fixed issues where the multi-intent queries weren't being properly handled by GPT-40

demos/use_cases/travel_agents/config.yaml

@@ -7,7 +7,7 @@ agents:
     url: http://host.docker.internal:10520
 
 model_providers:
-  - model: openai/gpt-4o
+  - model: openai/gpt-5.2
     access_key: $OPENAI_API_KEY
     default: true
   - model: openai/gpt-4o-mini

demos/use_cases/travel_agents/docker-compose.yaml

@@ -49,6 +49,10 @@ services:
       - DEFAULT_MODEL=gpt-4o-mini
       - ENABLE_OPENAI_API=true
       - OPENAI_API_BASE_URL=http://host.docker.internal:8001/v1
+      - ENABLE_FOLLOW_UP_GENERATION=false
+      - ENABLE_TITLE_GENERATION=false
+      - ENABLE_TAGS_GENERATION=false
+      - ENABLE_AUTOCOMPLETE_GENERATION=false
     depends_on:
       - weather-agent
       - flight-agent

demos/use_cases/travel_agents/src/travel_agents/flight_agent.py

@@ -19,7 +19,7 @@ logger = logging.getLogger(__name__)
 LLM_GATEWAY_ENDPOINT = os.getenv(
     "LLM_GATEWAY_ENDPOINT", "http://host.docker.internal:12000/v1"
 )
-FLIGHT_MODEL = "openai/gpt-4o"
+FLIGHT_MODEL = "openai/gpt-5.2"
 EXTRACTION_MODEL = "openai/gpt-4o-mini"
 
 AEROAPI_BASE_URL = "https://aeroapi.flightaware.com/aeroapi"
@@ -82,7 +82,7 @@ async def extract_flight_route(messages: list, request: Request) -> dict:
                 ],
             ],
             temperature=0.1,
-            max_tokens=100,
+            max_completion_tokens=100,
             extra_headers=extra_headers or None,
         )
 
@@ -124,7 +124,7 @@ async def resolve_airport_code(city_name: str, request: Request) -> Optional[str
                 {"role": "user", "content": city_name},
             ],
             temperature=0.1,
-            max_tokens=10,
+            max_completion_tokens=10,
             extra_headers=extra_headers or None,
         )
 
@@ -355,7 +355,7 @@ Ask the user to check the city name or provide a different city."""
             model=FLIGHT_MODEL,
             messages=response_messages,
             temperature=request_body.get("temperature", 0.7),
-            max_tokens=request_body.get("max_tokens", 1000),
+            max_completion_tokens=request_body.get("max_tokens", 3000),
             stream=True,
             extra_headers=extra_headers,
         )

demos/use_cases/travel_agents/src/travel_agents/weather_agent.py

@@ -26,7 +26,7 @@ logger = logging.getLogger(__name__)
 LLM_GATEWAY_ENDPOINT = os.getenv(
     "LLM_GATEWAY_ENDPOINT", "http://host.docker.internal:12001/v1"
 )
-WEATHER_MODEL = "openai/gpt-4o"
+WEATHER_MODEL = "openai/gpt-5.2"
 LOCATION_MODEL = "openai/gpt-4o-mini"
 
 # Initialize OpenAI client for plano
@@ -117,7 +117,7 @@ If no city can be found, output: NOT_FOUND"""
                     ],
                 ],
                 temperature=0.1,
-                max_tokens=10,
+                max_completion_tokens=10,
                 extra_headers=extra_headers if extra_headers else None,
             )
 
@@ -372,7 +372,7 @@ Present the weather information to the user in a clear, readable format. If ther
             model=WEATHER_MODEL,
             messages=response_messages,
             temperature=request_body.get("temperature", 0.7),
-            max_tokens=request_body.get("max_tokens", 1000),
+            max_completion_tokens=request_body.get("max_tokens", 3000),
             stream=True,
             extra_headers=extra_headers,
         )