← 返回
AI智能 中文

Model Switcher

Automatically switch between different AI models based on task complexity. Supports all available models in your OpenClaw setup. Triggers when detecting comp...
根据任务复杂度自动切换不同的AI模型。支持OpenClaw设置中的所有可用模型。当检测到复杂...
puaservice
AI智能 clawhub v1.0.2 1 版本 99930.9 Key: 无需
★ 0
Stars
📥 1,447
下载
💾 48
安装
1
版本
#latest#model-management#productivity

概述

Model Switcher

Automatically detect task complexity and switch to the appropriate model.

Model Configuration

Based on your setup:

  • Fast model (haiku): custom-kiro-cli-vipdump-eu-org/claude-haiku-4-5 - For simple, quick tasks
  • Powerful model (sonnet): custom-kiro-cli-vipdump-eu-org/claude-sonnet-4-5 - For complex analysis

Trigger Keywords (Chinese)

Switch to sonnet when message contains:

  • 分析、深入分析、详细分析
  • 重构、代码重构
  • 架构、系统架构、设计架构
  • 设计、系统设计
  • 优化、性能优化
  • 复杂、复杂问题
  • 调试、深度调试
  • 评估、技术评估

Workflow

  1. Check current model using session_status
  2. Detect keywords in user message
  3. Switch if needed:
    • Complex task detected + currently on haiku → switch to sonnet
    • Simple task + currently on sonnet → optionally switch back to haiku
  4. Inform user briefly about the switch

Implementation

Use session_status tool with model parameter:

// Switch to sonnet for complex tasks
session_status({ model: "kiro-cli" })

// Switch back to haiku for simple tasks
session_status({ model: "haiku" })

// Reset to default
session_status({ model: "default" })

Example Detection Logic

User message: "帮我分析一下这个系统的架构"
→ Contains: "分析", "架构"
→ Action: Switch to sonnet if not already on it
→ Response: "🔄 切换到 sonnet 模型来处理这个复杂任务..."

Notes

  • Be smart about switching - don't switch for every message
  • Batch related complex tasks on sonnet before switching back
  • Inform user only on actual switches, not when already on correct model
  • Consider context: if already discussing complex topic, stay on sonnet

版本历史

共 1 个版本

  • v1.0.2 当前
    2026-03-29 06:53 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

ai-intelligence

self-improving agent

pskoett
捕获经验教训、错误和纠正,以实现持续改进。使用时机:(1)命令或操作意外失败;(2)用户纠正……
★ 4,061 📥 799,115
ai-intelligence

Self-Improving + Proactive Agent

ivangdavila
自我反思+自我批评+自我学习+自组织记忆。智能体评估自身工作、发现错误并持续改进。
★ 1,362 📥 318,920
ai-intelligence

ontology

oswalpalash
类型化知识图谱,用于结构化智能体记忆与可组合技能。支持创建/查询实体(人员、项目、任务、事件、文档)及关联...
★ 714 📥 244,075