Add fast fail test using the context api

Finally this makes a cancelled root actor nursery not clobber child
tasks which request and lock the root's tty for the debugger repl.

Using an edge triggered event which is set after all fifo-lock-queued
tasks are complete, we can be sure that no lingering child tasks are
going to get interrupted during pdb use and tty lock acquisition.
Further, even if new tasks do queue up to get the lock, the root will
incrementally send cancel msgs to each sub-actor only once the tty is
not locked by a (set of) child request task(s). Add shielding around all
the critical sections where the child attempts to allocate the lock from
the root such that it won't be disrupted from cancel messages from the
root after the acquire lock transaction has started.

examples/debugging/fast_error_in_root_after_spawn.py

@@ -0,0 +1,53 @@
+'''
+fast fail test with a context.
+ensure the partially initialized sub-actor process
+doesn't cause a hang on error/cancel of the parent
+nrusery.
+
+'''
+import trio
+import tractor
+
+
+@tractor.context
+async def sleep(
+    ctx: tractor.Context,
+):
+    await trio.sleep(0.5)
+    await ctx.started()
+    await trio.sleep_forever()
+
+
+async def open_ctx(
+    n: tractor._trionics.ActorNursery
+):
+
+    # spawn both actors
+    portal = await n.start_actor(
+        name='sleeper',
+        enable_modules=[__name__],
+    )
+
+    async with portal.open_context(
+        sleep,
+    ) as (ctx, first):
+        assert first is None
+
+
+async def main():
+
+    async with tractor.open_nursery(
+        debug_mode=True,
+        loglevel='runtime',
+    ) as an:
+
+        async with trio.open_nursery() as n:
+            n.start_soon(open_ctx, an)
+
+            await trio.sleep(0.2)
+            await trio.sleep(0.1)
+            assert 0
+
+
+if __name__ == '__main__':
+    trio.run(main)

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

@@ -38,14 +38,28 @@ setup(
         'tractor.testing',
     ],
     install_requires=[
+
+        # trio related
         'trio>0.8',
-        'msgpack',
         'async_generator',
+        'tricycle',
+        'trio_typing',
+
+        # tooling
         'colorlog',
         'wrapt',
-        'trio_typing',
         'pdbpp',
+
+        # serialization
+        'msgpack',
+
     ],
+    extras_require={
+
+        # serialization
+        'msgspec': ["msgspec; python_version >= '3.9'"],
+
+    },
     tests_require=['pytest'],
     python_requires=">=3.7",
     keywords=[

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 tractor.ContextCancelled:
+            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].copy():
+            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_cancellation.py

@@ -123,8 +123,15 @@ def test_multierror_fast_nursery(arb_addr, start_method, num_subactors, delay):
 
     assert exc_info.type == tractor.MultiError
     err = exc_info.value
-    assert len(err.exceptions) == num_subactors
+    exceptions = err.exceptions
-    for exc in err.exceptions:
+
+    if len(exceptions) == 2:
+        # sometimes oddly now there's an embedded BrokenResourceError ?
+        exceptions = exceptions[1].exceptions
+
+    assert len(exceptions) == num_subactors
+
+    for exc in exceptions:
         assert isinstance(exc, tractor.RemoteActorError)
         assert exc.type == AssertionError
 

tests/test_debugger.py

@@ -307,19 +307,46 @@ def test_multi_daemon_subactors(spawn, loglevel):
     before = str(child.before.decode())
     assert "NameError" in before
 
-    child.sendline('c')
+    # XXX: hoorayy the root clobering the child here was fixed!
 
+    # now the root actor won't clobber the bp_forever child
+    # during it's first access to the debug lock, but will instead
+    # wait for the lock to release, by the edge triggered
+    # ``_debug._no_remote_has_tty`` event before sending cancel messages
+    # (via portals) to its underlings B)
+
+    # IMO, this demonstrates the true power of SC system design.
+    child.sendline('c')
+    child.expect(r"\(Pdb\+\+\)")
+    before = str(child.before.decode())
+    assert "Attaching pdb to actor: ('bp_forever'," in before
+
+
+    child.sendline('c')
+    child.expect(r"\(Pdb\+\+\)")
+    before = str(child.before.decode())
+
+    try:
+        # final error in root
+        assert "tractor._exceptions.RemoteActorError: ('name_error'" in before
+
+    except AssertionError:
+    # except pexpect.exceptions.TIMEOUT:
+
+        # one last entry in the root
+        child.sendline('c')
         child.expect(r"\(Pdb\+\+\)")
         before = str(child.before.decode())
         assert "tractor._exceptions.RemoteActorError: ('name_error'" in before
 
-    try:
+        # theory there should have been some msg like this from
-        child.sendline('c')
+        # root announcing it avoided a clobber of the child's lock,
-        child.expect(pexpect.EOF)
+        # but it seems unreliable in testing here to gnab it.
-    except pexpect.exceptions.TIMEOUT:
+        # assert "in use by child ('bp_forever'," in before
-        # Failed to exit using continue..?
 
-        child.sendline('q')
+    child.sendline('c')
+    # final error in root
+    assert "tractor._exceptions.RemoteActorError: ('name_error'" in before
     child.expect(pexpect.EOF)
 
 
@@ -372,7 +399,7 @@ def test_multi_nested_subactors_error_through_nurseries(spawn):
     child = spawn('multi_nested_subactors_error_up_through_nurseries')
 
     # startup time can be iffy
-    time.sleep(1)
+    # time.sleep(1)
 
     for i in range(12):
         try:
@@ -454,3 +481,21 @@ def test_root_nursery_cancels_before_child_releases_tty_lock(
         assert "tractor._exceptions.RemoteActorError: ('spawner0'" in before
         assert "tractor._exceptions.RemoteActorError: ('name_error'" in before
         assert "NameError: name 'doggypants' is not defined" in before
+
+
+def test_root_cancels_child_context_during_startup(
+    spawn,
+):
+    '''Verify a fast fail in the root doesn't lock up the child reaping
+    and all while using the new context api.
+
+    '''
+    child = spawn('fast_error_in_root_after_spawn')
+
+    child.expect(r"\(Pdb\+\+\)")
+
+    before = str(child.before.decode())
+    assert "AssertionError" in before
+
+    child.sendline('c')
+    child.expect(pexpect.EOF)

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

@@ -5,11 +5,21 @@ 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
@@ -21,6 +31,7 @@ __all__ = [
     'ModuleNotExposed',
     'MultiError',
     'RemoteActorError',
+    'ContextCancelled',
     'breakpoint',
     'current_actor',
     'find_actor',
@@ -33,7 +44,9 @@ __all__ = [
     '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 +61,44 @@ async def _invoke(
     """Invoke local func and deliver result(s) over provided channel.
     """
     treat_as_gen = False
-    cs = None
+
+    # possible a traceback (not sure what typing is for this..)
+    tb = 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 (
@@ -101,8 +136,9 @@ async def _invoke(
             # `StopAsyncIteration` system here for returning a final
             # value if desired
             await chan.send({'stop': True, 'cid': cid})
-        else:
+
-            if treat_as_gen:
+        # 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
@@ -111,10 +147,47 @@ async def _invoke(
             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)
+                try:
+                    await chan.send({'return': await coro, 'cid': cid})
+                except trio.Cancelled as err:
+                    tb = err.__traceback__
+
+            if cs.cancelled_caught:
+
+                # TODO: pack in ``trio.Cancelled.__traceback__`` here
+                # so they can be unwrapped and displayed on the caller
+                # side!
+
+                fname = func.__name__
+                if ctx._cancel_called:
+                    msg = f'{fname} cancelled itself'
+
+                elif cs.cancel_called:
+                    msg = (
+                        f'{fname} was remotely cancelled by its caller '
+                        f'{ctx.chan.uid}'
+                    )
+
+                # task-contex was cancelled so relay to the cancel to caller
+                raise ContextCancelled(
+                    msg,
+                    suberror_type=trio.Cancelled,
+                )
+
         else:
             # regular async function
             await chan.send({'functype': 'asyncfunc', 'cid': cid})
@@ -124,29 +197,45 @@ async def _invoke(
 
     except (Exception, trio.MultiError) as err:
 
-        # TODO: maybe we'll want differnet "levels" of debugging
+        if not is_multi_cancelled(err):
+
+            log.exception("Actor crashed:")
+
+            # TODO: maybe we'll want different "levels" of debugging
             # eventualy such as ('app', 'supervisory', 'runtime') ?
-        if not isinstance(err, trio.ClosedResourceError) and (
+
-            not is_multi_cancelled(err)
+            # if not isinstance(err, trio.ClosedResourceError) and (
+            # if not is_multi_cancelled(err) and (
+
+            entered_debug: bool = False
+            if not isinstance(err, ContextCancelled) or (
+                isinstance(err, ContextCancelled) and ctx._cancel_called
             ):
                 # XXX: is there any case where we'll want to debug IPC
-            # disconnects? I can't think of a reason that inspecting
+                # disconnects as a default?
+                #
+                # 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?
+                # in our transport layer itself? Going to keep this
-            entered = await _debug._maybe_enter_pm(err)
+                # open ended for now.
-            if not entered:
+
+                entered_debug = await _debug._maybe_enter_pm(err)
+
+            if not entered_debug:
                 log.exception("Actor crashed:")
 
         # always ship errors back to caller
-        err_msg = pack_error(err)
+        err_msg = pack_error(err, tb=tb)
         err_msg['cid'] = cid
         try:
             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
@@ -164,7 +253,7 @@ async def _invoke(
                 f"Task {func} likely errored or cancelled before it started")
         finally:
             if not actor._rpc_tasks:
-                log.info("All RPC tasks have completed")
+                log.runtime("All RPC tasks have completed")
                 actor._ongoing_rpc_tasks.set()
 
 
@@ -179,10 +268,10 @@ _lifetime_stack: ExitStack = ExitStack()
 class Actor:
     """The fundamental concurrency primitive.
 
-    An *actor* is the combination of a regular Python or
+    An *actor* is the combination of a regular Python process
-    ``multiprocessing.Process`` executing a ``trio`` task tree, communicating
+    executing a ``trio`` task tree, communicating
     with other actors through "portals" which provide a native async API
-    around "channels".
+    around various IPC transport "channels".
     """
     is_arbiter: bool = False
 
@@ -202,7 +291,7 @@ class Actor:
         enable_modules: List[str] = [],
         uid: str = None,
         loglevel: str = None,
-        arbiter_addr: Optional[Tuple[str, int]] = None,
+        arbiter_addr: Optional[Tuple[str, int]] = (None, None),
         spawn_method: Optional[str] = None
     ) -> None:
         """This constructor is called in the parent actor **before** the spawning
@@ -232,7 +321,7 @@ 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)
 
         # marked by the process spawning backend at startup
         # will be None for the parent most process started manually
@@ -262,7 +351,7 @@ 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 +415,34 @@ 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}")
+        log.runtime(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
 
@@ -353,11 +457,16 @@ class Actor:
             event.set()
 
         chans = self._peers[uid]
+
+        # TODO: re-use channels for new connections instead 
+        # of always new ones; will require changing all the
+        # discovery funcs
         if chans:
-            log.warning(
+            log.runtime(
                 f"already have channel(s) for {uid}:{chans}?"
             )
-        log.trace(f"Registered {chan} for {uid}")  # type: ignore
+
+        log.runtime(f"Registered {chan} for {uid}")  # type: ignore
         # append new channel
         self._peers[uid].append(chan)
 
@@ -366,10 +475,24 @@ 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 +505,22 @@ 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 +530,32 @@ 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")
@@ -423,7 +564,9 @@ 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)]
@@ -476,24 +619,35 @@ 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
+                    log.transport(   # type: ignore
                         f"Received msg {msg} from {chan.uid}")
 
                     cid = msg.get('cid')
                     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
@@ -554,7 +708,7 @@ class Actor:
                         else:
                             # mark that we have ongoing rpc tasks
                             self._ongoing_rpc_tasks = trio.Event()
-                            log.info(f"RPC func is {func}")
+                            log.runtime(f"RPC func is {func}")
                             # store cancel scope such that the rpc task can be
                             # cancelled gracefully if requested
                             self._rpc_tasks[(chan, cid)] = (
@@ -563,7 +717,7 @@ class Actor:
                         # self.cancel() was called so kill this msg loop
                         # and break out into ``_async_main()``
                         log.warning(
-                            f"{self.uid} was remotely cancelled; "
+                            f"Actor {self.uid} was remotely cancelled; "
                             "waiting on cancellation completion..")
                         await self._cancel_complete.wait()
                         loop_cs.cancel()
@@ -578,22 +732,35 @@ 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 surrounding
+            # caller's teardown sequence to clean up.
+            log.warning(f"Channel from {chan.uid} closed abruptly")
+
         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}")
@@ -633,8 +800,22 @@ class Actor:
                 _state._runtime_vars.update(rvs)
 
                 for attr, value in parent_data.items():
+
+                    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
 
         except OSError:  # failed to connect
@@ -1012,13 +1193,14 @@ 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")
+        log.runtime(f"Handshake with actor {uid}@{chan.raddr} complete")
         return uid
 
 
@@ -1082,8 +1264,9 @@ 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 +1276,4 @@ 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/_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 +31,22 @@ 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()
+_local_pdb_complete: Optional[trio.Event] = None
+_no_remote_has_tty: 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 +69,19 @@ 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()
 
 
@@ -102,7 +110,7 @@ class PdbwTeardown(pdbpp.Pdb):
 
 #     async with aclosing(async_stdin):
 #         async for msg in async_stdin:
-#             log.trace(f"Stdin input:\n{msg}")
+#             log.runtime(f"Stdin input:\n{msg}")
 #             # encode to bytes
 #             bmsg = str.encode(msg)
 
@@ -116,20 +124,72 @@ class PdbwTeardown(pdbpp.Pdb):
 
 @asynccontextmanager
 async def _acquire_debug_lock(uid: Tuple[str, str]) -> AsyncIterator[None]:
-    """Acquire a actor local FIFO lock meant to mutex entry to a local
+    '''Acquire a actor local FIFO lock meant to mutex entry to a local
-    debugger entry point to avoid tty clobbering by multiple processes.
+    debugger entry point to avoid tty clobbering a global root process.
-    """
+
+    '''
+    global _debug_lock, _global_actor_in_debug, _no_remote_has_tty
+
     task_name = trio.lowlevel.current_task().name
+
+    log.pdb(
+        f"Attempting to acquire TTY lock, remote task: {task_name}:{uid}"
+    )
+
+    we_acquired = False
+
+    if _no_remote_has_tty is None:
+        # mark the tty lock as being in use so that the runtime
+        # can try to avoid clobbering any connection from a child
+        # that's currently relying on it.
+        _no_remote_has_tty = trio.Event()
+
     try:
         log.debug(
-            f"Attempting to acquire TTY lock, remote task: {task_name}:{uid}")
+            f"entering lock checkpoint, remote task: {task_name}:{uid}"
+        )
+        # with trio.CancelScope(shield=True):
+        we_acquired = True
         await _debug_lock.acquire()
 
+        # we_acquired = True
+
+        _global_actor_in_debug = uid
         log.debug(f"TTY lock acquired, remote task: {task_name}:{uid}")
-        yield
+
+        # NOTE: critical section!
+        # this yield is unshielded.
+        # IF we received a cancel during the shielded lock
+        # entry of some next-in-queue requesting task,
+        # then the resumption here will result in that
+        # Cancelled being raised to our caller below!
+
+        # in this case the finally below should trigger
+        # and the surrounding calle side context should cancel
+        # normally relaying back to the caller.
+
+        yield _debug_lock
 
     finally:
+        # if _global_actor_in_debug == uid:
+        if we_acquired and _debug_lock.locked():
             _debug_lock.release()
+
+        # IFF there are no more requesting tasks queued up fire, the
+        # "tty-unlocked" event thereby alerting any monitors of the lock that
+        # we are now back in the "tty unlocked" state. This is basically
+        # and edge triggered signal around an empty queue of sub-actor
+        # tasks that may have tried to acquire the lock.
+        stats = _debug_lock.statistics()
+        if (
+            not stats.owner
+        ):
+            log.pdb(f"No more tasks waiting on tty lock! says {uid}")
+            _no_remote_has_tty.set()
+            _no_remote_has_tty = None
+
+        _global_actor_in_debug = None
+
         log.debug(f"TTY lock released, remote task: {task_name}:{uid}")
 
 
@@ -144,78 +204,142 @@ 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(
-    subactor_uid: Tuple[str, str]
-) -> AsyncIterator[str]:
-    # TODO: when we get to true remote debugging
-    # this will deliver stdin data
-    log.warning(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():
+    ctx: tractor.Context,
+    subactor_uid: Tuple[str, str]
+
+) -> str:
+    '''Hijack the tty in the root process of an actor tree such that
+    the pdbpp debugger console can be allocated to a sub-actor for repl
+    bossing.
+
+    '''
+    task_name = trio.lowlevel.current_task().name
+
+    # TODO: when we get to true remote debugging
+    # this will deliver stdin data?
+
+    log.debug(
+        "Attempting to acquire TTY lock\n"
+        f"remote task: {task_name}:{subactor_uid}"
+    )
+
+    log.debug(f"Actor {subactor_uid} is WAITING on stdin hijack lock")
+
+    with trio.CancelScope(shield=True):
+
+        async with _acquire_debug_lock(subactor_uid):
 
             # indicate to child that we've locked stdio
-        yield 'Locked'
+            await ctx.started('Locked')
+            log.pdb(  # 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'
 
-    log.debug(f"Actor {subactor_uid} RELEASED stdin hijack lock")
+                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}")
+
+    return "pdb_unlock_complete"
 
 
-# XXX: We only make this sync in case someone wants to
+async def _breakpoint(
-# overload the ``breakpoint()`` built-in.
+
-def _breakpoint(debug_func) -> Awaitable[None]:
+    debug_func,
-    """``tractor`` breakpoint entry for engaging pdb machinery
+
-    in subactors.
+    # TODO:
-    """
+    # shield: bool = False
+
+) -> None:
+    '''``tractor`` breakpoint entry for engaging pdb machinery
+    in the root or a subactor.
+
+    '''
+    # TODO: is it possible to debug a trio.Cancelled except block?
+    # right now it seems like we can kinda do with by shielding
+    # around ``tractor.breakpoint()`` but not if we move the shielded
+    # scope here???
+    # with trio.CancelScope(shield=shield):
+
     actor = tractor.current_actor()
-    do_unlock = trio.Event()
+    task_name = trio.lowlevel.current_task().name
+
+    global _local_pdb_complete, _pdb_release_hook
+    global _local_task_in_debug, _global_actor_in_debug
+
+    await trio.lowlevel.checkpoint()
 
     async def wait_for_parent_stdin_hijack(
         task_status=trio.TASK_STATUS_IGNORED
     ):
         global _debugger_request_cs
-        with trio.CancelScope() as cs:
+
+        with trio.CancelScope(shield=True) as cs:
             _debugger_request_cs = cs
+
             try:
                 async with get_root() as portal:
-                        async with portal.open_stream_from(
+
+                    log.error('got portal')
+
+                    # this syncs to child's ``Context.started()`` call.
+                    async with portal.open_context(
+
                         tractor._debug._hijack_stdin_relay_to_child,
                         subactor_uid=actor.uid,
-                        ) as stream:
 
-                                # block until first yield above
+                    ) as (ctx, val):
-                                async for val in stream:
 
+                        log.error('locked context')
                         assert val == 'Locked'
+
+                        async with ctx.open_stream() as stream:
+
+                            log.error('opened stream')
+                            # unblock local caller
                             task_status.started()
 
-                                    # with trio.CancelScope(shield=True):
+                            try:
-                                    await do_unlock.wait()
+                                await _local_pdb_complete.wait()
+
+                            finally:
+                                # TODO: shielding currently can cause hangs...
+                                with trio.CancelScope(shield=True):
+                                    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 _local_pdb_complete or _local_pdb_complete.is_set():
-        """Async breakpoint which schedules a parent stdio lock, and once complete
+        _local_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():
-            if _in_debug:
+
-                if _in_debug == task_name:
+        if _local_task_in_debug:
+            if _local_task_in_debug == task_name:
                 # this task already has the lock and is
                 # likely recurrently entering a breakpoint
                 return
@@ -223,40 +347,72 @@ def _breakpoint(debug_func) -> Awaitable[None]:
             # 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(
+            log.warning(f"{actor.uid} already has a debug lock, waiting...")
-                    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
+            await _local_pdb_complete.wait()
-            global _pdb_release_hook
+            await trio.sleep(0.1)
-            _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
+        _local_task_in_debug = task_name
+
+        # assign unlock callback for debugger teardown hooks
+        _pdb_release_hook = _local_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.
+
+        # NOTE: if we want to debug a trio.Cancelled triggered exception
+        # we have to figure out how to avoid having the service nursery
+        # cancel on this task start? I *think* this works below?
+        # actor._service_n.cancel_scope.shield = shield
+        with trio.CancelScope(shield=True):
             await actor._service_n.start(wait_for_parent_stdin_hijack)
+        # actor._service_n.cancel_scope.shield = False
 
     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
+        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.
+        if _debug_lock.locked():
+            log.warning(
+                'Root actor attempting to acquire active tty lock'
+                f' owned by {_global_actor_in_debug}')
+
         await _debug_lock.acquire()
-            _pdb_release_hook = _debug_lock.release
+
+        _global_actor_in_debug = actor.uid
+        _local_task_in_debug = task_name
+
+        # the lock must be released on pdb completion
+        def teardown():
+            global _local_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
+            _local_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)
 
-    # user code **must** await this!
-    return _bp()
-
 
 def _mk_pdb():
     # XXX: setting these flags on the pdb instance are absolutely
@@ -276,7 +432,7 @@ def _set_trace(actor=None):
     pdb = _mk_pdb()
 
     if actor is not None:
-        log.runtime(f"\nAttaching pdb to actor: {actor.uid}\n")
+        log.pdb(f"\nAttaching pdb to actor: {actor.uid}\n")  # type: ignore
 
         pdb.set_trace(
             # start 2 levels up in user code
@@ -285,8 +441,8 @@ 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
@@ -306,7 +462,7 @@ breakpoint = partial(
 
 
 def _post_mortem(actor):
-    log.runtime(f"\nAttaching to pdb in crashed actor: {actor.uid}\n")
+    log.pdb(f"\nAttaching to pdb in crashed actor: {actor.uid}\n")
     pdb = _mk_pdb()
 
     # custom Pdb post-mortem entry

tractor/_discovery.py

@@ -16,12 +16,14 @@ from ._state import current_actor, _runtime_vars
 
 @asynccontextmanager
 async def get_arbiter(
+
     host: str,
     port: int,
+
 ) -> typing.AsyncGenerator[Union[Portal, LocalPortal], None]:
-    """Return a portal instance connected to a local or remote
+    '''Return a portal instance connected to a local or remote
     arbiter.
-    """
+    '''
     actor = current_actor()
 
     if not actor:
@@ -33,7 +35,9 @@ async def get_arbiter(
         yield LocalPortal(actor, Channel((host, port)))
     else:
         async with _connect_chan(host, port) as chan:
+
             async with open_portal(chan) as arb_portal:
+
                 yield arb_portal
 
 
@@ -41,8 +45,10 @@ async def get_arbiter(
 async def get_root(
     **kwargs,
 ) -> typing.AsyncGenerator[Union[Portal, LocalPortal], None]:
+
     host, port = _runtime_vars['_root_mailbox']
     assert host is not None
+
     async with _connect_chan(host, port) as chan:
         async with open_portal(chan, **kwargs) as portal:
             yield portal
@@ -60,12 +66,16 @@ async def find_actor(
     """
     actor = current_actor()
     async with get_arbiter(*arbiter_sockaddr or actor._arb_addr) as arb_portal:
+
         sockaddr = await arb_portal.run_from_ns('self', 'find_actor', name=name)
+
         # TODO: return portals to all available actors - for now just
         # the last one that registered
         if name == 'arbiter' and actor.is_arbiter:
             raise RuntimeError("The current actor is the arbiter")
+
         elif sockaddr:
+
             async with _connect_chan(*sockaddr) as chan:
                 async with open_portal(chan) as portal:
                     yield portal
@@ -83,9 +93,12 @@ async def wait_for_actor(
     A portal to the first registered actor is returned.
     """
     actor = current_actor()
+
     async with get_arbiter(*arbiter_sockaddr or actor._arb_addr) as arb_portal:
+
         sockaddrs = await arb_portal.run_from_ns('self', 'wait_for_actor', name=name)
         sockaddr = sockaddrs[-1]
+
         async with _connect_chan(*sockaddr) as chan:
             async with open_portal(chan) as portal:
                 yield portal

tractor/_entry.py

@@ -3,7 +3,6 @@ Sub-process entry points.
 """
 from functools import partial
 from typing import Tuple, Any
-import signal
 
 import trio  # type: ignore
 
@@ -15,7 +14,7 @@ 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,
@@ -54,16 +53,13 @@ def _mp_main(
 
 
 def _trio_main(
-    actor: 'Actor',  # type: ignore
+    actor: 'Actor',  # type: ignore # noqa
     *,
     parent_addr: Tuple[str, int] = None,
 ) -> None:
     """Entry point for a `trio_run_in_process` subactor.
-    """
-    # Disable sigint handling in children;
-    # 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}")
 
     if actor.loglevel is not None:

tractor/_exceptions.py

@@ -1,7 +1,7 @@
 """
 Our classy exception set.
 """
-from typing import Dict, Any
+from typing import Dict, Any, Optional
 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[Exception] = 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 +37,10 @@ class InternalActorError(RemoteActorError):
     """
 
 
+class ContextCancelled(RemoteActorError):
+    "Inter-actor task context cancelled itself on the callee side."
+
+
 class NoResult(RuntimeError):
     "No final result is expected for this actor"
 
@@ -50,13 +53,22 @@ class NoRuntime(RuntimeError):
     "The root actor has not been initialized yet"
 
 
-def pack_error(exc: BaseException) -> Dict[str, Any]:
+def pack_error(
+    exc: BaseException,
+    tb = None,
+
+) -> Dict[str, Any]:
     """Create an "error message" for tranmission over
     a channel (aka the wire).
     """
+    if tb:
+        tb_str = ''.join(traceback.format_tb(tb))
+    else:
+        tb_str = traceback.format_exc()
+
     return {
         'error': {
-            'tb_str': traceback.format_exc(),
+            'tb_str': tb_str,
             'type_str': type(exc).__name__,
         }
     }
@@ -70,12 +82,35 @@ def unpack_error(
     """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 = 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 +1,19 @@
 """
 Inter-process comms abstractions
 """
+from functools import partial
+import struct
 import typing
 from typing import Any, Tuple, Optional
-from functools import partial
 
+from tricycle import BufferedReceiveStream
 import msgpack
 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 +24,32 @@ 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 first entry to read loop
         self._agen = self._iter_packets()
+
         self._send_lock = trio.StrictFIFOLock()
 
     async def _iter_packets(self) -> typing.AsyncGenerator[dict, None]:
@@ -46,16 +60,13 @@ class MsgpackStream:
             use_list=False,
         )
         while True:
-            try:
             data = await self.stream.receive_some(2**10)
             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 +84,8 @@ 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)
@@ -85,33 +97,112 @@ class MsgpackStream:
         return self.stream.socket.fileno() != -1
 
 
+class MsgspecTCPStream(MsgpackTCPStream):
+    '''A ``trio.SocketStream`` delivering ``msgpack`` formatted data
+    using ``msgspec``.
+
+    '''
+    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
+
+        import msgspec
+
+        # TODO: struct aware messaging coders
+        self.encode = msgspec.Encoder().encode
+        self.decode = msgspec.Decoder().decode  # dict[str, Any])
+
+    async def _iter_packets(self) -> typing.AsyncGenerator[dict, None]:
+        """Yield packets from the underlying stream.
+        """
+
+        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}')  # type: ignore
+
+            msg_bytes = await self.recv_stream.receive_exactly(size)
+
+            log.trace(f"received {msg_bytes}")  # type: ignore
+            yield self.decode(msg_bytes)
+
+    async def send(self, data: Any) -> None:
+        async with self._send_lock:
+
+            bytes_data: bytes = self.encode(data)
+
+            # supposedly the fastest says,
+            # https://stackoverflow.com/a/54027962
+            size: bytes = 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
+
     ) -> None:
+
         self._recon_seq = on_reconnect
         self._autorecon = auto_reconnect
-        self.msgstream: Optional[MsgpackStream] = MsgpackStream(
+
-            stream) if stream else None
+        stream_serializer_type = MsgpackTCPStream
+
+        try:
+            # if installed load the msgspec transport since it's faster
+            import msgspec  # noqa
+            stream_serializer_type = MsgspecTCPStream
+        except ImportError:
+            pass
+
+        self.stream_serializer_type = stream_serializer_type
+        self.msgstream = 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
+
         # set if far end actor errors internally
         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 +219,51 @@ 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,
+            **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
@@ -289,6 +295,7 @@ class Portal:
         self,
         async_gen_func: Callable,  # typing: ignore
         **kwargs,
+
     ) -> AsyncGenerator[ReceiveMsgStream, None]:
 
         if not inspect.isasyncgenfunction(async_gen_func):
@@ -312,13 +319,23 @@ 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 +343,127 @@ class Portal:
 
             self._streams.remove(rchan)
 
-    # @asynccontextmanager
+    @asynccontextmanager
-    # async def open_context(
+    async def open_context(
-    #     self,
+
-    #     func: Callable,
+        self,
-    #     **kwargs,
+        func: Callable,
-    # ) -> Context:
+        **kwargs,
-    #     # TODO
+
-    #     elif resptype == 'context':  # context manager style setup/teardown
+    ) -> AsyncGenerator[Tuple[Context, Any], None]:
-    #         # TODO likely not here though
+        '''Open an inter-actor task context.
-    #         raise NotImplementedError
+
+        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
+
+        _err = None
+        # 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
+
+                # await trio.lowlevel.checkpoint()
+                yield ctx, first
+
+                # if not ctx._cancel_called:
+                #     await ctx.result()
+
+            # await recv_chan.aclose()
+
+        except ContextCancelled as err:
+            _err = err
+            if not ctx._cancel_called:
+                # context was cancelled at the far end but was
+                # not part of this end requesting that cancel
+                # so raise for the local task to respond and handle.
+                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,
+            trio.MultiError,
+            Exception,
+        ) as err:
+            _err = err
+            # the context cancels itself on any cancel
+            # causing error.
+            log.error(f'Context {ctx} sending cancel to far end')
+            with trio.CancelScope(shield=True):
+                await ctx.cancel()
+            raise
+
+        finally:
+            result = await ctx.result()
+
+            # though it should be impossible for any tasks
+            # operating *in* this scope to have survived
+            # we tear down the runtime feeder chan last
+            # to avoid premature stream clobbers.
+            if recv_chan is not None:
+                await recv_chan.aclose()
+
+            if _err:
+                if ctx._cancel_called:
+                    log.warning(
+                        f'Context {fn_name} cancelled by caller with\n{_err}'
+                    )
+                elif _err is not None:
+                    log.warning(
+                        f'Context {fn_name} cancelled by callee with\n{_err}'
+                    )
+            else:
+                log.info(
+                    f'Context {fn_name} returned '
+                    f'value from callee `{self._result}`'
+                )
 
 
 @dataclass
@@ -360,10 +488,12 @@ class LocalPortal:
 
 @asynccontextmanager
 async def open_portal(
+
     channel: Channel,
     nursery: Optional[trio.Nursery] = None,
     start_msg_loop: bool = True,
     shield: bool = False,
+
 ) -> AsyncGenerator[Portal, None]:
     """Open a ``Portal`` through the provided ``channel``.
 
@@ -374,6 +504,7 @@ 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
@@ -395,12 +526,14 @@ 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)
+                # await channel.aclose()
 
             # cancel background msg loop task
             if msg_loop_cs:

tractor/_root.py

@@ -166,15 +166,17 @@ async def open_root_actor(
                 yield actor
 
             except (Exception, trio.MultiError) as err:
-                logger.exception("Actor crashed:")
+                # with trio.CancelScope(shield=True):
-                await _debug._maybe_enter_pm(err)
+                entered = await _debug._maybe_enter_pm(err)
+
+                if not entered:
+                    logger.exception("Root actor crashed:")
 
                 # always re-raise
                 raise
 
             finally:
                 logger.info("Shutting down root actor")
-                with trio.CancelScope(shield=True):
                 await actor.cancel()
     finally:
         _state._current_actor = None

tractor/_spawn.py

@@ -22,7 +22,14 @@ 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 ._debug import _global_actor_in_debug
+
 from .log import get_logger
 from ._portal import Portal
 from ._actor import Actor, ActorFailure
@@ -141,13 +148,34 @@ async def cancel_on_completion(
             )
 
         else:
-            log.info(
+            log.runtime(
                 f"Cancelling {portal.channel.uid} gracefully "
                 f"after result {result}")
 
         # cancel the process now that we have a final result
         await portal.cancel_actor()
 
+async def do_hard_kill(
+    proc: trio.Process,
+
+) -> None:
+    # 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:
+        # XXX: should pretty much never get here unless we have
+        # to move the bits from ``proc.__aexit__()`` out and
+        # into here.
+        log.critical(f"HARD KILLING {proc}")
+        proc.kill()
+
 
 @asynccontextmanager
 async def spawn_subactor(
@@ -180,26 +208,48 @@ async def spawn_subactor(
     proc = await trio.open_process(spawn_cmd)
     try:
         yield proc
+
     finally:
+        log.runtime(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:
+        #     and _global_actor_in_debug is not None
-                log.debug(f"Terminating {proc}")
+        # ):
-        if cs.cancelled_caught:
+        #     # XXX: this is ``trio.Process.aclose()`` MINUS the
-            log.critical(f"HARD KILLING {proc}")
+        #     # std-streams pre-closing steps inside ``proc.__aexit__()``
-            proc.kill()
+        #     # (see below) which incluses a ``Process.kill()`` call
+
+        #     log.error(
+        #         "Root process tty is locked in debug mode by "
+        #         f"{_global_actor_in_debug}. If the console is hanging, you "
+        #         "may need to trigger a KBI to kill any "
+        #         "not-fully-initialized" " subprocesses and allow errors "
+        #         "from `trio` to propagate"
+        #     )
+        #     try:
+        #         # one more graceful wait try can can be cancelled by KBI
+        #         # sent by user.
+        #         await proc.wait()
+
+        #     finally:
+        #         if proc.returncode is None:
+        #             # with trio.CancelScope(shield=True):
+        #             #     await proc.wait()
+
+        #             await do_hard_kill(proc)
+        # else:
+
+        await do_hard_kill(proc)
 
 
 async def new_proc(
@@ -212,7 +262,6 @@ 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,
     task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED
 ) -> None:
     """Create a new ``multiprocessing.Process`` using the
@@ -223,13 +272,13 @@ 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,
             ) 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
@@ -277,9 +326,14 @@ async def new_proc(
                 # reaping more stringently without the shield
                 # we used to have below...
 
-                # always "hard" join sub procs:
-                # no actor zombies allowed
                 # with trio.CancelScope(shield=True):
+                # async with proc:
+
+                # Always "hard" join sub procs since no actor zombies
+                # are allowed!
+
+                # this is a "light" (cancellable) join, the hard join is
+                # in the enclosing scope (see above).
                 await proc.wait()
 
             log.debug(f"Joined {proc}")
@@ -320,7 +374,6 @@ 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,
     task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED
 
 ) -> None:
@@ -380,7 +433,7 @@ 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 +1,312 @@
+"""
+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 ._exceptions import unpack_error, ContextCancelled
+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:
+
+            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
+
+    @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:
+            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:
 
@@ -50,15 +321,40 @@ 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:
+        '''Unpack and raise a msg error into the local scope
+        nursery for this context.
+
+        Acts as a form of "relay" for a remote error raised
+        in the corresponding remote callee task.
+        '''
+        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, (
+        side = 'caller' if self._portal else 'callee'
-            "No portal found, this is likely a callee side context")
+
+        log.warning(f'Cancelling {side} side of context to {self.chan}')
+
+        self._cancel_called = True
+
+        if side == 'caller':
+            if not self._portal:
+                raise RuntimeError(
+                    "No portal found, this is likely a callee side context"
+                )
 
             cid = self.cid
             with trio.move_on_after(0.5) as cs:
@@ -76,27 +372,175 @@ class Context:
                 # 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._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:
+            # callee side remote task
 
+            # 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
+        )
+
+        # Likewise if the surrounding context has been cancelled we error here
+        # since it likely means the surrounding block was exited or
+        # killed
+
+        if self._cancel_called:
+            task = trio.lowlevel.current_task().name
+            raise ContextCancelled(
+                f'Context around {actor.uid[0]}:{task} was already cancelled!'
+            )
+
+        # XXX: If the underlying channel feeder receive mem chan has
+        # been closed then likely client code has already exited
+        # a ``.open_stream()`` block prior or there was some other
+        # unanticipated error or cancellation from ``trio``.
+
+        if recv_chan._closed:
+            raise trio.ClosedResourceError(
+                'The underlying channel for this stream was already closed!?')
+
+        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:
@@ -115,146 +559,25 @@ def stream(func):
         raise TypeError(
             "The first argument to the stream function "
             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
@@ -169,16 +170,25 @@ class ActorNursery:
 
         log.warning(f"Cancelling nursery in {self._actor.uid}")
         with trio.move_on_after(3) as cs:
+
             async with trio.open_nursery() as nursery:
+
                 for subactor, proc, portal in self._children.values():
+
+                    # TODO: are we ever even going to use this or
+                    # is the spawning backend responsible for such
+                    # things? I'm thinking latter.
                     if hard_kill:
                         proc.terminate()
+
                     else:
                         if portal is None:  # actor hasn't fully spawned yet
                             event = self._actor._peer_connected[subactor.uid]
                             log.warning(
                                 f"{subactor.uid} wasn't finished spawning?")
+
                             await event.wait()
+
                             # channel/portal should now be up
                             _, _, portal = self._children[subactor.uid]
 
@@ -238,6 +248,7 @@ async def _open_and_supervise_one_cancels_all_nursery(
             # As such if the strategy propagates any error(s) upwards
             # the above "daemon actor" nursery will be notified.
             async with trio.open_nursery() as ria_nursery:
+
                 anursery = ActorNursery(
                     actor,
                     ria_nursery,
@@ -248,15 +259,53 @@ async def _open_and_supervise_one_cancels_all_nursery(
                     # spawning of actors happens in the caller's scope
                     # after we yield upwards
                     yield anursery
-                    log.debug(
+
+                    log.runtime(
                         f"Waiting on subactors {anursery._children} "
                         "to complete"
                     )
+
+                    # Last bit before first nursery block ends in the case
+                    # where we didn't error in the caller's scope
+
+                    # signal all process monitor tasks to conduct
+                    # hard join phase.
+                    anursery._join_procs.set()
+
                 except BaseException as err:
+
+                    # 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 since it
+                    # will make the pdb repl unusable.
+                    # Instead try to wait for pdb to be released before
+                    # tearing down.
+                    if is_root_process():
+                        log.exception(f"we're root with {err}")
+
+                        # wait to see if a sub-actor task
+                        # will be scheduled and grab the tty
+                        # lock on the next tick
+                        # await trio.testing.wait_all_tasks_blocked()
+
+                        debug_complete = _debug._no_remote_has_tty
+                        if (
+                            debug_complete and
+                            not debug_complete.is_set()
+                        ):
+                            log.warning(
+                                'Root has errored but pdb is in use by '
+                                f'child {_debug._global_actor_in_debug}\n'
+                                'Waiting on tty lock to release..')
+
+                            with trio.CancelScope(shield=True):
+                                await debug_complete.wait()
+
                     # if the caller's scope errored then we activate our
                     # one-cancels-all supervisor strategy (don't
                     # worry more are coming).
                     anursery._join_procs.set()
+
                     try:
                         # XXX: hypothetically an error could be
                         # raised and then a cancel signal shows up
@@ -292,15 +341,18 @@ async def _open_and_supervise_one_cancels_all_nursery(
                     else:
                         raise
 
-                # Last bit before first nursery block ends in the case
-                # where we didn't error in the caller's scope
-                log.debug("Waiting on all subactors to complete")
-                anursery._join_procs.set()
-
                 # ria_nursery scope end
 
         # XXX: do we need a `trio.Cancelled` catch here as well?
-        except (Exception, trio.MultiError, trio.Cancelled) as err:
+        # this is the catch around the ``.run_in_actor()`` nursery
+        except (
+
+            Exception,
+            trio.MultiError,
+            trio.Cancelled
+
+        ) as err:
+
             # If actor-local error was raised while waiting on
             # ".run_in_actor()" actors then we also want to cancel all
             # remaining sub-actors (due to our lone strategy:
@@ -357,7 +409,8 @@ 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 +419,7 @@ 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 +430,6 @@ async def open_nursery(
             async with _open_and_supervise_one_cancels_all_nursery(
                 actor
             ) as anursery:
-
                 yield anursery
 
     finally:

tractor/log.py

@@ -29,19 +29,20 @@ LOG_FORMAT = (
 DATE_FORMAT = '%b %d %H:%M:%S'
 LEVELS = {
     'GARBAGE': 1,
-    'TRACE': 5,
+    'TRANSPORT': 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',
+    'TRANSPORT': 'cyan',
     'GARBAGE': 'blue',
 }
 BOLD_PALETTE = {
@@ -76,7 +77,7 @@ def get_logger(
     # additional levels
     for name, val in LEVELS.items():
         logging.addLevelName(val, name)
-        # ex. create ``logger.trace()``
+        # ex. create ``logger.runtime()``
         setattr(logger, name.lower(), partial(logger.log, val))
 
     return logger

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)
 
@@ -256,7 +276,7 @@ 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,