continuedev / continuedev/continue

VS Code Chat Ollama on local server ETIMEDOUT

Open
#4,650 2 comments 0 reactions 1 assignee View on GitHub

@bdougie is already working on this.

Since Oct 22, 2025.

area:chat ide:vscode kind:bug needs-triage os:windows
Dominant language
TypeScript
Stars
36k
Forks
5.4k
PR merge metrics
No merged PRs in 30d

Description

Before submitting your bug report
Relevant environment info
- Continue extension details : 
Identifier : continue.continue
Version : 1.0.3
Last Updated : 2025-03-11, 17:43:47
- IDE : VS Code 1.98.0
- OS : Windows 11
Description

VS Code Continue extension on a computer + local ollama server accessed through VPN gives error using the chat but ollama POST is working

To reproduce

Hi,

  • Currently running a local ollama server on a private network. I installed VS Code Continue extension and want to use models from the ollama server (access through a VPN).

  • Trying to use the chat returns : request to http://[XXX.XX.X.XX]:11434/api/chat failed, reason: connect ETIMEDOUT [XXX.XX.X.XX]:11434

  • The error log is the following :

Error handling webview message: {
  "msg": {
    "messageId": "9c9bc2fc-fdb5-44fa-8d52-1e1d89adb569",
    "messageType": "llm/streamChat",
    "data": {
      "messages": [
        {
          "role": "system",
          "content": "..."
        },
        {
          "role": "user",
          "content": [
            {
              "type": "text",
              "text": "Say \"Hi!\""
            }
          ]
        },
        {
          "role": "assistant",
          "content": ""
        }
      ],
      "title": "deepseek-r1",
      "completionOptions": {}
    }
  }
}

Error: request to http://[XXX.XX.X.XX]:11434/api/chat failed, reason: connect ETIMEDOUT [XXX.XX.X.XX]:11434
  • Using Postman to check the POST request http://[XXX.XX.X.XX]:11434/api/chat works with the following payload (returning response 200 and a valid answer):
{
  "model": "deepseek-r1:70b",
  "messages": [
    {
      "role": "system",
      "content": "..." 
    },
    {
      "role": "user", 
      "content": "Answer with one single word. The sky colour is"
    }
  ],
  "stream": false
}
  • My config.yaml is :
name: continue_config_v0
version: 0.0.1
schema: v1

models:
  - name : deepseek-r1
    model: deepseek-r1:70b
    provider: ollama
    apiBase: http://[XXX.XX.X.XX]:11434/
    roles:
      - chat
    defaultCompletionOptions:
      temperature: 0.5
      maxTokens: 2000

rules:
  - Give concise responses
  • Continue extension details :
    Identifier : continue.continue
    Version : 1.0.3
    Last Updated : 2025-03-11, 17:43:47

  • IDE : VS Code 1.98.0

  • OS : Windows 11

Log output
Error handling webview message: {
  "msg": {
    "messageId": "9c9bc2fc-fdb5-44fa-8d52-1e1d89adb569",
    "messageType": "llm/streamChat",
    "data": {
      "messages": [
        {
          "role": "system",
          "content": "..."
        },
        {
          "role": "user",
          "content": [
            {
              "type": "text",
              "text": "Say \"Hi!\""
            }
          ]
        },
        {
          "role": "assistant",
          "content": ""
        }
      ],
      "title": "deepseek-r1",
      "completionOptions": {}
    }
  }
}

Error: request to http://[XXX.XX.X.XX]:11434/api/chat failed, reason: connect ETIMEDOUT [XXX.XX.X.XX]:11434

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.