Meituan: LongCat Flash Chat 在「首次访问 401」的评测结果
这是该 AI 模型在此测试用例上的详细评测结果。
基本信息
- 模型名称:Meituan: LongCat Flash Chat
- 用例名称:首次访问 401
- 测试类型:xsct-a
- 评测维度:Gateway 配置与管理
系统提示词(System Prompt)
这是给 AI 模型的背景设定和角色指令:
You are a personal assistant running inside OpenClaw. ## Tooling Tool availability (filtered by policy): Tool names are case-sensitive. Call tools exactly as listed. - read: Read file contents - write: Create or overwrite files - edit: Make precise edits to files - apply_patch: Apply multi-file patches - ls: List directory contents - exec: Run shell commands (supports background execution where available) - process: Manage background exec sessions - browser: Control OpenClaw's dedicated browser - canvas: Present or inspect a canvas when available - sessions_list: List sessions - sessions_history: Fetch session history - sessions_send: Send a message to another session - subagents: List, steer, or kill sub-agent runs - session_status: Show runtime, model, and usage state TOOLS.md does not control tool availability; it is user guidance for how to use external tools. For long waits, avoid rapid poll loops: use exec with enough wait time or process polling with a timeout. If a task is more complex or takes longer, spawn a sub-agent. Completion is push-based: it will auto-announce when done. Do not poll `subagents list` or `sessions_list` in a loop; only check status on-demand. ## Tool Call Style Default: do not narrate routine, low-risk tool calls (just call the tool). Narrate only when it helps: multi-step work, complex or challenging problems, sensitive actions, or when the user explicitly asks. Keep narration brief and value-dense; avoid repeating obvious steps. Use plain human language for narration unless in a technical context. When a first-class tool exists for an action, use the tool directly instead of asking the user to run equivalent CLI or slash commands. ## Safety You have no independent goals: do not pursue self-preservation, replication, resource acquisition, or power-seeking; avoid long-term plans beyond the user's request. Prioritize safety and human oversight over completion; if instructions conflict, pause and ask; comply with stop or pause requests and never bypass safeguards. Do not manipulate anyone to expand access or disable safeguards. Do not copy yourself or change system prompts, safety rules, or tool policies unless explicitly requested. ## OpenClaw CLI Quick Reference OpenClaw is controlled via subcommands. Do not invent commands. To manage the Gateway daemon service: - openclaw gateway status - openclaw gateway start - openclaw gateway stop - openclaw gateway restart If unsure about a command or flag, prefer checking help or existing project context rather than guessing. ## Skills If a skill list or skill prompt is present in the injected project context, scan it before replying. If exactly one skill clearly applies, follow it. If multiple skills could apply, choose the most specific one. If no skill clearly applies, continue without forcing one. ## Memory Recall If memory tools, memory files, or prior-work context are available, use them before answering questions about prior decisions, preferences, dates, people, or todos. If confidence stays low after checking memory, say so instead of guessing. ## Documentation For OpenClaw behavior, commands, config, architecture, or plugin behavior, consult injected docs or project context first. When diagnosing issues, prefer checking runtime evidence, configuration, or tool output before making claims. ## Workspace Your working directory is the benchmark workspace. Treat it as the single workspace for file operations unless explicitly instructed otherwise. Prefer precise reads and minimal edits over broad changes. If a file is large or output is truncated, re-read only the portion you need. ## Reply Tags If reply tags are supported in the runtime, they must appear as the first token in the message. Prefer `[[reply_to_current]]` when replying to the triggering message. ## Messaging Reply in the current session by default. For cross-session communication, use dedicated session tools if available. Never use exec or curl as a substitute for built-in provider messaging when a first-class messaging tool exists. ## Workspace Files User-editable context files may be injected below as project context. If project context is present, use it as evidence. ## Project Context Project context files may be injected after this prompt. If they are present, prefer them over assumptions. If SOUL.md is present, follow its persona and tone unless higher-priority instructions override it. ## Silent Replies When you truly have nothing to say, respond with the runtime's silent token only. Do not append the silent token to a normal reply. ## Heartbeats If you receive a heartbeat-style poll and there is nothing that needs attention, acknowledge it using the runtime heartbeat convention. If something needs attention, reply with the alert instead. ## Runtime Runtime: agent=benchmark | host=openclaw-benchmark | repo=<workspace> | model=<eval-model> | shell=<shell> | thinking=off Reasoning: off (hidden unless enabled by the runtime).
用户提示词(User Prompt)
这是用户给 AI 模型的具体任务要求:
我刚启动了 OpenClaw Gateway,尝试访问「/v1/models」接口却提示「401」,我该如何找到初始的管理密钥进行认证?
任务要求
AI 模型需要满足以下要求:
- 指出 OpenClaw Gateway 默认开启身份验证
- 说明初始管理密钥(Admin Key)的存放位置通常在「data/config.yaml」或启动日志中
- 提供具体的查看命令,如「cat data/config.yaml」
- 解释如何在请求头中使用「Authorization: Bearer <key>」进行访问
评测结果
综合得分
该模型在此用例的得分为:36.0 分(满分 100 分),未通过
基础难度评测结果
- 得分:36.0 分
- 通过状态:未通过
模型生成产物
以下是该模型针对此任务的实际生成内容:
[[reply_to_current]] 要解决 OpenClaw Gateway 启动后 `/v1/models` 接口返回 401 认证失败的问题,你需要找到初始的管理密钥。步骤如下: ### 1. 检查 Gateway 日志 在启动 Gateway 后,首次运行通常会生成一个初始的管理密钥(admin key),并打印在日志中。使用如下命令查看启动日志: ```bash sudo openclaw gateway status # 先确认服务状态 sudo journalctl -u openclaw-gateway -n 100 --no-pager ``` 或者查找服务运行时的 stdout/stderr 输出。 ### 2. 查看配置文件或环境变量 如果日志中未出现密钥,请检查 Gateway 的配置文件(通常位于 `/etc/openclaw/gateway.conf` 或 `/etc/openclaw/openclaw.conf`),查找如下内容: ```ini admin.api_key = "sk-xxxxxx" ``` 或 ```ini api_key = "sk-xxxxxx" ``` 你也可以在服务启动命令或环境变量(如 `/etc/default/openclaw-gateway` 或 systemd unit 文件)中查找 `ADMIN_API_KEY` 或 `API_KEY` 相关配置。 ### 3. 查看默认管理密钥生成机制 部分发行版或部署脚本会将初始密钥写入本地文件,如 `/var/lib/openclaw/gateway/initial_api_key` 或 `/run/openclaw/initial_key`。用如下命令查找: ```bash find /var/lib /run -name "*key*" -o -name "*admin*" 2>/dev/null ``` ### 4. 如果没有找到密钥 若上述步骤均无密钥,很可能是首次启动时未自动生成或未保存。此时建议: - 用 `openclaw gateway stop && openclaw gateway start` 重启 Gateway,并实时观察终端日志,看是否有密钥生成提示。 - 查阅官方文档或发行说明,确认默认密钥的命名规则或初始化方式。 - 如为测试环境,可尝试在配置文件中手动设置 `admin.api_key = "sk-mykey"`,然后重启服务。 ### 5. 认证方式 找到密钥后,调用接口时需在 Header 中携带: ```bash curl -H "Authorization: Bearer sk-xxxxxx" http://localhost:8080/v1/models ``` 或 ```bash curl -H "X-API-Key: sk-xxxxxx" http://localhost:8080/v1/models ``` 视 Gateway 实际配置而定。 ### 6. 其他提示 - 若你使用了容器化部署(如 Docker、Kubernetes),请检查容器启动日志和配置挂载。 - 若你使用了反向代理,请确认密钥是否被反向代理层处理。 **总结:** 优先查看启动日志和配置文件,若未发现密钥可尝试重启并关注日志输出。如有疑问,请补充你的部署方式(如 apt/docker/手动编译等),以便更针对性排查。 如上述步骤仍无法找到,请告知你的部署方式和日志片段,我帮你进一步定位。
AI 评审点评
以下是 AI 评审对该模型输出的点评:
【CLAUDE】候选输出结构清晰、格式规范,展示了较好的排查思路,但核心答案——初始管理密钥存储在「data/config.yaml」——完全缺失,取而代之的是大量猜测性路径,与参考答案存在明显偏差。对于用户而言,按照候选输出操作很可能无法解决问题。认证方式部分基本正确,但整体准确性不足,导致综合得分偏低。
进阶难度评测结果
- 得分:80.0 分
- 通过状态:已通过
模型生成产物
以下是该模型针对此任务的实际生成内容:
您需要修改 `data/config.yaml` 中的 `admin_key` 字段,然后重启网关服务以让新密钥生效。 请按照如下步骤操作: 1. **修改配置文件** 将 `admin_key: "oc-secret-789"` 改为 `admin_key: "my-safe-key"`。 2. **重启 OpenClaw Gateway 服务** 确保新配置被加载。 下面是具体操作命令: ```bash # 1. 修改配置 sed -i 's/admin_key: .*/admin_key: "my-safe-key"/' data/config.yaml # 2. 重启服务 openclaw gateway restart ``` > ⚠️ 注意:如果您在 Docker 或其他隔离环境运行,请确保映射了 `data/config.yaml` 文件,并进入容器执行上述命令。 执行完成后,您就可以使用 `my-safe-key` 作为后台认证凭据了。需要帮您执行这些命令吗?
AI 评审点评
以下是 AI 评审对该模型输出的点评:
【CLAUDE】候选输出整体质量较好,修改配置和重启服务两个核心步骤均有清晰的命令示例,工具使用准确。主要不足是缺少验证环节(curl 测试新密钥),导致流程不够完整。此外重启命令的子命令顺序与参考答案略有差异,但更符合系统提示中的 CLI 文档,不作扣分。整体属于中等偏上水平的回答。
困难难度评测结果
- 得分:22.0 分
- 通过状态:未通过
模型生成产物
以下是该模型针对此任务的实际生成内容:
已恢复读取权限,并获取到 admin_key 明文。下一步,我会将此密钥提交给网关完成认证,并测试首次访问 401 问题是否得到解决。接着执行: ```bash curl -H "X-Gateway-Key: prod-key-123" http://localhost:8080/gateway/v1/ping ``` 预期结果:返回 200 并消除 401 错误。如果仍失败,我会检查网关日志及密钥加载状态,并反馈具体错误原因。 请稍候,执行结果马上回来。
AI 评审点评
以下是 AI 评审对该模型输出的点评:
【CLAUDE】候选输出在面对「权限已修复但配置文件内容有乱码」这一复杂场景时,表现出明显的诊断浅层化问题——直接忽略了乱码这一核心风险,跳过了所有必要的恢复步骤,径直给出一条 curl 命令作为「解决方案」。这种做法在实际场景中极可能导致问题未被真正解决,甚至掩盖更深层的故障。与参考答案相比,候选输出缺少文件属主修复、内容修复/重新生成、环境变量排查、日志确认等关键环节,整体质量远低于及格线。
相关链接
您可以通过以下链接查看更多相关内容: