Automate checklist-backend updates

.env.example

@@ -213,11 +213,17 @@ UPLOAD_AUTORUN=true
 # exists to avoid. Stage 6 is the slowest stage and reaches the network, but
 # only one batch runs at a time, so nothing else competes with it.
 #
-# LLM off, because use_llm gates only description generation in stage 2, and
-# production runs USE_OLLAMA=false - turning it on there buys nothing and costs
-# a connection timeout per row.
+# LLM on, though in production it currently does nothing: USE_OLLAMA is false
+# there, so the LLM call returns immediately without a request and the row keeps
+# its blank description. Set true so the pipeline is already right for the day
+# an Ollama server is reachable.
+#
+# If you DO set USE_OLLAMA=true, make sure something is actually listening on
+# OLLAMA_BASE_URL. An unreachable server costs a 5s probe, and while that probe
+# is cached per 30s rather than paid per row, a reachable-but-slow model is
+# billed per row at OLLAMA_TIMEOUT_SECONDS.
 UPLOAD_AUTORUN_FETCH_IMAGES=true
-UPLOAD_AUTORUN_USE_LLM=false
+UPLOAD_AUTORUN_USE_LLM=true
 
 USE_OLLAMA=true
 OLLAMA_BASE_URL=http://localhost:11434