feat: sync full-stack Docker runtime and UI

backend/llm.py

@@ -22,20 +22,14 @@ LLM_API_KEY = os.getenv('LLM_API_KEY', 'ollama')
 # Auth headers for upstream LLM service (OpenAI-compatible Bearer token)
 LLM_HEADERS = {'Authorization': f'Bearer {LLM_API_KEY}'}
 
-# Model names (backward compat: fall back to OLLAMA_MODEL if LLM_MODEL not set)
-_raw_model = os.getenv('LLM_MODEL') or os.getenv('OLLAMA_MODEL', 'gpt-oss:20b')
-LLM_MODEL = _raw_model.strip() if _raw_model else 'gpt-oss:20b'
+# Model names
+DEFAULT_LLM_MODEL = 'Nex-N2-mini-mlx-OptiQ-8bit-MTP'
+_raw_model = os.getenv('LLM_MODEL', DEFAULT_LLM_MODEL)
+LLM_MODEL = _raw_model.strip() if _raw_model else DEFAULT_LLM_MODEL
 PRO_LLM_MODEL = os.getenv('PRO_LLM_MODEL', LLM_MODEL)
 
 # VLM for OCR (vision models)
-VLM_MODEL = os.getenv('VLM_MODEL', 'qwen3-vl:30b')
-
-# Fallback for legacy OLLAMA_HOST env var (auto-convert to /v1/ path)
-_legacy_host = os.getenv('OLLAMA_HOST')
-if _legacy_host and not os.getenv('LLM_BASE_URL'):
-    base = _legacy_host.rstrip('/')
-    if '/v1' not in base:
-        LLM_BASE_URL = f"{base}/v1/"
+VLM_MODEL = os.getenv('VLM_MODEL', DEFAULT_LLM_MODEL)
 
 # Normalize trailing slash for base URL
 LLM_BASE_URL = LLM_BASE_URL.rstrip('/') + '/'