Move some infos to runtime level

This change some super old (and bad) code from the project's very early
days. For some redic reason i must have thought masking `trio`'s
internal stream / transport errors and a TCP EOF as `StopAsyncIteration`
somehow a good idea. The reality is you probably
want to know the difference between an unexpected transport error
and a simple EOF lol. This begins to resolve that by adding our own
special `TransportClosed` error to signal the "graceful" termination of
a channel's underlying transport. Oh, and this builds on the `msgspec`
integration which helped shed light on the core issues here B)

docs/README.rst

@@ -322,6 +322,7 @@ channel`_!
 .. _async sandwich: https://trio.readthedocs.io/en/latest/tutorial.html#async-sandwich
 .. _structured concurrent: https://trio.discourse.group/t/concise-definition-of-structured-concurrency/228
 .. _3 axioms: https://www.youtube.com/watch?v=7erJ1DV_Tlo&t=162s
+.. .. _3 axioms: https://en.wikipedia.org/wiki/Actor_model#Fundamental_concepts
 .. _adherance to: https://www.youtube.com/watch?v=7erJ1DV_Tlo&t=1821s
 .. _trio gitter channel: https://gitter.im/python-trio/general
 .. _matrix channel: https://matrix.to/#/!tractor:matrix.org
@@ -330,7 +331,7 @@ channel`_!
 .. _messages: https://en.wikipedia.org/wiki/Message_passing
 .. _trio docs: https://trio.readthedocs.io/en/latest/
 .. _blog post: https://vorpus.org/blog/notes-on-structured-concurrency-or-go-statement-considered-harmful/
-.. _structured concurrency: https://vorpus.org/blog/notes-on-structured-concurrency-or-go-statement-considered-harmful/
+.. _structured concurrency: https://en.wikipedia.org/wiki/Structured_concurrency
 .. _unrequirements: https://en.wikipedia.org/wiki/Actor_model#Direct_communication_and_asynchrony
 .. _async generators: https://www.python.org/dev/peps/pep-0525/
 .. _trio-parallel: https://github.com/richardsheridan/trio-parallel

examples/debugging/root_timeout_while_child_crashed.py

@@ -0,0 +1,31 @@
+
+import trio
+import tractor
+
+
+async def key_error():
+    "Raise a ``NameError``"
+    return {}['doggy']
+
+
+async def main():
+    """Root dies 
+
+    """
+    async with tractor.open_nursery(
+        debug_mode=True,
+        loglevel='debug'
+    ) as n:
+
+        # spawn both actors
+        portal = await n.run_in_actor(key_error)
+
+        # XXX: originally a bug causes by this
+        # where root would enter debugger even
+        # though child should have it locked.
+        with trio.fail_after(1):
+            await trio.Event().wait()
+
+
+if __name__ == '__main__':
+    trio.run(main)

setup.py

@@ -38,13 +38,20 @@ setup(
         'tractor.testing',
     ],
     install_requires=[
+
+        # trio related
         'trio>0.8',
-        'msgpack',
         'async_generator',
+        'tricycle',
+        'trio_typing',
+
         'colorlog',
         'wrapt',
-        'trio_typing',
         'pdbpp',
+
+        # serialization
+        'msgpack',
+        'msgspec',
     ],
     tests_require=['pytest'],
     python_requires=">=3.7",

tests/test_2way.py

@@ -0,0 +1,498 @@
+"""
+Bidirectional streaming and context API.
+
+"""
+import pytest
+import trio
+import tractor
+
+from conftest import tractor_test
+
+# the general stream semantics are
+# - normal termination: far end relays a stop message which
+# terminates an ongoing ``MsgStream`` iteration
+# - cancel termination: context is cancelled on either side cancelling
+#  the "linked" inter-actor task context
+
+
+_state: bool = False
+
+
+@tractor.context
+async def simple_setup_teardown(
+
+    ctx: tractor.Context,
+    data: int,
+    block_forever: bool = False,
+
+) -> None:
+
+    # startup phase
+    global _state
+    _state = True
+
+    # signal to parent that we're up
+    await ctx.started(data + 1)
+
+    try:
+        if block_forever:
+            # block until cancelled
+            await trio.sleep_forever()
+        else:
+            return 'yo'
+    finally:
+        _state = False
+
+
+async def assert_state(value: bool):
+    global _state
+    assert _state == value
+
+
+@pytest.mark.parametrize(
+    'error_parent',
+    [False, True],
+)
+@pytest.mark.parametrize(
+    'callee_blocks_forever',
+    [False, True],
+)
+def test_simple_context(
+    error_parent,
+    callee_blocks_forever,
+):
+
+    async def main():
+
+        async with tractor.open_nursery() as n:
+
+            portal = await n.start_actor(
+                'simple_context',
+                enable_modules=[__name__],
+            )
+
+            async with portal.open_context(
+                simple_setup_teardown,
+                data=10,
+                block_forever=callee_blocks_forever,
+            ) as (ctx, sent):
+
+                assert sent == 11
+
+                if callee_blocks_forever:
+                    await portal.run(assert_state, value=True)
+                    await ctx.cancel()
+                else:
+                    assert await ctx.result() == 'yo'
+
+            # after cancellation
+            await portal.run(assert_state, value=False)
+
+            if error_parent:
+                raise ValueError
+
+            # shut down daemon
+            await portal.cancel_actor()
+
+    if error_parent:
+        try:
+            trio.run(main)
+        except ValueError:
+            pass
+    else:
+        trio.run(main)
+
+
+# basic stream terminations:
+# - callee context closes without using stream
+# - caller context closes without using stream
+# - caller context calls `Context.cancel()` while streaming
+#   is ongoing resulting in callee being cancelled
+# - callee calls `Context.cancel()` while streaming and caller
+#   sees stream terminated in `RemoteActorError`
+
+# TODO: future possible features
+# - restart request: far end raises `ContextRestart`
+
+
+@tractor.context
+async def close_ctx_immediately(
+
+    ctx: tractor.Context,
+
+) -> None:
+
+    await ctx.started()
+    global _state
+
+    async with ctx.open_stream():
+        pass
+
+
+@tractor_test
+async def test_callee_closes_ctx_after_stream_open():
+    'callee context closes without using stream'
+
+    async with tractor.open_nursery() as n:
+
+        portal = await n.start_actor(
+            'fast_stream_closer',
+            enable_modules=[__name__],
+        )
+
+        async with portal.open_context(
+            close_ctx_immediately,
+
+            # flag to avoid waiting the final result
+            # cancel_on_exit=True,
+
+        ) as (ctx, sent):
+
+            assert sent is None
+
+            with trio.fail_after(0.5):
+                async with ctx.open_stream() as stream:
+
+                    # should fall through since ``StopAsyncIteration``
+                    # should be raised through translation of
+                    # a ``trio.EndOfChannel`` by
+                    # ``trio.abc.ReceiveChannel.__anext__()``
+                    async for _ in stream:
+                        assert 0
+                    else:
+
+                        # verify stream is now closed
+                        try:
+                            await stream.receive()
+                        except trio.EndOfChannel:
+                            pass
+
+            # TODO: should be just raise the closed resource err
+            # directly here to enforce not allowing a re-open
+            # of a stream to the context (at least until a time of
+            # if/when we decide that's a good idea?)
+            try:
+                async with ctx.open_stream() as stream:
+                    pass
+            except trio.ClosedResourceError:
+                pass
+
+        await portal.cancel_actor()
+
+
+@tractor.context
+async def expect_cancelled(
+
+    ctx: tractor.Context,
+
+) -> None:
+    global _state
+    _state = True
+
+    await ctx.started()
+
+    try:
+        async with ctx.open_stream() as stream:
+            async for msg in stream:
+                await stream.send(msg)  # echo server
+
+    except trio.Cancelled:
+        # expected case
+        _state = False
+        raise
+
+    else:
+        assert 0, "Wasn't cancelled!?"
+
+
+@pytest.mark.parametrize(
+    'use_ctx_cancel_method',
+    [False, True],
+)
+@tractor_test
+async def test_caller_closes_ctx_after_callee_opens_stream(
+    use_ctx_cancel_method: bool,
+):
+    'caller context closes without using stream'
+
+    async with tractor.open_nursery() as n:
+
+        portal = await n.start_actor(
+            'ctx_cancelled',
+            enable_modules=[__name__],
+        )
+
+        async with portal.open_context(
+            expect_cancelled,
+        ) as (ctx, sent):
+            await portal.run(assert_state, value=True)
+
+            assert sent is None
+
+            # call cancel explicitly
+            if use_ctx_cancel_method:
+
+                await ctx.cancel()
+
+                try:
+                    async with ctx.open_stream() as stream:
+                        async for msg in stream:
+                            pass
+
+                except tractor.ContextCancelled:
+                    raise  # XXX: must be propagated to __aexit__
+
+                else:
+                    assert 0, "Should have context cancelled?"
+
+                # channel should still be up
+                assert portal.channel.connected()
+
+                # ctx is closed here
+                await portal.run(assert_state, value=False)
+
+            else:
+                try:
+                    with trio.fail_after(0.2):
+                        await ctx.result()
+                        assert 0, "Callee should have blocked!?"
+                except trio.TooSlowError:
+                    await ctx.cancel()
+        try:
+            async with ctx.open_stream() as stream:
+                async for msg in stream:
+                    pass
+        except trio.ClosedResourceError:
+            pass
+        else:
+            assert 0, "Should have received closed resource error?"
+
+        # ctx is closed here
+        await portal.run(assert_state, value=False)
+
+        # channel should not have been destroyed yet, only the
+        # inter-actor-task context
+        assert portal.channel.connected()
+
+        # teardown the actor
+        await portal.cancel_actor()
+
+
+@tractor_test
+async def test_multitask_caller_cancels_from_nonroot_task():
+
+    async with tractor.open_nursery() as n:
+
+        portal = await n.start_actor(
+            'ctx_cancelled',
+            enable_modules=[__name__],
+        )
+
+        async with portal.open_context(
+            expect_cancelled,
+        ) as (ctx, sent):
+
+            await portal.run(assert_state, value=True)
+            assert sent is None
+
+            async with ctx.open_stream() as stream:
+
+                async def send_msg_then_cancel():
+                    await stream.send('yo')
+                    await portal.run(assert_state, value=True)
+                    await ctx.cancel()
+                    await portal.run(assert_state, value=False)
+
+                async with trio.open_nursery() as n:
+                    n.start_soon(send_msg_then_cancel)
+
+                    try:
+                        async for msg in stream:
+                            assert msg == 'yo'
+
+                    except tractor.ContextCancelled:
+                        raise  # XXX: must be propagated to __aexit__
+
+                # channel should still be up
+                assert portal.channel.connected()
+
+                # ctx is closed here
+                await portal.run(assert_state, value=False)
+
+        # channel should not have been destroyed yet, only the
+        # inter-actor-task context
+        assert portal.channel.connected()
+
+        # teardown the actor
+        await portal.cancel_actor()
+
+
+@tractor.context
+async def cancel_self(
+
+    ctx: tractor.Context,
+
+) -> None:
+    global _state
+    _state = True
+
+    await ctx.cancel()
+    try:
+        with trio.fail_after(0.1):
+            await trio.sleep_forever()
+
+    except trio.Cancelled:
+        raise
+
+    except trio.TooSlowError:
+        # should never get here
+        assert 0
+
+
+@tractor_test
+async def test_callee_cancels_before_started():
+    '''callee calls `Context.cancel()` while streaming and caller
+    sees stream terminated in `ContextCancelled`.
+
+    '''
+    async with tractor.open_nursery() as n:
+
+        portal = await n.start_actor(
+            'cancels_self',
+            enable_modules=[__name__],
+        )
+        try:
+
+            async with portal.open_context(
+                cancel_self,
+            ) as (ctx, sent):
+                async with ctx.open_stream():
+
+                    await trio.sleep_forever()
+
+        # raises a special cancel signal
+        except tractor.ContextCancelled as ce:
+            ce.type == trio.Cancelled
+
+        # teardown the actor
+        await portal.cancel_actor()
+
+
+@tractor.context
+async def simple_rpc(
+
+    ctx: tractor.Context,
+    data: int,
+
+) -> None:
+    """Test a small ping-pong server.
+
+    """
+    # signal to parent that we're up
+    await ctx.started(data + 1)
+
+    print('opening stream in callee')
+    async with ctx.open_stream() as stream:
+
+        count = 0
+        while True:
+            try:
+                await stream.receive() == 'ping'
+            except trio.EndOfChannel:
+                assert count == 10
+                break
+            else:
+                print('pong')
+                await stream.send('pong')
+                count += 1
+
+
+@tractor.context
+async def simple_rpc_with_forloop(
+
+    ctx: tractor.Context,
+    data: int,
+
+) -> None:
+    """Same as previous test but using ``async for`` syntax/api.
+
+    """
+
+    # signal to parent that we're up
+    await ctx.started(data + 1)
+
+    print('opening stream in callee')
+    async with ctx.open_stream() as stream:
+
+        count = 0
+        async for msg in stream:
+
+            assert msg == 'ping'
+            print('pong')
+            await stream.send('pong')
+            count += 1
+
+        else:
+            assert count == 10
+
+
+@pytest.mark.parametrize(
+    'use_async_for',
+    [True, False],
+)
+@pytest.mark.parametrize(
+    'server_func',
+    [simple_rpc, simple_rpc_with_forloop],
+)
+def test_simple_rpc(server_func, use_async_for):
+    """The simplest request response pattern.
+
+    """
+    async def main():
+        async with tractor.open_nursery() as n:
+
+            portal = await n.start_actor(
+                'rpc_server',
+                enable_modules=[__name__],
+            )
+
+            async with portal.open_context(
+                server_func,  # taken from pytest parameterization
+                data=10,
+            ) as (ctx, sent):
+
+                assert sent == 11
+
+                async with ctx.open_stream() as stream:
+
+                    if use_async_for:
+
+                        count = 0
+                        # receive msgs using async for style
+                        print('ping')
+                        await stream.send('ping')
+
+                        async for msg in stream:
+                            assert msg == 'pong'
+                            print('ping')
+                            await stream.send('ping')
+                            count += 1
+
+                            if count >= 9:
+                                break
+
+                    else:
+                        # classic send/receive style
+                        for _ in range(10):
+
+                            print('ping')
+                            await stream.send('ping')
+                            assert await stream.receive() == 'pong'
+
+                # stream should terminate here
+
+            # final context result(s) should be consumed here in __aexit__()
+
+            await portal.cancel_actor()
+
+    trio.run(main)

tests/test_advanced_streaming.py

@@ -0,0 +1,220 @@
+"""
+Advanced streaming patterns using bidirectional streams and contexts.
+
+"""
+import itertools
+from typing import Set, Dict, List
+
+import trio
+import tractor
+
+
+_registry: Dict[str, Set[tractor.ReceiveMsgStream]] = {
+    'even': set(),
+    'odd': set(),
+}
+
+
+async def publisher(
+
+    seed: int = 0,
+
+) -> None:
+
+    global _registry
+
+    def is_even(i):
+        return i % 2 == 0
+
+    for val in itertools.count(seed):
+
+        sub = 'even' if is_even(val) else 'odd'
+
+        for sub_stream in _registry[sub]:
+            await sub_stream.send(val)
+
+        # throttle send rate to ~1kHz
+        # making it readable to a human user
+        await trio.sleep(1/1000)
+
+
+@tractor.context
+async def subscribe(
+
+    ctx: tractor.Context,
+
+) -> None:
+
+    global _registry
+
+    # syn caller
+    await ctx.started(None)
+
+    async with ctx.open_stream() as stream:
+
+        # update subs list as consumer requests
+        async for new_subs in stream:
+
+            new_subs = set(new_subs)
+            remove = new_subs - _registry.keys()
+
+            print(f'setting sub to {new_subs} for {ctx.chan.uid}')
+
+            # remove old subs
+            for sub in remove:
+                _registry[sub].remove(stream)
+
+            # add new subs for consumer
+            for sub in new_subs:
+                _registry[sub].add(stream)
+
+
+async def consumer(
+
+    subs: List[str],
+
+) -> None:
+
+    uid = tractor.current_actor().uid
+
+    async with tractor.wait_for_actor('publisher') as portal:
+        async with portal.open_context(subscribe) as (ctx, first):
+            async with ctx.open_stream() as stream:
+
+                # flip between the provided subs dynamically
+                if len(subs) > 1:
+
+                    for sub in itertools.cycle(subs):
+                        print(f'setting dynamic sub to {sub}')
+                        await stream.send([sub])
+
+                        count = 0
+                        async for value in stream:
+                            print(f'{uid} got: {value}')
+                            if count > 5:
+                                break
+                            count += 1
+
+                else:  # static sub
+
+                    await stream.send(subs)
+                    async for value in stream:
+                        print(f'{uid} got: {value}')
+
+
+def test_dynamic_pub_sub():
+
+    global _registry
+
+    from multiprocessing import cpu_count
+    cpus = cpu_count()
+
+    async def main():
+        async with tractor.open_nursery() as n:
+
+            # name of this actor will be same as target func
+            await n.run_in_actor(publisher)
+
+            for i, sub in zip(
+                range(cpus - 2),
+                itertools.cycle(_registry.keys())
+            ):
+                await n.run_in_actor(
+                    consumer,
+                    name=f'consumer_{sub}',
+                    subs=[sub],
+                )
+
+            # make one dynamic subscriber
+            await n.run_in_actor(
+                consumer,
+                name='consumer_dynamic',
+                subs=list(_registry.keys()),
+            )
+
+            # block until cancelled by user
+            with trio.fail_after(3):
+                await trio.sleep_forever()
+
+    try:
+        trio.run(main)
+    except trio.TooSlowError:
+        pass
+
+
+@tractor.context
+async def one_task_streams_and_one_handles_reqresp(
+
+    ctx: tractor.Context,
+
+) -> None:
+
+    await ctx.started()
+
+    async with ctx.open_stream() as stream:
+
+        async def pingpong():
+            '''Run a simple req/response service.
+
+            '''
+            async for msg in stream:
+                print('rpc server ping')
+                assert msg == 'ping'
+                print('rpc server pong')
+                await stream.send('pong')
+
+        async with trio.open_nursery() as n:
+            n.start_soon(pingpong)
+
+            for _ in itertools.count():
+                await stream.send('yo')
+                await trio.sleep(0.01)
+
+
+def test_reqresp_ontopof_streaming():
+    '''Test a subactor that both streams with one task and
+    spawns another which handles a small requests-response
+    dialogue over the same bidir-stream.
+
+    '''
+    async def main():
+
+        with trio.move_on_after(2):
+            async with tractor.open_nursery() as n:
+
+                # name of this actor will be same as target func
+                portal = await n.start_actor(
+                    'dual_tasks',
+                    enable_modules=[__name__]
+                )
+
+                # flat to make sure we get at least one pong
+                got_pong: bool = False
+
+                async with portal.open_context(
+                    one_task_streams_and_one_handles_reqresp,
+
+                ) as (ctx, first):
+
+                    assert first is None
+
+                    async with ctx.open_stream() as stream:
+
+                        await stream.send('ping')
+
+                        async for msg in stream:
+                            print(f'client received: {msg}')
+
+                            assert msg in {'pong', 'yo'}
+
+                            if msg == 'pong':
+                                got_pong = True
+                                await stream.send('ping')
+                                print('client sent ping')
+
+        assert got_pong
+
+    try:
+        trio.run(main)
+    except trio.TooSlowError:
+        pass

tests/test_infected_asyncio.py

@@ -0,0 +1,24 @@
+import asyncio
+
+import pytest
+import tractor
+
+async def sleep_and_err():
+    await asyncio.sleep(0.1)
+    assert 0
+
+
+async def asyncio_actor():
+    assert tractor.current_actor().is_infected_aio()
+
+    await tractor.to_asyncio.run_task(sleep_and_err)
+
+
+def test_infected_simple_error(arb_addr):
+
+    async def main():
+        async with tractor.open_nursery() as n:
+            await n.run_in_actor(asyncio_actor, infected_asyncio=True)
+
+    with pytest.raises(tractor.RemoteActorError) as excinfo:
+        tractor.run(main, arbiter_addr=arb_addr)

tests/test_streaming.py

@@ -32,13 +32,16 @@ async def async_gen_stream(sequence):
 
     # block indefinitely waiting to be cancelled by ``aclose()`` call
     with trio.CancelScope() as cs:
-        await trio.sleep(float('inf'))
+        await trio.sleep_forever()
         assert 0
     assert cs.cancelled_caught
 
 
 @tractor.stream
-async def context_stream(ctx, sequence):
+async def context_stream(
+    ctx: tractor.Context,
+    sequence
+):
     for i in sequence:
         await ctx.send_yield(i)
         await trio.sleep(0.1)
@@ -338,6 +341,8 @@ async def test_respawn_consumer_task(
                         print("all values streamed, BREAKING")
                         break
 
+                cs.cancel()
+
         # TODO: this is justification for a
         # ``ActorNursery.stream_from_actor()`` helper?
         await portal.cancel_actor()

tractor/__init__.py

@@ -5,14 +5,25 @@ tractor: An actor model micro-framework built on
 from trio import MultiError
 
 from ._ipc import Channel
-from ._streaming import Context, stream
+from ._streaming import (
+    Context,
+    ReceiveMsgStream,
+    MsgStream,
+    stream,
+    context,
+)
 from ._discovery import get_arbiter, find_actor, wait_for_actor
 from ._trionics import open_nursery
 from ._state import current_actor, is_root_process
-from ._exceptions import RemoteActorError, ModuleNotExposed
+from ._exceptions import (
+    RemoteActorError,
+    ModuleNotExposed,
+    ContextCancelled,
+)
 from ._debug import breakpoint, post_mortem
 from . import msg
 from ._root import run, run_daemon, open_root_actor
+from ._portal import Portal
 
 
 __all__ = [
@@ -21,6 +32,7 @@ __all__ = [
     'ModuleNotExposed',
     'MultiError',
     'RemoteActorError',
+    'ContextCancelled',
     'breakpoint',
     'current_actor',
     'find_actor',
@@ -29,11 +41,14 @@ __all__ = [
     'msg',
     'open_nursery',
     'open_root_actor',
+    'Portal',
     'post_mortem',
     'run',
     'run_daemon',
     'stream',
-    'wait_for_actor',
+    'context',
+    'ReceiveMsgStream',
+    'MsgStream',
     'to_asyncio',
     'wait_for_actor',
 ]

tractor/_actor.py

@@ -1,5 +1,6 @@
 """
 Actor primitives and helpers
+
 """
 from collections import defaultdict
 from functools import partial
@@ -11,9 +12,11 @@ import uuid
 import typing
 from typing import Dict, List, Tuple, Any, Optional, Union
 from types import ModuleType
+# import signal
 import sys
 import os
 from contextlib import ExitStack
+import warnings
 
 import trio  # type: ignore
 from trio_typing import TaskStatus
@@ -27,6 +30,8 @@ from ._exceptions import (
     unpack_error,
     ModuleNotExposed,
     is_multi_cancelled,
+    ContextCancelled,
+    TransportClosed,
 )
 from . import _debug
 from ._discovery import get_arbiter
@@ -43,6 +48,7 @@ class ActorFailure(Exception):
 
 
 async def _invoke(
+
     actor: 'Actor',
     cid: str,
     chan: Channel,
@@ -55,15 +61,41 @@ async def _invoke(
     """Invoke local func and deliver result(s) over provided channel.
     """
     treat_as_gen = False
-    cs = None
+
     cancel_scope = trio.CancelScope()
-    ctx = Context(chan, cid, cancel_scope)
+    cs: trio.CancelScope = None
+
+    ctx = Context(chan, cid)
+    context: bool = False
 
     if getattr(func, '_tractor_stream_function', False):
         # handle decorated ``@tractor.stream`` async functions
+        sig = inspect.signature(func)
+        params = sig.parameters
+
+        # compat with old api
         kwargs['ctx'] = ctx
+
+        if 'ctx' in params:
+            warnings.warn(
+                "`@tractor.stream decorated funcs should now declare "
+                "a `stream`  arg, `ctx` is now designated for use with "
+                "@tractor.context",
+                DeprecationWarning,
+                stacklevel=2,
+            )
+
+        elif 'stream' in params:
+            assert 'stream' in params
+            kwargs['stream'] = ctx
+
         treat_as_gen = True
 
+    elif getattr(func, '_tractor_context_function', False):
+        # handle decorated ``@tractor.context`` async function
+        kwargs['ctx'] = ctx
+        context = True
+
     # errors raised inside this block are propgated back to caller
     try:
         if not (
@@ -101,42 +133,78 @@ async def _invoke(
             # `StopAsyncIteration` system here for returning a final
             # value if desired
             await chan.send({'stop': True, 'cid': cid})
+
+        # one way @stream func that gets treated like an async gen
+        elif treat_as_gen:
+            await chan.send({'functype': 'asyncgen', 'cid': cid})
+            # XXX: the async-func may spawn further tasks which push
+            # back values like an async-generator would but must
+            # manualy construct the response dict-packet-responses as
+            # above
+            with cancel_scope as cs:
+                task_status.started(cs)
+                await coro
+
+            if not cs.cancelled_caught:
+                # task was not cancelled so we can instruct the
+                # far end async gen to tear down
+                await chan.send({'stop': True, 'cid': cid})
+
+        elif context:
+            # context func with support for bi-dir streaming
+            await chan.send({'functype': 'context', 'cid': cid})
+
+            async with trio.open_nursery() as scope_nursery:
+                ctx._scope_nursery = scope_nursery
+                cs = scope_nursery.cancel_scope
+                task_status.started(cs)
+                await chan.send({'return': await coro, 'cid': cid})
+
+            if cs.cancelled_caught:
+                if ctx._cancel_called:
+                    msg = f'{func.__name__} cancelled itself',
+
+                else:
+                    msg = f'{func.__name__} was remotely cancelled',
+
+                # task-contex was cancelled so relay to the cancel to caller
+                raise ContextCancelled(
+                    msg,
+                    suberror_type=trio.Cancelled,
+                )
+
         else:
-            if treat_as_gen:
+            # regular async function
-                await chan.send({'functype': 'asyncgen', 'cid': cid})
+            await chan.send({'functype': 'asyncfunc', 'cid': cid})
-                # XXX: the async-func may spawn further tasks which push
+            with cancel_scope as cs:
-                # back values like an async-generator would but must
+                task_status.started(cs)
-                # manualy construct the response dict-packet-responses as
+                await chan.send({'return': await coro, 'cid': cid})
-                # above
-                with cancel_scope as cs:
-                    task_status.started(cs)
-                    await coro
-                if not cs.cancelled_caught:
-                    # task was not cancelled so we can instruct the
-                    # far end async gen to tear down
-                    await chan.send({'stop': True, 'cid': cid})
-            else:
-                # regular async function
-                await chan.send({'functype': 'asyncfunc', 'cid': cid})
-                with cancel_scope as cs:
-                    task_status.started(cs)
-                    await chan.send({'return': await coro, 'cid': cid})
 
     except (Exception, trio.MultiError) as err:
 
-        # TODO: maybe we'll want differnet "levels" of debugging
+        if not is_multi_cancelled(err):
-        # eventualy such as ('app', 'supervisory', 'runtime') ?
+
-        if not isinstance(err, trio.ClosedResourceError) and (
+            log.exception("Actor crashed:")
-            not is_multi_cancelled(err)
+
-        ):
+            # TODO: maybe we'll want different "levels" of debugging
-            # XXX: is there any case where we'll want to debug IPC
+            # eventualy such as ('app', 'supervisory', 'runtime') ?
-            # disconnects? I can't think of a reason that inspecting
+
-            # this type of failure will be useful for respawns or
+            # if not isinstance(err, trio.ClosedResourceError) and (
-            # recovery logic - the only case is some kind of strange bug
+            # if not is_multi_cancelled(err) and (
-            # in `trio` itself?
+
-            entered = await _debug._maybe_enter_pm(err)
+            if not isinstance(err, ContextCancelled) or (
-            if not entered:
+                isinstance(err, ContextCancelled) and ctx._cancel_called
-                log.exception("Actor crashed:")
+            ):
+                # XXX: is there any case where we'll want to debug IPC
+                # disconnects? I can't think of a reason that inspecting
+                # this type of failure will be useful for respawns or
+                # recovery logic - the only case is some kind of strange bug
+                # in `trio` itself?
+                await _debug._maybe_enter_pm(err)
+
+                # entered = await _debug._maybe_enter_pm(err)
+                # if not entered:
+                #     log.exception("Actor crashed:")
 
         # always ship errors back to caller
         err_msg = pack_error(err)
@@ -145,8 +213,10 @@ async def _invoke(
             await chan.send(err_msg)
 
         except trio.ClosedResourceError:
-            log.warning(
+            # if we can't propagate the error that's a big boo boo
-                f"Failed to ship error to caller @ {chan.uid}")
+            log.error(
+                f"Failed to ship error to caller @ {chan.uid} !?"
+            )
 
         if cs is None:
             # error is from above code not from rpc invocation
@@ -195,6 +265,9 @@ class Actor:
     _parent_main_data: Dict[str, str]
     _parent_chan_cs: Optional[trio.CancelScope] = None
 
+    # if started on ``asycio`` running ``trio`` in guest mode
+    _infected_aio: bool = False
+
     def __init__(
         self,
         name: str,
@@ -232,7 +305,8 @@ class Actor:
         # TODO: consider making this a dynamically defined
         # @dataclass once we get py3.7
         self.loglevel = loglevel
-        self._arb_addr = arbiter_addr
+        self._arb_addr = tuple(
+            arbiter_addr) if arbiter_addr is not None else (None, None)
 
         # marked by the process spawning backend at startup
         # will be None for the parent most process started manually
@@ -262,7 +336,8 @@ class Actor:
         self._parent_chan: Optional[Channel] = None
         self._forkserver_info: Optional[
             Tuple[Any, Any, Any, Any, Any]] = None
-        self._actoruid2nursery: Dict[str, 'ActorNursery'] = {}  # type: ignore
+
+        self._actoruid2nursery: Dict[str, 'ActorNursery'] = {}  # type: ignore # noqa
 
     async def wait_for_peer(
         self, uid: Tuple[str, str]
@@ -326,19 +401,34 @@ class Actor:
             raise mne
 
     async def _stream_handler(
+
         self,
         stream: trio.SocketStream,
+
     ) -> None:
         """Entry point for new inbound connections to the channel server.
+
         """
         self._no_more_peers = trio.Event()  # unset
+
         chan = Channel(stream=stream)
         log.info(f"New connection to us {chan}")
 
         # send/receive initial handshake response
         try:
             uid = await self._do_handshake(chan)
-        except StopAsyncIteration:
+
+        except (
+            trio.BrokenResourceError,
+            trio.ClosedResourceError,
+            TransportClosed,
+        ):
+            # XXX: This may propagate up from ``Channel._aiter_recv()``
+            # and ``MsgpackStream._inter_packets()`` on a read from the
+            # stream particularly when the runtime is first starting up
+            # inside ``open_root_actor()`` where there is a check for
+            # a bound listener on the "arbiter" addr.  the reset will be
+            # because the handshake was never meant took place.
             log.warning(f"Channel {chan} failed to handshake")
             return
 
@@ -366,10 +456,24 @@ class Actor:
         try:
             await self._process_messages(chan)
         finally:
+
+            # channel cleanup sequence
+
+            # for (channel, cid) in self._rpc_tasks.copy():
+            #     if channel is chan:
+            #         with trio.CancelScope(shield=True):
+            #             await self._cancel_task(cid, channel)
+
+            #             # close all consumer side task mem chans
+            #             send_chan, _ = self._cids2qs[(chan.uid, cid)]
+            #             assert send_chan.cid == cid  # type: ignore
+            #             await send_chan.aclose()
+
             # Drop ref to channel so it can be gc-ed and disconnected
             log.debug(f"Releasing channel {chan} from {chan.uid}")
             chans = self._peers.get(chan.uid)
             chans.remove(chan)
+
             if not chans:
                 log.debug(f"No more channels for {chan.uid}")
                 self._peers.pop(chan.uid, None)
@@ -382,14 +486,22 @@ class Actor:
 
             # # XXX: is this necessary (GC should do it?)
             if chan.connected():
+                # if the channel is still connected it may mean the far
+                # end has not closed and we may have gotten here due to
+                # an error and so we should at least try to terminate
+                # the channel from this end gracefully.
+
                 log.debug(f"Disconnecting channel {chan}")
                 try:
-                    # send our msg loop terminate sentinel
+                    # send a msg loop terminate sentinel
                     await chan.send(None)
+
+                    # XXX: do we want this?
+                    # causes "[104] connection reset by peer" on other end
                     # await chan.aclose()
+
                 except trio.BrokenResourceError:
-                    log.exception(
+                    log.warning(f"Channel for {chan.uid} was already closed")
-                        f"Channel for {chan.uid} was already zonked..")
 
     async def _push_result(
         self,
@@ -399,22 +511,32 @@ class Actor:
     ) -> None:
         """Push an RPC result to the local consumer's queue.
         """
-        actorid = chan.uid
+        # actorid = chan.uid
-        assert actorid, f"`actorid` can't be {actorid}"
+        assert chan.uid, f"`chan.uid` can't be {chan.uid}"
-        send_chan, recv_chan = self._cids2qs[(actorid, cid)]
+        send_chan, recv_chan = self._cids2qs[(chan.uid, cid)]
         assert send_chan.cid == cid  # type: ignore
 
-        if 'stop' in msg:
+        if 'error' in msg:
-            log.debug(f"{send_chan} was terminated at remote end")
+            ctx = getattr(recv_chan, '_ctx', None)
-            # indicate to consumer that far end has stopped
+            # if ctx:
-            return await send_chan.aclose()
+            #     ctx._error_from_remote_msg(msg)
+
+        #     log.debug(f"{send_chan} was terminated at remote end")
+        #     # indicate to consumer that far end has stopped
+        #     return await send_chan.aclose()
 
         try:
-            log.debug(f"Delivering {msg} from {actorid} to caller {cid}")
+            log.debug(f"Delivering {msg} from {chan.uid} to caller {cid}")
             # maintain backpressure
             await send_chan.send(msg)
 
         except trio.BrokenResourceError:
+            # TODO: what is the right way to handle the case where the
+            # local task has already sent a 'stop' / StopAsyncInteration
+            # to the other side but and possibly has closed the local
+            # feeder mem chan? Do we wait for some kind of ack or just
+            # let this fail silently and bubble up (currently)?
+
             # XXX: local consumer has closed their side
             # so cancel the far end streaming task
             log.warning(f"{send_chan} consumer is already closed")
@@ -423,12 +545,14 @@ class Actor:
         self,
         actorid: Tuple[str, str],
         cid: str
+
     ) -> Tuple[trio.abc.SendChannel, trio.abc.ReceiveChannel]:
+
         log.debug(f"Getting result queue for {actorid} cid {cid}")
         try:
             send_chan, recv_chan = self._cids2qs[(actorid, cid)]
         except KeyError:
-            send_chan, recv_chan = trio.open_memory_channel(1000)
+            send_chan, recv_chan = trio.open_memory_channel(2*10)
             send_chan.cid = cid  # type: ignore
             recv_chan.cid = cid  # type: ignore
             self._cids2qs[(actorid, cid)] = send_chan, recv_chan
@@ -476,15 +600,25 @@ class Actor:
                 # ``scope = Nursery.start()``
                 task_status.started(loop_cs)
                 async for msg in chan:
+
                     if msg is None:  # loop terminate sentinel
+
                         log.debug(
                             f"Cancelling all tasks for {chan} from {chan.uid}")
-                        for (channel, cid) in self._rpc_tasks:
+
+                        for (channel, cid) in self._rpc_tasks.copy():
                             if channel is chan:
                                 await self._cancel_task(cid, channel)
+
+                                # close all consumer side task mem chans
+                                # send_chan, _ = self._cids2qs[(chan.uid, cid)]
+                                # assert send_chan.cid == cid  # type: ignore
+                                # await send_chan.aclose()
+
                         log.debug(
                                 f"Msg loop signalled to terminate for"
                                 f" {chan} from {chan.uid}")
+
                         break
 
                     log.trace(   # type: ignore
@@ -494,6 +628,7 @@ class Actor:
                     if cid:
                         # deliver response to local caller/waiter
                         await self._push_result(chan, cid, msg)
+
                         log.debug(
                             f"Waiting on next msg for {chan} from {chan.uid}")
                         continue
@@ -578,22 +713,36 @@ class Actor:
                     )
                     await self.cancel_rpc_tasks(chan)
 
-        except trio.ClosedResourceError:
+        except (
-            log.error(f"{chan} form {chan.uid} broke")
+            TransportClosed,
+            trio.BrokenResourceError,
+            trio.ClosedResourceError
+        ):
+            # channels "breaking" is ok since we don't have a teardown
+            # handshake for them (yet) and instead we simply bail out
+            # of the message loop and expect the teardown sequence
+            # to clean up.
+            log.error(f"{chan} form {chan.uid} closed abruptly")
+            # raise
+
         except (Exception, trio.MultiError) as err:
             # ship any "internal" exception (i.e. one from internal machinery
             # not from an rpc task) to parent
             log.exception("Actor errored:")
             if self._parent_chan:
                 await self._parent_chan.send(pack_error(err))
-            raise
+
             # if this is the `MainProcess` we expect the error broadcasting
             # above to trigger an error at consuming portal "checkpoints"
+            raise
+
         except trio.Cancelled:
             # debugging only
             log.debug(f"Msg loop was cancelled for {chan}")
             raise
+
         finally:
+            # msg debugging for when he machinery is brokey
             log.debug(
                 f"Exiting msg loop for {chan} from {chan.uid} "
                 f"with last msg:\n{msg}")
@@ -633,7 +782,21 @@ class Actor:
                 _state._runtime_vars.update(rvs)
 
                 for attr, value in parent_data.items():
-                    setattr(self, attr, value)
+
+                    if attr == '_arb_addr':
+                        # XXX: msgspec doesn't support serializing tuples
+                        # so just cash manually here since it's what our
+                        # internals expect.
+                        self._arb_addr = tuple(value)
+
+                    else:
+                        setattr(self, attr, value)
+
+                # Disable sigint handling in children if NOT running in
+                # debug mode; we shouldn't need it thanks to our
+                # cancellation machinery.
+                # if 'debug_mode' not in rvs:
+                #     signal.signal(signal.SIGINT, signal.SIG_IGN)
 
             return chan, accept_addr
 
@@ -1012,15 +1175,19 @@ class Actor:
         parlance.
         """
         await chan.send(self.uid)
-        uid: Tuple[str, str] = await chan.recv()
+        # breakpoint()
+        uid: Tuple[str, str] = tuple(await chan.recv())
 
-        if not isinstance(uid, tuple):
+        # if not isinstance(uid, tuple):
-            raise ValueError(f"{uid} is not a valid uid?!")
+        #     raise ValueError(f"{uid} is not a valid uid?!")
 
         chan.uid = uid
         log.info(f"Handshake with actor {uid}@{chan.raddr} complete")
         return uid
 
+    def is_infected_aio(self) -> bool:
+        return self._infected_aio
+
 
 class Arbiter(Actor):
     """A special actor who knows all the other actors and always has
@@ -1082,8 +1249,9 @@ class Arbiter(Actor):
     async def register_actor(
         self, uid: Tuple[str, str], sockaddr: Tuple[str, int]
     ) -> None:
+        uid = tuple(uid)
         name, uuid = uid
-        self._registry[uid] = sockaddr
+        self._registry[uid] = tuple(sockaddr)
 
         # pop and signal all waiter events
         events = self._waiters.pop(name, ())
@@ -1093,4 +1261,4 @@ class Arbiter(Actor):
                 event.set()
 
     async def unregister_actor(self, uid: Tuple[str, str]) -> None:
-        self._registry.pop(uid)
+        self._registry.pop(tuple(uid))

tractor/_child.py

@@ -19,12 +19,15 @@ def parse_ipaddr(arg):
     return (str(host), int(port))
 
 
+from ._entry import _trio_main
+
 if __name__ == "__main__":
 
     parser = argparse.ArgumentParser()
     parser.add_argument("--uid", type=parse_uid)
     parser.add_argument("--loglevel", type=str)
     parser.add_argument("--parent_addr", type=parse_ipaddr)
+    parser.add_argument("--asyncio", action='store_true')
     args = parser.parse_args()
 
     subactor = Actor(
@@ -36,5 +39,6 @@ if __name__ == "__main__":
 
     _trio_main(
         subactor,
-        parent_addr=args.parent_addr
+        parent_addr=args.parent_addr,
+        infect_asyncio=args.asyncio,
     )

tractor/_debug.py

@@ -1,13 +1,13 @@
 """
 Multi-core debugging for da peeps!
+
 """
 import bdb
 import sys
 from functools import partial
 from contextlib import asynccontextmanager
-from typing import Awaitable, Tuple, Optional, Callable, AsyncIterator
+from typing import Tuple, Optional, Callable, AsyncIterator
 
-from async_generator import aclosing
 import tractor
 import trio
 
@@ -31,14 +31,21 @@ log = get_logger(__name__)
 
 __all__ = ['breakpoint', 'post_mortem']
 
+
+# TODO: wrap all these in a static global class: ``DebugLock`` maybe?
+
 # placeholder for function to set a ``trio.Event`` on debugger exit
 _pdb_release_hook: Optional[Callable] = None
 
 # actor-wide variable pointing to current task name using debugger
-_in_debug = False
+_local_task_in_debug: Optional[str] = None
+
+# actor tree-wide actor uid that supposedly has the tty lock
+_global_actor_in_debug: Optional[Tuple[str, str]] = None
 
 # lock in root actor preventing multi-access to local tty
-_debug_lock = trio.StrictFIFOLock()
+_debug_lock: trio.StrictFIFOLock = trio.StrictFIFOLock()
+_pdb_complete: Optional[trio.Event] = None
 
 # XXX: set by the current task waiting on the root tty lock
 # and must be cancelled if this actor is cancelled via message
@@ -61,19 +68,19 @@ class PdbwTeardown(pdbpp.Pdb):
     # TODO: figure out how to dissallow recursive .set_trace() entry
     # since that'll cause deadlock for us.
     def set_continue(self):
-        global _in_debug
         try:
             super().set_continue()
         finally:
-            _in_debug = False
+            global _local_task_in_debug
+            _local_task_in_debug = None
             _pdb_release_hook()
 
     def set_quit(self):
-        global _in_debug
         try:
             super().set_quit()
         finally:
-            _in_debug = False
+            global _local_task_in_debug
+            _local_task_in_debug = None
             _pdb_release_hook()
 
 
@@ -119,18 +126,22 @@ async def _acquire_debug_lock(uid: Tuple[str, str]) -> AsyncIterator[None]:
     """Acquire a actor local FIFO lock meant to mutex entry to a local
     debugger entry point to avoid tty clobbering by multiple processes.
     """
-    task_name = trio.lowlevel.current_task().name
+    global _debug_lock, _global_actor_in_debug
-    try:
-        log.debug(
-            f"Attempting to acquire TTY lock, remote task: {task_name}:{uid}")
-        await _debug_lock.acquire()
 
+    task_name = trio.lowlevel.current_task().name
+
+    log.debug(
+        f"Attempting to acquire TTY lock, remote task: {task_name}:{uid}")
+
+    async with _debug_lock:
+
+        # _debug_lock._uid = uid
+        _global_actor_in_debug = uid
         log.debug(f"TTY lock acquired, remote task: {task_name}:{uid}")
         yield
 
-    finally:
+    _global_actor_in_debug = None
-        _debug_lock.release()
+    log.debug(f"TTY lock released, remote task: {task_name}:{uid}")
-        log.debug(f"TTY lock released, remote task: {task_name}:{uid}")
 
 
 # @contextmanager
@@ -144,118 +155,180 @@ async def _acquire_debug_lock(uid: Tuple[str, str]) -> AsyncIterator[None]:
 #         signal.signal(signal.SIGINT, prior_handler)
 
 
+@tractor.context
 async def _hijack_stdin_relay_to_child(
+
+    ctx: tractor.Context,
     subactor_uid: Tuple[str, str]
-) -> AsyncIterator[str]:
+
+) -> str:
+
+    global _pdb_complete
+
+    task_name = trio.lowlevel.current_task().name
+
     # TODO: when we get to true remote debugging
-    # this will deliver stdin data
+    # this will deliver stdin data?
-    log.warning(f"Actor {subactor_uid} is WAITING on stdin hijack lock")
+
+    log.debug(
+        "Attempting to acquire TTY lock, "
+        f"remote task: {task_name}:{subactor_uid}"
+    )
+
+    log.debug(f"Actor {subactor_uid} is WAITING on stdin hijack lock")
+
     async with _acquire_debug_lock(subactor_uid):
-        log.warning(f"Actor {subactor_uid} ACQUIRED stdin hijack lock")
 
-        # with _disable_sigint():
+        # XXX: only shield the context sync step!
+        with trio.CancelScope(shield=True):
 
-        # indicate to child that we've locked stdio
+            # indicate to child that we've locked stdio
-        yield 'Locked'
+            await ctx.started('Locked')
+            log.runtime(  # type: ignore
+                f"Actor {subactor_uid} ACQUIRED stdin hijack lock")
 
-        # wait for cancellation of stream by child
+        # wait for unlock pdb by child
-        # indicating debugger is dis-engaged
+        async with ctx.open_stream() as stream:
-        await trio.sleep_forever()
+            try:
+                assert await stream.receive() == 'pdb_unlock'
+
+            except trio.BrokenResourceError:
+                # XXX: there may be a race with the portal teardown
+                # with the calling actor which we can safely ignore
+                # the alternative would be sending an ack message
+                # and allowing the client to wait for us to teardown
+                # first?
+                pass
+
+    log.debug(
+        f"TTY lock released, remote task: {task_name}:{subactor_uid}")
 
     log.debug(f"Actor {subactor_uid} RELEASED stdin hijack lock")
+    return "pdb_unlock_complete"
 
 
-# XXX: We only make this sync in case someone wants to
+async def _breakpoint(debug_func) -> None:
-# overload the ``breakpoint()`` built-in.
-def _breakpoint(debug_func) -> Awaitable[None]:
     """``tractor`` breakpoint entry for engaging pdb machinery
     in subactors.
+
     """
     actor = tractor.current_actor()
-    do_unlock = trio.Event()
+    task_name = trio.lowlevel.current_task().name
+
+    global _pdb_complete, _pdb_release_hook
+    global _local_task_in_debug, _global_actor_in_debug
 
     async def wait_for_parent_stdin_hijack(
         task_status=trio.TASK_STATUS_IGNORED
     ):
         global _debugger_request_cs
+
         with trio.CancelScope() as cs:
             _debugger_request_cs = cs
+
             try:
                 async with get_root() as portal:
-                        async with portal.open_stream_from(
-                            tractor._debug._hijack_stdin_relay_to_child,
-                            subactor_uid=actor.uid,
-                        ) as stream:
 
-                                # block until first yield above
+                    # this syncs to child's ``Context.started()`` call.
-                                async for val in stream:
+                    async with portal.open_context(
 
-                                    assert val == 'Locked'
+                        tractor._debug._hijack_stdin_relay_to_child,
-                                    task_status.started()
+                        subactor_uid=actor.uid,
 
-                                    # with trio.CancelScope(shield=True):
+                    ) as (ctx, val):
-                                    await do_unlock.wait()
+
+                        assert val == 'Locked'
+
+                        async with ctx.open_stream() as stream:
+
+                            # unblock local caller
+                            task_status.started()
+
+                            # TODO: shielding currently can cause hangs...
+                            # with trio.CancelScope(shield=True):
+
+                            await _pdb_complete.wait()
+                            await stream.send('pdb_unlock')
+
+                            # sync with callee termination
+                            assert await ctx.result() == "pdb_unlock_complete"
+
+            except tractor.ContextCancelled:
+                log.warning('Root actor cancelled debug lock')
 
-                                    # trigger cancellation of remote stream
-                                    break
             finally:
                 log.debug(f"Exiting debugger for actor {actor}")
-                global _in_debug
+                global _local_task_in_debug
-                _in_debug = False
+                _local_task_in_debug = None
                 log.debug(f"Child {actor} released parent stdio lock")
 
-    async def _bp():
+    if not _pdb_complete or _pdb_complete.is_set():
-        """Async breakpoint which schedules a parent stdio lock, and once complete
+        _pdb_complete = trio.Event()
-        enters the ``pdbpp`` debugging console.
-        """
-        task_name = trio.lowlevel.current_task().name
 
-        global _in_debug
+    # TODO: need a more robust check for the "root" actor
-
+    if actor._parent_chan and not is_root_process():
-        # TODO: need a more robust check for the "root" actor
+        if _local_task_in_debug:
-        if actor._parent_chan and not is_root_process():
+            if _local_task_in_debug == task_name:
-            if _in_debug:
+                # this task already has the lock and is
-                if _in_debug == task_name:
+                # likely recurrently entering a breakpoint
-                    # this task already has the lock and is
-                    # likely recurrently entering a breakpoint
-                    return
-
-                # if **this** actor is already in debug mode block here
-                # waiting for the control to be released - this allows
-                # support for recursive entries to `tractor.breakpoint()`
-                log.warning(
-                    f"Actor {actor.uid} already has a debug lock, waiting...")
-                await do_unlock.wait()
-                await trio.sleep(0.1)
-
-            # assign unlock callback for debugger teardown hooks
-            global _pdb_release_hook
-            _pdb_release_hook = do_unlock.set
-
-            # mark local actor as "in debug mode" to avoid recurrent
-            # entries/requests to the root process
-            _in_debug = task_name
-
-            # this **must** be awaited by the caller and is done using the
-            # root nursery so that the debugger can continue to run without
-            # being restricted by the scope of a new task nursery.
-            await actor._service_n.start(wait_for_parent_stdin_hijack)
-
-        elif is_root_process():
-            # we also wait in the root-parent for any child that
-            # may have the tty locked prior
-            if _debug_lock.locked():  # root process already has it; ignore
                 return
-            await _debug_lock.acquire()
-            _pdb_release_hook = _debug_lock.release
 
-        # block here one (at the appropriate frame *up* where
+            # if **this** actor is already in debug mode block here
-        # ``breakpoint()`` was awaited and begin handling stdio
+            # waiting for the control to be released - this allows
-        log.debug("Entering the synchronous world of pdb")
+            # support for recursive entries to `tractor.breakpoint()`
-        debug_func(actor)
+            log.warning(f"{actor.uid} already has a debug lock, waiting...")
 
-    # user code **must** await this!
+            await _pdb_complete.wait()
-    return _bp()
+            await trio.sleep(0.1)
+
+        # mark local actor as "in debug mode" to avoid recurrent
+        # entries/requests to the root process
+        _local_task_in_debug = task_name
+
+        # assign unlock callback for debugger teardown hooks
+        _pdb_release_hook = _pdb_complete.set
+
+        # this **must** be awaited by the caller and is done using the
+        # root nursery so that the debugger can continue to run without
+        # being restricted by the scope of a new task nursery.
+        await actor._service_n.start(wait_for_parent_stdin_hijack)
+
+    elif is_root_process():
+
+        # we also wait in the root-parent for any child that
+        # may have the tty locked prior
+        global _debug_lock
+
+        # TODO: wait, what about multiple root tasks acquiring
+        # it though.. shrug?
+        # root process (us) already has it; ignore
+        if _global_actor_in_debug == actor.uid:
+            return
+
+        # XXX: since we need to enter pdb synchronously below,
+        # we have to release the lock manually from pdb completion
+        # callbacks. Can't think of a nicer way then this atm.
+        await _debug_lock.acquire()
+
+        _global_actor_in_debug = actor.uid
+        _local_task_in_debug = task_name
+
+        # the lock must be released on pdb completion
+        def teardown():
+            global _pdb_complete, _debug_lock
+            global _global_actor_in_debug, _local_task_in_debug
+
+            _debug_lock.release()
+            _global_actor_in_debug = None
+            _local_task_in_debug = None
+            _pdb_complete.set()
+
+        _pdb_release_hook = teardown
+
+    # block here one (at the appropriate frame *up* where
+    # ``breakpoint()`` was awaited and begin handling stdio
+    log.debug("Entering the synchronous world of pdb")
+    debug_func(actor)
 
 
 def _mk_pdb():
@@ -276,7 +349,7 @@ def _set_trace(actor=None):
     pdb = _mk_pdb()
 
     if actor is not None:
-        log.runtime(f"\nAttaching pdb to actor: {actor.uid}\n")
+        log.runtime(f"\nAttaching pdb to actor: {actor.uid}\n")  # type: ignore
 
         pdb.set_trace(
             # start 2 levels up in user code
@@ -285,8 +358,8 @@ def _set_trace(actor=None):
 
     else:
         # we entered the global ``breakpoint()`` built-in from sync code
-        global _in_debug, _pdb_release_hook
+        global _local_task_in_debug, _pdb_release_hook
-        _in_debug = 'sync'
+        _local_task_in_debug = 'sync'
 
         def nuttin():
             pass

tractor/_entry.py

@@ -3,23 +3,24 @@ Sub-process entry points.
 """
 from functools import partial
 from typing import Tuple, Any
-import signal
 
 import trio  # type: ignore
 
 from .log import get_console_log, get_logger
 from . import _state
+from .to_asyncio import run_as_asyncio_guest
 
 
 log = get_logger(__name__)
 
 
 def _mp_main(
-    actor: 'Actor',  # type: ignore
+    actor: 'Actor',  # type: ignore # noqa
     accept_addr: Tuple[str, int],
     forkserver_info: Tuple[Any, Any, Any, Any, Any],
     start_method: str,
     parent_addr: Tuple[str, int] = None,
+    infect_asyncio: bool = False,
 ) -> None:
     """The routine called *after fork* which invokes a fresh ``trio.run``
     """
@@ -45,7 +46,11 @@ def _mp_main(
         parent_addr=parent_addr
     )
     try:
-        trio.run(trio_main)
+        if infect_asyncio:
+            actor._infected_aio = True
+            run_as_asyncio_guest(trio_main)
+        else:
+            trio.run(trio_main)
     except KeyboardInterrupt:
         pass  # handle it the same way trio does?
 
@@ -54,15 +59,15 @@ def _mp_main(
 
 
 def _trio_main(
-    actor: 'Actor',  # type: ignore
+    actor: 'Actor',  # type: ignore # noqa
     *,
     parent_addr: Tuple[str, int] = None,
+    infect_asyncio: bool = False,
 ) -> None:
     """Entry point for a `trio_run_in_process` subactor.
+
     """
-    # Disable sigint handling in children;
+    log.info(f"Started new trio process for {actor.uid}")
-    # we don't need it thanks to our cancellation machinery.
-    signal.signal(signal.SIGINT, signal.SIG_IGN)
 
     log.info(f"Started new trio process for {actor.uid}")
 
@@ -83,7 +88,11 @@ def _trio_main(
     )
 
     try:
-        trio.run(trio_main)
+        if infect_asyncio:
+            actor._infected_aio = True
+            run_as_asyncio_guest(trio_main)
+        else:
+            trio.run(trio_main)
     except KeyboardInterrupt:
         log.warning(f"Actor {actor.uid} received KBI")
 

tractor/_exceptions.py

@@ -1,7 +1,7 @@
 """
 Our classy exception set.
 """
-from typing import Dict, Any
+from typing import Dict, Any, Optional, Type
 import importlib
 import builtins
 import traceback
@@ -15,17 +15,16 @@ _this_mod = importlib.import_module(__name__)
 class RemoteActorError(Exception):
     # TODO: local recontruction of remote exception deats
     "Remote actor exception bundled locally"
-    def __init__(self, message, type_str, **msgdata) -> None:
+    def __init__(
-        super().__init__(message)
+        self,
-        for ns in [builtins, _this_mod, trio]:
+        message: str,
-            try:
+        suberror_type: Optional[Type[BaseException]] = None,
-                self.type = getattr(ns, type_str)
+        **msgdata
-                break
-            except AttributeError:
-                continue
-        else:
-            self.type = Exception
 
+    ) -> None:
+        super().__init__(message)
+
+        self.type = suberror_type
         self.msgdata = msgdata
 
     # TODO: a trio.MultiError.catch like context manager
@@ -38,6 +37,14 @@ class InternalActorError(RemoteActorError):
     """
 
 
+class ContextCancelled(RemoteActorError):
+    "Inter-actor task context cancelled itself on the callee side."
+
+
+class TransportClosed(trio.ClosedResourceError):
+    "Underlying channel transport was closed prior to use"
+
+
 class NoResult(RuntimeError):
     "No final result is expected for this actor"
 
@@ -63,19 +70,45 @@ def pack_error(exc: BaseException) -> Dict[str, Any]:
 
 
 def unpack_error(
+
     msg: Dict[str, Any],
     chan=None,
     err_type=RemoteActorError
+
 ) -> Exception:
     """Unpack an 'error' message from the wire
     into a local ``RemoteActorError``.
+
     """
-    tb_str = msg['error'].get('tb_str', '')
+    error = msg['error']
-    return err_type(
+
-        f"{chan.uid}\n" + tb_str,
+    tb_str = error.get('tb_str', '')
+    message = f"{chan.uid}\n" + tb_str
+    type_name = error['type_str']
+    suberror_type: Type[BaseException] = Exception
+
+    if type_name == 'ContextCancelled':
+        err_type = ContextCancelled
+        suberror_type = trio.Cancelled
+
+    else:  # try to lookup a suitable local error type
+        for ns in [builtins, _this_mod, trio]:
+            try:
+                suberror_type = getattr(ns, type_name)
+                break
+            except AttributeError:
+                continue
+
+    exc = err_type(
+        message,
+        suberror_type=suberror_type,
+
+        # unpack other fields into error type init
         **msg['error'],
     )
 
+    return exc
+
 
 def is_multi_cancelled(exc: BaseException) -> bool:
     """Predicate to determine if a ``trio.MultiError`` contains only

tractor/_ipc.py

@@ -1,16 +1,21 @@
 """
 Inter-process comms abstractions
 """
+from functools import partial
+import math
+import struct
 import typing
 from typing import Any, Tuple, Optional
-from functools import partial
 
+from tricycle import BufferedReceiveStream
 import msgpack
+import msgspec
 import trio
 from async_generator import asynccontextmanager
 
 from .log import get_logger
-log = get_logger('ipc')
+from ._exceptions import TransportClosed
+log = get_logger(__name__)
 
 # :eyeroll:
 try:
@@ -21,21 +26,33 @@ except ImportError:
     Unpacker = partial(msgpack.Unpacker, strict_map_key=False)
 
 
-class MsgpackStream:
+class MsgpackTCPStream:
-    """A ``trio.SocketStream`` delivering ``msgpack`` formatted data.
+    '''A ``trio.SocketStream`` delivering ``msgpack`` formatted data
-    """
+    using ``msgpack-python``.
-    def __init__(self, stream: trio.SocketStream) -> None:
+
+    '''
+    def __init__(
+        self,
+        stream: trio.SocketStream,
+
+    ) -> None:
+
         self.stream = stream
         assert self.stream.socket
+
         # should both be IP sockets
         lsockname = stream.socket.getsockname()
         assert isinstance(lsockname, tuple)
         self._laddr = lsockname[:2]
+
         rsockname = stream.socket.getpeername()
         assert isinstance(rsockname, tuple)
         self._raddr = rsockname[:2]
 
+        # start and seed first entry to read loop
         self._agen = self._iter_packets()
+        # self._agen.asend(None) is None
+
         self._send_lock = trio.StrictFIFOLock()
 
     async def _iter_packets(self) -> typing.AsyncGenerator[dict, None]:
@@ -46,16 +63,13 @@ class MsgpackStream:
             use_list=False,
         )
         while True:
-            try:
+            data = await self.stream.receive_some(2**10)
-                data = await self.stream.receive_some(2**10)
+            log.trace(f"received {data}")  # type: ignore
-                log.trace(f"received {data}")  # type: ignore
-            except trio.BrokenResourceError:
-                log.warning(f"Stream connection {self.raddr} broke")
-                return
 
             if data == b'':
-                log.debug(f"Stream connection {self.raddr} was closed")
+                raise TransportClosed(
-                return
+                    f'transport {self} was already closed prior ro read'
+                )
 
             unpacker.feed(data)
             for packet in unpacker:
@@ -73,7 +87,8 @@ class MsgpackStream:
     async def send(self, data: Any) -> None:
         async with self._send_lock:
             return await self.stream.send_all(
-                msgpack.dumps(data, use_bin_type=True))
+                msgpack.dumps(data, use_bin_type=True)
+            )
 
     async def recv(self) -> Any:
         return await self._agen.asend(None)
@@ -85,26 +100,92 @@ class MsgpackStream:
         return self.stream.socket.fileno() != -1
 
 
+class MsgspecTCPStream(MsgpackTCPStream):
+    '''A ``trio.SocketStream`` delivering ``msgpack`` formatted data
+    using ``msgspec``.
+
+    '''
+    ms_encode = msgspec.Encoder().encode
+
+    def __init__(
+        self,
+        stream: trio.SocketStream,
+        prefix_size: int = 4,
+
+    ) -> None:
+        super().__init__(stream)
+        self.recv_stream = BufferedReceiveStream(transport_stream=stream)
+        self.prefix_size = prefix_size
+
+    async def _iter_packets(self) -> typing.AsyncGenerator[dict, None]:
+        """Yield packets from the underlying stream.
+        """
+        decoder = msgspec.Decoder()  # dict[str, Any])
+
+        while True:
+            try:
+                header = await self.recv_stream.receive_exactly(4)
+
+            except (ValueError):
+                raise TransportClosed(
+                    f'transport {self} was already closed prior ro read'
+                )
+
+            if header == b'':
+                raise TransportClosed(
+                    f'transport {self} was already closed prior ro read'
+                )
+
+            size, = struct.unpack("<I", header)
+
+            log.trace(f'received header {size}')
+
+            msg_bytes = await self.recv_stream.receive_exactly(size)
+
+            log.trace(f"received {msg_bytes}")  # type: ignore
+            yield decoder.decode(msg_bytes)
+
+    async def send(self, data: Any) -> None:
+        async with self._send_lock:
+
+            bytes_data = self.ms_encode(data)
+
+            # supposedly the fastest says,
+            # https://stackoverflow.com/a/54027962
+            size: int = struct.pack("<I", len(bytes_data))
+
+            return await self.stream.send_all(size + bytes_data)
+
+
 class Channel:
     """An inter-process channel for communication between (remote) actors.
 
     Currently the only supported transport is a ``trio.SocketStream``.
     """
     def __init__(
+
         self,
         destaddr: Optional[Tuple[str, int]] = None,
         on_reconnect: typing.Callable[..., typing.Awaitable] = None,
         auto_reconnect: bool = False,
         stream: trio.SocketStream = None,  # expected to be active
+
+        # stream_serializer_type: type = MsgspecTCPStream,
+        stream_serializer_type: type = MsgpackTCPStream,
+
     ) -> None:
+
         self._recon_seq = on_reconnect
         self._autorecon = auto_reconnect
-        self.msgstream: Optional[MsgpackStream] = MsgpackStream(
+        self.stream_serializer_type = stream_serializer_type
+        self.msgstream: Optional[type] = stream_serializer_type(
             stream) if stream else None
+
         if self.msgstream and destaddr:
             raise ValueError(
                 f"A stream was provided with local addr {self.laddr}"
             )
+
         self._destaddr = self.msgstream.raddr if self.msgstream else destaddr
         # set after handshake - always uid of far end
         self.uid: Optional[Tuple[str, str]] = None
@@ -112,6 +193,8 @@ class Channel:
         self._exc: Optional[Exception] = None
         self._agen = self._aiter_recv()
 
+        self._closed: bool = False
+
     def __repr__(self) -> str:
         if self.msgstream:
             return repr(
@@ -128,35 +211,52 @@ class Channel:
         return self.msgstream.raddr if self.msgstream else None
 
     async def connect(
-        self, destaddr: Tuple[Any, ...] = None,
+        self,
+        destaddr: Tuple[Any, ...] = None,
         **kwargs
+
     ) -> trio.SocketStream:
+
         if self.connected():
             raise RuntimeError("channel is already connected?")
+
         destaddr = destaddr or self._destaddr
         assert isinstance(destaddr, tuple)
-        stream = await trio.open_tcp_stream(*destaddr, **kwargs)
+
-        self.msgstream = MsgpackStream(stream)
+        stream = await trio.open_tcp_stream(
+            *destaddr,
+            happy_eyeballs_delay=math.inf,
+            **kwargs
+        )
+        self.msgstream = self.stream_serializer_type(stream)
         return stream
 
     async def send(self, item: Any) -> None:
+
         log.trace(f"send `{item}`")  # type: ignore
         assert self.msgstream
+
         await self.msgstream.send(item)
 
     async def recv(self) -> Any:
         assert self.msgstream
+
         try:
             return await self.msgstream.recv()
+
         except trio.BrokenResourceError:
             if self._autorecon:
                 await self._reconnect()
                 return await self.recv()
 
+            raise
+
     async def aclose(self) -> None:
         log.debug(f"Closing {self}")
         assert self.msgstream
         await self.msgstream.stream.aclose()
+        self._closed = True
+        log.error(f'CLOSING CHAN {self}')
 
     async def __aenter__(self):
         await self.connect()

tractor/_portal.py

@@ -17,7 +17,12 @@ from async_generator import asynccontextmanager
 from ._state import current_actor
 from ._ipc import Channel
 from .log import get_logger
-from ._exceptions import unpack_error, NoResult, RemoteActorError
+from ._exceptions import (
+    unpack_error,
+    NoResult,
+    RemoteActorError,
+    ContextCancelled,
+)
 from ._streaming import Context, ReceiveMsgStream
 
 
@@ -84,7 +89,7 @@ class Portal:
         ns: str,
         func: str,
         kwargs,
-    ) -> Tuple[str, trio.abc.ReceiveChannel, str, Dict[str, Any]]:
+    ) -> Tuple[str, trio.MemoryReceiveChannel, str, Dict[str, Any]]:
         """Submit a function to be scheduled and run by actor, return the
         associated caller id, response queue, response type str,
         first message packet as a tuple.
@@ -172,6 +177,7 @@ class Portal:
                 f"Cancelling all streams with {self.channel.uid}")
             for stream in self._streams.copy():
                 try:
+                    # with trio.CancelScope(shield=True):
                     await stream.aclose()
                 except trio.ClosedResourceError:
                     # don't error the stream having already been closed
@@ -312,13 +318,23 @@ class Portal:
 
         ctx = Context(self.channel, cid, _portal=self)
         try:
-            async with ReceiveMsgStream(ctx, recv_chan, self) as rchan:
+            # deliver receive only stream
+            async with ReceiveMsgStream(ctx, recv_chan) as rchan:
                 self._streams.add(rchan)
                 yield rchan
+
         finally:
+
             # cancel the far end task on consumer close
+            # NOTE: this is a special case since we assume that if using
+            # this ``.open_fream_from()`` api, the stream is one a one
+            # time use and we couple the far end tasks's lifetime to
+            # the consumer's scope; we don't ever send a `'stop'`
+            # message right now since there shouldn't be a reason to
+            # stop and restart the stream, right?
             try:
                 await ctx.cancel()
+
             except trio.ClosedResourceError:
                 # if the far end terminates before we send a cancel the
                 # underlying transport-channel may already be closed.
@@ -326,16 +342,105 @@ class Portal:
 
             self._streams.remove(rchan)
 
-    # @asynccontextmanager
+    @asynccontextmanager
-    # async def open_context(
+    async def open_context(
-    #     self,
+
-    #     func: Callable,
+        self,
-    #     **kwargs,
+        func: Callable,
-    # ) -> Context:
+        cancel_on_exit: bool = False,
-    #     # TODO
+        **kwargs,
-    #     elif resptype == 'context':  # context manager style setup/teardown
+
-    #         # TODO likely not here though
+    ) -> AsyncGenerator[Tuple[Context, Any], None]:
-    #         raise NotImplementedError
+        '''Open an inter-actor task context.
+
+        This is a synchronous API which allows for deterministic
+        setup/teardown of a remote task. The yielded ``Context`` further
+        allows for opening bidirectional streams, explicit cancellation
+        and synchronized final result collection. See ``tractor.Context``.
+
+        '''
+        # conduct target func method structural checks
+        if not inspect.iscoroutinefunction(func) and (
+            getattr(func, '_tractor_contex_function', False)
+        ):
+            raise TypeError(
+                f'{func} must be an async generator function!')
+
+        fn_mod_path, fn_name = func_deats(func)
+
+        recv_chan: Optional[trio.MemoryReceiveChannel] = None
+
+        cid, recv_chan, functype, first_msg = await self._submit(
+            fn_mod_path, fn_name, kwargs)
+
+        assert functype == 'context'
+        msg = await recv_chan.receive()
+
+        try:
+            # the "first" value here is delivered by the callee's
+            # ``Context.started()`` call.
+            first = msg['started']
+
+        except KeyError:
+            assert msg.get('cid'), ("Received internal error at context?")
+
+            if msg.get('error'):
+                # raise the error message
+                raise unpack_error(msg, self.channel)
+            else:
+                raise
+
+        # deliver context instance and .started() msg value in open
+        # tuple.
+        try:
+            async with trio.open_nursery() as scope_nursery:
+                ctx = Context(
+                    self.channel,
+                    cid,
+                    _portal=self,
+                    _recv_chan=recv_chan,
+                    _scope_nursery=scope_nursery,
+                )
+                recv_chan._ctx = ctx
+
+                yield ctx, first
+
+            log.info(f'Context for {func.__name__} completed')
+
+            if cancel_on_exit:
+                await ctx.cancel()
+
+            else:
+                if not ctx._cancel_called:
+                    await ctx.result()
+
+            await recv_chan.aclose()
+
+            # except TypeError:
+            #     # if fn_name == '_emsd_main':
+            #     import tractor
+            #     await tractor.breakpoint()
+
+        except ContextCancelled:
+            if not ctx._cancel_called:
+                raise
+
+            # if the context was cancelled by client code
+            # then we don't need to raise since user code
+            # is expecting this and the block should exit.
+            else:
+                log.debug(f'Context {ctx} cancelled gracefully')
+
+        except trio.Cancelled:
+            # the context cancels itself on any deviation
+            await ctx.cancel()
+            raise
+
+        # finally:
+        #     log.info(f'Context for {func.__name__} completed')
+
+        # finally:
+        #     if recv_chan is not None:
 
 
 @dataclass
@@ -374,6 +479,7 @@ async def open_portal(
     was_connected = False
 
     async with maybe_open_nursery(nursery, shield=shield) as nursery:
+
         if not channel.connected():
             await channel.connect()
             was_connected = True
@@ -395,11 +501,12 @@ async def open_portal(
         portal = Portal(channel)
         try:
             yield portal
+
         finally:
             await portal.aclose()
 
             if was_connected:
-                # cancel remote channel-msg loop
+                # gracefully signal remote channel-msg loop
                 await channel.send(None)
 
             # cancel background msg loop task

tractor/_root.py

@@ -174,8 +174,7 @@ async def open_root_actor(
 
             finally:
                 logger.info("Shutting down root actor")
-                with trio.CancelScope(shield=True):
+                await actor.cancel()
-                    await actor.cancel()
     finally:
         _state._current_actor = None
         logger.info("Root actor terminated")
@@ -227,7 +226,7 @@ def run(
 
 
 def run_daemon(
-    rpc_module_paths: List[str],
+    enable_modules: List[str],
     **kwargs
 ) -> None:
     """Spawn daemon actor which will respond to RPC.
@@ -236,9 +235,9 @@ def run_daemon(
     ``tractor.run(trio.sleep(float('inf')))`` such that the first actor spawned
     is meant to run forever responding to RPC requests.
     """
-    kwargs['rpc_module_paths'] = list(rpc_module_paths)
+    kwargs['enable_modules'] = list(enable_modules)
 
-    for path in rpc_module_paths:
+    for path in enable_modules:
         importlib.import_module(path)
 
     return run(partial(trio.sleep, float('inf')), **kwargs)

tractor/_spawn.py

@@ -22,7 +22,13 @@ from multiprocessing import forkserver  # type: ignore
 from typing import Tuple
 
 from . import _forkserver_override
-from ._state import current_actor, is_main_process
+from ._state import (
+    current_actor,
+    is_main_process,
+    is_root_process,
+    _runtime_vars,
+)
+
 from .log import get_logger
 from ._portal import Portal
 from ._actor import Actor, ActorFailure
@@ -141,7 +147,7 @@ async def cancel_on_completion(
             )
 
         else:
-            log.info(
+            log.runtime(
                 f"Cancelling {portal.channel.uid} gracefully "
                 f"after result {result}")
 
@@ -153,6 +159,7 @@ async def cancel_on_completion(
 async def spawn_subactor(
     subactor: 'Actor',
     parent_addr: Tuple[str, int],
+    infect_asyncio: bool,
 ):
     spawn_cmd = [
         sys.executable,
@@ -177,29 +184,55 @@ async def spawn_subactor(
             subactor.loglevel
         ]
 
+    # Tell child to run in guest mode on top of ``asyncio`` loop
+    if infect_asyncio:
+        spawn_cmd.append("--asyncio")
+
     proc = await trio.open_process(spawn_cmd)
     try:
         yield proc
+
     finally:
+        log.debug(f"Attempting to kill {proc}")
+
         # XXX: do this **after** cancellation/tearfown
         # to avoid killing the process too early
         # since trio does this internally on ``__aexit__()``
 
-        # NOTE: we always "shield" join sub procs in
+        if (
-        # the outer scope since no actor zombies are
+            is_root_process()
-        # ever allowed. This ``__aexit__()`` also shields
-        # internally.
-        log.debug(f"Attempting to kill {proc}")
 
-        # NOTE: this timeout effectively does nothing right now since
+            # XXX: basically the pre-closing of stdstreams in a
-        # we are shielding the ``.wait()`` inside ``new_proc()`` which
+            # root-processe's ``trio.Process.aclose()`` can clobber
-        # will pretty much never release until the process exits.
+            # any existing debugger session so we avoid
-        with trio.move_on_after(3) as cs:
+            and _runtime_vars['_debug_mode']
-            async with proc:
+        ):
-                log.debug(f"Terminating {proc}")
+            # XXX: this is ``trio.Process.aclose()`` minus
-        if cs.cancelled_caught:
+            # the std-streams pre-closing steps and ``Process.kill()``
-            log.critical(f"HARD KILLING {proc}")
+            # calls.
-            proc.kill()
+            try:
+                await proc.wait()
+            finally:
+                if proc.returncode is None:
+                    # XXX: skip this when in debug and a session might
+                    # still be live
+                    # proc.kill()
+                    with trio.CancelScope(shield=True):
+                        await proc.wait()
+        else:
+            # NOTE: this timeout used to do nothing since we were shielding
+            # the ``.wait()`` inside ``new_proc()`` which will pretty much
+            # never release until the process exits, now it acts as
+            # a hard-kill time ultimatum.
+            with trio.move_on_after(3) as cs:
+
+                # NOTE: This ``__aexit__()`` shields internally.
+                async with proc:  # calls ``trio.Process.aclose()``
+                    log.debug(f"Terminating {proc}")
+
+            if cs.cancelled_caught:
+                log.critical(f"HARD KILLING {proc}")
+                proc.kill()
 
 
 async def new_proc(
@@ -212,7 +245,7 @@ async def new_proc(
     parent_addr: Tuple[str, int],
     _runtime_vars: Dict[str, Any],  # serialized and sent to _child
     *,
-    use_trio_run_in_process: bool = False,
+    infect_asyncio: bool = False,
     task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED
 ) -> None:
     """Create a new ``multiprocessing.Process`` using the
@@ -223,13 +256,14 @@ async def new_proc(
     # mark the new actor with the global spawn method
     subactor._spawn_method = _spawn_method
 
-    if use_trio_run_in_process or _spawn_method == 'trio':
+    if _spawn_method == 'trio':
         async with trio.open_nursery() as nursery:
             async with spawn_subactor(
                 subactor,
                 parent_addr,
+                infect_asyncio=infect_asyncio
             ) as proc:
-                log.info(f"Started {proc}")
+                log.runtime(f"Started {proc}")
 
                 # wait for actor to spawn and connect back to us
                 # channel should have handshake completed by the
@@ -305,6 +339,7 @@ async def new_proc(
             bind_addr=bind_addr,
             parent_addr=parent_addr,
             _runtime_vars=_runtime_vars,
+            infect_asyncio=infect_asyncio,
             task_status=task_status,
         )
 
@@ -320,7 +355,7 @@ async def mp_new_proc(
     parent_addr: Tuple[str, int],
     _runtime_vars: Dict[str, Any],  # serialized and sent to _child
     *,
-    use_trio_run_in_process: bool = False,
+    infect_asyncio: bool = False,
     task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED
 
 ) -> None:
@@ -366,6 +401,7 @@ async def mp_new_proc(
                 fs_info,
                 start_method,
                 parent_addr,
+                infect_asyncio,
             ),
             # daemon=True,
             name=name,
@@ -380,7 +416,7 @@ async def mp_new_proc(
         if not proc.is_alive():
             raise ActorFailure("Couldn't start sub-actor?")
 
-        log.info(f"Started {proc}")
+        log.runtime(f"Started {proc}")
 
         try:
             # wait for actor to spawn and connect back to us

tractor/_streaming.py

@@ -1,41 +1,324 @@
+"""
+Message stream types and APIs.
+
+"""
 import inspect
-from contextlib import contextmanager  # , asynccontextmanager
+from contextlib import contextmanager, asynccontextmanager
 from dataclasses import dataclass
-from typing import Any, Iterator, Optional
+from typing import (
+    Any, Iterator, Optional, Callable,
+    AsyncGenerator, Dict,
+)
+
 import warnings
 
 import trio
 
 from ._ipc import Channel
 from ._exceptions import unpack_error
+from ._state import current_actor
 from .log import get_logger
 
 
 log = get_logger(__name__)
 
 
-@dataclass(frozen=True)
+# TODO: generic typing like trio's receive channel
-class Context:
+# but with msgspec messages?
-    """An IAC (inter-actor communication) context.
+# class ReceiveChannel(AsyncResource, Generic[ReceiveType]):
 
-    Allows maintaining task or protocol specific state between communicating
-    actors. A unique context is created on the receiving end for every request
-    to a remote actor.
 
-    A context can be cancelled and (eventually) restarted from
+class ReceiveMsgStream(trio.abc.ReceiveChannel):
-    either side of the underlying IPC channel.
+    """A wrapper around a ``trio._channel.MemoryReceiveChannel`` with
+    special behaviour for signalling stream termination across an
+    inter-actor ``Channel``. This is the type returned to a local task
+    which invoked a remote streaming function using `Portal.run()`.
 
-    A context can be used to open task oriented message streams.
+    Termination rules:
+
+    - if the local task signals stop iteration a cancel signal is
+      relayed to the remote task indicating to stop streaming
+    - if the remote task signals the end of a stream, raise
+      a ``StopAsyncIteration`` to terminate the local ``async for``
 
     """
+    def __init__(
+        self,
+        ctx: 'Context',  # typing: ignore # noqa
+        rx_chan: trio.abc.ReceiveChannel,
+        shield: bool = False,
+    ) -> None:
+        self._ctx = ctx
+        self._rx_chan = rx_chan
+        self._shielded = shield
+
+        # flag to denote end of stream
+        self._eoc: bool = False
+
+    # delegate directly to underlying mem channel
+    def receive_nowait(self):
+        msg = self._rx_chan.receive_nowait()
+        return msg['yield']
+
+    async def receive(self):
+        # see ``.aclose()`` for notes on the old behaviour prior to
+        # introducing this
+        if self._eoc:
+            raise trio.EndOfChannel
+
+        try:
+            # if self._ctx.chan.uid[0] == 'brokerd.ib':
+            #     breakpoint()
+
+            msg = await self._rx_chan.receive()
+            return msg['yield']
+
+        except KeyError:
+            # internal error should never get here
+            assert msg.get('cid'), ("Received internal error at portal?")
+
+            # TODO: handle 2 cases with 3.10 match syntax
+            # - 'stop'
+            # - 'error'
+            # possibly just handle msg['stop'] here!
+
+            if msg.get('stop'):
+                log.debug(f"{self} was stopped at remote end")
+
+                # # when the send is closed we assume the stream has
+                # # terminated and signal this local iterator to stop
+                # await self.aclose()
+
+                # XXX: this causes ``ReceiveChannel.__anext__()`` to
+                # raise a ``StopAsyncIteration`` **and** in our catch
+                # block below it will trigger ``.aclose()``.
+                raise trio.EndOfChannel
+
+            # TODO: test that shows stream raising an expected error!!!
+            elif msg.get('error'):
+                # raise the error message
+                raise unpack_error(msg, self._ctx.chan)
+
+            else:
+                raise
+
+        except (
+            trio.ClosedResourceError,  # by self._rx_chan
+            trio.EndOfChannel,  # by self._rx_chan or `stop` msg from far end
+            trio.Cancelled,  # by local cancellation
+        ):
+            # XXX: we close the stream on any of these error conditions:
+
+            # a ``ClosedResourceError`` indicates that the internal
+            # feeder memory receive channel was closed likely by the
+            # runtime after the associated transport-channel
+            # disconnected or broke.
+
+            # an ``EndOfChannel`` indicates either the internal recv
+            # memchan exhausted **or** we raisesd it just above after
+            # receiving a `stop` message from the far end of the stream.
+
+            # Previously this was triggered by calling ``.aclose()`` on
+            # the send side of the channel inside
+            # ``Actor._push_result()`` (should still be commented code
+            # there - which should eventually get removed), but now the
+            # 'stop' message handling has been put just above.
+
+            # TODO: Locally, we want to close this stream gracefully, by
+            # terminating any local consumers tasks deterministically.
+            # One we have broadcast support, we **don't** want to be
+            # closing this stream and not flushing a final value to
+            # remaining (clone) consumers who may not have been
+            # scheduled to receive it yet.
+
+            # when the send is closed we assume the stream has
+            # terminated and signal this local iterator to stop
+            await self.aclose()
+
+            raise  # propagate
+
+        # except trio.Cancelled:
+        #     if not self._shielded:
+        #         # if shielded we don't propagate a cancelled
+        #         raise
+
+        # except trio.Cancelled:
+        #     # relay cancels to the remote task
+        #     await self.aclose()
+        #     raise
+
+    @contextmanager
+    def shield(
+        self
+    ) -> Iterator['ReceiveMsgStream']:  # noqa
+        """Shield this stream's underlying channel such that a local consumer task
+        can be cancelled (and possibly restarted) using ``trio.Cancelled``.
+
+        Note that here, "shielding" here guards against relaying
+        a ``'stop'`` message to the far end of the stream thus keeping
+        the stream machinery active and ready for further use, it does
+        not have anything to do with an internal ``trio.CancelScope``.
+
+        """
+        self._shielded = True
+        yield self
+        self._shielded = False
+
+    async def aclose(self):
+        """Cancel associated remote actor task and local memory channel
+        on close.
+
+        """
+        # XXX: keep proper adherance to trio's `.aclose()` semantics:
+        # https://trio.readthedocs.io/en/stable/reference-io.html#trio.abc.AsyncResource.aclose
+        rx_chan = self._rx_chan
+
+        if rx_chan._closed:  # or self._eoc:
+            log.warning(f"{self} is already closed")
+
+            # this stream has already been closed so silently succeed as
+            # per ``trio.AsyncResource`` semantics.
+            # https://trio.readthedocs.io/en/stable/reference-io.html#trio.abc.AsyncResource.aclose
+            return
+
+        # TODO: broadcasting to multiple consumers
+        # stats = rx_chan.statistics()
+        # if stats.open_receive_channels > 1:
+        #     # if we've been cloned don't kill the stream
+        #     log.debug(
+        #       "there are still consumers running keeping stream alive")
+        #     return
+
+        if self._shielded:
+            log.warning(f"{self} is shielded, portal channel being kept alive")
+            return
+
+        # XXX: This must be set **AFTER** the shielded test above!
+        self._eoc = True
+
+        # NOTE: this is super subtle IPC messaging stuff:
+        # Relay stop iteration to far end **iff** we're
+        # in bidirectional mode. If we're only streaming
+        # *from* one side then that side **won't** have an
+        # entry in `Actor._cids2qs` (maybe it should though?).
+        # So any `yield` or `stop` msgs sent from the caller side
+        # will cause key errors on the callee side since there is
+        # no entry for a local feeder mem chan since the callee task
+        # isn't expecting messages to be sent by the caller.
+        # Thus, we must check that this context DOES NOT
+        # have a portal reference to ensure this is indeed the callee
+        # side and can relay a 'stop'.
+
+        # In the bidirectional case, `Context.open_stream()` will create
+        # the `Actor._cids2qs` entry from a call to
+        # `Actor.get_memchans()` and will send the stop message in
+        # ``__aexit__()`` on teardown so it **does not** need to be
+        # called here.
+        if not self._ctx._portal:
+            try:
+                # only for 2 way streams can we can send
+                # stop from the caller side
+                await self._ctx.send_stop()
+
+            except (
+                trio.BrokenResourceError,
+                trio.ClosedResourceError
+            ):
+                # the underlying channel may already have been pulled
+                # in which case our stop message is meaningless since
+                # it can't traverse the transport.
+                log.debug(f'Channel for {self} was already closed')
+
+        # close the local mem chan ``self._rx_chan`` ??!?
+
+        # DEFINITELY NOT if we're a bi-dir ``MsgStream``!
+        # BECAUSE this same core-msg-loop mem recv-chan is used to deliver
+        # the potential final result from the surrounding inter-actor
+        # `Context` so we don't want to close it until that context has
+        # run to completion.
+
+        # XXX: Notes on old behaviour:
+        # await rx_chan.aclose()
+
+        # In the receive-only case, ``Portal.open_stream_from()`` used
+        # to rely on this call explicitly on teardown such that a new
+        # call to ``.receive()`` after ``rx_chan`` had been closed, would
+        # result in us raising a ``trio.EndOfChannel`` (since we
+        # remapped the ``trio.ClosedResourceError`). However, now if for some
+        # reason the stream's consumer code tries to manually receive a new
+        # value before ``.aclose()`` is called **but** the far end has
+        # stopped `.receive()` **must** raise ``trio.EndofChannel`` in
+        # order to avoid an infinite hang on ``.__anext__()``; this is
+        # why we added ``self._eoc`` to denote stream closure indepedent
+        # of ``rx_chan``.
+
+        # In theory we could still use this old method and close the
+        # underlying msg-loop mem chan as above and then **not** check
+        # for ``self._eoc`` in ``.receive()`` (if for some reason we
+        # think that check is a bottle neck - not likely) **but** then
+        # we would need to map the resulting
+        # ``trio.ClosedResourceError`` to a ``trio.EndOfChannel`` in
+        # ``.receive()`` (as it originally was before bi-dir streaming
+        # support) in order to trigger stream closure. The old behaviour
+        # is arguably more confusing since we lose detection of the
+        # runtime's closure of ``rx_chan`` in the case where we may
+        # still need to consume msgs that are "in transit" from the far
+        # end (eg. for ``Context.result()``).
+
+
+class MsgStream(ReceiveMsgStream, trio.abc.Channel):
+    """
+    Bidirectional message stream for use within an inter-actor actor
+    ``Context```.
+
+    """
+    async def send(
+        self,
+        data: Any
+    ) -> None:
+        '''Send a message over this stream to the far end.
+
+        '''
+        await self._ctx.chan.send({'yield': data, 'cid': self._ctx.cid})
+
+    # TODO: but make it broadcasting to consumers
+    def clone(self):
+        """Clone this receive channel allowing for multi-task
+        consumption from the same channel.
+
+        """
+        return MsgStream(
+            self._ctx,
+            self._rx_chan.clone(),
+        )
+
+
+@dataclass
+class Context:
+    '''An inter-actor task communication context.
+
+    Allows maintaining task or protocol specific state between
+    2 communicating actor tasks. A unique context is created on the
+    callee side/end for every request to a remote actor from a portal.
+
+    A context can be cancelled and (possibly eventually restarted) from
+    either side of the underlying IPC channel.
+
+    A context can be used to open task oriented message streams and can
+    be thought of as an IPC aware inter-actor cancel scope.
+
+    '''
     chan: Channel
     cid: str
 
     # only set on the caller side
     _portal: Optional['Portal'] = None    # type: ignore # noqa
+    _recv_chan: Optional[trio.MemoryReceiveChannel] = None
+    _result: Optional[Any] = False
+    _cancel_called: bool = False
 
     # only set on the callee side
-    _cancel_scope: Optional[trio.CancelScope] = None
+    _scope_nursery: Optional[trio.Nursery] = None
 
     async def send_yield(self, data: Any) -> None:
 
@@ -50,53 +333,210 @@ class Context:
     async def send_stop(self) -> None:
         await self.chan.send({'stop': True, 'cid': self.cid})
 
+    def _error_from_remote_msg(
+        self,
+        msg: Dict[str, Any],
+
+    ) -> None:
+        async def raiser():
+            raise unpack_error(msg, self.chan)
+
+        self._scope_nursery.start_soon(raiser)
+
     async def cancel(self) -> None:
-        """Cancel this inter-actor-task context.
+        '''Cancel this inter-actor-task context.
 
         Request that the far side cancel it's current linked context,
-        timeout quickly to sidestep 2-generals...
+        Timeout quickly in an attempt to sidestep 2-generals...
 
-        """
+        '''
-        assert self._portal, (
+        self._cancel_called = True
-            "No portal found, this is likely a callee side context")
 
-        cid = self.cid
+        if self._portal:  # caller side:
-        with trio.move_on_after(0.5) as cs:
+            if not self._portal:
-            cs.shield = True
+                raise RuntimeError(
-            log.warning(
+                    "No portal found, this is likely a callee side context"
-                f"Cancelling stream {cid} to "
+                )
-                f"{self._portal.channel.uid}")
 
-            # NOTE: we're telling the far end actor to cancel a task
+            cid = self.cid
-            # corresponding to *this actor*. The far end local channel
+            with trio.move_on_after(0.5) as cs:
-            # instance is passed to `Actor._cancel_task()` implicitly.
+                cs.shield = True
-            await self._portal.run_from_ns('self', '_cancel_task', cid=cid)
-
-        if cs.cancelled_caught:
-            # XXX: there's no way to know if the remote task was indeed
-            # cancelled in the case where the connection is broken or
-            # some other network error occurred.
-            if not self._portal.channel.connected():
                 log.warning(
-                    "May have failed to cancel remote task "
+                    f"Cancelling stream {cid} to "
-                    f"{cid} for {self._portal.channel.uid}")
+                    f"{self._portal.channel.uid}")
 
+                # NOTE: we're telling the far end actor to cancel a task
+                # corresponding to *this actor*. The far end local channel
+                # instance is passed to `Actor._cancel_task()` implicitly.
+                await self._portal.run_from_ns('self', '_cancel_task', cid=cid)
+
+            if cs.cancelled_caught:
+                # XXX: there's no way to know if the remote task was indeed
+                # cancelled in the case where the connection is broken or
+                # some other network error occurred.
+                # if not self._portal.channel.connected():
+                if not self.chan.connected():
+                    log.warning(
+                        "May have failed to cancel remote task "
+                        f"{cid} for {self._portal.channel.uid}")
+        else:
+            # ensure callee side
+            assert self._scope_nursery
+            # TODO: should we have an explicit cancel message
+            # or is relaying the local `trio.Cancelled` as an
+            # {'error': trio.Cancelled, cid: "blah"} enough?
+            # This probably gets into the discussion in
+            # https://github.com/goodboy/tractor/issues/36
+            self._scope_nursery.cancel_scope.cancel()
+
+        if self._recv_chan:
+            await self._recv_chan.aclose()
+
+    @asynccontextmanager
+    async def open_stream(
+
+        self,
+        shield: bool = False,
+
+    ) -> AsyncGenerator[MsgStream, None]:
+        '''Open a ``MsgStream``, a bi-directional stream connected to the
+        cross-actor (far end) task for this ``Context``.
+
+        This context manager must be entered on both the caller and
+        callee for the stream to logically be considered "connected".
+
+        A ``MsgStream`` is currently "one-shot" use, meaning if you
+        close it you can not "re-open" it for streaming and instead you
+        must re-establish a new surrounding ``Context`` using
+        ``Portal.open_context()``.  In the future this may change but
+        currently there seems to be no obvious reason to support
+        "re-opening":
+            - pausing a stream can be done with a message.
+            - task errors will normally require a restart of the entire
+              scope of the inter-actor task context due to the nature of
+              ``trio``'s cancellation system.
+
+        '''
+        actor = current_actor()
+
+        # here we create a mem chan that corresponds to the
+        # far end caller / callee.
+
+        # NOTE: in one way streaming this only happens on the
+        # caller side inside `Actor.send_cmd()` so if you try
+        # to send a stop from the caller to the callee in the
+        # single-direction-stream case you'll get a lookup error
+        # currently.
+        _, recv_chan = actor.get_memchans(
+            self.chan.uid,
+            self.cid
+        )
+
+        # XXX: If the underlying receive mem chan has been closed then
+        # likely client code has already exited a ``.open_stream()``
+        # block prior. we error here until such a time that we decide
+        # allowing streams to be "re-connected" is supported and/or
+        # a good idea.
+        if recv_chan._closed:
+            task = trio.lowlevel.current_task().name
+            raise trio.ClosedResourceError(
+                f'stream for {actor.uid[0]}:{task} has already been closed.'
+                '\nRe-opening a closed stream is not yet supported!'
+                '\nConsider re-calling the containing `@tractor.context` func'
+            )
+
+        async with MsgStream(
+            ctx=self,
+            rx_chan=recv_chan,
+            shield=shield,
+        ) as rchan:
+
+            if self._portal:
+                self._portal._streams.add(rchan)
+
+            try:
+                # ensure we aren't cancelled before delivering
+                # the stream
+                # await trio.lowlevel.checkpoint()
+                yield rchan
+
+            except trio.EndOfChannel:
+                # likely the far end sent us a 'stop' message to
+                # terminate the stream.
+                raise
+
+            else:
+                # XXX: Make the stream "one-shot use".  On exit, signal
+                # ``trio.EndOfChannel``/``StopAsyncIteration`` to the
+                # far end.
+                await self.send_stop()
+
+            finally:
+                if self._portal:
+                    self._portal._streams.remove(rchan)
+
+    async def result(self) -> Any:
+        '''From a caller side, wait for and return the final result from
+        the callee side task.
+
+        '''
+        assert self._portal, "Context.result() can not be called from callee!"
+        assert self._recv_chan
+
+        if self._result is False:
+
+            if not self._recv_chan._closed:  # type: ignore
+
+                # wait for a final context result consuming
+                # and discarding any bi dir stream msgs still
+                # in transit from the far end.
+                while True:
+
+                    msg = await self._recv_chan.receive()
+                    try:
+                        self._result = msg['return']
+                        break
+                    except KeyError:
+
+                        if 'yield' in msg:
+                            # far end task is still streaming to us..
+                            log.warning(f'Remote stream deliverd {msg}')
+                            # do disard
+                            continue
+
+                        elif 'stop' in msg:
+                            log.debug('Remote stream terminated')
+                            continue
+
+                        # internal error should never get here
+                        assert msg.get('cid'), (
+                            "Received internal error at portal?")
+                        raise unpack_error(msg, self._portal.channel)
+
+        return self._result
+
+    async def started(self, value: Optional[Any] = None) -> None:
+
+        if self._portal:
+            raise RuntimeError(
+                f"Caller side context {self} can not call started!")
+
+        await self.chan.send({'started': value, 'cid': self.cid})
+
+    # TODO: do we need a restart api?
     # async def restart(self) -> None:
-    #     # TODO
-    #     pass
-
-    # @asynccontextmanager
-    # async def open_stream(
-    #     self,
-    # ) -> AsyncContextManager:
-    #     # TODO
     #     pass
 
 
-def stream(func):
+def stream(func: Callable) -> Callable:
     """Mark an async function as a streaming routine with ``@stream``.
+
     """
-    func._tractor_stream_function = True
+    # annotate
+    # TODO: apply whatever solution ``mypy`` ends up picking for this:
+    # https://github.com/python/mypy/issues/2087#issuecomment-769266912
+    func._tractor_stream_function = True  # type: ignore
+
     sig = inspect.signature(func)
     params = sig.parameters
     if 'stream' not in params and 'ctx' in params:
@@ -114,147 +554,26 @@ def stream(func):
     ):
         raise TypeError(
             "The first argument to the stream function "
-            f"{func.__name__} must be `ctx: tractor.Context`"
+            f"{func.__name__} must be `ctx: tractor.Context` "
+            "(Or ``to_trio`` if using ``asyncio`` in guest mode)."
         )
     return func
 
 
-class ReceiveMsgStream(trio.abc.ReceiveChannel):
+def context(func: Callable) -> Callable:
-    """A wrapper around a ``trio._channel.MemoryReceiveChannel`` with
+    """Mark an async function as a streaming routine with ``@context``.
-    special behaviour for signalling stream termination across an
-    inter-actor ``Channel``. This is the type returned to a local task
-    which invoked a remote streaming function using `Portal.run()`.
-
-    Termination rules:
-    - if the local task signals stop iteration a cancel signal is
-      relayed to the remote task indicating to stop streaming
-    - if the remote task signals the end of a stream, raise a
-      ``StopAsyncIteration`` to terminate the local ``async for``
 
     """
-    def __init__(
+    # annotate
-        self,
+    # TODO: apply whatever solution ``mypy`` ends up picking for this:
-        ctx: Context,
+    # https://github.com/python/mypy/issues/2087#issuecomment-769266912
-        rx_chan: trio.abc.ReceiveChannel,
+    func._tractor_context_function = True  # type: ignore
-        portal: 'Portal',  # type: ignore # noqa
-    ) -> None:
-        self._ctx = ctx
-        self._rx_chan = rx_chan
-        self._portal = portal
-        self._shielded = False
 
-    # delegate directly to underlying mem channel
+    sig = inspect.signature(func)
-    def receive_nowait(self):
+    params = sig.parameters
-        return self._rx_chan.receive_nowait()
+    if 'ctx' not in params:
-
+        raise TypeError(
-    async def receive(self):
+            "The first argument to the context function "
-        try:
+            f"{func.__name__} must be `ctx: tractor.Context`"
-            msg = await self._rx_chan.receive()
+        )
-            return msg['yield']
+    return func
-
-        except KeyError:
-            # internal error should never get here
-            assert msg.get('cid'), ("Received internal error at portal?")
-
-            # TODO: handle 2 cases with 3.10 match syntax
-            # - 'stop'
-            # - 'error'
-            # possibly just handle msg['stop'] here!
-
-            # TODO: test that shows stream raising an expected error!!!
-            if msg.get('error'):
-                # raise the error message
-                raise unpack_error(msg, self._portal.channel)
-
-        except (trio.ClosedResourceError, StopAsyncIteration):
-            # XXX: this indicates that a `stop` message was
-            # sent by the far side of the underlying channel.
-            # Currently this is triggered by calling ``.aclose()`` on
-            # the send side of the channel inside
-            # ``Actor._push_result()``, but maybe it should be put here?
-            # to avoid exposing the internal mem chan closing mechanism?
-            # in theory we could instead do some flushing of the channel
-            # if needed to ensure all consumers are complete before
-            # triggering closure too early?
-
-            # Locally, we want to close this stream gracefully, by
-            # terminating any local consumers tasks deterministically.
-            # We **don't** want to be closing this send channel and not
-            # relaying a final value to remaining consumers who may not
-            # have been scheduled to receive it yet?
-
-            # lots of testing to do here
-
-            # when the send is closed we assume the stream has
-            # terminated and signal this local iterator to stop
-            await self.aclose()
-            raise StopAsyncIteration
-
-        except trio.Cancelled:
-            # relay cancels to the remote task
-            await self.aclose()
-            raise
-
-    @contextmanager
-    def shield(
-        self
-    ) -> Iterator['ReceiveMsgStream']:  # noqa
-        """Shield this stream's underlying channel such that a local consumer task
-        can be cancelled (and possibly restarted) using ``trio.Cancelled``.
-
-        """
-        self._shielded = True
-        yield self
-        self._shielded = False
-
-    async def aclose(self):
-        """Cancel associated remote actor task and local memory channel
-        on close.
-        """
-        rx_chan = self._rx_chan
-
-        if rx_chan._closed:
-            log.warning(f"{self} is already closed")
-            return
-
-        # stats = rx_chan.statistics()
-        # if stats.open_receive_channels > 1:
-        #     # if we've been cloned don't kill the stream
-        #     log.debug(
-        #       "there are still consumers running keeping stream alive")
-        #     return
-
-        if self._shielded:
-            log.warning(f"{self} is shielded, portal channel being kept alive")
-            return
-
-        # close the local mem chan
-        rx_chan.close()
-
-        # cancel surrounding IPC context
-        await self._ctx.cancel()
-
-    # TODO: but make it broadcasting to consumers
-    # def clone(self):
-    #     """Clone this receive channel allowing for multi-task
-    #     consumption from the same channel.
-
-    #     """
-    #     return ReceiveStream(
-    #         self._cid,
-    #         self._rx_chan.clone(),
-    #         self._portal,
-    #     )
-
-
-# class MsgStream(ReceiveMsgStream, trio.abc.Channel):
-#     """
-#     Bidirectional message stream for use within an inter-actor actor
-#     ``Context```.
-
-#     """
-#     async def send(
-#         self,
-#         data: Any
-#     ) -> None:
-#         await self._ctx.chan.send({'yield': data, 'cid': self._ctx.cid})

tractor/_trionics.py

@@ -11,7 +11,8 @@ import warnings
 import trio
 from async_generator import asynccontextmanager
 
-from ._state import current_actor, is_main_process
+from . import _debug
+from ._state import current_actor, is_main_process, is_root_process
 from .log import get_logger, get_loglevel
 from ._actor import Actor
 from ._portal import Portal
@@ -60,6 +61,8 @@ class ActorNursery:
         enable_modules: List[str] = None,
         loglevel: str = None,  # set log level per subactor
         nursery: trio.Nursery = None,
+        infect_asyncio: bool = False,
+        debug_mode: Optional[bool] = None,
     ) -> Portal:
         loglevel = loglevel or self._actor.loglevel or get_loglevel()
 
@@ -67,6 +70,10 @@ class ActorNursery:
         _rtv = _state._runtime_vars.copy()
         _rtv['_is_root'] = False
 
+        # allow setting debug policy per actor
+        if debug_mode is not None:
+            _rtv['_debug_mode'] = debug_mode
+
         enable_modules = enable_modules or []
 
         if rpc_module_paths:
@@ -103,6 +110,7 @@ class ActorNursery:
                 bind_addr,
                 parent_addr,
                 _rtv,  # run time vars
+                infect_asyncio=infect_asyncio,
             )
         )
 
@@ -115,6 +123,7 @@ class ActorNursery:
         rpc_module_paths: Optional[List[str]] = None,
         enable_modules: List[str] = None,
         loglevel: str = None,  # set log level per subactor
+        infect_asyncio: bool = False,
         **kwargs,  # explicit args to ``fn``
     ) -> Portal:
         """Spawn a new actor, run a lone task, then terminate the actor and
@@ -139,6 +148,7 @@ class ActorNursery:
             loglevel=loglevel,
             # use the run_in_actor nursery
             nursery=self._ria_nursery,
+            infect_asyncio=infect_asyncio,
         )
 
         # XXX: don't allow stream funcs
@@ -253,6 +263,26 @@ async def _open_and_supervise_one_cancels_all_nursery(
                         "to complete"
                     )
                 except BaseException as err:
+
+                    if is_root_process() and (
+                        type(err) in {
+                            Exception, trio.MultiError, trio.Cancelled
+                        }
+                    ):
+                        # if we error in the root but the debugger is
+                        # engaged we don't want to prematurely kill (and
+                        # thus clobber access to) the local tty streams.
+                        # instead try to wait for pdb to be released before
+                        # tearing down.
+                        debug_complete = _debug._pdb_complete
+                        if debug_complete and not debug_complete.is_set():
+                            log.warning(
+                                "Root has errored but pdb is active..waiting "
+                                "on debug lock")
+                            await _debug._pdb_complete.wait()
+
+                        # raise
+
                     # if the caller's scope errored then we activate our
                     # one-cancels-all supervisor strategy (don't
                     # worry more are coming).
@@ -357,7 +387,8 @@ async def open_nursery(
     try:
         if actor is None and is_main_process():
 
-            # if we are the parent process start the actor runtime implicitly
+            # if we are the parent process start the
+            # actor runtime implicitly
             log.info("Starting actor runtime!")
 
             # mark us for teardown on exit
@@ -366,6 +397,7 @@ async def open_nursery(
             async with open_root_actor(**kwargs) as actor:
                 assert actor is current_actor()
 
+                # try:
                 async with _open_and_supervise_one_cancels_all_nursery(
                     actor
                 ) as anursery:
@@ -376,7 +408,6 @@ async def open_nursery(
             async with _open_and_supervise_one_cancels_all_nursery(
                 actor
             ) as anursery:
-
                 yield anursery
 
     finally:

tractor/log.py

@@ -30,16 +30,17 @@ DATE_FORMAT = '%b %d %H:%M:%S'
 LEVELS = {
     'GARBAGE': 1,
     'TRACE': 5,
-    'PROFILE': 15,
+    'RUNTIME': 15,
-    'RUNTIME': 500,
+    'PDB': 500,
     'QUIET': 1000,
 }
 STD_PALETTE = {
     'CRITICAL': 'red',
     'ERROR': 'red',
-    'RUNTIME': 'white',
+    'PDB': 'white',
     'WARNING': 'yellow',
     'INFO': 'green',
+    'RUNTIME': 'white',
     'DEBUG': 'white',
     'TRACE': 'cyan',
     'GARBAGE': 'blue',

tractor/msg.py

@@ -1,9 +1,13 @@
 """
 Messaging pattern APIs and helpers.
+
+NOTE: this module is likely deprecated by the new bi-directional streaming
+support provided by ``tractor.Context.open_stream()`` and friends.
+
 """
 import inspect
 import typing
-from typing import Dict, Any, Set, Callable
+from typing import Dict, Any, Set, Callable, List, Tuple
 from functools import partial
 from async_generator import aclosing
 
@@ -20,7 +24,7 @@ log = get_logger('messaging')
 
 async def fan_out_to_ctxs(
     pub_async_gen_func: typing.Callable,  # it's an async gen ... gd mypy
-    topics2ctxs: Dict[str, set],
+    topics2ctxs: Dict[str, list],
     packetizer: typing.Callable = None,
 ) -> None:
     """Request and fan out quotes to each subscribed actor channel.
@@ -34,24 +38,27 @@ async def fan_out_to_ctxs(
 
         async for published in pub_gen:
 
-            ctx_payloads: Dict[str, Any] = {}
+            ctx_payloads: List[Tuple[Context, Any]] = []
 
             for topic, data in published.items():
                 log.debug(f"publishing {topic, data}")
+
                 # build a new dict packet or invoke provided packetizer
                 if packetizer is None:
                     packet = {topic: data}
+
                 else:
                     packet = packetizer(topic, data)
-                for ctx in topics2ctxs.get(topic, set()):
+
-                    ctx_payloads.setdefault(ctx, {}).update(packet),
+                for ctx in topics2ctxs.get(topic, list()):
+                    ctx_payloads.append((ctx, packet))
 
             if not ctx_payloads:
                 log.debug(f"Unconsumed values:\n{published}")
 
             # deliver to each subscriber (fan out)
             if ctx_payloads:
-                for ctx, payload in ctx_payloads.items():
+                for ctx, payload in ctx_payloads:
                     try:
                         await ctx.send_yield(payload)
                     except (
@@ -60,15 +67,24 @@ async def fan_out_to_ctxs(
                         ConnectionRefusedError,
                     ):
                         log.warning(f"{ctx.chan} went down?")
-                        for ctx_set in topics2ctxs.values():
+                        for ctx_list in topics2ctxs.values():
-                            ctx_set.discard(ctx)
+                            try:
+                                ctx_list.remove(ctx)
+                            except ValueError:
+                                continue
 
             if not get_topics():
                 log.warning(f"No subscribers left for {pub_gen}")
                 break
 
 
-def modify_subs(topics2ctxs, topics, ctx):
+def modify_subs(
+
+    topics2ctxs: Dict[str, List[Context]],
+    topics: Set[str],
+    ctx: Context,
+
+) -> None:
     """Absolute symbol subscription list for each quote stream.
 
     Effectively a symbol subscription api.
@@ -77,7 +93,7 @@ def modify_subs(topics2ctxs, topics, ctx):
 
     # update map from each symbol to requesting client's chan
     for topic in topics:
-        topics2ctxs.setdefault(topic, set()).add(ctx)
+        topics2ctxs.setdefault(topic, list()).append(ctx)
 
     # remove any existing symbol subscriptions if symbol is not
     # found in ``symbols``
@@ -85,10 +101,14 @@ def modify_subs(topics2ctxs, topics, ctx):
     for topic in filter(
         lambda topic: topic not in topics, topics2ctxs.copy()
     ):
-        ctx_set = topics2ctxs.get(topic)
+        ctx_list = topics2ctxs.get(topic)
-        ctx_set.discard(ctx)
+        if ctx_list:
+            try:
+                ctx_list.remove(ctx)
+            except ValueError:
+                pass
 
-        if not ctx_set:
+        if not ctx_list:
             # pop empty sets which will trigger bg quoter task termination
             topics2ctxs.pop(topic)
 
@@ -101,6 +121,7 @@ def pub(
     wrapped: typing.Callable = None,
     *,
     tasks: Set[str] = set(),
+    send_on_connect: Any = None,
 ):
     """Publisher async generator decorator.
 
@@ -186,7 +207,7 @@ def pub(
 
     # handle the decorator not called with () case
     if wrapped is None:
-        return partial(pub, tasks=tasks)
+        return partial(pub, tasks=tasks, send_on_connect=send_on_connect)
 
     task2lock: Dict[str, trio.StrictFIFOLock] = {}
 
@@ -229,6 +250,11 @@ def pub(
 
             try:
                 modify_subs(topics2ctxs, topics, ctx)
+
+                # if specified send the startup message back to consumer
+                if send_on_connect is not None:
+                    await ctx.send_yield(send_on_connect)
+
                 # block and let existing feed task deliver
                 # stream data until it is cancelled in which case
                 # the next waiting task will take over and spawn it again
@@ -256,7 +282,7 @@ def pub(
                             respawn = True
             finally:
                 # remove all subs for this context
-                modify_subs(topics2ctxs, (), ctx)
+                modify_subs(topics2ctxs, set(), ctx)
 
                 # if there are truly no more subscriptions with this broker
                 # drop from broker subs dict

tractor/testing/_tractor_test.py

@@ -78,7 +78,7 @@ def tractor_test(fn):
 
         else:
             # use implicit root actor start
-            main = partial(fn, *args, **kwargs),
+            main = partial(fn, *args, **kwargs)
 
         return trio.run(main)
             # arbiter_addr=arb_addr,

tractor/to_asyncio.py

@@ -0,0 +1,311 @@
+"""
+Infection apis for ``asyncio`` loops running ``trio`` using guest mode.
+"""
+import asyncio
+import inspect
+from typing import (
+    Any,
+    Callable,
+    AsyncIterator,
+    Awaitable,
+)
+
+import trio
+
+from .log import get_logger
+from ._state import current_actor
+
+log = get_logger(__name__)
+
+
+__all__ = ['run_task', 'run_as_asyncio_guest']
+
+
+async def run_coro(
+    to_trio: trio.MemorySendChannel,
+    coro: Awaitable,
+) -> None:
+    """Await ``coro`` and relay result back to ``trio``.
+    """
+    to_trio.send_nowait(await coro)
+
+
+async def consume_asyncgen(
+    to_trio: trio.MemorySendChannel,
+    coro: AsyncIterator,
+) -> None:
+    """Stream async generator results back to ``trio``.
+
+    ``from_trio`` might eventually be used here for
+    bidirectional streaming.
+    """
+    async for item in coro:
+        to_trio.send_nowait(item)
+
+
+def _run_asyncio_task(
+    func: Callable,
+    *,
+    qsize: int = 1,
+    _treat_as_stream: bool = False,
+    **kwargs,
+) -> Any:
+    """Run an ``asyncio`` async function or generator in a task, return
+    or stream the result back to ``trio``.
+
+    """
+    assert current_actor().is_infected_aio()
+
+    # ITC (inter task comms)
+    from_trio = asyncio.Queue(qsize)  # type: ignore
+    to_trio, from_aio = trio.open_memory_channel(qsize)  # type: ignore
+
+    from_aio._err = None
+
+    args = tuple(inspect.getfullargspec(func).args)
+
+    if getattr(func, '_tractor_steam_function', None):
+        # the assumption is that the target async routine accepts the
+        # send channel then it intends to yield more then one return
+        # value otherwise it would just return ;P
+        # _treat_as_stream = True
+        assert qsize > 1
+
+    # allow target func to accept/stream results manually by name
+    if 'to_trio' in args:
+        kwargs['to_trio'] = to_trio
+
+    if 'from_trio' in args:
+        kwargs['from_trio'] = from_trio
+
+    # if 'from_aio' in args:
+    #     kwargs['from_aio'] = from_aio
+
+    coro = func(**kwargs)
+
+    # cancel_scope = trio.CancelScope()
+
+    # start the asyncio task we submitted from trio
+    if inspect.isawaitable(coro):
+        task = asyncio.create_task(run_coro(to_trio, coro))
+
+    elif inspect.isasyncgen(coro):
+        task = asyncio.create_task(consume_asyncgen(to_trio, coro))
+
+    else:
+        raise TypeError(f"No support for invoking {coro}")
+
+    aio_err = None
+
+    def cancel_trio(task):
+        """Cancel the calling ``trio`` task on error.
+        """
+        nonlocal aio_err
+        try:
+            aio_err = task.exception()
+        except asyncio.CancelledError as cerr:
+            aio_err = cerr
+
+        if aio_err:
+            log.exception(f"asyncio task errorred:\n{aio_err}")
+
+        # cancel_scope.cancel()
+        from_aio._err = aio_err
+
+    task.add_done_callback(cancel_trio)
+
+    return task, from_aio, to_trio
+
+
+async def run_task(
+    func: Callable,
+    *,
+    qsize: int = 2**10,
+    _treat_as_stream: bool = False,
+    **kwargs,
+) -> Any:
+    """Run an ``asyncio`` async function or generator in a task, return
+    or stream the result back to ``trio``.
+
+    """
+    # assert current_actor().is_infected_aio()
+
+    # # ITC (inter task comms)
+    # from_trio = asyncio.Queue(qsize)  # type: ignore
+    # to_trio, from_aio = trio.open_memory_channel(qsize)  # type: ignore
+
+    # args = tuple(inspect.getfullargspec(func).args)
+
+    # if getattr(func, '_tractor_steam_function', None):
+    #     # the assumption is that the target async routine accepts the
+    #     # send channel then it intends to yield more then one return
+    #     # value otherwise it would just return ;P
+    #     _treat_as_stream = True
+
+    # # allow target func to accept/stream results manually by name
+    # if 'to_trio' in args:
+    #     kwargs['to_trio'] = to_trio
+    # if 'from_trio' in args:
+    #     kwargs['from_trio'] = from_trio
+
+    # coro = func(**kwargs)
+
+    # cancel_scope = trio.CancelScope()
+
+    # # start the asyncio task we submitted from trio
+    # if inspect.isawaitable(coro):
+    #     task = asyncio.create_task(run_coro(to_trio, coro))
+
+    # elif inspect.isasyncgen(coro):
+    #     task = asyncio.create_task(consume_asyncgen(to_trio, coro))
+
+    # else:
+    #     raise TypeError(f"No support for invoking {coro}")
+
+    # aio_err = None
+
+    # def cancel_trio(task):
+    #     """Cancel the calling ``trio`` task on error.
+    #     """
+    #     nonlocal aio_err
+    #     aio_err = task.exception()
+
+    #     if aio_err:
+    #         log.exception(f"asyncio task errorred:\n{aio_err}")
+
+    #     cancel_scope.cancel()
+
+    # task.add_done_callback(cancel_trio)
+
+    # async iterator
+    # if inspect.isasyncgen(coro) or _treat_as_stream:
+
+    # if inspect.isasyncgenfunction(meth) or :
+    if _treat_as_stream:
+
+        task, from_aio, to_trio = _run_asyncio_task(
+            func,
+            qsize=2**8,
+            **kwargs,
+        )
+
+        return from_aio
+
+        # async def stream_results():
+        #     try:
+        #         with cancel_scope:
+        #             # stream values upward
+        #             async with from_aio:
+        #                 async for item in from_aio:
+        #                     yield item
+
+        #         if cancel_scope.cancelled_caught:
+        #             # always raise from any captured asyncio error
+        #             if aio_err:
+        #                 raise aio_err
+
+        #     except BaseException as err:
+        #         if aio_err is not None:
+        #             # always raise from any captured asyncio error
+        #             raise err from aio_err
+        #         else:
+        #             raise
+        #     finally:
+        #         # breakpoint()
+        #         task.cancel()
+
+        # return stream_results()
+
+    # simple async func
+    try:
+        task, from_aio, to_trio = _run_asyncio_task(
+            func,
+            qsize=1,
+            **kwargs,
+        )
+
+        # with cancel_scope:
+        # async with from_aio:
+            # return single value
+        return await from_aio.receive()
+
+        # if cancel_scope.cancelled_caught:
+        #     # always raise from any captured asyncio error
+        #     if aio_err:
+        #         raise aio_err
+
+    # Do we need this?
+    except Exception as err:
+        # await tractor.breakpoint()
+        aio_err = from_aio._err
+
+        # try:
+        if aio_err is not None:
+            # always raise from any captured asyncio error
+            raise err from aio_err
+        else:
+            raise
+        # finally:
+        #     if not task.done():
+        #         task.cancel()
+
+    except trio.Cancelled:
+        if not task.done():
+            task.cancel()
+
+        raise
+
+
+# async def stream_from_task
+#     pass
+
+
+def run_as_asyncio_guest(
+    trio_main: Callable,
+) -> None:
+    """Entry for an "infected ``asyncio`` actor".
+
+    Uh, oh. :o
+
+    It looks like your event loop has caught a case of the ``trio``s.
+
+    :()
+
+    Don't worry, we've heard you'll barely notice. You might hallucinate
+    a few more propagating errors and feel like your digestion has
+    slowed but if anything get's too bad your parents will know about
+    it.
+
+    :)
+    """
+    async def aio_main(trio_main):
+
+        loop = asyncio.get_running_loop()
+
+        trio_done_fut = asyncio.Future()
+
+        def trio_done_callback(main_outcome):
+
+            log.info(f"trio_main finished: {main_outcome!r}")
+            trio_done_fut.set_result(main_outcome)
+
+        # start the infection: run trio on the asyncio loop in "guest mode"
+        log.info(f"Infecting asyncio process with {trio_main}")
+
+        trio.lowlevel.start_guest_run(
+            trio_main,
+            run_sync_soon_threadsafe=loop.call_soon_threadsafe,
+            done_callback=trio_done_callback,
+        )
+
+        (await trio_done_fut).unwrap()
+
+    # might as well if it's installed.
+    try:
+        import uvloop
+        loop = uvloop.new_event_loop()
+        asyncio.set_event_loop(loop)
+    except ImportError:
+        pass
+
+    asyncio.run(aio_main(trio_main))