fix: disable preemptive_generation for tool call compatibility; add get_time tool

- preemptive_generation was incompatible with MCP tool calls: it starts
  generating before the turn finalizes, breaking the tool execution loop
  (agent said 'let me check' then hung forever)
- Add get_time(location?) to weather_mcp.py for date/time queries
- Update system prompt with Weather & Time section

agent/agent.py

@@ -70,10 +70,12 @@ SYSTEM_PROMPT = textwrap.dedent("""\
     source naturally ("according to..."). If a search comes up empty, say so
     briefly and move on.
 
-    # Weather
+    # Weather & Time
     You can check the weather for any location. Use get_weather when the user
     asks about current conditions, temperature, or forecasts. It returns a
     short summary — relay it naturally in your own words.
+    Use get_time when the user asks what time or day it is. If they mention
+    a city, pass it as the location argument.
 """)
 
 
@@ -269,8 +271,9 @@ async def handle_job(ctx: JobContext) -> None:
             # VAD-based turn detection: agent waits for user to stop speaking.
             # ("adaptive" mode requires the LiveKit Cloud barge-in service.)
             interruption={"mode": "vad"},
-            # Start generating the LLM response before the user fully stops
-            preemptive_generation={"enabled": True},
+            # Preemptive generation is incompatible with tool calls — it starts
+            # generating before the turn finalizes, breaking the MCP execution loop.
+            preemptive_generation={"enabled": False},
         ),
     )