feat(ai-pipeline): 支持 reasoning signature 及媒体内容块的跨格式流式转换

- 在 CanonicalStreamEvent 中新增 ReasoningSignature 和 ContentPart 变体，CanonicalContentPart 枚举覆盖图片/文件/音频
- Gemini 流解析器提取 thoughtSignature，并对 inlineData/fileData 等非文本 part 生成 ContentPart 事件
- Claude 流聚合支持 thinking_delta / signature_delta，输出 thinking block 携带 signature 字段
- Gemini 同步响应聚合重写，支持媒体 part 和 reasoning signature 的完整还原
- 跨格式矩阵（gemini↔claude↔openai）补全图片块双向转换及 reasoning signature 传递
- 请求转换层（to/from openai_chat）补全 Claude/Gemini 的 thinking、图片、工具调用字段映射
- 新增/扩展测试：inline image 双向重写、thinking signature 聚合、跨格式 sync product 媒体字段

apps/aether-gateway/src/ai_pipeline/finalize/tests_sync.rs

@@ -888,6 +888,7 @@ fn converts_claude_cli_tool_use_to_openai_cli_function_call() {
                 },
                 {
                     "type": "function_call",
+                    "id": "tool_123",
                     "call_id": "tool_123",
                     "name": "read_file",
                     "arguments": "{\"path\":\"/tmp/test.txt\"}"
@@ -952,7 +953,10 @@ fn converts_gemini_cli_response_to_openai_cli_response() {
             "usage": {
                 "input_tokens": 3,
                 "output_tokens": 7,
-                "total_tokens": 10
+                "total_tokens": 10,
+                "output_tokens_details": {
+                    "reasoning_tokens": 2
+                }
             }
         })
     );
@@ -1011,6 +1015,7 @@ fn converts_gemini_cli_function_call_to_openai_cli_function_call() {
                 },
                 {
                     "type": "function_call",
+                    "id": "call_auto_1",
                     "call_id": "call_auto_1",
                     "name": "get_weather",
                     "arguments": "{\"location\":\"Tokyo\"}"
@@ -1019,7 +1024,10 @@ fn converts_gemini_cli_function_call_to_openai_cli_function_call() {
             "usage": {
                 "input_tokens": 3,
                 "output_tokens": 7,
-                "total_tokens": 10
+                "total_tokens": 10,
+                "output_tokens_details": {
+                    "reasoning_tokens": 2
+                }
             }
         })
     );