feat(testing): add fixed tool simulations

backend/services/test_runs/text_runner.py

@@ -21,7 +21,6 @@ from pipecat.frames.frames import (
     ErrorFrame,
     FunctionCallInProgressFrame,
     FunctionCallResultFrame,
-    LLMContextFrame,
     LLMFullResponseEndFrame,
     LLMFullResponseStartFrame,
     LLMMessagesAppendFrame,
@@ -54,7 +53,13 @@ from services.pipecat.processors import (
 from services.pipecat.service_factory import config_with_resource
 from services.pipecat.workflow_services import build_workflow_llm_switcher
 from services.test_runs.errors import TestExecutionError
-from services.test_runs.mock_tools import MockToolExecutor, TextClientToolPort
+from services.test_runs.mock_tools import (
+    TOOL_SIMULATION_ERROR_CODES,
+    MockToolExecutor,
+    TextClientToolPort,
+    ToolSimulationError,
+    ToolSimulationResolver,
+)
 from services.vision import build_image_user_message
 from test_schemas import ContextTurn, FixedInputTurn, TestCaseDefinition, TestImageRef
 
@@ -197,18 +202,21 @@ class _TextCaptureProcessor(FrameProcessor):
         """Release every wait even when Pipecat reports the error upstream."""
 
         message = frame.error or "Pipeline 执行失败"
-        unmocked_tool = "UNMOCKED_TOOL_CALL" in message
+        simulation_code = next(
+            (code for code in TOOL_SIMULATION_ERROR_CODES if code in message),
+            None,
+        )
         self.error = TestExecutionError(
-            code="UNMOCKED_TOOL_CALL" if unmocked_tool else "PIPELINE_ERROR",
+            code=simulation_code or "PIPELINE_ERROR",
             message=message,
             stage=(
                 "tool"
-                if unmocked_tool
+                if simulation_code
                 else "model"
                 if frame.processor
                 else "pipeline"
             ),
-            retryable=not unmocked_tool,
+            retryable=simulation_code is None,
         )
         self.window.pending_tools.clear()
         self.window.touch()
@@ -573,14 +581,12 @@ class TextPipelineRunner:
         async def on_pipeline_error(_worker, frame):
             capture.fail(frame)
 
-        executor_holder: dict[str, MockToolExecutor] = {}
-        text_client_tools = TextClientToolPort()
+        simulation_resolver = ToolSimulationResolver(definition.tool_simulations)
+        text_client_tools = TextClientToolPort(simulation_resolver)
         workflow_vision_scope: dict[str, Any] = {"enabled": False}
 
         def create_test_executor(store) -> MockToolExecutor:
-            executor = MockToolExecutor(store)
-            executor_holder["executor"] = executor
-            return executor
+            return MockToolExecutor(store, simulation_resolver)
 
         async def queue_call_end(reason: str) -> None:
             logger.debug(f"文本测试收到会话结束请求: {reason}")
@@ -738,8 +744,6 @@ class TextPipelineRunner:
                 tool_executor_factory=create_test_executor,
             ),
         )
-        executor = executor_holder["executor"]
-
         # A transportless text run cannot synthesize audio, but the configured
         # greeting has already completed before scripted inputs begin. Mirror
         # production's provider-safe context fact so the model does not repeat it.
@@ -772,25 +776,11 @@ class TextPipelineRunner:
                 # response is therefore the equivalent of playback ending.
                 await call_end.finish()
 
-        all_tool_behaviors = [
-            behavior
-            for turn in definition.turns
-            for behavior in turn.behaviors
-            if behavior.type == "tool_call"
-        ]
-        executor.set_turn_behaviors(all_tool_behaviors)
-
         runner_task: asyncio.Task[None] | None = None
         try:
             startup_runtime_record_marker = len(capture.runtime_records)
+            simulation_resolver.enter_startup()
             await brain.run_preflight()
-            if executor.unmocked_calls:
-                raise TestExecutionError(
-                    code="UNMOCKED_TOOL_CALL",
-                    message="启动阶段调用了未配置 Mock 的工具: "
-                    + "、".join(executor.unmocked_calls),
-                    stage="tool",
-                )
 
             await runner.add_workers(worker)
             runner_task = asyncio.create_task(
@@ -803,12 +793,14 @@ class TextPipelineRunner:
             marker = capture.window.activity_count
             await brain.on_connected(greeting_pending=False)
             await brain.on_client_ready()
+            simulation_resolver.raise_if_failed()
             await _wait_for_startup(
                 worker,
                 capture,
                 runner_task,
                 marker,
             )
+            simulation_resolver.raise_if_failed()
             startup_greeting = _resolve_startup_greeting(
                 greeting,
                 capture.opening_speech_outputs,
@@ -844,7 +836,7 @@ class TextPipelineRunner:
                     worker,
                     runner_task,
                     capture,
-                    executor,
+                    simulation_resolver,
                     turn,
                     index,
                     image_assets=image_assets,
@@ -873,9 +865,24 @@ class TextPipelineRunner:
             )
         except TestExecutionError:
             raise
+        except ToolSimulationError as exc:
+            raise TestExecutionError(
+                code=exc.code,
+                message=str(exc),
+                stage="tool",
+                retryable=False,
+            ) from exc
         except asyncio.CancelledError:
             raise
         except Exception as exc:
+            if simulation_resolver.failure is not None:
+                error = simulation_resolver.failure
+                raise TestExecutionError(
+                    code=error.code,
+                    message=str(error),
+                    stage="tool",
+                    retryable=False,
+                ) from exc
             raise TestExecutionError(
                 code="PIPELINE_EXECUTION_FAILED",
                 message=str(exc) or type(exc).__name__,
@@ -894,17 +901,14 @@ class TextPipelineRunner:
         worker: PipelineWorker,
         runner_task: asyncio.Task[None],
         capture: _TextCaptureProcessor,
-        executor: MockToolExecutor,
+        simulation_resolver: ToolSimulationResolver,
         turn: FixedInputTurn,
         index: int,
         *,
         image_assets: dict[str, bytes],
         workflow_vision_scope: dict[str, Any],
     ) -> RawTurnResult:
-        tool_behaviors = [
-            behavior for behavior in turn.behaviors if behavior.type == "tool_call"
-        ]
-        executor.set_turn_behaviors(tool_behaviors)
+        simulation_resolver.enter_turn(turn.id)
         activity_marker = capture.window.activity_count
         output_marker = len(capture.outputs)
         tool_marker = len(capture.tool_calls)
@@ -942,13 +946,7 @@ class TextPipelineRunner:
             LLMMessagesAppendFrame(messages=[user_message], run_llm=True)
         )
         await _wait_for_quiescence(capture, runner_task, activity_marker)
-        if executor.unmocked_calls:
-            raise TestExecutionError(
-                code="UNMOCKED_TOOL_CALL",
-                message="本轮调用了未配置 Mock 的工具: "
-                + "、".join(executor.unmocked_calls),
-                stage="tool",
-            )
+        simulation_resolver.raise_if_failed()
         return RawTurnResult(
             id=turn.id,
             index=index,