feat: inject today's date into system prompt and add extended thinking support

Fixes age validation errors caused by the LLM not knowing the current date.

Changes:
- prompts.py: inject date.today() at the top of both system prompts so the
  LLM can accurately calculate a child's age from their date of birth
- llm.py: add optional thinking_budget parameter to complete(); when set,
  passes thinking={"type": "enabled", "budget_tokens": N} to litellm and
  raises max_tokens to thinking_budget + 4096 (Anthropic models only)
- config.py: add thinking_budget field, read from THINKING_BUDGET env var
- .env.example: document the THINKING_BUDGET option
- core.py: pass thinking_budget through to llm.complete()
- main.py: pass thinking_budget when constructing EmailAgent
- chat_app.py: switch from stream_complete to asyncio.to_thread(complete)
  so extended thinking works and so only the reply field is shown to
  the parent (not the raw JSON wrapper)

To enable extended thinking set THINKING_BUDGET=8000 in .env.

https://claude.ai/code/session_01SUWzMzFvSfWiHXA2p6rPg9

src/config.py

@@ -50,6 +50,11 @@ class Config:
     # Polling interval in seconds
     poll_interval: int = 60
 
+    # Extended thinking — Anthropic models only.
+    # When set, enables the thinking phase before the LLM replies.
+    # Recommended value: 8000 (tokens). Set to None/unset to disable.
+    thinking_budget: int | None = None
+
     @classmethod
     def from_env(cls) -> "Config":
         return cls(
@@ -74,4 +79,9 @@ class Config:
                 )
             ),
             poll_interval=int(os.getenv("POLL_INTERVAL", "60")),
+            thinking_budget=(
+                int(os.getenv("THINKING_BUDGET"))
+                if os.getenv("THINKING_BUDGET")
+                else None
+            ),
         )