feat: add chat_template_kwargs for nvidia nim provider

[andriixyz]

From the official documentation for nvidia nim it is possible to set "enable_thinking":true,"clear_thinking":false inside the request, this PR adds support of that
Resolves #13584.

https://build.nvidia.com/z-ai/glm5/modelcard

Example of code:

import OpenAI from 'openai';

const openai = new OpenAI({
  apiKey: '$NVIDIA_API_KEY',
  baseURL: 'https://integrate.api.nvidia.com/v1',
})
 
async function main() {
  const completion = await openai.chat.completions.create({
    model: "z-ai/glm5",
    messages: [{"role":"user","content":""}],
    temperature: 1,
    top_p: 1,
    max_tokens: 16384,
    chat_template_kwargs: {"enable_thinking":true,"clear_thinking":false},
    stream: true
  })
   
  for await (const chunk of completion) {
        const reasoning = chunk.choices[0]?.delta?.reasoning_content;
    if (reasoning) process.stdout.write(reasoning);
        process.stdout.write(chunk.choices[0]?.delta?.content || '')
    
  }
  
}

main();

[github-actions]

Thanks for your contribution!

This PR doesn't have a linked issue. All PRs must reference an existing issue.

Please:

1. Open an issue describing the bug/feature (if one doesn't exist)
2. Add Fixes #<number> or Closes #<number> to this PR description

See CONTRIBUTING.md for details.

[alexyaroshuk]

possible to avoid 'any' ?
see style preferences

[alexyaroshuk]

lgtm

[alexyaroshuk]

possible to avoid 'any' ? see style preferences

upon further review this comment is irrelevant, as the original file has 'any' typing to begin with https://github.com/anomalyco/opencode/blob/dev/packages/opencode/test/provider/transform.test.ts

[github-actions]

Closing this pull request because it has had no updates for more than 60 days. If you plan to continue working on it, feel free to reopen or open a new PR.

[arrrnmp]

What happened with this PR, this feature is key!