feat(kiro): enhance request translation and fix streaming issues

English:
- Fix <thinking> tag parsing: only parse at response start, avoid misinterpreting discussion text
- Add token counting support using tiktoken for local estimation
- Support top_p parameter in inference config
- Handle max_tokens=-1 as maximum (32000 tokens)
- Add tool_choice and response_format parameter handling via system prompt hints
- Support multiple thinking mode detection formats (Claude API, OpenAI reasoning_effort, AMP/Cursor)
- Shorten MCP tool names exceeding 64 characters
- Fix duplicate [DONE] marker in OpenAI SSE streaming
- Enhance token usage statistics with multiple event format support
- Add code fence markers to constants

中文:
- 修复 <thinking> 标签解析：仅在响应开头解析，避免误解析讨论文本中的标签
- 使用 tiktoken 实现本地 token 计数功能
- 支持 top_p 推理配置参数
- 处理 max_tokens=-1 转换为最大值（32000 tokens）
- 通过系统提示词注入实现 tool_choice 和 response_format 参数支持
- 支持多种思考模式检测格式（Claude API、OpenAI reasoning_effort、AMP/Cursor）
- 截断超过64字符的 MCP 工具名称
- 修复 OpenAI SSE 流中重复的 [DONE] 标记
- 增强 token 使用量统计，支持多种事件格式
- 添加代码围栏标记常量

internal/translator/kiro/common/constants.go

@@ -12,6 +12,15 @@ const (
 	// ThinkingEndTag is the end tag for thinking blocks in responses.
 	ThinkingEndTag = "</thinking>"
 
+	// CodeFenceMarker is the markdown code fence marker.
+	CodeFenceMarker = "```"
+
+	// AltCodeFenceMarker is the alternative markdown code fence marker.
+	AltCodeFenceMarker = "~~~"
+
+	// InlineCodeMarker is the markdown inline code marker (backtick).
+	InlineCodeMarker = "`"
+
 	// KiroAgenticSystemPrompt is injected only for -agentic models to prevent timeouts on large writes.
 	// AWS Kiro API has a 2-3 minute timeout for large file write operations.
 	KiroAgenticSystemPrompt = `