Wire Ollama properly: fix IP, upgrade to llama3.1:8b, use for guardian/sitrep

- reactor.py: fix OLLAMA_HOST .95 → .210 (actual Ollama VM IP)
- reactor.py: upgrade OLLAMA_MODEL 1b → 8b (llama3.1:8b has tool-calling, 131K ctx)
- reactor.py: guardian alerts and sitrep now use ollama instead of groq (free, on-LAN, no quota)
- config.example.php: same IP/model fixes + fix GROQ_MODEL_SEARCH to compound-beta-mini (groq/ prefix causes 404)
- deploy script: patch live config.php on every deploy to correct Ollama IP/model and Groq model name

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01X8tDRrQqgLjqXebMCBNcP3

deploy/jarvis-deploy.sh

@@ -80,6 +80,18 @@ while IFS= read -r path; do
         systemctl reload lsws 2>/dev/null || systemctl restart lsws 2>/dev/null
         log "OLS reloaded for JARVIS deploy"
 
+        # Patch live config.php with correct Ollama host/model and Groq search model
+        CONFIG="$path/api/config.php"
+        if [ -f "$CONFIG" ]; then
+            sed -i "s|http://10\.48\.200\.95:11434|http://10.48.200.210:11434|g" "$CONFIG"
+            sed -i "s|'llama3\.2:1b'|'llama3.1:8b'|g" "$CONFIG"
+            sed -i "s|\"llama3\.2:1b\"|\"llama3.1:8b\"|g" "$CONFIG"
+            sed -i "s|'llama3\.1:70b'|'llama3.1:8b'|g" "$CONFIG"
+            sed -i "s|\"llama3\.1:70b\"|\"llama3.1:8b\"|g" "$CONFIG"
+            sed -i "s|'groq/compound-mini'|'compound-beta-mini'|g;s|\"groq/compound-mini\"|\"compound-beta-mini\"|g" "$CONFIG"
+            log "Patched config.php: Ollama IP→.210, model→llama3.1:8b, Groq search→compound-beta-mini"
+        fi
+
         # Sync reactor.py + service file to runtime location if they changed
         if echo "$CHANGED" | grep -q 'deploy/reactor.py\|deploy/jarvis-arc.service'; then
             mkdir -p /opt/jarvis-arc