fix: prevent system prompt re-injection on subsequent turns

When tool results are sent back to the model, the system prompt was being
re-injected into the user message content, causing the model to think the
user had pasted the system prompt again. This was especially noticeable
after multiple tool uses.

The fix checks if there is conversation history (len(history) > 0). If so,
it's a subsequent turn and we skip system prompt injection. The system
prompt is only injected on the first turn (len(history) == 0).

This ensures:
- First turn: system prompt is injected
- Tool result turns: system prompt is NOT re-injected
- New conversations: system prompt is injected fresh

internal/translator/kiro/claude/kiro_claude_request.go

@@ -240,9 +240,13 @@ func BuildKiroPayload(claudeBody []byte, modelID, profileArn, origin string, isA
 	// Process messages and build history
 	history, currentUserMsg, currentToolResults := processMessages(messages, modelID, origin)
 
-	// Build content with system prompt
+	// Build content with system prompt (only on first turn to avoid re-injection)
 	if currentUserMsg != nil {
-		currentUserMsg.Content = buildFinalContent(currentUserMsg.Content, systemPrompt, currentToolResults)
+		effectiveSystemPrompt := systemPrompt
+		if len(history) > 0 {
+			effectiveSystemPrompt = "" // Don't re-inject on subsequent turns
+		}
+		currentUserMsg.Content = buildFinalContent(currentUserMsg.Content, effectiveSystemPrompt, currentToolResults)
 
 		// Deduplicate currentToolResults
 		currentToolResults = deduplicateToolResults(currentToolResults)