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
@@ -12,7 +12,6 @@ Permission Format: domain.category:action
|
||||
Examples:
|
||||
- control-room.general:admin - Full access to Control Room
|
||||
- media.general:viewer - View-only access to Media area
|
||||
- ai.ollama:user - User-level access to Ollama specifically (future)
|
||||
|
||||
Action Hierarchy (higher implies lower):
|
||||
- admin > editor > user > viewer
|
||||
@@ -554,7 +553,7 @@ def _extract_permissions_from_groups(groups: List[str]) -> List[str]:
|
||||
Examples:
|
||||
- tatlock-control-room-general-admin -> control-room.general:admin
|
||||
- tatlock-media-viewer -> media.general:viewer (shorthand)
|
||||
- tatlock-ai-ollama-user -> ai.ollama:user
|
||||
- tatlock-tools-dns-user -> tools.dns:user
|
||||
|
||||
Args:
|
||||
groups: List of Authentik group names
|
||||
|
||||
@@ -70,66 +70,18 @@ class HealthController(BaseController):
|
||||
|
||||
@router.get(
|
||||
"/health/full",
|
||||
summary="Fast health check for Docker",
|
||||
summary="Full health check with database",
|
||||
)
|
||||
async def full_health_check(response: Response):
|
||||
"""
|
||||
Fast health check for container orchestration (Docker/K8s).
|
||||
Health check including database connectivity.
|
||||
|
||||
Checks component availability WITHOUT running expensive operations.
|
||||
Returns 200 OK if all components are available, otherwise 503.
|
||||
|
||||
For detailed diagnostics, use /health/diagnostics instead.
|
||||
Returns 200 OK if database is available, otherwise 503.
|
||||
"""
|
||||
import time
|
||||
start_time = time.time()
|
||||
|
||||
# Import here to avoid circular imports
|
||||
from src.models.ollama_client import get_ollama_client
|
||||
|
||||
# Check 1: Ollama connection + verify agent model is available
|
||||
ollama_client = get_ollama_client()
|
||||
ollama_healthy = False
|
||||
ollama_error = None
|
||||
model_available = False
|
||||
|
||||
try:
|
||||
# Ping Ollama
|
||||
ollama_healthy = await ollama_client.health_check()
|
||||
|
||||
# Verify the agent model is pulled and check what's currently loaded
|
||||
models_info = {}
|
||||
if ollama_healthy:
|
||||
try:
|
||||
models_response = await ollama_client.list_models()
|
||||
available_models = [m.get('name', '') for m in models_response.get('models', [])]
|
||||
model_available = settings.agent_model in available_models
|
||||
|
||||
# Get info about currently loaded models (those with size in memory)
|
||||
loaded_models = [
|
||||
m.get('name', '') for m in models_response.get('models', [])
|
||||
if m.get('size', 0) > 0
|
||||
]
|
||||
|
||||
models_info = {
|
||||
"configured": settings.agent_model,
|
||||
"available": model_available,
|
||||
"total_in_ollama": len(available_models),
|
||||
"currently_loaded": loaded_models if loaded_models else ["none"]
|
||||
}
|
||||
|
||||
if not model_available:
|
||||
ollama_error = f"Model '{settings.agent_model}' not found in Ollama. Available: {', '.join(available_models[:3])}"
|
||||
ollama_healthy = False
|
||||
except Exception as e:
|
||||
ollama_error = f"Could not list Ollama models: {str(e)}"
|
||||
ollama_healthy = False
|
||||
|
||||
except Exception as e:
|
||||
ollama_error = str(e)
|
||||
logger.warning(f"Ollama health check failed: {ollama_error}")
|
||||
|
||||
# Check 2: Database connection
|
||||
# Check database connection
|
||||
database = get_database()
|
||||
db_healthy = False
|
||||
db_error = None
|
||||
@@ -140,25 +92,15 @@ class HealthController(BaseController):
|
||||
db_error = str(e)
|
||||
logger.warning(f"Database health check failed: {db_error}")
|
||||
|
||||
is_healthy = ollama_healthy and db_healthy
|
||||
|
||||
elapsed_ms = int((time.time() - start_time) * 1000)
|
||||
status_code = 200 if is_healthy else 503
|
||||
status_code = 200 if db_healthy else 503
|
||||
response.status_code = status_code
|
||||
|
||||
return {
|
||||
"status": "healthy" if is_healthy else "unhealthy",
|
||||
"status": "healthy" if db_healthy else "unhealthy",
|
||||
"status_code": status_code,
|
||||
"response_time_ms": elapsed_ms,
|
||||
"components": {
|
||||
"ollama": {
|
||||
"status": "healthy" if ollama_healthy else "unhealthy",
|
||||
"models": models_info if models_info else {
|
||||
"configured": settings.agent_model,
|
||||
"available": False
|
||||
},
|
||||
"error": ollama_error
|
||||
},
|
||||
"database": {
|
||||
"status": "healthy" if db_healthy else "unhealthy",
|
||||
"error": db_error
|
||||
@@ -170,19 +112,13 @@ class HealthController(BaseController):
|
||||
"/health/diagnostics",
|
||||
summary="Detailed system diagnostics",
|
||||
)
|
||||
async def diagnostics(deep_test: bool = False):
|
||||
async def diagnostics():
|
||||
"""
|
||||
Comprehensive system diagnostics with detailed component information.
|
||||
|
||||
Query Parameters:
|
||||
- deep_test: Set to true to actually test agent generation (slow, ~5-10s)
|
||||
|
||||
Returns detailed information about all system components.
|
||||
System diagnostics with service information.
|
||||
"""
|
||||
import time
|
||||
from src.models.ollama_client import get_ollama_client
|
||||
|
||||
start_time = time.time()
|
||||
|
||||
diagnostics = {
|
||||
"timestamp": time.time(),
|
||||
"service": {
|
||||
@@ -190,30 +126,9 @@ class HealthController(BaseController):
|
||||
"version": settings.app_version,
|
||||
"purpose": "Infrastructure management and tools API"
|
||||
},
|
||||
"components": {}
|
||||
}
|
||||
|
||||
# 1. Ollama Connection
|
||||
ollama_client = get_ollama_client()
|
||||
try:
|
||||
ollama_healthy = await ollama_client.health_check()
|
||||
diagnostics["components"]["ollama"] = {
|
||||
"status": "connected",
|
||||
"url": settings.ollama_base_url,
|
||||
"timeout": settings.ollama_timeout,
|
||||
"default_model": settings.default_model
|
||||
"configuration": {
|
||||
"cors_origins": settings.cors_origins[:2] if len(settings.cors_origins) > 2 else settings.cors_origins
|
||||
}
|
||||
except Exception as e:
|
||||
diagnostics["components"]["ollama"] = {
|
||||
"status": "error",
|
||||
"error": str(e)
|
||||
}
|
||||
|
||||
# 2. Configuration
|
||||
diagnostics["configuration"] = {
|
||||
"agent_fallback_enabled": settings.agent_fallback_enabled,
|
||||
"memory_tier1_max_turns": settings.memory_tier1_max_turns,
|
||||
"cors_origins": settings.cors_origins[:2] if len(settings.cors_origins) > 2 else settings.cors_origins
|
||||
}
|
||||
|
||||
elapsed_ms = int((time.time() - start_time) * 1000)
|
||||
|
||||
Reference in New Issue
Block a user