fix: increase LLM timeout 30s→60s, fix Gateway request format, add Ollama optimization guide

- Fixed Gateway: 'prompt' → 'message' field name
- Increased LLM provider timeout from 30s to 60s
- Added OLLAMA-OPTIMIZATION.md with performance tips
- DAARWIZZ now responds (slowly but works)

gateway-bot/http_api.py

@@ -124,7 +124,7 @@ async def telegram_webhook(update: TelegramUpdate):
         
         # Build request to Router with DAARWIZZ context
         router_request = {
-            "prompt": text,
+            "message": text,
             "mode": "chat",
             "agent": "daarwizz",  # DAARWIZZ agent identifier
             "metadata": {
@@ -197,7 +197,7 @@ async def discord_webhook(message: DiscordMessage):
         
         # Build request to Router with DAARWIZZ context
         router_request = {
-            "prompt": text,
+            "message": text,
             "mode": "chat",
             "agent": "daarwizz",
             "metadata": {