fix: increase embedding and LLM timeouts for large local models

qwen3-embedding:8b needs >60s on first load. Set EMBEDDING_TIMEOUT=300
(worker executes at 2x = 600s) and TIMEOUT=600 for LLM calls.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

.env.lightrag

@@ -12,6 +12,10 @@ EMBEDDING_DIM=4096
 # Storage (local files)
 RAG_DIR=./rag_storage
 
+# Timeouts (in seconds) — increase for large local models
+EMBEDDING_TIMEOUT=300
+TIMEOUT=600
+
 # Server
 HOST=0.0.0.0
 PORT=9621