Owen 2.5 Coder 7b misnamed in config file

[lucabae]

Before submitting your bug report

• I've tried using the "Ask AI" feature on the Continue docs site to see if the docs have an answer
• 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: macOS Sequoia
- Continue version: v1.0.0
- IDE version: VSCode 1.102.3 (Universal)
- Model: Qwen 2.5 Coder 7b
- config:
  
name: Local Agent
version: 1.0.0
schema: v1
models:
  - name: Qwen 2.5 Coder 7b
    provider: ollama
    model: qwen-coder2.5-7b

Description

This was an issue I had, but fixed it myself, problem is that your configuration file has a wrong model reference for ollama. The correct model name is qwen2.5-coder:7b, but your configuration file creates this: qwen-coder2.5:7b.
So what happened to me is that I got errors saying the model was not installed, but I saw that the model name in config.yaml was wrong.

To reproduce

Choose any model
Try to run it
Get model not installed error
Press install

Log output

notificationsAlerts.ts:42 Model "qwen-coder2.5-7b" is not found in Ollama. You need to install it.
c @ notificationsAlerts.ts:42
(anonymous) @ notificationsAlerts.ts:28
C @ event.ts:1219
D @ event.ts:1230
fire @ event.ts:1254
addNotification @ notifications.ts:228
notify @ notificationService.ts:234
(anonymous) @ mainThreadMessageService.ts:93
g @ mainThreadMessageService.ts:56
$showMessage @ mainThreadMessageService.ts:50
S @ rpcProtocol.ts:458
Q @ rpcProtocol.ts:443
M @ rpcProtocol.ts:373
L @ rpcProtocol.ts:299
(anonymous) @ rpcProtocol.ts:161
C @ event.ts:1219
fire @ event.ts:1250
fire @ ipc.net.ts:652
l.onmessage @ localProcessExtensionHost.ts:382
log.ts:460   ERR [Extension Host] Error handling webview message: {
  "msg": {
    "messageId": "8536ddd3-12bd-421b-be4b-3edd81757479",
    "messageType": "llm/streamChat",
    "data": {
      "completionOptions": {},
      "title": "Qwen 2.5 Coder 7b",
      "messages": [
        {
          "role": "system",
          "content": "<important_rules>\n  You are in chat mode.\n\n  If the user asks to make changes to files offer that they can use the Apply Button on the code block, or switch to Agent Mode to make the suggested updates automatically.\n  If needed concisely explain to the user they can switch to agent mode using the Mode Selector dropdown and provide no other details.\n\n  Always include the language and file name in the info string when you write code blocks.\n  If you are editing \"src/main.py\" for example, your code block should start with ' src/main.py'\n\n  When addressing code modification requests, present a concise code snippet that\n  emphasizes only the necessary changes and uses abbreviated placeholders for\n  unmodified sections. For example:\n\n   /path/to/file\n  // ... existing code ...\n\n  {{ modified code here }}\n\n  // ... existing code ...\n\n  {{ another modification }}\n\n  // ... rest of code ...\n  \n\n  In existing files, you should always restate the function or class that the snippet belongs to:\n\n   /path/to/file\n  // ... existing code ...\n\n  function exampleFunction() {\n    // ... existing code ...\n\n    {{ modified code here }}\n\n    // ... rest of function ...\n  }\n\n  // ... rest of code ...\n  \n\n  Since users have access to their complete file, they prefer reading only the\n  relevant modifications. It's perfectly acceptable to omit unmodified portions\n  at the beginning, middle, or end of files using these \"lazy\" comments. Only\n  provide the complete file when explicitly requested. Include a concise explanation\n  of changes unless the user specifically asks for code only.\n\n</important_rules>"
        },
        {
          "role": "user",
          "content": "hey"
        }
      ],
      "messageOptions": {
        "precompiled": true
      }
    }
  }
}

Error: The model "qwen-coder2.5-7b" was not found. To download it, run `ollama run qwen-coder2.5-7b`.
error @ log.ts:460
error @ log.ts:565
error @ logService.ts:51
Rds @ remoteConsoleUtil.ts:58
$logExtensionHostMessage @ mainThreadConsole.ts:38
S @ rpcProtocol.ts:458
Q @ rpcProtocol.ts:443
M @ rpcProtocol.ts:373
L @ rpcProtocol.ts:299
(anonymous) @ rpcProtocol.ts:161
C @ event.ts:1219
fire @ event.ts:1250
fire @ ipc.net.ts:652
l.onmessage @ localProcessExtensionHost.ts:382
console.ts:137 [Extension Host] Error handling webview message: {
  "msg": {
    "messageId": "8536ddd3-12bd-421b-be4b-3edd81757479",
    "messageType": "llm/streamChat",
    "data": {
      "completionOptions": {},
      "title": "Qwen 2.5 Coder 7b",
      "messages": [
        {
          "role": "system",
          "content": "<important_rules>\n  You are in chat mode.\n\n  If the user asks to make changes to files offer that they can use the Apply Button on the code block, or switch to Agent Mode to make the suggested updates automatically.\n  If needed concisely explain to the user they can switch to agent mode using the Mode Selector dropdown and provide no other details.\n\n  Always include the language and file name in the info string when you write code blocks.\n  If you are editing \"src/main.py\" for example, your code block should start with ' src/main.py'\n\n  When addressing code modification requests, present a concise code snippet that\n  emphasizes only the necessary changes and uses abbreviated placeholders for\n  unmodified sections. For example:\n\n   /path/to/file\n  // ... existing code ...\n\n  {{ modified code here }}\n\n  // ... existing code ...\n\n  {{ another modification }}\n\n  // ... rest of code ...\n  \n\n  In existing files, you should always restate the function or class that the snippet belongs to:\n\n   /path/to/file\n  // ... existing code ...\n\n  function exampleFunction() {\n    // ... existing code ...\n\n    {{ modified code here }}\n\n    // ... rest of function ...\n  }\n\n  // ... rest of code ...\n  \n\n  Since users have access to their complete file, they prefer reading only the\n  relevant modifications. It's perfectly acceptable to omit unmodified portions\n  at the beginning, middle, or end of files using these \"lazy\" comments. Only\n  provide the complete file when explicitly requested. Include a concise explanation\n  of changes unless the user specifically asks for code only.\n\n</important_rules>"
        },
        {
          "role": "user",
          "content": "hey"
        }
      ],
      "messageOptions": {
        "precompiled": true
      }
    }
  }
}

Error: The model "qwen-coder2.5-7b" was not found. To download it, run `ollama run qwen-coder2.5-7b`.