fix input_tokens adaptation error

[cuipengfei]

No description provided.

[Copilot]

Pull Request Overview

This PR fixes an input_tokens adaptation error by properly handling cached tokens in the token usage calculations for both streaming and non-streaming chat completion responses.

• Updates the ChatCompletionResponse interface to include optional prompt_tokens_details with cached_tokens
• Modifies input_tokens calculation to subtract cached tokens from prompt tokens
• Adds cache_read_input_tokens field when cached tokens are present

Reviewed Changes

Copilot reviewed 3 out of 3 changed files in this pull request and generated no comments.

File	Description
src/services/copilot/create-chat-completions.ts	Adds optional prompt_tokens_details field to support cached token tracking
src/routes/messages/stream-translation.ts	Updates token calculations in streaming responses to handle cached tokens
src/routes/messages/non-stream-translation.ts	Updates token calculations in non-streaming responses to handle cached tokens

---

_{Tip: Customize your code reviews with copilot-instructions.md. Create the file or learn how to get started.}