feat(core): AI 生成 Agent 化 — 多模型流式脚本 agent + 可插拔 Provider + gpt-image-2 参考图 + 模特库

- 后端·可插拔 Provider 层:通用 OpenAICompatibleProvider(tokenssr 等中转站,base_url+api_key,零改代码换站)+ ModelProvider.api_key
- 后端·脚本 agent:结构化 ScriptDraft 契约 + 加载电商 skill + 出稿/改稿一体对话 agent(3模式/多模型)+ 流式 SSE 端点(DRF SSE renderer)
- 后端·图像:gpt-image-2 参考图出图 + 故事板 @图1@图2@图3 多锚点合成(锁脸锁商品);Seedance 打开 generate_audio
- 后端·模特库:gpt-image-2 生成器(9:16氛围图→16:9白底三视图)+ seed_demo_models 管理命令
- DB·迁移:tokenssr 中转站 + 多模型 seed(豆包/GPT-5.5/Gemini + gpt-image-2);ScriptSegment 结构化字段
- 前端·脚本趴:接真 SSE(工具卡 + 思考流)+ 模型下拉 + 3模式 + 改稿;agentScriptStream
- skills/ecommerce-video-script 电商脚本技能(运行时依赖)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

core/backend/apps/projects/serializers.py

@@ -228,7 +228,10 @@ class ExportJobSerializer(serializers.ModelSerializer):
 class ScriptSegmentSerializer(serializers.ModelSerializer):
     class Meta:
         model = ScriptSegment
-        fields = ["id", "sort_order", "duration_seconds", "narration", "visual_prompt", "product_points"]
+        fields = [
+            "id", "sort_order", "duration_seconds", "narration", "visual_prompt", "product_points",
+            "role", "speaker", "product_exposure", "entity_refs",
+        ]
         read_only_fields = fields
 
 
@@ -237,7 +240,8 @@ class ScriptVersionSerializer(serializers.ModelSerializer):
 
     class Meta:
         model = ScriptVersion
-        fields = ["id", "title", "content", "source", "is_adopted", "segments", "created_at", "updated_at"]
+        # metadata 携带 ScriptDraft 的 hook/tone/entities,供前端结构化渲染与下游故事板 @图N
+        fields = ["id", "title", "content", "source", "is_adopted", "segments", "metadata", "created_at", "updated_at"]
         read_only_fields = fields