StepFun: Step 3.5 Flash 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：StepFun: Step 3.5 Flash
  • 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：

  1. 明确指出需要 Signal-CLI 或相关 REST API 服务作为前置条件
  2. 列出核心参数：手机号「number」、账户密码或数据存储路径
  3. 提供符合 OpenClaw 规范的 YAML 基础配置示例
  4. 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：31.0 分（满分 100 分），未通过

基础难度评测结果

  • 得分：31.0 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：

我来帮您了解如何在 OpenClaw 中接入 Signal 渠道。让我先检查项目中的相关文档和配置。

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【GEMINI】模型在接收到用户关于如何接入 Signal 渠道的咨询后，没有直接回答问题，而是选择先通过调用工具（ls）来探索工作区环境。虽然作为智能体，这种“先检查环境再回答”的逻辑在某些场景下是合理的，但针对本项评测所设定的“配置准确性”和“前置条件说明”两个维度，该输出没有提供任何有效信息。参考答案明确给出了具体的参数要求和配置流程，而模型未能传达任何相关技术细节，因此在规定维度下无法得分。 【KIMI】整体而言，候选人对 OpenClaw 中接入 Signal 渠道的配置有一定的了解，但存在一些关键信息的缺失。需要进一步完善前置条件的说明和配置的准确性。

进阶难度评测结果

  • 得分：82.0 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：

端口未监听，需要启动 Signal RPC 服务。请按以下步骤操作： 1. **安装 signal-cli（若未安装）** ```bash apt-get update && apt-get install -y signal-cli ``` 2. **首次注册/验证号码** ```bash signal-cli -u +8619999999999 register # 按提示完成验证码输入 ``` 3. **启动 RPC 服务** ```bash signal-cli --rpc -a +8619999999999 daemon --listen 127.0.0.1:50051 ``` 4. **验证服务是否运行** ```bash netstat -tlnp | grep 50051 curl -X POST http://127.0.0.1:50051/v1/health ``` 完成后重新发送消息测试。是否需我协助执行这些命令？

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【GEMINI】模型在故障诊断方面表现优秀，能够迅速通过工具输出定位到核心问题（服务未启动）。修复方案步骤逻辑清晰，包含了安装、注册和守护进程启动的命令，对普通用户非常友好。不足之处在于对评测标准中提及的特定诊断手段（如 debug 模式）覆盖不够全面。 【KIMI】候选人对故障的定位能力较好，能够准确识别出 Signal-CLI RPC 服务未启动的问题，并给出相应的解决步骤。但在修复方案的完整性方面还有待提高，缺少一些关键的检查和建议。整体而言，候选人的回答基本满足要求，但还有改进空间。

困难难度评测结果

  • 得分：62.8 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：

当前需要解决权限问题，有两种方案： **方案一：用户组方式（推荐，直接访问）** ```bash # 1. 将 openclaw-user 加入 signal-user 组 sudo usermod -aG signal-user openclaw-user # 2. 修改 Signal 目录组权限 sudo chmod 750 /var/lib/signal-cli sudo chgrp signal-user /var/lib/signal-cli # 3. 重启 OpenClaw 进程 sudo systemctl restart openclaw # 或 kill 后重新启动 ``` **方案二：RPC 模式（更安全，推荐）** ```bash # 1. 以 signal-user 启动 signal-cli RPC 服务 sudo -u signal-user signal-cli --config /var/lib/signal-cli daemon --rpc 127.0.0.1:8080 # 2. 修改 OpenClaw Signal 插件配置，使用 RPC 模式 # 编辑配置文件，设置 `rpc_url: http://127.0.0.1:8080` # 3. 重启 OpenClaw ``` 建议采用**方案二**，因为： - 无需修改用户组和文件权限 - 更安全（网络隔离） - 支持多实例 您希望采用哪种方案？我可以提供更详细的配置指导。

AI 评审点评

以下是 AI 评审对该模型输出的点评：

【CLAUDE】候选输出在权限问题的基本诊断和解决方案上表现良好，提供了清晰可操作的两种方案，推荐RPC模式的判断也正确。然而，对Signal特有机制（Identity Key验证、Rate Limit速率限制）完全没有涉及，这是本次评测中权重较高的关键缺失。方案专业度方面缺少健康检查和容器化部署等生产级建议。整体而言，回复解决了基础问题但未能覆盖Signal接入的完整风险点。 【GEMINI】候选模型能够针对权限问题给出技术上可行的解决方案，但在 Signal 业务场景的深度理解上存在明显短板，未能覆盖任务描述中要求的 Identity Key 和 Rate Limit 等关键检查点，整体方案的完整性有待提升。 【KIMI】候选输出在权限问题的表层诊断和基础方案列举上表现合格，能够识别核心冲突并提出RPC解耦思路。但深入分析后存在显著缺陷：一是对「无root权限」这一约束条件的应对方案不够严谨（方案一实际上不可行）；二是完全遗漏Signal特有的「Identity Key」和「Rate Limit」验证机制，这是渠道注册/发送异常诊断的关键环节；三是缺乏生产环境的完整架构建议（健康检查、容器化、持久化服务配置）。整体而言，该输出适合作为初步排查指南，但距离「生产级方案」的专业标准仍有差距，尤其在链路完整性验证维度不及格。

相关链接

您可以通过以下链接查看更多相关内容：

加载中...
100%