Inception: Mercury 2 在「首次访问 401」的评测结果

基本信息

• 模型名称：Inception: Mercury 2
• 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：27.0 分（满分 100 分），未通过

基础难度评测结果

• 得分：27.0 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：

{ "path": "." }

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【GEMINI】该模型的生成结果是一个与用户提问完全无关的 JSON 片段，未能满足任何功能要求。它没有提供密钥位置、查看命令或认证方法，属于无效的回答。 【KIMI】生成结果没有完全满足评分维度的要求，缺少了关键的信息和步骤。需要补充完整，给出明确的指令和步骤，才能提高得分。

进阶难度评测结果

• 得分：88.0 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：

下面是操作步骤： 1. **编辑 `data/config.yaml`** 把 `admin_key` 改为 `my-safe-key`。 2. **重新加载配置**：在 OpenClaw 中，配置会在网关服务启动时读取，所以需要重启网关服务使新 key 生效。 下面我会先完成编辑，然后执行网关重启。 --- **步骤 1：编辑文件** ```bash edit data/config.yaml ``` （将 `admin_key: "oc-secret-789"` 替换为 `admin_key: "my-safe-key"`） --- **步骤 2：重启网关** ```bash openclaw gateway restart ``` 这会让网关重新读取 `config.yaml`，新的 `admin_key` 将立即生效，随后您就可以使用 `my-safe-key` 进行后台访问，而不会再收到 401 错误。 如果重启后仍有问题，请检查： - `auth.enabled` 是否仍为 `true`（保持不变）。 - 确认您在请求中使用的 header 或参数名与网关期望的 `admin_key` 匹配（通常是 `X-Admin-Key` 或类似字段）。 完成以上两步后，您应该能够使用新 key 正常访问后台。祝使用顺利！

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【GEMINI】模型表现优秀，准确识别了 401 错误的解决方法（修改 key 并重启服务）。它正确使用了系统提供的 CLI 参考文档，给出的操作步骤简洁明了，具有很强的可操作性。唯一可以改进的地方是提供一个具体的验证命令以闭环整个流程。 【KIMI】整体上，该回答较好地满足了任务要求，提供了修改配置文件、重启服务和验证新密钥的完整流程。但在工具运用方面，可以进一步优化，提供更精确的命令来替换配置文件中的特定行，以提高操作的准确性和可靠性。

困难难度评测结果

• 得分：38.8 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：

We need to check gateway status.We need to run openclaw gateway status.Run command.We need to execute.Let's run.We need to actually call exec.已成功恢复 `data/config.yaml` 的读取权限并查看到其中的 `admin_key`（`prod-key-123`）。接下来，为了解决首次访问返回 **401 Unauthorized** 的问题，建议执行以下步骤： 1. **检查网关服务状态** ```bash openclaw gateway status ``` 确认网关是否正在运行以及是否有报错信息。 2. **确保网关使用了正确的 admin_key** - 打开网关的配置文件（通常位于 `gateway/config.yaml` 或 `gateway/settings.yaml`），检查 `admin_key` 是否与 `data/config.yaml` 中的值一致。 - 若不一致，请编辑该文件，使 `admin_key` 与 `prod-key-123` 完全匹配。 3. **重启网关服务**（在修改配置后） ```bash openclaw gateway restart ``` 4. **再次尝试访问** - 使用浏览器或 `curl` 发送带有正确 `Authorization` 头的请求，例如： ```bash curl -H "Authorization: Bearer prod-key-123" http://localhost:8080/your-endpoint ``` 5. **检查日志**（如果仍然 401） ```bash openclaw gateway logs # 或者查看 /var/log/openclaw/*.log ``` 查找与认证相关的错误信息，确保没有其他配置（如 JWT、OAuth）导致认证失败。 如果执行上述步骤后仍有问题，请把 `gateway status` 与 `gateway logs` 的输出贴出来，我可以进一步帮您定位。

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选回答在已有权限修复结果的基础上给出了一些通用的网关排查步骤，但未能深入识别配置文件内容损坏（乱码）这一核心问题，也未提及环境变量覆盖排查、文件属主修复、备份与重新生成配置等关键恢复决策。整体回答流于表面，与参考答案相比存在明显的诊断深度和恢复完整性差距，难以真正解决用户面临的 401 认证问题。 【GEMINI】模型在处理该任务时表现一般。虽然成功提取了密钥，但对故障的诊断过于浅显，未能识别出乱码带来的配置解析风险。在恢复决策上，模型未能结合上下文中的具体文件路径进行指导，且遗漏了环境变量排查这一关键排错步骤，整体闭环能力不足。 【KIMI】候选输出未能基于提供的对话上下文进行有效分析，忽略了已发现的乱码问题和已修复的权限问题，反而提出与实际情况不符的检查路径。整体表现为脱离上下文、缺乏深度诊断和系统恢复能力，未能满足「hard」难度任务的要求。

相关链接

您可以通过以下链接查看更多相关内容：

• 查看所有模型在此用例的表现：「首次访问 401」
• 查看该模型的所有评测结果：Inception: Mercury 2
• 浏览同维度的其他用例：「Gateway 配置与管理」
• 返回排行榜首页