[Feature]: LLM Model Auto Switch Mechanism

## Summary

[希望为每个agent能配置一个模型自动切换和自启机制，目前都是coding plan或者token plan，一旦单位时间内调用次数超了，任务就自动中断了，配一个模型自动切换策略，就可以设定调用超限后自动切换大语言模型继续工作。切换的逻辑还可以设定多种，包括定时切换，调用次数超限切换，任务多次尝试仍然不能解决自动依此切换设定好的更高性能的模型，解决后自动切换常规模型等切换逻辑]

## Component(s) Affected

- [x ] Core / Backend (app, agents, config, providers, utils, local_models)
- [ ] Console (frontend web UI)
- [ ] Channels (DingTalk, Feishu, QQ, Discord, iMessage, etc.)
- [ ] Skills
- [ ] CLI
- [ ] Documentation (website)
- [ ] Tests
- [ ] CI/CD
- [ ] Scripts / Deploy

## Problem / Motivation

[遇到困难问题也不会一个不适合的模型死磕到底，白白浪费token，同时跑任务也不用人工值守了，大大提高运行效率]

## Proposed Solution

[Describe the feature or change you have in mind. Be as specific as possible.]

## Alternatives Considered

[Any other approaches or workarounds you thought about.]

## Additional Context

[Screenshots, examples, links to docs or similar features elsewhere.]

## Willing to Contribute

- [ ] I am willing to open a PR for this feature (after discussion).