diff --git a/nanobot/providers/openai_compat_provider.py b/nanobot/providers/openai_compat_provider.py
index 4f726df2..d9eb64dd 100644
--- a/nanobot/providers/openai_compat_provider.py
+++ b/nanobot/providers/openai_compat_provider.py
@@ -446,10 +446,11 @@ class OpenAICompatProvider(LLMProvider):
         reasoning_effort: str | None,
     ) -> bool:
         """Use Responses API only for direct OpenAI requests that benefit from it."""
-        if self._spec and self._spec.name != "openai":
-            return False
-        if not _is_direct_openai_base(self._effective_base):
+        if self._spec and self._spec.name not in ("openai", "github_copilot"):
             return False
+        if self._spec is None or self._spec.name != "github_copilot":
+            if not _is_direct_openai_base(self._effective_base):
+                return False
 
         model_name = (model or self.default_model).lower()
         wants = False
@@ -527,6 +528,8 @@ class OpenAICompatProvider(LLMProvider):
     ) -> dict[str, Any]:
         """Build a Responses API body for direct OpenAI requests."""
         model_name = model or self.default_model
+        if self._spec and self._spec.strip_model_prefix:
+            model_name = model_name.split("/")[-1]
         sanitized_messages = self._sanitize_messages(self._sanitize_empty_content(messages))
         instructions, input_items = convert_messages(sanitized_messages)
 
@@ -987,6 +990,11 @@ class OpenAICompatProvider(LLMProvider):
                     self._record_responses_success(model, reasoning_effort)
                     return result
                 except Exception as responses_error:
+                    if self._spec and self._spec.name == "github_copilot":
+                        # Copilot gateway exposes GPT-5/o-series only via /responses;
+                        # falling back to /chat/completions cannot succeed and would
+                        # hide the real error.
+                        raise
                     if not self._should_fallback_from_responses_error(responses_error):
                         raise
                     self._record_responses_failure(model, reasoning_effort)
@@ -1045,6 +1053,11 @@ class OpenAICompatProvider(LLMProvider):
                         reasoning_content=reasoning_content,
                     )
                 except Exception as responses_error:
+                    if self._spec and self._spec.name == "github_copilot":
+                        # Copilot gateway exposes GPT-5/o-series only via /responses;
+                        # falling back to /chat/completions cannot succeed and would
+                        # hide the real error.
+                        raise
                     if not self._should_fallback_from_responses_error(responses_error):
                         raise
                     self._record_responses_failure(model, reasoning_effort)
diff --git a/nanobot/providers/registry.py b/nanobot/providers/registry.py
index 05237338..f633cc83 100644
--- a/nanobot/providers/registry.py
+++ b/nanobot/providers/registry.py
@@ -223,6 +223,7 @@ PROVIDERS: tuple[ProviderSpec, ...] = (
         default_api_base="https://api.githubcopilot.com",
         strip_model_prefix=True,
         is_oauth=True,
+        supports_max_completion_tokens=True,
     ),
     # DeepSeek: OpenAI-compatible at api.deepseek.com
     ProviderSpec(
diff --git a/tests/cli/test_commands.py b/tests/cli/test_commands.py
index 0344af23..2719beed 100644
--- a/tests/cli/test_commands.py
+++ b/tests/cli/test_commands.py
@@ -421,13 +421,13 @@ async def test_github_copilot_provider_refreshes_client_api_key_before_chat():
     })
 
     with patch("nanobot.providers.openai_compat_provider.AsyncOpenAI", return_value=mock_client):
-        provider = GitHubCopilotProvider(default_model="github-copilot/gpt-5.1")
+        provider = GitHubCopilotProvider(default_model="github-copilot/gpt-4")
 
     provider._get_copilot_access_token = AsyncMock(return_value="copilot-access-token")
 
     response = await provider.chat(
         messages=[{"role": "user", "content": "hi"}],
-        model="github-copilot/gpt-5.1",
+        model="github-copilot/gpt-4",
         max_tokens=16,
         temperature=0.1,
     )