llama.cpp - You must either implement templateMessages or _streamChat

[standas]

Starting with a fresh install of Continue extension in VS Code. Coming back to using Continue and I am migrating from my previously working config.json to config.yaml.

Erased ~/.continue before performing fresh plugin install.
Continue Plugin Version: 1.2.10

I have llama swap confirmed working at 10.0.2.22:8080 (running and tested with OpenWebUI), wanted to test an initial model before making updates and modified the config.yaml as following:

name: Local Config
version: 1.0.0
schema: v1
models:
  - name: gpt-oss-20b
    provider: llama.cpp
    model: gpt-oss-20b-q8
    apiBase: http://10.0.2.22:8080
    apiKey: 'XXX'

Receiving this error:

You must either implement templateMessages or _streamChat

I tried different models and '/v1/' endpoints appended to the apiBase, as well as the old workaround for using Ollama as the provider, but am still getting the error.

Here is the log:

console.ts:137 [Extension Host] Error handling webview message: {
"msg": {
"messageId": "dbb9af6e-0171-41e4-b6ca-8f53b44c4121",
"messageType": "llm/streamChat",
"data": {
"completionOptions": {
"reasoning": false
},
"title": "gpt-oss-20b",
"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 'python 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 language /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 language /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": "Hi"
}
],
"messageOptions": {
"precompiled": true
}
}
}
}

localProcessExtensionHost.ts:280 Extension Host
localProcessExtensionHost.ts:281 [@continuedev] error: You must either implement templateMessages or _streamChat {"context":"llm_stream_chat","model":"gpt-oss-20b-q8","provider":"llama.cpp","useOpenAIAdapter":false,"streamEnabled":true,"templateMessages":false}

Am I missing a config.yaml parameter or is there some other item?

Thanks in advance for your help!

[standas]

Found this link which recommended switching provider to openai:

#8601

Updated yaml which works is now (note adding v1 to apiBase):

name: Local Config
version: 1.0.0
schema: v1
models:
  - name: gpt-oss-20b
    provider: openai
    model: gpt-oss-20b-q8
    apiBase: http://10.0.2.22:8080/v1/
    apiKey: 'XXXX'