Updated based on code review

Author: hideyukikodama

packages/jupyter-ai-magics/jupyter_ai_magics/partner_providers/copilot.py

@@ -124,7 +124,7 @@ def _llm_type(self) -> str:
 class GitHubCopilotProvider(BaseProvider):
     id = "github-copilot"
     name = "GitHub Copilot"
-    models = ["*"]
+    models = ["default"]
     model_id_key = "model"
     pypi_package_deps = ["pylspclient"]
     help = (
@@ -143,6 +143,22 @@ def __init__(
     ):
         super().__init__(**kwargs)
         self._llm = GitHubCopilotLLM(lsp_bin_path=self.lsp_bin_path)
+        
+    @classmethod
+    def chat_models(self):
+        """
+        Empty list because Copilot LSP does not support the chat feature
+        https://github.com/github/copilot-language-server-release/issues/1
+        """
+        return []
+
+    @classmethod
+    def completion_models(self):
+        """
+        Only `default` (GPT-4o as of May 2025) because Copilot LSP does not support different model selection
+        https://docs.github.com/en/copilot/using-github-copilot/ai-models/changing-the-ai-model-for-copilot-code-completion
+        """
+        return ["default"]
 
     async def generate_inline_completions(self, request: InlineCompletionRequest):
         self._llm.ensure_lsp_server_initialized()

packages/jupyter-ai/jupyter_ai/chat_handlers/__init__.py

@@ -1,6 +1,5 @@
 from .ask import AskChatHandler
 from .base import BaseChatHandler, SlashCommandRoutingType
-from .copilot import GitHubCopilotChatHandler
 from .default import DefaultChatHandler
 from .generate import GenerateChatHandler
 from .help import HelpChatHandler

packages/jupyter-ai/jupyter_ai/chat_handlers/copilot.py

@@ -51,7 +51,6 @@ ask = "jupyter_ai.chat_handlers.ask:AskChatHandler"
 generate = "jupyter_ai.chat_handlers.generate:GenerateChatHandler"
 learn = "jupyter_ai.chat_handlers.learn:LearnChatHandler"
 help = "jupyter_ai.chat_handlers.help:HelpChatHandler"
-github = "jupyter_ai.chat_handlers.copilot:GitHubCopilotChatHandler"
 
 [project.optional-dependencies]
 test = [