from __future__ import annotations import unittest from types import SimpleNamespace from models import AssistantConfig from services.brains.base import RealtimeBrainRuntime from services.node_specs import validate_graph from services.vision import ( VISION_SYSTEM_HINT, resolve_vision_question, vision_system_hint, vision_tool_schema_parts, ) from services.workflow_engine import WorkflowEngine from services.workflow.realtime import WorkflowRealtimeController def workflow_settings(**overrides): settings = { "runtimeMode": "pipeline", "llmRoutingMode": "llm_router", "globalPrompt": "", "defaultRealtimeResourceId": "", "defaultLlmResourceId": "", "defaultAsrResourceId": "", "defaultTtsResourceId": "", "visionEnabled": False, "visionModelResourceId": "", "visionPromptMode": "runtime", "visionPrompt": "", "toolBindings": [], "builtInTools": {}, "knowledgeBaseId": "", "knowledgeMode": "disabled", "knowledgeTopN": 5, "knowledgeScoreThreshold": 0.0, "enableInterrupt": True, "turnConfig": { "bargeIn": {"strategy": "vad"}, "turnDetection": {"strategy": "smart_turn"}, }, } settings.update(overrides) return settings class VisionPromptModeTest(unittest.TestCase): def test_fixed_mode_has_no_runtime_question_parameter(self): description, properties, required = vision_tool_schema_parts( "fixed", "识别车辆数量和人员状态", ) self.assertIn("识别车辆数量和人员状态", description) self.assertEqual(properties, {}) self.assertEqual(required, []) self.assertEqual( resolve_vision_question("fixed", " 识别车辆数量 ", {}), "识别车辆数量", ) def test_runtime_mode_requires_model_generated_question(self): description, properties, required = vision_tool_schema_parts("runtime") self.assertNotIn("固定引导", description) self.assertIn("question", properties) self.assertEqual(required, ["question"]) self.assertEqual( resolve_vision_question( "runtime", "不会使用这个配置", {"question": "用户手里拿着什么？"}, ), "用户手里拿着什么？", ) def test_guided_mode_exposes_guide_but_uses_runtime_question(self): guide = "只询问画面中可直接确认的车辆损伤" description, properties, required = vision_tool_schema_parts( "guided", guide, ) self.assertIn(guide, description) self.assertIn(guide, properties["question"]["description"]) self.assertEqual(required, ["question"]) self.assertEqual( resolve_vision_question( "guided", guide, {"question": "右侧车门是否有明显凹陷？"}, ), "右侧车门是否有明显凹陷？", ) def test_mode_specific_system_hints(self): self.assertIn(VISION_SYSTEM_HINT, vision_system_hint("runtime")) self.assertIn("不需要生成", vision_system_hint("fixed", "固定问题")) self.assertIn("固定引导", vision_system_hint("guided", "业务引导")) def test_missing_required_config_or_question_is_rejected(self): with self.assertRaisesRegex(ValueError, "固定视觉提示词为空"): resolve_vision_question("fixed", "", {}) with self.assertRaisesRegex(ValueError, "视觉问题为空"): resolve_vision_question("runtime", "", {}) class WorkflowVisionPromptModeTest(unittest.TestCase): def test_workflow_resolves_global_and_node_modes(self): graph = { "specVersion": 4, "settings": workflow_settings( **{ "visionEnabled": True, "visionPromptMode": "fixed", "visionPrompt": "全局固定问题", } ), "nodes": [ { "id": "global-agent", "type": "agent", "data": {"name": "全局 Agent", "prompt": "处理任务"}, }, { "id": "custom-agent", "type": "agent", "data": { "name": "独立 Agent", "prompt": "检查车辆", "inheritGlobalConfig": False, "visionEnabled": True, "visionPromptMode": "guided", "visionPrompt": "节点引导", }, }, ], "edges": [], } engine = WorkflowEngine(graph) global_stage = engine.agent_stage_config("global-agent") self.assertEqual(global_stage.vision_prompt_mode, "fixed") self.assertEqual(global_stage.vision_prompt, "全局固定问题") custom_stage = engine.agent_stage_config("custom-agent") self.assertEqual(custom_stage.vision_prompt_mode, "guided") self.assertEqual(custom_stage.vision_prompt, "节点引导") def test_fixed_or_guided_mode_requires_prompt_when_vision_is_enabled(self): graph = { "specVersion": 4, "settings": workflow_settings( **{ "visionEnabled": True, "visionPromptMode": "fixed", "visionPrompt": "", } ), "nodes": [ {"id": "start", "type": "start", "data": {}}, { "id": "agent", "type": "agent", "data": { "name": "Agent", "prompt": "处理任务", "inheritGlobalConfig": True, "entryMode": "wait_user", }, } ], "edges": [ { "id": "begin", "source": "start", "target": "agent", "data": {"mode": "always", "priority": 0}, } ], } self.assertTrue( any("必须填写视觉提示词" in error for error in validate_graph(graph)) ) def test_invalid_mode_is_reported_instead_of_silently_rewritten(self): graph = { "specVersion": 4, "settings": workflow_settings(visionPromptMode="unexpected"), "nodes": [ {"id": "start", "type": "start", "data": {}}, { "id": "agent", "type": "agent", "data": { "name": "Agent", "prompt": "处理任务", "inheritGlobalConfig": True, "entryMode": "wait_user", }, } ], "edges": [ { "id": "begin", "source": "start", "target": "agent", "data": {"mode": "always", "priority": 0}, } ], } self.assertTrue( any("视觉提示词模式无效" in error for error in validate_graph(graph)) ) def test_realtime_tool_contract_changes_with_mode(self): graph = { "specVersion": 4, "settings": workflow_settings(), "nodes": [ { "id": "fixed-agent", "type": "agent", "data": { "name": "固定", "prompt": "处理任务", "inheritGlobalConfig": False, "visionEnabled": True, "visionPromptMode": "fixed", "visionPrompt": "检查安全帽", }, }, { "id": "guided-agent", "type": "agent", "data": { "name": "引导", "prompt": "处理任务", "inheritGlobalConfig": False, "visionEnabled": True, "visionPromptMode": "guided", "visionPrompt": "只询问安全设备", }, }, ], "edges": [], } engine = WorkflowEngine(graph) controller = WorkflowRealtimeController( cfg=AssistantConfig(type="workflow"), engine=engine, store=SimpleNamespace(), runtime=RealtimeBrainRuntime( realtime=SimpleNamespace(), queue_frame=lambda _frame: None, call_end=SimpleNamespace(ending=False), ), ) fixed_tool, _fixed_handler = controller._vision_tool("fixed-agent", 0) guided_tool, _guided_handler = controller._vision_tool("guided-agent", 0) self.assertEqual(fixed_tool.properties, {}) self.assertEqual(fixed_tool.required, ()) self.assertIn("只询问安全设备", guided_tool.description) self.assertEqual(guided_tool.required, ("question",)) if __name__ == "__main__": unittest.main()