docs(config.example): fix Claude thinking example — add supports_thinking and budget_tokens (#3068)

The commented Claude example used Claude 3.5 Sonnet with
when_thinking_enabled but lacked supports_thinking: true. Copying the
block and swapping to a Claude 4 model name would silently fall back to
non-thinking mode (agent.py line 380 suppresses the error and logs only
a warning).

A second trap: budget_tokens is required by the Anthropic API when
thinking.type == "enabled"; there is no server default. The old example
omitted it, so any user who did add supports_thinking: true would get an
API error on the first thinking request.

Replace with a Claude Sonnet 4 example that includes both fields and
inline comments explaining the constraints.

Closes #2336

Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>

config.example.yaml

@@ -118,19 +118,25 @@ models:
   # For Docker deployments, use host.docker.internal instead of localhost:
   #   base_url: http://host.docker.internal:11434
 
-  # Example: Anthropic Claude model
-  # - name: claude-3-5-sonnet
-  #   display_name: Claude 3.5 Sonnet
+  # Example: Anthropic Claude model (with extended thinking)
+  # supports_thinking: true is required — without it, DeerFlow silently falls
+  # back to non-thinking mode even when the UI thinking toggle is on.
+  # budget_tokens is required by the Anthropic API when thinking.type=enabled
+  # (no server default; min 1024; must be less than max_tokens).
+  # - name: claude-sonnet-4
+  #   display_name: Claude Sonnet 4
   #   use: langchain_anthropic:ChatAnthropic
-  #   model: claude-3-5-sonnet-20241022
+  #   model: claude-sonnet-4-20250514
   #   api_key: $ANTHROPIC_API_KEY
   #   default_request_timeout: 600.0
   #   max_retries: 2
-  #   max_tokens: 8192
-  #   supports_vision: true  # Enable vision support for view_image tool
+  #   max_tokens: 16000
+  #   supports_vision: true
+  #   supports_thinking: true
   #   when_thinking_enabled:
   #     thinking:
   #       type: enabled
+  #       budget_tokens: 4096   # required; min 1024; must be < max_tokens
   #   when_thinking_disabled:
   #     thinking:
   #       type: disabled