feat: support image inputs in assistant tests

backend/services/test_runs/orchestrator.py

@@ -14,6 +14,7 @@ from db.session import SessionLocal
 from models import RuntimeModelResource
 from services.config_resolver import resolve_runtime_config
 from services.runtime_variables import prepare_dynamic_config
+from services.test_case_assets import load_test_asset_bytes
 from services.test_runs.errors import TestExecutionError
 from services.test_runs.evaluator import EvaluationEngine
 from services.test_runs.text_runner import (
@@ -178,6 +179,19 @@ class TestRunOrchestrator:
                 snapshot = dict(row.case_snapshot or {})
                 definition = TestCaseDefinition.model_validate(snapshot)
                 max_attempts = row.max_attempts
+                try:
+                    image_assets = await load_test_asset_bytes(session, definition)
+                except Exception as exc:
+                    await self._mark_error(
+                        run_case_id,
+                        TestExecutionError(
+                            code="TEST_IMAGE_READ_FAILED",
+                            message=str(exc) or "测试图片无法读取",
+                            stage="pipeline",
+                            retryable=True,
+                        ),
+                    )
+                    return
 
             for attempt in range(1, max_attempts + 1):
                 if control.stop_event.is_set():
@@ -212,6 +226,7 @@ class TestRunOrchestrator:
                             attempt_cfg,
                             definition,
                             timeout_seconds=timeout_seconds,
+                            image_assets=image_assets,
                             on_turn_complete=save_turn_progress,
                             on_startup_complete=save_startup_progress,
                         )
@@ -346,6 +361,11 @@ class TestRunOrchestrator:
                 "id": turn.id,
                 "index": turn.index,
                 "userInput": turn.user_input,
+                "image": (
+                    turn.image.model_dump(mode="json", by_alias=True)
+                    if turn.image is not None
+                    else None
+                ),
                 "assistantReply": turn.assistant_reply,
                 "toolCalls": [item.as_result() for item in turn.tool_calls],
                 "runtimeRecords": list(turn.runtime_records),