From c1af61428953a4b97d986bc36108df18603a324b Mon Sep 17 00:00:00 2001
From: hermes-agent-dhabibi
 <274096618+hermes-agent-dhabibi@users.noreply.github.com>
Date: Fri, 10 Apr 2026 04:35:07 +0000
Subject: [PATCH] fix: wrap copilot Responses-API models in
 CodexAuxiliaryClient for auxiliary tasks

GPT-5+ models (except gpt-5-mini) are only accessible via the Responses
API on Copilot. When these models were configured as the compression
summary_model (or any auxiliary task), the plain OpenAI client sent them
to /chat/completions which returned a 400 error:

    model "gpt-5.4-mini" is not accessible via the /chat/completions endpoint

resolve_provider_client() now checks _should_use_copilot_responses_api()
for the copilot provider and wraps the client in CodexAuxiliaryClient
when needed, routing calls through responses.stream() transparently.

Adds tests for both the wrapping (gpt-5.4-mini) and non-wrapping
(gpt-4.1-mini) paths.
---
 agent/auxiliary_client.py            | 17 ++++++++
 tests/agent/test_auxiliary_client.py | 63 ++++++++++++++++++++++++++++
 2 files changed, 80 insertions(+)

diff --git a/agent/auxiliary_client.py b/agent/auxiliary_client.py
index d21b96240..104162cfe 100644
--- a/agent/auxiliary_client.py
+++ b/agent/auxiliary_client.py
@@ -1425,6 +1425,23 @@ def resolve_provider_client(
 
         client = OpenAI(api_key=api_key, base_url=base_url,
                         **({"default_headers": headers} if headers else {}))
+
+        # Copilot GPT-5+ models (except gpt-5-mini) require the Responses
+        # API — they are not accessible via /chat/completions.  Wrap the
+        # plain client in CodexAuxiliaryClient so call_llm() transparently
+        # routes through responses.stream().
+        if provider == "copilot" and final_model and not raw_codex:
+            try:
+                from hermes_cli.models import _should_use_copilot_responses_api
+                if _should_use_copilot_responses_api(final_model):
+                    logger.debug(
+                        "resolve_provider_client: copilot model %s needs "
+                        "Responses API — wrapping with CodexAuxiliaryClient",
+                        final_model)
+                    client = CodexAuxiliaryClient(client, final_model)
+            except ImportError:
+                pass
+
         logger.debug("resolve_provider_client: %s (%s)", provider, final_model)
         return (_to_async_client(client, final_model) if async_mode
                 else (client, final_model))
diff --git a/tests/agent/test_auxiliary_client.py b/tests/agent/test_auxiliary_client.py
index 7038582ff..9a376d674 100644
--- a/tests/agent/test_auxiliary_client.py
+++ b/tests/agent/test_auxiliary_client.py
@@ -756,6 +756,69 @@ class TestAuxiliaryPoolAwareness:
         assert call_kwargs["base_url"] == "https://api.githubcopilot.com"
         assert call_kwargs["default_headers"]["Editor-Version"]
 
+    def test_copilot_responses_api_model_wrapped_in_codex_client(self, monkeypatch):
+        """Copilot GPT-5+ models (needing Responses API) are wrapped in CodexAuxiliaryClient."""
+        monkeypatch.delenv("GITHUB_TOKEN", raising=False)
+        monkeypatch.delenv("GH_TOKEN", raising=False)
+
+        with (
+            patch(
+                "hermes_cli.auth.resolve_api_key_provider_credentials",
+                return_value={
+                    "provider": "copilot",
+                    "api_key": "test-token",
+                    "base_url": "https://api.githubcopilot.com",
+                    "source": "gh auth token",
+                },
+            ),
+            patch("agent.auxiliary_client.OpenAI"),
+        ):
+            client, model = resolve_provider_client("copilot", model="gpt-5.4-mini")
+
+        from agent.auxiliary_client import CodexAuxiliaryClient
+        assert isinstance(client, CodexAuxiliaryClient)
+        assert model == "gpt-5.4-mini"
+
+    def test_copilot_chat_completions_model_not_wrapped(self, monkeypatch):
+        """Copilot models using Chat Completions are returned as plain OpenAI clients."""
+        monkeypatch.delenv("GITHUB_TOKEN", raising=False)
+        monkeypatch.delenv("GH_TOKEN", raising=False)
+
+        with (
+            patch(
+                "hermes_cli.auth.resolve_api_key_provider_credentials",
+                return_value={
+                    "provider": "copilot",
+                    "api_key": "test-token",
+                    "base_url": "https://api.githubcopilot.com",
+                    "source": "gh auth token",
+                },
+            ),
+            patch("agent.auxiliary_client.OpenAI") as mock_openai,
+        ):
+            client, model = resolve_provider_client("copilot", model="gpt-4.1-mini")
+
+        from agent.auxiliary_client import CodexAuxiliaryClient
+        assert not isinstance(client, CodexAuxiliaryClient)
+        assert model == "gpt-4.1-mini"
+        # Should be the raw mock OpenAI client
+        assert client is mock_openai.return_value
+
+    def test_vision_auto_uses_active_provider_as_fallback(self, monkeypatch):
+        """When no OpenRouter/Nous available, vision auto falls back to active provider."""
+        monkeypatch.setenv("ANTHROPIC_API_KEY", "***")
+        with (
+            patch("agent.auxiliary_client._read_nous_auth", return_value=None),
+            patch("agent.auxiliary_client._read_main_provider", return_value="anthropic"),
+            patch("agent.auxiliary_client._read_main_model", return_value="claude-sonnet-4"),
+            patch("agent.anthropic_adapter.build_anthropic_client", return_value=MagicMock()),
+            patch("agent.anthropic_adapter.resolve_anthropic_token", return_value="***"),
+        ):
+            client, model = get_vision_auxiliary_client()
+
+        assert client is not None
+        assert client.__class__.__name__ == "AnthropicAuxiliaryClient"
+
     def test_vision_auto_prefers_active_provider_over_openrouter(self, monkeypatch):
         """Active provider is tried before OpenRouter in vision auto."""
         monkeypatch.setenv("OPENROUTER_API_KEY", "or-key")