Can´t use DeepSeek API

### Describe the bug

When I run the following command:

```bash
export COPILOT_PROVIDER_BASE_URL="https://api.deepseek.com" \
export COPILOT_PROVIDER_API_KEY="...." \
export COPILOT_PROVIDER_TYPE="openai" \
export COPILOT_MODEL="deepseek-v4-pro" \
copilot
```

When I make a question to the copilot, I get this answer back:

```
● Request failed (transient_bad_request). Retrying...
● Request failed (transient_bad_request). Retrying...
✗ 400 The `reasoning_content` in the thinking mode must be passed back to the API.
```

I confirm that the DeepSeek API needs the entire reasoning_content field to be returned back to the API every time. In my own code I had the same problem and could rapidly fix the issue by sending back the the entire conversation.

### Affected version

_No response_

### Steps to reproduce the behavior

I run the following command:

```bash
export COPILOT_PROVIDER_BASE_URL="https://api.deepseek.com" \
export COPILOT_PROVIDER_API_KEY="...." \
export COPILOT_PROVIDER_TYPE="openai" \
export COPILOT_MODEL="deepseek-v4-pro" \
copilot
```

Ensure to have a valid api key for the DeepSeek endpoint

### Expected behavior

I expect the request to be fulfilled.

### Additional context

_No response_

Start by reproducing the issue through the `copilot` entry point with the documented DeepSeek environment variables and inspect how the request conversation is assembled. The fix is done when the complete `reasoning_content` is passed back to the DeepSeek API and the request succeeds without the 400 error.

Rédigé par le modèle d'indexation à partir du texte de l'issue.