bugfix: convert several providers stop_reason to valid openai finish_reason

[unsync]

Description:
Currently, we forward the anthropic stop_reason, which is not compatible with the openai finish_reason.

This can cause warnings from some OpenAI sdk.

The conversion function returns stop as a default value in case new stop_reason are added.

There was also a bug in the groq and google providers for the finish_reason

Side note:
It would probably be beneficial to update the types to we can get compilation-time validation :

gateway/src/providers/types.ts

Lines 101 to 123 in 77f32e5

	/**
	* The structure of a completion response for the 'complete' function.
	* @interface
	*/
	export interface CompletionResponse extends CResponse {
	choices: {
	text: string;
	index: number;
	logprobs: null;
	finish_reason: string;
	}[];
	}
	/**
	* The structure of a choice in a chat completion response.
	* @interface
	*/
	export interface ChatChoice {
	index: number;
	message: Message;
	finish_reason: string;
	logprobs?: object | null;
	}

Proposed change :

export interface ChatChoice {
  index: number;
  message: Message;
  finish_reason: 'stop' | 'length' | 'function_call' | 'content_filter' | null;
  logprobs?: object | null;
}

export interface CompletionResponse extends CResponse {
  choices: {
    text: string;
    index: number;
    logprobs: null;
    finish_reason: 'stop' | 'length' | 'function_call' | 'content_filter' | null;
  }[];
}

see https://platform.openai.com/docs/guides/text-generation/chat-completions-response-format

[unsync]

hello @vrushankportkey @VisargD, i'm not sure if there is a process after opening a PR to request a review, any chance this PR could be considered ?

[vrushankportkey]

Thank you so much @unsync! Yes, we're checking the PR and will share review if any in some time! Really appreciate you pushing this bugfix 🙌