VScode copilot: No lowest priority node found

I’ve found the vscode copilot error “No lowest priority node found” to be about a context overflow somewhere in the chain “inference engine” -> “LLM” -> copilot.

Some/all of the workarounds you can try when that happens:

• Reduce/disable agent tools
• Increase the input window in chatLanguageModels.json, eg.

{
	"id": "gemma-4-12b-it-qat-q4_0",
	"name": "gemma-4-12b-it-qat-q4_0",
	"url": "http://localhost:11434",
	"toolCalling": true,
	"vision": false,
	"maxInputTokens": 32768,	
	"maxOutputTokens": 32768
}

Of course, that will only work if the inference engine and model support larger windows.

• Configure the inference engine to use a larger input token window, eg. use the “-c 32768” llama-server parameter.
• Slightly different, but also works: num_ctx in ollama modelfiles.