refactor: remove Ollama integration and unused AI configuration
- Remove src/models/ollama_client.py, embeddings.py, embeddings_ollama.py - Remove model aliases and AI config from settings (both config.py files) - Update health endpoints to only check database connectivity - Update tests to reflect database-only health checks - Update README, .env.example, and OIDC docstrings 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
Jeroen Schweitzer
co-authored by
Claude Opus 4.5
Claude Opus 4.5
parent
4df5cfc106
commit
c1f16d44e5
+19
-87
@@ -80,24 +80,24 @@ class TestFullHealthCheck:
|
||||
"""Test /health/full endpoint."""
|
||||
|
||||
@patch("src.shared.database.Database.health_check")
|
||||
@patch("src.models.ollama_client.get_ollama_client")
|
||||
def test_full_health_returns_503_when_unhealthy(self, mock_get_ollama, mock_db_health, client):
|
||||
"""Full health should return 503 when Ollama unhealthy."""
|
||||
mock_client = AsyncMock()
|
||||
mock_client.health_check.return_value = False
|
||||
mock_get_ollama.return_value = mock_client
|
||||
def test_full_health_returns_200_when_healthy(self, mock_db_health, client):
|
||||
"""Full health should return 200 when database is healthy."""
|
||||
mock_db_health.return_value = True
|
||||
|
||||
response = client.get("/health/full")
|
||||
assert response.status_code == 200
|
||||
|
||||
@patch("src.shared.database.Database.health_check")
|
||||
def test_full_health_returns_503_when_unhealthy(self, mock_db_health, client):
|
||||
"""Full health should return 503 when database is unhealthy."""
|
||||
mock_db_health.return_value = False
|
||||
|
||||
response = client.get("/health/full")
|
||||
assert response.status_code == 503
|
||||
|
||||
@patch("src.shared.database.Database.health_check")
|
||||
@patch("src.models.ollama_client.get_ollama_client")
|
||||
def test_full_health_returns_components_status(self, mock_get_ollama, mock_db_health, client):
|
||||
def test_full_health_returns_components_status(self, mock_db_health, client):
|
||||
"""Full health should return component status."""
|
||||
mock_client = AsyncMock()
|
||||
mock_client.health_check.return_value = False
|
||||
mock_get_ollama.return_value = mock_client
|
||||
mock_db_health.return_value = True
|
||||
|
||||
response = client.get("/health/full")
|
||||
@@ -105,63 +105,32 @@ class TestFullHealthCheck:
|
||||
|
||||
assert "status" in data
|
||||
assert "components" in data
|
||||
assert "ollama" in data["components"]
|
||||
assert "database" in data["components"]
|
||||
assert "response_time_ms" in data
|
||||
|
||||
@patch("src.shared.database.Database.health_check")
|
||||
@patch("src.models.ollama_client.get_ollama_client")
|
||||
def test_full_health_handles_list_models_error(self, mock_get_ollama, mock_db_health, client):
|
||||
"""Full health should handle list_models errors."""
|
||||
mock_client = AsyncMock()
|
||||
mock_client.health_check.return_value = True
|
||||
mock_client.list_models.side_effect = Exception("Connection error")
|
||||
mock_get_ollama.return_value = mock_client
|
||||
mock_db_health.return_value = True
|
||||
def test_full_health_handles_database_error(self, mock_db_health, client):
|
||||
"""Full health should handle database errors gracefully."""
|
||||
mock_db_health.side_effect = Exception("Connection error")
|
||||
|
||||
response = client.get("/health/full")
|
||||
data = response.json()
|
||||
|
||||
# Should report error in component status
|
||||
assert "ollama" in data["components"]
|
||||
|
||||
@patch("src.shared.database.Database.health_check")
|
||||
@patch("src.models.ollama_client.get_ollama_client")
|
||||
def test_full_health_handles_health_check_exception(self, mock_get_ollama, mock_db_health, client):
|
||||
"""Full health should handle health check exceptions gracefully."""
|
||||
mock_client = AsyncMock()
|
||||
# Return False instead of raising exception to test unhealthy path
|
||||
mock_client.health_check.return_value = False
|
||||
mock_get_ollama.return_value = mock_client
|
||||
mock_db_health.return_value = True
|
||||
|
||||
response = client.get("/health/full")
|
||||
# Should return 503 for unhealthy
|
||||
assert response.status_code == 503
|
||||
data = response.json()
|
||||
assert data["status"] == "unhealthy"
|
||||
assert "error" in data["components"]["database"]
|
||||
|
||||
|
||||
class TestDiagnosticsEndpoint:
|
||||
"""Test /health/diagnostics endpoint."""
|
||||
|
||||
@patch("src.models.ollama_client.get_ollama_client")
|
||||
def test_diagnostics_returns_200(self, mock_get_ollama, client):
|
||||
def test_diagnostics_returns_200(self, client):
|
||||
"""Diagnostics should return 200."""
|
||||
mock_client = AsyncMock()
|
||||
mock_client.health_check.return_value = True
|
||||
mock_get_ollama.return_value = mock_client
|
||||
|
||||
response = client.get("/health/diagnostics")
|
||||
assert response.status_code == 200
|
||||
|
||||
@patch("src.models.ollama_client.get_ollama_client")
|
||||
def test_diagnostics_returns_service_info(self, mock_get_ollama, client):
|
||||
def test_diagnostics_returns_service_info(self, client):
|
||||
"""Diagnostics should return service information."""
|
||||
mock_client = AsyncMock()
|
||||
mock_client.health_check.return_value = True
|
||||
mock_get_ollama.return_value = mock_client
|
||||
|
||||
response = client.get("/health/diagnostics")
|
||||
data = response.json()
|
||||
|
||||
@@ -169,54 +138,17 @@ class TestDiagnosticsEndpoint:
|
||||
assert "name" in data["service"]
|
||||
assert "version" in data["service"]
|
||||
|
||||
@patch("src.models.ollama_client.get_ollama_client")
|
||||
def test_diagnostics_returns_components(self, mock_get_ollama, client):
|
||||
"""Diagnostics should return component details."""
|
||||
mock_client = AsyncMock()
|
||||
mock_client.health_check.return_value = True
|
||||
mock_get_ollama.return_value = mock_client
|
||||
|
||||
response = client.get("/health/diagnostics")
|
||||
data = response.json()
|
||||
|
||||
assert "components" in data
|
||||
assert "ollama" in data["components"]
|
||||
|
||||
@patch("src.models.ollama_client.get_ollama_client")
|
||||
def test_diagnostics_returns_configuration(self, mock_get_ollama, client):
|
||||
def test_diagnostics_returns_configuration(self, client):
|
||||
"""Diagnostics should return configuration info."""
|
||||
mock_client = AsyncMock()
|
||||
mock_client.health_check.return_value = True
|
||||
mock_get_ollama.return_value = mock_client
|
||||
|
||||
response = client.get("/health/diagnostics")
|
||||
data = response.json()
|
||||
|
||||
assert "configuration" in data
|
||||
|
||||
@patch("src.models.ollama_client.get_ollama_client")
|
||||
def test_diagnostics_returns_response_time(self, mock_get_ollama, client):
|
||||
def test_diagnostics_returns_response_time(self, client):
|
||||
"""Diagnostics should return response time."""
|
||||
mock_client = AsyncMock()
|
||||
mock_client.health_check.return_value = True
|
||||
mock_get_ollama.return_value = mock_client
|
||||
|
||||
response = client.get("/health/diagnostics")
|
||||
data = response.json()
|
||||
|
||||
assert "response_time_ms" in data
|
||||
assert isinstance(data["response_time_ms"], int)
|
||||
|
||||
@patch("src.models.ollama_client.get_ollama_client")
|
||||
def test_diagnostics_handles_ollama_error(self, mock_get_ollama, client):
|
||||
"""Diagnostics should handle Ollama connection errors."""
|
||||
mock_client = AsyncMock()
|
||||
mock_client.health_check.side_effect = Exception("Connection refused")
|
||||
mock_get_ollama.return_value = mock_client
|
||||
|
||||
response = client.get("/health/diagnostics")
|
||||
data = response.json()
|
||||
|
||||
# Should still return 200 with error info
|
||||
assert response.status_code == 200
|
||||
assert "error" in data["components"]["ollama"]
|
||||
|
||||
@@ -1,307 +0,0 @@
|
||||
"""Tests for Ollama client."""
|
||||
import pytest
|
||||
from unittest.mock import patch, AsyncMock, MagicMock
|
||||
import json
|
||||
|
||||
from src.models.ollama_client import OllamaClient, get_ollama_client, close_ollama_client
|
||||
|
||||
|
||||
class TestOllamaClientInit:
|
||||
"""Test OllamaClient initialization."""
|
||||
|
||||
@patch("src.models.ollama_client.settings")
|
||||
def test_uses_settings_defaults(self, mock_settings):
|
||||
"""Client should use settings for defaults."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 60
|
||||
|
||||
client = OllamaClient()
|
||||
|
||||
assert client.base_url == "http://ollama:11434"
|
||||
assert client.timeout == 60
|
||||
|
||||
@patch("src.models.ollama_client.settings")
|
||||
def test_creates_http_client(self, mock_settings):
|
||||
"""Client should create httpx AsyncClient."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
|
||||
client = OllamaClient()
|
||||
|
||||
assert client.client is not None
|
||||
|
||||
|
||||
class TestOllamaClientClose:
|
||||
"""Test client close functionality."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("src.models.ollama_client.settings")
|
||||
async def test_close_closes_client(self, mock_settings):
|
||||
"""close should close the HTTP client."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
|
||||
client = OllamaClient()
|
||||
|
||||
with patch.object(client.client, "aclose", new_callable=AsyncMock) as mock_close:
|
||||
await client.close()
|
||||
mock_close.assert_called_once()
|
||||
|
||||
|
||||
class TestOllamaClientResolveModel:
|
||||
"""Test model resolution."""
|
||||
|
||||
@patch("src.models.ollama_client.settings")
|
||||
def test_resolves_aliased_model(self, mock_settings):
|
||||
"""resolve_model should map alias to actual model."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
mock_settings.model_aliases = {"gpt-3.5-turbo": "gemma:7b"}
|
||||
|
||||
client = OllamaClient()
|
||||
result = client.resolve_model("gpt-3.5-turbo")
|
||||
|
||||
assert result == "gemma:7b"
|
||||
|
||||
@patch("src.models.ollama_client.settings")
|
||||
def test_returns_original_if_no_alias(self, mock_settings):
|
||||
"""resolve_model should return original if no alias found."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
mock_settings.model_aliases = {}
|
||||
|
||||
client = OllamaClient()
|
||||
result = client.resolve_model("llama2")
|
||||
|
||||
assert result == "llama2"
|
||||
|
||||
|
||||
class TestOllamaClientHealthCheck:
|
||||
"""Test health check functionality."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("src.models.ollama_client.settings")
|
||||
async def test_health_check_returns_true_on_200(self, mock_settings):
|
||||
"""Health check should return True when Ollama responds 200."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
|
||||
client = OllamaClient()
|
||||
|
||||
mock_response = MagicMock()
|
||||
mock_response.status_code = 200
|
||||
|
||||
with patch.object(client.client, "get", new_callable=AsyncMock) as mock_get:
|
||||
mock_get.return_value = mock_response
|
||||
result = await client.health_check()
|
||||
|
||||
assert result is True
|
||||
mock_get.assert_called_once()
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("src.models.ollama_client.settings")
|
||||
async def test_health_check_returns_false_on_error(self, mock_settings):
|
||||
"""Health check should return False on connection error."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
|
||||
client = OllamaClient()
|
||||
|
||||
with patch.object(client.client, "get", new_callable=AsyncMock) as mock_get:
|
||||
mock_get.side_effect = Exception("Connection refused")
|
||||
result = await client.health_check()
|
||||
|
||||
assert result is False
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("src.models.ollama_client.settings")
|
||||
async def test_health_check_returns_false_on_non_200(self, mock_settings):
|
||||
"""Health check should return False on non-200 status."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
|
||||
client = OllamaClient()
|
||||
|
||||
mock_response = MagicMock()
|
||||
mock_response.status_code = 500
|
||||
|
||||
with patch.object(client.client, "get", new_callable=AsyncMock) as mock_get:
|
||||
mock_get.return_value = mock_response
|
||||
result = await client.health_check()
|
||||
|
||||
assert result is False
|
||||
|
||||
|
||||
class TestOllamaClientListModels:
|
||||
"""Test list models functionality."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("src.models.ollama_client.settings")
|
||||
async def test_list_models_returns_dict(self, mock_settings):
|
||||
"""list_models should return dict with models."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
|
||||
client = OllamaClient()
|
||||
|
||||
models_data = {
|
||||
"models": [
|
||||
{"name": "llama2", "size": 1000000},
|
||||
{"name": "gemma:7b", "size": 2000000}
|
||||
]
|
||||
}
|
||||
|
||||
mock_response = MagicMock()
|
||||
mock_response.status_code = 200
|
||||
mock_response.json.return_value = models_data
|
||||
mock_response.raise_for_status = MagicMock()
|
||||
|
||||
with patch.object(client.client, "get", new_callable=AsyncMock) as mock_get:
|
||||
mock_get.return_value = mock_response
|
||||
result = await client.list_models()
|
||||
|
||||
assert result == models_data
|
||||
assert len(result["models"]) == 2
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("src.models.ollama_client.settings")
|
||||
async def test_list_models_raises_on_error(self, mock_settings):
|
||||
"""list_models should raise on error."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
|
||||
client = OllamaClient()
|
||||
|
||||
with patch.object(client.client, "get", new_callable=AsyncMock) as mock_get:
|
||||
mock_get.side_effect = Exception("Connection error")
|
||||
|
||||
with pytest.raises(Exception):
|
||||
await client.list_models()
|
||||
|
||||
|
||||
class TestOllamaClientGenerateNonStreaming:
|
||||
"""Test non-streaming generation."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("src.models.ollama_client.settings")
|
||||
async def test_generate_non_streaming_returns_response(self, mock_settings):
|
||||
"""generate_non_streaming should return response dict."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
mock_settings.model_aliases = {}
|
||||
|
||||
client = OllamaClient()
|
||||
|
||||
response_data = {
|
||||
"message": {"content": "Hello! How can I help?"},
|
||||
"prompt_eval_count": 10,
|
||||
"eval_count": 20
|
||||
}
|
||||
|
||||
mock_response = MagicMock()
|
||||
mock_response.status_code = 200
|
||||
mock_response.json.return_value = response_data
|
||||
mock_response.raise_for_status = MagicMock()
|
||||
|
||||
with patch.object(client.client, "post", new_callable=AsyncMock) as mock_post:
|
||||
mock_post.return_value = mock_response
|
||||
result = await client.generate_non_streaming("llama2", "Hello")
|
||||
|
||||
assert result["response"] == "Hello! How can I help?"
|
||||
assert result["tokens"]["prompt"] == 10
|
||||
assert result["tokens"]["completion"] == 20
|
||||
assert result["tokens"]["total"] == 30
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("src.models.ollama_client.settings")
|
||||
async def test_generate_non_streaming_includes_max_tokens(self, mock_settings):
|
||||
"""generate_non_streaming should include max_tokens in payload."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
mock_settings.model_aliases = {}
|
||||
|
||||
client = OllamaClient()
|
||||
|
||||
mock_response = MagicMock()
|
||||
mock_response.status_code = 200
|
||||
mock_response.json.return_value = {"message": {"content": "Hi"}}
|
||||
mock_response.raise_for_status = MagicMock()
|
||||
|
||||
with patch.object(client.client, "post", new_callable=AsyncMock) as mock_post:
|
||||
mock_post.return_value = mock_response
|
||||
await client.generate_non_streaming("llama2", "Hello", max_tokens=100)
|
||||
|
||||
call_args = mock_post.call_args
|
||||
assert call_args[1]["json"]["options"]["num_predict"] == 100
|
||||
|
||||
|
||||
class TestOllamaClientGenerateStreaming:
|
||||
"""Test streaming generation."""
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("src.models.ollama_client.settings")
|
||||
async def test_generate_streaming_yields_content(self, mock_settings):
|
||||
"""generate_streaming should yield content chunks."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
mock_settings.model_aliases = {}
|
||||
|
||||
client = OllamaClient()
|
||||
|
||||
# Create mock streaming response
|
||||
async def mock_aiter_lines():
|
||||
yield json.dumps({"message": {"content": "Hello"}})
|
||||
yield json.dumps({"message": {"content": " world"}})
|
||||
yield json.dumps({"done": True})
|
||||
|
||||
mock_response = MagicMock()
|
||||
mock_response.status_code = 200
|
||||
mock_response.raise_for_status = MagicMock()
|
||||
mock_response.aiter_lines = mock_aiter_lines
|
||||
|
||||
mock_stream_context = AsyncMock()
|
||||
mock_stream_context.__aenter__.return_value = mock_response
|
||||
mock_stream_context.__aexit__.return_value = None
|
||||
|
||||
with patch.object(client.client, "stream", return_value=mock_stream_context):
|
||||
chunks = []
|
||||
async for chunk in client.generate_streaming("llama2", "Hi"):
|
||||
chunks.append(chunk)
|
||||
|
||||
assert "Hello" in chunks
|
||||
assert " world" in chunks
|
||||
|
||||
|
||||
class TestOllamaClientSingleton:
|
||||
"""Test singleton pattern."""
|
||||
|
||||
@patch("src.models.ollama_client.settings")
|
||||
def test_get_ollama_client_returns_same_instance(self, mock_settings):
|
||||
"""get_ollama_client should return singleton."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
|
||||
import src.models.ollama_client as module
|
||||
module._ollama_client = None
|
||||
|
||||
client1 = get_ollama_client()
|
||||
client2 = get_ollama_client()
|
||||
|
||||
assert client1 is client2
|
||||
|
||||
@pytest.mark.asyncio
|
||||
@patch("src.models.ollama_client.settings")
|
||||
async def test_close_ollama_client_clears_singleton(self, mock_settings):
|
||||
"""close_ollama_client should clear the singleton."""
|
||||
mock_settings.ollama_base_url = "http://ollama:11434"
|
||||
mock_settings.ollama_timeout = 30
|
||||
|
||||
import src.models.ollama_client as module
|
||||
module._ollama_client = None
|
||||
|
||||
client = get_ollama_client()
|
||||
|
||||
with patch.object(client.client, "aclose", new_callable=AsyncMock):
|
||||
await close_ollama_client()
|
||||
|
||||
assert module._ollama_client is None
|
||||
Reference in New Issue
Block a user