feat: support image inputs in assistant tests

backend/test_schemas.py

@@ -143,20 +143,36 @@ ExpectedBehavior = Annotated[
 ]
 
 
-class FixedInputTurn(CamelModel):
-    id: str = Field(min_length=1, max_length=128)
-    user_input: str = Field(min_length=1, max_length=20_000)
-    behaviors: list[ExpectedBehavior] = Field(default_factory=list, max_length=100)
+class TestImageRef(CamelModel):
+    asset_id: str = Field(min_length=1, max_length=40)
+    filename: str = Field(default="image.jpg", max_length=255)
+    width: int = Field(ge=1)
+    height: int = Field(ge=1)
+    size_bytes: int = Field(default=0, ge=0)
 
-    @field_validator("user_input")
+    @field_validator("asset_id", "filename")
     @classmethod
-    def strip_user_input(cls, value: str) -> str:
+    def strip_image_text(cls, value: str) -> str:
         value = value.strip()
         if not value:
-            raise ValueError("用户输入不能为空")
+            raise ValueError("图片资源信息不完整")
         return value
 
 
+class FixedInputTurn(CamelModel):
+    id: str = Field(min_length=1, max_length=128)
+    user_input: str = Field(default="", max_length=20_000)
+    image: TestImageRef | None = None
+    behaviors: list[ExpectedBehavior] = Field(default_factory=list, max_length=100)
+
+    @model_validator(mode="after")
+    def validate_input(self):
+        self.user_input = self.user_input.strip()
+        if not self.user_input and self.image is None:
+            raise ValueError("用户输入和图片至少填写一项")
+        return self
+
+
 class OverallCriterion(CamelModel):
     id: str = Field(min_length=1, max_length=128)
     type: Literal["llm"] = "llm"
@@ -272,7 +288,7 @@ class TestCaseWrite(CamelModel):
     @model_validator(mode="after")
     def validate_mvp_definition(self):
         if self.input_mode != "fixed_script_text":
-            raise ValueError("第一版只支持固定脚本 · 文字")
+            raise ValueError("第一版只支持固定脚本 · 多模态")
         TestCaseDefinition(
             context_turns=self.context_turns,
             turns=self.turns,
@@ -362,6 +378,7 @@ class BatchTurnResult(CamelModel):
     id: str
     index: int
     user_input: str
+    image: TestImageRef | None = None
     assistant_reply: str
     tool_calls: list[BatchToolCallRecord] = Field(default_factory=list)
     runtime_records: list[dict[str, Any]] = Field(default_factory=list)