Docs: add MODEL, SERP_CACHE_TTL_HOURS, and LOG_LEVEL to .env.example

These environment variables were already supported in config.py but
were not documented in .env.example, making them hard to discover.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

.env.example

@@ -47,12 +47,27 @@ STORAGE_BACKEND=local
 # AWS_SECRET_ACCESS_KEY=minioadmin
 # To start MinIO locally: docker compose --profile s3 up -d minio
 
+# ---- LLM ----
+
+# LLM model to use via OpenRouter
+# Supported: anthropic/claude-3.5-sonnet, openai/gpt-4o, openai/gpt-4o-mini,
+#            google/gemini-pro-1.5, meta-llama/llama-3.1-70b-instruct
+# MODEL=anthropic/claude-3.5-sonnet
+
 # ---- Cache ----
 
 # When USE_CACHE=true: check database for cached responses before making API calls
 # When USE_CACHE=false: always make fresh API calls (still stores results in database)
 USE_CACHE=true
 
+# SERP API cache TTL in hours (how long cached search results are considered fresh)
+# SERP_CACHE_TTL_HOURS=24
+
+# ---- Logging ----
+
+# Log level: DEBUG, INFO, WARNING, ERROR, CRITICAL
+# LOG_LEVEL=INFO
+
 # ---- Webhooks ----
 
 # Comma-separated list of webhook URLs for job completion and alert notifications