fix: align Nous Portal model slugs with OpenRouter naming (#3253)

Nous Portal now passes through OpenRouter model names and routes from
there. Update the static fallback model list and auxiliary client default
to use OpenRouter-format slugs (provider/model) instead of bare names.

- _PROVIDER_MODELS['nous']: full OpenRouter catalog
- _NOUS_MODEL: google/gemini-3-flash-preview (was gemini-3-flash)
- Updated 4 test assertions for the new default model name

agent/auxiliary_client.py

@@ -82,7 +82,7 @@ auxiliary_is_nous: bool = False
 
 # Default auxiliary models per provider
 _OPENROUTER_MODEL = "google/gemini-3-flash-preview"
-_NOUS_MODEL = "gemini-3-flash"
+_NOUS_MODEL = "google/gemini-3-flash-preview"
 _NOUS_DEFAULT_BASE_URL = "https://inference-api.nousresearch.com/v1"
 _ANTHROPIC_DEFAULT_BASE_URL = "https://api.anthropic.com"
 _AUTH_JSON_PATH = get_hermes_home() / "auth.json"

hermes_cli/models.py

@@ -53,12 +53,29 @@ OPENROUTER_MODELS: list[tuple[str, str]] = [
 
 _PROVIDER_MODELS: dict[str, list[str]] = {
     "nous": [
-        "claude-opus-4-6",
-        "claude-sonnet-4-6",
-        "gpt-5.4",
-        "gemini-3-flash",
-        "gemini-3.0-pro-preview",
-        "deepseek-v3.2",
+        "anthropic/claude-opus-4.6",
+        "anthropic/claude-sonnet-4.5",
+        "anthropic/claude-haiku-4.5",
+        "openai/gpt-5.4",
+        "openai/gpt-5.4-mini",
+        "xiaomi/mimo-v2-pro",
+        "openai/gpt-5.3-codex",
+        "google/gemini-3-pro-preview",
+        "google/gemini-3-flash-preview",
+        "qwen/qwen3.5-plus-02-15",
+        "qwen/qwen3.5-35b-a3b",
+        "stepfun/step-3.5-flash",
+        "minimax/minimax-m2.7",
+        "minimax/minimax-m2.5",
+        "z-ai/glm-5",
+        "z-ai/glm-5-turbo",
+        "moonshotai/kimi-k2.5",
+        "x-ai/grok-4.20-beta",
+        "nvidia/nemotron-3-super-120b-a12b",
+        "nvidia/nemotron-3-super-120b-a12b:free",
+        "arcee-ai/trinity-large-preview:free",
+        "openai/gpt-5.4-pro",
+        "openai/gpt-5.4-nano",
     ],
     "openai-codex": [
         "gpt-5.3-codex",

tests/agent/test_auxiliary_client.py

@@ -461,7 +461,7 @@ class TestGetTextAuxiliaryClient:
              patch("agent.auxiliary_client.OpenAI") as mock_openai:
             mock_nous.return_value = {"access_token": "nous-tok"}
             client, model = get_text_auxiliary_client()
-        assert model == "gemini-3-flash"
+        assert model == "google/gemini-3-flash-preview"
 
     def test_custom_endpoint_over_codex(self, monkeypatch, codex_auth_dir):
         monkeypatch.setenv("OPENAI_BASE_URL", "http://localhost:1234/v1")
@@ -693,7 +693,7 @@ class TestVisionClientFallback:
              patch("agent.auxiliary_client.OpenAI"):
             mock_nous.return_value = {"access_token": "nous-tok"}
             client, model = get_vision_auxiliary_client()
-        assert model == "gemini-3-flash"
+        assert model == "google/gemini-3-flash-preview"
         assert client is not None
 
     def test_vision_forced_main_uses_custom_endpoint(self, monkeypatch):
@@ -789,7 +789,7 @@ class TestResolveForcedProvider:
              patch("agent.auxiliary_client.OpenAI"):
             mock_nous.return_value = {"access_token": "nous-tok"}
             client, model = _resolve_forced_provider("nous")
-        assert model == "gemini-3-flash"
+        assert model == "google/gemini-3-flash-preview"
         assert client is not None
 
     def test_forced_nous_not_configured(self, monkeypatch):

tests/test_provider_parity.py

@@ -556,7 +556,7 @@ class TestAuxiliaryClientProviderPriority:
         with patch("agent.auxiliary_client._read_nous_auth", return_value={"access_token": "nous-tok"}), \
              patch("agent.auxiliary_client.OpenAI") as mock:
             client, model = get_text_auxiliary_client()
-        assert model == "gemini-3-flash"
+        assert model == "google/gemini-3-flash-preview"
 
     def test_custom_endpoint_when_no_nous(self, monkeypatch):
         monkeypatch.delenv("OPENROUTER_API_KEY", raising=False)