_id") == user_role:
+            if _permission_covers(entry.get("permission"), permission):
+                return True
+    return False
+
+
+def _permission_covers(granted: str | None, required: str) -> bool:
+    """权限覆盖判断：write/execute 覆盖 read；admin 覆盖一切。"""
+    if not granted:
+        return False
+    if granted == "admin":
+        return True
+    if granted == required:
+        return True
+    # write 覆盖 read
+    if required == "read" and granted in ("write", "execute"):
+        return True
+    return False
+
+
+def filter_accessible_resource_ids(
+    resource_type: str,
+    all_ids: list[str],
+    user: dict[str, Any],
+) -> list[str]:
+    """
+    从全部资源 ID 中过滤出当前用户可访问的 ID 列表。
+    - admin 直接返回全部。
+    - 普通用户查 acls 表取交集。
+    """
+    if user.get("role") == "admin" or user.get("protected"):
+        return all_ids
+
+    if not all_ids:
+        return []
+
+    store = get_platform_store()
+    user_id = user.get("id")
+    user_role = user.get("role")
+
+    # 查询该用户在该资源类型下有 read 权限的所有 resource_id
+    with store.connect() as conn:
+        rows = conn.execute(
+            """
+            SELECT DISTINCT resource_id FROM acls
+            WHERE resource_type=? AND (
+                (principal_type='user' AND principal_id=?)
+                OR (principal_type='role' AND principal_id=?)
+            )
+            """,
+            (resource_type, user_id, user_role),
+        ).fetchall()
+
+    accessible = {r["resource_id"] for r in rows}
+    return [rid for rid in all_ids if rid in accessible]

backend/app/core/config.py

@@ -2,6 +2,18 @@
 from functools import lru_cache
 import os
 
+try:
+    from pathlib import Path as _Path
+
+    from dotenv import load_dotenv
+
+    # 显式指定 backend 目录下的 .env，并强制覆盖已有环境变量，
+    # 确保远程数据库配置生效，不被本地默认值或残留环境变量影响。
+    _env_path = _Path(__file__).resolve().parent.parent.parent / ".env"
+    load_dotenv(dotenv_path=_env_path, override=True)
+except ImportError:
+    pass
+
 
 def _int_env(name: str, default: int) -> int:
     raw = os.getenv(name)

backend/app/db/sql/001_platform_runtime.sql

@@ -33,7 +33,10 @@ CREATE TABLE IF NOT EXISTS trained_models (
     create_time TEXT NOT NULL,
     merged INTEGER NOT NULL DEFAULT 0,
     merging INTEGER NOT NULL DEFAULT 0,
-    merged_path TEXT
+    merged_path TEXT,
+    artifact_dir TEXT,
+    compute_node_id TEXT,
+    compute_node_name TEXT
 );
 
 CREATE TABLE IF NOT EXISTS model_lineage (
@@ -282,3 +285,51 @@ CREATE INDEX IF NOT EXISTS idx_sync_jobs_node_status ON resource_sync_jobs(targe
 CREATE INDEX IF NOT EXISTS idx_eval_tasks_status ON eval_tasks(status);
 CREATE INDEX IF NOT EXISTS idx_eval_dimensions_active ON eval_dimensions(is_active);
 CREATE INDEX IF NOT EXISTS idx_compare_tasks_status ON compare_tasks(status);
+
+-- ===================== Project / Tenant =====================
+
+CREATE TABLE IF NOT EXISTS projects (
+    id TEXT PRIMARY KEY,
+    tenant_id TEXT NOT NULL DEFAULT 'default',
+    name TEXT NOT NULL,
+    code TEXT NOT NULL,
+    description TEXT,
+    quota TEXT,
+    status TEXT NOT NULL DEFAULT 'active',
+    create_time TEXT NOT NULL,
+    create_by TEXT,
+    updated_at TEXT
+);
+
+CREATE TABLE IF NOT EXISTS project_members (
+    project_id TEXT NOT NULL REFERENCES projects(id) ON DELETE CASCADE,
+    user_id TEXT NOT NULL REFERENCES users(id) ON DELETE CASCADE,
+    role TEXT NOT NULL DEFAULT 'member',
+    create_time TEXT NOT NULL,
+    PRIMARY KEY (project_id, user_id)
+);
+
+CREATE TABLE IF NOT EXISTS roles (
+    id TEXT PRIMARY KEY,
+    name TEXT NOT NULL,
+    permissions TEXT NOT NULL DEFAULT '[]',
+    create_time TEXT
+);
+
+CREATE TABLE IF NOT EXISTS sessions (
+    id TEXT PRIMARY KEY,
+    user_id TEXT NOT NULL,
+    issued_at TEXT NOT NULL,
+    expires_at TEXT NOT NULL,
+    ip TEXT
+);
+
+CREATE TABLE IF NOT EXISTS acls (
+    id TEXT PRIMARY KEY,
+    resource_type TEXT NOT NULL,
+    resource_id TEXT NOT NULL,
+    principal_type TEXT NOT NULL,
+    principal_id TEXT NOT NULL,
+    permission TEXT NOT NULL,
+    create_time TEXT
+);

backend/app/db/sql/002_data_process.sql

@@ -80,6 +80,17 @@ CREATE TABLE IF NOT EXISTS data_process_tasks (
     error_count BIGINT NOT NULL DEFAULT 0 CHECK (error_count >= 0),
     failure_reason TEXT,
     generation_run_id TEXT,
+    results_confirmed BOOLEAN NOT NULL DEFAULT TRUE,
+    workflow_step VARCHAR(20) NOT NULL DEFAULT 'create'
+        CHECK (workflow_step IN ('create', 'model', 'upload', 'preview', 'generate', 'results')),
+    preview_status VARCHAR(20) NOT NULL DEFAULT 'idle'
+        CHECK (preview_status IN ('idle', 'queued', 'running', 'completed', 'failed', 'cancelled')),
+    preview_progress NUMERIC(5,2) NOT NULL DEFAULT 0
+        CHECK (preview_progress >= 0 AND preview_progress <= 100),
+    preview_run_id TEXT,
+    preview_failure_reason TEXT,
+    preview_total_files INTEGER NOT NULL DEFAULT 0 CHECK (preview_total_files >= 0),
+    preview_completed_files INTEGER NOT NULL DEFAULT 0 CHECK (preview_completed_files >= 0),
     tenant_id TEXT,
     project_id TEXT,
     owner_id TEXT,
@@ -95,6 +106,87 @@ CREATE TABLE IF NOT EXISTS data_process_tasks (
 );
 
 ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS generation_run_id TEXT;
+-- 历史任务在引入六步确认流程前已经完成审核，默认保留为已确认；
+-- 新任务由创建接口显式写入 FALSE，并在第六步确认后转为 TRUE。
+ALTER TABLE data_process_tasks
+    ADD COLUMN IF NOT EXISTS results_confirmed BOOLEAN NOT NULL DEFAULT TRUE;
+UPDATE data_process_tasks
+SET results_confirmed=FALSE
+WHERE status <> 'completed' AND results_confirmed=TRUE;
+
+-- 先以可空列接入旧库，才能只回填历史行；随后再收紧默认值与约束。
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS workflow_step VARCHAR(20);
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS preview_status VARCHAR(20);
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS preview_progress NUMERIC(5,2);
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS preview_run_id TEXT;
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS preview_failure_reason TEXT;
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS preview_total_files INTEGER;
+ALTER TABLE data_process_tasks ADD COLUMN IF NOT EXISTS preview_completed_files INTEGER;
+
+CREATE TEMP TABLE data_process_workflow_backfill_ids ON COMMIT DROP AS
+SELECT id FROM data_process_tasks WHERE workflow_step IS NULL;
+
+UPDATE data_process_tasks task
+SET workflow_step = CASE
+    WHEN task.status IN ('running', 'failed', 'stopped') THEN 'generate'
+    WHEN task.status = 'completed' AND task.results_confirmed=FALSE THEN 'generate'
+    WHEN task.status = 'completed' THEN 'results'
+    ELSE 'create'
+END
+WHERE task.workflow_step IS NULL;
+UPDATE data_process_tasks
+SET preview_status='idle', preview_progress=0,
+    preview_total_files=0, preview_completed_files=0
+WHERE preview_status IS NULL OR preview_progress IS NULL
+   OR preview_total_files IS NULL OR preview_completed_files IS NULL;
+
+ALTER TABLE data_process_tasks ALTER COLUMN workflow_step SET DEFAULT 'create';
+ALTER TABLE data_process_tasks ALTER COLUMN workflow_step SET NOT NULL;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_status SET DEFAULT 'idle';
+ALTER TABLE data_process_tasks ALTER COLUMN preview_status SET NOT NULL;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_progress SET DEFAULT 0;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_progress SET NOT NULL;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_total_files SET DEFAULT 0;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_total_files SET NOT NULL;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_completed_files SET DEFAULT 0;
+ALTER TABLE data_process_tasks ALTER COLUMN preview_completed_files SET NOT NULL;
+
+DO $$
+BEGIN
+    IF NOT EXISTS (
+        SELECT 1 FROM pg_constraint
+        WHERE conrelid='data_process_tasks'::regclass
+          AND conname='ck_data_process_tasks_workflow_step'
+    ) THEN
+        ALTER TABLE data_process_tasks ADD CONSTRAINT ck_data_process_tasks_workflow_step
+            CHECK (workflow_step IN ('create', 'model', 'upload', 'preview', 'generate', 'results'));
+    END IF;
+    IF NOT EXISTS (
+        SELECT 1 FROM pg_constraint
+        WHERE conrelid='data_process_tasks'::regclass
+          AND conname='ck_data_process_tasks_preview_status'
+    ) THEN
+        ALTER TABLE data_process_tasks ADD CONSTRAINT ck_data_process_tasks_preview_status
+            CHECK (preview_status IN ('idle', 'queued', 'running', 'completed', 'failed', 'cancelled'));
+    END IF;
+    IF NOT EXISTS (
+        SELECT 1 FROM pg_constraint
+        WHERE conrelid='data_process_tasks'::regclass
+          AND conname='ck_data_process_tasks_preview_progress'
+    ) THEN
+        ALTER TABLE data_process_tasks ADD CONSTRAINT ck_data_process_tasks_preview_progress
+            CHECK (preview_progress >= 0 AND preview_progress <= 100);
+    END IF;
+    IF NOT EXISTS (
+        SELECT 1 FROM pg_constraint
+        WHERE conrelid='data_process_tasks'::regclass
+          AND conname='ck_data_process_tasks_preview_file_counts'
+    ) THEN
+        ALTER TABLE data_process_tasks ADD CONSTRAINT ck_data_process_tasks_preview_file_counts
+            CHECK (preview_total_files >= 0 AND preview_completed_files >= 0
+                   AND preview_completed_files <= preview_total_files);
+    END IF;
+END $$;
 
 CREATE UNIQUE INDEX IF NOT EXISTS uq_data_process_tasks_name_alive
     ON data_process_tasks(name) WHERE deleted_at IS NULL;
@@ -153,6 +245,22 @@ CREATE TABLE IF NOT EXISTS data_process_preview_items (
 CREATE INDEX IF NOT EXISTS idx_data_process_preview_task_file
     ON data_process_preview_items(task_id, source_file_id, created_at);
 
+-- 子表在新库中到这里才存在；只修复本次新增 workflow_step 前的历史任务。
+UPDATE data_process_tasks task
+SET workflow_step = CASE
+    WHEN EXISTS (
+        SELECT 1 FROM data_process_preview_items preview
+        WHERE preview.task_id=task.id
+    ) THEN 'preview'
+    WHEN EXISTS (
+        SELECT 1 FROM data_process_source_files source_file
+        WHERE source_file.task_id=task.id AND source_file.deleted_at IS NULL
+    ) THEN 'upload'
+    ELSE task.workflow_step
+END
+WHERE task.id IN (SELECT id FROM data_process_workflow_backfill_ids)
+  AND task.status='pending';
+
 CREATE TABLE IF NOT EXISTS data_process_results (
     id TEXT PRIMARY KEY,
     task_id TEXT NOT NULL REFERENCES data_process_tasks(id) ON DELETE CASCADE,

backend/app/db/sql/002_governance.sql

@@ -0,0 +1,68 @@
+-- 平台治理：租户 / 审批 / 审计（字段以 platform_store 实际写入为准）
+CREATE TABLE IF NOT EXISTS tenants (
+    id TEXT PRIMARY KEY,
+    name TEXT NOT NULL,
+    code TEXT,
+    status TEXT DEFAULT 'active',
+    owner_user_id TEXT,
+    quota TEXT,
+    retention_policy_id TEXT,
+    create_time TEXT
+);
+
+CREATE TABLE IF NOT EXISTS approval_templates (
+    id TEXT PRIMARY KEY,
+    name TEXT NOT NULL,
+    steps TEXT,
+    create_time TEXT
+);
+
+CREATE TABLE IF NOT EXISTS approval_instances (
+    id TEXT PRIMARY KEY,
+    template_id TEXT,
+    resource_type TEXT,
+    resource_id TEXT,
+    applicant_id TEXT,
+    status TEXT DEFAULT 'pending',
+    current_step INTEGER DEFAULT 0,
+    create_time TEXT
+);
+
+CREATE TABLE IF NOT EXISTS approval_steps (
+    id TEXT PRIMARY KEY,
+    instance_id TEXT,
+    step_index INTEGER,
+    approver_id TEXT,
+    status TEXT DEFAULT 'pending',
+    comment TEXT,
+    time TEXT
+);
+
+CREATE TABLE IF NOT EXISTS audit_logs (
+    id TEXT PRIMARY KEY,
+    tenant_id TEXT,
+    project_id TEXT,
+    actor_id TEXT,
+    action TEXT,
+    target_type TEXT,
+    target_id TEXT,
+    detail TEXT,
+    client_ip TEXT,
+    time TEXT
+);
+
+CREATE INDEX IF NOT EXISTS idx_audit_tenant ON audit_logs(tenant_id);
+CREATE INDEX IF NOT EXISTS idx_audit_project ON audit_logs(project_id);
+CREATE INDEX IF NOT EXISTS idx_audit_action ON audit_logs(action);
+CREATE INDEX IF NOT EXISTS idx_audit_time ON audit_logs(time);
+
+CREATE TABLE IF NOT EXISTS retention_policies (
+    id TEXT PRIMARY KEY,
+    name TEXT NOT NULL,
+    scope TEXT,
+    rule TEXT,
+    status TEXT DEFAULT 'active',
+    create_time TEXT,
+    create_by TEXT,
+    updated_at TEXT
+);

backend/app/db/sql/003_model_path_governance.sql

@@ -0,0 +1,18 @@
+-- 003_model_path_governance
+-- 模型路径治理：增加 can_train 标识，区分本地可训练模型与 API / 远程模型。
+-- 训练预检阶段依赖该字段拦截不适合 LLaMA-Factory 本地训练的基座模型。
+
+-- 1. models 表增加 can_train（默认 0，后设搬迁为 1 的规则如下）
+ALTER TABLE models ADD COLUMN IF NOT EXISTS can_train INTEGER NOT NULL DEFAULT 0;
+
+-- 2. 将已有模型按规则推定 can_train：
+--    - path 非空 且 model_source != 'api' → 可训练 (1)
+--    - 其余 → 不可训练 (0)
+UPDATE models
+SET can_train = CASE
+    WHEN path IS NOT NULL AND path != '' AND model_source IS NOT NULL AND model_source != 'api' THEN 1
+    ELSE 0
+END;
+
+-- 3. 给 trained_models 增加 artifact_dir（训练产物目录扫描结果目录）
+ALTER TABLE trained_models ADD COLUMN IF NOT EXISTS artifact_dir TEXT;

backend/app/db/sql/003_tenant_quota.sql

@@ -0,0 +1,3 @@
+-- 租户配额与保留策略扩展（如后续治理表需补列，可在此追加）
+ALTER TABLE tenants ADD COLUMN IF NOT EXISTS gpu_quota TEXT;
+ALTER TABLE tenants ADD COLUMN IF NOT EXISTS storage_quota TEXT;

backend/app/modules/approval/router.py

@@ -0,0 +1,91 @@
+from __future__ import annotations
+
+from fastapi import APIRouter, Body
+from typing import Any
+
+from app.api.v1.endpoints.platform import ok, fail
+from app.db.platform_store import get_platform_store
+
+router = APIRouter(prefix="/approvals", tags=["approval"])
+
+
+@router.get("/templates")
+def list_templates() -> dict[str, Any]:
+    return ok(get_platform_store().approval_templates())
+
+
+@router.post("/templates")
+def create_template(payload: dict[str, Any] = Body(...)) -> dict[str, Any]:
+    if not payload.get("name"):
+        raise fail(400, "name 必填")
+    return ok(get_platform_store().create_approval_template(payload))
+
+
+@router.get("/templates/{template_id}")
+def get_template(template_id: str) -> dict[str, Any]:
+    try:
+        return ok(get_platform_store().approval_template(template_id))
+    except KeyError:
+        raise fail(404, "template not found")
+
+
+@router.put("/templates/{template_id}")
+def update_template(template_id: str, payload: dict[str, Any] = Body(...)) -> dict[str, Any]:
+    try:
+        return ok(get_platform_store().update_approval_template(template_id, payload))
+    except KeyError:
+        raise fail(404, "template not found")
+
+
+@router.delete("/templates/{template_id}")
+def delete_template(template_id: str) -> dict[str, Any]:
+    try:
+        return ok(get_platform_store().delete_approval_template(template_id))
+    except KeyError:
+        raise fail(404, "template not found")
+
+
+@router.get("")
+def list_instances(status: str | None = None) -> dict[str, Any]:
+    return ok(get_platform_store().approval_instances(status=status))
+
+
+@router.post("")
+def create_instance(payload: dict[str, Any] = Body(...)) -> dict[str, Any]:
+    for field in ("resource_type", "resource_id", "applicant_id"):
+        if not payload.get(field):
+            raise fail(400, f"{field} 必填")
+    try:
+        return ok(get_platform_store().create_approval_instance(payload))
+    except KeyError:
+        raise fail(404, "template not found")
+
+
+@router.get("/{instance_id}")
+def get_instance(instance_id: str) -> dict[str, Any]:
+    try:
+        return ok(get_platform_store().approval_instance(instance_id))
+    except KeyError:
+        raise fail(404, "instance not found")
+
+
+@router.post("/{instance_id}/steps/{step_index}/decision")
+def decide(
+    instance_id: str,
+    step_index: int,
+    payload: dict[str, Any] = Body(...),
+) -> dict[str, Any]:
+    if not payload.get("approver_id"):
+        raise fail(400, "approver_id 必填")
+    try:
+        return ok(
+            get_platform_store().decide_approval_step(
+                instance_id,
+                step_index,
+                approver_id=payload["approver_id"],
+                approved=bool(payload.get("approved", False)),
+                comment=payload.get("comment"),
+            )
+        )
+    except (KeyError, ValueError) as e:
+        raise fail(400, str(e))

backend/app/modules/compute_gateway/client.py

@@ -33,6 +33,16 @@ def _unwrap_dict(payload: Any) -> dict[str, Any]:
     return payload if isinstance(payload, dict) else {}
 
 
+# Inference calls are intentionally short-timeout:
+#   - load dispatch only confirms the compute node accepted the request
+#     (the actual model load now runs asynchronously on the node).
+#   - status/unload must never block the platform for long when a node is
+#     unreachable but still marked online.
+INFERENCE_LOAD_TIMEOUT = httpx.Timeout(30, connect=10)
+INFERENCE_STATUS_TIMEOUT = httpx.Timeout(30, connect=5)
+INFERENCE_UNLOAD_TIMEOUT = httpx.Timeout(30, connect=5)
+
+
 class ComputeNodeClient:
     """Application-side client for one compute node.
 
@@ -182,6 +192,36 @@ class ComputeNodeClient:
             response.raise_for_status()
             return _unwrap_dict(response.json())
 
+    async def _request(
+        self,
+        method: str,
+        path: str,
+        json_data: dict[str, Any] | None = None,
+        timeout: float | None = None,
+    ) -> dict[str, Any]:
+        """Generic request method for compute API endpoints."""
+        url = _join_url(self.api_base_url, f"{self.route_prefix}{path}")
+        async with httpx.AsyncClient(timeout=timeout or 300, headers=self.headers()) as client:
+            if method.upper() == "GET":
+                response = await client.get(url)
+            else:
+                response = await client.post(url, json=json_data)
+            response.raise_for_status()
+            return _unwrap_dict(response.json())
+
+    # ── Inference helpers (short timeouts — see module constants) ──────────
+
+    async def inference_load(self, payload: dict[str, Any]) -> dict[str, Any]:
+        """Dispatch a model load. Returns as soon as the node accepts the
+        request; the node now loads asynchronously (status goes 'loading')."""
+        return await self._request("POST", "/inference/load", json_data=payload, timeout=INFERENCE_LOAD_TIMEOUT)
+
+    async def inference_status(self) -> dict[str, Any]:
+        return await self._request("GET", "/inference/status", timeout=INFERENCE_STATUS_TIMEOUT)
+
+    async def inference_unload(self) -> dict[str, Any]:
+        return await self._request("POST", "/inference/unload", json_data={}, timeout=INFERENCE_UNLOAD_TIMEOUT)
+
     async def upload_file(
         self,
         filename: str,
@@ -196,7 +236,8 @@ class ComputeNodeClient:
             "resource_id": resource_id or "",
         }
         files = {"file": (filename, content)}
-        async with httpx.AsyncClient(timeout=max(self.timeout, 60), headers=self.headers()) as client:
+        timeout = httpx.Timeout(max(self.timeout, 60), connect=self.timeout)
+        async with httpx.AsyncClient(timeout=timeout, headers=self.headers()) as client:
             response = await client.post(
                 _join_url(self.api_base_url, f"{self.route_prefix}/compute/files/upload"),
                 data=data,

backend/app/modules/compute_gateway/sync.py

@@ -1,15 +1,119 @@
 from __future__ import annotations
 
+import json
+import time
 from typing import Any
 
 from app.db.platform_store import get_platform_store
 from app.modules.compute_gateway.client import ComputeNodeClient
 
+# starting 状态允许的最大轮询次数（约 40 * 3s ≈ 2 分钟），超过即判定节点不可达
+MAX_STARTING_ATTEMPTS = 40
+
 
 def _node_for_task(task: dict[str, Any]) -> dict[str, Any] | None:
     return next((node for node in get_platform_store().compute_nodes() if node["id"] == task.get("compute_node_id")), None)
 
 
+def _parse_inference_load_status(task: dict[str, Any]) -> tuple[list[dict[str, Any]], dict[str, Any]]:
+    load_status = task.get("load_status") or {}
+    if isinstance(load_status, str):
+        try:
+            load_status = json.loads(load_status)
+        except (json.JSONDecodeError, TypeError):
+            load_status = {}
+    return load_status.get("loaded_models") or [], load_status
+
+
+async def reconcile_inference_loads(store: Any) -> list[dict[str, Any]]:
+    """推进处于 starting 状态的推理加载。
+
+    模型加载已改为异步派发：/model-compare/{id}/load 立即返回，这里在每次
+    轮询时查询对应计算节点的 /inference/status，把任务从 starting 推进到
+    ready/error。使用短超时，单节点不可达不会阻塞整轮轮询。
+    """
+    reconciled: list[dict[str, Any]] = []
+    now = time.time()
+    for task in store.compare_tasks():
+        items, _ = _parse_inference_load_status(task)
+        if not any(item.get("status") == "starting" for item in items):
+            continue
+        # dirty 只要处理过任一 starting 项就置位：load_attempts / last_polled_at
+        # 必须落库，否则节点不可达时计数不会累积，封顶逻辑永远触发不了
+        dirty = False
+        for item in items:
+            if item.get("status") != "starting":
+                continue
+            # 节流：同一 item 每 3s 只查询一次
+            if now - float(item.get("last_polled_at") or 0) < 3:
+                continue
+            item["last_polled_at"] = now
+            item["load_attempts"] = int(item.get("load_attempts") or 0) + 1
+            dirty = True
+            node = next((n for n in store.compute_nodes() if n["id"] == item.get("node_id")), None)
+            if not node:
+                item["status"] = "error"
+                item["error"] = "compute node deleted"
+                store.mark_inference_unloaded(item.get("node_id") or "")
+                continue
+            if not node.get("enabled") or node.get("scheduler_status") != "online":
+                item["status"] = "error"
+                item["error"] = "compute node offline"
+                store.mark_inference_unloaded(node["id"])
+                continue
+            try:
+                status = await ComputeNodeClient(node["api_base_url"]).inference_status()
+            except Exception as exc:  # noqa: BLE001 - node unreachable; keep retrying until cap
+                if int(item.get("load_attempts") or 0) >= MAX_STARTING_ATTEMPTS:
+                    item["status"] = "error"
+                    item["error"] = f"compute node unreachable: {exc}"
+                    store.mark_inference_unloaded(node["id"])
+                continue
+            node_status = status.get("status")
+            if node_status == "ready":
+                item["status"] = "ready"
+                item.pop("error", None)
+                store.mark_inference_loaded(node["id"])
+            elif node_status == "error":
+                item["status"] = "error"
+                item["error"] = status.get("error") or "model load failed on compute node"
+                store.mark_inference_unloaded(node["id"])
+            elif node_status == "idle":
+                # 节点重启导致已加载模型丢失
+                item["status"] = "error"
+                item["error"] = "model disappeared from compute node (node may have restarted)"
+                store.mark_inference_unloaded(node["id"])
+            # node_status == "loading" -> 保持 starting，下轮再查
+        if dirty:
+            if any(i.get("status") in {"ready", "running"} for i in items):
+                new_status = "loaded"
+            elif any(i.get("status") == "starting" for i in items):
+                new_status = "starting"  # 仍在加载中，保持 starting
+            else:
+                new_status = "failed"
+            store.update_compare_task(task["id"], {"status": new_status, "load_status": {"loaded_models": items}})
+            reconciled.append({"task_id": task["id"], "status": new_status})
+    return reconciled
+
+
+async def fetch_eval_result_content(client: ComputeNodeClient, node: dict[str, Any], job: dict[str, Any]) -> dict[str, Any] | None:
+    output_dir = job.get("output_dir")
+    if not output_dir:
+        return None
+    full_path = f"{str(output_dir).rstrip('/')}/eval_results.json"
+    data_root = "/data/yg-ft/"
+    if full_path.startswith(data_root):
+        full_path = full_path[len(data_root):]
+    rel_path = full_path.lstrip("/")
+    import httpx
+    url = f"{node['api_base_url'].rstrip('/')}/modelTF/compute/files/read"
+    async with httpx.AsyncClient(timeout=30, headers=client.headers()) as http:
+        response = await http.get(url, params={"path": rel_path})
+        response.raise_for_status()
+        payload = response.json()
+        return payload if isinstance(payload, dict) else None
+
+
 async def poll_compute_jobs_once() -> dict[str, Any]:
     store = get_platform_store()
     synced: list[dict[str, Any]] = []
@@ -27,6 +131,13 @@ async def poll_compute_jobs_once() -> dict[str, Any]:
                 store.record_training_log_metrics(task["id"], str(logs.get("content") or ""))
             except Exception:
                 pass
+            # P0-4: Force-fetch last log snippet when job reaches terminal state
+            if job.get("status") in {"failed", "stopped"}:
+                try:
+                    last_logs = await client.job_logs(task["compute_job_id"], tail_lines=200)
+                    job["log_snippet"] = str(last_logs.get("content") or "")[:8192]
+                except Exception:
+                    pass
             synced.append(store.apply_compute_job(task["id"], job))
         except Exception as exc:  # noqa: BLE001 - keep polling other jobs
             failed.append({"task_id": task["id"], "error": str(exc)})
@@ -41,4 +152,40 @@ async def poll_compute_jobs_once() -> dict[str, Any]:
             standalone_synced.append(store.sync_model_merge_job(record["id"], job))
         except Exception as exc:  # noqa: BLE001 - keep polling other jobs
             failed.append({"job_id": record["id"], "error": str(exc)})
-    return {"synced": len(synced) + len(standalone_synced), "failed": failed, "items": synced, "standalone": standalone_synced}
+
+    # ── Eval job sync ────────────────────────────────────────────────
+    eval_synced = 0
+    for eval_task in store.running_eval_tasks():
+        node = next(
+            (item for item in store.compute_nodes() if item["id"] == eval_task.get("compute_node_id")),
+            None,
+        )
+        if not node:
+            failed.append({"eval_task_id": eval_task["id"], "error": "compute node not found"})
+            continue
+        try:
+            client = ComputeNodeClient(node["api_base_url"])
+            job = await client.get_job(eval_task["compute_job_id"])
+            result_content = None
+            # Try to read eval_results.json from the job output directory
+            if job.get("status") == "completed" and job.get("output_dir"):
+                try:
+                    result_content = await fetch_eval_result_content(client, node, job)
+                except Exception:
+                    pass
+            store.apply_eval_job_result(eval_task["id"], job, result_content)
+            # 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)})
+
+    # ── Inference load reconciliation ─────────────────────────────────────
+    try:
+        inference_reconciled = await reconcile_inference_loads(store)
+    except Exception as exc:  # noqa: BLE001 - keep polling alive
+        failed.append({"inference_reconcile": str(exc)})
+        inference_reconciled = []
+
+    return {"synced": len(synced) + len(standalone_synced) + eval_synced, "failed": failed,
+            "items": synced, "standalone": standalone_synced, "eval_synced": eval_synced,
+            "inference_reconciled": inference_reconciled}

backend/app/modules/data_process/dataset_format.py

@@ -0,0 +1,148 @@
+"""Dataset format validation for Alpaca, ShareGPT, DPO, CPT formats.
+
+Used by the training preflight flow to validate that uploaded dataset files
+conform to the declared format before submitting to the compute node.
+"""
+
+from __future__ import annotations
+
+import json
+from typing import Any
+
+
+def _load_sample(path: str | None, content: str | None = None, max_samples: int = 20) -> list[dict[str, Any]]:
+    """Load up to max_samples records from JSONL file path or raw content string."""
+    try:
+        if content is not None:
+            text = content.strip()
+        elif path:
+            with open(path, "r", encoding="utf-8") as fh:
+                text = fh.read().strip()
+        else:
+            return []
+    except Exception:
+        return []
+
+    if not text:
+        return []
+
+    lines = text.splitlines()[:max_samples]
+    records: list[dict[str, Any]] = []
+    for line in lines:
+        line = line.strip()
+        if not line:
+            continue
+        try:
+            record = json.loads(line)
+        except json.JSONDecodeError:
+            continue
+        if isinstance(record, dict):
+            records.append(record)
+    return records
+
+
+def _check_alpaca(records: list[dict[str, Any]]) -> list[str]:
+    """Validate Alpaca format: requires 'instruction' field."""
+    errors: list[str] = []
+    if not records:
+        errors.append("Alpaca 格式数据集无有效记录")
+        return errors
+    missing_instruction = sum(1 for r in records if not r.get("instruction"))
+    if missing_instruction:
+        errors.append(
+            f"Alpaca 格式要求每条记录包含 instruction 字段，"
+            f"前{len(records)}条中有{missing_instruction}条缺失"
+        )
+    return errors
+
+
+def _check_sharegpt(records: list[dict[str, Any]]) -> list[str]:
+    """Validate ShareGPT format: requires 'messages' (list of dicts with role/content)."""
+    errors: list[str] = []
+    if not records:
+        errors.append("ShareGPT 格式数据集无有效记录")
+        return errors
+    bad = 0
+    for r in records:
+        messages = r.get("messages")
+        if not isinstance(messages, list) or not messages:
+            bad += 1
+            continue
+        for msg in messages:
+            if not isinstance(msg, dict) or "role" not in msg or "content" not in msg:
+                bad += 1
+                break
+    if bad:
+        errors.append(
+            f"ShareGPT 格式要求每条记录包含 messages 列表，"
+            f"每条消息需有 role 和 content 字段，前{len(records)}条中有{bad}条不符合"
+        )
+    return errors
+
+
+def _check_dpo(records: list[dict[str, Any]]) -> list[str]:
+    """Validate DPO format: requires 'chosen' and 'rejected' fields."""
+    errors: list[str] = []
+    if not records:
+        errors.append("DPO 格式数据集无有效记录")
+        return errors
+    missing_chosen = sum(1 for r in records if not r.get("chosen"))
+    missing_rejected = sum(1 for r in records if not r.get("rejected"))
+    if missing_chosen:
+        errors.append(f"DPO 格式要求 chosen 字段，前{len(records)}条中有{missing_chosen}条缺失")
+    if missing_rejected:
+        errors.append(f"DPO 格式要求 rejected 字段，前{len(records)}条中有{missing_rejected}条缺失")
+    return errors
+
+
+def _check_cpt(records: list[dict[str, Any]]) -> list[str]:
+    """Validate CPT format: requires 'text' field, should NOT have instruction/output."""
+    errors: list[str] = []
+    if not records:
+        errors.append("CPT 格式数据集无有效记录")
+        return errors
+    missing_text = sum(1 for r in records if not r.get("text"))
+    has_instruction = sum(1 for r in records if r.get("instruction") or r.get("output"))
+    if missing_text:
+        errors.append(f"CPT 格式要求 text 字段，前{len(records)}条中有{missing_text}条缺失")
+    if has_instruction:
+        errors.append(
+            f"CPT 格式不应包含 instruction/output 字段（疑似 Alpaca 格式），"
+            f"前{len(records)}条中有{has_instruction}条包含此类字段"
+        )
+    return errors
+
+
+FORMAT_VALIDATORS = {
+    "alpaca": _check_alpaca,
+    "alpaca_jsonl": _check_alpaca,
+    "sharegpt": _check_sharegpt,
+    "dpo": _check_dpo,
+    "cpt": _check_cpt,
+    "pt": _check_cpt,
+}
+
+
+def validate_dataset_format(
+    dataset_format: str,
+    content: str | None = None,
+    path: str | None = None,
+    max_samples: int = 20,
+) -> list[str]:
+    """Validate dataset content against expected format.
+
+    Args:
+        dataset_format: One of 'alpaca', 'sharegpt', 'dpo', 'cpt'.
+        content: Raw file content (JSONL text). Mutually exclusive with path.
+        path: File path to read content from.
+        max_samples: Maximum records to sample for validation.
+
+    Returns:
+        List of error messages (empty if valid).
+    """
+    fmt = str(dataset_format).lower().strip()
+    validator = FORMAT_VALIDATORS.get(fmt)
+    if not validator:
+        return [f"不支持的数据集格式: {dataset_format}，支持的格式: {', '.join(sorted(FORMAT_VALIDATORS))}"]
+    records = _load_sample(path=path, content=content, max_samples=max_samples)
+    return validator(records)

backend/app/modules/data_process/generation.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import hashlib
 import json
+import logging
 import re
 from collections.abc import Callable, Iterable, Mapping
 from typing import Any
@@ -22,6 +23,10 @@ class ModelGenerationError(ValueError):
     """模型配置、响应或调用失败。"""
 
 
+class _TerminalModelGenerationError(ModelGenerationError):
+    """使用相同参数重试也无法恢复的模型响应错误。"""
+
+
 OUTPUT_TYPE_STANDARD = "standard"
 OUTPUT_TYPE_REASONING = "reasoning"
 SUPPORTED_OUTPUT_TYPES = {OUTPUT_TYPE_STANDARD, OUTPUT_TYPE_REASONING}
@@ -31,6 +36,25 @@ SUPPORTED_REASONING_DETAILS = {
     REASONING_DETAIL_NORMAL,
     REASONING_DETAIL_DETAILED,
 }
+MINIMAX_M3_API_HOSTS = {"api.minimax.io", "api.minimaxi.com"}
+MINIMAX_M3_MIN_COMPLETION_TOKENS = 4096
+logger = logging.getLogger(__name__)
+
+
+def _is_retryable_generation_error(exc: Exception) -> bool:
+    if isinstance(exc, _TerminalModelGenerationError):
+        return False
+    if isinstance(exc, httpx.HTTPStatusError):
+        status_code = exc.response.status_code
+        return status_code in {408, 425, 429} or status_code >= 500
+    if isinstance(exc, httpx.RequestError):
+        return True
+    return isinstance(exc, (json.JSONDecodeError, ModelGenerationError))
+
+
+def _is_official_minimax_m3(endpoint: str, model_name: str) -> bool:
+    host = (urlsplit(endpoint).hostname or "").casefold()
+    return host in MINIMAX_M3_API_HOSTS and model_name.casefold() == "minimax-m3"
 
 
 def chat_completions_url(value: str) -> str:
@@ -59,32 +83,139 @@ def chat_completions_url(value: str) -> str:
     return urlunsplit((parsed.scheme, parsed.netloc, target_path, "", ""))
 
 
-def _message_content(payload: Mapping[str, Any]) -> str:
+def _response_choice(payload: Mapping[str, Any]) -> Mapping[str, Any]:
     try:
-        content = payload["choices"][0]["message"]["content"]
+        choice = payload["choices"][0]
     except (KeyError, IndexError, TypeError) as exc:
-        raise ModelGenerationError(
-            "model response does not contain choices[0].message.content"
-        ) from exc
+        raise ModelGenerationError("模型响应缺少 choices[0]") from exc
+    if not isinstance(choice, Mapping):
+        raise ModelGenerationError("模型响应 choices[0] 不是对象")
+    return choice
+
+
+def _response_finish_reason(payload: Mapping[str, Any]) -> str:
+    try:
+        return str(_response_choice(payload).get("finish_reason") or "").strip().lower()
+    except ModelGenerationError:
+        return ""
+
+
+def _response_content_length(payload: Mapping[str, Any]) -> int:
+    try:
+        message = _response_choice(payload).get("message")
+        if not isinstance(message, Mapping):
+            return 0
+        content = message.get("content")
+        if isinstance(content, str):
+            return len(content)
+        if isinstance(content, list):
+            return sum(
+                len(str(item.get("text") or ""))
+                for item in content
+                if isinstance(item, Mapping)
+            )
+    except ModelGenerationError:
+        pass
+    return 0
+
+
+def _raise_for_terminal_response(payload: Mapping[str, Any]) -> Mapping[str, Any]:
+    choice = _response_choice(payload)
+    base_response = payload.get("base_resp")
+    status_code: Any = None
+    status_message = ""
+    if isinstance(base_response, Mapping):
+        status_code = base_response.get("status_code")
+        status_message = re.sub(
+            r"\s+", " ", str(base_response.get("status_msg") or "")
+        ).strip()[:200]
+
+    if bool(payload.get("input_sensitive")) or status_code in {1026, "1026"}:
+        raise _TerminalModelGenerationError(
+            f"模型输入触发内容安全拦截（code={status_code or 1026}）"
+        )
+    if bool(payload.get("output_sensitive")) or status_code in {1027, "1027"}:
+        raise _TerminalModelGenerationError(
+            f"模型输出触发内容安全拦截（code={status_code or 1027}）"
+        )
+
+    finish_reason = str(choice.get("finish_reason") or "").strip().lower()
+    if finish_reason == "length":
+        raise _TerminalModelGenerationError(
+            "模型输出因达到 Token 上限被截断（finish_reason=length），"
+            "请提高最大输出长度后重试"
+        )
+    if finish_reason == "content_filter":
+        raise _TerminalModelGenerationError(
+            "模型输出被内容安全策略拦截（finish_reason=content_filter）"
+        )
+    if finish_reason in {"tool_calls", "function_call"}:
+        raise _TerminalModelGenerationError(
+            f"模型返回了当前生成任务不支持的工具调用（finish_reason={finish_reason}）"
+        )
+    if status_code not in {None, "", 0, "0"}:
+        detail = f"：{status_message}" if status_message else ""
+        raise _TerminalModelGenerationError(
+            f"模型服务返回业务错误（code={status_code}）{detail}"
+        )
+    return choice
+
+
+def _message_content(payload: Mapping[str, Any]) -> str:
+    choice = _raise_for_terminal_response(payload)
+    message = choice.get("message")
+    if not isinstance(message, Mapping):
+        raise ModelGenerationError("模型响应缺少 choices[0].message")
+    content = message.get("content")
     if isinstance(content, str):
-        return content
-    if isinstance(content, list):
+        result = content
+    elif isinstance(content, list):
         parts = [
             str(item.get("text") or "")
             for item in content
             if isinstance(item, Mapping) and item.get("type") in {None, "text", "output_text"}
         ]
-        if parts:
-            return "".join(parts)
-    raise ModelGenerationError("model response content must be text")
+        result = "".join(parts)
+    elif content is None:
+        result = ""
+    else:
+        raise ModelGenerationError("模型响应 content 必须是文本")
+    if not result.strip():
+        raise ModelGenerationError("模型返回的最终内容为空，未生成可解析的 JSON")
+    return result
+
+
+def _json_documents(content: str) -> list[Any]:
+    decoder = json.JSONDecoder()
+    documents: list[Any] = []
+    cursor = 0
+    while cursor < len(content):
+        match = re.search(r"[\[{]", content[cursor:])
+        if not match:
+            break
+        start = cursor + match.start()
+        try:
+            value, end = decoder.raw_decode(content[start:])
+        except json.JSONDecodeError:
+            cursor = start + 1
+            continue
+        if isinstance(value, (Mapping, list)):
+            documents.append(value)
+        cursor = start + max(end, 1)
+    return documents
 
 
 def _json_payload(content: str) -> Any:
     # 只移除模型在 JSON 之前自行输出的思考过程，不能破坏 JSON 字段中的训练内容。
+    cleaned = content.strip()
+    if re.match(r"^\s*<think>", cleaned, flags=re.IGNORECASE) and not re.match(
+        r"^\s*<think>[\s\S]*?</think>", cleaned, flags=re.IGNORECASE
+    ):
+        raise ModelGenerationError("模型思考内容未闭合，响应可能已被截断")
     cleaned = re.sub(
-        r"^\s*<think>[\s\S]*?</think>\s*",
+        r"^\s*(?:<think>[\s\S]*?</think>\s*)+",
         "",
-        content,
+        cleaned,
         count=1,
         flags=re.IGNORECASE,
     ).strip()
@@ -93,10 +224,16 @@ def _json_payload(content: str) -> Any:
         cleaned = fenced.group(1).strip()
     try:
         return json.loads(cleaned)
-    except json.JSONDecodeError as exc:
+    except json.JSONDecodeError as direct_error:
+        documents = _json_documents(cleaned)
+        if len(documents) == 1:
+            return documents[0]
+        if len(documents) > 1:
+            raise ModelGenerationError("模型响应包含多个 JSON 对象，无法确定应使用哪一个")
         raise ModelGenerationError(
-            f"model response is not valid JSON at line {exc.lineno}, column {exc.colno}"
-        ) from exc
+            "模型响应中没有找到唯一且完整的 JSON 对象"
+            f"（第 {direct_error.lineno} 行，第 {direct_error.colno} 列）"
+        ) from direct_error
 
 
 def _result_items(payload: Any) -> list[Mapping[str, Any]]:
@@ -206,6 +343,7 @@ def generate_model_records(
     model_name = str(model.get("online_model_name") or model.get("name") or "").strip()
     if not model_name:
         raise ModelGenerationError("generation model name is required")
+    is_minimax_m3 = _is_official_minimax_m3(endpoint, model_name)
 
     temperature = float(config.get("temperature", 0.7))
     max_tokens = int(config.get("max_tokens", 1024))
@@ -246,9 +384,18 @@ def generate_model_records(
                         reasoning_detail=reasoning_detail,
                     ),
                     "temperature": temperature,
-                    "max_tokens": max_tokens,
                 }
-                if bool(config.get("json_mode", False)):
+                if is_minimax_m3:
+                    request_payload.update(
+                        reasoning_split=True,
+                        max_completion_tokens=max(
+                            max_tokens,
+                            MINIMAX_M3_MIN_COMPLETION_TOKENS,
+                        ),
+                    )
+                else:
+                    request_payload["max_tokens"] = max_tokens
+                if bool(config.get("json_mode", False)) and not is_minimax_m3:
                     request_payload["response_format"] = {"type": "json_object"}
 
                 last_error: Exception | None = None
@@ -264,7 +411,24 @@ def generate_model_records(
                         body = response.json()
                         if not isinstance(body, Mapping):
                             raise ModelGenerationError("model response body must be a JSON object")
-                        candidate_items = _result_items(_json_payload(_message_content(body)))
+                        try:
+                            candidate_items = _result_items(
+                                _json_payload(_message_content(body))
+                            )
+                        except ModelGenerationError as exc:
+                            logger.warning(
+                                "data process model response rejected task_id=%s model=%s "
+                                "finish_reason=%s response_chars=%s input_sensitive=%s "
+                                "output_sensitive=%s reason=%s",
+                                task_id,
+                                model_name,
+                                _response_finish_reason(body) or "missing",
+                                _response_content_length(body),
+                                bool(body.get("input_sensitive")),
+                                bool(body.get("output_sensitive")),
+                                str(exc),
+                            )
+                            raise
                         if len(candidate_items) < batch_count:
                             raise ModelGenerationError(
                                 "model response contains fewer result objects than requested: "
@@ -278,6 +442,8 @@ def generate_model_records(
                         ModelGenerationError,
                     ) as exc:
                         last_error = exc
+                        if not _is_retryable_generation_error(exc):
+                            break
 
                 if generated_items is None:
                     error_message = str(last_error or "model generation failed")[:2000]

backend/app/modules/data_process/office_preview.py

@@ -0,0 +1,308 @@
+"""Word 与 Excel 原文件的安全、受限预览模型。
+
+预览只返回浏览器绘制所需的结构化数据，不返回或执行 Office 包中的活动内容。
+DOCX 的字符偏移与上传时的正文抽取规则保持一致，供前端定位当前切片。
+"""
+
+from __future__ import annotations
+
+import io
+import re
+from typing import Any
+
+from docx import Document
+from docx.oxml.table import CT_Tbl
+from docx.oxml.text.paragraph import CT_P
+from docx.table import Table
+from docx.text.paragraph import Paragraph
+from openpyxl import load_workbook
+
+from app.modules.data_process.algorithms import (
+    _MAX_WORKBOOK_COLUMNS,
+    _MAX_WORKBOOK_HEADER_SCAN_ROWS,
+    _infer_xlsx_header_region,
+    _normalize_spreadsheet_value,
+    _rewrite_xlsx_workbook_relationships,
+    _validate_office_archive,
+    _xlsx_sheet_merge_ranges,
+    normalize_text,
+)
+
+MAX_DOCX_PREVIEW_BLOCKS = 2_000
+MAX_XLSX_PREVIEW_ROWS = 200
+
+
+def _docx_alignment(paragraph: Paragraph) -> str:
+    value = paragraph.alignment
+    return {
+        0: "left",
+        1: "center",
+        2: "right",
+        3: "justify",
+        4: "distribute",
+        5: "justify",
+        7: "justify",
+        8: "distribute",
+        9: "distribute",
+    }.get(int(value) if value is not None else -1, "left")
+
+
+def _docx_heading_level(paragraph: Paragraph) -> int | None:
+    style = paragraph.style
+    if style is None:
+        return None
+    style_name = str(style.name or "")
+    style_id = str(style.style_id or "")
+    match = re.search(r"(?:heading|标题)\s*([1-6])", f"{style_name} {style_id}", re.IGNORECASE)
+    return int(match.group(1)) if match else None
+
+
+def build_docx_preview(raw: bytes) -> dict[str, Any]:
+    """把 DOCX 转为保留标题、段落和表格顺序的浏览器预览模型。"""
+
+    _validate_office_archive(raw, "docx")
+    try:
+        document = Document(io.BytesIO(raw))
+    except Exception as exc:
+        raise ValueError(f"invalid DOCX file: {exc}") from exc
+
+    blocks: list[dict[str, Any]] = []
+    source_cursor = 0
+    has_source_content = False
+    rendered_blocks = 0
+    truncated = False
+
+    def source_range(value: str) -> tuple[str, int, int] | None:
+        nonlocal source_cursor, has_source_content
+        text = normalize_text(value)
+        if not text:
+            return None
+        if has_source_content:
+            source_cursor += 2
+        start = source_cursor
+        source_cursor += len(text)
+        has_source_content = True
+        return text, start, source_cursor
+
+    for child in document.element.body.iterchildren():
+        if rendered_blocks >= MAX_DOCX_PREVIEW_BLOCKS:
+            truncated = True
+            break
+
+        if isinstance(child, CT_P):
+            paragraph = Paragraph(child, document)
+            located = source_range(paragraph.text)
+            if located is None:
+                continue
+            text, start, end = located
+            style_name = str(paragraph.style.name or "") if paragraph.style else ""
+            blocks.append(
+                {
+                    "type": "paragraph",
+                    "text": text,
+                    "style": style_name,
+                    "heading_level": _docx_heading_level(paragraph),
+                    "alignment": _docx_alignment(paragraph),
+                    "is_list": "list" in style_name.casefold() or "列表" in style_name,
+                    "source_start": start,
+                    "source_end": end,
+                }
+            )
+            rendered_blocks += 1
+            continue
+
+        if not isinstance(child, CT_Tbl):
+            continue
+        table = Table(child, document)
+        preview_rows: list[dict[str, Any]] = []
+        for row in table.rows:
+            if rendered_blocks >= MAX_DOCX_PREVIEW_BLOCKS:
+                truncated = True
+                break
+            cell_values = [normalize_text(cell.text) for cell in row.cells]
+            located = source_range("\t".join(cell_values))
+            if located is None:
+                continue
+            _, start, end = located
+            preview_rows.append(
+                {
+                    "cells": cell_values,
+                    "source_start": start,
+                    "source_end": end,
+                }
+            )
+            rendered_blocks += 1
+        if preview_rows:
+            blocks.append({"type": "table", "rows": preview_rows})
+        if truncated:
+            break
+
+    return {
+        "format": "docx",
+        "blocks": blocks,
+        "truncated": truncated,
+    }
+
+
+def build_xlsx_preview(
+    raw: bytes,
+    *,
+    sheet_index: int = 0,
+    offset: int = 0,
+    limit: int = 100,
+) -> dict[str, Any]:
+    """按工作表分页返回 XLSX 的表头和记录网格。"""
+
+    if sheet_index < 0 or offset < 0:
+        raise ValueError("sheet_index and offset must be non-negative")
+    if limit < 1 or limit > MAX_XLSX_PREVIEW_ROWS:
+        raise ValueError(
+            f"XLSX preview limit must be in [1, {MAX_XLSX_PREVIEW_ROWS}]"
+        )
+
+    _validate_office_archive(raw, "xlsx")
+    merged_by_sheet, normalized_targets = _xlsx_sheet_merge_ranges(raw)
+    workbook_raw = (
+        _rewrite_xlsx_workbook_relationships(raw, normalized_targets)
+        if normalized_targets
+        else raw
+    )
+    try:
+        workbook = load_workbook(
+            io.BytesIO(workbook_raw),
+            read_only=True,
+            data_only=True,
+            keep_links=False,
+        )
+    except Exception as exc:
+        raise ValueError(f"invalid XLSX file: {exc}") from exc
+
+    try:
+        sheets = [
+            {
+                "index": index,
+                "name": worksheet.title,
+                "state": worksheet.sheet_state,
+            }
+            for index, worksheet in enumerate(workbook.worksheets)
+        ]
+        if not sheets:
+            raise ValueError("XLSX workbook contains no worksheets")
+        if sheet_index >= len(sheets):
+            raise ValueError("XLSX worksheet index is out of range")
+
+        worksheet = workbook.worksheets[sheet_index]
+        reset_dimensions = getattr(worksheet, "reset_dimensions", None)
+        if callable(reset_dimensions):
+            reset_dimensions()
+        row_iterator = enumerate(worksheet.iter_rows(values_only=True), start=1)
+        buffered_rows: dict[int, tuple[Any, ...]] = {}
+
+        def normalized_values(row: tuple[Any, ...]) -> list[Any]:
+            values = list(row)
+            while values and values[-1] in {None, ""}:
+                values.pop()
+            if len(values) > _MAX_WORKBOOK_COLUMNS:
+                raise ValueError(
+                    f"XLSX worksheet {worksheet.title!r} exceeds "
+                    f"{_MAX_WORKBOOK_COLUMNS} columns"
+                )
+            return values
+
+        for row_number, row in row_iterator:
+            values = normalized_values(row)
+            if not values or all(value in {None, ""} for value in values):
+                continue
+            buffered_rows[row_number] = tuple(values)
+            if len(buffered_rows) >= _MAX_WORKBOOK_HEADER_SCAN_ROWS:
+                break
+
+        if not buffered_rows:
+            return {
+                "format": "xlsx",
+                "sheets": sheets,
+                "active_sheet": {
+                    "index": sheet_index,
+                    "name": worksheet.title,
+                    "columns": [],
+                    "rows": [],
+                    "offset": offset,
+                    "limit": limit,
+                    "has_more": False,
+                },
+            }
+
+        _, header_end_row, headers = _infer_xlsx_header_region(
+            worksheet.title,
+            buffered_rows,
+            merged_by_sheet.get(worksheet.title, ()),
+        )
+        preview_rows: list[dict[str, Any]] = []
+        record_index = 0
+        has_more = False
+
+        def append_row(row_number: int, values: tuple[Any, ...] | list[Any]) -> bool:
+            nonlocal record_index, has_more
+            row_values = list(values)
+            if len(row_values) > len(headers):
+                raise ValueError(
+                    f"XLSX worksheet {worksheet.title!r} has a row wider than its header"
+                )
+            row_values.extend([None] * (len(headers) - len(row_values)))
+            record = {
+                header: _normalize_spreadsheet_value(value)
+                for header, value in zip(headers, row_values, strict=True)
+            }
+            if not any(value not in {"", None} for value in record.values()):
+                return False
+            current_index = record_index
+            record_index += 1
+            if current_index < offset:
+                return False
+            if len(preview_rows) >= limit:
+                has_more = True
+                return True
+            preview_rows.append(
+                {
+                    "row_number": row_number,
+                    "record_index": current_index,
+                    "values": [record[header] for header in headers],
+                    "record": record,
+                }
+            )
+            return False
+
+        for row_number, values in buffered_rows.items():
+            if row_number > header_end_row and append_row(row_number, values):
+                break
+        else:
+            for row_number, row in row_iterator:
+                values = normalized_values(row)
+                if not values or all(value in {None, ""} for value in values):
+                    continue
+                if append_row(row_number, values):
+                    break
+
+        return {
+            "format": "xlsx",
+            "sheets": sheets,
+            "active_sheet": {
+                "index": sheet_index,
+                "name": worksheet.title,
+                "columns": headers,
+                "rows": preview_rows,
+                "offset": offset,
+                "limit": limit,
+                "has_more": has_more,
+            },
+        }
+    finally:
+        workbook.close()
+
+
+__all__ = [
+    "MAX_DOCX_PREVIEW_BLOCKS",
+    "MAX_XLSX_PREVIEW_ROWS",
+    "build_docx_preview",
+    "build_xlsx_preview",
+]

backend/app/modules/data_process/schema_cli.py

@@ -7,6 +7,18 @@ from urllib.parse import urlsplit
 
 from app.modules.data_process.store import DataProcessStore
 
+REQUIRED_TASK_COLUMNS = (
+    "generation_run_id",
+    "results_confirmed",
+    "workflow_step",
+    "preview_status",
+    "preview_progress",
+    "preview_run_id",
+    "preview_failure_reason",
+    "preview_total_files",
+    "preview_completed_files",
+)
+
 
 def _target_label(database_url: str) -> str:
     parsed = urlsplit(database_url)
@@ -18,14 +30,13 @@ def _schema_ready(store: DataProcessStore) -> bool:
     with store.connect() as conn:
         row = conn.execute(
             """
-            SELECT EXISTS (
-                SELECT 1
-                FROM information_schema.columns
-                WHERE table_schema=current_schema()
-                  AND table_name='data_process_tasks'
-                  AND column_name='generation_run_id'
-            ) AS ready
-            """
+            SELECT COUNT(*) = %s AS ready
+            FROM information_schema.columns
+            WHERE table_schema=current_schema()
+              AND table_name='data_process_tasks'
+              AND column_name = ANY(%s)
+            """,
+            (len(REQUIRED_TASK_COLUMNS), list(REQUIRED_TASK_COLUMNS)),
         ).fetchone()
     return bool(row and row["ready"])
 

backend/app/modules/data_process/storage.py

@@ -137,6 +137,67 @@ class LocalDataProcessStorage:
         self._issued_staged_objects[temporary_path] = staged
         return staged
 
+    def stage_copy(
+        self,
+        *,
+        batch_id: str,
+        source_reference: str,
+        expected_source_task_id: str,
+        expected_source_file_id: str,
+        task_id: str,
+        source_file_id: str,
+        version: int,
+        name: str,
+    ) -> StagedSourceObject:
+        """为不可变源对象创建独立目录项，不把大文件重新读入内存。"""
+
+        batch_id = _safe_component(batch_id, "batch id")
+        task_id = _safe_component(task_id, "task id")
+        source_file_id = _safe_component(source_file_id, "source file id")
+        if isinstance(version, bool) or not isinstance(version, int) or version < 1:
+            raise DataProcessStorageError("invalid source file version")
+        basename = _safe_basename(name)
+        source_relative = self._relative_from_reference(source_reference)
+        if source_relative is None:
+            raise DataProcessStorageError("original source object is not available")
+        self._assert_expected_owner(
+            source_relative,
+            expected_task_id=expected_source_task_id,
+            expected_source_file_id=expected_source_file_id,
+        )
+        descriptor, source_info = self._open_read_descriptor(source_relative)
+        os.close(descriptor)
+
+        batch_directory = self._ensure_directory(self._root / ".staging" / batch_id)
+        temporary_path = batch_directory / f"{source_file_id}-{uuid.uuid4().hex}.tmp"
+        source_path = self._path_for_relative(source_relative)
+        try:
+            os.link(source_path, temporary_path, follow_symlinks=False)
+            copy_info = temporary_path.lstat()
+            if (
+                not stat.S_ISREG(copy_info.st_mode)
+                or source_info.st_dev != copy_info.st_dev
+                or source_info.st_ino != copy_info.st_ino
+            ):
+                raise DataProcessStorageError("source storage object changed while copying")
+        except Exception:
+            temporary_path.unlink(missing_ok=True)
+            raise
+
+        relative_path = PurePosixPath(
+            task_id,
+            source_file_id,
+            f"v{version}",
+            basename,
+        )
+        reference = (
+            "local://data-process/"
+            f"{task_id}/{source_file_id}/v{version}/{quote(basename, safe='')}"
+        )
+        staged = StagedSourceObject(reference, temporary_path, relative_path)
+        self._issued_staged_objects[temporary_path] = staged
+        return staged
+
     def publish(self, objects: Iterable[StagedSourceObject]) -> None:
         staged = list(objects)
         published: list[StagedSourceObject] = []

backend/app/modules/project/router.py

@@ -0,0 +1,244 @@
+from __future__ import annotations
+
+from fastapi import APIRouter, Body, Depends, Request
+from typing import Any
+
+from app.api.v1.endpoints.platform import ok, fail
+from app.core.auth import filter_accessible_resource_ids, get_current_user, has_resource_access, is_admin
+from app.db.platform_store import get_platform_store
+
+router = APIRouter(prefix="/projects", tags=["project"])
+
+
+def _actor(request: Request) -> str | None:
+    auth = request.headers.get("Authorization", "")
+    token = auth.replace("Bearer ", "").strip()
+    return token or None
+
+
+def _require_no_pending_approval(resource_type: str, resource_id: str) -> None:
+    """第 4 周：写操作审批拦截——存在待审批实例时拒绝执行。"""
+    store = get_platform_store()
+    pending = [
+        i for i in store.approval_instances(status="pending")
+        if i["resource_type"] == resource_type and i["resource_id"] == resource_id
+    ]
+    if pending:
+        raise fail(409, "存在待审批的变更，请先完成审批")
+
+
+def _require_approval_or_admin(
+    resource_type: str,
+    resource_id: str,
+    current_user: dict[str, Any],
+    action_desc: str = "",
+) -> dict[str, Any] | None:
+    """高风险操作审批旁路：admin 直接放行，普通用户创建审批实例（code=202）。"""
+    if is_admin(current_user):
+        return None
+    store = get_platform_store()
+    instance = store.create_approval_instance({
+        "resource_type": resource_type,
+        "resource_id": resource_id,
+        "applicant_id": current_user.get("id"),
+        "template_id": None,
+    })
+    return {
+        "code": 202,
+        "message": f"操作已提交审批，等待管理员批准：{action_desc}",
+        "data": {"approval_required": True, "approval_id": instance["id"]},
+    }
+
+
+@router.get("")
+def list_projects(
+    tenant_id: str = "default",
+    status: str | None = None,
+    keyword: str | None = None,
+    current_user: dict = Depends(get_current_user),
+) -> dict[str, Any]:
+    store = get_platform_store()
+    projects = store.projects(tenant_id=tenant_id, status=status, keyword=keyword)
+    # #1 ACL 过滤：admin 直接放行，普通用户只能看到自己被授权的项目
+    accessible_ids = set(
+        filter_accessible_resource_ids("project", [p["id"] for p in projects], current_user)
+    )
+    filtered = [p for p in projects if p["id"] in accessible_ids]
+    return ok(filtered)
+
+
+@router.post("")
+def create_project(payload: dict[str, Any] = Body(...), request: Request = None) -> dict[str, Any]:
+    store = get_platform_store()
+    proj = store.create_project(payload)
+    store.record_audit(
+        action="project.create",
+        actor_id=_actor(request) if request else None,
+        target_type="project",
+        target_id=proj["id"],
+        tenant_id=proj.get("tenant_id"),
+        detail=f"name={proj.get('name')}",
+    )
+    return ok(proj)
+
+
+@router.get("/{project_id}")
+def get_project(project_id: str, current_user: dict = Depends(get_current_user)) -> dict[str, Any]:
+    # #2 访问控制：普通用户无 read 权限则拒绝
+    if not has_resource_access("project", project_id, current_user, "read"):
+        raise fail(403, "no permission to access this project")
+    try:
+        return ok(get_platform_store().project(project_id))
+    except KeyError:
+        raise fail(404, "project not found")
+
+
+@router.put("/{project_id}")
+def update_project(
+    project_id: str,
+    payload: dict[str, Any] = Body(...),
+    request: Request = None,
+    current_user: dict = Depends(get_current_user),
+) -> dict[str, Any]:
+    if not has_resource_access("project", project_id, current_user, "write"):
+        raise fail(403, "no permission to update this project")
+    store = get_platform_store()
+    try:
+        proj = store.update_project(project_id, payload)
+    except KeyError:
+        raise fail(404, "project not found")
+    store.record_audit(
+        action="project.update",
+        actor_id=_actor(request) if request else None,
+        target_type="project",
+        target_id=project_id,
+        tenant_id=proj.get("tenant_id"),
+        detail=f"fields={','.join(payload.keys())}",
+    )
+    return ok(proj)
+
+
+@router.post("/{project_id}/archive")
+def archive_project(
+    project_id: str,
+    request: Request = None,
+    current_user: dict = Depends(get_current_user),
+) -> dict[str, Any]:
+    _require_no_pending_approval("project", project_id)
+    pending = _require_approval_or_admin("project", project_id, current_user, f"归档项目 {project_id}")
+    if pending:
+        return pending
+    store = get_platform_store()
+    try:
+        proj = store.archive_project(project_id)
+    except KeyError:
+        raise fail(404, "project not found")
+    store.record_audit(
+        action="project.archive",
+        actor_id=_actor(request) if request else None,
+        target_type="project",
+        target_id=project_id,
+        tenant_id=proj.get("tenant_id"),
+    )
+    return ok(proj)
+
+
+@router.delete("/{project_id}")
+def delete_project(
+    project_id: str,
+    request: Request = None,
+    current_user: dict = Depends(get_current_user),
+) -> dict[str, Any]:
+    _require_no_pending_approval("project", project_id)
+    pending = _require_approval_or_admin("project", project_id, current_user, f"删除项目 {project_id}")
+    if pending:
+        return pending
+    store = get_platform_store()
+    store.delete_project(project_id)
+    store.record_audit(
+        action="project.delete",
+        actor_id=_actor(request) if request else None,
+        target_type="project",
+        target_id=project_id,
+    )
+    return ok(None)
+
+
+@router.get("/{project_id}/members")
+def list_members(project_id: str, current_user: dict = Depends(get_current_user)) -> dict[str, Any]:
+    if not has_resource_access("project", project_id, current_user, "read"):
+        raise fail(403, "no permission to access this project")
+    try:
+        return ok(get_platform_store().project_members(project_id))
+    except KeyError:
+        raise fail(404, "project not found")
+
+
+@router.post("/{project_id}/members")
+def add_member(
+    project_id: str,
+    payload: dict[str, Any] = Body(...),
+    request: Request = None,
+    current_user: dict = Depends(get_current_user),
+) -> dict[str, Any]:
+    if not has_resource_access("project", project_id, current_user, "write"):
+        raise fail(403, "no permission to manage members of this project")
+    store = get_platform_store()
+    try:
+        member = store.add_project_member(project_id, payload)
+    except KeyError:
+        raise fail(404, "project not found")
+    store.record_audit(
+        action="project.member.add",
+        actor_id=_actor(request) if request else None,
+        target_type="project.member",
+        target_id=project_id,
+        detail=f"user_id={payload.get('user_id')},role={payload.get('role')}",
+    )
+    return ok(member)
+
+
+@router.put("/{project_id}/members/{user_id}")
+def update_member(
+    project_id: str,
+    user_id: str,
+    payload: dict[str, Any] = Body(...),
+    request: Request = None,
+    current_user: dict = Depends(get_current_user),
+) -> dict[str, Any]:
+    if not has_resource_access("project", project_id, current_user, "write"):
+        raise fail(403, "no permission to manage members of this project")
+    store = get_platform_store()
+    try:
+        member = store.update_project_member_role(project_id, user_id, payload)
+    except KeyError:
+        raise fail(404, "project or member not found")
+    store.record_audit(
+        action="project.member.update",
+        actor_id=_actor(request) if request else None,
+        target_type="project.member",
+        target_id=project_id,
+        detail=f"user_id={user_id},role={payload.get('role')}",
+    )
+    return ok(member)
+
+
+@router.delete("/{project_id}/members/{user_id}")
+def remove_member(
+    project_id: str,
+    user_id: str,
+    request: Request = None,
+    current_user: dict = Depends(get_current_user),
+) -> dict[str, Any]:
+    if not has_resource_access("project", project_id, current_user, "write"):
+        raise fail(403, "no permission to manage members of this project")
+    store = get_platform_store()
+    store.remove_project_member(project_id, user_id)
+    store.record_audit(
+        action="project.member.remove",
+        actor_id=_actor(request) if request else None,
+        target_type="project.member",
+        target_id=project_id,
+        detail=f"user_id={user_id}",
+    )
+    return ok(None)

backend/app/modules/resource/__init__.py

@@ -0,0 +1 @@
+"""Resource access control list (ACL) module."""

backend/app/modules/resource/router.py

@@ -0,0 +1,41 @@
+from __future__ import annotations
+
+from fastapi import APIRouter, Body, Request
+from typing import Any
+
+from app.api.v1.endpoints.platform import ok, fail
+from app.db.platform_store import get_platform_store
+
+router = APIRouter(prefix="/resources", tags=["resource"])
+
+
+def _actor(request: Request) -> str | None:
+    auth = request.headers.get("Authorization", "")
+    token = auth.replace("Bearer ", "").strip()
+    return token or None
+
+
+@router.get("/{resource_type}/{resource_id}/acl")
+def get_acl(resource_type: str, resource_id: str) -> dict[str, Any]:
+    """查询资源 ACL，返回按主体分组的权限列表。"""
+    return ok(get_platform_store().resource_acl(resource_type, resource_id))
+
+
+@router.put("/{resource_type}/{resource_id}/acl")
+def set_acl(
+    resource_type: str,
+    resource_id: str,
+    payload: dict[str, Any] = Body(...),
+    request: Request = None,
+) -> dict[str, Any]:
+    """设置资源 ACL，body: { entries: [{ subject_type, subject_id, permissions: [] }] }"""
+    entries = payload.get("entries") or []
+    result = get_platform_store().set_resource_acl(resource_type, resource_id, entries)
+    get_platform_store().record_audit(
+        action="resource.acl.set",
+        actor_id=_actor(request) if request else None,
+        target_type=resource_type,
+        target_id=resource_id,
+        detail=f"entries={len(entries)}",
+    )
+    return ok(result)

backend/app/modules/retention/router.py

@@ -0,0 +1,75 @@
+from __future__ import annotations
+
+from fastapi import APIRouter, Body, Request
+from typing import Any
+
+from app.api.v1.endpoints.platform import ok, fail
+from app.db.platform_store import get_platform_store
+
+router = APIRouter(prefix="/retention-policies", tags=["retention"])
+
+
+def _actor(request: Request) -> str | None:
+    auth = request.headers.get("Authorization", "")
+    token = auth.replace("Bearer ", "").strip()
+    return token or None
+
+
+@router.get("")
+def list_policies() -> dict[str, Any]:
+    return ok(get_platform_store().retention_policies())
+
+
+@router.post("")
+def create_policy(payload: dict[str, Any] = Body(...), request: Request = None) -> dict[str, Any]:
+    if not payload.get("name"):
+        raise fail(400, "name 必填")
+    policy = get_platform_store().create_retention_policy(payload)
+    get_platform_store().record_audit(
+        action="retention.create",
+        actor_id=_actor(request) if request else None,
+        target_type="retention_policy",
+        target_id=policy["id"],
+        detail=f"name={policy.get('name')}",
+    )
+    return ok(policy)
+
+
+@router.get("/{policy_id}")
+def get_policy(policy_id: str) -> dict[str, Any]:
+    try:
+        return ok(get_platform_store().retention_policy(policy_id))
+    except KeyError:
+        raise fail(404, "retention policy not found")
+
+
+@router.put("/{policy_id}")
+def update_policy(
+    policy_id: str, payload: dict[str, Any] = Body(...), request: Request = None
+) -> dict[str, Any]:
+    store = get_platform_store()
+    try:
+        policy = store.update_retention_policy(policy_id, payload)
+    except KeyError:
+        raise fail(404, "retention policy not found")
+    store.record_audit(
+        action="retention.update",
+        actor_id=_actor(request) if request else None,
+        target_type="retention_policy",
+        target_id=policy_id,
+        detail=f"fields={','.join(payload.keys())}",
+    )
+    return ok(policy)
+
+
+@router.delete("/{policy_id}")
+def delete_policy(policy_id: str, request: Request = None) -> dict[str, Any]:
+    store = get_platform_store()
+    store.delete_retention_policy(policy_id)
+    store.record_audit(
+        action="retention.delete",
+        actor_id=_actor(request) if request else None,
+        target_type="retention_policy",
+        target_id=policy_id,
+    )
+    return ok({"deleted": policy_id})

backend/app/modules/system/router.py

@@ -0,0 +1,115 @@
+from __future__ import annotations
+
+from fastapi import APIRouter, Body, Query, Request
+from fastapi.responses import StreamingResponse
+
+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）。"""
+    return {"code": 0, "message": "ok", "data": {"codes": ALL_PERMISSIONS}}
+
+
+@router.get("/permissions")
+def permissions_overview() -> dict:
+    """返回权限码清单与角色定义。"""
+    store = get_platform_store()
+    return {
+        "code": 0,
+        "message": "ok",
+        "data": {"codes": ALL_PERMISSIONS, "roles": store.roles()},
+    }
+
+
+@router.get("/audit-logs")
+def audit_logs(
+    tenant_id: str | None = Query(default=None, description="租户 ID"),
+    project_id: str | None = Query(default=None, description="项目 ID"),
+    actor_id: str | None = Query(default=None, description="操作人 ID"),
+    action: str | None = Query(default=None, description="动作类型"),
+    target_type: str | None = Query(default=None, description="目标类型"),
+    start_time: str | None = Query(default=None, description="ISO8601 起始时间"),
+    end_time: str | None = Query(default=None, description="ISO8601 结束时间"),
+    limit: int = Query(default=50, ge=1, le=200),
+    offset: int = Query(default=0, ge=0),
+) -> dict:
+    """审计日志查询：按租户/项目/操作人/动作/目标类型/时间范围分页过滤。"""
+    store = get_platform_store()
+    result = store.audit_logs(
+        tenant_id=tenant_id,
+        project_id=project_id,
+        actor_id=actor_id,
+        action=action,
+        target_type=target_type,
+        start_time=start_time,
+        end_time=end_time,
+        limit=limit,
+        offset=offset,
+    )
+    return {"code": 0, "message": "ok", "data": result}
+
+
+@router.get("/audit-logs/export")
+def audit_logs_export(
+    tenant_id: str | None = Query(default=None, description="租户 ID"),
+    project_id: str | None = Query(default=None, description="项目 ID"),
+    actor_id: str | None = Query(default=None, description="操作人 ID"),
+    action: str | None = Query(default=None, description="动作类型"),
+    target_type: str | None = Query(default=None, description="目标类型"),
+    start_time: str | None = Query(default=None, description="ISO8601 起始时间"),
+    end_time: str | None = Query(default=None, description="ISO8601 结束时间"),
+) -> StreamingResponse:
+    """审计日志导出：返回 CSV 流，与应用查询相同的过滤条件。"""
+    store = get_platform_store()
+    result = store.audit_logs(
+        tenant_id=tenant_id,
+        project_id=project_id,
+        actor_id=actor_id,
+        action=action,
+        target_type=target_type,
+        start_time=start_time,
+        end_time=end_time,
+        limit=10000,
+        offset=0,
+    )
+    items = result["items"]
+    columns = ["time", "tenant_id", "project_id", "actor_id", "action", "target_type", "target_id", "detail", "client_ip"]
+    header = ",".join(columns) + "\n"
+
+    def iter_rows():
+        yield header
+        for row in items:
+            yield ",".join(f'"{str(row.get(c, "") or "")}"' for c in columns) + "\n"
+
+    return StreamingResponse(
+        iter_rows(),
+        media_type="text/csv",
+        headers={"Content-Disposition": "attachment; filename=audit_logs.csv"},
+    )

backend/app/modules/tenant/router.py

@@ -0,0 +1,116 @@
+from __future__ import annotations
+
+from fastapi import APIRouter, Body, Request
+from typing import Any
+
+from app.api.v1.endpoints.platform import ok, fail
+from app.db.platform_store import get_platform_store
+
+router = APIRouter(prefix="/tenants", tags=["tenant"])
+
+
+def _actor(request: Request) -> str | None:
+    auth = request.headers.get("Authorization", "")
+    token = auth.replace("Bearer ", "").strip()
+    return token or None
+
+
+@router.get("")
+def list_tenants() -> dict[str, Any]:
+    return ok(get_platform_store().tenants())
+
+
+@router.post("")
+def create_tenant(payload: dict[str, Any] = Body(...), request: Request = None) -> dict[str, Any]:
+    store = get_platform_store()
+    try:
+        tenant = store.create_tenant(payload)
+    except KeyError as e:
+        raise fail(400, f"missing field: {e}")
+    store.record_audit(
+        action="tenant.create",
+        actor_id=_actor(request) if request else None,
+        target_type="tenant",
+        target_id=tenant["id"],
+        tenant_id=tenant["id"],
+        detail=f"name={tenant.get('name')}",
+    )
+    return ok(tenant)
+
+
+@router.get("/{tenant_id}")
+def get_tenant(tenant_id: str) -> dict[str, Any]:
+    try:
+        return ok(get_platform_store().tenant(tenant_id))
+    except KeyError:
+        raise fail(404, "tenant not found")
+
+
+@router.put("/{tenant_id}")
+def update_tenant(tenant_id: str, payload: dict[str, Any] = Body(...), request: Request = None) -> dict[str, Any]:
+    store = get_platform_store()
+    try:
+        tenant = store.update_tenant(tenant_id, payload)
+    except KeyError:
+        raise fail(404, "tenant not found")
+    store.record_audit(
+        action="tenant.update",
+        actor_id=_actor(request) if request else None,
+        target_type="tenant",
+        target_id=tenant_id,
+        tenant_id=tenant_id,
+        detail=f"fields={','.join(payload.keys())}",
+    )
+    return ok(tenant)
+
+
+@router.put("/{tenant_id}/quota")
+def set_quota(tenant_id: str, payload: dict[str, Any] = Body(...), request: Request = None) -> dict[str, Any]:
+    store = get_platform_store()
+    try:
+        tenant = store.set_tenant_quota(tenant_id, payload.get("quota", {}))
+    except KeyError:
+        raise fail(404, "tenant not found")
+    store.record_audit(
+        action="tenant.quota.set",
+        actor_id=_actor(request) if request else None,
+        target_type="tenant",
+        target_id=tenant_id,
+        tenant_id=tenant_id,
+    )
+    return ok(tenant)
+
+
+@router.put("/{tenant_id}/retention-policy")
+def set_retention(tenant_id: str, payload: dict[str, Any] = Body(...), request: Request = None) -> dict[str, Any]:
+    store = get_platform_store()
+    try:
+        tenant = store.set_tenant_retention(tenant_id, payload.get("retention_policy_id"))
+    except KeyError:
+        raise fail(404, "tenant not found")
+    store.record_audit(
+        action="tenant.retention.set",
+        actor_id=_actor(request) if request else None,
+        target_type="tenant",
+        target_id=tenant_id,
+        tenant_id=tenant_id,
+    )
+    return ok(tenant)
+
+
+@router.delete("/{tenant_id}")
+def delete_tenant(tenant_id: str, request: Request = None) -> dict[str, Any]:
+    store = get_platform_store()
+    try:
+        tenant = store.delete_tenant(tenant_id)
+    except KeyError:
+        raise fail(404, "tenant not found")
+    store.record_audit(
+        action="tenant.delete",
+        actor_id=_actor(request) if request else None,
+        target_type="tenant",
+        target_id=tenant_id,
+        tenant_id=tenant_id,
+        detail=f"name={tenant.get('name')}",
+    )
+    return ok(tenant)

backend/app/schemas/data_process.py

@@ -109,6 +109,24 @@ class DataProcessStatus(StrEnum):
     stopped = "stopped"
 
 
+class DataProcessWorkflowStep(StrEnum):
+    create = "create"
+    model = "model"
+    upload = "upload"
+    preview = "preview"
+    generate = "generate"
+    results = "results"
+
+
+class DataProcessPreviewStatus(StrEnum):
+    idle = "idle"
+    queued = "queued"
+    running = "running"
+    completed = "completed"
+    failed = "failed"
+    cancelled = "cancelled"
+
+
 class ProcessType(StrEnum):
     structured = "structured"
     unstructured = "unstructured"
@@ -164,6 +182,14 @@ class DataProcessTaskUpdate(BaseModel):
         return self
 
 
+class DataProcessWorkflowStepUpdate(BaseModel):
+    """仅保存创建向导位置，不修改配置或使下游产物失效。"""
+
+    model_config = ConfigDict(extra="forbid")
+
+    workflow_step: DataProcessWorkflowStep
+
+
 class DataProcessRegenerateRequest(BaseModel):
     """以一份完整配置准备任务重新生成。
 
@@ -194,6 +220,19 @@ class DataProcessRegenerateRequest(BaseModel):
         return self
 
 
+class DataProcessRepeatRequest(BaseModel):
+    """按已确认任务的完整快照创建一批独立的新生成结果。"""
+
+    model_config = ConfigDict(extra="forbid")
+
+    expected_updated_at: str = Field(min_length=1)
+    request_id: str = Field(
+        min_length=8,
+        max_length=80,
+        pattern=r"^[A-Za-z0-9_-]+$",
+    )
+
+
 class PreviewBuildRequest(BaseModel):
     model_config = ConfigDict(extra="forbid")
 
@@ -288,6 +327,32 @@ class ResultUpdate(BaseModel):
     expected_updated_at: str | None = None
 
 
+class ResultRegenerateRequest(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
+    expected_updated_at: str = Field(min_length=1, max_length=100)
+
+
+class ResultBatchRegenerateItem(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
+    result_id: str = Field(min_length=1, max_length=100)
+    expected_updated_at: str = Field(min_length=1, max_length=100)
+
+
+class ResultBatchRegenerateRequest(BaseModel):
+    model_config = ConfigDict(extra="forbid")
+
+    items: list[ResultBatchRegenerateItem] = Field(min_length=1, max_length=100)
+
+    @model_validator(mode="after")
+    def validate_unique_results(self) -> "ResultBatchRegenerateRequest":
+        result_ids = [item.result_id for item in self.items]
+        if len(result_ids) != len(set(result_ids)):
+            raise ValueError("result_id values must be unique")
+        return self
+
+
 class DatasetSplit(BaseModel):
     model_config = ConfigDict(extra="forbid")
 

backend/pyproject.toml

@@ -10,6 +10,7 @@ dependencies = [
   "pydantic>=2.7.0",
   "sqlalchemy>=2.0.30",
   "psycopg[binary]>=3.2.1",
+  "psycopg-pool>=3.2.1",
   "alembic>=1.13.1",
   "redis>=5.0.4",
   "httpx>=0.27.0",

backend/requirements.txt

@@ -4,6 +4,7 @@ python-multipart>=0.0.9
 pydantic>=2.7.0
 sqlalchemy>=2.0.30
 psycopg[binary]>=3.2.1
+psycopg-pool>=3.2.1
 alembic>=1.13.1
 redis>=5.0.4
 httpx>=0.27.0
@@ -18,3 +19,7 @@ llama-index-core==0.14.23
 llama-index-embeddings-huggingface==0.6.1
 docling==2.115.0
 tiktoken>=0.7.0
+
+# 测试与代码检查
+pytest>=8.2.0
+ruff>=0.5.0

backend/tests/test_compare_inference_async.py

@@ -0,0 +1,276 @@
+"""
+模型推理异步加载改造的单元测试。
+
+覆盖：
+- model_compare_load：异步派发，立即返回 starting + 节点信息（不等待加载完成）
+- model_compare_delete：先删记录，卸载失败也不阻塞删除
+- reconcile_inference_loads：starting -> ready/error/idle/不可达的状态迁移与封顶
+- _unload_from_compute_node：任务感知，只命中记录中的节点
+"""
+
+from __future__ import annotations
+
+import asyncio
+from types import SimpleNamespace
+from typing import Any
+
+from app.api.v1.endpoints.platform import model_compare_delete, model_compare_load
+import app.api.v1.endpoints.platform as platform
+from app.modules.compute_gateway.client import ComputeNodeClient
+from app.modules.compute_gateway.sync import MAX_STARTING_ATTEMPTS, reconcile_inference_loads
+
+
+class FakeInferenceStore:
+    """内存 store，仅实现推理加载/对账用到的接口。"""
+
+    def __init__(self, tasks: list[dict[str, Any]] | None = None, nodes: list[dict[str, Any]] | None = None) -> None:
+        self._tasks: dict[str, dict[str, Any]] = {t["id"]: dict(t) for t in (tasks or [])}
+        self._nodes = nodes or []
+        self._inference_nodes: set[str] = set()
+
+    def compare_task(self, task_id: str) -> dict[str, Any]:
+        if task_id not in self._tasks:
+            raise KeyError(task_id)
+        return dict(self._tasks[task_id])
+
+    def compare_tasks(self) -> list[dict[str, Any]]:
+        return [dict(t) for t in self._tasks.values()]
+
+    def update_compare_task(self, task_id: str, payload: dict[str, Any]) -> dict[str, Any]:
+        current = self._tasks[task_id]
+        merged = {**current, **payload, "id": task_id}
+        self._tasks[task_id] = merged
+        return dict(merged)
+
+    def delete_compare_task(self, task_id: str) -> None:
+        self._tasks.pop(task_id, None)
+
+    def compute_nodes(self) -> list[dict[str, Any]]:
+        return [dict(n) for n in self._nodes]
+
+    def model(self, model_id: str) -> dict[str, Any]:
+        raise KeyError(model_id)
+
+    def trained_models(self) -> list[dict[str, Any]]:
+        return []
+
+    def mark_inference_loaded(self, node_id: str) -> None:
+        self._inference_nodes.add(node_id)
+
+    def mark_inference_unloaded(self, node_id: str) -> None:
+        self._inference_nodes.discard(node_id)
+
+    def is_inference_loaded(self, node_id: str) -> bool:
+        return node_id in self._inference_nodes
+
+
+def _node(node_id: str, code: str = "") -> dict[str, Any]:
+    return {
+        "id": node_id,
+        "code": code or node_id,
+        "name": code or node_id,
+        "api_base_url": f"http://{code or node_id}:19100",
+        "enabled": True,
+        "scheduler_status": "online",
+    }
+
+
+def _task(task_id: str, *, node_id: str | None = None, load_status: dict[str, Any] | None = None) -> dict[str, Any]:
+    return {
+        "id": task_id,
+        "name": f"task-{task_id}",
+        "status": "pending",
+        "models": [
+            {"model_id": "m_1", "model_name": "qwen", "model_path": "/models/qwen", "node_id": node_id}
+        ],
+        "load_status": load_status or {"loaded_models": []},
+    }
+
+
+async def _fake_inference_load(self, payload: dict[str, Any]) -> dict[str, Any]:
+    return {"loaded": False, "status": "loading", "request_id": "req-1"}
+
+
+async def _fake_inference_unload(self) -> dict[str, Any]:
+    return {"unloaded": True, "status": "idle"}
+
+
+def _patch_store(monkeypatch, store: FakeInferenceStore) -> None:
+    monkeypatch.setattr(platform, "get_platform_store", lambda: store)
+    monkeypatch.setattr(platform, "get_settings", lambda: SimpleNamespace(compute_mode="real"))
+
+
+def test_select_eval_node_prefers_model_node(monkeypatch) -> None:
+    from app.api.v1.endpoints.platform import _select_eval_node
+
+    store = FakeInferenceStore(nodes=[_node("n1"), _node("n2")])
+    # 指定模型所在节点时优先返回该节点
+    assert _select_eval_node(store, "n2")["id"] == "n2"
+    # 无指定节点时回退到第一个在线节点
+    assert _select_eval_node(store, None)["id"] == "n1"
+
+
+def test_select_eval_node_returns_none_when_model_node_offline(monkeypatch) -> None:
+    from app.api.v1.endpoints.platform import _select_eval_node
+
+    nodes = [_node("n1"), _node("n2")]
+    nodes[1]["enabled"] = False
+    store = FakeInferenceStore(nodes=nodes)
+    # 模型所在节点不可用 → 明确失败，不派发到其它节点
+    assert _select_eval_node(store, "n2") is None
+    # 无指定节点时仍回退第一个在线节点
+    assert _select_eval_node(store, None)["id"] == "n1"
+
+
+def test_model_compare_load_dispatches_and_returns_starting(monkeypatch) -> None:
+    store = FakeInferenceStore(tasks=[_task("t1", node_id="n1")], nodes=[_node("n1")])
+    _patch_store(monkeypatch, store)
+    monkeypatch.setattr(ComputeNodeClient, "inference_load", _fake_inference_load)
+
+    result = asyncio.run(model_compare_load("t1"))
+    assert result["code"] == 0
+    updated = result["data"]
+    assert updated["status"] == "starting"
+    items = updated["load_status"]["loaded_models"]
+    assert items[0]["status"] == "starting"
+    assert items[0]["node_id"] == "n1"
+    assert "n1" in store._inference_nodes
+
+
+def test_model_compare_load_marks_error_when_all_nodes_fail(monkeypatch) -> None:
+    store = FakeInferenceStore(tasks=[_task("t1", node_id="n1")], nodes=[_node("n1")])
+    _patch_store(monkeypatch, store)
+
+    async def _raise(self, payload: dict[str, Any]) -> dict[str, Any]:
+        raise RuntimeError("conn refused")
+
+    monkeypatch.setattr(ComputeNodeClient, "inference_load", _raise)
+
+    result = asyncio.run(model_compare_load("t1"))
+    updated = result["data"]
+    assert updated["status"] == "failed"
+    assert updated["load_status"]["loaded_models"][0]["status"] == "error"
+    assert "conn refused" in updated["load_status"]["loaded_models"][0]["error"]
+
+
+def test_model_compare_delete_removes_record_even_if_unload_raises(monkeypatch) -> None:
+    task = _task(
+        "t1",
+        node_id="n1",
+        load_status={"loaded_models": [{"model_id": "m_1", "status": "ready", "node_id": "n1"}]},
+    )
+    store = FakeInferenceStore(tasks=[task], nodes=[_node("n1")])
+    _patch_store(monkeypatch, store)
+
+    async def _raise(self) -> dict[str, Any]:
+        raise RuntimeError("unload boom")
+
+    monkeypatch.setattr(ComputeNodeClient, "inference_unload", _raise)
+
+    result = asyncio.run(model_compare_delete("t1"))
+    assert result["data"] == {"deleted": "t1"}
+    assert "t1" not in store._tasks
+    # finally 中仍清掉了节点标记
+    assert "n1" not in store._inference_nodes
+
+
+def test_unload_from_compute_node_only_hits_recorded_node(monkeypatch) -> None:
+    task = _task(
+        "t1",
+        load_status={"loaded_models": [{"model_id": "m_1", "status": "ready", "node_id": "n1"}]},
+    )
+    store = FakeInferenceStore(tasks=[task], nodes=[_node("n1"), _node("n2")])
+    _patch_store(monkeypatch, store)
+    monkeypatch.setattr(ComputeNodeClient, "inference_unload", _fake_inference_unload)
+
+    from app.api.v1.endpoints.platform import _unload_from_compute_node
+
+    result = asyncio.run(_unload_from_compute_node(store, task=task))
+    assert result["unloaded"] is True
+    # 只命中任务记录中的节点 n1，n2 未被卸载
+    assert [r["node_id"] for r in result["nodes"]] == ["n1"]
+    assert "n1" not in store._inference_nodes
+
+
+async def _status_ready(self) -> dict[str, Any]:
+    return {"loaded": True, "status": "ready", "model_name": "qwen"}
+
+
+def test_reconcile_transitions_starting_to_ready(monkeypatch) -> None:
+    task = _task(
+        "t1",
+        node_id="n1",
+        load_status={"loaded_models": [{"model_id": "m_1", "status": "starting", "node_id": "n1"}]},
+    )
+    store = FakeInferenceStore(tasks=[task], nodes=[_node("n1")])
+    monkeypatch.setattr(ComputeNodeClient, "inference_status", _status_ready)
+
+    reconciled = asyncio.run(reconcile_inference_loads(store))
+    assert reconciled == [{"task_id": "t1", "status": "loaded"}]
+    updated = store._tasks["t1"]
+    assert updated["status"] == "loaded"
+    assert updated["load_status"]["loaded_models"][0]["status"] == "ready"
+    assert "n1" in store._inference_nodes
+
+
+def test_reconcile_transitions_to_error_and_failed(monkeypatch) -> None:
+    async def _status_error(self) -> dict[str, Any]:
+        return {"loaded": False, "status": "error", "error": "CUDA out of memory"}
+
+    task = _task(
+        "t1",
+        node_id="n1",
+        load_status={"loaded_models": [{"model_id": "m_1", "status": "starting", "node_id": "n1"}]},
+    )
+    store = FakeInferenceStore(tasks=[task], nodes=[_node("n1")])
+    monkeypatch.setattr(ComputeNodeClient, "inference_status", _status_error)
+
+    reconciled = asyncio.run(reconcile_inference_loads(store))
+    assert reconciled == [{"task_id": "t1", "status": "failed"}]
+    item = store._tasks["t1"]["load_status"]["loaded_models"][0]
+    assert item["status"] == "error"
+    assert "CUDA out of memory" in item["error"]
+    assert "n1" not in store._inference_nodes
+
+
+def test_reconcile_idle_marks_model_disappeared(monkeypatch) -> None:
+    async def _status_idle(self) -> dict[str, Any]:
+        return {"loaded": False, "status": "idle"}
+
+    task = _task(
+        "t1",
+        node_id="n1",
+        load_status={"loaded_models": [{"model_id": "m_1", "status": "starting", "node_id": "n1"}]},
+    )
+    store = FakeInferenceStore(tasks=[task], nodes=[_node("n1")])
+    monkeypatch.setattr(ComputeNodeClient, "inference_status", _status_idle)
+
+    asyncio.run(reconcile_inference_loads(store))
+    item = store._tasks["t1"]["load_status"]["loaded_models"][0]
+    assert item["status"] == "error"
+    assert "disappeared" in item["error"]
+    assert store._tasks["t1"]["status"] == "failed"
+
+
+def test_reconcile_unreachable_node_flips_to_error_after_cap(monkeypatch) -> None:
+    async def _raise(self) -> dict[str, Any]:
+        raise RuntimeError("conn refused")
+
+    task = _task(
+        "t1",
+        node_id="n1",
+        load_status={"loaded_models": [{"model_id": "m_1", "status": "starting", "node_id": "n1"}]},
+    )
+    store = FakeInferenceStore(tasks=[task], nodes=[_node("n1")])
+    monkeypatch.setattr(ComputeNodeClient, "inference_status", _raise)
+
+    # 每次轮询前重置节流时间戳，逐次推进 load_attempts 到封顶
+    for _ in range(MAX_STARTING_ATTEMPTS):
+        item = store._tasks["t1"]["load_status"]["loaded_models"][0]
+        item["last_polled_at"] = 0
+        asyncio.run(reconcile_inference_loads(store))
+
+    item = store._tasks["t1"]["load_status"]["loaded_models"][0]
+    assert item["status"] == "error"
+    assert "unreachable" in item["error"]
+    assert store._tasks["t1"]["status"] == "failed"

backend/tests/test_data_process_algorithms.py

@@ -5,6 +5,7 @@ import json
 import xml.etree.ElementTree as ET
 import zipfile
 from datetime import datetime
+from decimal import Decimal
 
 import pytest
 from docx import Document
@@ -29,11 +30,13 @@ from app.modules.data_process.algorithms import (
     normalize_text,
     parse_text_content,
     preprocess_structured_records,
+    preprocess_structured_records_with_lineage,
     record_fingerprint,
     remove_document_noise,
     score_quality,
     stable_split,
     stable_split_assignments,
+    structured_json_dumps,
 )
 
 
@@ -194,6 +197,75 @@ def test_parse_utf8_json_jsonl_csv_markdown_and_txt() -> None:
     assert parsed_txt.text == "普通文本"
 
 
+def test_structured_text_record_locators_preserve_logical_source_positions() -> None:
+    root_json = parse_text_content('{"id":1}', filename="root.json")
+    assert root_json.record_locators == (
+        {
+            "kind": "json",
+            "record_index": 1,
+            "json_pointer": "",
+            "source_start": 0,
+            "source_end": 8,
+            "start_line": 1,
+            "end_line": 1,
+        },
+    )
+
+    wrapped_json = parse_text_content(
+        '{"records":[{"id":1},{"id":1}]}',
+        filename="wrapped.json",
+    )
+    assert [locator["json_pointer"] for locator in wrapped_json.record_locators] == [
+        "/records/0",
+        "/records/1",
+    ]
+
+    parsed_jsonl = parse_text_content(
+        '{"id":1}\r\n\r\n{"id":1}',
+        filename="records.jsonl",
+    )
+    assert [
+        (locator["record_index"], locator["start_line"], locator["end_line"])
+        for locator in parsed_jsonl.record_locators
+    ] == [(1, 1, 1), (2, 3, 3)]
+    assert [
+        parsed_jsonl.text[locator["source_start"] : locator["source_end"]]
+        for locator in parsed_jsonl.record_locators
+    ] == ['{"id":1}', '{"id":1}']
+
+    parsed_csv = parse_text_content(
+        'id,note\r\n1,"hello\r\nworld"\r\n\r\n2,plain',
+        filename="records.csv",
+    )
+    assert [
+        (locator["record_index"], locator["start_line"], locator["end_line"])
+        for locator in parsed_csv.record_locators
+    ] == [(1, 2, 3), (2, 5, 5)]
+    assert [
+        parsed_csv.text[locator["source_start"] : locator["source_end"]]
+        for locator in parsed_csv.record_locators
+    ] == ['1,"hello\nworld"', "2,plain"]
+
+
+def test_structured_preprocess_lineage_survives_column_cleanup_and_row_removal() -> None:
+    processed = preprocess_structured_records_with_lineage(
+        [
+            {"id": "A", "value": "first", "empty": ""},
+            {"id": "", "value": "invalid", "empty": ""},
+            {"id": "A", "value": "duplicate identity", "empty": ""},
+            {"id": "B", "value": "second", "empty": ""},
+        ],
+        ["clean_invalid", "deduplicate"],
+    )
+    assert [entry.source_index for entry in processed] == [0, 1, 2, 3]
+    assert [entry.record for entry in processed] == [
+        {"id": "A", "value": "first"},
+        {"id": "", "value": "invalid"},
+        {"id": "A", "value": "duplicate identity"},
+        {"id": "B", "value": "second"},
+    ]
+
+
 def test_parse_pdf_docx_xlsx_and_pptx() -> None:
     parsed_pdf = parse_text_content(_minimal_pdf(), filename="manual.pdf")
     assert parsed_pdf.format == "pdf"
@@ -220,6 +292,24 @@ def test_parse_pdf_docx_xlsx_and_pptx() -> None:
         {"name": "Alice", "score": 95, "created_at": "2026-07-23T10:30:00"},
         {"name": "Bob", "score": 88, "created_at": "2026-07-24T09:00:00"},
     )
+    assert parsed_xlsx.record_locators == (
+        {
+            "kind": "xlsx",
+            "record_index": 1,
+            "sheet_index": 0,
+            "sheet_name": "数据",
+            "row_number": 2,
+            "sheet_record_index": 0,
+        },
+        {
+            "kind": "xlsx",
+            "record_index": 2,
+            "sheet_index": 0,
+            "sheet_name": "数据",
+            "row_number": 3,
+            "sheet_record_index": 1,
+        },
+    )
     assert json.loads(parsed_xlsx.text.splitlines()[0]) == parsed_xlsx.records[0]
 
     parsed_pptx = parse_text_content(_pptx_bytes(), filename="slides.pptx")
@@ -228,6 +318,44 @@ def test_parse_pdf_docx_xlsx_and_pptx() -> None:
     assert parsed_pptx.records == ()
 
 
+def test_xlsx_record_locators_distinguish_sheets_rows_and_duplicate_records() -> None:
+    workbook = Workbook()
+    first = workbook.active
+    first.title = "甲表"
+    first.append(["说明"])
+    first.append([])
+    first.append(["id", "value"])
+    first.append([1, "same"])
+    first.append([1, "same"])
+    second = workbook.create_sheet("乙表")
+    second.append(["id", "value"])
+    second.append([1, "same"])
+    output = io.BytesIO()
+    workbook.save(output)
+    workbook.close()
+
+    parsed = parse_text_content(output.getvalue(), filename="duplicate.xlsx")
+    assert parsed.records == (
+        {"id": 1, "value": "same"},
+        {"id": 1, "value": "same"},
+        {"id": 1, "value": "same"},
+    )
+    assert [
+        (
+            locator["record_index"],
+            locator["sheet_index"],
+            locator["sheet_name"],
+            locator["row_number"],
+            locator["sheet_record_index"],
+        )
+        for locator in parsed.record_locators
+    ] == [
+        (1, 0, "甲表", 4, 0),
+        (2, 0, "甲表", 5, 1),
+        (3, 1, "乙表", 2, 0),
+    ]
+
+
 def test_pdf_document_noise_removes_headers_page_numbers_and_toc_safely() -> None:
     pages = _pdf_page_texts(
         """
@@ -568,7 +696,130 @@ def test_extract_json_scalar_and_nested_values_are_stable() -> None:
         json.dumps({"items": [{"text": "  内容  "}], "ignored": 1}, ensure_ascii=False),
         "json",
     )
-    assert result == [{"text": "内容"}]
+    assert result == [{"items": [{"text": "  内容  "}], "ignored": 1}]
+
+    assert extract_structured_records(
+        '{"items":[{"text":"  内容  "}],"total":1}',
+        "json",
+    ) == [{"text": "  内容  "}]
+
+
+def test_json_parsing_is_strict_and_preserves_field_values() -> None:
+    source = '{"code":"００１","text":"  内容  ","quote":"＂"}'
+    parsed = parse_text_content(source, filename="records.json")
+    assert parsed.text == source
+    assert parsed.records == (
+        {"code": "００１", "text": "  内容  ", "quote": "＂"},
+    )
+
+    invalid_values = (
+        '{"id":1,"id":2}',
+        '{"nested":{"id":1,"id":2}}',
+        '{"value":NaN}',
+        '{"value":Infinity}',
+        '{"value":-Infinity}',
+        '{"value":"bad\x00control"}',
+    )
+    for invalid in invalid_values:
+        with pytest.raises(ValueError):
+            parse_text_content(invalid, filename="invalid.json")
+
+    with pytest.raises(ValueError):
+        parse_text_content("｛\"id\":1｝", filename="invalid.json")
+    with pytest.raises(ValueError, match="nesting exceeds"):
+        parse_text_content("[" * 65 + "0" + "]" * 65, filename="deep.json")
+
+
+def test_jsonl_uses_the_same_strict_lossless_number_and_text_contract() -> None:
+    source = (
+        '  {"code":"００１","text":"  内容  ",'
+        '"value":0.123456789012345678901234567890}\r\n\r\n'
+        '{"id":2}\r\n'
+    )
+    parsed = parse_text_content(source, filename="records.jsonl")
+    assert parsed.text == source
+    assert parsed.records[0] == {
+        "code": "００１",
+        "text": "  内容  ",
+        "value": Decimal("0.123456789012345678901234567890"),
+    }
+    assert [
+        source[locator["source_start"] : locator["source_end"]]
+        for locator in parsed.record_locators
+    ] == [
+        (
+            '{"code":"００１","text":"  内容  ",'
+            '"value":0.123456789012345678901234567890}'
+        ),
+        '{"id":2}',
+    ]
+    assert [locator["start_line"] for locator in parsed.record_locators] == [1, 3]
+
+    for invalid in ('{"id":1,"id":2}', '{"value":NaN}'):
+        with pytest.raises(ValueError, match="invalid JSONL at line 1"):
+            parse_text_content(invalid, filename="invalid.jsonl")
+
+
+def test_json_record_contract_avoids_business_field_collisions() -> None:
+    assert extract_structured_records('[{"id":1},{"id":2}]', "json") == [
+        {"id": 1},
+        {"id": 2},
+    ]
+    assert extract_structured_records('{"id":1,"data":[{"id":2}]}', "json") == [
+        {"id": 1, "data": [{"id": 2}]}
+    ]
+    assert extract_structured_records(
+        '{"records":[{"id":1}],"data":[{"id":2}]}',
+        "json",
+    ) == [{"records": [{"id": 1}], "data": [{"id": 2}]}]
+    assert extract_structured_records(
+        '{"response":{"data":[{"id":1}],"status":"ok"},"success":true,"code":0}',
+        "json",
+    ) == [{"id": 1}]
+    assert extract_structured_records(
+        '{"payload":{"data":[{"id":2}],"total":1}}',
+        "json",
+    ) == [{"id": 2}]
+    assert extract_structured_records('{"records":[],"total":0}', "json") == []
+    # 包装数组中的非对象不是记录集合，整体按一条业务对象保留。
+    assert extract_structured_records('{"data":[1,2]}', "json") == [
+        {"data": [1, 2]}
+    ]
+
+
+def test_json_record_locators_cover_pretty_and_minified_sources() -> None:
+    pretty = (
+        '{\n  "records": [\n    {"id": 1},\n'
+        '    {\n      "id": 2\n    }\n  ],\n  "total": 2\n}'
+    )
+    parsed = parse_text_content(pretty, filename="pretty.json")
+    assert [
+        pretty[locator["source_start"] : locator["source_end"]]
+        for locator in parsed.record_locators
+    ] == ['{"id": 1}', '{\n      "id": 2\n    }']
+    assert [
+        (locator["start_line"], locator["end_line"])
+        for locator in parsed.record_locators
+    ] == [(3, 3), (4, 6)]
+
+    minified = '[{"id":1},{"id":2}]'
+    parsed = parse_text_content(minified, filename="minified.json")
+    assert [
+        minified[locator["source_start"] : locator["source_end"]]
+        for locator in parsed.record_locators
+    ] == ['{"id":1}', '{"id":2}']
+
+
+def test_high_precision_json_numbers_serialize_without_type_or_value_loss() -> None:
+    source = '[{"value":0.123456789012345678901234567890},{"value":1e400}]'
+    parsed = parse_text_content(source, filename="precise.json")
+    assert parsed.records[0]["value"] == Decimal("0.123456789012345678901234567890")
+    assert parsed.records[1]["value"] == Decimal("1e400")
+    assert structured_json_dumps(parsed.records[0]) == (
+        '{"value":0.123456789012345678901234567890}'
+    )
+    assert structured_json_dumps(parsed.records[1]) == '{"value":1E+400}'
+    assert isinstance(parsed.records[0]["value"], Decimal)
 
 
 def test_desensitize_pii_returns_masked_text_and_counts() -> None:
@@ -587,9 +838,20 @@ def test_every_structured_preprocess_option_has_independent_behavior() -> None:
     assert preprocess_structured_records(clean_source, []) == clean_source
     assert preprocess_structured_records(clean_source, ["clean_invalid"]) == [
         {"id": "1", "name": "有效"},
+        {"id": "", "name": "缺少关键字段"},
         {"id": "2", "name": "有效"},
     ]
 
+    hierarchy = [
+        {"id": "1", "parent_id": None, "name": "根节点", "empty": ""},
+        {"id": "2", "parent_id": "1", "name": "子节点", "empty": ""},
+        {"id": "", "parent_id": "", "name": "", "empty": ""},
+    ]
+    assert preprocess_structured_records(hierarchy, ["clean_invalid"]) == [
+        {"id": "1", "parent_id": None, "name": "根节点"},
+        {"id": "2", "parent_id": "1", "name": "子节点"},
+    ]
+
     nested = [{"id": 1, "profile": {"name": "张三", "level": 2}}]
     assert "profile" in preprocess_structured_records(nested, [])[0]
     assert preprocess_structured_records(nested, ["detect_structure"])[0] == {
@@ -601,13 +863,15 @@ def test_every_structured_preprocess_option_has_independent_behavior() -> None:
     duplicates = [
         {"customer_id": "C-1", "value": "first"},
         {"customer_id": "C-1", "value": "updated"},
+        {"customer_id": "C-1", "value": "first"},
         {"customer_id": "", "value": "blank-one"},
         {"customer_id": "", "value": "blank-two"},
     ]
-    assert len(preprocess_structured_records(duplicates, [])) == 4
+    assert len(preprocess_structured_records(duplicates, [])) == 5
     deduplicated = preprocess_structured_records(duplicates, ["deduplicate"])
     assert [record["value"] for record in deduplicated] == [
         "first",
+        "updated",
         "blank-one",
         "blank-two",
     ]
@@ -660,6 +924,41 @@ def test_structured_desensitization_counts_and_document_helpers() -> None:
     )
 
 
+def test_structured_desensitization_only_masks_explicit_person_name_fields() -> None:
+    masked, counts = desensitize_structured_record(
+        {
+            "table_name": "customer_profile",
+            "chinese_name": "zh_CN",
+            "english_name": "en_US",
+            "product_name": "智能助手",
+            "metadata.table_name": "customer_archive",
+            "name": "张三",
+            "contact_name": "李四",
+            "姓名": "王五",
+            "profile.name": "赵六",
+        }
+    )
+
+    assert masked == {
+        "table_name": "customer_profile",
+        "chinese_name": "zh_CN",
+        "english_name": "en_US",
+        "product_name": "智能助手",
+        "metadata.table_name": "customer_archive",
+        "name": "[NAME]",
+        "contact_name": "[NAME]",
+        "姓名": "[NAME]",
+        "profile.name": "[NAME]",
+    }
+    assert counts == {
+        "email": 0,
+        "phone": 0,
+        "id_card": 0,
+        "name": 4,
+        "total": 4,
+    }
+
+
 def test_quality_scoring_covers_all_dimensions_and_duplicates() -> None:
     valid = {
         "instruction": "如何修改收货地址？",

backend/tests/test_data_process_generation.py

@@ -88,6 +88,344 @@ def test_generate_model_records_uses_prompt_auth_and_stable_split() -> None:
     assert progress_updates == [(1, 1)]
 
 
+def test_minimax_m3_uses_split_reasoning_and_completion_token_budget() -> None:
+    requests: list[dict[str, object]] = []
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        payload = json.loads(request.content)
+        requests.append(payload)
+        return httpx.Response(
+            200,
+            json={
+                "choices": [{
+                    "finish_reason": "stop",
+                    "message": {
+                        "reasoning_content": "模型内部思考不应混入业务 JSON",
+                        "content": json.dumps({
+                            "items": [{
+                                "instruction": "申请编号有什么作用？",
+                                "reasoning": "来源说明它用于标识报销申请。",
+                                "answer": "它用于唯一标识一笔报销申请。",
+                            }],
+                        }, ensure_ascii=False),
+                    },
+                }],
+                "output_sensitive": False,
+                "base_resp": {"status_code": 0, "status_msg": ""},
+            },
+        )
+
+    records = generate_model_records(
+        [{"id": "preview-minimax", "edited_content": "申请编号用于标识报销申请。"}],
+        model={
+            "name": "MiniMax",
+            "online_model_name": "MiniMax-M3",
+            "api_url": "https://api.minimaxi.com/v1",
+        },
+        config={
+            "output_type": "reasoning",
+            "json_mode": True,
+            "max_tokens": 1024,
+            "generation_retries": 0,
+        },
+        task_id="task-minimax",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=httpx.Client(transport=httpx.MockTransport(handler)),
+    )
+
+    assert records[0]["status"] == "valid"
+    assert len(requests) == 1
+    assert requests[0]["reasoning_split"] is True
+    assert requests[0]["max_completion_tokens"] >= 4096
+    assert "max_tokens" not in requests[0]
+    assert "response_format" not in requests[0]
+
+
+def test_minimax_m3_keeps_larger_configured_completion_budget() -> None:
+    requests: list[dict[str, object]] = []
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        requests.append(json.loads(request.content))
+        return httpx.Response(
+            200,
+            json={
+                "choices": [{
+                    "message": {
+                        "content": json.dumps({
+                            "items": [{
+                                "instruction": "问题",
+                                "output": "这是满足测试要求的完整答案。",
+                            }],
+                        }, ensure_ascii=False),
+                    },
+                }],
+            },
+        )
+
+    generate_model_records(
+        [{"id": "preview-minimax-budget", "edited_content": "来源正文"}],
+        model={
+            "online_model_name": "MiniMax-M3",
+            "api_url": "https://api.minimax.io/v1",
+        },
+        config={"max_tokens": 8192, "generation_retries": 0},
+        task_id="task-minimax-budget",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=httpx.Client(transport=httpx.MockTransport(handler)),
+    )
+
+    assert requests[0]["max_completion_tokens"] == 8192
+
+
+def test_minimax_m3_name_on_custom_proxy_keeps_generic_openai_parameters() -> None:
+    requests: list[dict[str, object]] = []
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        requests.append(json.loads(request.content))
+        return httpx.Response(
+            200,
+            json={
+                "choices": [{
+                    "message": {
+                        "content": json.dumps({
+                            "items": [{
+                                "instruction": "问题",
+                                "output": "这是代理服务返回的完整答案。",
+                            }],
+                        }, ensure_ascii=False),
+                    },
+                }],
+            },
+        )
+
+    generate_model_records(
+        [{"id": "preview-minimax-proxy", "edited_content": "来源正文"}],
+        model={
+            "online_model_name": "MiniMax-M3",
+            "api_url": "https://model-proxy.example/v1",
+        },
+        config={"max_tokens": 1024, "json_mode": True, "generation_retries": 0},
+        task_id="task-minimax-proxy",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=httpx.Client(transport=httpx.MockTransport(handler)),
+    )
+
+    assert requests[0]["max_tokens"] == 1024
+    assert requests[0]["response_format"] == {"type": "json_object"}
+    assert "reasoning_split" not in requests[0]
+    assert "max_completion_tokens" not in requests[0]
+
+
+def test_generate_model_records_extracts_json_surrounded_by_model_explanation() -> None:
+    content = "模型结果如下：\n```json\n" + json.dumps(
+        {
+            "items": [{
+                "instruction": "字段有什么作用？",
+                "output": "该字段用于唯一标识记录。",
+            }],
+        },
+        ensure_ascii=False,
+    ) + "\n```\n生成完毕。"
+    client = httpx.Client(
+        transport=httpx.MockTransport(
+            lambda _: httpx.Response(
+                200,
+                json={"choices": [{"message": {"content": content}}]},
+            )
+        )
+    )
+
+    records = generate_model_records(
+        [{"id": "preview-explanation", "edited_content": "字段用于唯一标识记录。"}],
+        model={"name": "model", "api_url": "https://model.example/v1"},
+        config={"generation_retries": 0},
+        task_id="task-explanation",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=client,
+    )
+
+    assert records[0]["status"] == "valid"
+    assert records[0]["output"] == "该字段用于唯一标识记录。"
+
+
+def test_generate_model_records_reports_token_truncation_instead_of_json_error() -> None:
+    client = httpx.Client(
+        transport=httpx.MockTransport(
+            lambda _: httpx.Response(
+                200,
+                json={
+                    "choices": [{
+                        "finish_reason": "length",
+                        "message": {"content": ""},
+                    }],
+                    "output_sensitive": False,
+                },
+            )
+        )
+    )
+
+    records = generate_model_records(
+        [{"id": "preview-truncated", "edited_content": "来源正文"}],
+        model={"name": "model", "api_url": "https://model.example/v1"},
+        config={"generation_retries": 0},
+        task_id="task-truncated",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=client,
+    )
+
+    assert records[0]["status"] == "invalid"
+    assert "Token" in records[0]["error"]
+    assert "截断" in records[0]["error"]
+
+
+def test_token_truncation_is_not_retried_even_when_json_looks_complete() -> None:
+    request_count = 0
+    content = json.dumps({
+        "items": [{
+            "instruction": "问题",
+            "output": "表面完整但服务端已声明截断。",
+        }],
+    }, ensure_ascii=False)
+
+    def handler(_: httpx.Request) -> httpx.Response:
+        nonlocal request_count
+        request_count += 1
+        return httpx.Response(
+            200,
+            json={
+                "choices": [{
+                    "finish_reason": "length",
+                    "message": {"content": content},
+                }],
+            },
+        )
+
+    records = generate_model_records(
+        [{"id": "preview-length", "edited_content": "来源正文"}],
+        model={"name": "model", "api_url": "https://model.example/v1"},
+        config={"generation_retries": 5},
+        task_id="task-length",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=httpx.Client(transport=httpx.MockTransport(handler)),
+    )
+
+    assert request_count == 1
+    assert records[0]["status"] == "invalid"
+    assert "finish_reason=length" in records[0]["error"]
+
+
+def test_sensitive_model_response_is_not_retried_or_saved() -> None:
+    request_count = 0
+
+    def handler(_: httpx.Request) -> httpx.Response:
+        nonlocal request_count
+        request_count += 1
+        return httpx.Response(
+            200,
+            json={
+                "choices": [{
+                    "finish_reason": "stop",
+                    "message": {"content": "{}"},
+                }],
+                "output_sensitive": True,
+                "base_resp": {"status_code": 1027, "status_msg": "output sensitive"},
+            },
+        )
+
+    records = generate_model_records(
+        [{"id": "preview-sensitive", "edited_content": "来源正文"}],
+        model={"name": "model", "api_url": "https://model.example/v1"},
+        config={"generation_retries": 5},
+        task_id="task-sensitive",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=httpx.Client(transport=httpx.MockTransport(handler)),
+    )
+
+    assert request_count == 1
+    assert records[0]["status"] == "invalid"
+    assert "安全拦截" in records[0]["error"]
+    assert "1027" in records[0]["error"]
+
+
+def test_empty_model_content_can_retry_then_succeed() -> None:
+    request_count = 0
+
+    def handler(_: httpx.Request) -> httpx.Response:
+        nonlocal request_count
+        request_count += 1
+        if request_count == 1:
+            return httpx.Response(
+                200,
+                json={"choices": [{"finish_reason": "stop", "message": {"content": ""}}]},
+            )
+        return httpx.Response(
+            200,
+            json={
+                "choices": [{
+                    "finish_reason": "stop",
+                    "message": {
+                        "content": json.dumps({
+                            "items": [{
+                                "instruction": "问题",
+                                "output": "第二次请求返回了完整答案。",
+                            }],
+                        }, ensure_ascii=False),
+                    },
+                }],
+            },
+        )
+
+    records = generate_model_records(
+        [{"id": "preview-empty-retry", "edited_content": "来源正文"}],
+        model={"name": "model", "api_url": "https://model.example/v1"},
+        config={"generation_retries": 1},
+        task_id="task-empty-retry",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=httpx.Client(transport=httpx.MockTransport(handler)),
+    )
+
+    assert request_count == 2
+    assert records[0]["status"] == "valid"
+
+
+def test_multiple_top_level_json_documents_are_rejected_as_ambiguous() -> None:
+    first = json.dumps({
+        "items": [{"instruction": "问题一", "output": "答案一"}],
+    }, ensure_ascii=False)
+    second = json.dumps({
+        "items": [{"instruction": "问题二", "output": "答案二"}],
+    }, ensure_ascii=False)
+    client = httpx.Client(
+        transport=httpx.MockTransport(
+            lambda _: httpx.Response(
+                200,
+                json={"choices": [{"message": {"content": f"{first}\n{second}"}}]},
+            )
+        )
+    )
+
+    records = generate_model_records(
+        [{"id": "preview-ambiguous", "edited_content": "来源正文"}],
+        model={"name": "model", "api_url": "https://model.example/v1"},
+        config={"generation_retries": 0},
+        task_id="task-ambiguous",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=client,
+    )
+
+    assert records[0]["status"] == "invalid"
+    assert "多个 JSON" in records[0]["error"]
+
+
 def test_generate_model_records_builds_reasoning_output_with_think_tags() -> None:
     def handler(request: httpx.Request) -> httpx.Response:
         payload = json.loads(request.content)
@@ -414,6 +752,112 @@ def test_generate_model_records_retries_short_batch_then_marks_it_invalid() -> N
     assert "expected 10, got 1" in records[0]["error"]
 
 
+def test_generate_model_records_does_not_retry_non_retryable_http_errors() -> None:
+    request_count = 0
+
+    def handler(_: httpx.Request) -> httpx.Response:
+        nonlocal request_count
+        request_count += 1
+        return httpx.Response(401, json={"error": {"message": "unauthorized"}})
+
+    records = generate_model_records(
+        [{"id": "preview-auth", "edited_content": "来源内容"}],
+        model={
+            "api_url": "https://model.example/v1",
+            "online_model_name": "test-model",
+            "api_key": "invalid",
+        },
+        config={"generation_retries": 5},
+        task_id="task-auth",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=httpx.Client(transport=httpx.MockTransport(handler)),
+    )
+
+    assert request_count == 1
+    assert records[0]["status"] == "invalid"
+    assert "401" in records[0]["error"]
+
+
+@pytest.mark.parametrize("status_code", [408, 425, 429, 500])
+def test_generate_model_records_retries_retryable_http_statuses(
+    status_code: int,
+) -> None:
+    request_count = 0
+
+    def handler(_: httpx.Request) -> httpx.Response:
+        nonlocal request_count
+        request_count += 1
+        if request_count == 1:
+            return httpx.Response(status_code)
+        return httpx.Response(
+            200,
+            json={
+                "choices": [{
+                    "message": {
+                        "content": json.dumps({
+                            "items": [{
+                                "instruction": "来源内容是什么？",
+                                "output": "这是用于验证可重试错误的来源内容。",
+                            }],
+                        }, ensure_ascii=False),
+                    },
+                }],
+            },
+        )
+
+    records = generate_model_records(
+        [{"id": "preview-retryable", "edited_content": "来源内容"}],
+        model={"name": "model", "api_url": "https://model.example/v1"},
+        config={"generation_retries": 1},
+        task_id="task-retryable",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=httpx.Client(transport=httpx.MockTransport(handler)),
+    )
+
+    assert request_count == 2
+    assert records[0]["status"] == "valid"
+
+
+def test_generate_model_records_retries_transient_network_errors() -> None:
+    request_count = 0
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        nonlocal request_count
+        request_count += 1
+        if request_count == 1:
+            raise httpx.ConnectError("temporary connection failure", request=request)
+        return httpx.Response(
+            200,
+            json={
+                "choices": [{
+                    "message": {
+                        "content": json.dumps({
+                            "items": [{
+                                "instruction": "网络恢复了吗？",
+                                "output": "临时连接错误后，第二次模型请求已经成功。",
+                            }],
+                        }, ensure_ascii=False),
+                    },
+                }],
+            },
+        )
+
+    records = generate_model_records(
+        [{"id": "preview-network", "edited_content": "网络重试来源"}],
+        model={"name": "model", "api_url": "https://model.example/v1"},
+        config={"generation_retries": 1},
+        task_id="task-network",
+        split={"train": 100, "validation": 0, "test": 0},
+        qa_pairs_per_item=1,
+        client=httpx.Client(transport=httpx.MockTransport(handler)),
+    )
+
+    assert request_count == 2
+    assert records[0]["status"] == "valid"
+
+
 @pytest.mark.parametrize("qa_pairs_per_item", [0, 51])
 def test_generate_model_records_rejects_out_of_range_count(
     qa_pairs_per_item: int,

backend/tests/test_data_process_migration.py

@@ -2,7 +2,7 @@ from __future__ import annotations
 
 from pathlib import Path
 
-from app.modules.data_process.schema_cli import _target_label
+from app.modules.data_process.schema_cli import REQUIRED_TASK_COLUMNS, _target_label
 
 
 def test_runtime_migration_fails_fast_on_incompatible_schema() -> None:
@@ -18,6 +18,24 @@ def test_runtime_migration_fails_fast_on_incompatible_schema() -> None:
     assert "requires 001_platform_runtime.sql first" in sql
     assert "supports only the current TEXT runtime schema" in sql
     assert "generation_run_id" in sql
+    assert "results_confirmed BOOLEAN NOT NULL DEFAULT TRUE" in sql
+    assert "WHERE status <> 'completed' AND results_confirmed=TRUE" in sql
+    assert "ADD COLUMN IF NOT EXISTS workflow_step VARCHAR(20)" in sql
+    assert "ADD COLUMN IF NOT EXISTS preview_status VARCHAR(20)" in sql
+    assert "ADD COLUMN IF NOT EXISTS preview_progress NUMERIC(5,2)" in sql
+    assert "ADD COLUMN IF NOT EXISTS preview_run_id TEXT" in sql
+    assert "ADD COLUMN IF NOT EXISTS preview_failure_reason TEXT" in sql
+    assert "ADD COLUMN IF NOT EXISTS preview_total_files INTEGER" in sql
+    assert "ADD COLUMN IF NOT EXISTS preview_completed_files INTEGER" in sql
+    assert "data_process_workflow_backfill_ids" in sql
+    assert "ck_data_process_tasks_workflow_step" in sql
+    assert "ck_data_process_tasks_preview_status" in sql
+    assert "ck_data_process_tasks_preview_progress" in sql
+    assert "ck_data_process_tasks_preview_file_counts" in sql
+    for value in ("create", "model", "upload", "preview", "generate", "results"):
+        assert f"'{value}'" in sql
+    for value in ("idle", "queued", "running", "completed", "failed", "cancelled"):
+        assert f"'{value}'" in sql
     assert "CREATE TABLE IF NOT EXISTS data_process_results" in sql
     assert sql.count("BEGIN;") == 1
     assert sql.rstrip().endswith("COMMIT;")
@@ -27,3 +45,17 @@ def test_schema_cli_target_label_never_contains_credentials() -> None:
     label = _target_label("postgresql://secret-user:secret-password@db.example:5433/yg_ft")
     assert label == "db.example:5433/yg_ft"
     assert "secret" not in label
+
+
+def test_schema_check_requires_current_runtime_columns() -> None:
+    assert REQUIRED_TASK_COLUMNS == (
+        "generation_run_id",
+        "results_confirmed",
+        "workflow_step",
+        "preview_status",
+        "preview_progress",
+        "preview_run_id",
+        "preview_failure_reason",
+        "preview_total_files",
+        "preview_completed_files",
+    )

backend/tests/test_data_process_storage.py

@@ -63,6 +63,40 @@ def test_stage_publish_read_delete_roundtrip_with_unicode_filename(tmp_path: Pat
     _assert_staging_empty(storage)
 
 
+def test_stage_copy_creates_an_independently_deletable_source_object(
+    tmp_path: Path,
+) -> None:
+    storage = LocalDataProcessStorage(tmp_path / "storage")
+    original = _stage(storage, content=b"immutable source")
+    storage.publish([original])
+
+    copied = storage.stage_copy(
+        batch_id="batch-copy",
+        source_reference=original.reference,
+        expected_source_task_id="task-1",
+        expected_source_file_id="source-1",
+        task_id="task-2",
+        source_file_id="source-2",
+        version=1,
+        name="source.txt",
+    )
+    storage.publish([copied])
+
+    assert storage.read(copied.reference) == b"immutable source"
+    assert storage.delete(
+        original.reference,
+        expected_task_id="task-1",
+        expected_source_file_id="source-1",
+    ) is True
+    assert storage.read(copied.reference) == b"immutable source"
+    assert storage.delete(
+        copied.reference,
+        expected_task_id="task-2",
+        expected_source_file_id="source-2",
+    ) is True
+    _assert_staging_empty(storage)
+
+
 def test_db_reference_is_left_to_database_storage(tmp_path: Path) -> None:
     storage = LocalDataProcessStorage(tmp_path / "storage")
 

backend/tests/test_data_process_store.py

@@ -1,5 +1,6 @@
 from __future__ import annotations
 
+import inspect
 import json
 from collections.abc import Iterator
 from contextlib import contextmanager
@@ -17,9 +18,18 @@ from app.modules.data_process.store import (
     _preview_config_changed,
     _reasoning_output_is_valid,
     _source_storage_descriptor,
+    repeat_task_id,
 )
 
 
+def test_preview_replace_sql_never_uses_untyped_null_placeholders() -> None:
+    source = inspect.getsource(DataProcessStore.replace_preview_items)
+
+    assert "%s IS NULL" not in source
+    assert "is_direct_build = preview_run_id is None" in source
+    assert "workflow_step=CASE WHEN %s THEN 'preview'" in source
+
+
 class _Result:
     def __init__(self, *, row: dict[str, Any] | None = None, rows: list[dict[str, Any]] | None = None):
         self.row = row
@@ -146,6 +156,7 @@ class _PublishStore(DataProcessStore):
         return {
             "id": task_id,
             "status": "completed",
+            "results_confirmed": True,
             "description": "",
             "config": self._task_config,
             "output_dataset_id": train_dataset and train_dataset["id"],
@@ -321,6 +332,140 @@ class _TaskDetailStore(DataProcessStore):
         yield self._conn
 
 
+class _RepeatConnection:
+    def __init__(self) -> None:
+        self.source_files = [
+            {
+                "id": "source-old",
+                "name": "source.jsonl",
+                "size_bytes": 12,
+                "record_count": 1,
+                "file_format": "jsonl",
+                "checksum_sha256": "a" * 64,
+                "content": '{"id":1}\n',
+                "content_preview": '{"id":1}',
+                "metadata": {"storage_backend": "local"},
+                "created_by": "user-1",
+            }
+        ]
+        self.source_previews = [
+            {
+                "id": "preview-old",
+                "source_file_id": "source-old",
+                "original_content": '{"id":1}',
+                "edited_content": '{"id":1,"checked":true}',
+                "source_start": 0,
+                "source_end": 8,
+                "source_start_line": 1,
+                "source_end_line": 1,
+                "token_count": 5,
+                "status": "modified",
+                "quality_score": {"overall": 90},
+            }
+        ]
+        self.created_task: dict[str, Any] | None = None
+        self.created_files: list[dict[str, Any]] = []
+        self.created_previews: list[dict[str, Any]] = []
+
+    def execute(self, sql: str, params: Any = None) -> _Result:
+        normalized = " ".join(sql.split())
+        if params is not None:
+            assert normalized.count("%s") == len(params)
+        if normalized.startswith("SELECT * FROM data_process_tasks WHERE id="):
+            return _Result(row=None)
+        if normalized.startswith("SELECT * FROM data_process_source_files"):
+            return _Result(rows=[dict(item) for item in self.source_files])
+        if normalized.startswith("SELECT * FROM data_process_preview_items"):
+            return _Result(rows=[dict(item) for item in self.source_previews])
+        if normalized.startswith("INSERT INTO data_process_tasks"):
+            self.created_task = {
+                "id": params[0],
+                "name": params[1],
+                "description": params[2],
+                "status": "pending",
+                "process_type": params[3],
+                "source_dataset_id": params[4],
+                "config": params[5],
+                "progress": 20,
+                "input_count": params[6],
+                "results_confirmed": False,
+                "workflow_step": "preview",
+                "preview_status": "completed",
+                "preview_progress": 100,
+                "preview_total_files": params[7],
+                "preview_completed_files": params[8],
+                "created_at": params[15],
+                "updated_at": params[16],
+            }
+            return _Result(row=dict(self.created_task))
+        if normalized.startswith("INSERT INTO data_process_source_files"):
+            self.created_files.append(
+                {
+                    "id": params[0],
+                    "task_id": params[1],
+                    "storage_object_id": params[2],
+                    "content": params[8],
+                }
+            )
+            return _Result()
+        if normalized.startswith("INSERT INTO data_process_preview_items"):
+            self.created_previews.append(
+                {
+                    "id": params[0],
+                    "task_id": params[1],
+                    "source_file_id": params[2],
+                    "edited_content": params[4],
+                }
+            )
+            return _Result()
+        if normalized.startswith("SELECT (SELECT COUNT(*) FROM data_process_source_files"):
+            return _Result(
+                row={
+                    "source_file_count": len(self.created_files),
+                    "preview_count": len(self.created_previews),
+                }
+            )
+        raise AssertionError(f"unexpected SQL: {normalized}")
+
+
+class _RepeatStore(DataProcessStore):
+    def __init__(self, conn: _RepeatConnection) -> None:
+        self._conn = conn
+
+    @contextmanager
+    def connect(self) -> Iterator[_RepeatConnection]:
+        yield self._conn
+
+    def _task_in_connection(
+        self,
+        conn: Any,
+        task_id: str,
+        *,
+        for_update: bool = False,
+    ) -> dict[str, Any]:
+        assert task_id == "task-source"
+        assert for_update is True
+        return {
+            "id": task_id,
+            "name": "原任务",
+            "description": "原描述",
+            "status": "completed",
+            "process_type": "structured",
+            "source_dataset_id": None,
+            "config": {
+                "temperature": 0.3,
+                "_regeneration_prepared": {"prepared": True},
+            },
+            "results_confirmed": True,
+            "preview_status": "completed",
+            "tenant_id": "tenant-1",
+            "project_id": "project-1",
+            "owner_id": "owner-1",
+            "created_by": "user-1",
+            "updated_at": "2026-07-28T12:00:00Z",
+        }
+
+
 class _TaskListConnection:
     def __init__(self) -> None:
         self.task = {
@@ -454,12 +599,14 @@ class _LegacyRecoveryConnection:
             record["preview_item_id"] = params[1]
             return _Result()
         if normalized.startswith("UPDATE data_process_tasks SET status='completed'"):
+            assert "workflow_step='results'" in normalized
             self.task.update(
                 {
                     "status": "completed",
                     "progress": 100,
                     "output_dataset_id": params[0],
                     "output_count": params[1],
+                    "workflow_step": "results",
                 }
             )
             return _Result()
@@ -496,6 +643,7 @@ class _StartGenerationConnection:
                 config=config,
                 output_dataset_id="dataset_train" if published_prepared else None,
                 output_count=28,
+                results_confirmed=published_prepared,
             ),
             "generation_run_id": None,
         }
@@ -512,6 +660,7 @@ class _StartGenerationConnection:
         assert normalized.startswith("UPDATE data_process_tasks SET config=%s, status='running'")
         assert "output_dataset_id=NULL" in normalized
         assert "output_count=0" in normalized
+        assert "results_confirmed=FALSE" in normalized
         self.task.update(
             {
                 "config": params[0],
@@ -526,6 +675,7 @@ class _StartGenerationConnection:
                 "duplicate_count": 0,
                 "error_count": 0,
                 "generation_run_id": params[2],
+                "results_confirmed": False,
                 "updated_at": params[3],
             }
         )
@@ -559,6 +709,47 @@ def test_decode_row_serializes_postgres_numeric_values_as_json_numbers() -> None
     assert decoded == {"progress": 100.0, "duration_seconds": 389.0}
 
 
+def test_repeat_task_copies_business_snapshot_with_new_resource_ids() -> None:
+    conn = _RepeatConnection()
+    store = _RepeatStore(conn)
+    request_id = "repeat-request-0001"
+    target_task_id = repeat_task_id("task-source", request_id)
+
+    repeated = store.repeat_task(
+        "task-source",
+        expected_updated_at="2026-07-28T12:00:00Z",
+        request_id=request_id,
+        file_copies={
+            "source-old": {
+                "id": "source-new",
+                "storage_object_id": (
+                    f"local://data-process/{target_task_id}/source-new/v1/source.jsonl"
+                ),
+            }
+        },
+    )
+
+    assert repeated["created"] is True
+    assert repeated["task"]["id"] == target_task_id
+    assert repeated["task"]["config"] == {"temperature": 0.3}
+    assert repeated["task"]["results_confirmed"] is False
+    assert repeated["copied_source_file_count"] == 1
+    assert repeated["copied_preview_count"] == 1
+    assert conn.created_files == [
+        {
+            "id": "source-new",
+            "task_id": target_task_id,
+            "storage_object_id": (
+                f"local://data-process/{target_task_id}/source-new/v1/source.jsonl"
+            ),
+            "content": '{"id":1}\n',
+        }
+    ]
+    assert conn.created_previews[0]["task_id"] == target_task_id
+    assert conn.created_previews[0]["source_file_id"] == "source-new"
+    assert conn.created_previews[0]["edited_content"] == '{"id":1,"checked":true}'
+
+
 def test_decode_row_decodes_aggregated_output_datasets_json() -> None:
     decoded = _decode_row(
         {
@@ -713,6 +904,7 @@ def test_start_generation_clears_previous_output_count() -> None:
 
     assert task["status"] == "running"
     assert task["output_count"] == 0
+    assert task["results_confirmed"] is False
     assert conn.results == []
 
 
@@ -737,6 +929,7 @@ def test_prepared_published_task_survives_generation_preflight_failure() -> None
     assert conn.task["status"] == "completed"
     assert conn.task["output_dataset_id"] == "dataset_train"
     assert conn.task["output_count"] == 28
+    assert conn.task["results_confirmed"] is True
     assert "_regeneration_prepared" in conn.task["config"]
     assert conn.results == [{"id": "old-result"}]
 
@@ -752,6 +945,7 @@ def test_legacy_aborted_regeneration_recovers_results_and_published_state() -> N
     assert conn.task["progress"] == 100
     assert conn.task["output_dataset_id"] == "dataset_train"
     assert conn.task["output_count"] == 2
+    assert conn.task["workflow_step"] == "results"
     assert conn.task["started_at"] is None
     assert conn.task["completed_at"] is None
     assert [item["id"] for item in conn.results] == ["result_train", "result_test"]
@@ -1185,3 +1379,96 @@ def test_source_storage_descriptor_rejects_unowned_or_unsupported_references(
             "dpt_task",
             "dpsf_source",
         )
+
+
+class _LifecycleConnection:
+    def __init__(self) -> None:
+        self.task: dict[str, Any] = {
+            "id": "task-lifecycle",
+            "status": "running",
+            "generation_run_id": "generation-active",
+            "workflow_step": "generate",
+            "preview_status": "running",
+            "preview_progress": Decimal("40.00"),
+            "preview_run_id": "preview-active",
+            "preview_failure_reason": None,
+            "preview_total_files": 5,
+            "preview_completed_files": 2,
+            "deleted_at": None,
+            "deleted_by": None,
+        }
+        self.last_update_sql = ""
+
+    def execute(self, sql: str, params: Any = None) -> _Result:
+        normalized = " ".join(sql.split())
+        if params is not None:
+            assert normalized.count("%s") == len(params)
+        if normalized.startswith("SELECT * FROM data_process_tasks"):
+            row = None if self.task["deleted_at"] is not None else dict(self.task)
+            return _Result(row=row)
+        if normalized.startswith("UPDATE data_process_tasks SET workflow_step="):
+            self.last_update_sql = normalized
+            workflow_step, updated_at, task_id = params
+            assert task_id == self.task["id"]
+            self.task.update(workflow_step=workflow_step, updated_at=updated_at)
+            return _Result(row=dict(self.task))
+        if normalized.startswith("UPDATE data_process_tasks SET status=CASE"):
+            self.last_update_sql = normalized
+            deleted_at, deleted_by, updated_at, task_id = params
+            assert task_id == self.task["id"]
+            self.task.update(
+                status="stopped",
+                generation_run_id=None,
+                preview_status="cancelled",
+                preview_run_id=None,
+                deleted_at=deleted_at,
+                deleted_by=deleted_by,
+                updated_at=updated_at,
+            )
+            return _Result()
+        if normalized.startswith("SELECT status, generation_run_id"):
+            row = None if self.task["deleted_at"] is not None else dict(self.task)
+            return _Result(row=row)
+        if normalized.startswith("SELECT preview_status, preview_run_id"):
+            row = None if self.task["deleted_at"] is not None else dict(self.task)
+            return _Result(row=row)
+        raise AssertionError(f"unexpected SQL: {normalized}")
+
+
+class _LifecycleStore(DataProcessStore):
+    def __init__(self, conn: _LifecycleConnection) -> None:
+        self._conn = conn
+
+    @contextmanager
+    def connect(self) -> Iterator[_LifecycleConnection]:
+        yield self._conn
+
+
+def test_workflow_step_update_does_not_invalidate_active_runs() -> None:
+    conn = _LifecycleConnection()
+
+    task = _LifecycleStore(conn).update_workflow_step("task-lifecycle", "results")
+
+    assert task["workflow_step"] == "results"
+    assert task["status"] == "running"
+    assert task["generation_run_id"] == "generation-active"
+    assert task["preview_status"] == "running"
+    assert task["preview_run_id"] == "preview-active"
+    assert "generation_run_id" not in conn.last_update_sql
+    assert "preview_run_id" not in conn.last_update_sql
+
+
+def test_delete_atomically_invalidates_generation_and_preview_runs() -> None:
+    conn = _LifecycleConnection()
+    store = _LifecycleStore(conn)
+
+    store.delete_task("task-lifecycle", deleted_by="user-1")
+
+    assert conn.task["status"] == "stopped"
+    assert conn.task["generation_run_id"] is None
+    assert conn.task["preview_status"] == "cancelled"
+    assert conn.task["preview_run_id"] is None
+    assert conn.task["deleted_by"] == "user-1"
+    assert conn.task["deleted_at"] is not None
+    assert store.generation_is_running("task-lifecycle", "generation-active") is False
+    assert store.preview_is_running("task-lifecycle", "preview-active") is False

backend/tests/test_governance.py

@@ -0,0 +1,774 @@
+"""
+平台治理功能集成测试 —— 覆盖第 1-4 周交付内容。
+
+测试策略：
+- 在导入 app 模块前 mock psycopg / psycopg_pool，避免依赖真实数据库驱动
+- 使用 FastAPI TestClient 对真实路由栈发起请求
+- 通过 mock.get_platform_store 替换为内存 FakeStore
+- 每周交付内容对应一组 test class，方便分阶段验收
+
+覆盖范围：
+  第 1 周 — 登录、当前用户、用户列表、权限码、日志查询
+  第 2 周 — 租户、项目、项目成员、资源 ACL
+  第 3 周 — 审批实例、审批模板、审计日志查询和导出
+  第 4 周 — 写操作审计、审批拦截、权限校验
+"""
+
+from __future__ import annotations
+
+import json
+import sys
+import types
+from contextlib import contextmanager
+from typing import Any, Iterator
+from unittest.mock import MagicMock, patch
+
+import pytest
+from fastapi import FastAPI
+from fastapi.testclient import TestClient
+
+# ============================================================
+# 在导入 app 之前 mock psycopg / psycopg_pool
+# ============================================================
+
+_psycopg_mock = types.ModuleType("psycopg")
+_psycopg_mock.PgConn = type("PgConn", (), {})
+_psycopg_mock.PostgresConnectionPool = MagicMock()
+_psycopg_mock.connection = MagicMock()
+sys.modules.setdefault("psycopg", _psycopg_mock)
+
+_psycopg_pool_mock = types.ModuleType("psycopg_pool")
+_psycopg_pool_mock.ConnectionPool = MagicMock()
+sys.modules.setdefault("psycopg_pool", _psycopg_pool_mock)
+
+# 现在安全导入 app 模块
+from app.api.v1.endpoints.platform import ok, fail  # noqa: E402
+from app.modules.tenant.router import router as tenant_router  # noqa: E402
+from app.modules.project.router import router as project_router  # noqa: E402
+from app.modules.approval.router import router as approval_router  # noqa: E402
+from app.modules.system.router import router as system_router  # noqa: E402
+from app.modules.retention.router import router as retention_router  # noqa: E402
+from app.modules.resource.router import router as resource_router  # noqa: E402
+from app.api.v1.endpoints.platform import router as platform_router  # noqa: E402
+
+PREFIX = "/modelTF"
+ADMIN_TOKEN = "platform-token-u_admin"
+OP_TOKEN = "platform-token-u_op"
+
+
+# ============================================================
+# FakePlatformStore —— 内存实现，模拟 PlatformStore 全部治理接口
+# ============================================================
+
+class FakePlatformStore:
+    """平台治理测试专用内存 store，确保测试不连接真实数据库。"""
+
+    def __init__(self) -> None:
+        self._users: list[dict[str, Any]] = [
+            {
+                "id": "u_admin",
+                "username": "admin",
+                "display_name": "Admin",
+                "role": "admin",
+                "status": "active",
+                "permissions": [
+                    "dashboard", "fine-tune", "model-eval", "model-inference",
+                    "model-manage", "dataset", "data-process", "data-convert",
+                    "compute", "hardware", "logs", "user-settings",
+                ],
+                "last_login": "2026-08-01T10:00:00Z",
+                "protected": True,
+            },
+            {
+                "id": "u_op",
+                "username": "operator",
+                "display_name": "Operator",
+                "role": "operator",
+                "status": "active",
+                "permissions": ["dashboard", "fine-tune"],
+                "last_login": "2026-08-01T11:00:00Z",
+                "protected": False,
+            },
+        ]
+        self._tenants: dict[str, dict[str, Any]] = {}
+        self._projects: dict[str, dict[str, Any]] = {}
+        self._members: dict[str, list[dict[str, Any]]] = {}
+        self._acl: dict[str, list[dict[str, Any]]] = {}
+        self._audit_logs: list[dict[str, Any]] = []
+        self._approval_templates: dict[str, dict[str, Any]] = {}
+        self._approval_instances: dict[str, dict[str, Any]] = {}
+        self._retention_policies: dict[str, dict[str, Any]] = {}
+        self._models: list[dict[str, Any]] = []
+        self._datasets: list[dict[str, Any]] = []
+        self._tasks: list[dict[str, Any]] = []
+        self._compute_nodes: list[dict[str, Any]] = []
+        self._gpus: list[dict[str, Any]] = []
+        self._sessions: list[dict[str, Any]] = []
+        self._seq = 0
+
+    @contextmanager
+    def connect(self) -> Iterator[Any]:
+        class FakeConn:
+            def execute(self, *a, **kw):
+                return []
+
+            def commit(self):
+                pass
+
+            def rollback(self):
+                pass
+
+            def close(self):
+                pass
+
+        yield FakeConn()
+
+    # ---- helpers ----
+
+    def _next_id(self, prefix: str) -> str:
+        self._seq += 1
+        return f"{prefix}_{self._seq}"
+
+    # ==================== 第1周：登录 / 用户 / 权限码 / 日志 ====================
+
+    def login(self, username: str, password: str) -> dict[str, Any] | None:
+        for u in self._users:
+            if u["username"] == username and u["status"] == "active":
+                if password in ("admin123", "operator123", "test123"):
+                    return dict(u)
+        return None
+
+    def users(self) -> list[dict[str, Any]]:
+        return [dict(u) for u in self._users]
+
+    def create_user(self, payload: dict[str, Any]) -> dict[str, Any]:
+        u = {"id": self._next_id("u"), "protected": False, **payload}
+        self._users.append(u)
+        return u
+
+    def update_user(self, user_id: str, payload: dict[str, Any]) -> dict[str, Any]:
+        for u in self._users:
+            if u["id"] == user_id:
+                u.update(payload)
+                return u
+        raise KeyError(user_id)
+
+    def delete_user(self, user_id: str) -> None:
+        self._users = [u for u in self._users if u["id"] != user_id]
+
+    def roles(self) -> list[dict[str, Any]]:
+        return [
+            {"name": "admin", "display_name": "管理员"},
+            {"name": "operator", "display_name": "操作员"},
+            {"name": "viewer", "display_name": "访客"},
+        ]
+
+    def log_files(self, date: str | None = None) -> list[dict[str, Any]]:
+        return [{"name": "backend-2026-08-01.log", "size": "1 KB", "date": "2026-08-01"}]
+
+    def log_content(self, file: str) -> dict[str, Any]:
+        return {"file": file, "content": "[INFO] test line", "size": "1 KB"}
+
+    def training_log_files(self) -> list[dict[str, Any]]:
+        return [{"task_id": "ft_001", "name": "ft_001.log", "size": "2 KB"}]
+
+    def training_log_content(self, file: str) -> dict[str, Any]:
+        return {"file": file, "content": "epoch 0 loss 1.0", "size": "2 KB"}
+
+    # ==================== 第2周：租户 / 项目 / 成员 / ACL ====================
+
+    def tenants(self) -> list[dict[str, Any]]:
+        return list(self._tenants.values())
+
+    def tenant(self, tenant_id: str) -> dict[str, Any]:
+        if tenant_id not in self._tenants:
+            raise KeyError(tenant_id)
+        return dict(self._tenants[tenant_id])
+
+    def create_tenant(self, payload: dict[str, Any]) -> dict[str, Any]:
+        tid = self._next_id("tnt")
+        t = {"id": tid, "status": "active", "quota": "{}", "retention_policy_id": None,
+             "create_time": "2026-08-01T00:00:00Z", **payload}
+        self._tenants[tid] = t
+        return dict(t)
+
+    def update_tenant(self, tenant_id: str, payload: dict[str, Any]) -> dict[str, Any]:
+        self._tenants[tenant_id].update(payload)
+        return dict(self._tenants[tenant_id])
+
+    def set_tenant_quota(self, tenant_id: str, quota: dict[str, Any]) -> dict[str, Any]:
+        self._tenants[tenant_id]["quota"] = json.dumps(quota)
+        return dict(self._tenants[tenant_id])
+
+    def set_tenant_retention(self, tenant_id: str, retention_policy_id: str | None) -> dict[str, Any]:
+        self._tenants[tenant_id]["retention_policy_id"] = retention_policy_id
+        return dict(self._tenants[tenant_id])
+
+    def projects(self, *, tenant_id: str = "default", status: str | None = None, keyword: str | None = None) -> list[dict[str, Any]]:
+        result = []
+        for p in self._projects.values():
+            if p.get("tenant_id") != tenant_id:
+                continue
+            if status and p.get("status") != status:
+                continue
+            if keyword and keyword.lower() not in p.get("name", "").lower():
+                continue
+            result.append(dict(p))
+        return result
+
+    def project(self, project_id: str) -> dict[str, Any]:
+        if project_id not in self._projects:
+            raise KeyError(project_id)
+        return dict(self._projects[project_id])
+
+    def create_project(self, payload: dict[str, Any]) -> dict[str, Any]:
+        pid = self._next_id("prj")
+        p = {"id": pid, "status": "active", "quota": "{}", "create_time": "2026-08-01T00:00:00Z", **payload}
+        self._projects[pid] = p
+        self._members[pid] = []
+        return dict(p)
+
+    def update_project(self, project_id: str, payload: dict[str, Any]) -> dict[str, Any]:
+        self._projects[project_id].update(payload)
+        return dict(self._projects[project_id])
+
+    def archive_project(self, project_id: str) -> dict[str, Any]:
+        self._projects[project_id]["status"] = "archived"
+        return dict(self._projects[project_id])
+
+    def delete_project(self, project_id: str) -> None:
+        self._projects.pop(project_id, None)
+        self._members.pop(project_id, None)
+
+    def project_members(self, project_id: str) -> list[dict[str, Any]]:
+        return [dict(m) for m in self._members.get(project_id, [])]
+
+    def add_project_member(self, project_id: str, payload: dict[str, Any]) -> dict[str, Any]:
+        m = {"joined_at": "2026-08-01T00:00:00Z", **payload}
+        self._members.setdefault(project_id, []).append(m)
+        return m
+
+    def update_project_member_role(self, project_id: str, user_id: str, role: str) -> dict[str, Any]:
+        for m in self._members.get(project_id, []):
+            if m["user_id"] == user_id:
+                m["role"] = role
+                return m
+        raise KeyError(user_id)
+
+    def remove_project_member(self, project_id: str, user_id: str) -> None:
+        self._members[project_id] = [m for m in self._members.get(project_id, []) if m["user_id"] != user_id]
+
+    # ---- ACL ----
+
+    def get_acl(self, resource_type: str, resource_id: str) -> list[dict[str, Any]]:
+        key = f"{resource_type}:{resource_id}"
+        return [dict(a) for a in self._acl.get(key, [])]
+
+    def set_acl(self, resource_type: str, resource_id: str, entries: list[dict[str, Any]]) -> list[dict[str, Any]]:
+        key = f"{resource_type}:{resource_id}"
+        self._acl[key] = [dict(e) for e in entries]
+        return self.get_acl(resource_type, resource_id)
+
+    def resource_acl(self, resource_type: str, resource_id: str) -> list[dict[str, Any]]:
+        rows = self.get_acl(resource_type, resource_id)
+        grouped: dict[str, dict[str, Any]] = {}
+        for r in rows:
+            k = f"{r.get('principal_type')}:{r.get('principal_id')}"
+            bucket = grouped.setdefault(k, {
+                "subject_type": r.get("principal_type"),
+                "subject_id": r.get("principal_id"),
+                "permissions": [],
+            })
+            perm = r.get("permission")
+            if perm and perm not in bucket["permissions"]:
+                bucket["permissions"].append(perm)
+        return list(grouped.values())
+
+    def set_resource_acl(self, resource_type: str, resource_id: str, entries: list[dict[str, Any]]) -> list[dict[str, Any]]:
+        flat: list[dict[str, Any]] = []
+        for e in entries:
+            for perm in e.get("permissions") or []:
+                flat.append({
+                    "principal_type": e.get("subject_type"),
+                    "principal_id": e.get("subject_id"),
+                    "permission": perm,
+                })
+        self.set_acl(resource_type, resource_id, flat)
+        return self.resource_acl(resource_type, resource_id)
+
+    # ==================== 第3周：审批 / 审计 / 留存 ====================
+
+    def approval_templates(self) -> list[dict[str, Any]]:
+        return list(self._approval_templates.values())
+
+    def create_approval_template(self, payload: dict[str, Any]) -> dict[str, Any]:
+        tid = payload.get("id") or self._next_id("tpl")
+        t = {"id": tid, "steps": [], "create_time": "2026-08-01T00:00:00Z", **payload}
+        self._approval_templates[tid] = t
+        return dict(t)
+
+    def approval_instances(self, *, status: str | None = None) -> list[dict[str, Any]]:
+        result = []
+        for i in self._approval_instances.values():
+            if status and i.get("status") != status:
+                continue
+            result.append(dict(i))
+        return result
+
+    def approval_instance(self, instance_id: str) -> dict[str, Any]:
+        if instance_id not in self._approval_instances:
+            raise KeyError(instance_id)
+        return dict(self._approval_instances[instance_id])
+
+    def create_approval_instance(self, payload: dict[str, Any]) -> dict[str, Any]:
+        iid = self._next_id("appr")
+        inst = {
+            "id": iid,
+            "status": "pending",
+            "current_step": 0,
+            "steps": [],
+            "create_time": "2026-08-01T00:00:00Z",
+            **payload,
+        }
+        self._approval_instances[iid] = inst
+        return dict(inst)
+
+    def decide_approval_step(self, instance_id: str, step_index: int, *, approver_id: str, approved: bool, comment: str | None = None) -> dict[str, Any]:
+        inst = self._approval_instances[instance_id]
+        inst["status"] = "approved" if approved else "rejected"
+        inst["current_step"] = step_index + 1
+        return dict(inst)
+
+    def audit_logs(self, **kw) -> dict[str, Any]:
+        items = [dict(l) for l in self._audit_logs]
+        for filter_key in ("tenant_id", "project_id", "actor_id", "action", "target_type"):
+            val = kw.get(filter_key)
+            if val:
+                items = [l for l in items if l.get(filter_key) == val]
+        limit = kw.get("limit", 50)
+        offset = kw.get("offset", 0)
+        total = len(items)
+        items = items[offset:offset + limit]
+        return {"items": items, "total": total}
+
+    def record_audit(self, **kw) -> None:
+        log = {"id": self._next_id("log"), "time": "2026-08-01T12:00:00Z", **kw}
+        self._audit_logs.append(log)
+
+    # ---- 留存策略 ----
+
+    def retention_policies(self) -> list[dict[str, Any]]:
+        return list(self._retention_policies.values())
+
+    def retention_policy(self, policy_id: str) -> dict[str, Any]:
+        if policy_id not in self._retention_policies:
+            raise KeyError(policy_id)
+        return dict(self._retention_policies[policy_id])
+
+    def create_retention_policy(self, payload: dict[str, Any]) -> dict[str, Any]:
+        pid = payload.get("id") or self._next_id("rpol")
+        p = {"id": pid, "status": "active", "create_time": "2026-08-01T00:00:00Z", **payload}
+        self._retention_policies[pid] = p
+        return dict(p)
+
+    def update_retention_policy(self, policy_id: str, payload: dict[str, Any]) -> dict[str, Any]:
+        self._retention_policies[policy_id].update(payload)
+        return dict(self._retention_policies[policy_id])
+
+    def delete_retention_policy(self, policy_id: str) -> None:
+        self._retention_policies.pop(policy_id, None)
+
+    # ---- dashboard & other stubs ----
+
+    def login_duration_rank(self, limit: int = 8, days: int = 30) -> list[dict[str, Any]]:
+        return [{"user": "admin", "role": "admin", "duration": 10.0}]
+
+    def models(self) -> list[dict[str, Any]]:
+        return self._models
+
+    def datasets(self) -> list[dict[str, Any]]:
+        return self._datasets
+
+    def tasks(self) -> list[dict[str, Any]]:
+        return self._tasks
+
+    def compute_nodes(self) -> list[dict[str, Any]]:
+        return self._compute_nodes
+
+    def gpus(self) -> list[dict[str, Any]]:
+        return self._gpus
+
+    def system_info(self) -> dict[str, Any]:
+        return {"cpu": {}, "memory": {}}
+
+
+# ============================================================
+# 测试 fixtures
+# ============================================================
+
+@pytest.fixture(scope="module")
+def fake_store() -> FakePlatformStore:
+    return FakePlatformStore()
+
+
+def _build_client(store: FakePlatformStore) -> TestClient:
+    """构建 TestClient，patch 所有治理模块的 get_platform_store。"""
+    app = FastAPI()
+    app.include_router(platform_router, prefix=PREFIX)
+    app.include_router(system_router, prefix=PREFIX)
+    app.include_router(tenant_router, prefix=PREFIX)
+    app.include_router(project_router, prefix=PREFIX)
+    app.include_router(approval_router, prefix=PREFIX)
+    app.include_router(retention_router, prefix=PREFIX)
+    app.include_router(resource_router, prefix=PREFIX)
+
+    patches = [
+        patch("app.db.platform_store.get_platform_store", return_value=store),
+        patch("app.core.auth.get_platform_store", return_value=store),
+        patch("app.api.v1.endpoints.platform.get_platform_store", return_value=store),
+        patch("app.modules.system.router.get_platform_store", return_value=store),
+        patch("app.modules.tenant.router.get_platform_store", return_value=store),
+        patch("app.modules.project.router.get_platform_store", return_value=store),
+        patch("app.modules.approval.router.get_platform_store", return_value=store),
+        patch("app.modules.retention.router.get_platform_store", return_value=store),
+        patch("app.modules.resource.router.get_platform_store", return_value=store),
+    ]
+    for p in patches:
+        p.start()
+    client = TestClient(app, raise_server_exceptions=False)
+    client._fake_store = store  # type: ignore[attr-defined]
+    return client
+
+
+@pytest.fixture(scope="module")
+def client(fake_store: FakePlatformStore) -> TestClient:
+    c = _build_client(fake_store)
+    yield c
+
+
+def _admin_headers() -> dict[str, str]:
+    return {"Authorization": f"Bearer {ADMIN_TOKEN}"}
+
+
+def _op_headers() -> dict[str, str]:
+    return {"Authorization": f"Bearer {OP_TOKEN}"}
+
+
+# ============================================================
+# 第 1 周测试：登录、当前用户、用户列表、权限码、日志查询
+# ============================================================
+
+class TestWeek1AuthUserPermissionsLogs:
+    """第 1 周：登录、当前用户、用户列表、权限码、日志查询接口。"""
+
+    def test_login_success(self, client: TestClient):
+        resp = client.post(f"{PREFIX}/login", json={"username": "admin", "password": "admin123"})
+        assert resp.status_code == 200
+        data = resp.json()["data"]
+        assert data["token"] == ADMIN_TOKEN
+        assert data["user"]["username"] == "admin"
+
+    def test_login_invalid(self, client: TestClient):
+        resp = client.post(f"{PREFIX}/login", json={"username": "admin", "password": "wrong"})
+        assert resp.status_code == 401
+
+    def test_me_with_valid_token(self, client: TestClient):
+        resp = client.get(f"{PREFIX}/me", headers=_admin_headers())
+        assert resp.status_code == 200
+        assert resp.json()["data"]["username"] == "admin"
+
+    def test_me_without_token(self, client: TestClient):
+        resp = client.get(f"{PREFIX}/me")
+        assert resp.status_code == 401
+
+    def test_users_list(self, client: TestClient):
+        resp = client.get(f"{PREFIX}/users", headers=_admin_headers())
+        assert resp.status_code == 200
+        users = resp.json()["data"]
+        assert len(users) >= 2
+        assert any(u["username"] == "admin" for u in users)
+
+    def test_create_user(self, client: TestClient):
+        resp = client.post(
+            f"{PREFIX}/users",
+            json={"username": "tester", "display_name": "Tester", "role": "viewer", "password": "test123"},
+            headers=_admin_headers(),
+        )
+        assert resp.status_code == 200
+        assert resp.json()["data"]["username"] == "tester"
+
+    def test_permission_codes(self, client: TestClient):
+        resp = client.get(f"{PREFIX}/system/permissions/codes")
+        assert resp.status_code == 200
+        codes = resp.json()["data"]["codes"]
+        assert "dashboard" in codes
+        assert "user-settings" in codes
+
+    def test_permissions_overview(self, client: TestClient):
+        resp = client.get(f"{PREFIX}/system/permissions")
+        assert resp.status_code == 200
+        data = resp.json()["data"]
+        assert "codes" in data
+        assert "roles" in data
+
+    def test_log_files(self, client: TestClient):
+        resp = client.get(f"{PREFIX}/log-files", headers=_admin_headers())
+        assert resp.status_code == 200
+        files = resp.json()["data"]
+        assert len(files) >= 1
+
+    def test_log_content(self, client: TestClient):
+        resp = client.get(f"{PREFIX}/log-content", params={"file": "backend.log"}, headers=_admin_headers())
+        assert resp.status_code == 200
+        assert "content" in resp.json()["data"]
+
+    def test_training_log_files(self, client: TestClient):
+        resp = client.get(f"{PREFIX}/training-log-files", headers=_admin_headers())
+        assert resp.status_code == 200
+        assert len(resp.json()["data"]) >= 1
+
+    def test_training_log_content(self, client: TestClient):
+        resp = client.get(f"{PREFIX}/training-log-content", params={"file": "ft_001.log"}, headers=_admin_headers())
+        assert resp.status_code == 200
+        assert "content" in resp.json()["data"]
+
+
+# ============================================================
+# 第 2 周测试：租户、项目、项目成员、资源 ACL
+# ============================================================
+
+class TestWeek2TenantProjectACL:
+    """第 2 周：租户、项目、项目成员、资源 ACL。"""
+
+    def test_tenant_crud(self, client: TestClient):
+        # 创建
+        resp = client.post(f"{PREFIX}/tenants", json={"name": "Tenant-A", "code": "ta"}, headers=_admin_headers())
+        assert resp.status_code == 200
+        tid = resp.json()["data"]["id"]
+        # 查列表
+        resp = client.get(f"{PREFIX}/tenants", headers=_admin_headers())
+        assert resp.status_code == 200
+        assert any(t["id"] == tid for t in resp.json()["data"])
+        # 查详情
+        resp = client.get(f"{PREFIX}/tenants/{tid}", headers=_admin_headers())
+        assert resp.status_code == 200
+        assert resp.json()["data"]["name"] == "Tenant-A"
+        # 更新
+        resp = client.put(f"{PREFIX}/tenants/{tid}", json={"name": "Tenant-A2"}, headers=_admin_headers())
+        assert resp.status_code == 200
+        assert resp.json()["data"]["name"] == "Tenant-A2"
+
+    def test_tenant_quota(self, client: TestClient):
+        resp = client.post(f"{PREFIX}/tenants", json={"name": "Q-Tenant", "code": "qt"}, headers=_admin_headers())
+        tid = resp.json()["data"]["id"]
+        resp = client.put(f"{PREFIX}/tenants/{tid}/quota", json={"quota": {"gpu": 4}}, headers=_admin_headers())
+        assert resp.status_code == 200
+
+    def test_tenant_retention(self, client: TestClient):
+        resp = client.post(f"{PREFIX}/tenants", json={"name": "R-Tenant", "code": "rt"}, headers=_admin_headers())
+        tid = resp.json()["data"]["id"]
+        resp = client.put(f"{PREFIX}/tenants/{tid}/retention-policy", json={"retention_policy_id": "rpol_1"}, headers=_admin_headers())
+        assert resp.status_code == 200
+
+    def test_project_crud(self, client: TestClient):
+        # 创建项目
+        resp = client.post(f"{PREFIX}/projects", json={"name": "Proj-1", "code": "p1", "tenant_id": "default"}, headers=_admin_headers())
+        assert resp.status_code == 200
+        pid = resp.json()["data"]["id"]
+        # 查列表
+        resp = client.get(f"{PREFIX}/projects", params={"tenant_id": "default"}, headers=_admin_headers())
+        assert resp.status_code == 200
+        assert any(p["id"] == pid for p in resp.json()["data"])
+        # 查详情
+        resp = client.get(f"{PREFIX}/projects/{pid}", headers=_admin_headers())
+        assert resp.status_code == 200
+        assert resp.json()["data"]["name"] == "Proj-1"
+        # 更新
+        resp = client.put(f"{PREFIX}/projects/{pid}", json={"description": "updated"}, headers=_admin_headers())
+        assert resp.status_code == 200
+        # 归档
+        resp = client.post(f"{PREFIX}/projects/{pid}/archive", headers=_admin_headers())
+        assert resp.status_code == 200
+        assert resp.json()["data"]["status"] == "archived"
+
+    def test_project_members(self, client: TestClient):
+        resp = client.post(f"{PREFIX}/projects", json={"name": "Proj-M", "code": "pm", "tenant_id": "default"}, headers=_admin_headers())
+        pid = resp.json()["data"]["id"]
+        # 加成员
+        resp = client.post(f"{PREFIX}/projects/{pid}/members", json={"user_id": "u_op", "role": "developer"}, headers=_admin_headers())
+        assert resp.status_code == 200
+        # 列成员
+        resp = client.get(f"{PREFIX}/projects/{pid}/members", headers=_admin_headers())
+        assert resp.status_code == 200
+        assert len(resp.json()["data"]) >= 1
+        # 改角色
+        resp = client.put(f"{PREFIX}/projects/{pid}/members/u_op", json={"role": "maintainer"}, headers=_admin_headers())
+        assert resp.status_code == 200
+        # 删成员
+        resp = client.delete(f"{PREFIX}/projects/{pid}/members/u_op", headers=_admin_headers())
+        assert resp.status_code == 200
+
+    def test_resource_acl(self, client: TestClient):
+        # 设置 ACL
+        resp = client.put(
+            f"{PREFIX}/resources/model/m001/acl",
+            json={"entries": [{"subject_type": "user", "subject_id": "u_op", "permissions": ["read", "write"]}]},
+            headers=_admin_headers(),
+        )
+        assert resp.status_code == 200
+        result = resp.json()["data"]
+        assert len(result) == 1
+        assert set(result[0]["permissions"]) == {"read", "write"}
+        # 查询 ACL
+        resp = client.get(f"{PREFIX}/resources/model/m001/acl", headers=_admin_headers())
+        assert resp.status_code == 200
+        assert len(resp.json()["data"]) == 1
+
+
+# ============================================================
+# 第 3 周测试：审批实例、审批模板、审计日志查询和导出
+# ============================================================
+
+class TestWeek3ApprovalAudit:
+    """第 3 周：审批实例、审批模板、审计日志查询和导出。"""
+
+    def test_approval_template_crud(self, client: TestClient):
+        # 创建模板
+        resp = client.post(f"{PREFIX}/approvals/templates", json={"name": "delete-approval", "steps": [{"approver_id": "u_admin", "status": "pending"}]}, headers=_admin_headers())
+        assert resp.status_code == 200
+        tpl_id = resp.json()["data"]["id"]
+        # 查列表
+        resp = client.get(f"{PREFIX}/approvals/templates", headers=_admin_headers())
+        assert resp.status_code == 200
+        assert any(t["id"] == tpl_id for t in resp.json()["data"])
+
+    def test_approval_instance_flow(self, client: TestClient):
+        # 创建审批实例
+        resp = client.post(f"{PREFIX}/approvals", json={
+            "resource_type": "dataset", "resource_id": "ds_001",
+            "applicant_id": "u_op",
+        }, headers=_admin_headers())
+        assert resp.status_code == 200
+        iid = resp.json()["data"]["id"]
+        # 查详情
+        resp = client.get(f"{PREFIX}/approvals/{iid}", headers=_admin_headers())
+        assert resp.status_code == 200
+        assert resp.json()["data"]["status"] == "pending"
+        # 审批决策
+        resp = client.post(f"{PREFIX}/approvals/{iid}/steps/0/decision", json={
+            "approver_id": "u_admin", "approved": True, "comment": "ok",
+        }, headers=_admin_headers())
+        assert resp.status_code == 200
+        assert resp.json()["data"]["status"] == "approved"
+
+    def test_approval_instance_reject(self, client: TestClient):
+        resp = client.post(f"{PREFIX}/approvals", json={
+            "resource_type": "model", "resource_id": "m_002",
+            "applicant_id": "u_op",
+        }, headers=_admin_headers())
+        iid = resp.json()["data"]["id"]
+        resp = client.post(f"{PREFIX}/approvals/{iid}/steps/0/decision", json={
+            "approver_id": "u_admin", "approved": False, "comment": "no",
+        }, headers=_admin_headers())
+        assert resp.status_code == 200
+        assert resp.json()["data"]["status"] == "rejected"
+
+    def test_approval_missing_field(self, client: TestClient):
+        resp = client.post(f"{PREFIX}/approvals", json={"resource_type": "dataset"}, headers=_admin_headers())
+        assert resp.status_code == 400
+
+    def test_audit_logs_query(self, client: TestClient):
+        # 通过 API 写操作触发审计
+        client.post(f"{PREFIX}/tenants", json={"name": "Audit-Tenant", "code": "at"}, headers=_admin_headers())
+        # 查询
+        resp = client.get(f"{PREFIX}/system/audit-logs", params={"limit": 50}, headers=_admin_headers())
+        assert resp.status_code == 200
+        data = resp.json()["data"]
+        assert "items" in data
+        assert "total" in data
+        assert data["total"] >= 1
+
+    def test_audit_logs_filter_by_action(self, client: TestClient):
+        resp = client.get(f"{PREFIX}/system/audit-logs", params={"action": "tenant.create"}, headers=_admin_headers())
+        assert resp.status_code == 200
+        items = resp.json()["data"]["items"]
+        assert all(i.get("action") == "tenant.create" for i in items)
+
+    def test_audit_logs_export_csv(self, client: TestClient):
+        resp = client.get(f"{PREFIX}/system/audit-logs/export", headers=_admin_headers())
+        assert resp.status_code == 200
+        assert "text/csv" in resp.headers.get("content-type", "")
+        # CSV 首行是表头
+        lines = resp.text.strip().split("\n")
+        assert "time" in lines[0]
+
+
+# ============================================================
+# 第 4 周测试：写操作审计、审批拦截、权限校验
+# ============================================================
+
+class TestWeek4AuditInterceptPermission:
+    """第 4 周：写操作审计、审批拦截、权限校验。"""
+
+    def test_write_operation_produces_audit(self, client: TestClient, fake_store: FakePlatformStore):
+        # 清空审计日志便于断言
+        fake_store._audit_logs.clear()
+        # 创建租户 → 应产生 tenant.create 审计
+        client.post(f"{PREFIX}/tenants", json={"name": "W-Tenant", "code": "wt"}, headers=_admin_headers())
+        assert any(l["action"] == "tenant.create" for l in fake_store._audit_logs)
+        # 创建项目 → 应产生 project.create 审计
+        client.post(f"{PREFIX}/projects", json={"name": "W-Proj", "code": "wp", "tenant_id": "default"}, headers=_admin_headers())
+        assert any(l["action"] == "project.create" for l in fake_store._audit_logs)
+        # 设置 ACL → 应产生 resource.acl.set 审计
+        client.put(f"{PREFIX}/resources/model/w001/acl", json={"entries": []}, headers=_admin_headers())
+        assert any(l["action"] == "resource.acl.set" for l in fake_store._audit_logs)
+
+    def test_approval_intercept_on_project_archive(self, client: TestClient, fake_store: FakePlatformStore):
+        # 创建项目
+        resp = client.post(f"{PREFIX}/projects", json={"name": "I-Proj", "code": "ip", "tenant_id": "default"}, headers=_admin_headers())
+        pid = resp.json()["data"]["id"]
+        # 无待审批 → 可归档
+        resp = client.post(f"{PREFIX}/projects/{pid}/archive", headers=_admin_headers())
+        assert resp.status_code == 200
+
+    def test_approval_intercept_blocks_when_pending(self, client: TestClient, fake_store: FakePlatformStore):
+        # 创建项目
+        resp = client.post(f"{PREFIX}/projects", json={"name": "B-Proj", "code": "bp", "tenant_id": "default"}, headers=_admin_headers())
+        pid = resp.json()["data"]["id"]
+        # 注入一条待审批实例
+        fake_store.create_approval_instance({
+            "resource_type": "project",
+            "resource_id": pid,
+            "applicant_id": "u_op",
+        })
+        # 有待审批 → 归档应被拒绝
+        resp = client.post(f"{PREFIX}/projects/{pid}/archive", headers=_admin_headers())
+        assert resp.status_code == 409
+
+    def test_retention_policy_crud_with_audit(self, client: TestClient, fake_store: FakePlatformStore):
+        fake_store._audit_logs.clear()
+        # 创建
+        resp = client.post(f"{PREFIX}/retention-policies", json={"name": "30d-keep", "scope": "tenant"}, headers=_admin_headers())
+        assert resp.status_code == 200
+        rpid = resp.json()["data"]["id"]
+        assert any(l["action"] == "retention.create" for l in fake_store._audit_logs)
+        # 查列表
+        resp = client.get(f"{PREFIX}/retention-policies", headers=_admin_headers())
+        assert resp.status_code == 200
+        assert any(p["id"] == rpid for p in resp.json()["data"])
+        # 更新
+        resp = client.put(f"{PREFIX}/retention-policies/{rpid}", json={"status": "inactive"}, headers=_admin_headers())
+        assert resp.status_code == 200
+        assert resp.json()["data"]["status"] == "inactive"
+        # 删除
+        resp = client.delete(f"{PREFIX}/retention-policies/{rpid}", headers=_admin_headers())
+        assert resp.status_code == 200
+
+    def test_login_duration_rank_in_dashboard(self, client: TestClient):
+        resp = client.get(f"{PREFIX}/dashboard/stats", headers=_admin_headers())
+        assert resp.status_code == 200
+        data = resp.json()["data"]
+        assert "login_duration_rank" in data
+        assert "recent_login_users" in data
+        assert "service_status" in data
+        assert "training_7d" in data

compute/api/main.py

@@ -1,5 +1,7 @@
 from __future__ import annotations
 
+import asyncio
+import json
 import os
 import math
 import hashlib
@@ -10,10 +12,11 @@ from pathlib import Path
 from typing import Any
 
 from fastapi import FastAPI, File, Form, HTTPException, Query, Request, UploadFile
-from fastapi.responses import FileResponse, JSONResponse
+from fastapi.responses import FileResponse, JSONResponse, StreamingResponse
 
 from compute.agent.process_manager import ProcessManager
 from compute.engines.llama_factory.adapter import build_command, parse_log_line, prepare_runtime_files
+from compute.engines.llama_factory.inference import get_inference_session
 
 
 def create_app() -> FastAPI:
@@ -448,6 +451,29 @@ def create_app() -> FastAPI:
                 accelerator_errors, accelerator_warnings, accelerator = _validate_training_accelerator(payload)
                 errors.extend(accelerator_errors)
                 warnings.extend(accelerator_warnings)
+        elif engine == "eval":
+            # Eval engine: validate model path and dataset path
+            if not payload.get("model_name_or_path"):
+                errors.append("model_name_or_path is required for eval")
+            else:
+                path_checks.append(_check_path_item({
+                    "name": "model_name_or_path",
+                    "path": payload.get("model_name_or_path", ""),
+                    "type": "any",
+                    "required": True,
+                }))
+            if payload.get("dataset_path"):
+                path_checks.append(_check_path_item({
+                    "name": "dataset_path",
+                    "path": payload.get("dataset_path", ""),
+                    "type": "file",
+                    "required": True,
+                }))
+            else:
+                errors.append("dataset_path is required for eval")
+            if shutil.which("python") is None:
+                errors.append("python runtime not found")
+
         elif engine == "smoke":
             warnings.append("smoke engine skips model and dataset path checks")
 
@@ -666,6 +692,88 @@ def create_app() -> FastAPI:
         metrics = [parse_log_line(line) for line in window["content"].splitlines()]
         return {"job_id": job_id, **window, "metrics": [m for m in metrics if m]}
 
+    # ── Inference Endpoints ───────────────────────────────────────────
+
+    @app.post(f"{route_prefix}/inference/load")
+    async def inference_load(payload: dict[str, Any]) -> dict[str, Any]:
+        """Load a model for inference using LLaMA-Factory ChatModel.
+
+        Expected payload:
+            model_name_or_path: str (required)
+            adapter_name_or_path: str (optional, for LoRA adapters)
+            template: str (default: "qwen")
+            infer_backend: str (default: "huggingface")
+            infer_dtype: str (default: "auto")
+        """
+        session = get_inference_session()
+        result = session.load(
+            model_name_or_path=payload.get("model_name_or_path", ""),
+            adapter_name_or_path=payload.get("adapter_name_or_path", ""),
+            template=payload.get("template", "qwen"),
+            infer_backend=payload.get("infer_backend", "huggingface"),
+            infer_dtype=payload.get("infer_dtype", "auto"),
+        )
+        return result
+
+    @app.post(f"{route_prefix}/inference/unload")
+    async def inference_unload() -> dict[str, Any]:
+        """Unload the currently loaded model and free GPU memory."""
+        # Teardown (gc.collect + cuda.empty_cache) can take a while; run it off
+        # the event loop so /health and /inference/status stay responsive.
+        return await asyncio.to_thread(get_inference_session().unload)
+
+    @app.get(f"{route_prefix}/inference/status")
+    async def inference_status() -> dict[str, Any]:
+        """Get the current inference session status."""
+        return get_inference_session().info()
+
+    @app.post(f"{route_prefix}/inference/chat")
+    async def inference_chat(payload: dict[str, Any]) -> dict[str, Any]:
+        """Chat with the loaded model (non-streaming).
+
+        Expected payload:
+            messages: list[dict] (OpenAI format)
+            temperature: float (default 0.95)
+            top_p: float (default 0.7)
+            max_new_tokens: int (default 1024)
+        """
+        messages = payload.get("messages") or []
+        if not messages:
+            raise HTTPException(status_code=400, detail="messages is required")
+        # Generation is long-running; run it in a thread so the event loop keeps
+        # serving /inference/status and /health during inference.
+        result = await asyncio.to_thread(
+            get_inference_session().chat,
+            messages=messages,
+            temperature=float(payload.get("temperature", 0.95)),
+            top_p=float(payload.get("top_p", 0.7)),
+            max_new_tokens=int(payload.get("max_new_tokens", 1024)),
+            do_sample=bool(payload.get("do_sample", True)),
+        )
+        if result.get("error"):
+            raise HTTPException(status_code=500, detail=result["error"])
+        return {"response": result["response"]}
+
+    @app.post(f"{route_prefix}/inference/chat/stream")
+    async def inference_chat_stream(payload: dict[str, Any]) -> StreamingResponse:
+        """Chat with streaming response (Server-Sent Events)."""
+        messages = payload.get("messages") or []
+        if not messages:
+            raise HTTPException(status_code=400, detail="messages is required")
+
+        def generate():
+            session = get_inference_session()
+            for chunk in session.chat_stream(
+                messages=messages,
+                temperature=float(payload.get("temperature", 0.95)),
+                top_p=float(payload.get("top_p", 0.7)),
+                max_new_tokens=int(payload.get("max_new_tokens", 1024)),
+                do_sample=bool(payload.get("do_sample", True)),
+            ):
+                yield chunk
+
+        return StreamingResponse(generate(), media_type="text/event-stream")
+
     @app.post(f"{route_prefix}/compute/files/upload")
     async def upload_file(
         file: UploadFile | None = File(default=None),
@@ -733,6 +841,22 @@ def create_app() -> FastAPI:
             "checksum_sha256": checksum,
         }
 
+    @app.get(f"{route_prefix}/compute/files/read")
+    async def read_file(path: str = Query(...)) -> JSONResponse:
+        """Read a text file from within YG_FT_DATA_ROOT.  Used by the backend
+        to fetch eval results and other job outputs."""
+        data_root = Path(os.getenv("YG_FT_DATA_ROOT", "/data/yg-ft"))
+        target = (data_root / path.lstrip("/\\")).resolve()
+        if not _path_inside(data_root, target):
+            raise HTTPException(status_code=400, detail="path must stay inside YG_FT_DATA_ROOT")
+        if not target.is_file():
+            raise HTTPException(status_code=404, detail="file not found")
+        try:
+            content = target.read_text(encoding="utf-8")
+            return JSONResponse(json.loads(content) if content.strip().startswith("{") else {"content": content})
+        except Exception as exc:
+            raise HTTPException(status_code=500, detail=str(exc))
+
     @app.get(f"{route_prefix}/compute/files/{{file_id}}/download")
     async def download_file(file_id: str) -> FileResponse:
         upload_root = Path(os.getenv("YG_FT_DATA_ROOT", "/data/yg-ft")) / "uploads"

compute/engines/llama_factory/adapter.py

@@ -204,6 +204,31 @@ def build_command(config: dict[str, Any], llama_factory_home: str = "/app/LLaMA-
             command.extend(["--quantization_bit", str(quantization_bit)])
         return LlamaFactoryCommand(command=command, work_dir=str(Path(llama_factory_home)), env={})
 
+    if engine == "eval":
+        output_dir = config.get("output_dir") or f"/data/yg-ft/outputs/{config.get('name', 'eval-job')}"
+        eval_config_path = str(Path(output_dir) / "eval_config.json")
+        eval_config = {
+            "model_name_or_path": config.get("model_name_or_path", ""),
+            "adapter_name_or_path": config.get("adapter_name_or_path", ""),
+            "template": config.get("template", "qwen"),
+            "dataset_path": config.get("dataset_path", ""),
+            "output_dir": output_dir,
+            "basic_metrics": config.get("basic_metrics", {}),
+            "dimension": config.get("dimension", {}),
+            "temperature": config.get("temperature", 0.1),
+            "top_p": config.get("top_p", 0.95),
+            "max_new_tokens": config.get("max_new_tokens", 512),
+            "infer_backend": config.get("infer_backend", "huggingface"),
+            "infer_dtype": config.get("infer_dtype", "auto"),
+        }
+        Path(output_dir).mkdir(parents=True, exist_ok=True)
+        Path(eval_config_path).write_text(json.dumps(eval_config, ensure_ascii=False, indent=2), encoding="utf-8")
+        return LlamaFactoryCommand(
+            command=["python", "-u", "-m", "compute.engines.llama_factory.eval_runner", "--config", eval_config_path],
+            work_dir="/app",
+            env={},
+        )
+
     errors = validate_config(config)
     if errors:
         raise ValueError("; ".join(errors))

compute/engines/llama_factory/eval_runner.py

@@ -0,0 +1,485 @@
+"""
+Evaluation runner — executes model evaluation as a subprocess job.
+
+Usage:
+    python -m compute.engines.llama_factory.eval_runner --config <config_json_path>
+
+The config JSON is written by the compute API before spawning this subprocess.
+Results are written to ``output_dir/eval_results.json`` and progress is printed
+to stdout (captured as job logs).
+"""
+
+from __future__ import annotations
+
+import json
+import math
+import re
+import sys
+import time
+from difflib import SequenceMatcher
+from pathlib import Path
+from typing import Any
+
+
+def _load_dataset(path: str) -> list[dict[str, Any]]:
+    """Load a JSON or JSONL dataset file.
+
+    Supports common field names used across the platform:
+    * ``instruction`` + ``input`` + ``output``  (Alpaca-style)
+    * ``question`` + ``answer``
+    * ``messages``  (ShareGPT-style – the last assistant message is treated as reference)
+    """
+    file_path = Path(path)
+    text = file_path.read_text(encoding="utf-8", errors="replace").strip()
+    if not text:
+        return []
+    if file_path.suffix.lower() == ".json":
+        value = json.loads(text)
+        if isinstance(value, list):
+            return [item for item in value if isinstance(item, dict)]
+        return [value] if isinstance(value, dict) else []
+
+    samples: list[dict[str, Any]] = []
+    for line in text.splitlines():
+        line = line.strip()
+        if not line:
+            continue
+        try:
+            obj = json.loads(line)
+        except json.JSONDecodeError:
+            continue
+        if isinstance(obj, dict):
+            samples.append(obj)
+    return samples
+
+
+def _sample_question(sample: dict[str, Any]) -> str:
+    """Extract the user-facing question / instruction from a sample."""
+    if sample.get("instruction"):
+        text = sample["instruction"]
+        if sample.get("input"):
+            text += "\n" + sample["input"]
+        return text
+    if sample.get("question"):
+        return sample["question"]
+    # ShareGPT-style: use the last user message as question
+    messages = sample.get("messages") or []
+    user_msgs = [m["content"] for m in messages if m.get("role") == "user"]
+    return user_msgs[-1] if user_msgs else ""
+
+
+def _sample_reference(sample: dict[str, Any]) -> str:
+    """Extract the reference answer from a sample."""
+    if sample.get("output"):
+        return sample["output"]
+    if sample.get("answer"):
+        return sample["answer"]
+    messages = sample.get("messages") or []
+    assistant_msgs = [m["content"] for m in messages if m.get("role") == "assistant"]
+    return assistant_msgs[-1] if assistant_msgs else ""
+
+
+# ---------------------------------------------------------------------------
+# Basic metrics
+# ---------------------------------------------------------------------------
+
+def _compute_bleu(references: list[str], predictions: list[str], ngram: int = 4) -> dict[str, Any]:
+    """Compute BLEU score via sacrebleu (corpus-level)."""
+    try:
+        from sacrebleu.metrics import BLEU
+    except ImportError:
+        return {"enabled": False, "error": "sacrebleu not installed", "score": 0}
+    bleu = BLEU(max_ngram_order=ngram)
+    # sacrebleu expects list-of-strings; we have one reference per prediction
+    score = bleu.corpus_score(predictions, [references])
+    return {
+        "enabled": True,
+        "score": round(score.score, 2),
+        "bleu": round(score.score, 2),
+    }
+
+
+def _compute_rouge(references: list[str], predictions: list[str], methods: list[str] | None = None) -> dict[str, Any]:
+    """Compute ROUGE scores via rouge-score."""
+    try:
+        from rouge_score import rouge_scorer
+    except ImportError:
+        return {"enabled": False, "error": "rouge-score not installed", "score": 0}
+    methods = methods or ["rouge1", "rouge2", "rougeL"]
+    # Normalize: map "rouge_1"/"rouge1" → "rouge1", "rouge_l"/"rougeL" → "rougeL"
+    _rouge_aliases = {"rouge_1": "rouge1", "rouge_2": "rouge2", "rouge_l": "rougeL"}
+    methods = [_rouge_aliases.get(m, m.replace("_", "")) for m in methods]
+    scorer = rouge_scorer.RougeScorer(methods, use_stemmer=True)
+    totals: dict[str, float] = {}
+    n = max(len(predictions), 1)
+    for ref, pred in zip(references, predictions):
+        result = scorer.score(ref, pred)
+        for key in methods:
+            totals[key] = totals.get(key, 0) + result[key].fmeasure
+    avg = {k: round(v / n, 4) for k, v in totals.items()}
+    return {"enabled": True, "score": round(avg.get("rougeL", avg.get("rouge1", 0)) * 100, 2), **avg}
+
+
+def _compute_cosine(references: list[str], predictions: list[str]) -> dict[str, Any]:
+    """Compute average cosine similarity via sklearn."""
+    try:
+        from sklearn.feature_extraction.text import TfidfVectorizer
+        from sklearn.metrics.pairwise import cosine_similarity
+    except ImportError:
+        return {"enabled": False, "error": "scikit-learn not installed", "score": 0}
+    try:
+        vectorizer = TfidfVectorizer()
+        tfidf = vectorizer.fit_transform(references + predictions)
+        n = len(references)
+        ref_vec = tfidf[:n]
+        pred_vec = tfidf[n:]
+        sims = cosine_similarity(ref_vec, pred_vec).diagonal()
+        return {"enabled": True, "score": round(float(sims.mean()) * 100, 2)}
+    except ValueError:
+        return {"enabled": True, "score": 0, "error": "insufficient text for vectorization"}
+
+
+def _normalize_text(value: str) -> str:
+    return re.sub(r"\s+", " ", str(value or "").strip().lower())
+
+
+def _compute_exact_match(references: list[str], predictions: list[str]) -> dict[str, Any]:
+    total = len(predictions)
+    if not total:
+        return {"enabled": True, "score": 0, "matched": 0, "total": 0}
+    matched = sum(
+        1
+        for ref, pred in zip(references, predictions)
+        if _normalize_text(ref) == _normalize_text(pred)
+    )
+    return {"enabled": True, "score": round(matched / total * 100, 2), "matched": matched, "total": total}
+
+
+def _compute_text_similarity(references: list[str], predictions: list[str]) -> dict[str, Any]:
+    if not predictions:
+        return {"enabled": True, "score": 0}
+    scores = [
+        SequenceMatcher(None, _normalize_text(ref), _normalize_text(pred)).ratio()
+        for ref, pred in zip(references, predictions)
+    ]
+    return {"enabled": True, "score": round(sum(scores) / max(len(scores), 1) * 100, 2)}
+
+
+# ---------------------------------------------------------------------------
+# LLM Judge
+# ---------------------------------------------------------------------------
+
+def _judge_sample(
+    question: str,
+    reference: str,
+    prediction: str,
+    config: dict[str, Any],
+) -> dict[str, Any]:
+    """Call an OpenAI-compatible LLM to judge a single sample.
+
+    Returns a dict with keys:
+        score, max_score, passed, judgement, evaluation_reason, error_type
+    """
+    api_url = (config.get("api_url") or "").strip().rstrip("/")
+    api_key = (config.get("api_key") or "").strip()
+    eval_model = (config.get("eval_model") or "").strip()
+    # 优先使用模型记录里配置的真实 API 模型名（如 deepseek-chat），
+    # 否则回退到平台内部模型名
+    api_model = (config.get("api_model") or "").strip() or eval_model
+    eval_prompt = (config.get("eval_prompt") or "").strip()
+    score_min = float(config.get("score_min", 0))
+    score_max = float(config.get("score_max", 5))
+    pass_threshold = float(config.get("pass_threshold", 3))
+
+    if not api_url or not eval_model:
+        return {"score": 0, "max_score": score_max, "passed": False, "judgement": "未配置",
+                "evaluation_reason": "未配置评测模型", "error_type": "其他"}
+
+    system_msg = (
+        eval_prompt
+        or "你是一个专业的评测专家。请根据参考答-案对被测模型的输出进行评分。"
+    )
+    user_msg = (
+        f"## 问题\n{question}\n\n"
+        f"## 参考答案\n{reference}\n\n"
+        f"## 模型输出\n{prediction}\n\n"
+        f"请给出 {score_min}-{score_max} 分的评分，并说明理由。"
+    )
+
+    try:
+        import urllib.request
+        import urllib.error
+
+        body = json.dumps({
+            "model": api_model,
+            "messages": [
+                {"role": "system", "content": system_msg},
+                {"role": "user", "content": user_msg},
+            ],
+            "temperature": 0.3,
+            "max_tokens": 512,
+        }).encode("utf-8")
+
+        req = urllib.request.Request(
+            f"{api_url}/v1/chat/completions",
+            data=body,
+            headers={
+                "Content-Type": "application/json",
+                "Authorization": f"Bearer {api_key}",
+            },
+        )
+        resp = urllib.request.urlopen(req, timeout=120)
+        data = json.loads(resp.read().decode("utf-8"))
+        reply = data["choices"][0]["message"]["content"]
+    except Exception as exc:
+        return {"score": 0, "max_score": score_max, "passed": False,
+                "judgement": "错误", "evaluation_reason": f"评测模型调用失败: {exc}",
+                "error_type": "其他"}
+
+    # Parse score from reply — look for patterns like "4分" or "Score: 4"
+    score = 0
+    import re
+    score_patterns = [
+        r'(?:得分|分数|评分|score)[^\d]*(\d+(?:\.\d+)?)',
+        r'(\d+(?:\.\d+)?)\s*分',
+        r'(\d+(?:\.\d+)?)\s*/\s*\d+',
+    ]
+    for pat in score_patterns:
+        m = re.search(pat, reply, re.IGNORECASE)
+        if m:
+            try:
+                score = float(m.group(1))
+            except ValueError:
+                continue
+            break
+    score = max(score_min, min(score_max, score))
+    passed = score >= pass_threshold
+
+    # Determine judgement label
+    if score >= pass_threshold + 1:
+        judgement = "正确"
+    elif score >= pass_threshold:
+        judgement = "部分正确"
+    else:
+        judgement = "错误"
+
+    # Guess error type from reply
+    reply_lower = reply.lower()
+    if any(w in reply_lower for w in ["幻觉", "hallucination", "编造"]):
+        error_type = "幻觉"
+    elif any(w in reply_lower for w in ["不完整", "incomplete", "遗漏"]):
+        error_type = "不完整"
+    elif any(w in reply_lower for w in ["格式", "format"]):
+        error_type = "格式偏差"
+    elif any(w in reply_lower for w in ["混淆", "confusion", "错误"]):
+        error_type = "混淆"
+    else:
+        error_type = "其他"
+
+    return {
+        "score": score,
+        "max_score": score_max,
+        "passed": passed,
+        "judgement": judgement,
+        "evaluation_reason": reply[:2000],
+        "error_type": error_type,
+    }
+
+
+# ---------------------------------------------------------------------------
+# Main entry point
+# ---------------------------------------------------------------------------
+
+def run_eval(config: dict[str, Any]) -> dict[str, Any]:
+    """Execute a full evaluation run.  Returns the result dict (also written to file)."""
+    model_path = config["model_name_or_path"]
+    adapter_path = config.get("adapter_name_or_path", "")
+    template = config.get("template", "qwen")
+    dataset_path = config["dataset_path"]
+    output_dir = Path(config["output_dir"])
+    output_dir.mkdir(parents=True, exist_ok=True)
+    basic_cfg = config.get("basic_metrics", {})
+    dimension_cfg = config.get("dimension", {}) or {}
+    output_precision = int(basic_cfg.get("output_precision", 2))
+
+    # ---- 1. Load dataset ----
+    print(f"[eval] loading dataset: {dataset_path}")
+    raw_samples = _load_dataset(dataset_path)
+    print(f"[eval] loaded {len(raw_samples)} samples")
+
+    # ---- 2. Load model ----
+    print(f"[eval] loading model: {model_path}")
+    from compute.engines.llama_factory.inference import InferenceSession
+    session = InferenceSession()
+    session.load(
+        model_name_or_path=model_path,
+        adapter_name_or_path=adapter_path,
+        template=template,
+        infer_backend=config.get("infer_backend", "huggingface"),
+        infer_dtype=config.get("infer_dtype", "auto"),
+    )
+    # load() 为异步加载（立即返回 loading），必须等待后台线程完成后再进行推理
+    load_result = session.wait_until_loaded(timeout=float(config.get("load_timeout", 1800)))
+    if not load_result.get("loaded"):
+        raise RuntimeError(f"model load failed: {load_result.get('error', 'unknown')}")
+    print(f"[eval] model loaded OK")
+
+    # ---- 3. Run inference on each sample ----
+    samples: list[dict[str, Any]] = []
+    predictions: list[str] = []
+    references: list[str] = []
+    questions: list[str] = []
+
+    total = len(raw_samples)
+    judge_enabled = bool(dimension_cfg.get("eval_model") and dimension_cfg.get("api_url"))
+    print(f"[eval] starting inference on {total} samples, judge={'enabled' if judge_enabled else 'disabled'}")
+
+    for idx, raw in enumerate(raw_samples, start=1):
+        question = _sample_question(raw)
+        reference = _sample_reference(raw)
+        if not question:
+            print(f"[eval] sample {idx}/{total}: skipped (no question)")
+            continue
+
+        # Inference
+        chat_msgs = [{"role": "user", "content": question}]
+        result = session.chat(
+            chat_msgs,
+            temperature=float(config.get("temperature", 0.1)),
+            top_p=float(config.get("top_p", 0.95)),
+            max_new_tokens=int(config.get("max_new_tokens", 512)),
+            do_sample=False,
+        )
+        prediction = result.get("response", "") if not result.get("error") else f"[ERROR] {result['error']}"
+
+        predictions.append(prediction)
+        references.append(reference)
+        questions.append(question)
+
+        # LLM Judge
+        judge_result: dict[str, Any] = {}
+        if judge_enabled:
+            judge_result = _judge_sample(question, reference, prediction, dimension_cfg)
+
+        samples.append({
+            "index": idx,
+            "input": question,
+            "reference_answer": reference,
+            "model_output": prediction,
+            "score": judge_result.get("score"),
+            "max_score": judge_result.get("max_score", dimension_cfg.get("score_max", 5)),
+            "passed": judge_result.get("passed"),
+            "judgement": judge_result.get("judgement"),
+            "evaluation_reason": judge_result.get("evaluation_reason", ""),
+            "error_type": judge_result.get("error_type"),
+            "dimension_scores": [
+                {"name": "judge_score", "score": judge_result.get("score", 0),
+                 "max_score": judge_result.get("max_score", dimension_cfg.get("score_max", 5))},
+            ] if judge_result else [],
+            "status": "completed",
+        })
+
+        progress_pct = int(idx / max(total, 1) * 100)
+        print(f"[eval] sample {idx}/{total} ({progress_pct}%) done")
+
+    # ---- 4. Compute basic metrics ----
+    print(f"[eval] computing basic metrics on {len(predictions)} predictions")
+    metrics_result: dict[str, Any] = {}
+
+    bleu_cfg = basic_cfg.get("bleu", {})
+    if bleu_cfg.get("enabled"):
+        metrics_result["bleu"] = _compute_bleu(references, predictions, int(bleu_cfg.get("ngram", 4)))
+
+    rouge_cfg = basic_cfg.get("rouge", {})
+    if rouge_cfg.get("enabled"):
+        metrics_result["rouge"] = _compute_rouge(references, predictions, rouge_cfg.get("methods"))
+
+    cosine_cfg = basic_cfg.get("cosine", {})
+    if cosine_cfg.get("enabled"):
+        metrics_result["cosine"] = _compute_cosine(references, predictions)
+    metrics_result["exact_match"] = _compute_exact_match(references, predictions)
+    metrics_result["text_similarity"] = _compute_text_similarity(references, predictions)
+
+    # ---- 5. Summarise ----
+    completed = len(samples)
+    if judge_enabled:
+        scored = [s for s in samples if s.get("score") is not None]
+        passed_count = len([s for s in scored if s.get("passed")])
+        avg_score = round(sum(s["score"] for s in scored) / max(len(scored), 1), output_precision)
+        max_score = dimension_cfg.get("score_max", 5)
+        overall_score = round(avg_score / max_score * 100, output_precision)
+        overall_score_max = 100
+        dimension_summary = [{
+            "name": "综合评分",
+            "score": overall_score,
+            "max_score": 100,
+            "pass_rate": round(passed_count / max(completed, 1) * 100, 1),
+        }]
+        overall_evaluation = f"评测完成：{completed} 样本，{passed_count} 通过，平均 {avg_score}/{max_score} 分"
+    else:
+        passed_count = 0
+        enabled_scores = [
+            float(item.get("score") or 0)
+            for item in metrics_result.values()
+            if isinstance(item, dict) and item.get("enabled", True) and item.get("score") is not None
+        ]
+        overall_score = round(sum(enabled_scores) / len(enabled_scores), output_precision) if enabled_scores else 0
+        overall_score_max = 100
+        dimension_summary = [
+            {
+                "name": name,
+                "score": float(item.get("score") or 0),
+                "max_score": 100,
+                "pass_rate": float(item.get("score") or 0),
+            }
+            for name, item in metrics_result.items()
+            if isinstance(item, dict) and item.get("enabled", True) and item.get("score") is not None
+        ]
+        overall_evaluation = f"评测完成：{completed} 样本（未配置 LLM 评委）"
+
+    result = {
+        "overall_score": overall_score,
+        "overall_score_max": overall_score_max,
+        "overall_evaluation": overall_evaluation,
+        "improvement_suggestions": [],
+        "dimension_summary": dimension_summary,
+        "samples": samples,
+        "sample_count": total,
+        "completed_count": completed,
+        "passed_count": passed_count,
+        "basic_metrics": metrics_result,
+    }
+
+    # ---- 6. Write results ----
+    result_path = output_dir / "eval_results.json"
+    result_path.write_text(json.dumps(result, ensure_ascii=False, indent=2), encoding="utf-8")
+    print(f"[eval] results written to {result_path}")
+    return result
+
+
+def main() -> None:
+    import argparse
+    parser = argparse.ArgumentParser(description="YG-FT Evaluation Runner")
+    parser.add_argument("--config", required=True, help="Path to eval config JSON file")
+    args = parser.parse_args()
+
+    config_path = Path(args.config)
+    if not config_path.exists():
+        print(f"FATAL: config file not found: {args.config}", file=sys.stderr)
+        sys.exit(1)
+
+    config = json.loads(config_path.read_text(encoding="utf-8"))
+    start = time.time()
+    try:
+        run_eval(config)
+        elapsed = time.time() - start
+        print(f"[eval] DONE in {elapsed:.1f}s")
+    except Exception as exc:
+        print(f"[eval] FAILED: {exc}", file=sys.stderr)
+        import traceback
+        traceback.print_exc()
+        sys.exit(1)
+
+
+if __name__ == "__main__":
+    main()

compute/engines/llama_factory/inference.py

@@ -0,0 +1,272 @@
+from __future__ import annotations
+
+import threading
+import time
+import uuid
+from typing import Any, Iterator
+
+
+class InferenceSession:
+    """Manages a loaded model for inference with LLaMA-Factory ChatModel.
+
+    Model loading is asynchronous: ``load()`` spawns a background daemon thread
+    and returns immediately with ``status == "loading"``. ``info()`` (served by
+    ``/inference/status``) is always responsive, so the platform backend can
+    poll loading progress without being blocked by a minutes-long model load —
+    which previously froze the whole compute node event loop.
+
+    State machine: idle -> loading -> ready | error, ready -> idle (unload),
+    loading -> idle (cancelled). Long operations (ChatModel build, teardown,
+    generation) never run while holding ``_state_lock``; they either run in the
+    worker thread or under ``_chat_lock`` only.
+    """
+
+    def __init__(self) -> None:
+        self._state_lock = threading.Lock()  # brief state transitions only
+        self._chat_lock = threading.Lock()  # serialize chat/teardown
+        self._status: str = "idle"
+        self._error: str = ""
+        self._request_id: str = ""
+        self._load_args: dict[str, Any] = {}
+        self._teardown_old = False  # load-while-ready: unload old before loading new
+        self._cancel_requested = False  # unload-while-loading: tear down after load finishes
+        self._load_thread: threading.Thread | None = None
+        self._model: Any = None
+        self._tokenizer: Any = None
+        self._generating_args: dict[str, Any] = {}
+        self._model_name: str = ""
+        self._adapter_path: str = ""
+        self._loaded_at: float = 0.0
+
+    @property
+    def status(self) -> str:
+        with self._state_lock:
+            return self._status
+
+    def info(self) -> dict[str, Any]:
+        with self._state_lock:
+            return {
+                "loaded": self._status == "ready",
+                "status": self._status,
+                "model_name": self._model_name,
+                "adapter_path": self._adapter_path,
+                "loaded_at": self._loaded_at,
+                "request_id": self._request_id,
+                "error": self._error,
+            }
+
+    def wait_until_loaded(self, timeout: float | None = None) -> dict[str, Any]:
+        """Wait for an in-flight async load to finish and return its outcome.
+
+        供同步消费方（如 eval_runner 子进程）使用：``load()`` 立即返回 loading 后，
+        调用本方法等待后台加载线程完成，拿到最终的 loaded/error 结果。
+        若在 timeout 秒内仍未加载完成，返回 ``status == "loading"`` 并附上超时提示。
+        """
+        with self._state_lock:
+            thread = self._load_thread
+        if thread is not None and thread.is_alive():
+            thread.join(timeout=timeout)
+        with self._state_lock:
+            loaded = self._status == "ready"
+            status = self._status
+            error = self._error
+        if not loaded and status == "loading":
+            error = error or f"model load timed out after {timeout or 'N/A'}s"
+        return {
+            "loaded": loaded,
+            "status": status,
+            "model_name": self._model_name,
+            "adapter_path": self._adapter_path,
+            "error": error,
+        }
+
+    def load(
+        self,
+        model_name_or_path,
+        adapter_name_or_path="",
+        template="qwen",
+        infer_backend="huggingface",
+        infer_dtype="auto",
+        **kwargs,
+    ) -> dict[str, Any]:
+        with self._state_lock:
+            if self._status == "loading":
+                # A model is already loading — dedupe, reuse the same request id.
+                return {"loaded": False, "status": "loading", "request_id": self._request_id}
+            self._teardown_old = self._status == "ready"
+            self._status = "loading"
+            self._error = ""
+            self._request_id = uuid.uuid4().hex[:12]
+            self._cancel_requested = False
+            self._load_args = {
+                "model_name_or_path": model_name_or_path,
+                "template": template,
+                "infer_backend": infer_backend,
+                "infer_dtype": infer_dtype,
+            }
+            if adapter_name_or_path:
+                self._load_args["adapter_name_or_path"] = adapter_name_or_path
+            self._load_args.update(kwargs)
+            self._model_name = model_name_or_path
+            self._adapter_path = adapter_name_or_path
+            self._load_thread = threading.Thread(target=self._load_worker, daemon=True)
+            self._load_thread.start()
+            return {"loaded": False, "status": "loading", "request_id": self._request_id}
+
+    def _load_worker(self) -> None:
+        """Build the ChatModel off the state lock so info() never blocks."""
+        model = None
+        tokenizer = None
+        generating_args: dict[str, Any] = {}
+        error = ""
+        try:
+            if self._teardown_old:
+                self._release_model()
+            from llamafactory.chat import ChatModel
+            from llamafactory.hparams import get_infer_args
+
+            args = dict(self._load_args)
+            infer_result = get_infer_args(args)
+            model = ChatModel(args)
+            tokenizer = getattr(model, "tokenizer", None) or model.engine.tokenizer
+            generating_args = infer_result[-1]
+            if hasattr(generating_args, "__dataclass_fields__"):
+                generating_args = {
+                    k: v for k, v in vars(generating_args).items() if not k.startswith("_")
+                }
+            else:
+                generating_args = dict(generating_args)
+        except Exception as exc:  # noqa: BLE001 - surface load failure via status
+            error = str(exc)
+        with self._state_lock:
+            if error:
+                self._model = None
+                self._tokenizer = None
+                self._status = "error"
+                self._error = error
+                return
+            if self._cancel_requested:
+                # Unload was requested while loading — drop the fresh model.
+                model = None
+                tokenizer = None
+                self._model = None
+                self._tokenizer = None
+                self._status = "idle"
+                return
+            self._model = model
+            self._tokenizer = tokenizer
+            self._generating_args = generating_args
+            self._loaded_at = time.time()
+            self._status = "ready"
+
+    def _release_model(self) -> None:
+        with self._chat_lock:
+            with self._state_lock:
+                self._status = "unloading"
+                model = self._model
+                self._model = None
+                self._tokenizer = None
+            if model is not None:
+                try:
+                    del model
+                except Exception:  # noqa: BLE001 - best-effort teardown
+                    pass
+                # 强制释放 PyTorch CUDA 缓存，真正归还 GPU 显存
+                try:
+                    import gc
+
+                    gc.collect()
+                    import torch
+
+                    if torch.cuda.is_available():
+                        torch.cuda.empty_cache()
+                        torch.cuda.synchronize()
+                except Exception:  # noqa: BLE001 - teardown must not raise
+                    pass
+            with self._state_lock:
+                self._status = "idle"
+                self._model_name = ""
+                self._adapter_path = ""
+                self._loaded_at = 0.0
+                self._error = ""
+
+    def unload(self) -> dict[str, Any]:
+        with self._state_lock:
+            if self._status == "loading":
+                # Ask the worker to tear down right after the load finishes.
+                self._cancel_requested = True
+                return {"unloaded": False, "status": "cancelling", "request_id": self._request_id}
+            was_ready = self._status == "ready"
+        if was_ready:
+            self._release_model()
+        else:
+            with self._state_lock:
+                self._model = None
+                self._tokenizer = None
+                self._status = "idle"
+                self._model_name = ""
+                self._adapter_path = ""
+                self._loaded_at = 0.0
+                self._error = ""
+        return {"unloaded": True, "status": "idle"}
+
+    def chat(self, messages, temperature=0.95, top_p=0.7, max_new_tokens=1024, do_sample=True, **kwargs) -> dict[str, Any]:
+        with self._chat_lock:
+            with self._state_lock:
+                if self._status == "loading":
+                    return {
+                        "error": f"model is still loading (request_id={self._request_id}); please retry",
+                        "response": "",
+                    }
+                if self._status == "error":
+                    return {"error": f"model load failed: {self._error}", "response": ""}
+                if self._status != "ready" or self._model is None:
+                    return {"error": "model not loaded", "response": ""}
+            try:
+                generate_kwargs = {
+                    "temperature": temperature,
+                    "top_p": top_p,
+                    "max_new_tokens": max_new_tokens,
+                    "do_sample": do_sample,
+                }
+                generate_kwargs.update(kwargs)
+                system = next((m["content"] for m in messages if m["role"] == "system"), None)
+                user_messages = [m for m in messages if m["role"] != "system"]
+                responses = []
+                for response in self._model.stream_chat(user_messages, system=system, **generate_kwargs):
+                    responses.append(response)
+                full_response = "".join(str(r) for r in responses)
+                return {"response": full_response}
+            except Exception as exc:  # noqa: BLE001 - return generation error to caller
+                return {"error": str(exc), "response": ""}
+
+    def chat_stream(self, messages, **kwargs) -> Iterator[str]:
+        with self._chat_lock:
+            with self._state_lock:
+                if self._status == "loading":
+                    yield 'data: {"error": "model is still loading; please retry"}\n\n'
+                    return
+                if self._status == "error":
+                    yield 'data: {"error": "model load failed: ' + str(self._error) + '"}\n\n'
+                    return
+                if self._status != "ready" or self._model is None:
+                    yield 'data: {"error": "model not loaded"}\n\n'
+                    return
+            try:
+                generate_kwargs = {**kwargs}
+                system = next((m["content"] for m in messages if m["role"] == "system"), None)
+                user_messages = [m for m in messages if m["role"] != "system"]
+                for new_text in self._model.stream_chat(user_messages, system=system, **generate_kwargs):
+                    yield new_text
+            except Exception as exc:  # noqa: BLE001 - stream error as SSE event
+                yield 'data: {"error": "' + str(exc) + '"}\n\n'
+
+
+_inference_session = None
+
+
+def get_inference_session() -> InferenceSession:
+    global _inference_session
+    if _inference_session is None:
+        _inference_session = InferenceSession()
+    return _inference_session

compute/requirements.txt

@@ -4,3 +4,9 @@ python-multipart>=0.0.9
 pydantic>=2.7.0
 python-dotenv>=1.0.1
 httpx>=0.27.0
+# 模型评测指标
+sacrebleu>=2.4.0
+rouge-score>=0.1.2
+scikit-learn>=1.3.0
+# LLaMA-Factory 训练引擎
+llamafactory

compute/tests/test_inference_session.py

@@ -0,0 +1,146 @@
+from __future__ import annotations
+
+import sys
+import time
+import types
+from typing import Any
+
+import pytest
+
+from compute.engines.llama_factory.inference import InferenceSession
+
+# 模拟模型加载耗时，用于验证 load() 立即返回、info() 不阻塞
+LOAD_DELAY = 0.2
+
+
+class FakeChatModel:
+    def __init__(self, args: dict[str, Any]) -> None:
+        time.sleep(LOAD_DELAY)
+        self.tokenizer = object()
+        self.engine = types.SimpleNamespace(tokenizer=object())
+        self._output = "hello from model"
+
+    def stream_chat(self, *args, **kwargs):
+        for _ in range(1):
+            yield self._output
+
+
+class FailingChatModel:
+    def __init__(self, args: dict[str, Any]) -> None:
+        time.sleep(LOAD_DELAY)
+        raise RuntimeError("boom: fake load failure")
+
+
+def _get_infer_args(args: dict[str, Any]) -> list[Any]:
+    # 最后一个元素为 generating_args，worker 会转成 dict
+    return [None, None, {"temperature": 0.7}]
+
+
+def _install_llamafactory(monkeypatch, chat_model: type) -> None:
+    llmf = types.ModuleType("llamafactory")
+    chat_mod = types.ModuleType("llamafactory.chat")
+    hparams_mod = types.ModuleType("llamafactory.hparams")
+    chat_mod.ChatModel = chat_model
+    hparams_mod.get_infer_args = _get_infer_args
+    llmf.chat = chat_mod
+    llmf.hparams = hparams_mod
+    monkeypatch.setitem(sys.modules, "llamafactory", llmf)
+    monkeypatch.setitem(sys.modules, "llamafactory.chat", chat_mod)
+    monkeypatch.setitem(sys.modules, "llamafactory.hparams", hparams_mod)
+
+
+@pytest.fixture
+def stub_llamafactory(monkeypatch) -> None:
+    _install_llamafactory(monkeypatch, FakeChatModel)
+
+
+@pytest.fixture
+def stub_failing_llamafactory(monkeypatch) -> None:
+    _install_llamafactory(monkeypatch, FailingChatModel)
+
+
+def _wait_for_status(session: InferenceSession, status: str, timeout: float = 3.0) -> bool:
+    deadline = time.time() + timeout
+    while time.time() < deadline:
+        if session.info()["status"] == status:
+            return True
+        time.sleep(0.02)
+    return False
+
+
+def test_load_returns_immediately_then_ready(stub_llamafactory) -> None:
+    session = InferenceSession()
+    started = time.time()
+    result = session.load("/models/qwen")
+    assert result["status"] == "loading"
+    assert result["loaded"] is False
+    assert result["request_id"]
+    # 在慢加载完成前就返回，且 info() 加载期间可响应
+    assert time.time() - started < LOAD_DELAY
+    assert session.info()["status"] == "loading"
+    assert _wait_for_status(session, "ready")
+    info = session.info()
+    assert info["loaded"] is True
+    assert info["status"] == "ready"
+    assert info["model_name"] == "/models/qwen"
+
+
+def test_second_load_while_loading_deduped(stub_llamafactory) -> None:
+    session = InferenceSession()
+    r1 = session.load("/models/a")
+    r2 = session.load("/models/b")
+    assert r2["status"] == "loading"
+    assert r2["request_id"] == r1["request_id"]
+    assert _wait_for_status(session, "ready")
+    assert session.info()["status"] == "ready"
+
+
+def test_load_error_surfaces_in_status(stub_failing_llamafactory) -> None:
+    session = InferenceSession()
+    session.load("/models/bad")
+    assert _wait_for_status(session, "error")
+    assert "boom" in session.info()["error"]
+
+
+def test_unload_while_loading_cancels(stub_llamafactory) -> None:
+    session = InferenceSession()
+    session.load("/models/qwen")
+    result = session.unload()
+    assert result["status"] == "cancelling"
+    assert _wait_for_status(session, "idle")
+
+
+def test_chat_while_loading_returns_loading_error(stub_llamafactory) -> None:
+    session = InferenceSession()
+    session.load("/models/qwen")
+    out = session.chat([{"role": "user", "content": "hi"}])
+    assert "still loading" in (out.get("error") or "")
+    assert _wait_for_status(session, "ready")
+    out = session.chat([{"role": "user", "content": "hi"}])
+    assert out.get("response") == "hello from model"
+
+
+def test_chat_stream_while_loading_yields_error(stub_llamafactory) -> None:
+    session = InferenceSession()
+    session.load("/models/qwen")
+    chunks = list(session.chat_stream([{"role": "user", "content": "hi"}]))
+    assert any("still loading" in c for c in chunks)
+
+
+def test_wait_until_loaded_blocks_until_ready(stub_llamafactory) -> None:
+    session = InferenceSession()
+    result = session.load("/models/qwen")
+    assert result["status"] == "loading"
+    # 同步等待后台加载线程完成
+    outcome = session.wait_until_loaded(timeout=3.0)
+    assert outcome["loaded"] is True
+    assert outcome["status"] == "ready"
+
+
+def test_wait_until_loaded_reports_load_error(stub_failing_llamafactory) -> None:
+    session = InferenceSession()
+    session.load("/models/bad")
+    outcome = session.wait_until_loaded(timeout=3.0)
+    assert outcome["loaded"] is False
+    assert outcome["status"] == "error"
+    assert "boom" in outcome["error"]

design-qa.md

@@ -328,6 +328,57 @@ final result: blocked
 
 ---
 
+# Failed Result Regeneration Design QA
+
+## Evidence
+
+- Source visual truth: `/var/folders/nk/yks07zp14wb4rv3jqq0pt_4h0000gn/T/codex-clipboard-0c2e6f90-aaac-4817-9084-bc31496aed0a.png`.
+- Implementation route: `http://localhost:16801/data-process/:id/workflow`, step 6.
+- Browser evidence: `/Users/caoxiaozhu/.codex/visualizations/2026/07/27/019fa277-626b-76a1-af02-48948d66c7ec/data-process-empty-list.png`.
+- Viewport: 1280 × 720.
+- Target state: a completed task on step 6 with a selected invalid result.
+- Available browser state: authenticated data-process list with zero tasks; no representative invalid result could be opened without creating or mutating local business data.
+
+## Static and automated evidence
+
+- Invalid results render a primary plain `重新生成` button in the right side of the result header.
+- Valid results keep the existing `恢复生成结果` action.
+- While regeneration is running, the selected row shows a spinner, the button shows loading, editors are disabled, and the footer confirmation action is disabled.
+- A successful response replaces only the selected row in place; a failed second generation leaves the original invalid row untouched.
+- `regression-data-process-wizard.mjs`: passed.
+- `regression-data-process-detail.mjs`: passed.
+- `regression-data-process-list.mjs`: passed.
+- `vue-tsc -b --noEmit`: passed.
+- Relevant backend tests: 97 passed, with one third-party deprecation warning.
+
+## Required fidelity surfaces
+
+- Typography and hierarchy: the action uses the existing Element Plus small-button hierarchy and remains secondary to result content.
+- Spacing and layout rhythm: the action is placed in the existing flex header's right action slot, matching the source location.
+- Colors and tokens: the action uses the existing product primary color and existing Font Awesome refresh icon.
+- Copy and content: the visible label is exactly `重新生成`; only server-saved invalid results expose it.
+- Interaction: optimistic concurrency protects against overwriting a newer edit, and persistence happens only after the replacement passes generation and quality validation.
+
+## Findings
+
+- [P2] Representative rendered comparison unavailable
+  Location: step 6 result header with an invalid result selected.
+  Evidence: the authenticated local database currently contains zero data-processing tasks, so the target state cannot be reached without creating test business data or invoking the configured model.
+  Impact: automated and static checks prove the contract and placement, but cannot prove pixel-level spacing against the supplied screenshot.
+  Fix: open any existing failed result after one is available, capture the same 1280 × 720 state, and compare it side by side with the source screenshot.
+
+## Comparison history
+
+### Iteration 1 — blocked
+
+- Source screenshot was inspected and the implementation was aligned to its existing right-header action slot.
+- Local login and list navigation succeeded.
+- The target result state was unavailable because the local task list was empty.
+
+final result: blocked
+
+---
+
 # Dataset Version Actions Design QA
 
 ## Evidence

docker/app/Dockerfile.backend

@@ -11,7 +11,7 @@ RUN pip install --upgrade pip -i https://pypi.tuna.tsinghua.edu.cn/simple \
     && pip install -r /tmp/requirements.txt -i https://pypi.tuna.tsinghua.edu.cn/simple \
     && rm -f /tmp/requirements.txt
 
-RUN python -c "import fastapi, uvicorn, psycopg, sqlalchemy, redis, jwt, passlib, httpx, alembic; print('backend dependency check ok')"
+RUN python -c "import fastapi, uvicorn, psycopg, psycopg_pool, sqlalchemy, redis, jwt, passlib, httpx, alembic; print('backend dependency check ok')"
 
 RUN mkdir -p /opt/yg-ft/logs/backend /data/yg-ft \
     && chmod -R 0775 /opt/yg-ft /data/yg-ft

docker/compute/.env

@@ -35,6 +35,6 @@ COMPUTE_GPU_MEMORY_GB=80
 COMPUTE_GPU_POWER_LIMIT_W=300
 
 LOG_DIR=/opt/yg-ft/logs/compute
-CUDA_VISIBLE_DEVICES=all
+CUDA_VISIBLE_DEVICES=0
 NVIDIA_VISIBLE_DEVICES=all
 NVIDIA_DRIVER_CAPABILITIES=compute,utility

docker/nginx.conf.template

@@ -14,8 +14,8 @@ server {
     proxy_set_header X-Real-IP $remote_addr;
     proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
     proxy_set_header X-Forwarded-Proto $scheme;
-    proxy_read_timeout 300s;
-    proxy_send_timeout 300s;
+    proxy_read_timeout 900s;
+    proxy_send_timeout 900s;
   }
 
   location = /modelTF {
@@ -25,8 +25,8 @@ server {
     proxy_set_header X-Real-IP $remote_addr;
     proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
     proxy_set_header X-Forwarded-Proto $scheme;
-    proxy_read_timeout 300s;
-    proxy_send_timeout 300s;
+    proxy_read_timeout 900s;
+    proxy_send_timeout 900s;
   }
 
   location ~* \.(?:js|css|png|jpg|jpeg|gif|ico|svg|woff|woff2|ttf)$ {

docs/模型评测功能总结.md

@@ -0,0 +1,121 @@
+# 模型评测功能总结
+
+本项目（基于 LLaMA-Factory 的微调训练平台）包含 **4 套相对独立** 的模型评测能力，分别面向不同的使用场景：
+
+| 能力 | 入口/目录 | 评测类型 | 打分方式 |
+| --- | --- | --- | --- |
+| 1. 学术 Benchmark 评测 | `llamafactory/eval/` | 选择题式基准（类 MMLU/C-Eval） | 选项匹配 + few-shot |
+| 2. 评估工作台 | `backend/app/api/v1/eval/` | 生成式问答（指令跟随） | BLEU / ROUGE / ExactMatch + 可选 LLM 评审 |
+| 3. 平台评估系统 | `backend/app/api/v1/evaluation/` | 基于评估数据集的问答 | 判卷模型（judge model）打分（0–5 分） |
+| 4. 训练时验证评估 | `backend/app/services/task_runner.py` | 训练验证集 | loss 指标 |
+
+下面分别说明。
+
+---
+
+## 1. 学术 Benchmark 评测（LLaMA-Factory 原生）
+
+面向标准学术选择题基准（如 MMLU、C-Eval 等），复用 LLaMA-Factory 原生的评测框架。
+
+**核心文件**
+- `llamafactory/eval/evaluator.py`：`Evaluator` 类 + `run_eval()` 入口
+- `llamafactory/eval/template.py`：评测 prompt 模板（中/英，含 few-shot 示例构建）
+- `llamafactory/hparams/evaluation_args.py`：`EvaluationArguments` 配置类
+
+**工作流程**
+1. 按 `task`（benchmark 名称）加载数据集，按科目（subject）拆分。
+2. 每个样本构造 few-shot 提示词（`n_shot` 控制示例数，由 `lang` 决定中/英模板），将题干与候选选项拼入 prompt。
+3. 调用模型推理得到预测，与标准答案比对，统计每个科目及整体的 `accuracy`。
+4. 结果写入 `save_dir`，打印各科目与平均准确率。
+
+**关键参数（`EvaluationArguments`）**
+- `task`：基准数据集名
+- `batch_size` / `n_shot` / `lang` / `save_dir` / `seed`
+- `model_name_or_path`、`template`、`trust_remote_code` 等模型相关参数
+
+> 该能力属于框架底层，本平台前端未直接提供操作入口，主要通过配置文件/脚本调用。
+
+---
+
+## 2. 评估工作台（生成式评测 + 指标计算）
+
+后端路由位于 `backend/app/api/v1/eval/__init__.py`，前端称为「评估工作台」。**适用于评测模型的指令跟随与生成质量**，并支持 LLM 作为裁判（LLM-as-a-Judge）。
+
+**API 端点**
+- `GET  /evaluation/tasks`：列出评测任务（`frontend/src/api/evaluation.ts:listTasks`）
+- `POST /evaluation/run`：提交一次评测（`runEval`）
+- `GET  /evaluation/report/{task_id}`：拉取评测报告（`getReport`）
+- `DELETE /evaluation/tasks/{task_id}`：删除任务（`deleteTask`）
+
+**评测流程（`run_eval`）**
+1. 通过 **LLaMA-Factory 数据管道**（`get_dataset`) 加载数据集，支持 `subset` 与抽样（`eval_sample`）。
+2. 用 **原生 transformers** 加载模型在本地做生成推理（单进程顺序生成，便于展示样本）。
+3. 计算客观指标（`compute_score`）：
+   - `BLEU`（sacrebleu）
+   - `ROUGE-1 / ROUGE-2 / ROUGE-L`（rouge-score）
+   - `Exact Match`
+4. **可选 LLM 评审**（judge）：当配置了 `judge_model` / `judge_api_base` / `judge_api_key` 时，调用 OpenAI 兼容接口对每条样本打分（10 分制），并输出 4 个维度与理由：
+   - 核心事实正确性 `factual`
+   - 信息完整性 `completeness`
+   - 无幻觉 `no_hallucination`
+   - 格式合规性 `format`
+   - 综合分 `score` + `reason`
+5. 任务状态持久化在后端 `eval_tasks.json`（支持 running/completed/failed/stopped），前端轮询进度。
+
+**前端页面**
+- `frontend/src/views/evaluation/EvaluateTask.vue`：任务列表、创建评测对话框（选模型、数据集、指标、可选 judge 配置）
+- `frontend/src/views/evaluation/EvaluateReport.vue`：报告页，展示综合得分、BLEU、ROUGE-L、各维度指标及「参考答案 vs 模型预测 vs LLM 评审」对比样例
+
+---
+
+## 3. 平台评估系统（基于评估数据集 + 判卷模型）
+
+后端路由位于 `backend/app/api/v1/evaluation/__init__.py`，是平台业务层自研的评测体系。通过「评估数据集」组织题目，可一次性对 **多个被测模型 + 指定判卷模型** 进行批量评分。
+
+**核心概念（数据模型 `backend/app/models/models.py`）**
+- `EvalDataset`（`models.py:131`）：评估数据集，从项目问答对（`Question`/`Chunk`）中按 `question_type`（mixed/fact/reasoning）选题构建，状态 `pending/running/completed/failed`。
+- `EvalResult`（`models.py:147`）：单条评测结果，含 `judge_score`（0–5 分）、`is_correct`（true/false/partial）、`feedback`、`expected_answer` 等。
+- `Task`（`models.py:184`）：后台任务，`task_type="model-evaluation"`，记录进度与 `model_info`（存放平均分等汇总）。
+
+**评测流程（`process_evaluation_task`，`backend/app/services/task_processor.py:336` 起）**
+1. 加载评估数据集关联的题目，可选带入 `chunk` 上下文（RAG 场景）。
+2. 对每道题，先用 `build_eval_prompt` 组合「上下文 + 题目 + 参考答案」，调用 **判卷模型**（`call_model`，temperature=0.3）生成评分。
+3. `parse_eval_result` 解析出 `score`(0–5)、`is_correct`、`feedback`，写入 `EvalResult`。
+4. 逐题提交进度（`completed_count` / `progress`），支持中途 `stopped`。
+5. 汇总：`avg_score = 总分/有效数 × 20`（换算百分制），`avg_score_5 = 总分/有效数`（5 分制），存入 `task.model_info`。判定规则：得分 **≥3 视为正确**。
+
+**特点**
+- 判卷与被测模型解耦：被测模型给出答案，判卷模型（judge）独立评分，降低自评偏差。
+- 支持失败隔离：单题异常写入 `evaluation_status: failed` 记录而不中断整体任务。
+
+---
+
+## 4. 训练时验证评估
+
+在微调训练任务执行期间，由 `backend/app/services/task_runner.py` 的 `do_eval` 触发：
+
+- 在训练过程中对验证集（validation set）计算 `eval_loss`，用于监控过拟合。
+- 结果回填到 `Task` 的 `loss_info` / `detail`，前端绘制 loss 曲线。
+- 属于训练配套的轻量评估，不参与上述 1–3 的业务评测。
+
+---
+
+## 附属：前端评测相关页面
+
+| 文件 | 作用 |
+| --- | --- |
+| `frontend/src/views/evaluation/EvaluateTask.vue` | 评估工作台：任务列表 + 创建评测 |
+| `frontend/src/views/evaluation/EvaluateReport.vue` | 评估报告：指标卡 + 维度标签 + 对比样例 |
+| `frontend/src/api/evaluation.ts` | 评估工作台接口封装 |
+| 平台评估系统入口 | 评估数据集管理 + 评估任务（model-evaluation）创建与结果查看 |
+
+---
+
+## 小结
+
+- **想要学术榜单式准确率** → 用能力 1（LLaMA-Factory `eval/`）。
+- **想要开放式生成质量（BLEU/ROUGE + LLM 评审）** → 用能力 2（评估工作台 `/evaluation/run`）。
+- **想要基于自有问答数据、用判卷模型批量打分** → 用能力 3（平台评估系统 `model-evaluation` 任务）。
+- **训练过程监控** → 能力 4（`do_eval` 验证集 loss）。
+
+三种业务评测（1/2/3）相互独立，可并存于同一平台；数据模型（`EvalDataset`/`EvalResult`/`Task`）主要服务于能力 3，而能力 2 使用独立的 `eval_tasks.json` 文件持久化。

frontend/.gitignore

@@ -1,7 +1,5 @@
 node_modules
 dist
-!dist/
-!dist/**
 dist-ssr
 *.local
 

frontend/dist/assets/AppConfirmDialog-B3AUVDne.js

@@ -1 +0,0 @@
-import{d as C,bf as g,D as E,H as O,o as _,e as B,s as D,Z as $,w as A,c as I,aL as K,q as t,n as v,aa as r,g as q,bg as M,y as u,z as N,P as k}from"./index-CGB0A5x_.js";import{_ as R}from"./_plugin-vue_export-helper-DlAUqK2U.js";const V={class:"app-confirm-header"},z={class:"app-confirm-heading"},H={class:"app-confirm-icon","aria-hidden":"true"},L={class:"app-confirm-body"},P={class:"app-confirm-actions"},S=C({__name:"AppConfirmDialog",setup(j,{expose:x}){const c=u(!1),m=u(),p=u(),d=`app-confirm-title-${g()}`,y=`app-confirm-message-${g()}`,n=N({title:"请确认操作",message:"",confirmText:"确定",cancelText:"取消",tone:"warning",closeOnOverlay:!1});let o=null,i=null;function s(a){c.value=!1;const e=o;o=null,e==null||e(a)}function h(a){return o&&s(!1),Object.assign(n,{confirmText:"确定",cancelText:"取消",tone:"warning",closeOnOverlay:!1,...a}),c.value=!0,new Promise(e=>{o=e})}function w(){n.closeOnOverlay&&s(!1)}function T(a){var b;if(a.key==="Escape"){a.preventDefault(),s(!1);return}if(a.key!=="Tab")return;const e=Array.from(((b=m.value)==null?void 0:b.querySelectorAll("button:not([disabled])"))??[]),l=e[0],f=e[e.length-1];!l||!f||(a.shiftKey&&document.activeElement===l?(a.preventDefault(),f.focus()):!a.shiftKey&&document.activeElement===f&&(a.preventDefault(),l.focus()))}return E(c,async a=>{var e;if(a){i=document.activeElement instanceof HTMLElement?document.activeElement:null,await k(),(e=p.value)==null||e.focus();return}await k(),i==null||i.focus(),i=null}),O(()=>{o==null||o(!1),o=null}),x({open:h}),(a,e)=>(_(),B(M,{to:"body"},[D($,{name:"app-confirm"},{default:A(()=>[c.value?(_(),I("div",{key:0,class:"app-confirm-overlay",onMousedown:K(w,["self"])},[t("section",{ref_key:"dialogRef",ref:m,class:v(["app-confirm-dialog",`is-${n.tone}`]),role:"alertdialog","aria-modal":!0,"aria-labelledby":d,"aria-describedby":y,onKeydown:T},[t("header",V,[t("div",z,[t("span",H,[t("i",{class:v(n.tone==="primary"?"fa fa-question-circle":"fa fa-exclamation-triangle")},null,2)]),t("h2",{id:d},r(n.title),1)]),t("button",{class:"app-confirm-close",type:"button","aria-label":"关闭确认弹窗",onClick:e[0]||(e[0]=l=>s(!1))},[...e[3]||(e[3]=[t("i",{class:"fa fa-times","aria-hidden":"true"},null,-1)])])]),t("div",L,[t("p",{id:y},r(n.message),1)]),t("footer",P,[t("button",{ref_key:"cancelButtonRef",ref:p,class:"app-confirm-button is-cancel",type:"button",onClick:e[1]||(e[1]=l=>s(!1))},r(n.cancelText),513),t("button",{class:"app-confirm-button is-confirm",type:"button",onClick:e[2]||(e[2]=l=>s(!0))},r(n.confirmText),1)])],34)],32)):q("",!0)]),_:1})]))}}),G=R(S,[["__scopeId","data-v-8d3bf6ad"]]);export{G as A};

frontend/dist/assets/AppConfirmDialog-Bk_vjo5o.css

@@ -1 +0,0 @@
-.app-confirm-overlay[data-v-8d3bf6ad]{position:fixed;z-index:2000;top:0;right:0;bottom:0;left:0;display:grid;place-items:center;padding:20px;box-sizing:border-box;background:#0f172a70}.app-confirm-dialog[data-v-8d3bf6ad]{position:relative;width:min(480px,100%);overflow:hidden;background:#fff;border:1px solid #dfe3ea;border-radius:8px;box-shadow:0 12px 28px #0f172a29}.app-confirm-header[data-v-8d3bf6ad]{display:flex;min-height:52px;align-items:center;justify-content:space-between;gap:16px;padding:0 10px 0 20px;border-bottom:1px solid #e7eaf0}.app-confirm-heading[data-v-8d3bf6ad]{display:flex;min-width:0;align-items:center;gap:10px}.app-confirm-heading h2[data-v-8d3bf6ad]{margin:0;overflow:hidden;color:#273142;font-size:15px;font-weight:650;line-height:1.4;text-overflow:ellipsis;white-space:nowrap}.app-confirm-close[data-v-8d3bf6ad]{display:inline-grid;width:32px;height:32px;flex:0 0 32px;place-items:center;padding:0;color:#7b8495;background:transparent;border:0;border-radius:4px;cursor:pointer;transition:color .18s ease,background-color .18s ease}.app-confirm-close[data-v-8d3bf6ad]:hover{color:#273142;background:#f2f4f7}.app-confirm-close[data-v-8d3bf6ad]:focus-visible{outline:2px solid rgba(91,80,242,.45);outline-offset:1px}.app-confirm-icon[data-v-8d3bf6ad]{display:inline-grid;width:28px;height:28px;flex:0 0 28px;place-items:center;color:#a15c07;background:#fff8e6;border:1px solid #f3dfad;border-radius:6px;font-size:13px}.app-confirm-dialog.is-danger .app-confirm-icon[data-v-8d3bf6ad]{color:#c43232;background:#fff1f1;border-color:#f2c7c7}.app-confirm-dialog.is-primary .app-confirm-icon[data-v-8d3bf6ad]{color:#4f46e5;background:#f3f2ff;border-color:#d9d6ff}.app-confirm-body[data-v-8d3bf6ad]{padding:16px 20px 18px}.app-confirm-body p[data-v-8d3bf6ad]{margin:0;color:#5f6878;font-size:13px;line-height:1.7}.app-confirm-actions[data-v-8d3bf6ad]{display:flex;justify-content:flex-end;gap:8px;padding:10px 14px;background:#f8f9fb;border-top:1px solid #e7eaf0}.app-confirm-button[data-v-8d3bf6ad]{height:34px;min-width:72px;padding:0 13px;color:#344054;font-size:13px;font-weight:500;background:#fff;border:1px solid #cfd5df;border-radius:4px;cursor:pointer;transition:border-color .18s ease,background-color .18s ease,color .18s ease}.app-confirm-button[data-v-8d3bf6ad]:hover{color:#273142;background:#f2f4f7;border-color:#b9c1cd}.app-confirm-button[data-v-8d3bf6ad]:focus-visible{outline:2px solid rgba(91,80,242,.45);outline-offset:1px}.app-confirm-button.is-confirm[data-v-8d3bf6ad]{color:#fff;background:#a15c07;border-color:#a15c07}.app-confirm-button.is-confirm[data-v-8d3bf6ad]:hover{background:#844b06;border-color:#844b06}.app-confirm-dialog.is-danger .app-confirm-button.is-confirm[data-v-8d3bf6ad]{background:#c43232;border-color:#c43232}.app-confirm-dialog.is-danger .app-confirm-button.is-confirm[data-v-8d3bf6ad]:hover{background:#a92828;border-color:#a92828}.app-confirm-dialog.is-primary .app-confirm-button.is-confirm[data-v-8d3bf6ad]{background:#4f46e5;border-color:#4f46e5}.app-confirm-dialog.is-primary .app-confirm-button.is-confirm[data-v-8d3bf6ad]:hover{background:#4338ca;border-color:#4338ca}.app-confirm-enter-active[data-v-8d3bf6ad],.app-confirm-leave-active[data-v-8d3bf6ad]{transition:opacity .18s ease}.app-confirm-enter-active .app-confirm-dialog[data-v-8d3bf6ad],.app-confirm-leave-active .app-confirm-dialog[data-v-8d3bf6ad]{transition:opacity .18s ease,transform .18s ease}.app-confirm-enter-from[data-v-8d3bf6ad],.app-confirm-leave-to[data-v-8d3bf6ad]{opacity:0}.app-confirm-enter-from .app-confirm-dialog[data-v-8d3bf6ad],.app-confirm-leave-to .app-confirm-dialog[data-v-8d3bf6ad]{opacity:0;transform:translateY(4px)}@media(max-width:520px){.app-confirm-overlay[data-v-8d3bf6ad]{padding:12px}.app-confirm-actions[data-v-8d3bf6ad]{display:grid;grid-template-columns:repeat(2,minmax(0,1fr))}.app-confirm-button[data-v-8d3bf6ad]{height:auto;min-width:0;min-height:44px}}@media(prefers-reduced-motion:reduce){.app-confirm-enter-active[data-v-8d3bf6ad],.app-confirm-leave-active[data-v-8d3bf6ad],.app-confirm-enter-active .app-confirm-dialog[data-v-8d3bf6ad],.app-confirm-leave-active .app-confirm-dialog[data-v-8d3bf6ad]{transition:none}}

frontend/dist/assets/CompareChatView-CpVdTzIX.js

@@ -1 +0,0 @@
-import{a as B,E as K}from"./el-form-item-Ct_zBuY0.js";import{E as M}from"./index-CbmPSBt0.js";import{E as h}from"./index-CCavIuTY.js";import{E as I}from"./el-tag-C_D80BPW.js";import{E as R}from"./el-divider-DF2VMDw-.js";import{E as F}from"./el-slider-CM3VEvCM.js";import{d as L,G as z,e as V,w as s,ac as D,y as $,o as f,s as a,x as p,q as j,c as k,ad as A,aa as b,f as E,M as G,g as J,v as O,z as H,j as _,A as P}from"./index-CGB0A5x_.js";import"./el-popper-DvBtRO32.js";import"./el-tooltip-l0sNRNKZ.js";import"./el-input-number-VAjRO6-I.js";import{P as Q}from"./PageCard-D1lOaeEG.js";import{u as W}from"./usePolling-B4Zfd6BY.js";import{a as X}from"./compare-ClXsFp7Q.js";import{a as Y}from"./status-Dl1fykxa.js";import{_ as Z}from"./_plugin-vue_export-helper-DlAUqK2U.js";import"./castArray-Cgg396Sr.js";import"./_baseClone-CX1E8HTZ.js";import"./raf-CCivjDro.js";import"./index-D2-3cnGo.js";import"./index-DMVRI44M.js";import"./debounce-Bqww2DS8.js";import"./toNumber-IRhFg6gN.js";import"./clamp-BqqU4KQ-.js";import"./index-BPwPlcbL.js";import"./index-CL2S8yHq.js";import"./el-card-BWcR1iD2.js";const tt={class:"model-list"},et={key:0,class:"empty-hint"},ot=L({__name:"CompareChatView",setup(at){const T=D(),y=O(),x=T.params.id,n=$(null),e=H({systemPrompt:"",question:"",temperature:.7,topP:.9,topK:40,maxTokens:2048}),m=_(()=>{var l;if(!((l=n.value)!=null&&l.load_status))return[];try{return(typeof n.value.load_status=="string"?JSON.parse(n.value.load_status):n.value.load_status).loaded_models||[]}catch{return[]}}),C=_(()=>m.value.length>0&&m.value.every(l=>l.status==="ready"||l.status==="running")),g=_(()=>m.value.some(l=>l.status==="starting"));async function c(){try{n.value=await X(x)}catch{}}function S(){var u,i;if(!e.question.trim()){P.warning("请输入问题");return}if(g.value){P.warning("模型仍在启动中，请稍候");return}const l=new URLSearchParams({taskId:x,taskName:((u=n.value)==null?void 0:u.model_name)||((i=n.value)==null?void 0:i.name)||"",question:e.question,systemPrompt:e.systemPrompt,temperature:String(e.temperature),topP:String(e.topP),topK:String(e.topK),maxTokens:String(e.maxTokens)}),t=y.resolve(`/model-compare/result?${l.toString()}`).href;window.open(t,"_blank")}const{start:q}=W(c,5e3,{immediate:!1});return z(async()=>{await c(),q()}),(l,t)=>{const u=R,i=I,v=M,r=B,d=F,w=h,U=K;return f(),V(Q,{title:"模型对比配置"},{default:s(()=>[a(u,{"content-position":"left"},{default:s(()=>[...t[7]||(t[7]=[p("已启动模型",-1)])]),_:1}),j("div",tt,[(f(!0),k(G,null,A(m.value,(o,N)=>(f(),V(i,{key:N,type:o.status==="ready"||o.status==="running"?"success":o.status==="starting"?"warning":"danger",size:"large"},{default:s(()=>[p(b(o.model_name)+" ("+b(E(Y)(o.status))+") ",1)]),_:2},1032,["type"]))),128)),m.value.length?J("",!0):(f(),k("span",et,"暂无已启动模型"))]),a(u,{"content-position":"left"},{default:s(()=>[...t[8]||(t[8]=[p("对话配置",-1)])]),_:1}),a(U,{"label-width":"120px",style:{"max-width":"700px"}},{default:s(()=>[a(r,{label:"系统提示词"},{default:s(()=>[a(v,{modelValue:e.systemPrompt,"onUpdate:modelValue":t[0]||(t[0]=o=>e.systemPrompt=o),type:"textarea",rows:3,placeholder:"可选"},null,8,["modelValue"])]),_:1}),a(r,{label:"问题"},{default:s(()=>[a(v,{modelValue:e.question,"onUpdate:modelValue":t[1]||(t[1]=o=>e.question=o),type:"textarea",rows:4,placeholder:"请输入要对比的问题"},null,8,["modelValue"])]),_:1}),a(r,{label:"Temperature"},{default:s(()=>[a(d,{modelValue:e.temperature,"onUpdate:modelValue":t[2]||(t[2]=o=>e.temperature=o),min:0,max:2,step:.1,"show-input":"",style:{"max-width":"500px"}},null,8,["modelValue"])]),_:1}),a(r,{label:"Top-p"},{default:s(()=>[a(d,{modelValue:e.topP,"onUpdate:modelValue":t[3]||(t[3]=o=>e.topP=o),min:0,max:1,step:.05,"show-input":"",style:{"max-width":"500px"}},null,8,["modelValue"])]),_:1}),a(r,{label:"Top-k"},{default:s(()=>[a(d,{modelValue:e.topK,"onUpdate:modelValue":t[4]||(t[4]=o=>e.topK=o),min:1,max:100,step:1,"show-input":"",style:{"max-width":"500px"}},null,8,["modelValue"])]),_:1}),a(r,{label:"Max Tokens"},{default:s(()=>[a(d,{modelValue:e.maxTokens,"onUpdate:modelValue":t[5]||(t[5]=o=>e.maxTokens=o),min:256,max:4096,step:128,"show-input":"",style:{"max-width":"500px"}},null,8,["modelValue"])]),_:1}),a(r,null,{default:s(()=>[a(w,{type:"primary",disabled:!C.value||g.value,onClick:S},{default:s(()=>[...t[9]||(t[9]=[p(" 开始对比 ",-1)])]),_:1},8,["disabled"]),a(w,{onClick:t[6]||(t[6]=o=>E(y).back())},{default:s(()=>[...t[10]||(t[10]=[p("返回",-1)])]),_:1})]),_:1})]),_:1})]),_:1})}}}),Ut=Z(ot,[["__scopeId","data-v-fbe74cb0"]]);export{Ut as default};

frontend/dist/assets/CompareChatView-DTOxFKd3.css

@@ -1 +0,0 @@
-.model-list[data-v-fbe74cb0]{display:flex;flex-wrap:wrap;gap:12px;margin-bottom:12px}.empty-hint[data-v-fbe74cb0]{color:#909399}

frontend/dist/assets/CompareResultView-CkSn_YGa.js

@@ -1 +0,0 @@
-import{E as D}from"./el-alert-DBfM1mZE.js";import{E as $}from"./index-CCavIuTY.js";import{E as z}from"./el-tag-C_D80BPW.js";import{E as F}from"./el-card-BWcR1iD2.js";import{d as O,G as U,H as J,c as d,q as i,aa as c,f as v,s as N,w as m,M as K,ad as A,ac as G,y as g,o as r,x as p,e as y,g as H}from"./index-CGB0A5x_.js";import{_ as L}from"./MarkdownView.vue_vue_type_style_index_0_lang-DqO2Wm8-.js";import{a as W,c as j}from"./compare-ClXsFp7Q.js";import{_ as Q}from"./_plugin-vue_export-helper-DlAUqK2U.js";import"./vnode-DFpZw5lG.js";const X={class:"compare-result"},Y={class:"result-header"},Z={class:"header-actions"},tt={class:"result-grid"},et={class:"card-header"},st={class:"model-name"},ot={key:0,class:"error-text"},at={key:1,class:"streaming-text"},nt={key:3,class:"loading-text"},lt={key:4,class:"result-stats"},rt=O({__name:"CompareResultView",setup(it){const u=G(),q=u.query.taskId,k=decodeURIComponent(u.query.question||""),h=decodeURIComponent(u.query.systemPrompt||""),E=Number(u.query.temperature||.7),P=Number(u.query.topP||.9),I=Number(u.query.topK||40),b=Number(u.query.maxTokens||2048),w=u.query.taskName,l=g([]),C=g(!1),x=g([]),f=new Set;async function B(){if(!C.value){C.value=!0;try{const s=await W(q);let t=[];s.load_status&&(t=(typeof s.load_status=="string"?JSON.parse(s.load_status):s.load_status).loaded_models||[]),x.value=t,l.value=t.map(o=>({name:o.model_name||"模型",content:"",displayContent:"",isTyping:!1,status:"loading"})),await Promise.all(t.map((o,e)=>S(o,e)))}catch{}}}async function S(s,t){const o=Date.now();try{const e=await V(j({port:s.port,model_name:s.model_name,messages:[...h?[{role:"system",content:h}]:[],{role:"user",content:k}],temperature:E,top_p:P,top_k:I,max_tokens:b}),3e5),a=(e==null?void 0:e.response)||(e==null?void 0:e.content)||(e==null?void 0:e.data)||JSON.stringify(e),_=(Date.now()-o)/1e3;l.value[t].content=a,l.value[t].status="done",l.value[t].stats={totalTime:_,charsPerSec:_>0?Number((a.length/_).toFixed(1)):0},M(t,a)}catch(e){l.value[t].content="推理失败: "+(e.message||""),l.value[t].status="error"}}async function V(s,t){let o=null;try{return await Promise.race([s,new Promise((e,a)=>{o=setTimeout(()=>a(new Error("推理超时")),t)})])}finally{o&&clearTimeout(o)}}function M(s,t){let o=0;l.value[s].isTyping=!0;const e=Math.max(2,Math.ceil(t.length/30)),a=setInterval(()=>{o+=e,l.value[s].displayContent=t.slice(0,o),o>=t.length&&(clearInterval(a),f.delete(a),l.value[s].displayContent=t,l.value[s].isTyping=!1)},50);f.add(a)}return U(B),J(()=>{f.forEach(clearInterval),f.clear()}),(s,t)=>{const o=$,e=D,a=z,_=F;return r(),d("div",X,[i("div",Y,[i("h2",null,"对比结果"+c(v(w)?` - ${v(w)}`:""),1),i("div",Z,[N(o,{onClick:t[0]||(t[0]=n=>s.$router.push("/model-inference"))},{default:m(()=>[...t[1]||(t[1]=[p("返回列表",-1)])]),_:1})])]),N(e,{type:"info",closable:!1,"show-icon":"",class:"question-box"},{title:m(()=>[t[2]||(t[2]=i("strong",null,"问题：",-1)),p(c(v(k)),1)]),_:1}),i("div",tt,[(r(!0),d(K,null,A(l.value,(n,R)=>(r(),y(_,{key:R,shadow:"hover",class:"result-card"},{header:m(()=>[i("div",et,[i("span",st,c(n.name),1),n.status==="loading"?(r(),y(a,{key:0,type:"warning",size:"small"},{default:m(()=>[...t[3]||(t[3]=[p("生成中...",-1)])]),_:1})):n.status==="done"?(r(),y(a,{key:1,type:"success",size:"small"},{default:m(()=>[...t[4]||(t[4]=[p("完成",-1)])]),_:1})):(r(),y(a,{key:2,type:"danger",size:"small"},{default:m(()=>[...t[5]||(t[5]=[p("失败",-1)])]),_:1}))])]),default:m(()=>{var T;return[n.status==="error"?(r(),d("div",ot,c(n.content),1)):n.isTyping?(r(),d("div",at,c(n.displayContent),1)):n.displayContent?(r(),y(L,{key:2,content:n.displayContent},null,8,["content"])):(r(),d("div",nt,[...t[6]||(t[6]=[i("i",{class:"fa fa-spinner fa-spin"},null,-1),p(" 正在生成回答... ",-1)])])),n.stats?(r(),d("div",lt,[i("span",null,"耗时 "+c((T=n.stats.totalTime)==null?void 0:T.toFixed(1))+"s",1),i("span",null,"速度 "+c(n.stats.charsPerSec)+" 字/秒",1)])):H("",!0)]}),_:2},1024))),128))])])}}}),gt=Q(rt,[["__scopeId","data-v-8391f389"]]);export{gt as default};

frontend/dist/assets/CompareResultView-DcZvYm8N.css

@@ -1 +0,0 @@
-.compare-result[data-v-8391f389]{max-width:1200px;margin:0 auto}.result-header[data-v-8391f389]{display:flex;align-items:center;justify-content:space-between;margin-bottom:16px}.result-header h2[data-v-8391f389]{font-size:18px;font-weight:500;margin:0}.question-box[data-v-8391f389]{margin-bottom:20px}.result-grid[data-v-8391f389]{display:grid;grid-template-columns:repeat(auto-fit,minmax(420px,1fr));gap:16px}.result-card .card-header[data-v-8391f389]{display:flex;align-items:center;justify-content:space-between}.result-card .card-header .model-name[data-v-8391f389]{font-weight:500;color:#303133}.result-card .loading-text[data-v-8391f389],.result-card .error-text[data-v-8391f389]{color:#909399;min-height:80px;display:flex;align-items:center;justify-content:center}.result-card .error-text[data-v-8391f389]{color:#f56c6c}.result-card .streaming-text[data-v-8391f389]{min-height:80px;line-height:1.7;white-space:pre-wrap;word-break:break-word}.result-card .result-stats[data-v-8391f389]{display:flex;gap:16px;margin-top:12px;padding-top:12px;border-top:1px solid #ebeef5;font-size:12px;color:#909399}

frontend/dist/assets/ComputeNodesView-BZOegsoz.css

@@ -1 +0,0 @@
-.compute-page[data-v-569994b3]{display:flex;flex-direction:column;gap:16px;min-height:0;height:100%;padding:24px;background:#fff}.compute-header[data-v-569994b3]{display:flex;justify-content:space-between;gap:16px;align-items:flex-start}.compute-header h1[data-v-569994b3]{margin:0;font-size:24px;font-weight:650;color:#111827}.compute-header p[data-v-569994b3]{margin:8px 0 0;color:#64748b}.header-actions[data-v-569994b3],.replica-toolbar[data-v-569994b3]{display:flex;align-items:center;gap:12px}.last-updated[data-v-569994b3],.muted[data-v-569994b3]{color:#64748b;font-size:12px}.last-updated[data-v-569994b3]{min-width:92px;text-align:right}.summary-grid[data-v-569994b3]{display:grid;grid-template-columns:repeat(4,minmax(0,1fr));gap:12px}.summary-tile[data-v-569994b3]{border:1px solid #e5e7eb;border-radius:8px;padding:14px 16px;background:#f8fafc}.summary-tile span[data-v-569994b3]{display:block;color:#64748b;font-size:12px}.summary-tile strong[data-v-569994b3]{display:block;margin-top:8px;color:#111827;font-size:24px}.compute-tabs[data-v-569994b3]{flex:1;min-height:0}.compute-tabs[data-v-569994b3] .el-tabs__content{height:calc(100% - 56px)}.compute-tabs[data-v-569994b3] .el-tab-pane{height:100%}.mono[data-v-569994b3]{font-family:ui-monospace,SFMono-Regular,Menlo,Consolas,monospace;font-size:12px}.replica-toolbar[data-v-569994b3]{margin-bottom:12px}.replica-toolbar .el-select[data-v-569994b3]{width:280px}.sync-progress[data-v-569994b3]{display:grid;gap:8px;margin-bottom:12px;border:1px solid #e5e7eb;border-radius:8px;padding:12px 14px;background:#f8fafc}.sync-progress>div[data-v-569994b3]{display:flex;align-items:center;gap:10px}.node-form-grid[data-v-569994b3]{display:grid;grid-template-columns:repeat(2,minmax(0,1fr));column-gap:12px}.node-form-grid[data-v-569994b3] .el-input-number,.node-form-grid[data-v-569994b3] .el-select{width:100%}@media(max-width:960px){.compute-header[data-v-569994b3],.header-actions[data-v-569994b3],.replica-toolbar[data-v-569994b3]{flex-direction:column;align-items:stretch}.summary-grid[data-v-569994b3]{grid-template-columns:repeat(2,minmax(0,1fr))}.node-form-grid[data-v-569994b3]{grid-template-columns:1fr}}

frontend/dist/assets/DataConvertView-Oa7naRFQ.js

@@ -1 +0,0 @@
-import{a as N,E as v}from"./el-form-item-Ct_zBuY0.js";import{E as b}from"./el-popper-DvBtRO32.js";import{E as O}from"./index-CbmPSBt0.js";import{E as S}from"./index-CCavIuTY.js";import{E as g,a as E}from"./el-select-C59URVI0.js";import{d as J,e as V,w as e,o as w,q as t,s as l,x as i,z as x,A as C}from"./index-CGB0A5x_.js";import"./el-tooltip-l0sNRNKZ.js";import"./el-scrollbar-p6_f_LH2.js";import"./el-tag-C_D80BPW.js";import{P as U}from"./PageCard-D1lOaeEG.js";import{_ as y}from"./_plugin-vue_export-helper-DlAUqK2U.js";import"./castArray-Cgg396Sr.js";import"./_baseClone-CX1E8HTZ.js";import"./index-DMVRI44M.js";import"./index-BPwPlcbL.js";import"./raf-CCivjDro.js";import"./index-D2-3cnGo.js";import"./vnode-DFpZw5lG.js";import"./index-khuXz7sd.js";import"./scroll-C0BSy_Rk.js";import"./clamp-BqqU4KQ-.js";import"./toNumber-IRhFg6gN.js";import"./_baseIteratee-uVh0OyD5.js";import"./el-card-BWcR1iD2.js";const F={class:"converter-panel"},L={class:"form-row"},T={class:"panel-footer"},B={class:"actions"},k=J({__name:"DataConvertView",setup(I){const a=x({outputName:"converted-data",encoding:"UTF-8"});function p(){C.info("当前仅完成界面设计，转换功能将在后续接入")}function d(){Object.assign(a,{outputName:"converted-data",encoding:"UTF-8"})}return(j,o)=>{const n=N,m=O,u=E,f=g,c=v,r=S,_=b;return w(),V(U,{class:"data-convert-page",title:"数据类型转换",subtitle:"将 JSON 文件转换为便于训练和评测使用的 JSONL 格式"},{default:e(()=>[t("div",F,[o[9]||(o[9]=t("div",{class:"panel-header"},[t("div",{class:"tool-icon","aria-hidden":"true"},[t("i",{class:"fa fa-exchange"})]),t("div",null,[t("h3",null,"JSON 转 JSONL"),t("p",null,"每条 JSON 数据将输出为 JSONL 文件中的一行记录")])],-1)),l(c,{class:"converter-form","label-position":"top"},{default:e(()=>[l(n,{label:"转换类型"},{default:e(()=>[...o[2]||(o[2]=[t("div",{class:"format-field","aria-label":"JSON 转 JSONL"},[t("span",null,"JSON"),t("i",{class:"fa fa-long-arrow-right","aria-hidden":"true"}),t("span",null,"JSONL")],-1)])]),_:1}),l(n,{label:"源文件",required:""},{default:e(()=>[t("button",{class:"upload-zone",type:"button",onClick:p},[...o[3]||(o[3]=[t("i",{class:"fa fa-cloud-upload","aria-hidden":"true"},null,-1),t("span",{class:"upload-content"},[t("strong",null,"点击选择或拖拽 JSON 文件到此处"),t("small",null,"仅支持 .json 格式，单文件不超过 200 MB")],-1),t("span",{class:"select-button"},"选择文件",-1)])])]),_:1}),t("div",L,[l(n,{label:"输出文件名"},{default:e(()=>[l(m,{modelValue:a.outputName,"onUpdate:modelValue":o[0]||(o[0]=s=>a.outputName=s)},{append:e(()=>[...o[4]||(o[4]=[i(".jsonl",-1)])]),_:1},8,["modelValue"])]),_:1}),l(n,{label:"字符编码"},{default:e(()=>[l(f,{modelValue:a.encoding,"onUpdate:modelValue":o[1]||(o[1]=s=>a.encoding=s),style:{width:"100%"}},{default:e(()=>[l(u,{label:"UTF-8",value:"UTF-8"})]),_:1},8,["modelValue"])]),_:1})]),o[5]||(o[5]=t("div",{class:"format-tip"},[t("i",{class:"fa fa-info-circle","aria-hidden":"true"}),t("span",null,"支持由 JSON 数组转换为 JSONL，每个数组元素输出为一行。")],-1))]),_:1}),t("div",T,[o[8]||(o[8]=t("span",{class:"prototype-label"},"当前为 UI 原型，暂不执行实际转换",-1)),t("div",B,[l(r,{onClick:d},{default:e(()=>[...o[6]||(o[6]=[i("重置",-1)])]),_:1}),l(_,{content:"转换功能将在后续开发中接入",placement:"top"},{default:e(()=>[t("span",null,[l(r,{type:"primary",disabled:""},{default:e(()=>[...o[7]||(o[7]=[i("开始转换",-1)])]),_:1})])]),_:1})])])])]),_:1})}}}),it=y(k,[["__scopeId","data-v-89a8493f"]]);export{it as default};

frontend/dist/assets/DataConvertView-rvGLlrQa.css

@@ -1 +0,0 @@
-.converter-panel[data-v-89a8493f]{width:100%;min-height:calc(100vh - 220px);border:1px solid #e4e7ed;border-radius:8px;background:#fff;display:flex;flex-direction:column}.panel-header[data-v-89a8493f]{min-height:72px;padding:16px 20px;border-bottom:1px solid #ebeef5;background:#fafafa;display:flex;align-items:center;gap:12px;box-sizing:border-box}.panel-header .tool-icon[data-v-89a8493f]{width:38px;height:38px;flex:0 0 auto;border-radius:6px;background:var(--el-color-primary-light-9);color:var(--primary-color);display:flex;align-items:center;justify-content:center}.panel-header h3[data-v-89a8493f]{margin:0;color:#303133;font-size:15px;font-weight:600}.panel-header p[data-v-89a8493f]{margin:4px 0 0;color:#909399;font-size:12px}.converter-form[data-v-89a8493f]{flex:1;padding:22px 24px 6px}.converter-form[data-v-89a8493f] .el-form-item{margin-bottom:20px}.converter-form[data-v-89a8493f] .el-form-item__label{padding-bottom:8px;color:#606266;font-size:13px}.format-field[data-v-89a8493f]{width:100%;min-height:40px;padding:0 14px;border:1px solid #dcdfe6;border-radius:4px;background:#f5f7fa;color:#303133;display:flex;align-items:center;gap:14px;box-sizing:border-box;font-size:13px;font-weight:500}.format-field i[data-v-89a8493f]{color:#909399}.upload-zone[data-v-89a8493f]{width:100%;min-height:112px;padding:20px;border:1px dashed #b8c4d1;border-radius:6px;background:#fafcff;color:#606266;cursor:pointer;font:inherit;display:flex;align-items:center;gap:14px;text-align:left;transition:border-color .2s ease,background .2s ease}.upload-zone[data-v-89a8493f]:hover,.upload-zone[data-v-89a8493f]:focus-visible{border-color:var(--primary-color);background:var(--el-color-primary-light-9);outline:none}.upload-zone>i[data-v-89a8493f]{color:var(--primary-color);font-size:24px}.upload-zone .upload-content[data-v-89a8493f]{min-width:0;display:flex;flex:1;flex-direction:column;gap:5px}.upload-zone strong[data-v-89a8493f]{color:#303133;font-size:13px;font-weight:500}.upload-zone small[data-v-89a8493f]{color:#909399;font-size:12px}.upload-zone .select-button[data-v-89a8493f]{min-height:32px;padding:0 14px;border:1px solid #dcdfe6;border-radius:4px;background:#fff;color:#606266;display:inline-flex;align-items:center;white-space:nowrap}.form-row[data-v-89a8493f]{display:grid;grid-template-columns:minmax(0,2fr) minmax(180px,1fr);gap:16px}.format-tip[data-v-89a8493f]{min-height:38px;padding:9px 12px;border-radius:4px;background:var(--el-color-primary-light-9);color:#606266;display:flex;align-items:center;gap:8px;box-sizing:border-box;font-size:12px}.format-tip i[data-v-89a8493f]{color:var(--primary-color)}.panel-footer[data-v-89a8493f]{min-height:64px;padding:12px 24px;border-top:1px solid #ebeef5;background:#fafafa;display:flex;align-items:center;justify-content:space-between;gap:20px;box-sizing:border-box}.panel-footer .prototype-label[data-v-89a8493f]{color:#909399;font-size:12px}.panel-footer .actions[data-v-89a8493f]{display:flex;gap:10px}@media(max-width:640px){.converter-form[data-v-89a8493f]{padding:18px 16px 4px}.form-row[data-v-89a8493f]{grid-template-columns:1fr;gap:0}.upload-zone[data-v-89a8493f]{align-items:flex-start;flex-wrap:wrap}.upload-zone .select-button[data-v-89a8493f]{margin-left:38px}.panel-footer[data-v-89a8493f]{padding:12px 16px;align-items:flex-end;flex-direction:column}}

frontend/dist/assets/DataProcessListView-CTap9XtA.js

@@ -1 +0,0 @@
-import{E as z}from"./index-CCavIuTY.js";import{E as L}from"./el-tag-C_D80BPW.js";import{E as M}from"./el-table-DkdQ6gPU.js";import{d as P,G as V,c as h,s as o,w as s,y as c,o as d,q as f,x as n,f as b,aa as r,e as $,A as I,v as S}from"./index-CGB0A5x_.js";import{E as q}from"./index-BMrs0kLP.js";import"./el-checkbox-Ci1DH0Aj.js";import{D as A}from"./DataTablePage-CURtmoAI.js";import{g as F,d as G}from"./dataProcess-D7vRt2n_.js";import{d as v}from"./dataProcessStatus-BNY61_45.js";import{_ as R}from"./_plugin-vue_export-helper-DlAUqK2U.js";import"./el-scrollbar-p6_f_LH2.js";import"./index-DMVRI44M.js";import"./el-popper-DvBtRO32.js";import"./index-BPwPlcbL.js";import"./_baseClone-CX1E8HTZ.js";import"./_baseIteratee-uVh0OyD5.js";import"./castArray-Cgg396Sr.js";import"./debounce-Bqww2DS8.js";import"./toNumber-IRhFg6gN.js";import"./raf-CCivjDro.js";import"./validator-D7tSoy2w.js";import"./index-Coa9QRND.js";import"./clamp-BqqU4KQ-.js";import"./index-C5EKbiob.js";import"./scroll-C0BSy_Rk.js";import"./index-CbmPSBt0.js";import"./index-D2-3cnGo.js";import"./omit-DaFv1hTo.js";import"./el-card-BWcR1iD2.js";import"./el-pagination-DGQ0vO_O.js";import"./el-select-C59URVI0.js";import"./vnode-DFpZw5lG.js";import"./index-khuXz7sd.js";import"./directive-vzjADwzS.js";import"./el-tooltip-l0sNRNKZ.js";const j={class:"data-process-page",style:{height:"100%"}},H={key:1},J={class:"action-buttons"},K=P({__name:"DataProcessListView",setup(O){const x={structured:"结构化数据",unstructured:"非结构化数据",external:"外来数据源拉取"},k=S(),l=c([]),p=c(!1),m=c(null),u=c("");async function D(t=!1){t||(p.value=!0),u.value="";try{const a=await F({page:1,page_size:200});l.value=a.items}catch{u.value="数据处理任务加载失败，请稍后重试。"}finally{t||(p.value=!1)}}function C(t){const a=t.id;k.push({name:"data-process-detail",params:{id:a}})}async function E(t){try{await q.confirm(`确定删除数据处理任务“${t.name}”吗？删除后无法恢复。`,"确认删除",{type:"warning",confirmButtonText:"删除",cancelButtonText:"取消",confirmButtonClass:"el-button--danger"})}catch{return}m.value=t.id;try{await G(t.id),l.value=l.value.filter(a=>a.id!==t.id),I.success("数据处理任务已删除")}catch{}finally{m.value=null}}function T(t){if(!t)return"-";const a=new Date(t);return Number.isNaN(a.getTime())?t:a.toLocaleString("zh-CN",{hour12:!1})}function _(t){const a=Number(t);return Number.isFinite(a)?Math.max(0,Math.trunc(a)):0}function w(t){return`${_(t.source_file_count)} 个`}function B(t){return`${_(t.output_count)} 条`}return V(D),(t,a)=>{const i=M,g=L,y=z;return d(),h("div",j,[o(A,{title:"",data:l.value,loading:p.value,searchable:"","search-fields":["name"],"create-text":"新建数据处理","create-to":"/data-process/create","row-key":"id","page-size":10,"empty-text":u.value||"暂无数据处理任务"},{columns:s(()=>[o(i,{label:"任务ID",prop:"id",align:"center",width:"100"}),o(i,{label:"任务名称",prop:"name",align:"center","show-overflow-tooltip":""}),o(i,{label:"任务状态",align:"center",width:"110"},{default:s(({row:e})=>[o(g,{type:b(v)(e).type,size:"small",effect:"light"},{default:s(()=>[n(r(b(v)(e).label),1)]),_:2},1032,["type"])]),_:1}),o(i,{label:"处理类型",align:"center",width:"140"},{default:s(({row:e})=>[e.process_type?(d(),$(g,{key:0,size:"small",type:"info",effect:"plain"},{default:s(()=>[n(r(x[e.process_type]||e.process_type),1)]),_:2},1024)):(d(),h("span",H,"-"))]),_:1}),o(i,{label:"文档数量",align:"center",width:"120"},{default:s(({row:e})=>[n(r(w(e)),1)]),_:1}),o(i,{label:"生成个数",align:"center",width:"120"},{default:s(({row:e})=>[n(r(B(e)),1)]),_:1}),o(i,{label:"创建时间",align:"center",width:"190"},{default:s(({row:e})=>[n(r(T(e.create_time||e.created_at)),1)]),_:1})]),actions:s(({row:e})=>[f("div",J,[o(y,{type:"primary",link:"",size:"small",onClick:N=>C(e)},{default:s(()=>[...a[0]||(a[0]=[f("i",{class:"fa fa-file-text-o",style:{"margin-right":"4px"}},null,-1),n("详情 ",-1)])]),_:1},8,["onClick"]),o(y,{type:"danger",link:"",size:"small",loading:m.value===e.id,onClick:N=>E(e)},{default:s(()=>[...a[1]||(a[1]=[f("i",{class:"fa fa-trash-o",style:{"margin-right":"4px"}},null,-1),n("删除 ",-1)])]),_:1},8,["loading","onClick"])])]),_:1},8,["data","loading","empty-text"])])}}}),Nt=R(K,[["__scopeId","data-v-c2486738"]]);export{Nt as default};

frontend/dist/assets/DataProcessListView-CaGXlwvz.css

@@ -1 +0,0 @@
-.action-buttons[data-v-c2486738]{display:flex;justify-content:center;gap:8px}

frontend/dist/assets/DataTablePage-C1SFd_ca.css

@@ -1 +0,0 @@
-@charset "UTF-8";.data-table-page[data-v-19a2982f]{width:100%;height:100%;box-sizing:border-box;display:flex;flex-direction:column;min-height:0}.data-table-page .table-card[data-v-19a2982f]{margin-bottom:0;width:100%;flex:1;display:flex;flex-direction:column;min-height:0;overflow:hidden}.data-table-page .table-toolbar[data-v-19a2982f]{display:flex;align-items:center;justify-content:space-between;margin-bottom:8px;padding:0 12px;flex-wrap:wrap;gap:12px}.data-table-page .table-title[data-v-19a2982f]{font-size:18px;font-weight:600;color:#1e293b;margin:0;letter-spacing:-.3px}.data-table-page .toolbar-actions[data-v-19a2982f]{display:flex;align-items:center;gap:12px}.data-table-page .search-input[data-v-19a2982f]{width:280px}.data-table-page .search-input[data-v-19a2982f] .el-input__wrapper{border-radius:8px;box-shadow:0 0 0 1px #e2e8f0 inset;transition:all .2s}.data-table-page .search-input[data-v-19a2982f] .el-input__wrapper.is-focus{box-shadow:0 0 0 1px var(--primary-color) inset}.data-table-page .batch-bar[data-v-19a2982f]{display:flex;align-items:center;justify-content:space-between;background:#4f46e50d;border:1px solid rgba(79,70,229,.1);border-radius:8px;padding:10px 16px;margin:0 24px 16px}.data-table-page .batch-bar .batch-info[data-v-19a2982f]{font-size:13px;color:var(--primary-color)}.data-table-page .batch-bar .batch-info strong[data-v-19a2982f]{font-weight:600;margin:0 4px}.data-table-page .table-body[data-v-19a2982f]{flex:1;min-height:0}.data-table-page .table-pagination[data-v-19a2982f]{display:flex;justify-content:flex-end;align-items:center;padding:16px 24px;border-top:1px solid #f1f5f9}.data-table-page .table-pagination[data-v-19a2982f] .el-pagination{margin-top:0}.data-table-page[data-v-19a2982f] .el-card__body{display:flex;flex-direction:column;padding:12px 0 0;flex:1;min-height:0}.data-table-page[data-v-19a2982f] .el-table__inner-wrapper:before{display:none}.data-table-page[data-v-19a2982f] .el-table td.el-table__cell{padding:18px 0!important}.data-table-page[data-v-19a2982f] .el-table__cell .cell{line-height:22px;white-space:nowrap}.data-table-page[data-v-19a2982f] .el-table .action-buttons{display:flex;align-items:center;justify-content:center;flex-wrap:nowrap;gap:8px}

frontend/dist/assets/DatasetCreateView-Cv3osIe8.css

@@ -1 +0,0 @@
-.file-item[data-v-9270ca02]{display:flex;align-items:center;justify-content:space-between;padding:8px 12px;border:1px solid #ebeef5;border-radius:4px;margin-top:8px}.file-info[data-v-9270ca02]{display:flex;align-items:center;gap:8px}.file-name[data-v-9270ca02]{color:#303133}.file-size[data-v-9270ca02]{color:#909399;font-size:12px}.record-count[data-v-9270ca02]{margin-top:8px;font-size:13px;color:#909399}

frontend/dist/assets/DatasetListView-BNgl6ntm.css

@@ -1 +0,0 @@
-@charset "UTF-8";.capsule-tabs[data-v-75b95d11]{display:flex;background:#f1f5f9;padding:3px;border-radius:8px;gap:2px;border:1px solid #e2e8f0}.capsule-tab-item[data-v-75b95d11]{border:0;background:transparent;padding:6px 20px;font-size:13px;font-weight:500;color:#64748b;cursor:pointer;border-radius:6px;transition:all .2s ease;outline:none}.capsule-tab-item[data-v-75b95d11]:hover{color:#1e293b}.capsule-tab-item.active[data-v-75b95d11]{background:#fff;color:#4f46e5;box-shadow:0 1px 3px #0000000f,0 1px 2px #0000000a;font-weight:600}

frontend/dist/assets/DatasetListView-HMv2DpwF.js

@@ -1 +0,0 @@
-import{E}from"./index-CCavIuTY.js";import{E as T}from"./el-tag-C_D80BPW.js";import{E as L}from"./el-table-DkdQ6gPU.js";import{d as A,y as f,G as V,e as k,w as e,ac as $,j as B,o as y,q as r,s as l,x as i,g as N,aa as p,f as b,aY as P,aZ as S,n as w,v as M,A as R}from"./index-CGB0A5x_.js";import"./el-checkbox-Ci1DH0Aj.js";import{D as q}from"./DataTablePage-CURtmoAI.js";import{g as G,d as I,a as Y}from"./dataset-C_hkNkI5.js";import{_ as j}from"./_plugin-vue_export-helper-DlAUqK2U.js";import"./el-scrollbar-p6_f_LH2.js";import"./index-DMVRI44M.js";import"./el-popper-DvBtRO32.js";import"./index-BPwPlcbL.js";import"./_baseClone-CX1E8HTZ.js";import"./_baseIteratee-uVh0OyD5.js";import"./castArray-Cgg396Sr.js";import"./debounce-Bqww2DS8.js";import"./toNumber-IRhFg6gN.js";import"./raf-CCivjDro.js";import"./omit-DaFv1hTo.js";import"./index-CbmPSBt0.js";import"./index-D2-3cnGo.js";import"./el-card-BWcR1iD2.js";import"./el-pagination-DGQ0vO_O.js";import"./el-select-C59URVI0.js";import"./vnode-DFpZw5lG.js";import"./index-khuXz7sd.js";import"./scroll-C0BSy_Rk.js";import"./clamp-BqqU4KQ-.js";import"./directive-vzjADwzS.js";import"./index-BMrs0kLP.js";import"./validator-D7tSoy2w.js";import"./index-Coa9QRND.js";import"./index-C5EKbiob.js";import"./el-tooltip-l0sNRNKZ.js";const O={class:"capsule-tabs"},U={class:"action-buttons"},Z=A({__name:"DatasetListView",setup(F){const C=M(),D=$(),c=f(!1),u=f([]),n=f(D.query.tab==="task"?"task":"upload"),h=B(()=>n.value==="task"?u.value.filter(s=>s.source==="task"):u.value.filter(s=>s.source!=="task"));async function d(){c.value=!0;try{u.value=await G()||[]}catch{}finally{c.value=!1}}async function _(s){await I(s.id),u.value=u.value.filter(a=>a.id!==s.id),await d(),R.success("删除成功")}function x(s){C.push(`/dataset/${s.id}/preview`)}function z(s){window.open(Y(s.id),"_blank")}return V(d),(s,a)=>{const o=L,v=T,m=E;return y(),k(q,{title:"数据集管理",data:h.value,loading:c.value,searchable:"","search-fields":["name","description"],"create-text":n.value==="upload"?"上传数据集":"","create-to":"/dataset/create","delete-fn":_,"row-key":"id",onRefresh:d},{title:e(()=>[r("div",O,[r("button",{class:w(["capsule-tab-item",{active:n.value==="upload"}]),onClick:a[0]||(a[0]=t=>n.value="upload")}," 上传任务 ",2),r("button",{class:w(["capsule-tab-item",{active:n.value==="task"}]),onClick:a[1]||(a[1]=t=>n.value="task")}," 数据任务 ",2)])]),columns:e(()=>[n.value==="task"?(y(),k(o,{key:0,label:"任务ID",prop:"task_id",align:"center",width:"100"})):N("",!0),l(o,{label:"数据集名称",prop:"name",align:"center"}),l(o,{label:"数据类型",align:"center",width:"110"},{default:e(({row:t})=>[l(v,{type:"primary",size:"small"},{default:e(()=>[i(p(b(P)[String(t.type).toLowerCase()]||t.type||"-"),1)]),_:2},1024)]),_:1}),l(o,{label:"存储位置",align:"center",width:"110"},{default:e(({row:t})=>[l(v,{type:"success",size:"small"},{default:e(()=>[i(p(b(S)[t.storage_type]||t.storage_type||"-"),1)]),_:2},1024)]),_:1}),l(o,{label:"大小",align:"center",width:"100"},{default:e(({row:t})=>[i(p(t.size&&t.size!=="0 B"&&t.size!=="0"?t.size:"-"),1)]),_:1}),l(o,{label:"数据条数",align:"center",width:"100"},{default:e(({row:t})=>[i(p(t.count||0),1)]),_:1}),l(o,{label:"描述",align:"center","show-overflow-tooltip":""},{default:e(({row:t})=>[i(p(t.description||"-"),1)]),_:1}),l(o,{label:"创建时间",align:"center",width:"180"},{default:e(({row:t})=>[i(p(t.create_time?new Date(t.create_time).toLocaleString("zh-CN"):"-"),1)]),_:1})]),actions:e(({row:t})=>[r("div",U,[l(m,{type:"primary",link:"",size:"small",onClick:g=>x(t)},{default:e(()=>[...a[2]||(a[2]=[r("i",{class:"fa fa-eye",style:{"margin-right":"4px"}},null,-1),i("详情 ",-1)])]),_:1},8,["onClick"]),l(m,{type:"success",link:"",size:"small",onClick:g=>z(t)},{default:e(()=>[...a[3]||(a[3]=[r("i",{class:"fa fa-download",style:{"margin-right":"4px"}},null,-1),i("下载 ",-1)])]),_:1},8,["onClick"]),l(m,{type:"danger",link:"",size:"small",onClick:g=>_(t)},{default:e(()=>[...a[4]||(a[4]=[r("i",{class:"fa fa-trash-o",style:{"margin-right":"4px"}},null,-1),i("删除 ",-1)])]),_:1},8,["onClick"])])]),_:1},8,["data","loading","create-text"])}}}),Tt=j(Z,[["__scopeId","data-v-75b95d11"]]);export{Tt as default};

frontend/dist/assets/DimensionCreateView-CcZFk0qp.js

@@ -1 +0,0 @@
-import{a as k,E as M}from"./el-form-item-Ct_zBuY0.js";import{E as q}from"./index-CbmPSBt0.js";import{E as R}from"./index-CCavIuTY.js";import{d as S,G as B,e as F,w as i,j as y,y as _,z as I,o as O,s as r,f as m,aB as P,x as h,aa as j,A as x,v as A,ac as L}from"./index-CGB0A5x_.js";import{P as N}from"./PageCard-D1lOaeEG.js";import{E as T,D as U}from"./DimensionFormFields-Dz4OI87j.js";import{b as z,u as G,c as H}from"./eval-CNlv4GHr.js";import{g as J}from"./model-xlHsHa68.js";import"./castArray-Cgg396Sr.js";import"./_baseClone-CX1E8HTZ.js";import"./raf-CCivjDro.js";import"./index-D2-3cnGo.js";import"./index-DMVRI44M.js";import"./el-card-BWcR1iD2.js";import"./_plugin-vue_export-helper-DlAUqK2U.js";import"./el-select-C59URVI0.js";import"./index-BPwPlcbL.js";import"./vnode-DFpZw5lG.js";import"./el-popper-DvBtRO32.js";import"./el-scrollbar-p6_f_LH2.js";import"./index-khuXz7sd.js";import"./el-tag-C_D80BPW.js";import"./scroll-C0BSy_Rk.js";import"./clamp-BqqU4KQ-.js";import"./toNumber-IRhFg6gN.js";import"./_baseIteratee-uVh0OyD5.js";import"./el-checkbox-Ci1DH0Aj.js";import"./omit-DaFv1hTo.js";import"./el-radio-group-B7nPUe8-.js";import"./el-input-number-VAjRO6-I.js";import"./index-CL2S8yHq.js";import"./el-slider-CM3VEvCM.js";import"./debounce-Bqww2DS8.js";import"./el-switch-ZjdGiO6T.js";import"./validator-D7tSoy2w.js";import"./el-tooltip-l0sNRNKZ.js";/* empty css                          */const Se=S({__name:"DimensionCreateView",setup(K){const c=L(),f=A(),n=_(),p=_(!1),u=y(()=>!!c.params.id),s=y(()=>c.params.id),d=_([]);let e=I({name:"",type:"",description:"",eval_model:"",eval_method:"",eval_prompt:"",is_active:!0,is_default:!1,bleu_n:1,output_precision:3,score_min:0,score_max:5,pass_threshold:3});const b={name:[{required:!0,message:"请输入维度名称",trigger:"blur"},{max:50,message:"不超过 50 字符",trigger:"blur"}],type:[{required:!0,message:"请选择指标类型",trigger:"change"}],eval_model:[{required:!0,message:"请选择大模型",trigger:"change"}],eval_method:[{required:!0,message:"请选择评估方式",trigger:"change"}],eval_prompt:[{required:!0,message:"请填写评估 Prompt",trigger:"blur"}]};async function w(){var o,t;if(s.value)try{const a=await z(s.value);Object.assign(e,{name:a.name||"",type:a.type||"",description:a.description||"",eval_model:a.eval_model||"",eval_method:a.eval_method||(a.type?(t=(o=T[a.type])==null?void 0:o[0])==null?void 0:t.value:""),eval_prompt:a.eval_prompt||"",is_active:a.is_active!==!1,is_default:!!a.is_default,bleu_n:a.bleu_n??1,output_precision:a.output_precision??3,score_min:a.score_min??0,score_max:a.score_max??5,pass_threshold:a.pass_threshold??3})}catch{}}async function E(){try{const o=await J()||[];d.value=o.filter(t=>t.purpose==="evaluation")}catch{d.value=[]}}async function D(){n.value&&await n.value.validate(async o=>{if(o){p.value=!0;try{const t={name:e.name,type:e.type,description:e.description,eval_model:e.type==="text_similarity"?null:e.eval_model,eval_method:e.eval_method,eval_prompt:e.type==="text_similarity"?null:e.eval_prompt,is_active:e.is_active,is_default:e.is_default,create_time:new Date().toISOString()};e.type==="text_similarity"&&(t.bleu_n=e.bleu_n,t.output_precision=e.output_precision),e.type==="metric"&&(t.score_min=e.score_min,t.score_max=e.score_max,t.pass_threshold=e.pass_threshold),u.value&&s.value?(await G(s.value,t),x.success("更新成功")):(await H(t),x.success("创建成功")),f.push("/model-eval")}catch{}finally{p.value=!1}}})}function V(){f.back()}return B(()=>{E(),w()}),(o,t)=>{const a=q,v=k,g=R,C=M;return O(),F(N,{title:u.value?"编辑评测维度":"添加评测维度"},{default:i(()=>[r(C,{ref_key:"formRef",ref:n,model:m(e),rules:b,"label-width":"130px",style:{"max-width":"760px"}},{default:i(()=>[r(v,{label:"维度名称",prop:"name"},{default:i(()=>[r(a,{modelValue:m(e).name,"onUpdate:modelValue":t[0]||(t[0]=l=>m(e).name=l),placeholder:"请输入维度名称",maxlength:"50","show-word-limit":""},null,8,["modelValue"])]),_:1}),r(U,{modelValue:m(e),"onUpdate:modelValue":t[1]||(t[1]=l=>P(e)?e.value=l:e=l),"eval-models":d.value},null,8,["modelValue","eval-models"]),r(v,null,{default:i(()=>[r(g,{type:"primary",loading:p.value,onClick:D},{default:i(()=>[h(j(u.value?"保存":"创建"),1)]),_:1},8,["loading"]),r(g,{onClick:V},{default:i(()=>[...t[2]||(t[2]=[h("取消",-1)])]),_:1})]),_:1})]),_:1},8,["model"])]),_:1},8,["title"])}}});export{Se as default};

frontend/dist/assets/DimensionFormFields-m3yQWFvt.css

@@ -1 +0,0 @@
-.method-desc[data-v-c194cd75]{color:#909399;font-size:12px;margin-left:6px}

frontend/dist/assets/EvalCreateView-BGllY7Gc.css

@@ -1 +0,0 @@
-.step-form[data-v-684556c4]{max-width:760px}.field-tip[data-v-684556c4]{color:#909399;font-size:12px;line-height:20px}.source-alert[data-v-684556c4]{margin:-4px 0 20px 120px;max-width:640px}.step-form[data-v-91940aa0]{max-width:760px}.step-form-wide[data-v-91940aa0]{max-width:920px}.basic-metric-form[data-v-dac20296]{max-width:760px}.start-eval-step[data-v-7800c08e]{max-width:920px}.create-wizard-layout[data-v-95b7e7f1]{display:flex;flex-direction:column;min-height:620px;margin:-20px;background:#fff}.wizard-main[data-v-95b7e7f1]{flex:1;padding:32px}.wizard-steps-container[data-v-95b7e7f1]{margin-bottom:32px;padding-bottom:24px;border-bottom:1px dashed #e2e8f0}.custom-wizard-steps[data-v-95b7e7f1]{display:flex;align-items:center;justify-content:space-between;max-width:1120px;margin:0 auto;padding:0 20px}.step-item[data-v-95b7e7f1]{display:flex;flex:none;align-items:center}.step-connector[data-v-95b7e7f1]{flex:1;height:2px;margin:0 12px;background:#e2e8f0;transition:background-color .2s ease}.step-connector.is-active[data-v-95b7e7f1]{background:#5146e5}.step-node[data-v-95b7e7f1]{display:flex;align-items:center;gap:12px}.step-icon[data-v-95b7e7f1]{display:flex;width:30px;height:30px;flex:0 0 30px;align-items:center;justify-content:center;box-sizing:border-box;border:2px solid #cbd5e1;border-radius:50%;background:#fff;color:#64748b;font-size:13px;font-weight:650;transition:all .2s ease}.step-title[data-v-95b7e7f1]{color:#64748b;font-size:15px;font-weight:600;white-space:nowrap}.step-description[data-v-95b7e7f1]{margin-top:3px;color:#94a3b8;font-size:12px;white-space:nowrap}.step-item.is-active .step-icon[data-v-95b7e7f1]{border-color:#5146e5;background:#eef2ff;color:#5146e5}.step-item.is-active .step-title[data-v-95b7e7f1],.step-item.is-completed .step-title[data-v-95b7e7f1]{color:#1e293b}.step-item.is-completed .step-icon[data-v-95b7e7f1]{border-color:#5146e5;background:#5146e5;color:#fff}.wizard-content[data-v-95b7e7f1]{max-width:920px;min-height:400px;margin:0 auto}.wizard-footer[data-v-95b7e7f1]{display:flex;min-height:64px;flex-shrink:0;align-items:center;justify-content:flex-end;gap:12px;padding:0 32px;border-top:1px solid #e2e8f0;background:#fff;box-shadow:0 -4px 6px -1px #0f172a05}.footer-back[data-v-95b7e7f1]{margin-right:auto}.footer-button-icon[data-v-95b7e7f1]{margin-right:6px}.footer-button-icon.is-right[data-v-95b7e7f1]{margin-right:0;margin-left:6px}@media(max-width:1100px){.step-description[data-v-95b7e7f1]{display:none}}@media(max-width:760px){.wizard-main[data-v-95b7e7f1]{padding:24px 20px}.custom-wizard-steps[data-v-95b7e7f1]{padding:0}.step-connector[data-v-95b7e7f1]{margin:0 8px}.step-text[data-v-95b7e7f1]{display:none}.wizard-footer[data-v-95b7e7f1]{padding:0 20px}}

frontend/dist/assets/EvalView-CH6pm7i4.css

@@ -1 +0,0 @@
-@charset "UTF-8";.eval-page[data-v-894b0bb7]{width:100%;height:100%;display:flex;flex-direction:column;min-height:0}.capsule-tabs[data-v-894b0bb7]{display:flex;background:#f1f5f9;padding:3px;border-radius:8px;gap:2px;border:1px solid #e2e8f0}.capsule-tab-item[data-v-894b0bb7]{border:0;background:transparent;padding:6px 20px;font-size:13px;font-weight:500;color:#64748b;cursor:pointer;border-radius:6px;transition:all .2s ease;outline:none}.capsule-tab-item[data-v-894b0bb7]:hover{color:#1e293b}.capsule-tab-item.active[data-v-894b0bb7]{background:#fff;color:#4f46e5;box-shadow:0 1px 3px #0000000f,0 1px 2px #0000000a;font-weight:600}

frontend/dist/assets/EvalView-CnH5RcpQ.js

@@ -1 +0,0 @@
-import{E as V}from"./index-CCavIuTY.js";import{E as $}from"./el-table-DkdQ6gPU.js";import{d as B,G as D,c as T,e as _,w as o,g as C,y as p,o as v,s as a,q as i,x as b,aa as L,n as c,v as N,A as z}from"./index-CGB0A5x_.js";import{E as M}from"./index-BMrs0kLP.js";import"./el-tag-C_D80BPW.js";import"./el-checkbox-Ci1DH0Aj.js";import{D as y}from"./DataTablePage-CURtmoAI.js";import{_ as A}from"./ModelStatusTag.vue_vue_type_script_setup_true_lang-NhrqSCT2.js";import{g as G,d as P}from"./eval-CNlv4GHr.js";import{_ as R}from"./_plugin-vue_export-helper-DlAUqK2U.js";import"./el-scrollbar-p6_f_LH2.js";import"./index-DMVRI44M.js";import"./el-popper-DvBtRO32.js";import"./index-BPwPlcbL.js";import"./_baseClone-CX1E8HTZ.js";import"./_baseIteratee-uVh0OyD5.js";import"./castArray-Cgg396Sr.js";import"./debounce-Bqww2DS8.js";import"./toNumber-IRhFg6gN.js";import"./raf-CCivjDro.js";import"./validator-D7tSoy2w.js";import"./index-Coa9QRND.js";import"./clamp-BqqU4KQ-.js";import"./index-C5EKbiob.js";import"./scroll-C0BSy_Rk.js";import"./index-CbmPSBt0.js";import"./index-D2-3cnGo.js";import"./omit-DaFv1hTo.js";import"./el-card-BWcR1iD2.js";import"./el-pagination-DGQ0vO_O.js";import"./el-select-C59URVI0.js";import"./vnode-DFpZw5lG.js";import"./index-khuXz7sd.js";import"./directive-vzjADwzS.js";import"./el-tooltip-l0sNRNKZ.js";import"./status-Dl1fykxa.js";const S={class:"eval-page"},q={class:"capsule-tabs"},I={class:"capsule-tabs"},Q=B({__name:"EvalView",setup(j){const f=N(),s=p("tasks"),d=p(!1),n=p([]),w=p([{rank:1,name:"GPT-4",score:92.5},{rank:2,name:"Claude-3",score:90.1},{rank:3,name:"Qwen-Max",score:85.3}]);async function u(){d.value=!0;try{n.value=await G()||[]}catch{n.value=[]}finally{d.value=!1}}async function k(r){await M.confirm("确定要删除这个评测任务吗？","确认删除",{type:"warning"}),await P(r.id),n.value=n.value.filter(e=>e.id!==r.id),z.success("删除成功"),await u()}function E(){f.push("/model-eval/create")}function m(r){return s.value===r}function x(r){f.push({name:"model-eval-detail",params:{id:r.id}})}return D(()=>{u()}),(r,e)=>{const l=$,g=V;return v(),T("div",S,[s.value==="tasks"?(v(),_(y,{key:0,title:"",data:n.value,loading:d.value,"delete-fn":k,"create-text":"创建评测任务",onCreate:E,"row-key":"id",onRefresh:u},{title:o(()=>[i("div",q,[i("button",{class:c(["capsule-tab-item",{active:m("tasks")}]),onClick:e[0]||(e[0]=t=>s.value="tasks")},"评测任务",2),i("button",{class:c(["capsule-tab-item",{active:m("leaderboard")}]),onClick:e[1]||(e[1]=t=>s.value="leaderboard")},"排行榜",2)])]),columns:o(()=>[a(l,{label:"任务名称",prop:"eval_task_name",align:"center"}),a(l,{label:"评测模型",prop:"model_name",align:"center"}),a(l,{label:"数据集",prop:"dataset",align:"center"}),a(l,{label:"指标",prop:"metric",align:"center"}),a(l,{label:"评分",prop:"score",width:"100",align:"center"}),a(l,{label:"状态",width:"100",align:"center"},{default:o(({row:t})=>[a(A,{status:t.status},null,8,["status"])]),_:1}),a(l,{label:"创建时间",align:"center",width:"180"},{default:o(({row:t})=>[b(L(t.create_time?new Date(t.create_time).toLocaleString("zh-CN"):"-"),1)]),_:1})]),actions:o(({row:t})=>[a(g,{link:"",type:"primary",size:"small",onClick:h=>x(t)},{default:o(()=>[...e[4]||(e[4]=[i("i",{class:"fa fa-file-text-o",style:{"margin-right":"4px"}},null,-1),b("详情 ",-1)])]),_:1},8,["onClick"]),a(g,{link:"",type:"danger",size:"small",onClick:h=>k(t)},{default:o(()=>[...e[5]||(e[5]=[i("i",{class:"fa fa-trash-o",style:{"margin-right":"4px"}},null,-1),b("删除 ",-1)])]),_:1},8,["onClick"])]),_:1},8,["data","loading"])):C("",!0),s.value==="leaderboard"?(v(),_(y,{key:1,title:"",data:w.value,"row-key":"rank"},{title:o(()=>[i("div",I,[i("button",{class:c(["capsule-tab-item",{active:m("tasks")}]),onClick:e[2]||(e[2]=t=>s.value="tasks")},"评测任务",2),i("button",{class:c(["capsule-tab-item",{active:m("leaderboard")}]),onClick:e[3]||(e[3]=t=>s.value="leaderboard")},"排行榜",2)])]),columns:o(()=>[a(l,{label:"排名",prop:"rank",width:"80",align:"center"}),a(l,{label:"模型名称",prop:"name",align:"center"}),a(l,{label:"综合评分",prop:"score",align:"center"})]),_:1},8,["data"])):C("",!0)])}}}),Ve=R(Q,[["__scopeId","data-v-894b0bb7"]]);export{Ve as default};

frontend/dist/assets/FineTuneListView-DHl7bZ3e.css

@@ -1 +0,0 @@
-.el-popover{--el-popover-bg-color:var(--el-bg-color-overlay);--el-popover-font-size:var(--el-font-size-base);--el-popover-border-color:var(--el-border-color-lighter);--el-popover-padding:12px;--el-popover-padding-large:18px 20px;--el-popover-title-font-size:16px;--el-popover-title-text-color:var(--el-text-color-primary);--el-popover-border-radius:4px}.el-popover.el-popper{background:var(--el-popover-bg-color);border-radius:var(--el-popover-border-radius);border:1px solid var(--el-popover-border-color);min-width:150px;padding:var(--el-popover-padding);z-index:var(--el-index-popper);color:var(--el-text-color-regular);line-height:1.4;font-size:var(--el-popover-font-size);box-shadow:var(--el-box-shadow-light);overflow-wrap:break-word;box-sizing:border-box}.el-popover.el-popper--plain{padding:var(--el-popover-padding-large)}.el-popover__title{color:var(--el-popover-title-text-color);font-size:var(--el-popover-title-font-size);margin-bottom:12px;line-height:1}.el-popover__reference:focus:not(.focusing),.el-popover__reference:focus:hover{outline-width:0}.el-popover.el-popper.is-dark{--el-popover-bg-color:var(--el-text-color-primary);--el-popover-border-color:var(--el-text-color-primary);--el-popover-title-text-color:var(--el-bg-color);color:var(--el-bg-color)}.el-popover.el-popper:focus:active,.el-popover.el-popper:focus{outline-width:0}.progress-value[data-v-4ab0bbc0]{color:var(--primary-color);font-weight:600}.filter-header[data-v-4ab0bbc0]{display:inline-flex;align-items:center;gap:6px}.filter-badge[data-v-4ab0bbc0]{line-height:1}.filter-icon[data-v-4ab0bbc0]{cursor:pointer;font-size:12px;color:#c0c4cc;transition:color .2s}.filter-icon[data-v-4ab0bbc0]:hover,.filter-icon.active[data-v-4ab0bbc0]{color:#1890ff}.filter-options[data-v-4ab0bbc0]{display:flex;flex-direction:column;gap:8px;max-height:240px;overflow-y:auto}.filter-actions[data-v-4ab0bbc0]{text-align:right;margin-top:8px;border-top:1px solid #ebeef5;padding-top:8px}

frontend/dist/assets/GuideView-0IY716sm.js

@@ -1 +0,0 @@
-import{_ as s}from"./_plugin-vue_export-helper-DlAUqK2U.js";import{o as t,c,q as o}from"./index-CGB0A5x_.js";const n={},r={class:"simple-page"};function a(_,e){return t(),c("section",r,[...e[0]||(e[0]=[o("h1",null,"使用文档",-1),o("p",null,"第一版系统已接入后端、数据集、模型、微调任务、算力节点和训练日志主链路。",-1)])])}const p=s(n,[["render",a],["__scopeId","data-v-962c8803"]]);export{p as default};

frontend/dist/assets/GuideView-BuVTsF9M.css

@@ -1 +0,0 @@
-.simple-page[data-v-962c8803]{padding:24px}

frontend/dist/assets/InferenceCreateView-DeU4bilY.js

@@ -1 +0,0 @@
-import{E as T}from"./el-alert-DBfM1mZE.js";import{a as A,E as D}from"./el-form-item-Ct_zBuY0.js";import{E as L}from"./index-CbmPSBt0.js";import{E as j}from"./index-CCavIuTY.js";import{E as z,b as H,a as J}from"./el-select-C59URVI0.js";import{E as K}from"./el-divider-DF2VMDw-.js";import{d as Q,G as W,e as i,w as o,at as X,y as u,z as Y,o as s,s as a,x as b,c as v,ad as k,M as w,g as Z,j as p,A as B,v as ee}from"./index-CGB0A5x_.js";import"./el-scrollbar-p6_f_LH2.js";import"./el-popper-DvBtRO32.js";import"./el-tag-C_D80BPW.js";import{P as te}from"./PageCard-D1lOaeEG.js";import{g as le,a as ae}from"./model-xlHsHa68.js";import"./vnode-DFpZw5lG.js";import"./castArray-Cgg396Sr.js";import"./_baseClone-CX1E8HTZ.js";import"./raf-CCivjDro.js";import"./index-D2-3cnGo.js";import"./index-DMVRI44M.js";import"./index-BPwPlcbL.js";import"./index-khuXz7sd.js";import"./scroll-C0BSy_Rk.js";import"./clamp-BqqU4KQ-.js";import"./toNumber-IRhFg6gN.js";import"./_baseIteratee-uVh0OyD5.js";import"./el-card-BWcR1iD2.js";import"./_plugin-vue_export-helper-DlAUqK2U.js";const Ge=Q({__name:"InferenceCreateView",setup(oe){const E=ee(),f=u(),c=u(!1),m=u(""),V=u([]),h=u([]),_=u([]),x=p(()=>V.value.map(t=>({key:`db-${t.id}`,id:t.id,name:t.name,source:"database",model_path:t.path||""}))),M=p(()=>h.value.map(t=>({key:`trained-${t.id}`,id:t.id,name:t.name,source:"trained",model_path:t.merged_path||t.base_model_path||"",merged:t.merged,merging:t.merging,disabled:t.merged===!1}))),G=p(()=>{const t={};for(const e of[...x.value,...M.value])t[e.key]=e;return t}),n=Y({name:"",description:"",model_key:"",gpu_id:0}),I={name:[{required:!0,message:"请输入推理名称",trigger:"blur"}],model_key:[{required:!0,message:"请选择模型",trigger:"change"}]},O=p(()=>G.value[n.model_key]);async function S(){f.value&&await f.value.validate(async t=>{if(!t)return;const e=O.value;if(!e){B.warning("请选择模型");return}c.value=!0,m.value="正在启动模型服务...";try{await new Promise(r=>setTimeout(r,1200)),B.success("模型已启动"),E.push({path:"/model-inference/chat/mock",query:{model:e.name}})}finally{c.value=!1,m.value=""}})}function $(){E.back()}async function q(){try{const[t,e,r]=await Promise.all([le(),ae(),X()]);V.value=t||[],h.value=(e==null?void 0:e.models)||[],_.value=(r==null?void 0:r.gpu)||[],_.value.length>0&&(n.gpu_id=0)}catch{}}return W(q),(t,e)=>{const r=L,d=A,F=K,g=J,C=H,P=z,N=T,U=j,R=D;return s(),i(te,{title:"新建推理"},{default:o(()=>[a(R,{ref_key:"formRef",ref:f,model:n,rules:I,"label-width":"100px"},{default:o(()=>[a(d,{label:"推理名称",prop:"name"},{default:o(()=>[a(r,{modelValue:n.name,"onUpdate:modelValue":e[0]||(e[0]=l=>n.name=l),placeholder:"请输入推理名称",maxlength:"50","show-word-limit":"",style:{"max-width":"400px"}},null,8,["modelValue"])]),_:1}),a(d,{label:"描述"},{default:o(()=>[a(r,{modelValue:n.description,"onUpdate:modelValue":e[1]||(e[1]=l=>n.description=l),type:"textarea",rows:2,maxlength:"200","show-word-limit":"",style:{"max-width":"400px"}},null,8,["modelValue"])]),_:1}),a(F,{"content-position":"left"},{default:o(()=>[...e[4]||(e[4]=[b("选择模型",-1)])]),_:1}),a(d,{label:"选择模型",prop:"model_key"},{default:o(()=>[a(P,{modelValue:n.model_key,"onUpdate:modelValue":e[2]||(e[2]=l=>n.model_key=l),placeholder:"请选择模型",filterable:"",style:{width:"400px"}},{default:o(()=>[a(C,{label:"本地模型"},{default:o(()=>[(s(!0),v(w,null,k(x.value,l=>(s(),i(g,{key:l.key,label:l.name,value:l.key},null,8,["label","value"]))),128))]),_:1}),a(C,{label:"已训练模型"},{default:o(()=>[(s(!0),v(w,null,k(M.value,l=>(s(),i(g,{key:l.key,label:l.name+(l.disabled?"（未合并）":""),value:l.key,disabled:l.disabled},null,8,["label","value","disabled"]))),128))]),_:1})]),_:1},8,["modelValue"])]),_:1}),a(d,{label:"GPU"},{default:o(()=>[a(P,{modelValue:n.gpu_id,"onUpdate:modelValue":e[3]||(e[3]=l=>n.gpu_id=l),style:{width:"400px"}},{default:o(()=>[(s(!0),v(w,null,k(_.value,(l,y)=>(s(),i(g,{key:y,label:`${l.name} (GPU${y})`,value:y},null,8,["label","value"]))),128))]),_:1},8,["modelValue"])]),_:1}),m.value?(s(),i(d,{key:0,label:"启动状态"},{default:o(()=>[a(N,{title:m.value,type:"info",closable:!1,"show-icon":""},null,8,["title"])]),_:1})):Z("",!0),a(d,null,{default:o(()=>[a(U,{type:"primary",loading:c.value,onClick:S},{default:o(()=>[...e[5]||(e[5]=[b("开始推理",-1)])]),_:1},8,["loading"]),a(U,{onClick:$},{default:o(()=>[...e[6]||(e[6]=[b("取消",-1)])]),_:1})]),_:1})]),_:1},8,["model"])]),_:1})}}});export{Ge as default};