Skip to content

prefect.engine

Client-side execution and orchestration of flows and tasks.

Engine process overview

  • The flow or task is called by the user. See Flow.__call__, Task.__call__

  • A synchronous engine function acts as an entrypoint to the async engine. See enter_flow_run_engine, enter_task_run_engine

  • The async engine creates a run via the API and prepares for execution of user-code. See begin_flow_run, begin_task_run

  • The run is orchestrated through states, calling the user's function as necessary. See orchestrate_flow_run, orchestrate_task_run

begin_flow_run async

Begins execution of a flow run; blocks until completion of the flow run

  • Starts a task runner
  • Determines the result storage block to use
  • Orchestrates the flow run (runs the user-function and generates tasks)
  • Waits for tasks to complete / shutsdown the task runner
  • Sets a terminal state for the flow run

Note that the flow_run contains a parameters attribute which is the serialized parameters sent to the backend while the parameters argument here should be the deserialized and validated dictionary of python objects.

Returns:

Type Description
State

The final state of the run

Source code in prefect/engine.py
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
async def begin_flow_run(
    flow: Flow,
    flow_run: FlowRun,
    parameters: Dict[str, Any],
    client: PrefectClient,
) -> State:
    """
    Begins execution of a flow run; blocks until completion of the flow run

    - Starts a task runner
    - Determines the result storage block to use
    - Orchestrates the flow run (runs the user-function and generates tasks)
    - Waits for tasks to complete / shutsdown the task runner
    - Sets a terminal state for the flow run

    Note that the `flow_run` contains a `parameters` attribute which is the serialized
    parameters sent to the backend while the `parameters` argument here should be the
    deserialized and validated dictionary of python objects.

    Returns:
        The final state of the run
    """
    logger = flow_run_logger(flow_run, flow)

    log_prints = should_log_prints(flow)
    flow_run_context = PartialModel(FlowRunContext, log_prints=log_prints)

    async with AsyncExitStack() as stack:
        await stack.enter_async_context(
            report_flow_run_crashes(flow_run=flow_run, client=client)
        )

        # Create a task group for background tasks
        flow_run_context.background_tasks = await stack.enter_async_context(
            anyio.create_task_group()
        )

        # If the flow is async, we need to provide a portal so sync tasks can run
        flow_run_context.sync_portal = (
            stack.enter_context(start_blocking_portal()) if flow.isasync else None
        )

        logger.debug(
            f"Starting {type(flow.task_runner).__name__!r}; submitted tasks "
            f"will be run {CONCURRENCY_MESSAGES[flow.task_runner.concurrency_type]}..."
        )
        flow_run_context.task_runner = await stack.enter_async_context(
            flow.task_runner.start()
        )

        flow_run_context.result_factory = await ResultFactory.from_flow(
            flow, client=client
        )

        flow_run_context.events = await stack.enter_async_context(
            async_get_events_worker()
        )

        if log_prints:
            stack.enter_context(patch_print())

        terminal_or_paused_state = await orchestrate_flow_run(
            flow,
            flow_run=flow_run,
            parameters=parameters,
            wait_for=None,
            client=client,
            partial_flow_run_context=flow_run_context,
            # Orchestration needs to be interruptible if it has a timeout
            interruptible=flow.timeout_seconds is not None,
        )

    if terminal_or_paused_state.is_paused():
        timeout = terminal_or_paused_state.state_details.pause_timeout
        logger.log(
            level=logging.INFO,
            msg=(
                "Currently paused and suspending execution. Resume before"
                f" {timeout.to_rfc3339_string()} to finish execution."
            ),
        )
        APILogHandler.flush(block=True)

        return terminal_or_paused_state
    else:
        terminal_state = terminal_or_paused_state

    # If debugging, use the more complete `repr` than the usual `str` description
    display_state = repr(terminal_state) if PREFECT_DEBUG_MODE else str(terminal_state)

    logger.log(
        level=logging.INFO if terminal_state.is_completed() else logging.ERROR,
        msg=f"Finished in state {display_state}",
    )

    # When a "root" flow run finishes, flush logs so we do not have to rely on handling
    # during interpreter shutdown
    APILogHandler.flush(block=True)

    return terminal_state

begin_task_map async

Async entrypoint for task mapping

Source code in prefect/engine.py
 973
 974
 975
 976
 977
 978
 979
 980
 981
 982
 983
 984
 985
 986
 987
 988
 989
 990
 991
 992
 993
 994
 995
 996
 997
 998
 999
1000
1001
1002
1003
1004
1005
1006
1007
1008
1009
1010
1011
1012
1013
1014
1015
1016
1017
1018
1019
1020
1021
1022
1023
1024
1025
1026
1027
1028
1029
1030
1031
1032
1033
1034
1035
1036
1037
1038
1039
1040
1041
1042
1043
1044
1045
1046
1047
1048
1049
async def begin_task_map(
    task: Task,
    flow_run_context: FlowRunContext,
    parameters: Dict[str, Any],
    wait_for: Optional[Iterable[PrefectFuture]],
    return_type: EngineReturnType,
    task_runner: Optional[BaseTaskRunner],
) -> List[Union[PrefectFuture, Awaitable[PrefectFuture]]]:
    """Async entrypoint for task mapping"""
    # We need to resolve some futures to map over their data, collect the upstream
    # links beforehand to retain relationship tracking.
    task_inputs = {
        k: await collect_task_run_inputs(v, max_depth=0) for k, v in parameters.items()
    }

    # Resolve the top-level parameters in order to get mappable data of a known length.
    # Nested parameters will be resolved in each mapped child where their relationships
    # will also be tracked.
    parameters = await resolve_inputs(parameters, max_depth=1)

    iterable_parameters = {}
    static_parameters = {}
    annotated_parameters = {}
    for key, val in parameters.items():
        if isinstance(val, allow_failure):
            # Unwrap annotated parameters to determine if they are iterable
            annotated_parameters[key] = val
            val = val.unwrap()

        if isinstance(val, unmapped):
            static_parameters[key] = val.value
        elif isiterable(val):
            iterable_parameters[key] = list(val)
        else:
            static_parameters[key] = val

    if not len(iterable_parameters):
        raise MappingMissingIterable(
            "No iterable parameters were received. Parameters for map must "
            f"include at least one iterable. Parameters: {parameters}"
        )

    iterable_parameter_lengths = {
        key: len(val) for key, val in iterable_parameters.items()
    }
    lengths = set(iterable_parameter_lengths.values())
    if len(lengths) > 1:
        raise MappingLengthMismatch(
            "Received iterable parameters with different lengths. Parameters for map"
            f" must all be the same length. Got lengths: {iterable_parameter_lengths}"
        )

    map_length = list(lengths)[0]

    task_runs = []
    for i in range(map_length):
        call_parameters = {key: value[i] for key, value in iterable_parameters.items()}
        call_parameters.update({key: value for key, value in static_parameters.items()})

        # Re-apply annotations to each key again
        for key, annotation in annotated_parameters.items():
            call_parameters[key] = annotation.rewrap(call_parameters[key])

        task_runs.append(
            partial(
                get_task_call_return_value,
                task=task,
                flow_run_context=flow_run_context,
                parameters=call_parameters,
                wait_for=wait_for,
                return_type=return_type,
                task_runner=task_runner,
                extra_task_inputs=task_inputs,
            )
        )

    return await gather(*task_runs)

begin_task_run async

Entrypoint for task run execution.

This function is intended for submission to the task runner.

This method may be called from a worker so we ensure the settings context has been entered. For example, with a runner that is executing tasks in the same event loop, we will likely not enter the context again because the current context already matches:

main thread: --> Flow called with settings A --> begin_task_run executes same event loop --> Profile A matches and is not entered again

However, with execution on a remote environment, we are going to need to ensure the settings for the task run are respected by entering the context:

main thread: --> Flow called with settings A --> begin_task_run is scheduled on a remote worker, settings A is serialized remote worker: --> Remote worker imports Prefect (may not occur) --> Global settings is loaded with default settings --> begin_task_run executes on a different event loop than the flow --> Current settings is not set or does not match, settings A is entered

Source code in prefect/engine.py
1275
1276
1277
1278
1279
1280
1281
1282
1283
1284
1285
1286
1287
1288
1289
1290
1291
1292
1293
1294
1295
1296
1297
1298
1299
1300
1301
1302
1303
1304
1305
1306
1307
1308
1309
1310
1311
1312
1313
1314
1315
1316
1317
1318
1319
1320
1321
1322
1323
1324
1325
1326
1327
1328
1329
1330
1331
1332
1333
1334
1335
1336
1337
1338
1339
1340
1341
1342
1343
1344
1345
1346
1347
1348
1349
1350
1351
1352
1353
1354
1355
1356
1357
1358
1359
1360
1361
1362
1363
1364
1365
1366
1367
1368
1369
1370
1371
1372
1373
1374
1375
1376
1377
1378
1379
1380
1381
1382
1383
1384
1385
1386
1387
1388
1389
1390
async def begin_task_run(
    task: Task,
    task_run: TaskRun,
    parameters: Dict[str, Any],
    wait_for: Optional[Iterable[PrefectFuture]],
    result_factory: ResultFactory,
    log_prints: bool,
    settings: prefect.context.SettingsContext,
):
    """
    Entrypoint for task run execution.

    This function is intended for submission to the task runner.

    This method may be called from a worker so we ensure the settings context has been
    entered. For example, with a runner that is executing tasks in the same event loop,
    we will likely not enter the context again because the current context already
    matches:

    main thread:
    --> Flow called with settings A
    --> `begin_task_run` executes same event loop
    --> Profile A matches and is not entered again

    However, with execution on a remote environment, we are going to need to ensure the
    settings for the task run are respected by entering the context:

    main thread:
    --> Flow called with settings A
    --> `begin_task_run` is scheduled on a remote worker, settings A is serialized
    remote worker:
    --> Remote worker imports Prefect (may not occur)
    --> Global settings is loaded with default settings
    --> `begin_task_run` executes on a different event loop than the flow
    --> Current settings is not set or does not match, settings A is entered
    """
    maybe_flow_run_context = prefect.context.FlowRunContext.get()

    async with AsyncExitStack() as stack:
        # The settings context may be null on a remote worker so we use the safe `.get`
        # method and compare it to the settings required for this task run
        if prefect.context.SettingsContext.get() != settings:
            stack.enter_context(settings)
            setup_logging()

        if maybe_flow_run_context:
            # Accessible if on a worker that is running in the same thread as the flow
            client = maybe_flow_run_context.client
            # Only run the task in an interruptible thread if it in the same thread as
            # the flow _and_ the flow run has a timeout attached. If the task is on a
            # worker, the flow run timeout will not be raised in the worker process.
            interruptible = maybe_flow_run_context.timeout_scope is not None
            background_tasks = maybe_flow_run_context.background_tasks
        else:
            # Otherwise, retrieve a new client
            client = await stack.enter_async_context(get_client())
            interruptible = False
            background_tasks = await stack.enter_async_context(
                anyio.create_task_group()
            )

        await stack.enter_async_context(report_task_run_crashes(task_run, client))

        # TODO: Use the background tasks group to manage logging for this task

        if log_prints:
            stack.enter_context(patch_print())

        connect_error = await client.api_healthcheck()
        if connect_error:
            raise RuntimeError(
                f"Cannot orchestrate task run '{task_run.id}'. "
                f"Failed to connect to API at {client.api_url}."
            ) from connect_error

        try:
            state = await orchestrate_task_run(
                task=task,
                task_run=task_run,
                parameters=parameters,
                wait_for=wait_for,
                result_factory=result_factory,
                log_prints=log_prints,
                interruptible=interruptible,
                client=client,
            )

            if not maybe_flow_run_context:
                # When a a task run finishes on a remote worker flush logs to prevent
                # loss if the process exits
                APILogHandler.flush(block=True)

        except Abort as abort:
            # Task run probably already completed, fetch its state
            task_run = await client.read_task_run(task_run.id)

            if task_run.state.is_final():
                task_run_logger(task_run).info(
                    f"Task run '{task_run.id}' already finished."
                )
            else:
                # TODO: This is a concerning case; we should determine when this occurs
                #       1. This can occur when the flow run is not in a running state
                task_run_logger(task_run).warning(
                    f"Task run '{task_run.id}' received abort during orchestration: "
                    f"{abort} Task run is in {task_run.state.type.value} state."
                )
            state = task_run.state

        except Pause:
            task_run_logger(task_run).info(
                "Task run encountered a pause signal during orchestration."
            )
            state = Paused()

        return state

collect_task_run_inputs async

This function recurses through an expression to generate a set of any discernable task run inputs it finds in the data structure. It produces a set of all inputs found.

Example

task_inputs = { k: await collect_task_run_inputs(v) for k, v in parameters.items() }

Source code in prefect/engine.py
1052
1053
1054
1055
1056
1057
1058
1059
1060
1061
1062
1063
1064
1065
1066
1067
1068
1069
1070
1071
1072
1073
1074
1075
1076
1077
1078
1079
1080
1081
1082
1083
1084
1085
1086
1087
async def collect_task_run_inputs(expr: Any, max_depth: int = -1) -> Set[TaskRunInput]:
    """
    This function recurses through an expression to generate a set of any discernable
    task run inputs it finds in the data structure. It produces a set of all inputs
    found.

    Example:
        >>> task_inputs = {
        >>>    k: await collect_task_run_inputs(v) for k, v in parameters.items()
        >>> }
    """
    # TODO: This function needs to be updated to detect parameters and constants

    inputs = set()

    def add_futures_and_states_to_inputs(obj):
        if isinstance(obj, PrefectFuture):
            run_async_from_worker_thread(obj._wait_for_submission)
            inputs.add(TaskRunResult(id=obj.task_run.id))
        elif isinstance(obj, State):
            if obj.state_details.task_run_id:
                inputs.add(TaskRunResult(id=obj.state_details.task_run_id))
        else:
            state = get_state_for_result(obj)
            if state and state.state_details.task_run_id:
                inputs.add(TaskRunResult(id=state.state_details.task_run_id))

    await run_sync_in_worker_thread(
        visit_collection,
        expr,
        visit_fn=add_futures_and_states_to_inputs,
        return_data=False,
        max_depth=max_depth,
    )

    return inputs

create_and_begin_subflow_run async

Async entrypoint for flows calls within a flow run

Subflows differ from parent flows in that they - Resolve futures in passed parameters into values - Create a dummy task for representation in the parent flow - Retrieve default result storage from the parent flow rather than the server

Returns:

Type Description
Any

The final state of the run

Source code in prefect/engine.py
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
@inject_client
async def create_and_begin_subflow_run(
    flow: Flow,
    parameters: Dict[str, Any],
    wait_for: Optional[Iterable[PrefectFuture]],
    return_type: EngineReturnType,
    client: PrefectClient,
) -> Any:
    """
    Async entrypoint for flows calls within a flow run

    Subflows differ from parent flows in that they
    - Resolve futures in passed parameters into values
    - Create a dummy task for representation in the parent flow
    - Retrieve default result storage from the parent flow rather than the server

    Returns:
        The final state of the run
    """
    parent_flow_run_context = FlowRunContext.get()
    parent_logger = get_run_logger(parent_flow_run_context)
    log_prints = should_log_prints(flow)

    parent_logger.debug(f"Resolving inputs to {flow.name!r}")
    task_inputs = {k: await collect_task_run_inputs(v) for k, v in parameters.items()}

    if wait_for:
        task_inputs["wait_for"] = await collect_task_run_inputs(wait_for)

    rerunning = parent_flow_run_context.flow_run.run_count > 1

    # Generate a task in the parent flow run to represent the result of the subflow run
    dummy_task = Task(name=flow.name, fn=flow.fn, version=flow.version)
    parent_task_run = await client.create_task_run(
        task=dummy_task,
        flow_run_id=parent_flow_run_context.flow_run.id,
        dynamic_key=_dynamic_key_for_task_run(parent_flow_run_context, dummy_task),
        task_inputs=task_inputs,
        state=Pending(),
    )

    # Resolve any task futures in the input
    parameters = await resolve_inputs(parameters)

    if parent_task_run.state.is_final() and not (
        rerunning and not parent_task_run.state.is_completed()
    ):
        # Retrieve the most recent flow run from the database
        flow_runs = await client.read_flow_runs(
            flow_run_filter=FlowRunFilter(
                parent_task_run_id={"any_": [parent_task_run.id]}
            ),
            sort=FlowRunSort.EXPECTED_START_TIME_ASC,
        )
        flow_run = flow_runs[-1]

        # Set up variables required downstream
        terminal_state = flow_run.state
        logger = flow_run_logger(flow_run, flow)

    else:
        flow_run = await client.create_flow_run(
            flow,
            parameters=flow.serialize_parameters(parameters),
            parent_task_run_id=parent_task_run.id,
            state=parent_task_run.state if not rerunning else Pending(),
            tags=TagsContext.get().current_tags,
        )

        parent_logger.info(
            f"Created subflow run {flow_run.name!r} for flow {flow.name!r}"
        )
        logger = flow_run_logger(flow_run, flow)
        result_factory = await ResultFactory.from_flow(
            flow, client=parent_flow_run_context.client
        )

        if flow.should_validate_parameters:
            failed_state = None
            try:
                parameters = flow.validate_parameters(parameters)
            except Exception:
                message = "Validation of flow parameters failed with error:"
                logger.exception(message)
                failed_state = await exception_to_failed_state(
                    message=message, result_factory=result_factory
                )

            if failed_state is not None:
                await propose_state(
                    client,
                    state=failed_state,
                    flow_run_id=flow_run.id,
                )
                return failed_state

        async with AsyncExitStack() as stack:
            await stack.enter_async_context(
                report_flow_run_crashes(flow_run=flow_run, client=client)
            )
            task_runner = await stack.enter_async_context(flow.task_runner.start())

            if log_prints:
                stack.enter_context(patch_print())

            terminal_state = await orchestrate_flow_run(
                flow,
                flow_run=flow_run,
                parameters=parameters,
                wait_for=wait_for,
                # If the parent flow run has a timeout, then this one needs to be
                # interruptible as well
                interruptible=parent_flow_run_context.timeout_scope is not None,
                client=client,
                partial_flow_run_context=PartialModel(
                    FlowRunContext,
                    sync_portal=parent_flow_run_context.sync_portal,
                    task_runner=task_runner,
                    background_tasks=parent_flow_run_context.background_tasks,
                    result_factory=result_factory,
                    log_prints=log_prints,
                ),
            )

    # Display the full state (including the result) if debugging
    display_state = repr(terminal_state) if PREFECT_DEBUG_MODE else str(terminal_state)
    logger.log(
        level=logging.INFO if terminal_state.is_completed() else logging.ERROR,
        msg=f"Finished in state {display_state}",
    )

    # Track the subflow state so the parent flow can use it to determine its final state
    parent_flow_run_context.flow_run_states.append(terminal_state)

    if return_type == "state":
        return terminal_state
    elif return_type == "result":
        return await terminal_state.result(fetch=True)
    else:
        raise ValueError(f"Invalid return type for flow engine {return_type!r}.")

create_then_begin_flow_run async

Async entrypoint for flow calls

Creates the flow run in the backend, then enters the main flow run engine.

Source code in prefect/engine.py
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
@inject_client
async def create_then_begin_flow_run(
    flow: Flow,
    parameters: Dict[str, Any],
    wait_for: Optional[Iterable[PrefectFuture]],
    return_type: EngineReturnType,
    client: PrefectClient,
) -> Any:
    """
    Async entrypoint for flow calls

    Creates the flow run in the backend, then enters the main flow run engine.
    """
    # TODO: Returns a `State` depending on `return_type` and we can add an overload to
    #       the function signature to clarify this eventually.

    connect_error = await client.api_healthcheck()
    if connect_error:
        raise RuntimeError(
            f"Cannot create flow run. Failed to reach API at {client.api_url}."
        ) from connect_error
    state = Pending()
    if flow.should_validate_parameters:
        try:
            parameters = flow.validate_parameters(parameters)
        except Exception:
            state = await exception_to_failed_state(
                message="Validation of flow parameters failed with error:"
            )

    flow_run = await client.create_flow_run(
        flow,
        # Send serialized parameters to the backend
        parameters=flow.serialize_parameters(parameters),
        state=state,
        tags=TagsContext.get().current_tags,
    )

    engine_logger.info(f"Created flow run {flow_run.name!r} for flow {flow.name!r}")

    if state.is_failed():
        flow_run_logger(flow_run).error(state.message)
        engine_logger.info(
            f"Flow run {flow_run.name!r} received invalid parameters and is marked as"
            " failed."
        )
    else:
        state = await begin_flow_run(
            flow=flow, flow_run=flow_run, parameters=parameters, client=client
        )

    if return_type == "state":
        return state
    elif return_type == "result":
        return await state.result(fetch=True)
    else:
        raise ValueError(f"Invalid return type for flow engine {return_type!r}.")

enter_flow_run_engine_from_flow_call

Sync entrypoint for flow calls.

This function does the heavy lifting of ensuring we can get into an async context for flow run execution with minimal overhead.

Source code in prefect/engine.py
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
def enter_flow_run_engine_from_flow_call(
    flow: Flow,
    parameters: Dict[str, Any],
    wait_for: Optional[Iterable[PrefectFuture]],
    return_type: EngineReturnType,
) -> Union[State, Awaitable[State]]:
    """
    Sync entrypoint for flow calls.

    This function does the heavy lifting of ensuring we can get into an async context
    for flow run execution with minimal overhead.
    """
    setup_logging()

    registry = PrefectObjectRegistry.get()
    if registry and registry.block_code_execution:
        engine_logger.warning(
            f"Script loading is in progress, flow {flow.name!r} will not be executed."
            " Consider updating the script to only call the flow if executed"
            f' directly:\n\n\tif __name__ == "main":\n\t\t{flow.fn.__name__}()'
        )
        return None

    if TaskRunContext.get():
        raise RuntimeError(
            "Flows cannot be run from within tasks. Did you mean to call this "
            "flow in a flow?"
        )

    parent_flow_run_context = FlowRunContext.get()
    is_subflow_run = parent_flow_run_context is not None

    if wait_for is not None and not is_subflow_run:
        raise ValueError("Only flows run as subflows can wait for dependencies.")

    begin_run = partial(
        create_and_begin_subflow_run if is_subflow_run else create_then_begin_flow_run,
        flow=flow,
        parameters=parameters,
        wait_for=wait_for,
        return_type=return_type,
        client=parent_flow_run_context.client if is_subflow_run else None,
    )

    if not is_subflow_run:
        # Async flow run
        if flow.isasync:
            return begin_run()  # Return a coroutine for the user to await
        # Sync flow run
        elif in_async_main_thread():
            # An event loop is already running and we must create a blocking portal to
            # run async code from this synchronous context
            with start_blocking_portal() as portal:
                return portal.call(begin_run)
        else:
            # An event loop is not running so we will create one
            return anyio.run(begin_run)

    if not parent_flow_run_context.flow.isasync:
        # Async subflow run in sync flow run
        return run_async_from_worker_thread(begin_run)
    elif parent_flow_run_context.flow.isasync and flow.isasync:
        # Async subflow run in async flow run
        return begin_run()
    else:
        # Sync subflow run in async flow run
        return parent_flow_run_context.sync_portal.call(begin_run)

enter_flow_run_engine_from_subprocess

Sync entrypoint for flow runs that have been submitted for execution by an agent

Differs from enter_flow_run_engine_from_flow_call in that we have a flow run id but not a flow object. The flow must be retrieved before execution can begin. Additionally, this assumes that the caller is always in a context without an event loop as this should be called from a fresh process.

Source code in prefect/engine.py
188
189
190
191
192
193
194
195
196
197
198
199
def enter_flow_run_engine_from_subprocess(flow_run_id: UUID) -> State:
    """
    Sync entrypoint for flow runs that have been submitted for execution by an agent

    Differs from `enter_flow_run_engine_from_flow_call` in that we have a flow run id
    but not a flow object. The flow must be retrieved before execution can begin.
    Additionally, this assumes that the caller is always in a context without an event
    loop as this should be called from a fresh process.
    """
    setup_logging()

    return anyio.run(retrieve_flow_then_begin_flow_run, flow_run_id)

enter_task_run_engine

Sync entrypoint for task calls

Source code in prefect/engine.py
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
def enter_task_run_engine(
    task: Task,
    parameters: Dict[str, Any],
    wait_for: Optional[Iterable[PrefectFuture]],
    return_type: EngineReturnType,
    task_runner: Optional[BaseTaskRunner],
    mapped: bool,
) -> Union[PrefectFuture, Awaitable[PrefectFuture]]:
    """
    Sync entrypoint for task calls
    """

    flow_run_context = FlowRunContext.get()
    if not flow_run_context:
        raise RuntimeError(
            "Tasks cannot be run outside of a flow. To call the underlying task"
            " function outside of a flow use `task.fn()`."
        )

    if TaskRunContext.get():
        raise RuntimeError(
            "Tasks cannot be run from within tasks. Did you mean to call this "
            "task in a flow?"
        )

    if flow_run_context.timeout_scope and flow_run_context.timeout_scope.cancel_called:
        raise TimeoutError("Flow run timed out")

    begin_run = partial(
        begin_task_map if mapped else get_task_call_return_value,
        task=task,
        flow_run_context=flow_run_context,
        parameters=parameters,
        wait_for=wait_for,
        return_type=return_type,
        task_runner=task_runner,
    )

    # Async task run in async flow run
    if task.isasync and flow_run_context.flow.isasync:
        return begin_run()  # Return a coroutine for the user to await

    # Async or sync task run in sync flow run
    elif not flow_run_context.flow.isasync:
        return run_async_from_worker_thread(begin_run)

    # Sync task run in async flow run
    else:
        # Call out to the sync portal since we are not in a worker thread
        return flow_run_context.sync_portal.call(begin_run)

get_state_for_result

Get the state related to a result object.

link_state_to_result must have been called first.

Source code in prefect/engine.py
1925
1926
1927
1928
1929
1930
1931
1932
1933
def get_state_for_result(obj: Any) -> Optional[State]:
    """
    Get the state related to a result object.

    `link_state_to_result` must have been called first.
    """
    flow_run_context = FlowRunContext.get()
    if flow_run_context:
        return flow_run_context.task_run_results.get(id(obj))

Caches a link between a state and a result and its components using the id of the components to map to the state. The cache is persisted to the current flow run context since task relationships are limited to within a flow run.

This allows dependency tracking to occur when results are passed around. Note: Because id is used, we cannot cache links between singleton objects.

We only cache the relationship between components 1-layer deep.

Example

Given the result [1, ["a","b"], ("c",)], the following elements will be mapped to the state: - [1, ["a","b"], ("c",)] - ["a","b"] - ("c",)

Note: the int 1 will not be mapped to the state because it is a singleton.

Other Notes: We do not hash the result because: - If changes are made to the object in the flow between task calls, we can still track that they are related. - Hashing can be expensive. - Not all objects are hashable.

We do not set an attribute, e.g. __prefect_state__, on the result because:

  • Mutating user's objects is dangerous.
  • Unrelated equality comparisons can break unexpectedly.
  • The field can be preserved on copy.
  • We cannot set this attribute on Python built-ins.
Source code in prefect/engine.py
1936
1937
1938
1939
1940
1941
1942
1943
1944
1945
1946
1947
1948
1949
1950
1951
1952
1953
1954
1955
1956
1957
1958
1959
1960
1961
1962
1963
1964
1965
1966
1967
1968
1969
1970
1971
1972
1973
1974
1975
1976
1977
1978
1979
1980
1981
1982
1983
1984
1985
1986
1987
1988
1989
1990
def link_state_to_result(state: State, result: Any) -> None:
    """
    Caches a link between a state and a result and its components using
    the `id` of the components to map to the state. The cache is persisted to the
    current flow run context since task relationships are limited to within a flow run.

    This allows dependency tracking to occur when results are passed around.
    Note: Because `id` is used, we cannot cache links between singleton objects.

    We only cache the relationship between components 1-layer deep.
    Example:
        Given the result [1, ["a","b"], ("c",)], the following elements will be
        mapped to the state:
        - [1, ["a","b"], ("c",)]
        - ["a","b"]
        - ("c",)

        Note: the int `1` will not be mapped to the state because it is a singleton.

    Other Notes:
    We do not hash the result because:
    - If changes are made to the object in the flow between task calls, we can still
      track that they are related.
    - Hashing can be expensive.
    - Not all objects are hashable.

    We do not set an attribute, e.g. `__prefect_state__`, on the result because:

    - Mutating user's objects is dangerous.
    - Unrelated equality comparisons can break unexpectedly.
    - The field can be preserved on copy.
    - We cannot set this attribute on Python built-ins.
    """

    flow_run_context = FlowRunContext.get()

    def link_if_trackable(obj: Any) -> None:
        """Track connection between a task run result and its associated state if it has a unique ID.

        We cannot track booleans, Ellipsis, None, NotImplemented, or the integers from -5 to 256
        because they are singletons.

        This function will mutate the State if the object is an untrackable type by setting the value
        for `State.state_details.untrackable_result` to `True`.

        """
        if (type(obj) in UNTRACKABLE_TYPES) or (
            isinstance(obj, int) and (-5 <= obj <= 256)
        ):
            state.state_details.untrackable_result = True
            return
        flow_run_context.task_run_results[id(obj)] = state

    if flow_run_context:
        visit_collection(expr=result, visit_fn=link_if_trackable, max_depth=1)

orchestrate_flow_run async

Executes a flow run.

Note on flow timeouts

Since async flows are run directly in the main event loop, timeout behavior will match that described by anyio. If the flow is awaiting something, it will immediately return; otherwise, the next time it awaits it will exit. Sync flows are being task runner in a worker thread, which cannot be interrupted. The worker thread will exit at the next task call. The worker thread also has access to the status of the cancellation scope at FlowRunContext.timeout_scope.cancel_called which allows it to raise a TimeoutError to respect the timeout.

Returns:

Type Description
State

The final state of the run

Source code in prefect/engine.py
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
async def orchestrate_flow_run(
    flow: Flow,
    flow_run: FlowRun,
    parameters: Dict[str, Any],
    wait_for: Optional[Iterable[PrefectFuture]],
    interruptible: bool,
    client: PrefectClient,
    partial_flow_run_context: PartialModel[FlowRunContext],
) -> State:
    """
    Executes a flow run.

    Note on flow timeouts:
        Since async flows are run directly in the main event loop, timeout behavior will
        match that described by anyio. If the flow is awaiting something, it will
        immediately return; otherwise, the next time it awaits it will exit. Sync flows
        are being task runner in a worker thread, which cannot be interrupted. The worker
        thread will exit at the next task call. The worker thread also has access to the
        status of the cancellation scope at `FlowRunContext.timeout_scope.cancel_called`
        which allows it to raise a `TimeoutError` to respect the timeout.

    Returns:
        The final state of the run
    """

    logger = flow_run_logger(flow_run, flow)

    flow_run_context = None

    try:
        # Resolve futures in any non-data dependencies to ensure they are ready
        if wait_for is not None:
            await resolve_inputs(wait_for, return_data=False)
    except UpstreamTaskError as upstream_exc:
        return await propose_state(
            client,
            Pending(name="NotReady", message=str(upstream_exc)),
            flow_run_id=flow_run.id,
            # if orchestrating a run already in a pending state, force orchestration to
            # update the state name
            force=flow_run.state.is_pending(),
        )

    if flow.flow_run_name:
        flow_run_name = flow.flow_run_name.format(**parameters)
        await client.update_flow_run(flow_run_id=flow_run.id, name=flow_run_name)
        logger.extra["flow_run_name"] = flow_run_name
        logger.debug(f"Renamed flow run {flow_run.name!r} to {flow_run_name!r}")
        flow_run.name = flow_run_name

    state = await propose_state(client, Running(), flow_run_id=flow_run.id)

    while state.is_running():
        waited_for_task_runs = False

        # Update the flow run to the latest data
        flow_run = await client.read_flow_run(flow_run.id)
        try:
            timeout_context = anyio.fail_after(
                flow.timeout_seconds if flow.timeout_seconds else None
            )

            with timeout_context as timeout_scope:
                with partial_flow_run_context.finalize(
                    flow=flow,
                    flow_run=flow_run,
                    client=client,
                    timeout_scope=timeout_scope,
                ) as flow_run_context:
                    args, kwargs = parameters_to_args_kwargs(flow.fn, parameters)
                    logger.debug(
                        f"Executing flow {flow.name!r} for flow run"
                        f" {flow_run.name!r}..."
                    )

                    if PREFECT_DEBUG_MODE:
                        logger.debug(f"Executing {call_repr(flow.fn, *args, **kwargs)}")
                    else:
                        logger.debug(
                            f"Beginning execution...", extra={"state_message": True}
                        )

                    flow_call = partial(flow.fn, *args, **kwargs)

                    if flow.isasync:
                        result = await flow_call()
                    else:
                        run_sync = (
                            run_sync_in_interruptible_worker_thread
                            if interruptible or timeout_scope
                            else run_sync_in_worker_thread
                        )
                        result = await run_sync(flow_call)

                waited_for_task_runs = await wait_for_task_runs_and_report_crashes(
                    flow_run_context.task_run_futures, client=client
                )
        except PausedRun:
            paused_flow_run = await client.read_flow_run(flow_run.id)
            paused_flow_run_state = paused_flow_run.state
            return paused_flow_run_state
        except Exception as exc:
            name = message = None
            if (
                # Flow run timeouts
                isinstance(exc, TimeoutError)
                and timeout_scope
                # Only update the message if the timeout was actually encountered since
                # this could be a timeout in the user's code
                and timeout_scope.cancel_called
            ):
                # TODO: Cancel task runs if feasible
                name = "TimedOut"
                message = f"Flow run exceeded timeout of {flow.timeout_seconds} seconds"
            else:
                # Generic exception in user code
                message = "Flow run encountered an exception."
                logger.exception("Encountered exception during execution:")
            terminal_state = await exception_to_failed_state(
                name=name,
                message=message,
                result_factory=flow_run_context.result_factory,
            )
        else:
            if result is None:
                # All tasks and subflows are reference tasks if there is no return value
                # If there are no tasks, use `None` instead of an empty iterable
                result = (
                    flow_run_context.task_run_futures
                    + flow_run_context.task_run_states
                    + flow_run_context.flow_run_states
                ) or None

            terminal_state = await return_value_to_state(
                await resolve_futures_to_states(result),
                result_factory=flow_run_context.result_factory,
            )

        if not waited_for_task_runs:
            # An exception occured that prevented us from waiting for task runs to
            # complete. Ensure that we wait for them before proposing a final state
            # for the flow run.
            await wait_for_task_runs_and_report_crashes(
                flow_run_context.task_run_futures, client=client
            )

        # Before setting the flow run state, store state.data using
        # block storage and send the resulting data document to the Prefect API instead.
        # This prevents the pickled return value of flow runs
        # from being sent to the Prefect API and stored in the Prefect database.
        # state.data is left as is, otherwise we would have to load
        # the data from block storage again after storing.
        state = await propose_state(
            client,
            state=terminal_state,
            flow_run_id=flow_run.id,
        )

        await _run_flow_hooks(flow=flow, flow_run=flow_run, state=state)

        if state.type != terminal_state.type and PREFECT_DEBUG_MODE:
            logger.debug(
                (
                    f"Received new state {state} when proposing final state"
                    f" {terminal_state}"
                ),
                extra={"send_to_orion": False},
            )

        if not state.is_final():
            logger.info(
                (
                    f"Received non-final state {state.name!r} when proposing final"
                    f" state {terminal_state.name!r} and will attempt to run again..."
                ),
                extra={"send_to_orion": False},
            )
            # Attempt to enter a running state again
            state = await propose_state(client, Running(), flow_run_id=flow_run.id)

    return state

orchestrate_task_run async

Execute a task run

This function should be submitted to an task runner. We must construct the context here instead of receiving it already populated since we may be in a new environment.

Proposes a RUNNING state, then - if accepted, the task user function will be run - if rejected, the received state will be returned

When the user function is run, the result will be used to determine a final state - if an exception is encountered, it is trapped and stored in a FAILED state - otherwise, return_value_to_state is used to determine the state

If the final state is COMPLETED, we generate a cache key as specified by the task

The final state is then proposed - if accepted, this is the final state and will be returned - if rejected and a new final state is provided, it will be returned - if rejected and a non-final state is provided, we will attempt to enter a RUNNING state again

Returns:

Type Description
State

The final state of the run

Source code in prefect/engine.py
1393
1394
1395
1396
1397
1398
1399
1400
1401
1402
1403
1404
1405
1406
1407
1408
1409
1410
1411
1412
1413
1414
1415
1416
1417
1418
1419
1420
1421
1422
1423
1424
1425
1426
1427
1428
1429
1430
1431
1432
1433
1434
1435
1436
1437
1438
1439
1440
1441
1442
1443
1444
1445
1446
1447
1448
1449
1450
1451
1452
1453
1454
1455
1456
1457
1458
1459
1460
1461
1462
1463
1464
1465
1466
1467
1468
1469
1470
1471
1472
1473
1474
1475
1476
1477
1478
1479
1480
1481
1482
1483
1484
1485
1486
1487
1488
1489
1490
1491
1492
1493
1494
1495
1496
1497
1498
1499
1500
1501
1502
1503
1504
1505
1506
1507
1508
1509
1510
1511
1512
1513
1514
1515
1516
1517
1518
1519
1520
1521
1522
1523
1524
1525
1526
1527
1528
1529
1530
1531
1532
1533
1534
1535
1536
1537
1538
1539
1540
1541
1542
1543
1544
1545
1546
1547
1548
1549
1550
1551
1552
1553
1554
1555
1556
1557
1558
1559
1560
1561
1562
1563
1564
1565
1566
1567
1568
1569
1570
1571
1572
1573
1574
1575
1576
1577
1578
1579
1580
1581
1582
1583
1584
1585
1586
1587
1588
1589
1590
1591
1592
1593
1594
1595
1596
1597
1598
1599
1600
1601
1602
1603
1604
1605
1606
1607
1608
async def orchestrate_task_run(
    task: Task,
    task_run: TaskRun,
    parameters: Dict[str, Any],
    wait_for: Optional[Iterable[PrefectFuture]],
    result_factory: ResultFactory,
    log_prints: bool,
    interruptible: bool,
    client: PrefectClient,
) -> State:
    """
    Execute a task run

    This function should be submitted to an task runner. We must construct the context
    here instead of receiving it already populated since we may be in a new environment.

    Proposes a RUNNING state, then
    - if accepted, the task user function will be run
    - if rejected, the received state will be returned

    When the user function is run, the result will be used to determine a final state
    - if an exception is encountered, it is trapped and stored in a FAILED state
    - otherwise, `return_value_to_state` is used to determine the state

    If the final state is COMPLETED, we generate a cache key as specified by the task

    The final state is then proposed
    - if accepted, this is the final state and will be returned
    - if rejected and a new final state is provided, it will be returned
    - if rejected and a non-final state is provided, we will attempt to enter a RUNNING
        state again

    Returns:
        The final state of the run
    """
    logger = task_run_logger(task_run, task=task)

    partial_task_run_context = PartialModel(
        TaskRunContext,
        task_run=task_run,
        task=task,
        client=client,
        result_factory=result_factory,
        log_prints=log_prints,
    )

    try:
        # Resolve futures in parameters into data
        resolved_parameters = await resolve_inputs(parameters)
        # Resolve futures in any non-data dependencies to ensure they are ready
        await resolve_inputs(wait_for, return_data=False)
    except UpstreamTaskError as upstream_exc:
        return await propose_state(
            client,
            Pending(name="NotReady", message=str(upstream_exc)),
            task_run_id=task_run.id,
            # if orchestrating a run already in a pending state, force orchestration to
            # update the state name
            force=task_run.state.is_pending(),
        )

    # Generate the cache key to attach to proposed states
    # The cache key uses a TaskRunContext that does not include a `timeout_context``
    cache_key = (
        task.cache_key_fn(partial_task_run_context.finalize(), resolved_parameters)
        if task.cache_key_fn
        else None
    )

    # Ignore the cached results for a cache key, default = false
    # Setting on task level overrules the Prefect setting (env var)
    refresh_cache = (
        task.refresh_cache
        if task.refresh_cache is not None
        else PREFECT_TASKS_REFRESH_CACHE.value()
    )

    # Transition from `PENDING` -> `RUNNING`
    state = await propose_state(
        client,
        Running(
            state_details=StateDetails(cache_key=cache_key, refresh_cache=refresh_cache)
        ),
        task_run_id=task_run.id,
    )

    # flag to ensure we only update the task run name once
    run_name_set = False

    # Only run the task if we enter a `RUNNING` state
    while state.is_running():
        # Need to create timeout_context from inside of loop so that a
        # new context is created on retries
        timeout_context = (
            anyio.fail_after(task.timeout_seconds)
            if task.timeout_seconds
            else nullcontext()
        )

        # Retrieve the latest metadata for the task run context
        task_run = await client.read_task_run(task_run.id)

        try:
            with timeout_context as timeout_scope:
                task_run_context = partial_task_run_context.finalize(
                    timeout_scope=timeout_scope
                )
                args, kwargs = parameters_to_args_kwargs(task.fn, resolved_parameters)

                # update task run name
                if not run_name_set and task.task_run_name:
                    task_run_name = task.task_run_name.format(**resolved_parameters)
                    await client.set_task_run_name(
                        task_run_id=task_run.id, name=task_run_name
                    )
                    logger.extra["task_run_name"] = task_run_name
                    logger.debug(
                        f"Renamed task run {task_run.name!r} to {task_run_name!r}"
                    )
                    task_run.name = task_run_name
                    run_name_set = True

                if PREFECT_DEBUG_MODE.value():
                    logger.debug(f"Executing {call_repr(task.fn, *args, **kwargs)}")
                else:
                    logger.debug(
                        f"Beginning execution...", extra={"state_message": True}
                    )

                with task_run_context.copy(
                    update={"task_run": task_run, "start_time": pendulum.now("UTC")}
                ):
                    if task.isasync:
                        result = await task.fn(*args, **kwargs)
                    else:
                        run_sync = (
                            run_sync_in_interruptible_worker_thread
                            if interruptible or timeout_scope
                            else run_sync_in_worker_thread
                        )
                        result = await run_sync(task.fn, *args, **kwargs)

        except Exception as exc:
            name = message = None
            if (
                # Task run timeouts
                isinstance(exc, TimeoutError)
                and timeout_scope
                # Only update the message if the timeout was actually encountered since
                # this could be a timeout in the user's code
                and timeout_scope.cancel_called
            ):
                name = "TimedOut"
                message = f"Task run exceeded timeout of {task.timeout_seconds} seconds"
                logger.exception(message)
            else:
                message = "Task run encountered an exception:"
                logger.exception("Encountered exception during execution:")

            terminal_state = await exception_to_failed_state(
                name=name,
                message=message,
                result_factory=task_run_context.result_factory,
            )
        else:
            terminal_state = await return_value_to_state(
                result,
                result_factory=task_run_context.result_factory,
            )

            # for COMPLETED tasks, add the cache key and expiration
            if terminal_state.is_completed():
                terminal_state.state_details.cache_expiration = (
                    (pendulum.now("utc") + task.cache_expiration)
                    if task.cache_expiration
                    else None
                )
                terminal_state.state_details.cache_key = cache_key

        state = await propose_state(client, terminal_state, task_run_id=task_run.id)

        await _run_task_hooks(
            task=task,
            task_run=task_run,
            state=state,
        )

        if state.type != terminal_state.type and PREFECT_DEBUG_MODE:
            logger.debug(
                (
                    f"Received new state {state} when proposing final state"
                    f" {terminal_state}"
                ),
                extra={"send_to_orion": False},
            )

        if not state.is_final():
            logger.info(
                (
                    f"Received non-final state {state.name!r} when proposing final"
                    f" state {terminal_state.name!r} and will attempt to run again..."
                ),
                extra={"send_to_orion": False},
            )
            # Attempt to enter a running state again
            state = await propose_state(client, Running(), task_run_id=task_run.id)

    # If debugging, use the more complete `repr` than the usual `str` description
    display_state = repr(state) if PREFECT_DEBUG_MODE else str(state)

    logger.log(
        level=logging.INFO if state.is_completed() else logging.ERROR,
        msg=f"Finished in state {display_state}",
    )

    return state

pause_flow_run async

Pauses the current flow run by stopping execution until resumed.

When called within a flow run, execution will block and no downstream tasks will run until the flow is resumed. Task runs that have already started will continue running. A timeout parameter can be passed that will fail the flow run if it has not been resumed within the specified time.

Parameters:

Name Type Description Default
flow_run_id UUID

a flow run id. If supplied, this function will attempt to pause the specified flow run outside of the flow run process. When paused, the flow run will continue execution until the NEXT task is orchestrated, at which point the flow will exit. Any tasks that have already started will run until completion. When resumed, the flow run will be rescheduled to finish execution. In order pause a flow run in this way, the flow needs to have an associated deployment and results need to be configured with the persist_results option.

None
timeout int

the number of seconds to wait for the flow to be resumed before failing. Defaults to 5 minutes (300 seconds). If the pause timeout exceeds any configured flow-level timeout, the flow might fail even after resuming.

300
poll_interval int

The number of seconds between checking whether the flow has been resumed. Defaults to 10 seconds.

10
reschedule bool

Flag that will reschedule the flow run if resumed. Instead of blocking execution, the flow will gracefully exit (with no result returned) instead. To use this flag, a flow needs to have an associated deployment and results need to be configured with the persist_results option.

False
key str

An optional key to prevent calling pauses more than once. This defaults to the number of pauses observed by the flow so far, and prevents pauses that use the "reschedule" option from running the same pause twice. A custom key can be supplied for custom pausing behavior.

None
Source code in prefect/engine.py
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
@sync_compatible
async def pause_flow_run(
    flow_run_id: UUID = None,
    timeout: int = 300,
    poll_interval: int = 10,
    reschedule: bool = False,
    key: str = None,
):
    """
    Pauses the current flow run by stopping execution until resumed.

    When called within a flow run, execution will block and no downstream tasks will
    run until the flow is resumed. Task runs that have already started will continue
    running. A timeout parameter can be passed that will fail the flow run if it has not
    been resumed within the specified time.

    Args:
        flow_run_id: a flow run id. If supplied, this function will attempt to pause
            the specified flow run outside of the flow run process. When paused, the
            flow run will continue execution until the NEXT task is orchestrated, at
            which point the flow will exit. Any tasks that have already started will
            run until completion. When resumed, the flow run will be rescheduled to
            finish execution. In order pause a flow run in this way, the flow needs to
            have an associated deployment and results need to be configured with the
            `persist_results` option.
        timeout: the number of seconds to wait for the flow to be resumed before
            failing. Defaults to 5 minutes (300 seconds). If the pause timeout exceeds
            any configured flow-level timeout, the flow might fail even after resuming.
        poll_interval: The number of seconds between checking whether the flow has been
            resumed. Defaults to 10 seconds.
        reschedule: Flag that will reschedule the flow run if resumed. Instead of
            blocking execution, the flow will gracefully exit (with no result returned)
            instead. To use this flag, a flow needs to have an associated deployment and
            results need to be configured with the `persist_results` option.
        key: An optional key to prevent calling pauses more than once. This defaults to
            the number of pauses observed by the flow so far, and prevents pauses that
            use the "reschedule" option from running the same pause twice. A custom key
            can be supplied for custom pausing behavior.
    """
    if flow_run_id:
        return await _out_of_process_pause(
            flow_run_id=flow_run_id,
            timeout=timeout,
            reschedule=reschedule,
            key=key,
        )
    else:
        return await _in_process_pause(
            timeout=timeout, poll_interval=poll_interval, reschedule=reschedule, key=key
        )

propose_state async

Propose a new state for a flow run or task run, invoking Prefect orchestration logic.

If the proposed state is accepted, the provided state will be augmented with details and returned.

If the proposed state is rejected, a new state returned by the Prefect API will be returned.

If the proposed state results in a WAIT instruction from the Prefect API, the function will sleep and attempt to propose the state again.

If the proposed state results in an ABORT instruction from the Prefect API, an error will be raised.

Parameters:

Name Type Description Default
state State

a new state for the task or flow run

required
task_run_id UUID

an optional task run id, used when proposing task run states

None
flow_run_id UUID

an optional flow run id, used when proposing flow run states

None

Returns:

Type Description
State

a State model representation of the flow or task run state

Raises:

Type Description
ValueError

if neither task_run_id or flow_run_id is provided

prefect.exceptions.Abort

if an ABORT instruction is received from the Prefect API

Source code in prefect/engine.py
1803
1804
1805
1806
1807
1808
1809
1810
1811
1812
1813
1814
1815
1816
1817
1818
1819
1820
1821
1822
1823
1824
1825
1826
1827
1828
1829
1830
1831
1832
1833
1834
1835
1836
1837
1838
1839
1840
1841
1842
1843
1844
1845
1846
1847
1848
1849
1850
1851
1852
1853
1854
1855
1856
1857
1858
1859
1860
1861
1862
1863
1864
1865
1866
1867
1868
1869
1870
1871
1872
1873
1874
1875
1876
1877
1878
1879
1880
1881
1882
1883
1884
1885
1886
1887
1888
1889
1890
1891
1892
1893
1894
1895
1896
1897
1898
1899
1900
1901
1902
1903
1904
1905
async def propose_state(
    client: PrefectClient,
    state: State,
    force: bool = False,
    task_run_id: UUID = None,
    flow_run_id: UUID = None,
) -> State:
    """
    Propose a new state for a flow run or task run, invoking Prefect orchestration logic.

    If the proposed state is accepted, the provided `state` will be augmented with
     details and returned.

    If the proposed state is rejected, a new state returned by the Prefect API will be
    returned.

    If the proposed state results in a WAIT instruction from the Prefect API, the
    function will sleep and attempt to propose the state again.

    If the proposed state results in an ABORT instruction from the Prefect API, an
    error will be raised.

    Args:
        state: a new state for the task or flow run
        task_run_id: an optional task run id, used when proposing task run states
        flow_run_id: an optional flow run id, used when proposing flow run states

    Returns:
        a [State model][prefect.server.schemas.states] representation of the flow or task run
            state

    Raises:
        ValueError: if neither task_run_id or flow_run_id is provided
        prefect.exceptions.Abort: if an ABORT instruction is received from
            the Prefect API
    """

    # Determine if working with a task run or flow run
    if not task_run_id and not flow_run_id:
        raise ValueError("You must provide either a `task_run_id` or `flow_run_id`")

    # Handle task and sub-flow tracing
    if state.is_final():
        if isinstance(state.data, BaseResult) and state.data.has_cached_object():
            # Avoid fetching the result unless it is cached, otherwise we defeat
            # the purpose of disabling `cache_result_in_memory`
            result = await state.result(raise_on_failure=False, fetch=True)
        else:
            result = state.data

        link_state_to_result(state, result)

    # Attempt to set the state
    if task_run_id:
        response = await client.set_task_run_state(
            task_run_id,
            state,
            force=force,
        )
    elif flow_run_id:
        response = await client.set_flow_run_state(
            flow_run_id,
            state,
            force=force,
        )
    else:
        raise ValueError(
            "Neither flow run id or task run id were provided. At least one must "
            "be given."
        )

    # Parse the response to return the new state
    if response.status == SetStateStatus.ACCEPT:
        # Update the state with the details if provided
        if response.state.state_details:
            state.state_details = response.state.state_details
        return state

    elif response.status == SetStateStatus.ABORT:
        raise prefect.exceptions.Abort(response.details.reason)

    elif response.status == SetStateStatus.WAIT:
        engine_logger.debug(
            f"Received wait instruction for {response.details.delay_seconds}s: "
            f"{response.details.reason}"
        )
        await anyio.sleep(response.details.delay_seconds)
        return await propose_state(
            client,
            state,
            task_run_id=task_run_id,
            flow_run_id=flow_run_id,
        )

    elif response.status == SetStateStatus.REJECT:
        if response.state.is_paused():
            raise Pause(response.details.reason)
        return response.state

    else:
        raise ValueError(
            f"Received unexpected `SetStateStatus` from server: {response.status!r}"
        )

report_flow_run_crashes async

Detect flow run crashes during this context and update the run to a proper final state.

This context must reraise the exception to properly exit the run.

Source code in prefect/engine.py
1660
1661
1662
1663
1664
1665
1666
1667
1668
1669
1670
1671
1672
1673
1674
1675
1676
1677
1678
1679
1680
1681
1682
1683
1684
1685
1686
1687
1688
1689
1690
1691
1692
1693
1694
1695
1696
1697
1698
1699
1700
1701
1702
1703
1704
1705
1706
1707
1708
1709
1710
@asynccontextmanager
async def report_flow_run_crashes(flow_run: FlowRun, client: PrefectClient):
    """
    Detect flow run crashes during this context and update the run to a proper final
    state.

    This context _must_ reraise the exception to properly exit the run.
    """

    def cancel_flow_run(*args):
        raise TerminationSignal(signal=signal.SIGTERM)

    original_term_handler = None
    try:
        original_term_handler = signal.signal(signal.SIGTERM, cancel_flow_run)
    except ValueError:
        # Signals only work in the main thread
        pass

    try:
        yield
    except (Abort, Pause):
        # Do not capture internal signals as crashes
        raise
    except BaseException as exc:
        state = await exception_to_crashed_state(exc)
        logger = flow_run_logger(flow_run)
        with anyio.CancelScope(shield=True):
            logger.error(f"Crash detected! {state.message}")
            logger.debug("Crash details:", exc_info=exc)
            await client.set_flow_run_state(
                state=state,
                flow_run_id=flow_run.id,
            )
            engine_logger.debug(
                f"Reported crashed flow run {flow_run.name!r} successfully!"
            )

        if isinstance(exc, TerminationSignal):
            # Termination signals are swapped out during a flow run to perform
            # a graceful shutdown and raise this exception. This `os.kill` call
            # ensures that the previous handler, likely the Python default,
            # gets called as well.
            signal.signal(exc.signal, original_term_handler)
            os.kill(os.getpid(), exc.signal)

        # Reraise the exception
        raise exc from None
    finally:
        if original_term_handler is not None:
            signal.signal(signal.SIGTERM, original_term_handler)

report_task_run_crashes async

Detect task run crashes during this context and update the run to a proper final state.

This context must reraise the exception to properly exit the run.

Source code in prefect/engine.py
1713
1714
1715
1716
1717
1718
1719
1720
1721
1722
1723
1724
1725
1726
1727
1728
1729
1730
1731
1732
1733
1734
1735
1736
1737
1738
1739
1740
1741
1742
@asynccontextmanager
async def report_task_run_crashes(task_run: TaskRun, client: PrefectClient):
    """
    Detect task run crashes during this context and update the run to a proper final
    state.

    This context _must_ reraise the exception to properly exit the run.
    """
    try:
        yield
    except (Abort, Pause):
        # Do not capture internal signals as crashes
        raise
    except BaseException as exc:
        state = await exception_to_crashed_state(exc)
        logger = task_run_logger(task_run)
        with anyio.CancelScope(shield=True):
            logger.error(f"Crash detected! {state.message}")
            logger.debug("Crash details:", exc_info=exc)
            await client.set_task_run_state(
                state=state,
                task_run_id=task_run.id,
                force=True,
            )
            engine_logger.debug(
                f"Reported crashed task run {task_run.name!r} successfully!"
            )

        # Reraise the exception
        raise

resolve_inputs async

Resolve any Quote, PrefectFuture, or State types nested in parameters into data.

Returns:

Type Description
Dict[str, Any]

A copy of the parameters with resolved data

Raises:

Type Description
UpstreamTaskError

If any of the upstream states are not COMPLETED

Source code in prefect/engine.py
1745
1746
1747
1748
1749
1750
1751
1752
1753
1754
1755
1756
1757
1758
1759
1760
1761
1762
1763
1764
1765
1766
1767
1768
1769
1770
1771
1772
1773
1774
1775
1776
1777
1778
1779
1780
1781
1782
1783
1784
1785
1786
1787
1788
1789
1790
1791
1792
1793
1794
1795
1796
1797
1798
1799
1800
async def resolve_inputs(
    parameters: Dict[str, Any], return_data: bool = True, max_depth: int = -1
) -> Dict[str, Any]:
    """
    Resolve any `Quote`, `PrefectFuture`, or `State` types nested in parameters into
    data.

    Returns:
        A copy of the parameters with resolved data

    Raises:
        UpstreamTaskError: If any of the upstream states are not `COMPLETED`
    """

    def resolve_input(expr, context):
        state = None

        # Expressions inside quotes should not be modified
        if isinstance(context.get("annotation"), quote):
            raise StopVisiting()

        if isinstance(expr, PrefectFuture):
            state = run_async_from_worker_thread(expr._wait)
        elif isinstance(expr, State):
            state = expr
        else:
            return expr

        # Do not allow uncompleted upstreams except failures when `allow_failure` has
        # been used
        if not state.is_completed() and not (
            # TODO: Note that the contextual annotation here is only at the current level
            #       if `allow_failure` is used then another annotation is used, this will
            #       incorrectly evaulate to false — to resolve this, we must track all
            #       annotations wrapping the current expression but this is not yet
            #       implemented.
            isinstance(context.get("annotation"), allow_failure)
            and state.is_failed()
        ):
            raise UpstreamTaskError(
                f"Upstream task run '{state.state_details.task_run_id}' did not reach a"
                " 'COMPLETED' state."
            )

        # Only retrieve the result if requested as it may be expensive
        return state.result(raise_on_failure=False, fetch=True) if return_data else None

    return await run_sync_in_worker_thread(
        visit_collection,
        parameters,
        visit_fn=resolve_input,
        return_data=return_data,
        max_depth=max_depth,
        remove_annotations=True,
        context={},
    )

resume_flow_run async

Resumes a paused flow.

Parameters:

Name Type Description Default
flow_run_id

the flow_run_id to resume

required
Source code in prefect/engine.py
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
@sync_compatible
async def resume_flow_run(flow_run_id):
    """
    Resumes a paused flow.

    Args:
        flow_run_id: the flow_run_id to resume
    """
    client = get_client()
    flow_run = await client.read_flow_run(flow_run_id)

    if not flow_run.state.is_paused():
        raise NotPausedError("Cannot resume a run that isn't paused!")

    response = await client.resume_flow_run(flow_run_id)

    if response.status == SetStateStatus.REJECT:
        if response.state.type == StateType.FAILED:
            raise FlowPauseTimeout("Flow run can no longer be resumed.")
        else:
            raise RuntimeError(f"Cannot resume this run: {response.details.reason}")

retrieve_flow_then_begin_flow_run async

Async entrypoint for flow runs that have been submitted for execution by an agent

  • Retrieves the deployment information
  • Loads the flow object using deployment information
  • Updates the flow run version
Source code in prefect/engine.py
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
@inject_client
async def retrieve_flow_then_begin_flow_run(
    flow_run_id: UUID, client: PrefectClient
) -> State:
    """
    Async entrypoint for flow runs that have been submitted for execution by an agent

    - Retrieves the deployment information
    - Loads the flow object using deployment information
    - Updates the flow run version
    """
    flow_run = await client.read_flow_run(flow_run_id)
    try:
        flow = await load_flow_from_flow_run(flow_run, client=client)
    except Exception as exc:
        message = "Flow could not be retrieved from deployment."
        flow_run_logger(flow_run).exception(message)
        state = await exception_to_failed_state(message=message)
        await client.set_flow_run_state(
            state=state, flow_run_id=flow_run_id, force=True
        )
        return state

    # Update the flow run policy defaults to match settings on the flow
    # Note: Mutating the flow run object prevents us from performing another read
    #       operation if these properties are used by the client downstream
    if flow_run.empirical_policy.retry_delay is None:
        flow_run.empirical_policy.retry_delay = flow.retry_delay_seconds

    if flow_run.empirical_policy.retries is None:
        flow_run.empirical_policy.retries = flow.retries

    await client.update_flow_run(
        flow_run_id=flow_run_id,
        flow_version=flow.version,
        empirical_policy=flow_run.empirical_policy,
    )

    if flow.should_validate_parameters:
        failed_state = None
        try:
            parameters = flow.validate_parameters(flow_run.parameters)
        except Exception:
            message = "Validation of flow parameters failed with error: "
            flow_run_logger(flow_run).exception(message)
            failed_state = await exception_to_failed_state(message=message)

        if failed_state is not None:
            await propose_state(
                client,
                state=failed_state,
                flow_run_id=flow_run_id,
            )
            return failed_state
    else:
        parameters = flow_run.parameters

    # Ensure default values are populated
    parameters = {**get_parameter_defaults(flow.fn), **parameters}

    return await begin_flow_run(
        flow=flow,
        flow_run=flow_run,
        parameters=parameters,
        client=client,
    )