Add conversation history management and API endpoints

- Introduce new database models for conversation sessions, messages, and artifacts to support conversation history tracking.
- Implement API routes for listing conversations and retrieving detailed conversation data, enhancing user interaction with historical records.
- Add a conversation recorder service to persist conversation messages in real-time without disrupting ongoing calls.
- Update the frontend to display conversation history, including filtering and sorting options, improving user experience.
- Enhance the pipeline to integrate conversation history recording seamlessly during interactions.

backend/schemas.py

@@ -7,6 +7,7 @@ JSON 用 camelCase(modelId/interfaceType/apiUrl/apiKey),Python 内部用 snake_c
 
 from __future__ import annotations
 
+from datetime import datetime
 from typing import Annotated, Any, Literal, Union
 
 from pydantic import BaseModel, ConfigDict, Field, field_validator, model_validator
@@ -199,3 +200,37 @@ class ModelResourceTestResult(CamelModel):
     latency_ms: int | None = None
     message: str
     detail: str = ""
+
+
+# ---------- 对话历史 ----------
+class ConversationMessageOut(CamelModel):
+    id: str
+    sequence: int
+    role: Literal["user", "assistant"]
+    content_type: str
+    content: str
+    occurred_at: datetime
+    extra: dict[str, Any] = Field(default_factory=dict)
+
+
+class ConversationOut(CamelModel):
+    id: str
+    assistant_id: str | None
+    assistant_name: str
+    channel: str
+    runtime_mode: str
+    status: str
+    message_count: int
+    started_at: datetime
+    ended_at: datetime | None
+
+
+class ConversationDetailOut(ConversationOut):
+    messages: list[ConversationMessageOut] = Field(default_factory=list)
+
+
+class ConversationListOut(CamelModel):
+    items: list[ConversationOut]
+    total: int
+    page: int
+    page_size: int