update model provider

[c121914yu]

No description provided.

[github-actions]

✅ Build Successful - Preview Images for this PR:

registry.cn-hangzhou.aliyuncs.com/fastgpt/fastgpt-plugin-pr:cfff8a9c50cc570f1903517f5d0197b0b883c40f

Changed packages:
None

[Copilot]

Pull request overview

This PR updates model provider configurations across OpenAI, MiniMax, and ChatGLM providers. The changes include adjusting context window limits for existing models, adding new model variants, and expanding TTS (text-to-speech) support for MiniMax.

• Reduced maxContext and quoteMaxToken limits for OpenAI gpt-5.x model variants from 400,000 to 250,000 and 200,000 respectively
• Added three new MiniMax LLM models (M2.1, M2, M1) with reasoning capabilities and three new TTS models (speech-02-turbo, speech-02-hd, speech-01-hd) with extensive voice options
• Introduced ChatGLM glm-4.7 model with reasoning support and 200K context window

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 1 comment.

File	Description
modules/model/provider/OpenAI/index.ts	Reduced maxContext from 400K to 250K and quoteMaxToken from 400K to 200K for gpt-5.2, gpt-5.1, gpt-5, gpt-5-mini, and gpt-5-nano models
modules/model/provider/MiniMax/index.ts	Added three new LLM models (MiniMax-M2.1, M2, M1) and three TTS models (speech-02-turbo, speech-02-hd, speech-01-hd) with 46 voice options each; updated MiniMax-Text-01 configuration and removed abab6.5s-chat model
modules/model/provider/ChatGLM/index.ts	Added new glm-4.7 model with 200K context, 130K max tokens, reasoning capability, and JSON object response format support
modules/model/constants.ts	Reordered MiniMax and Ernie entries in ModelProviderMap (no functional change)

---

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

[Copilot]

The quoteMaxToken value for MiniMax-Text-01 appears inconsistent with the pattern used for MiniMax-M1. Both models have maxContext of 1000000, but MiniMax-M1 has quoteMaxToken of 900000 (90% of maxContext) while MiniMax-Text-01 has only 90000 (9% of maxContext). This seems like it may be a typo - consider verifying if this should be 900000 instead of 90000 to align with the M1 model configuration.

Suggested change

	quoteMaxToken: 90000,
	quoteMaxToken: 900000,