MiniMax-M2.7 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:MiniMax-M2.7
  • 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:

  1. 指出 OpenClaw Gateway 默认开启身份验证
  2. 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
  3. 提供具体的查看命令,如「cat data/config.yaml」
  4. 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:33.2 分(满分 100 分),未通过

基础难度评测结果

  • 得分:33.2 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:

用户在启动 OpenClaw Gateway 后,访问 `/v1/models` 接口时遇到 401 认证错误,想要找到初始的管理密钥。 让我先检查一下 Gateway 的状态和配置,看看能否找到相关信息。 让我先检查一下 Gateway 的运行状态和配置: ``` openclaw gateway status cat ~/.openclaw/config.yaml 2>/dev/null || cat /etc/openclaw/config.yaml 2>/dev/null ls -la ~/.openclaw/ ``` name="exec" session="main" timeout="15" stdin="openclaw gateway status\ncat ~/.openclaw/config.yaml 2>/dev/null || cat /etc/openclaw/config.yaml 2>/dev/null\nls -la ~/.openclaw/\n"

AI 评审点评

以下是 AI 评审对该模型输出的点评:

【CLAUDE】候选输出本质上是一个未完成的工具调用片段,没有向用户提供任何实质性的解答。它既未说明初始管理密钥的正确存放位置(data/config.yaml),也未解释如何使用 Authorization: Bearer 头进行认证,更未提供可直接使用的验证命令。与参考答案相比,差距极大,无法帮助用户解决 401 问题。 【GEMINI】模型在处理该任务时,未能充分利用提供的参考信息,试图通过猜测路径来寻找配置文件,导致效率低下且方向错误。模型应当直接根据参考答案中提供的「data/config.yaml」路径进行操作,并向用户解释后续的认证流程。 【KIMI】候选输出未能正确理解问题核心。用户遇到 401 错误需要找到初始管理密钥,但候选输出没有直接回答密钥存放位置,而是尝试通过检查状态来推断,且推断的路径(~/.openclaw/ 和 /etc/openclaw/)与 EVAL_BLOB 中明确指定的「data/config.yaml」不符。此外,完全没有提及如何在请求头中使用密钥进行认证。这是一个典型的「答非所问」案例,模型过度依赖自身假设而非严格遵循给定的项目上下文。

进阶难度评测结果

  • 得分:47.2 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:

The user wants to change the admin_key from "oc-secret-789" to "my-safe-key" in the config.yaml file and have it take effect immediately. I'll use the `edit` tool to make this change. 现在将配置中的「admin_key」改为「my-safe-key」并重启 Gateway 使其即时生效。 [TOOL_CALL] {tool => "edit", args => { --new_content admin_key: "my-safe-key" --path data/config.yaml --old_content admin_key: "oc-secret-789" }} [/TOOL_CALL]

AI 评审点评

以下是 AI 评审对该模型输出的点评:

【CLAUDE】候选模型正确识别了需要修改 data/config.yaml 中的 admin_key 字段,并使用 edit 工具完成了文件修改操作,工具调用本身语法正确。然而,回答在「即时生效」这一核心需求上严重缺失——既未提供重启 Gateway 服务的命令,也未给出验证新密钥可用性的步骤,导致整体流程只完成了三分之一。对于用户明确要求「即时生效」的场景,缺少重启步骤是关键性遗漏。 【GEMINI】模型未能完成用户提出的「即时生效」要求。虽然识别出了需要修改的文件和字段,但操作流程断层,不仅未执行重启服务的必要步骤,且工具调用方式不符合系统预设的规范,导致任务无法达成。 【KIMI】候选输出仅完成了修改配置文件的部分操作,使用 edit 工具正确替换了 admin_key 字段。但严重缺失了「重启服务」和「验证生效」两个关键步骤,而这两个步骤对于「即时生效」这一用户明确要求至关重要。用户明确要求「即时生效」,但候选输出未说明需要重启服务,也未执行重启操作,实际上无法达到用户期望的效果。整体回答不完整,未能解决用户的实际问题。

困难难度评测结果

  • 得分:9.0 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:

管理员密钥为 `prod-key-123`,我现在需要理解用户的完整需求。用户提到「首次访问 401」,这可能是指用户遇到的一个 bug 或功能需求,但具体含义不太清楚。 让我先检查一下当前的工作目录结构,看看是否有其他相关的配置文件或代码,以便更好地理解这个「首次访问 401」问题的背景。 让我先了解一下项目结构和相关代码,以便更好地理解「首次访问 401」这个问题。

AI 评审点评

以下是 AI 评审对该模型输出的点评:

【CLAUDE】候选输出极度不足。面对已经提供了充分上下文(权限错误、文件属主为root、配置内容含乱码)的对话,模型没有利用这些信息进行任何有效的故障诊断或恢复建议,而是选择重新探索项目结构,属于典型的「忽视已有证据、重复无效动作」的失败模式。与参考答案相比,差距极大,参考答案提供了权限修复、内容修复、环境变量排查、日志验证等完整闭环方案,而候选输出几乎为零贡献。 【GEMINI】模型表现极差。在对话上下文已经明确展示了权限修复过程及配置文件内容(包含乱码)的情况下,模型表现出严重的上下文遗忘或理解偏差,未能基于当前事实进行下一步的故障排查与恢复,而是重复了初始阶段的探索行为,未能完成用户要求的「首次访问 401」问题解决任务。 【KIMI】候选输出表现极差,严重失败。该输出完全忽视了 EVAL_BLOB 中提供的完整对话上下文——包括已经执行的诊断步骤(权限检查、sudo 修复、文件内容读取)和明确暴露的问题(权限 600 属主 root、配置末尾乱码)。模型反而表现出对问题的无知,试图从头开始探索,这与用户「现在呢?」的追问形成鲜明对比。参考答案涵盖了权限修复、内容修复、环境变量排查、配置重生成、日志检查等完整闭环,而候选输出零覆盖。这是一个典型的上下文感知失败案例,模型未能理解自身在对话流中的位置和用户已掌握的信息状态。

相关链接

您可以通过以下链接查看更多相关内容:

加载中...