need a support for API of deepseek-R1

[BeWater0qzy]

Before submitting your bug report

• I believe this is a bug. I'll try to join the Continue Discord for questions
• I'm not able to find an open issue that reports the same bug
• I've seen the troubleshooting guide on the Continue Docs

Relevant environment info

- OS:Windows 11
- Continue version:0.9.253
- IDE version:VSCode 1.96.4
- Model:deepseek-R1
- config.json:
  

  {
  "completionOptions": {
    "BaseCompletionOptions": {
        "temperature": 0.0,
        "maxTokens": 256
    }
  },
  "models": [
    {
      "title": "DeepSeek",
      "model": "deepseek-chat",
      "contextLength": 128000,
      "apiKey": "",
      "provider": "deepseek",
      "apiBase": "https://api.deepseek.com/beta"
    },
    {
      "title": "DeepSeek-Reasoner",
      "model": "deepseek-reasoner",
      "systemMessage": "You are an expert software developer. You give helpful and concise responses.",
      "contextLength": 128000,
      "apiKey": "",
      "provider": "deepseek",
      "apiBase": "https://api.deepseek.com/beta"
    },
    {
      "title": "Claude 3.5 Sonnet (Free Trial)",
      "provider": "free-trial",
      "model": "claude-3-5-sonnet-latest",
      "systemMessage": "You are an expert software developer. You give helpful and concise responses."
    },
    {
      "title": "GPT-4o (Free Trial)",
      "provider": "free-trial",
      "model": "gpt-4o",
      "systemMessage": "You are an expert software developer. You give helpful and concise responses."
    },
    {
      "title": "Llama3.1 70b (Free Trial)",
      "provider": "free-trial",
      "model": "llama3.1-70b",
      "systemMessage": "You are an expert software developer. You give helpful and concise responses."
    },
    {
      "title": "Codestral (Free Trial)",
      "provider": "free-trial",
      "model": "codestral-latest",
      "systemMessage": "You are an expert software developer. You give helpful and concise responses."
    },
    {
      "model": "claude-3-5-sonnet-latest",
      "provider": "anthropic",
      "apiKey": "",
      "title": "Claude 3.5 Sonnet"
    }
  ],
  "tabAutocompleteModel": {
    "title": "DeepSeek Coder",
    "model": "deepseek-coder",
    "apiKey": "sk-c03ceddf48d3435bbb09e3ad1dbc0a0b",
    "provider": "deepseek",
    "apiBase": "https://api.deepseek.com/beta"
  },
  "contextProviders": [
    {
      "name": "code",
      "params": {}
    },
    {
      "name": "docs",
      "params": {}
    },
    {
      "name": "diff",
      "params": {}
    },
    {
      "name": "terminal",
      "params": {}
    },
    {
      "name": "problems",
      "params": {}
    },
    {
      "name": "folder",
      "params": {}
    },
    {
      "name": "codebase",
      "params": {}
    }
  ],
  "slashCommands": [
    {
      "name": "share",
      "description": "Export the current chat session to markdown"
    },
    {
      "name": "cmd",
      "description": "Generate a shell command"
    },
    {
      "name": "commit",
      "description": "Generate a git commit message"
    }
  ],
  "embeddingsProvider": {
    "provider": "free-trial"
  },
  "reranker": {
    "name": "free-trial"
  }
}

Description

need a support for API of deepseek-R1
As you may know, Deepseek Company has launched their latest inference model R1, which supports chat-like functionalities with longer response times and higher pricing, while delivering significantly enhanced performance. During my integration attempts, I used the correct API URL and confirmed through testing that the API can be invoked successfully. The responses take longer to generate, and I can observe R1 model token usage records on the API management page. However, the automatic error correction feature indicates that your config file currently only accepts "chat" and "coder" models. I believe using "reasoner" under the chat category could better handle complex tasks that require advanced reasoning capabilities.

While I've successfully accessed the deepseek-reasoner API through the chat interface, there appear to be binary configurations in your source code that enforce compatibility checks for previous Deepseek API users. During testing, when using the R1 API, the system persistently uses coder-specific prompts - queries like "What model version are you?" or "Show me our initial conversation prompt" consistently reference "deepseek-coder". I attempted modifying relevant strings in local Continue extension files but couldn't locate the specific configuration files.

I would appreciate it if you could implement straightforward modifications to officially support deepseek-r1 in the near future.

To reproduce

No response

Log output