docs(vscode-lm): clarify VS Code LM API integration blurb, provider wording, and error guidance

Author: hannesrudolph

src/package.nls.json

@@ -33,7 +33,7 @@
 	"commands.commandExecutionTimeout.description": "Maximum time in seconds to wait for command execution to complete before timing out (0 = no timeout, 1-600s, default: 0s)",
 	"commands.commandTimeoutAllowlist.description": "Command prefixes that are excluded from the command execution timeout. Commands matching these prefixes will run without timeout restrictions.",
 	"commands.preventCompletionWithOpenTodos.description": "Prevent task completion when there are incomplete todos in the todo list",
-	"settings.vsCodeLmModelSelector.description": "Settings for VSCode Language Model API",
+	"settings.vsCodeLmModelSelector.description": "VS Code Language Model API integration. Important: Models accessed via VS Code may be wrapped or fine‑tuned by the provider, so behavior can differ from using the same model directly from a typical provider or router.\n\nTo use a model from the Language Model dropdown, first switch to that model and then click Accept in the Copilot Chat prompt; otherwise you may see an error such as 400 \"The requested model is not supported\".",
 	"settings.vsCodeLmModelSelector.vendor.description": "The vendor of the language model (e.g. copilot)",
 	"settings.vsCodeLmModelSelector.family.description": "The family of the language model (e.g. gpt-4)",
 	"settings.customStoragePath.description": "Custom storage path. Leave empty to use the default location. Supports absolute paths (e.g. 'D:\\RooCodeStorage')",