← 返回
未分类

Codex Reset Radar

Monitor Codex usage reset windows via codex-reset-radar.pages.dev. Polls current.json, detects window open/close, prediction level changes, and probability j...
通过 codex-reset-radar.pages.dev 监控 Codex 使用重置窗口。轮询 current.json,检测窗口开启/关闭、预测等级变化以及概率跳变。
advnljs
未分类 clawhub v1.0.4 2 版本 99651.6 Key: 无需
★ 1
Stars
📥 266
下载
💾 0
安装
2
版本
#codex#cron#feishu#latest#monitoring#quota#radar

概述

Codex Reset Radar — Usage Reset Window Monitor

Monitors the Codex Reset Radar current.json endpoint to detect Codex usage quota reset windows ("speed windows"), pushing alerts via OpenClaw cron to the default agent chat channel.

How It Works

Cron triggers
     │
     ▼
① Data collection: python3 scripts/codex-radar-check.py
   → fetch current.json + compare against local cache
     │
     ▼
② JSON diff: outputs has_changes + events[] or has_changes: false
   → no changes → agent replies NO_REPLY (silent)
     │
     ▼
③ LLM formatting: reads JSON diff only
   → formats into a friendly chat message
     │
     ▼
④ Chat push: announce → user session (default chat channel)

Detection Script

scripts/codex-radar-check.py — stdlib only, zero dependencies:

  • Fetches https://codex-reset-radar.pages.dev/current.json
  • Compares against cache/codex-radar-last.json from previous run
  • Creates baseline on first run

Change types detected:

EventTriggerOutput type
-----------------------------
Window openedwindow_open false→truewindow_opened
Window closedwindow_open true→falsewindow_closed
Status changestatus field changedstatus_change
New windowlast_window.id changednew_window
Prediction changeprediction.level changedprediction_change
Probability jumpprediction.probability_24h crosses 0.1 thresholdprediction_probability_change

Output JSON Examples

No changes:

{"has_changes": false}

Changes detected:

{
  "has_changes": true,
  "events": [
    {"type": "window_opened", "detail": "Codex usage reset window opened", "opened_at": "2026-05-24T08:21:33+08:00", "scope": "Codex users"}
  ],
  "current_status": {
    "window_open": true,
    "status": "open",
    "last_window_id": "codex-speed-window-2026-05-24-codex",
    "prediction_level": "low",
    "probability_24h": 0.06
  }
}

Installation

clawhub install codex-reset-radar

Cron Setup

Create an OpenClaw cron job (recommended: hourly 8 AM–11 PM, silent overnight).

The delivery target will automatically use your default agent chat channel:

{
  "name": "Codex Reset Radar Monitor",
  "schedule": {"kind": "cron", "expr": "0 8-23 * * *", "tz": "Asia/Shanghai"},
  "sessionTarget": "isolated",
  "payload": {
    "kind": "agentTurn",
    "timeoutSeconds": 60,
    "lightContext": true,
    "message": "Codex Reset Radar monitor.\n1. cd ~/.openclaw/workspace && python3 skills/codex-reset-radar/scripts/codex-radar-check.py\n2. If has_changes: false, reply NO_REPLY\n3. If changes detected, format and push to default chat channel"
  }
}

> 💡 The cron job will push alerts to whatever chat channel your OpenClaw agent uses by default (Feishu, Discord, Telegram, etc.). No channel-specific config needed.

Recommended schedules:

  • 0 8-23 * — hourly during waking hours, silent 0-7
  • /10 * — every 10 minutes (urgent monitoring)

Design Principles

  • LLM only sees JSON diffs — no raw RSS/HTML semantic analysis, minimal token usage
  • Zero-cost silencehas_changes: false → agent replies NO_REPLY → nothing pushed to chat
  • Stdlib only — uses json, urllib, datetime, os; zero external dependencies
  • Fault-tolerant — network errors output {"has_changes": false, "error": "..."}, never false-trigger or crash
  • Channel-agnostic — works with any chat channel (Feishu, Discord, Telegram, etc.) via OpenClaw's delivery system

版本历史

共 2 个版本

  • v1.0.4 当前
    2026-05-26 23:40 安全 安全
  • v1.0.3
    2026-05-25 17:24 安全 安全

安全检测

腾讯云安全 (Keen)

安全,无风险
查看报告

腾讯云安全 (Sanbu)

安全,无风险
查看报告

🔗 相关推荐

dev-programming

Github

steipete
使用 `gh` CLI 与 GitHub 交互,通过 `gh issue`、`gh pr`、`gh run` 和 `gh api` 管理议题、PR、CI 运行及高级查询。
★ 676 📥 325,377
ai-agent

self-improving agent

pskoett
捕获经验教训、错误及修正内容,以实现持续改进。适用于以下场景:(1)命令或操作意外失败;(2)用户纠正Claude(如“不,那不对……”“实际上……”);(3)用户请求的功能不存在;(4)外部API或工具出现故障;(5)Claude发现自身
★ 4,081 📥 809,649
ai-agent

Skill Vetter

spclaudehome
AI智能体技能安全预审工具。安装ClawdHub、GitHub等来源技能前,检查风险信号、权限范围及可疑模式。
★ 1,226 📥 267,763