test(grok,llama): red phase for Grok (xAI) + Llama (multi-backend) (8 tests, 6 fail)

8 failing tests in 2 new files for the upcoming Grok and Llama
provider implementations.

Grok (tests/test_grok_provider.py, 2 tests):
1. test_send_grok_uses_xai_endpoint: _send_grok calls _ensure_grok_client
   and uses an xAI client (base_url https://api.x.ai/v1)
2. test_grok_2_vision_supports_image: structural check that the
   capability registry has vision=True for grok-2-vision (already
   populated in Phase 1, so this test passes in Red phase; it is a
   regression guard for the registry, not an implementation test)

Llama (tests/test_llama_provider.py, 6 tests):
1. test_send_llama_ollama_backend: _send_llama with localhost:11434
   (Ollama) base URL
2. test_send_llama_openrouter_backend: _send_llama with OpenRouter URL
3. test_send_llama_custom_url: _send_llama with custom URL
   (escape hatch for self-hosted)
4. test_llama_model_discovery_unions_ollama_and_openrouter: _list_llama_models
   returns the 8 models from the capability registry
5. test_llama_3_2_vision_vision_capability: structural check for
   llama-3.2-11b-vision-preview (passes in Red phase)
6. test_llama_local_backend_cost_tracking_false_for_ollama: the local-LLM
   signal -- when base_url is localhost, _get_llama_cost_tracking()
   returns False. This is the first test that exercises the local LLM
   support that the capability matrix was designed for.

Both _reset_grok_state and _reset_llama_state fixtures use hasattr() to
be no-ops when the state doesn't exist (Red phase).

Test signatures use the real 10-arg _send_minimax signature, NOT the
plan's 12-arg with enable_tools / rag_engine.

Red phase: 6/8 tests fail (4 AttributeError on missing _send_*,
2 ImportError on missing _list_*/_get_*). 2/8 pass (registry structural
checks).

Next: Green phase - implement _send_grok + _ensure_grok_client +
_send_llama + _ensure_llama_client + _list_llama_models +
_get_llama_cost_tracking in src/ai_client.py.

tests/test_grok_provider.py

@@ -0,0 +1,28 @@
+from unittest.mock import MagicMock, patch
+import pytest
+from src import ai_client
+
+@pytest.fixture(autouse=True)
+def _reset_grok_state():
+ if hasattr(ai_client, '_grok_client'):
+  ai_client._grok_client = None
+ if hasattr(ai_client, '_grok_history'):
+  ai_client._grok_history = []
+ yield
+
+def test_send_grok_uses_xai_endpoint(monkeypatch: pytest.MonkeyPatch) -> None:
+ ai_client.set_provider("grok", "grok-2")
+ mock_client = MagicMock()
+ mock_client.chat.completions.create.return_value = MagicMock(
+  choices=[MagicMock(message=MagicMock(content="hi from grok", tool_calls=[]))],
+  usage=MagicMock(prompt_tokens=10, completion_tokens=5),
+ )
+ with patch("src.ai_client._ensure_grok_client", return_value=mock_client):
+  result = ai_client._send_grok("system", "user", ".", None, "", False, None, None, None)
+  assert result == "hi from grok"
+  assert mock_client.chat.completions.create.called
+
+def test_grok_2_vision_supports_image() -> None:
+ from src.vendor_capabilities import get_capabilities
+ caps = get_capabilities("grok", "grok-2-vision")
+ assert caps.vision is True

tests/test_llama_provider.py

@@ -0,0 +1,68 @@
+from unittest.mock import MagicMock, patch
+import pytest
+from src import ai_client
+
+@pytest.fixture(autouse=True)
+def _reset_llama_state():
+ if hasattr(ai_client, '_llama_client'):
+  ai_client._llama_client = None
+ if hasattr(ai_client, '_llama_history'):
+  ai_client._llama_history = []
+ if hasattr(ai_client, '_llama_base_url'):
+  ai_client._llama_base_url = "http://localhost:11434/v1"
+ if hasattr(ai_client, '_llama_api_key'):
+  ai_client._llama_api_key = "ollama"
+ yield
+
+def test_send_llama_ollama_backend(monkeypatch: pytest.MonkeyPatch) -> None:
+ ai_client._llama_base_url = "http://localhost:11434/v1"
+ ai_client.set_provider("llama", "llama-3.2-3b-preview")
+ mock_client = MagicMock()
+ mock_client.chat.completions.create.return_value = MagicMock(
+  choices=[MagicMock(message=MagicMock(content="hi from ollama", tool_calls=[]))],
+  usage=MagicMock(prompt_tokens=5, completion_tokens=3),
+ )
+ with patch("src.ai_client._ensure_llama_client", return_value=mock_client):
+  result = ai_client._send_llama("system", "user", ".", None, "", False, None, None, None)
+  assert result == "hi from ollama"
+
+def test_send_llama_openrouter_backend(monkeypatch: pytest.MonkeyPatch) -> None:
+ ai_client._llama_base_url = "https://openrouter.ai/api/v1"
+ ai_client.set_provider("llama", "llama-3.1-70b-versatile")
+ captured_client = MagicMock()
+ captured_client.chat.completions.create.return_value = MagicMock(
+  choices=[MagicMock(message=MagicMock(content="hi from openrouter", tool_calls=[]))],
+  usage=MagicMock(prompt_tokens=5, completion_tokens=3),
+ )
+ with patch("src.ai_client._ensure_llama_client", return_value=captured_client) as ensure:
+  result = ai_client._send_llama("system", "user", ".", None, "", False, None, None, None)
+  assert result == "hi from openrouter"
+  assert ensure.called
+
+def test_send_llama_custom_url(monkeypatch: pytest.MonkeyPatch) -> None:
+ ai_client._llama_base_url = "http://my-server:9999/v1"
+ mock_client = MagicMock()
+ mock_client.chat.completions.create.return_value = MagicMock(
+  choices=[MagicMock(message=MagicMock(content="hi from custom", tool_calls=[]))],
+  usage=MagicMock(prompt_tokens=5, completion_tokens=3),
+ )
+ with patch("src.ai_client._ensure_llama_client", return_value=mock_client):
+  result = ai_client._send_llama("system", "user", ".", None, "", False, None, None, None)
+  assert result == "hi from custom"
+
+def test_llama_model_discovery_unions_ollama_and_openrouter() -> None:
+ from src.ai_client import _list_llama_models
+ models = _list_llama_models()
+ assert "llama-3.1-8b-instant" in models
+ assert "llama-3.2-11b-vision-preview" in models
+ assert "llama-3.3-70b-specdec" in models
+
+def test_llama_3_2_vision_vision_capability() -> None:
+ from src.vendor_capabilities import get_capabilities
+ caps = get_capabilities("llama", "llama-3.2-11b-vision-preview")
+ assert caps.vision is True
+
+def test_llama_local_backend_cost_tracking_false_for_ollama() -> None:
+ ai_client._llama_base_url = "http://localhost:11434/v1"
+ from src.ai_client import _get_llama_cost_tracking
+ assert _get_llama_cost_tracking() is False