server: Support chat_template_kwargs for /v1/messages

[Soreepeong]

Overview

This PR passthroughs chat_template_kwargs when the feature is invoked using Anthropic compatible endpoint.

OpenAI compatible endpoint /v1/completions will handle chat_template_kwargs, but Anthropic compatible endpoint /v1/messages does not. As it is a nonstandard option in OAI anyway, I thought it's fine to add nonstandard feature to Anthropic handler too.

Additional information

Use case

I am using a custom proxy application that transforms model name suffix to parameter presets, such as /think suffix will add {"chat_template_kwargs": true} to the completions/messages request body.

Testing

The model is configured to have thinking disabled.

Command

curl -v http://127.0.0.1:12345/v1/messages ^
  -H "anthropic-version: 2023-06-01" ^
  -H "content-type: application/json" ^
  --data-raw "{\"model\": \"Qwen3.6-35B-A3B\", \"chat_template_kwargs\": {\"enable_thinking\": true}, \"messages\": [{\"role\": \"user\", \"content\": \"What is 1 + 1?\"}]}"

Before this PR

{"id":"chatcmpl-AzD7ukLinv1EGcbg3fX6gV7Sy1AH54tq","type":"message","role":"assistant","content":[{"type":"text","text":"1 + 1 equals **2**."}],"model":"Qwen3.6-35B-A3B","stop_reason":"end_turn","stop_sequence":null,"usage":{"cache_read_input_tokens":0,"input_tokens":20,"output_tokens":9}}

After this PR

{"id":"chatcmpl-O9T75TOmt4gRo5NnzlaVLQcIVuZAOopd","type":"message","role":"assistant","content":[{"type":"thinking","thinking":"Here's a thinking process:\n\n1.  **Analyze User Input:** The user asks \"What is 1 + 1?\"\n2.  **Identify Core Task:** This is a basic arithmetic question.\n3.  **Calculate Result:** 1 + 1 = 2.\n4.  **Formulate Response:** State the answer clearly and concisely. \"1 + 1 equals 2.\"\n5.  **Check for Edge Cases/Context:** None. It's a straightforward math question with no tricks or additional context needed.\n6.  **Final Output Generation:** Provide the direct answer.✅\n","signature":""},{"type":"text","text":"1 + 1 equals **2**."}],"model":"Qwen3.6-35B-A3B","stop_reason":"end_turn","stop_sequence":null,"usage":{"cache_read_input_tokens":0,"input_tokens":18,"output_tokens":144}}*

Requirements

• I have read and agree with the contributing guidelines
• AI usage disclosure: NO