fix: preserve reasoning_content for OpenAI-compatible reasoning models

Models like Moonshot kimi-k2.5 and DeepSeek-R1 return a
reasoning_content field in assistant messages. When thinking is enabled,
the API requires this field to be echoed back in subsequent requests.
PicoClaw was silently dropping it, causing 400 errors on tool-call
round-trips.

- Add ReasoningContent to Message and LLMResponse types
- Parse reasoning_content in openai_compat parseResponse()
- Carry reasoning_content through assistant tool-call messages
- Add unit test for reasoning_content parsing

Fixes #588

pkg/agent/loop.go

@@ -622,8 +622,9 @@ func (al *AgentLoop) runLLMIteration(
 
 		// Build assistant message with tool calls
 		assistantMsg := providers.Message{
-			Role:    "assistant",
-			Content: response.Content,
+			Role:             "assistant",
+			Content:          response.Content,
+			ReasoningContent: response.ReasoningContent,
 		}
 		for _, tc := range normalizedToolCalls {
 			argumentsJSON, _ := json.Marshal(tc.Arguments)