feat: support image inputs in assistant tests

backend/routes/test_runs.py

@@ -18,6 +18,8 @@ from fastapi import APIRouter, Depends, HTTPException
 from services.auth import require_admin
 from services.config_resolver import resolve_runtime_config
 from services.runtime_variables import DynamicVariableError, prepare_dynamic_config
+from services.realtime.launcher import validate_visual_runtime
+from services.test_case_assets import canonicalize_test_assets, image_asset_ids
 from services.test_runs.orchestrator import test_run_orchestrator
 from sqlalchemy import select
 from sqlalchemy.ext.asyncio import AsyncSession
@@ -140,13 +142,18 @@ async def create_test_run(
         raise HTTPException(422, "测试用例不存在: " + "、".join(missing))
     ordered_cases = [by_id[case_id] for case_id in body.case_ids]
     tools_by_id = {tool.id: tool for tool in runtime_config.tools}
+    definitions_by_id: dict[str, TestCaseDefinition] = {}
+    has_image_input = False
     for row in ordered_cases:
         if row.input_mode != "fixed_script_text":
-            raise HTTPException(422, f"用例“{row.name}”不是可运行的固定文字模式")
+            raise HTTPException(422, f"用例“{row.name}”不是可运行的固定多模态模式")
         try:
             definition = TestCaseDefinition.model_validate(row.definition or {})
+            await canonicalize_test_assets(session, definition)
         except ValueError as exc:
             raise HTTPException(422, f"用例“{row.name}”校验失败: {exc}") from exc
+        definitions_by_id[row.id] = definition
+        has_image_input = has_image_input or bool(image_asset_ids(definition))
         for turn in definition.turns:
             for behavior in turn.behaviors:
                 if behavior.type != "tool_call":
@@ -159,6 +166,14 @@ async def create_test_run(
                         "不属于当前被测助手",
                     )
 
+    if has_image_input:
+        try:
+            vision_enabled = validate_visual_runtime(runtime_config)
+        except ValueError as exc:
+            raise HTTPException(422, str(exc)) from exc
+        if not vision_enabled:
+            raise HTTPException(422, "测试用例包含图片，但当前助手未开启视觉能力")
+
     suite_ids = list(dict.fromkeys(row.suite_id for row in ordered_cases))
     suites = (
         await session.execute(select(TestSuite).where(TestSuite.id.in_(suite_ids)))
@@ -192,7 +207,7 @@ async def create_test_run(
     )
     session.add(run)
     for position, row in enumerate(ordered_cases):
-        definition = TestCaseDefinition.model_validate(row.definition or {})
+        definition = definitions_by_id[row.id]
         snapshot = {
             "id": row.id,
             "suiteId": row.suite_id,