129 lines
5.9 KiB
Python
129 lines
5.9 KiB
Python
"""Red tests for native Ollama adapter (_send_llama_native + ollama_chat).
|
|
|
|
When _llama_base_url points at localhost/127.0.0.1 (Ollama default), _send_llama
|
|
should route to a native adapter that POSTs to /api/chat (NOT the OpenAI-compat
|
|
/v1/chat/completions endpoint). The native adapter supports Ollama's vendor-
|
|
specific fields: think, images, thinking.
|
|
|
|
This file is t4_2 (red phase) of qwen_llama_grok_followup_20260611 Phase 4.
|
|
"""
|
|
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 _mock_requests_with(post_response: MagicMock):
|
|
"""Return a context manager that patches _require_warmed('requests') with a mock whose .post returns the given response."""
|
|
mock_requests = MagicMock()
|
|
mock_requests.post.return_value = post_response
|
|
return patch("src.ai_client._require_warmed", return_value=mock_requests)
|
|
|
|
def test_ollama_chat_posts_to_native_api_chat_endpoint() -> None:
|
|
"""ollama_chat hits /api/chat (not /v1/chat/completions) and returns parsed JSON."""
|
|
mock_response = MagicMock()
|
|
mock_response.json.return_value = {
|
|
"message": {"role": "assistant", "content": "ok"},
|
|
"done": True,
|
|
}
|
|
with _mock_requests_with(mock_response) as warm:
|
|
result = ai_client.ollama_chat(model="llama3.2:3b", messages=[{"role": "user", "content": "hi"}])
|
|
assert result["message"]["content"] == "ok"
|
|
post = warm.return_value.post
|
|
called_url = post.call_args.args[0]
|
|
assert called_url == "http://localhost:11434/api/chat"
|
|
payload = post.call_args.kwargs["json"]
|
|
assert payload["model"] == "llama3.2:3b"
|
|
assert payload["stream"] is False
|
|
assert payload["messages"] == [{"role": "user", "content": "hi"}]
|
|
|
|
def test_ollama_chat_includes_think_param_when_set() -> None:
|
|
"""Ollama native adapter should set the 'think' field in the payload."""
|
|
mock_response = MagicMock()
|
|
mock_response.json.return_value = {"message": {"content": "ok"}, "done": True}
|
|
with _mock_requests_with(mock_response) as warm:
|
|
ai_client.ollama_chat(model="qwen3:8b", messages=[{"role": "user", "content": "x"}], think="high")
|
|
payload = warm.return_value.post.call_args.kwargs["json"]
|
|
assert payload["think"] == "high"
|
|
|
|
def test_ollama_chat_includes_images_when_provided() -> None:
|
|
"""Ollama native adapter should include images in the payload (base64 strings)."""
|
|
mock_response = MagicMock()
|
|
mock_response.json.return_value = {"message": {"content": "i see a cat"}, "done": True}
|
|
with _mock_requests_with(mock_response) as warm:
|
|
ai_client.ollama_chat(
|
|
model="llama3.2-vision:11b",
|
|
messages=[{"role": "user", "content": "describe this"}],
|
|
images=["iVBOR..."],
|
|
)
|
|
payload = warm.return_value.post.call_args.kwargs["json"]
|
|
assert payload["images"] == ["iVBOR..."]
|
|
|
|
def test_send_llama_native_calls_ollama_chat_when_localhost() -> None:
|
|
"""_send_llama_native wraps ollama_chat and returns the message content."""
|
|
ai_client.set_provider("llama", "llama-3.2-3b-preview")
|
|
ai_client._llama_base_url = "http://localhost:11434/v1"
|
|
mock_response = MagicMock()
|
|
mock_response.json.return_value = {
|
|
"message": {"role": "assistant", "content": "hi from native ollama"},
|
|
"done": True,
|
|
}
|
|
with _mock_requests_with(mock_response):
|
|
result = ai_client._send_llama_native("system", "user", ".", None, "", False, None, None, None)
|
|
assert result.ok and "hi from native ollama" in result.data
|
|
|
|
def test_send_llama_native_preserves_thinking_field() -> None:
|
|
"""Ollama's 'thinking' field should be captured and rendered in the output."""
|
|
ai_client.set_provider("llama", "qwen3:8b")
|
|
ai_client._llama_base_url = "http://localhost:11434/v1"
|
|
mock_response = MagicMock()
|
|
mock_response.json.return_value = {
|
|
"message": {"role": "assistant", "content": "answer", "thinking": "I thought about it"},
|
|
"done": True,
|
|
}
|
|
with _mock_requests_with(mock_response):
|
|
result = ai_client._send_llama_native("system", "user", ".", None, "", False, None, None, None)
|
|
assert result.ok and "I thought about it" in result.data
|
|
assert "answer" in result.data
|
|
|
|
def test_send_llama_routes_to_native_when_localhost() -> None:
|
|
"""The dispatcher in _send_llama must route localhost/127.0.0.1 to _send_llama_native."""
|
|
ai_client.set_provider("llama", "llama-3.2-3b-preview")
|
|
ai_client._llama_base_url = "http://localhost:11434/v1"
|
|
mock_response = MagicMock()
|
|
mock_response.json.return_value = {
|
|
"message": {"role": "assistant", "content": "via native"},
|
|
"done": True,
|
|
}
|
|
with _mock_requests_with(mock_response), \
|
|
patch("src.ai_client._ensure_llama_client") as ensure:
|
|
result = ai_client._send_llama("system", "user", ".", None, "", False, None, None, None)
|
|
assert result.ok and "via native" in result.data
|
|
assert not ensure.called, "_send_llama should NOT instantiate the openai client for native backend"
|
|
|
|
def test_send_llama_keeps_openai_path_for_non_local() -> None:
|
|
"""_send_llama must NOT route to native for non-localhost URLs (custom server, OpenRouter)."""
|
|
ai_client.set_provider("llama", "llama-3.1-70b-versatile")
|
|
ai_client._llama_base_url = "https://openrouter.ai/api/v1"
|
|
mock_client = MagicMock()
|
|
mock_client.chat.completions.create.return_value = MagicMock(
|
|
choices=[MagicMock(message=MagicMock(content="via openrouter", tool_calls=[]))],
|
|
usage=MagicMock(prompt_tokens=5, completion_tokens=3),
|
|
)
|
|
with patch("src.ai_client._ensure_llama_client", return_value=mock_client) as ensure, \
|
|
_mock_requests_with(MagicMock(json=MagicMock(return_value={}))) as warm:
|
|
result = ai_client._send_llama("system", "user", ".", None, "", False, None, None, None)
|
|
assert result.ok and "via openrouter" in result.data
|
|
assert ensure.called
|
|
assert not warm.return_value.post.called, "non-local backend must NOT hit Ollama's /api/chat"
|