chore: Refine environment configurations and enhance error handling

- Updated PYTHONPATH in docker-compose.yml to point directly to the API package, improving module resolution.
- Changed log level in env.development from DEBUG to INFO to reduce log verbosity during development.
- Added validation for the GOOGLE_API_KEY in the worker to ensure a valid API key is configured before analysis.
- Enhanced error handling in the analyze_repository function to log failures during LLM analysis, improving debugging capabilities.
- Removed unnecessary debug logs in various modules to reduce log noise and improve clarity.
- Ensured compliance with project structure and coding standards, including type hints and documentation.

Author: viral-sangani

docker-compose.yml

@@ -57,7 +57,7 @@ services:
       - GOOGLE_API_KEY=${GOOGLE_API_KEY}
       - GITHUB_TOKEN=${GITHUB_TOKEN}
       - JWT_SECRET=${JWT_SECRET:-dev_secret_key}
-      - PYTHONPATH=/app
+      - PYTHONPATH=/app/packages/api
       - WATCHDOG_POLLING=True
     volumes:
       - .:/app
@@ -94,7 +94,7 @@ services:
       - GOOGLE_API_KEY=${GOOGLE_API_KEY}
       - GITHUB_TOKEN=${GITHUB_TOKEN}
       - JWT_SECRET=${JWT_SECRET:-dev_secret_key}
-      - PYTHONPATH=/app
+      - PYTHONPATH=/app/packages/api
       - WATCHDOG_POLLING=True
     volumes:
       - .:/app

packages/api/app/worker.py

@@ -75,6 +75,12 @@ def analyze_repository(task_id: str, github_url: str, options: dict):
         code_digest = repo_data["content"]
         metrics = repo_data.get("metrics", {})
 
+        # Validate API key before proceeding
+        if not settings.GOOGLE_API_KEY or settings.GOOGLE_API_KEY == "your_gemini_api_key_here":
+            raise Exception(
+                "GOOGLE_API_KEY is not configured. Please set a valid Gemini API key in your .env file."
+            )
+
         # Get analysis options
         model = options.get("model", settings.DEFAULT_MODEL)
         temperature = float(options.get("temperature", settings.TEMPERATURE))
@@ -105,15 +111,22 @@ def analyze_repository(task_id: str, github_url: str, options: dict):
         else:
             prompt_path = prompt_option
 
-        analysis = analyze_single_repository(
-            repo_name,
-            code_digest,
-            prompt_path,
-            model_name=model,
-            temperature=temperature,
-            output_json=False,
-            metrics_data=metrics,
-        )
+        logger.debug(f"Starting LLM analysis for {repo_name} using model {model}")
+
+        try:
+            analysis = analyze_single_repository(
+                repo_name,
+                code_digest,
+                prompt_path,
+                model_name=model,
+                temperature=temperature,
+                output_json=False,
+                metrics_data=metrics,
+            )
+            logger.debug(f"LLM analysis completed for {repo_name}")
+        except Exception as llm_error:
+            logger.error(f"LLM analysis failed for {repo_name}: {str(llm_error)}")
+            raise Exception(f"LLM analysis failed: {str(llm_error)}")
 
         # Update progress
         task.progress = 80

packages/api/src/worker.py

@@ -6,22 +6,15 @@
 import argparse
 import logging
 import os
-import sys
-from pathlib import Path
 
 from redis import Redis
 from rq import Queue, Worker
 
 # Prevent issues with fork() on macOS
 os.environ["OBJC_DISABLE_INITIALIZE_FORK_SAFETY"] = "YES"
 
-# Add project root to path
-project_root = Path(__file__).parent.parent.parent
-sys.path.insert(0, str(project_root))
-
-# Add packages/api to path so app.* imports work
-api_package_path = project_root / "packages" / "api"
-sys.path.insert(0, str(api_package_path))
+# PYTHONPATH is set via Docker environment variables
+# No manual sys.path manipulation needed
 
 # Load environment variables
 from dotenv import load_dotenv

packages/core/src/config.py

@@ -40,6 +40,11 @@ def get_gemini_api_key() -> str:
             f"{GEMINI_API_KEY_ENV} environment variable is not set. "
             f"Please set it in your .env file or export it directly."
         )
+    if api_key in ["your_gemini_api_key_here", "your_actual_gemini_api_key_here"]:
+        raise ValueError(
+            f"{GEMINI_API_KEY_ENV} is set to a placeholder value. "
+            f"Please set a real Gemini API key from https://aistudio.google.com/app/apikey"
+        )
     return api_key
 
 
@@ -129,6 +134,13 @@ def setup_logging(level_name: Optional[str] = None) -> None:
     logging.getLogger("httpx").setLevel(logging.WARNING)
     logging.getLogger("httpcore").setLevel(logging.WARNING)
 
+    # Suppress HTTP connection debug logs (very noisy)
+    logging.getLogger("urllib3").setLevel(logging.WARNING)
+    logging.getLogger("urllib3.connectionpool").setLevel(logging.WARNING)
+
+    # Suppress asyncio debug logs
+    logging.getLogger("asyncio").setLevel(logging.WARNING)
+
     # Suppress RQ (Redis Queue) INFO logs
     logging.getLogger("rq.worker").setLevel(logging.WARNING)
     logging.getLogger("rq.queue").setLevel(logging.WARNING)
@@ -155,4 +167,10 @@ def setup_logging(level_name: Optional[str] = None) -> None:
     logging.getLogger("watchfiles.main").setLevel(logging.WARNING)
     logging.getLogger("alembic").setLevel(logging.WARNING)
 
-    logging.debug(f"Logging initialized at level: {level_name}")
+    # Suppress GitHub API and gitingest debug logs
+    logging.getLogger("github").setLevel(logging.WARNING)
+    logging.getLogger("gitingest").setLevel(logging.WARNING)
+
+    # Only log the initialization at INFO level to avoid noise
+    if level >= logging.INFO:
+        logging.info(f"Logging initialized at level: {level_name}")

packages/core/src/fetcher.py

@@ -241,7 +241,7 @@ def normalize_repo_url(url: str) -> str:
     # Remove trailing slashes
     url = url.rstrip("/")
 
-    logger.debug(f"Normalized URL: {url}")
+    # URL normalized (removed debug log for noise reduction)
     return url
 
 

packages/core/src/metrics.py

@@ -34,7 +34,7 @@ def __init__(self, token: Optional[str] = None, max_workers: int = 5):
         self.token = token or os.environ.get("GITHUB_TOKEN")
         self.github = self._initialize_github()
         self.max_workers = max_workers
-        logger.debug(f"GitHub metrics fetcher initialized with {max_workers} workers")
+        # GitHub metrics fetcher initialized (removed debug log for noise reduction)
 
     def _initialize_github(self) -> Github:
         """
@@ -46,7 +46,7 @@ def _initialize_github(self) -> Github:
         if self.token:
             auth = Auth.Token(self.token)
             github = Github(auth=auth)
-            logger.debug("GitHub client initialized with token")
+            # GitHub client initialized with token (removed debug log for noise reduction)
         else:
             github = Github()
             logger.warning("GitHub client initialized without token (rate-limited)")
@@ -94,7 +94,7 @@ def get_repository(self, url: str):
 
         try:
             repo = self.github.get_repo(full_name)
-            logger.debug(f"Fetched repository: {full_name}")
+            # Repository fetched successfully (removed debug log for noise reduction)
             return repo
         except Exception as e:
             logger.error(f"Error fetching repository {full_name}: {str(e)}")