glm-4.7 在「Signal 接入」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：glm-4.7
- 用例名称：Signal 接入
- 测试类型：xsct-a
- 评测维度：渠道连接与消息路由
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：
我想在 OpenClaw 中接入「Signal」渠道，请告诉我需要准备哪些核心参数，以及如何在配置文件中定义一个基础的 Signal 接收器？
任务要求
AI 模型需要满足以下要求：
- 明确指出需要 Signal-CLI 或相关 REST API 服务作为前置条件
- 列出核心参数：手机号「number」、账户密码或数据存储路径
- 提供符合 OpenClaw 规范的 YAML 基础配置示例
- 提及权限验证或注册流程的必要性
评测结果
综合得分
该模型在此用例的得分为：39.0 分（满分 100 分），未通过
基础难度评测结果
- 得分：39.0 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：
我来帮你了解如何在 OpenClaw 中配置 Signal 渠道。让我先查看一下项目中的相关配置文档。ls
AI 评审点评
以下是 AI 评审对该模型输出的点评：
【GEMINI】模型在面对用户的接入咨询时，选择先查阅工作区文档（通过 `ls` 命令），这符合其作为 OpenClaw 助手的操作逻辑，体现了一定的谨慎性。然而，根据评测标准，该回复未能提供用户要求的核心参数、配置示例及前置条件说明，因此在功能性得分上处于极低水平。建议模型在尝试调研的同时，可根据其内置知识库先给出初步的参考建议。 【KIMI】整体而言，候选人对于如何在OpenClaw中配置Signal渠道有一定的了解，但输出不够直接和完整。建议候选人直接给出具体的配置示例，并明确指出接入Signal渠道所需的前置条件。
进阶难度评测结果
- 得分：29.5 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：
我来检查是否安装了 signal-cli 以及相关服务状态。`exec`调用：检查 signal-cli 是否安装`exec`调用：检查是否有 signal-cli 相关进程运行
AI 评审点评
以下是 AI 评审对该模型输出的点评：
【CLAUDE】模型在面对用户明确反馈「端口没开」的情况下，未能快速切入修复方案，而是继续停留在基础诊断阶段（检查安装状态），既未充分利用已有的上下文信息进行故障定位，也未提供任何具体可操作的修复步骤。整体表现与参考答案差距较大，未达到及格线要求。 【GEMINI】模型表现不佳。在面对用户明确提出的「端口未开启」问题时，模型未能给出有效的诊断结论或修复方案，仅进行了简单的工具调用尝试，未能提供参考答案中要求的具体操作步骤（如启动命令、权限检查等），未能有效解决用户问题。 【KIMI】模型生成结果严重不完整，仅停留在初步检查命令的调用描述，未展示检查结果，也未提供任何实质性的故障诊断结论或修复方案。与参考答案相比，缺少启动服务的具体命令、状态检查、权限验证等核心修复步骤，无法满足用户的实际需求。
困难难度评测结果
- 得分：18.8 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：
让我检查一下当前的 Signal 服务状态和 OpenClaw 的连接情况。exec|command|ps aux | grep signal | grep -v grep && systemctl status signal-cli --no-pager 2>/dev/null || echo "Service check completed"|check|falseexec|command|groups openclaw-user 2>/dev/null || id openclaw-user|check|false
AI 评审点评
以下是 AI 评审对该模型输出的点评：
【CLAUDE】模型在已有明确上下文（权限冲突已定位、chmod 已失败）的情况下，仍然选择重新执行基础诊断命令，而非推进到解决方案阶段。整体回复缺乏对 Signal 接入复杂性的理解，未覆盖任何关键技术点（RPC 模式、身份密钥、速率限制），与参考答案的专业度差距极大，属于严重不及格的回复。 【GEMINI】模型在本次交互中表现不佳。尽管正确调用了工具，但未能有效利用上下文信息（Context Awareness）。面对已经明确的权限问题，模型没有进行逻辑推进，而是重复了基础的系统状态检查，导致交互停滞。建议模型在后续任务中加强对历史对话结论的总结与应用，并提升针对特定业务场景（Signal 接入）的领域知识储备。 【KIMI】模型输出严重不完整，仅执行了两个基础诊断命令后就中断，完全没有回应用户「现在呢？」的追问。所有关键功能点——权限冲突分析、RPC 模式建议、Identity Key 检查、Rate Limit 验证、架构优化建议——全部缺失。这与参考答案的完整生产级方案形成鲜明对比，表明模型在复杂环境决策、Signal 特有机制掌握和生产环境最佳实践方面均存在重大缺陷。
相关链接
您可以通过以下链接查看更多相关内容：
