Fix temperature param + add thinking for anthropic

The temperature param was not passed to the llm.
Now support anthropic models in 'thinking' mode.

config.example.toml

@@ -24,6 +24,8 @@ temperature = 0.3  # Slightly higher temperature for more creative implementatio
 # Options: "ephemeral", "5minute", "1hour"
 # Reduces costs and latency for repeated prompts. Uses Anthropic's prompt caching with different TTLs.
 # enable_1m_context = true    # optional, more expensive
+# thinking_budget_tokens = 10000  # Optional: Enable extended thinking mode with token budget
+# Allows the model to "think" before responding. Useful for complex reasoning tasks.
 
 
 # Multiple OpenAI-compatible providers can be configured with custom names