⏩ Continue is the leading open-source AI code assistant. You can connect any models and any context to build custom autocomplete and chat experiences inside VS Code and JetBrains
According to my needs, I want to add a model drop-down box option of my own (just UI requirements, not local models), so I add model configuration in the continue\extensions.continue-debug\config.json file as follows:
"models": [
{
"model": "my-test-model",
"title": "My Test Model",
"systemMessage": "this is my test model.",
"apiKey": "test",
"provider": "test-model"
},
{
"model": "gpt-4o-mini",
"title": "GPT-4o Mini",
"systemMessage": "You are an expert software developer. You give helpful and concise responses.",
"apiKey": "test",
"provider": "openai"
}
],
For the provider configuration, it once prompted me that I could not set "test-model", so I added "test-model" to the ModelDescription.properties.provider.enum array in the extensions\vscode\config_schema.json file, so that the config.json file allowed me to set "provider": "test-model"
But I can still only see the "GPT-4o Mini" option in the model selection drop-down box in the extended UI, and I can't see the "My Test Model" option I added. But I tried to set the provider value of my newly added "My Test Model" to openai, and I can see that the "My Test Model" option appears in the model drop-down box in the UI. So it seems that the incorrect setting of "provider": "test-model" caused my "My Test Model" to not be loaded correctly in the UI. I would like to ask you why this is the case. If I want to set the provider of my own custom model to a custom value, what should I modify?
Before submitting your bug report
Relevant environment info
Description
According to my needs, I want to add a model drop-down box option of my own (just UI requirements, not local models), so I add model configuration in the continue\extensions.continue-debug\config.json file as follows: "models": [ { "model": "my-test-model", "title": "My Test Model", "systemMessage": "this is my test model.", "apiKey": "test", "provider": "test-model" }, { "model": "gpt-4o-mini", "title": "GPT-4o Mini", "systemMessage": "You are an expert software developer. You give helpful and concise responses.", "apiKey": "test", "provider": "openai" } ], For the provider configuration, it once prompted me that I could not set "test-model", so I added "test-model" to the ModelDescription.properties.provider.enum array in the extensions\vscode\config_schema.json file, so that the config.json file allowed me to set "provider": "test-model"
But I can still only see the "GPT-4o Mini" option in the model selection drop-down box in the extended UI, and I can't see the "My Test Model" option I added. But I tried to set the provider value of my newly added "My Test Model" to openai, and I can see that the "My Test Model" option appears in the model drop-down box in the UI. So it seems that the incorrect setting of "provider": "test-model" caused my "My Test Model" to not be loaded correctly in the UI. I would like to ask you why this is the case. If I want to set the provider of my own custom model to a custom value, what should I modify?
To reproduce
No response
Log output
No response