Fix OMP_NUM_THREADS warning and restart loop issues

v1.3.10 - Final fixes for clean startup:
1. Moved OMP_NUM_THREADS=1 to Dockerfile ENV (not Python os.environ)
2. Moved all HF cache environment variables to Dockerfile ENV
3. Extended health check timing: 300s start period, 60s interval, 5 retries
(allows more time for Moshi model loading without failing health checks)
4. Cleaned up Python environment variable setting code

Should eliminate both libgomp warning and restart loops

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

Dockerfile

@@ -43,11 +43,17 @@ RUN chown -R appuser:appuser /app
 # Switch back to non-root user for running the app
 USER appuser
 
+# Set environment variables to fix OpenMP and caching issues
+ENV OMP_NUM_THREADS=1
+ENV HF_HOME=/app/hf_cache
+ENV HUGGINGFACE_HUB_CACHE=/app/hf_cache
+ENV TRANSFORMERS_CACHE=/app/hf_cache
+
 # Expose port
 EXPOSE 7860
 
-# Health check
-HEALTHCHECK --interval=30s --timeout=30s --start-period=180s --retries=3 \
+# Health check - allow more time for model loading
+HEALTHCHECK --interval=60s --timeout=45s --start-period=300s --retries=5 \
     CMD curl -f http://localhost:7860/health || exit 1
 
 # Run application as non-root user

app.py

@@ -6,13 +6,8 @@ import os
 from typing import Optional
 from contextlib import asynccontextmanager
 
-# Fix OpenMP warning - MUST be set before importing torch
-os.environ['OMP_NUM_THREADS'] = '1'
-
-# Fix cache directory permissions - set to writable directory
-os.environ['HF_HOME'] = '/app/hf_cache'
-os.environ['HUGGINGFACE_HUB_CACHE'] = '/app/hf_cache'
-os.environ['TRANSFORMERS_CACHE'] = '/app/hf_cache'
+# Environment variables now set in Dockerfile
+# OMP_NUM_THREADS=1, HF_HOME=/app/hf_cache, etc.
 
 import torch
 import numpy as np
@@ -21,7 +16,7 @@ from fastapi.responses import JSONResponse, HTMLResponse
 import uvicorn
 
 # Version tracking
-VERSION = "1.3.9"
+VERSION = "1.3.10"
 COMMIT_SHA = "TBD"
 
 # Configure logging