Add ruff for code quality and linting

Add ruff 0.8.4 as development dependency with configuration in
pyproject.toml. Auto-fix 170 code quality issues including import
sorting, modern Python syntax, and redundant code patterns.

Configure ruff with:
- Line length: 100 characters
- Python 3.11+ syntax enforcement
- Import sorting (isort)
- Common bug detection rules

Update DEVELOPER_GUIDE.md with linting workflow and usage examples.

Co-Authored-By: Claude <noreply@anthropic.com>
Signed-off-by: Andre Fredette <afredette@redhat.com>

Author: anfredette

backend/src/api/routes.py

@@ -3,18 +3,18 @@
 import logging
 import os
 from datetime import datetime
-from typing import List, Optional
+
 from fastapi import FastAPI, HTTPException
 from fastapi.middleware.cors import CORSMiddleware
 from pydantic import BaseModel
 
-from ..context_intent.schema import DeploymentRecommendation, ConversationMessage
-from ..orchestration.workflow import RecommendationWorkflow
+from ..context_intent.schema import ConversationMessage, DeploymentRecommendation
+from ..deployment.cluster import KubernetesClusterManager, KubernetesDeploymentError
+from ..deployment.generator import DeploymentGenerator
+from ..deployment.validator import ValidationError, YAMLValidator
 from ..knowledge_base.model_catalog import ModelCatalog
 from ..knowledge_base.slo_templates import SLOTemplateRepository
-from ..deployment.generator import DeploymentGenerator
-from ..deployment.validator import YAMLValidator, ValidationError
-from ..deployment.cluster import KubernetesClusterManager, KubernetesDeploymentError
+from ..orchestration.workflow import RecommendationWorkflow
 
 # Configure logging - check for DEBUG environment variable
 debug_mode = os.getenv("COMPASS_DEBUG", "false").lower() == "true"
@@ -64,7 +64,7 @@
 class RecommendationRequest(BaseModel):
     """Request for deployment recommendation."""
     user_message: str
-    conversation_history: Optional[List[ConversationMessage]] = None
+    conversation_history: list[ConversationMessage] | None = None
 
 
 class SimpleRecommendationRequest(BaseModel):
@@ -76,14 +76,14 @@ class RecommendationResponse(BaseModel):
     """Response with deployment recommendation."""
     recommendation: DeploymentRecommendation
     success: bool = True
-    message: Optional[str] = None
+    message: str | None = None
 
 
 class ErrorResponse(BaseModel):
     """Error response."""
     success: bool = False
     error: str
-    details: Optional[str] = None
+    details: str | None = None
 
 
 class DeploymentRequest(BaseModel):
@@ -98,7 +98,7 @@ class DeploymentResponse(BaseModel):
     namespace: str
     files: dict
     success: bool = True
-    message: Optional[str] = None
+    message: str | None = None
 
 
 class DeploymentStatusResponse(BaseModel):
@@ -109,7 +109,7 @@ class DeploymentStatusResponse(BaseModel):
     resource_utilization: dict
     cost_analysis: dict
     traffic_patterns: dict
-    recommendations: Optional[List[str]] = None
+    recommendations: list[str] | None = None
 
 
 # Health check endpoint
@@ -619,15 +619,13 @@ async def get_deployment_yaml(deployment_id: str):
     """
     try:
         # Get the output directory from deployment generator
-        import os
-        from pathlib import Path
 
         output_dir = deployment_generator.output_dir
 
         # Find all YAML files for this deployment
         yaml_files = {}
         for file_path in output_dir.glob(f"{deployment_id}*.yaml"):
-            with open(file_path, 'r') as f:
+            with open(file_path) as f:
                 yaml_files[file_path.name] = f.read()
 
         if not yaml_files:

backend/src/context_intent/extractor.py

@@ -1,13 +1,12 @@
 """Intent extraction from conversational input."""
 
 import logging
-from typing import List, Dict, Optional
-from pathlib import Path
 from datetime import datetime
+from pathlib import Path
 
-from .schema import DeploymentIntent, ConversationMessage
 from ..llm.ollama_client import OllamaClient
-from ..llm.prompts import build_intent_extraction_prompt, INTENT_EXTRACTION_SCHEMA
+from ..llm.prompts import INTENT_EXTRACTION_SCHEMA, build_intent_extraction_prompt
+from .schema import ConversationMessage, DeploymentIntent
 
 logger = logging.getLogger(__name__)
 
@@ -19,7 +18,7 @@
 class IntentExtractor:
     """Extract structured deployment intent from natural language conversation."""
 
-    def __init__(self, llm_client: Optional[OllamaClient] = None):
+    def __init__(self, llm_client: OllamaClient | None = None):
         """
         Initialize intent extractor.
 
@@ -31,7 +30,7 @@ def __init__(self, llm_client: Optional[OllamaClient] = None):
     def extract_intent(
         self,
         user_message: str,
-        conversation_history: Optional[List[ConversationMessage]] = None
+        conversation_history: list[ConversationMessage] | None = None
     ) -> DeploymentIntent:
         """
         Extract deployment intent from user message.
@@ -106,7 +105,7 @@ def extract_intent(
             logger.error(f"Failed to extract intent: {e}")
             raise ValueError(f"Intent extraction failed: {e}")
 
-    def _parse_extracted_intent(self, raw_data: Dict) -> DeploymentIntent:
+    def _parse_extracted_intent(self, raw_data: dict) -> DeploymentIntent:
         """
         Parse and validate raw LLM output into DeploymentIntent.
 
@@ -128,7 +127,7 @@ def _parse_extracted_intent(self, raw_data: Dict) -> DeploymentIntent:
             logger.error(f"Failed to parse intent from: {cleaned_data}")
             raise ValueError(f"Invalid intent data: {e}")
 
-    def _clean_llm_output(self, data: Dict) -> Dict:
+    def _clean_llm_output(self, data: dict) -> dict:
         """
         Clean common LLM output mistakes.
 

backend/src/context_intent/schema.py

@@ -1,18 +1,19 @@
 """Data schemas for deployment intent and specifications."""
 
-from typing import Optional, List, Literal
+from typing import Literal
+
 from pydantic import BaseModel, Field
 
 
 class TrafficProfile(BaseModel):
     """Traffic characteristics for the deployment."""
 
     prompt_tokens_mean: int = Field(..., description="Average prompt length in tokens")
-    prompt_tokens_variance: Optional[int] = Field(None, description="Variance in prompt length")
+    prompt_tokens_variance: int | None = Field(None, description="Variance in prompt length")
     generation_tokens_mean: int = Field(..., description="Average generation length in tokens")
-    generation_tokens_variance: Optional[int] = Field(None, description="Variance in generation length")
+    generation_tokens_variance: int | None = Field(None, description="Variance in generation length")
     expected_qps: float = Field(..., description="Expected queries per second")
-    requests_per_user_per_day: Optional[int] = Field(None, description="User request frequency")
+    requests_per_user_per_day: int | None = Field(None, description="User request frequency")
 
 
 class SLOTargets(BaseModel):
@@ -62,12 +63,12 @@ class DeploymentIntent(BaseModel):
         description="Cost sensitivity"
     )
 
-    domain_specialization: List[str] = Field(
+    domain_specialization: list[str] = Field(
         default_factory=lambda: ["general"],
         description="Domain requirements (general, code, multilingual, enterprise)"
     )
 
-    additional_context: Optional[str] = Field(
+    additional_context: str | None = Field(
         None,
         description="Any other relevant details from conversation"
     )
@@ -103,7 +104,7 @@ class DeploymentRecommendation(BaseModel):
     # Metadata
     meets_slo: bool = Field(..., description="Whether configuration meets SLO targets")
     reasoning: str = Field(..., description="Explanation of recommendation choice")
-    alternative_options: Optional[List[dict]] = Field(
+    alternative_options: list[dict] | None = Field(
         default=None,
         description="Alternative configurations with trade-offs"
     )
@@ -114,4 +115,4 @@ class ConversationMessage(BaseModel):
 
     role: Literal["user", "assistant", "system"]
     content: str
-    timestamp: Optional[str] = None
+    timestamp: str | None = None

backend/src/deployment/cluster.py

@@ -4,12 +4,11 @@
 and the Kubernetes Python client.
 """
 
-import os
 import logging
+import os
 import subprocess
-from pathlib import Path
-from typing import Dict, Any, List, Optional
 from datetime import datetime
+from typing import Any
 
 logger = logging.getLogger(__name__)
 
@@ -87,7 +86,7 @@ def create_namespace_if_not_exists(self) -> bool:
         except subprocess.TimeoutExpired:
             raise KubernetesDeploymentError("Namespace operation timed out")
 
-    def apply_yaml(self, yaml_path: str) -> Dict[str, Any]:
+    def apply_yaml(self, yaml_path: str) -> dict[str, Any]:
         """
         Apply a YAML file to the cluster.
 
@@ -124,7 +123,7 @@ def apply_yaml(self, yaml_path: str) -> Dict[str, Any]:
         except subprocess.TimeoutExpired:
             raise KubernetesDeploymentError(f"Timeout applying {yaml_path}")
 
-    def deploy_all(self, yaml_files: List[str]) -> Dict[str, Any]:
+    def deploy_all(self, yaml_files: list[str]) -> dict[str, Any]:
         """
         Deploy all YAML files to the cluster.
 
@@ -164,7 +163,7 @@ def deploy_all(self, yaml_files: List[str]) -> Dict[str, Any]:
             "timestamp": datetime.now().isoformat()
         }
 
-    def get_inferenceservice_status(self, deployment_id: str) -> Dict[str, Any]:
+    def get_inferenceservice_status(self, deployment_id: str) -> dict[str, Any]:
         """
         Get status of an InferenceService.
 
@@ -234,7 +233,7 @@ def get_inferenceservice_status(self, deployment_id: str) -> Dict[str, Any]:
                 "error": str(e)
             }
 
-    def get_deployment_pods(self, deployment_id: str) -> List[Dict[str, Any]]:
+    def get_deployment_pods(self, deployment_id: str) -> list[dict[str, Any]]:
         """
         Get pods associated with a deployment.
 
@@ -285,7 +284,7 @@ def get_deployment_pods(self, deployment_id: str) -> List[Dict[str, Any]]:
             logger.error(f"Error getting pods: {e}")
             return []
 
-    def delete_inferenceservice(self, deployment_id: str) -> Dict[str, Any]:
+    def delete_inferenceservice(self, deployment_id: str) -> dict[str, Any]:
         """
         Delete an InferenceService.
 
@@ -328,7 +327,7 @@ def delete_inferenceservice(self, deployment_id: str) -> Dict[str, Any]:
                 "error": str(e)
             }
 
-    def list_inferenceservices(self) -> List[str]:
+    def list_inferenceservices(self) -> list[str]:
         """
         List all InferenceServices in namespace.
 

backend/src/deployment/generator.py

@@ -4,12 +4,12 @@
 LLM inference deployments using Jinja2 templates.
 """
 
-import os
 import logging
 from datetime import datetime
 from pathlib import Path
-from typing import Dict, Any, List, Optional
-from jinja2 import Environment, FileSystemLoader, Template
+from typing import Any
+
+from jinja2 import Environment, FileSystemLoader
 
 from ..context_intent.schema import DeploymentRecommendation
 
@@ -31,7 +31,7 @@ class DeploymentGenerator:
     # vLLM version to use
     VLLM_VERSION = "v0.6.2"
 
-    def __init__(self, output_dir: Optional[str] = None, simulator_mode: bool = False):
+    def __init__(self, output_dir: str | None = None, simulator_mode: bool = False):
         """
         Initialize the deployment generator.
 
@@ -107,7 +107,7 @@ def _prepare_template_context(
         recommendation: DeploymentRecommendation,
         deployment_id: str,
         namespace: str = "default"
-    ) -> Dict[str, Any]:
+    ) -> dict[str, Any]:
         """
         Prepare context dictionary for Jinja2 templates.
 
@@ -237,7 +237,7 @@ def generate_all(
         self,
         recommendation: DeploymentRecommendation,
         namespace: str = "default"
-    ) -> Dict[str, str]:
+    ) -> dict[str, str]:
         """
         Generate all deployment YAML files.
 
@@ -299,7 +299,7 @@ def generate_all(
     def generate_kserve_yaml(
         self,
         recommendation: DeploymentRecommendation,
-        deployment_id: Optional[str] = None,
+        deployment_id: str | None = None,
         namespace: str = "default"
     ) -> str:
         """