openclaw-logfire

Installs and configures the openclaw-logfire plugin for OpenClaw, including LOGFIRE_TOKEN setup, openclaw.json edits, provider mapping, privacy settings, and Logfire write token onboarding. Use when a user wants Logfire observability, traces, token metrics, or help connecting OpenClaw to Logfire.

Safety Notice

This listing is imported from skills.sh public index metadata. Review upstream SKILL.md and repository scripts before running.

Copy this and send it to your AI assistant to learn

Install skill "openclaw-logfire" with this command: npx skills add chenbaiyujason/openclaw-logfire/chenbaiyujason-openclaw-logfire-openclaw-logfire

OpenClaw Logfire

Use this skill when the user wants to install, configure, debug, or explain the @shichen335/openclaw-logfire plugin.

Goal

Set up openclaw-logfire so OpenClaw exports agent traces and metrics to Pydantic Logfire.

Preconditions

Confirm these before editing anything:

  • OpenClaw version is >= 2026.2.1
  • Node.js version is >= 20
  • The plugin entry key will be plugins.entries.openclaw-logfire
  • A Logfire write token is available, or the user wants guidance to create one

Default Workflow

Follow this order:

  1. Install the plugin:
openclaw plugins install @shichen335/openclaw-logfire
  1. Prefer environment-based auth:
export LOGFIRE_TOKEN="<your-write-token>"
  1. Add or update openclaw.json:
{
  "plugins": {
    "entries": {
      "openclaw-logfire": {
        "enabled": true,
        "config": {}
      }
    }
  }
}
  1. Restart OpenClaw.
  2. Verify that Logfire receives spans.

If The User Does Not Have A Token Yet

Guide them through the Logfire web UI:

  1. Open Logfire Login.
  2. Sign up or sign in.
  3. If needed, create a project in Organization > Projects.
  4. Open the target project.
  5. Go to Settings > Write tokens.
  6. Create a new write token.
  7. Tell the user to save it immediately.
  8. Use that value as LOGFIRE_TOKEN.

Use the term write token, not project token. Use the environment variable LOGFIRE_TOKEN, not LOGFIRE_WRITE_TOKEN.

Recommended Config Templates

Minimal

Use this when the user wants the safest starting point:

{
  "plugins": {
    "entries": {
      "openclaw-logfire": {
        "enabled": true,
        "config": {}
      }
    }
  }
}

Rich Debugging

Use this when the user wants deep payload visibility and accepts privacy trade-offs:

{
  "plugins": {
    "entries": {
      "openclaw-logfire": {
        "enabled": true,
        "config": {
          // Use LOGFIRE_TOKEN in the environment unless the user explicitly
          // wants to keep the token in config.
          "projectUrl": "https://logfire.pydantic.dev/<org>/<project>",
          "providerNameMap": {
            "customprovider": "openai"
          },
          "captureMessageContent": true,
          "captureHistoryMessages": true,
          "historyMessagesMaxLength": 100000,
          "toolInputMaxLength": 100000,
          "toolOutputMaxLength": 16384,
          "redactSecrets": false,
          "saveHookLogs": false
        }
      }
    }
  }
}

Supported Config Keys

These keys currently affect runtime behavior:

KeyDefaultNotes
token""Prefer LOGFIRE_TOKEN. Without a token, the plugin disables itself.
projectUrl""Enables clickable trace links when enableTraceLinks is true.
region"us"Accepts "us" or "eu".
environment"development"Falls back to LOGFIRE_ENVIRONMENT.
serviceName"openclaw-agent"OTEL service.name.
providerName""Falls back to LOGFIRE_PROVIDER_NAME.
providerNameMap{}Useful for ids such as customprovider -> openai.
captureToolInputtrueCaptures tool arguments.
captureToolOutputfalseCaptures tool results.
toolInputMaxLength2048Integer truncation limit.
toolOutputMaxLength512Integer truncation limit.
captureMessageContentfalseCaptures chat content and system instructions. Privacy-sensitive.
captureHistoryMessagesfalseHelps reconstruct conversation history on the root span.
historyMessagesMaxLength16384Integer truncation limit for serialized history.
redactSecretstrueBest-effort secret redaction.
distributedTracing.enabledfalseEnables outbound command propagation.
distributedTracing.injectIntoCommandstrueInjects traceparent into matching commands.
distributedTracing.urlPatterns["*"]URL glob allowlist.
enableMetricstrueSends token and duration metrics.
metricsIntervalMs60000Metrics export interval.
enableTraceLinkstrueLogs clickable trace links when projectUrl exists.
saveHookLogsfalseWrites raw hook payloads to ~/.openclaw/logs/.
resourceAttributes{}Additional OTEL resource attributes.
spanProcessorType"batch"Use "simple" for debugging.
batchConfig.maxQueueSize2048Batch exporter queue size.
batchConfig.maxExportBatchSize512Batch size limit.
batchConfig.scheduledDelayMs5000Batch delay.

Accepted But Not Fully Wired

These keys are accepted by the schema or resolver, but should not be described as fully effective:

KeyStatus
captureStackTracesReserved
captureToolDefinitionsReserved
distributedTracing.extractFromWebhooksReserved
logLevelReserved
useGenAiCompatibilityScopeLegacy compatibility field

Behavior Notes The Agent Should Know

  • The plugin reconstructs chat <model> spans at llm_output, not at llm_input.
  • llm_output should run after OpenClaw has assembled the full lastAssistant, or Logfire may show incomplete output.
  • agent_end may wait briefly for pending llm_output processing before finalizing the root span.
  • captureMessageContent: true increases the amount of captured content significantly.
  • saveHookLogs: true writes local files and should usually be temporary.

Privacy Defaults

Prefer these defaults unless the user explicitly asks for richer capture:

  • keep captureMessageContent: false
  • keep captureToolOutput: false
  • keep redactSecrets: true
  • keep saveHookLogs: false
  • keep the token in the environment, not in committed config

Troubleshooting Checklist

If traces do not appear:

  1. Check that LOGFIRE_TOKEN exists in the runtime environment.
  2. Check that the plugin key is exactly openclaw-logfire.
  3. Check that OpenClaw was restarted.
  4. Check that OpenClaw is new enough to emit llm_input, llm_output, and before_tool_call.
  5. Check network access to the selected Logfire region.

If chat spans are missing or incomplete:

  1. Check whether llm_output is emitted with the final lastAssistant.
  2. Check whether the run only produced tool calls without a completed assistant payload.

If the user wants to inspect hook payloads:

  1. Temporarily enable saveHookLogs: true.
  2. Reproduce the issue.
  3. Turn saveHookLogs back off after debugging.

Output Guidance

When helping a user:

  • prefer a minimal config first
  • explain privacy-sensitive options before enabling them
  • never echo or commit a real token
  • redact any shared secrets when quoting openclaw.json
  • use projectUrl only for the Logfire web project URL, not an OTLP endpoint

Source Transparency

This detail page is rendered from real SKILL.md content. Trust labels are metadata-based hints, not a safety guarantee.

Related Skills

Related by shared tags or category signals.

General

问专家 - Playwriter模式

# 问专家技能 - 使用 Playwriter 控制已登录的浏览器

Archived SourceRecently Updated
General

ai-image-generator

AI 图片与视频异步生成技能,调用 AI Artist API 根据文本提示词生成图片或视频,自动轮询直到任务完成。 ⚠️ 使用前必须设置环境变量 AI_ARTIST_TOKEN 为你自己的 API Key! 获取 API Key:访问 https://staging.kocgo.vip/index 注册登录后创建。 支持图片模型:SEEDREAM5_0(默认高质量图片)、NANO_BANANA_2(轻量快速)。 支持视频模型:SEEDANCE_1_5_PRO(文生视频,支持音频)、SORA2(文生视频或首尾帧图生视频,支持 firstImageUrl/lastImageUrl)。 触发场景: - 用户要求生成图片,如"生成一匹狼"、"画一只猫"、"风景画"、"帮我画"等。 - 用户要求生成视频,如"生成视频"、"用 SORA2 生成"、"文生视频"、"图生视频"、"生成一段...的视频"等。 - 用户指定模型:SEEDREAM5_0、NANO_BANANA_2、SEEDANCE_1_5_PRO、SORA2。

Archived SourceRecently Updated
General

淘宝投放数据分析

# 投放数据分析技能

Archived SourceRecently Updated
General

productclank-campaigns

Community-powered growth for builders. Boost amplifies your social posts with authentic community engagement (replies, likes, reposts). Discover finds relevant conversations and generates AI-powered replies at scale. Use Boost when the user has a post URL. Use Discover when the user wants to find and engage in conversations about their product.

Archived SourceRecently Updated