feat: support image inputs in assistant tests

backend/services/vision.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import asyncio
 import base64
+from dataclasses import dataclass
 from io import BytesIO
 from typing import Any
 
@@ -30,6 +31,14 @@ VISION_ANALYSIS_SYSTEM_PROMPT = (
 )
 
 
+@dataclass(frozen=True)
+class VisionInputResolution:
+    """The active model path for one explicit user image turn."""
+
+    native: bool
+    config: AssistantConfig
+
+
 def _require(value: str, label: str) -> str:
     if value:
         return value
@@ -246,3 +255,83 @@ def config_with_main_llm_as_vision(cfg: AssistantConfig) -> AssistantConfig:
     result.vision_llm_api_key = cfg.llm_api_key
     result.vision_llm_base_url = cfg.llm_base_url
     return result
+
+
+def resolve_vision_input(
+    cfg: AssistantConfig,
+    workflow_scope: dict[str, Any] | None = None,
+) -> VisionInputResolution:
+    """Resolve native versus auxiliary vision using the active runtime scope."""
+
+    if cfg.type != "workflow":
+        if not cfg.vision_enabled:
+            raise ValueError("当前助手未开启视觉能力")
+        if cfg.vision_model_resource_id:
+            if not cfg.vision_llm_support_image_input:
+                raise ValueError("当前视觉模型不支持图片输入")
+            return VisionInputResolution(native=False, config=cfg)
+        if not cfg.llm_support_image_input:
+            raise ValueError("当前大语言模型不支持图片输入")
+        return VisionInputResolution(native=True, config=cfg)
+
+    scope = workflow_scope or {}
+    if not scope.get("enabled"):
+        raise ValueError("当前 Workflow Agent 节点未启用视觉能力")
+    vision_resource_id = str(scope.get("vision_model_resource_id") or "")
+    llm_resource_id = str(scope.get("llm_resource_id") or "")
+    resource_id = vision_resource_id or llm_resource_id
+    resource = cfg.workflow_model_resources.get(resource_id)
+    if resource is not None:
+        if not resource.support_image_input:
+            raise ValueError(f"当前视觉模型不支持图片输入: {resource.id}")
+        result = config_with_vision_resource(cfg, resource)
+    elif not vision_resource_id:
+        result = config_with_main_llm_as_vision(cfg)
+    else:
+        raise ValueError(f"视觉模型资源未加载: {vision_resource_id}")
+
+    result.vision_prompt_mode = normalize_vision_prompt_mode(
+        scope.get("vision_prompt_mode")
+    )
+    result.vision_prompt = str(scope.get("vision_prompt") or "").strip()
+    return VisionInputResolution(
+        native=not bool(vision_resource_id),
+        config=result,
+    )
+
+
+async def build_image_user_message(
+    cfg: AssistantConfig,
+    image_bytes: bytes,
+    prompt_text: str,
+    *,
+    workflow_scope: dict[str, Any] | None = None,
+) -> dict[str, Any]:
+    """Build the same model-facing user message used by an explicit photo turn."""
+
+    question = prompt_text.strip() or "请根据用户刚提交的图片进行回复。"
+    frame = await asyncio.to_thread(image_frame_from_jpeg, image_bytes)
+    resolution = resolve_vision_input(cfg, workflow_scope)
+    if resolution.native:
+        data_uri = await asyncio.to_thread(image_data_uri, frame)
+        return {
+            "role": "user",
+            "content": [
+                {"type": "text", "text": question},
+                {"type": "image_url", "image_url": {"url": data_uri}},
+            ],
+        }
+
+    observation = await analyze_image_with_vision_model(
+        resolution.config,
+        frame,
+        question,
+    )
+    return {
+        "role": "user",
+        "content": (
+            f"{question}\n\n"
+            "[视觉模型对用户刚提交图片的观察]\n"
+            f"{observation or '视觉模型没有返回有效观察结果。'}"
+        ),
+    }