Merge pull request #358 from goodboy/switch_to_pdbp

Switch to `pdbp` 🏄🏼

docs/README.rst

@@ -6,8 +6,14 @@
 ``tractor`` is a `structured concurrent`_, multi-processing_ runtime
 built on trio_.
 
-Fundamentally ``tractor`` gives you parallelism via ``trio``-"*actors*":
+Fundamentally, ``tractor`` gives you parallelism via
-our nurseries_ let you spawn new Python processes which each run a ``trio``
+``trio``-"*actors*": independent Python processes (aka
+non-shared-memory threads) which maintain structured
+concurrency (SC) *end-to-end* inside a *supervision tree*.
+
+Cross-process (and thus cross-host) SC is accomplished through the
+combined use of our "actor nurseries_" and an "SC-transitive IPC
+protocol" constructed on top of multiple Pythons each running a ``trio``
 scheduled runtime - a call to ``trio.run()``.
 
 We believe the system adheres to the `3 axioms`_ of an "`actor model`_"
@@ -23,7 +29,8 @@ Features
 - **It's just** a ``trio`` API
 - *Infinitely nesteable* process trees
 - Builtin IPC streaming APIs with task fan-out broadcasting
-- A (first ever?) "native" multi-core debugger UX for Python using `pdb++`_
+- A "native" multi-core debugger REPL using `pdbp`_ (a fork & fix of
+  `pdb++`_ thanks to @mdmintz!)
 - Support for a swappable, OS specific, process spawning layer
 - A modular transport stack, allowing for custom serialization (eg. with
   `msgspec`_), communications protocols, and environment specific IPC
@@ -118,7 +125,7 @@ Zombie safe: self-destruct a process tree
             f"running in pid {os.getpid()}"
         )
 
-       await trio.sleep_forever()
+        await trio.sleep_forever()
 
 
     async def main():
@@ -149,7 +156,7 @@ it **is a bug**.
 
 "Native" multi-process debugging
 --------------------------------
-Using the magic of `pdb++`_ and our internal IPC, we've
+Using the magic of `pdbp`_ and our internal IPC, we've
 been able to create a native feeling debugging experience for
 any (sub-)process in your ``tractor`` tree.
 
@@ -597,6 +604,7 @@ channel`_!
 .. _adherance to: https://www.youtube.com/watch?v=7erJ1DV_Tlo&t=1821s
 .. _trio gitter channel: https://gitter.im/python-trio/general
 .. _matrix channel: https://matrix.to/#/!tractor:matrix.org
+.. _pdbp: https://github.com/mdmintz/pdbp
 .. _pdb++: https://github.com/pdbpp/pdbpp
 .. _guest mode: https://trio.readthedocs.io/en/stable/reference-lowlevel.html?highlight=guest%20mode#using-guest-mode-to-run-trio-on-top-of-other-event-loops
 .. _messages: https://en.wikipedia.org/wiki/Message_passing

examples/debugging/asyncio_bp.py

@@ -1,117 +0,0 @@
-import asyncio
-
-import trio
-import tractor
-from tractor import to_asyncio
-
-
-async def aio_sleep_forever():
-    await asyncio.sleep(float('inf'))
-
-
-async def bp_then_error(
-    to_trio: trio.MemorySendChannel,
-    from_trio: asyncio.Queue,
-
-    raise_after_bp: bool = True,
-
-) -> None:
-
-    # sync with ``trio``-side (caller) task
-    to_trio.send_nowait('start')
-
-    # NOTE: what happens here inside the hook needs some refinement..
-    # => seems like it's still `._debug._set_trace()` but
-    #    we set `Lock.local_task_in_debug = 'sync'`, we probably want
-    #    some further, at least, meta-data about the task/actoq in debug
-    #    in terms of making it clear it's asyncio mucking about.
-    breakpoint()
-
-    # short checkpoint / delay
-    await asyncio.sleep(0.5)
-
-    if raise_after_bp:
-        raise ValueError('blah')
-
-    # TODO: test case with this so that it gets cancelled?
-    else:
-        # XXX NOTE: this is required in order to get the SIGINT-ignored
-        # hang case documented in the module script section!
-        await aio_sleep_forever()
-
-
-@tractor.context
-async def trio_ctx(
-    ctx: tractor.Context,
-    bp_before_started: bool = False,
-):
-
-    # this will block until the ``asyncio`` task sends a "first"
-    # message, see first line in above func.
-    async with (
-
-        to_asyncio.open_channel_from(
-            bp_then_error,
-            raise_after_bp=not bp_before_started,
-        ) as (first, chan),
-
-        trio.open_nursery() as n,
-    ):
-
-        assert first == 'start'
-
-        if bp_before_started:
-            await tractor.breakpoint()
-
-        await ctx.started(first)
-
-        n.start_soon(
-            to_asyncio.run_task,
-            aio_sleep_forever,
-        )
-        await trio.sleep_forever()
-
-
-async def main(
-    bps_all_over: bool = False,
-
-) -> None:
-
-    async with tractor.open_nursery() as n:
-
-        p = await n.start_actor(
-            'aio_daemon',
-            enable_modules=[__name__],
-            infect_asyncio=True,
-            debug_mode=True,
-            loglevel='cancel',
-        )
-
-        async with p.open_context(
-            trio_ctx,
-            bp_before_started=bps_all_over,
-        ) as (ctx, first):
-
-            assert first == 'start'
-
-            if bps_all_over:
-                await tractor.breakpoint()
-
-            # await trio.sleep_forever()
-            await ctx.cancel()
-            assert 0
-
-        # TODO: case where we cancel from trio-side while asyncio task
-        # has debugger lock?
-        # await p.cancel_actor()
-
-
-if __name__ == '__main__':
-
-    # works fine B)
-    trio.run(main)
-
-    # will hang and ignores SIGINT !!
-    # NOTE: you'll need to send a SIGQUIT (via ctl-\) to kill it
-    # manually..
-    # trio.run(main, True)

nooz/356.trivial.rst

@@ -0,0 +1,7 @@
+Drop `trio.Process.aclose()` usage, copy into our spawning code.
+
+The details are laid out in https://github.com/goodboy/tractor/issues/330.
+`trio` changed is process running quite some time ago, this just copies
+out the small bit we needed (from the old `.aclose()`) for hard kills
+where a soft runtime cancel request fails and our "zombie killer"
+implementation kicks in.

nooz/358.feature.rst

@@ -0,0 +1,15 @@
+Switch to using the fork & fix of `pdb++`, `pdbp`:
+https://github.com/mdmintz/pdbp
+
+Allows us to sidestep a variety of issues that aren't being maintained
+in the upstream project thanks to the hard work of @mdmintz!
+
+We also include some default settings adjustments as per recent
+development on the fork:
+
+- sticky mode is still turned on by default but now activates when
+  a using the `ll` repl command.
+- turn off line truncation by default to avoid inter-line gaps when
+  resizing the terimnal during use.
+- when using the backtrace cmd either by `w` or `bt`, the config
+  automatically switches to non-sticky mode.

requirements-test.txt

@@ -1,7 +1,7 @@
 pytest
 pytest-trio
 pytest-timeout
-pdbpp
+pdbp
 mypy
 trio_typing
 pexpect

setup.py

@@ -26,12 +26,12 @@ with open('docs/README.rst', encoding='utf-8') as f:
 setup(
     name="tractor",
     version='0.1.0a6dev0',  # alpha zone
-    description='structured concurrrent "actors"',
+    description='structured concurrrent `trio`-"actors"',
     long_description=readme,
     license='AGPLv3',
     author='Tyler Goodlet',
     maintainer='Tyler Goodlet',
-    maintainer_email='jgbt@protonmail.com',
+    maintainer_email='goodboy_foss@protonmail.com',
     url='https://github.com/goodboy/tractor',
     platforms=['linux', 'windows'],
     packages=[
@@ -52,12 +52,10 @@ setup(
         # tooling
         'tricycle',
         'trio_typing',
-
-        # tooling
         'colorlog',
         'wrapt',
 
-        # serialization
+        # IPC serialization
         'msgspec',
 
         # debug mode REPL
@@ -73,10 +71,9 @@ setup(
         # https://github.com/pdbpp/fancycompleter/issues/37
         'pyreadline3 ; platform_system == "Windows"',
 
-
     ],
     tests_require=['pytest'],
-    python_requires=">=3.9",
+    python_requires=">=3.10",
     keywords=[
         'trio',
         'async',

tests/test_clustering.py

@@ -49,7 +49,7 @@ async def worker(
     await ctx.started()
 
     async with ctx.open_stream(
-        allow_overruns=True,
+        backpressure=True,
     ) as stream:
 
         # TODO: this with the below assert causes a hang bug?

tests/test_context_stream_semantics.py

@@ -13,10 +13,7 @@ from typing import Optional
 import pytest
 import trio
 import tractor
-from tractor._exceptions import (
+from tractor._exceptions import StreamOverrun
-    StreamOverrun,
-    ContextCancelled,
-)
 
 from conftest import tractor_test
 
@@ -94,10 +91,7 @@ async def not_started_but_stream_opened(
 
 @pytest.mark.parametrize(
     'target',
-    [
+    [too_many_starteds, not_started_but_stream_opened],
-        too_many_starteds,
-        not_started_but_stream_opened,
-    ],
     ids='misuse_type={}'.format,
 )
 def test_started_misuse(target):
@@ -234,88 +228,6 @@ def test_simple_context(
         trio.run(main)
 
 
-@pytest.mark.parametrize(
-    'callee_returns_early',
-    [True, False],
-    ids=lambda item: f'callee_returns_early={item}'
-)
-@pytest.mark.parametrize(
-    'cancel_method',
-    ['ctx', 'portal'],
-    ids=lambda item: f'cancel_method={item}'
-)
-@pytest.mark.parametrize(
-    'chk_ctx_result_before_exit',
-    [True, False],
-    ids=lambda item: f'chk_ctx_result_before_exit={item}'
-)
-def test_caller_cancels(
-    cancel_method: str,
-    chk_ctx_result_before_exit: bool,
-    callee_returns_early: bool,
-):
-    '''
-    Verify that when the opening side of a context (aka the caller)
-    cancels that context, the ctx does not raise a cancelled when
-    either calling `.result()` or on context exit.
-
-    '''
-    async def check_canceller(
-        ctx: tractor.Context,
-    ) -> None:
-        # should not raise yet return the remote
-        # context cancelled error.
-        res = await ctx.result()
-
-        if callee_returns_early:
-            assert res == 'yo'
-
-        else:
-            err = res
-            assert isinstance(err, ContextCancelled)
-            assert (
-                tuple(err.canceller)
-                ==
-                tractor.current_actor().uid
-            )
-
-    async def main():
-        async with tractor.open_nursery() as nursery:
-            portal = await nursery.start_actor(
-                'simple_context',
-                enable_modules=[__name__],
-            )
-            timeout = 0.5 if not callee_returns_early else 2
-            with trio.fail_after(timeout):
-                async with portal.open_context(
-                    simple_setup_teardown,
-                    data=10,
-                    block_forever=not callee_returns_early,
-                ) as (ctx, sent):
-
-                    if callee_returns_early:
-                        # ensure we block long enough before sending
-                        # a cancel such that the callee has already
-                        # returned it's result.
-                        await trio.sleep(0.5)
-
-                    if cancel_method == 'ctx':
-                        await ctx.cancel()
-                    else:
-                        await portal.cancel_actor()
-
-                    if chk_ctx_result_before_exit:
-                        await check_canceller(ctx)
-
-            if not chk_ctx_result_before_exit:
-                await check_canceller(ctx)
-
-            if cancel_method != 'portal':
-                await portal.cancel_actor()
-
-    trio.run(main)
-
-
 # basic stream terminations:
 # - callee context closes without using stream
 # - caller context closes without using stream
@@ -594,6 +506,7 @@ async def test_callee_cancels_before_started():
                 cancel_self,
             ) as (ctx, sent):
                 async with ctx.open_stream():
+
                     await trio.sleep_forever()
 
         # raises a special cancel signal
@@ -646,6 +559,7 @@ async def keep_sending_from_callee(
     'overrun_by',
     [
         ('caller', 1, never_open_stream),
+        ('cancel_caller_during_overrun', 1, never_open_stream),
         ('callee', 0, keep_sending_from_callee),
     ],
     ids='overrun_condition={}'.format,
@@ -675,13 +589,14 @@ def test_one_end_stream_not_opened(overrun_by):
                 if 'caller' in overrunner:
 
                     async with ctx.open_stream() as stream:
-
-                        # itersend +1 msg more then the buffer size
-                        # to cause the most basic overrun.
                         for i in range(buf_size):
                             print(f'sending {i}')
                             await stream.send(i)
 
+                        if 'cancel' in overrunner:
+                            # without this we block waiting on the child side
+                            await ctx.cancel()
+
                         else:
                             # expect overrun error to be relayed back
                             # and this sleep interrupted
@@ -695,9 +610,7 @@ def test_one_end_stream_not_opened(overrun_by):
 
     # 2 overrun cases and the no overrun case (which pushes right up to
     # the msg limit)
-    if (
+    if overrunner == 'caller' or 'cance' in overrunner:
-        overrunner == 'caller'
-    ):
         with pytest.raises(tractor.RemoteActorError) as excinfo:
             trio.run(main)
 
@@ -721,102 +634,40 @@ async def echo_back_sequence(
 
     ctx:  tractor.Context,
     seq: list[int],
-    wait_for_cancel: bool,
+    msg_buffer_size: Optional[int] = None,
-    allow_overruns_side: str,
-    be_slow: bool = False,
-    msg_buffer_size: int = 1,
 
 ) -> None:
     '''
-    Send endlessly on the calleee stream using a small buffer size
+    Send endlessly on the calleee stream.
-    setting on the contex to simulate backlogging that would normally
-    cause overruns.
 
     '''
-    # NOTE: ensure that if the caller is expecting to cancel this task
-    # that we stay echoing much longer then they are so we don't
-    # return early instead of receive the cancel msg.
-    total_batches: int = 1000 if wait_for_cancel else 6
-
     await ctx.started()
-    # await tractor.breakpoint()
     async with ctx.open_stream(
         msg_buffer_size=msg_buffer_size,
-
-        # literally the point of this test XD
-        allow_overruns=(allow_overruns_side in {'child', 'both'}),
     ) as stream:
 
-        # ensure mem chan settings are correct
+        seq = list(seq)  # bleh, `msgpack`...
-        assert (
+        count = 0
-            ctx._send_chan._state.max_buffer_size
+        while count < 3:
-            ==
-            msg_buffer_size
-        )
-
-        seq = list(seq)  # bleh, msgpack sometimes ain't decoded right
-        for _ in range(total_batches):
             batch = []
             async for msg in stream:
                 batch.append(msg)
                 if batch == seq:
                     break
 
-                if be_slow:
-                    await trio.sleep(0.05)
-
-                print('callee waiting on next')
-
             for msg in batch:
                 print(f'callee sending {msg}')
                 await stream.send(msg)
 
-    print(
+            count += 1
-        'EXITING CALLEEE:\n'
+
-        f'{ctx.cancel_called_remote}'
+        return 'yo'
-    )
-    return 'yo'
 
 
-@pytest.mark.parametrize(
+def test_stream_backpressure():
-    # aka the side that will / should raise
-    # and overrun under normal conditions.
-    'allow_overruns_side',
-    ['parent', 'child', 'none', 'both'],
-    ids=lambda item: f'allow_overruns_side={item}'
-)
-@pytest.mark.parametrize(
-    # aka the side that will / should raise
-    # and overrun under normal conditions.
-    'slow_side',
-    ['parent', 'child'],
-    ids=lambda item: f'slow_side={item}'
-)
-@pytest.mark.parametrize(
-    'cancel_ctx',
-    [True, False],
-    ids=lambda item: f'cancel_ctx={item}'
-)
-def test_maybe_allow_overruns_stream(
-    cancel_ctx: bool,
-    slow_side: str,
-    allow_overruns_side: str,
-    loglevel: str,
-):
     '''
     Demonstrate small overruns of each task back and forth
-    on a stream not raising any errors by default by setting
+    on a stream not raising any errors by default.
-    the ``allow_overruns=True``.
-
-    The original idea here was to show that if you set the feeder mem
-    chan to a size smaller then the # of msgs sent you could could not
-    get a `StreamOverrun` crash plus maybe get all the msgs that were
-    sent. The problem with the "real backpressure" case is that due to
-    the current arch it can result in the msg loop being blocked and thus
-    blocking cancellation - which is like super bad. So instead this test
-    had to be adjusted to more or less just "not send overrun errors" so
-    as to handle the case where the sender just moreso cares about not getting
-    errored out when it send to fast..
 
     '''
     async def main():
@@ -824,104 +675,38 @@ def test_maybe_allow_overruns_stream(
             portal = await n.start_actor(
                 'callee_sends_forever',
                 enable_modules=[__name__],
-                loglevel=loglevel,
-
-                # debug_mode=True,
             )
-            seq = list(range(10))
+            seq = list(range(3))
             async with portal.open_context(
                 echo_back_sequence,
                 seq=seq,
-                wait_for_cancel=cancel_ctx,
+                msg_buffer_size=1,
-                be_slow=(slow_side == 'child'),
-                allow_overruns_side=allow_overruns_side,
             ) as (ctx, sent):
-
                 assert sent is None
 
-                async with ctx.open_stream(
+                async with ctx.open_stream(msg_buffer_size=1) as stream:
-                    msg_buffer_size=1 if slow_side == 'parent' else None,
+                    count = 0
-                    allow_overruns=(allow_overruns_side in {'parent', 'both'}),
+                    while count < 3:
-                ) as stream:
-
-                    total_batches: int = 2
-                    for _ in range(total_batches):
                         for msg in seq:
-                            # print(f'root tx {msg}')
+                            print(f'caller sending {msg}')
                             await stream.send(msg)
-                            if slow_side == 'parent':
+                            await trio.sleep(0.1)
-                                # NOTE: we make the parent slightly
-                                # slower, when it is slow, to make sure
-                                # that in the overruns everywhere case
-                                await trio.sleep(0.16)
 
                         batch = []
                         async for msg in stream:
-                            print(f'root rx {msg}')
                             batch.append(msg)
                             if batch == seq:
                                 break
 
-                if cancel_ctx:
+                        count += 1
-                    # cancel the remote task
-                    print('sending root side cancel')
-                    await ctx.cancel()
 
-            res = await ctx.result()
+            # here the context should return
-
+            assert await ctx.result() == 'yo'
-            if cancel_ctx:
-                assert isinstance(res, ContextCancelled)
-                assert tuple(res.canceller) == tractor.current_actor().uid
-
-            else:
-                print(f'RX ROOT SIDE RESULT {res}')
-                assert res == 'yo'
 
             # cancel the daemon
             await portal.cancel_actor()
 
-    if (
+    trio.run(main)
-        allow_overruns_side == 'both'
-        or slow_side == allow_overruns_side
-    ):
-        trio.run(main)
-
-    elif (
-        slow_side != allow_overruns_side
-    ):
-
-        with pytest.raises(tractor.RemoteActorError) as excinfo:
-            trio.run(main)
-
-        err = excinfo.value
-
-        if (
-            allow_overruns_side == 'none'
-        ):
-            # depends on timing is is racy which side will
-            # overrun first :sadkitty:
-
-            # NOTE: i tried to isolate to a deterministic case here
-            # based on timeing, but i was kinda wasted, and i don't
-            # think it's sane to catch them..
-            assert err.type in (
-                tractor.RemoteActorError,
-                StreamOverrun,
-            )
-
-        elif (
-            slow_side == 'child'
-        ):
-            assert err.type == StreamOverrun
-
-        elif slow_side == 'parent':
-            assert err.type == tractor.RemoteActorError
-            assert 'StreamOverrun' in err.msgdata['tb_str']
-
-    else:
-        # if this hits the logic blocks from above are not
-        # exhaustive..
-        pytest.fail('PARAMETRIZED CASE GEN PROBLEM YO')
 
 
 @tractor.context
@@ -952,18 +737,18 @@ async def attach_to_sleep_forever():
             finally:
                 # XXX: previously this would trigger local
                 # ``ContextCancelled`` to be received and raised in the
-                # local context overriding any local error due to logic
+                # local context overriding any local error due to
-                # inside ``_invoke()`` which checked for an error set on
+                # logic inside ``_invoke()`` which checked for
-                # ``Context._error`` and raised it in a cancellation
+                # an error set on ``Context._error`` and raised it in
-                # scenario.
+                # under a cancellation scenario.
-                # ------
+
-                # The problem is you can have a remote cancellation that
+                # The problem is you can have a remote cancellation
-                # is part of a local error and we shouldn't raise
+                # that is part of a local error and we shouldn't raise
-                # ``ContextCancelled`` **iff** we **were not** the side
+                # ``ContextCancelled`` **iff** we weren't the side of
-                # of the context to initiate it, i.e.
+                # the context to initiate it, i.e.
                 # ``Context._cancel_called`` should **NOT** have been
                 # set. The special logic to handle this case is now
-                # inside ``Context._maybe_raise_from_remote_msg()`` XD
+                # inside ``Context._may_raise_from_remote_msg()`` XD
                 await peer_ctx.cancel()
 
 
@@ -984,10 +769,9 @@ async def error_before_started(
 
 def test_do_not_swallow_error_before_started_by_remote_contextcancelled():
     '''
-    Verify that an error raised in a remote context which itself opens
+    Verify that an error raised in a remote context which itself opens another
-    another remote context, which it cancels, does not ovverride the
+    remote context, which it cancels, does not ovverride the original error that
-    original error that caused the cancellation of the secondardy
+    caused the cancellation of the secondardy context.
-    context.
 
     '''
     async def main():

tests/test_debugger.py

@@ -151,19 +151,6 @@ def ctlc(
 
     use_ctlc = request.param
 
-    # TODO: we can remove this bc pdbp right?
-    if (
-        sys.version_info <= (3, 10)
-        and use_ctlc
-    ):
-        # on 3.9 it seems the REPL UX
-        # is highly unreliable and frankly annoying
-        # to test for. It does work from manual testing
-        # but i just don't think it's wroth it to try
-        # and get this working especially since we want to
-        # be 3.10+ mega-asap.
-        pytest.skip('Py3.9 and `pdbpp` son no bueno..')
-
     node = request.node
     markers = node.own_markers
     for mark in markers:
@@ -194,13 +181,15 @@ def ctlc(
     ids=lambda item: f'{item[0]} -> {item[1]}',
 )
 def test_root_actor_error(spawn, user_in_out):
-    """Demonstrate crash handler entering pdbpp from basic error in root actor.
+    '''
-    """
+    Demonstrate crash handler entering pdb from basic error in root actor.
+
+    '''
     user_input, expect_err_str = user_in_out
 
     child = spawn('root_actor_error')
 
-    # scan for the pdbpp prompt
+    # scan for the prompt
     expect(child, PROMPT)
 
     before = str(child.before.decode())
@@ -231,7 +220,7 @@ def test_root_actor_bp(spawn, user_in_out):
     user_input, expect_err_str = user_in_out
     child = spawn('root_actor_breakpoint')
 
-    # scan for the pdbpp prompt
+    # scan for the prompt
     child.expect(PROMPT)
 
     assert 'Error' not in str(child.before)
@@ -339,7 +328,7 @@ def test_subactor_error(
     '''
     child = spawn('subactor_error')
 
-    # scan for the pdbpp prompt
+    # scan for the prompt
     child.expect(PROMPT)
 
     before = str(child.before.decode())
@@ -387,7 +376,7 @@ def test_subactor_breakpoint(
 
     child = spawn('subactor_breakpoint')
 
-    # scan for the pdbpp prompt
+    # scan for the prompt
     child.expect(PROMPT)
 
     before = str(child.before.decode())
@@ -448,7 +437,7 @@ def test_multi_subactors(
     '''
     child = spawn(r'multi_subactors')
 
-    # scan for the pdbpp prompt
+    # scan for the prompt
     child.expect(PROMPT)
 
     before = str(child.before.decode())
@@ -688,7 +677,7 @@ def test_multi_subactors_root_errors(
     '''
     child = spawn('multi_subactor_root_errors')
 
-    # scan for the pdbpp prompt
+    # scan for the prompt
     child.expect(PROMPT)
 
     # at most one subactor should attach before the root is cancelled

tests/test_infected_asyncio.py

@@ -15,7 +15,6 @@ import tractor
 from tractor import (
     to_asyncio,
     RemoteActorError,
-    ContextCancelled,
 )
 from tractor.trionics import BroadcastReceiver
 
@@ -225,23 +224,14 @@ def test_context_spawns_aio_task_that_errors(
 
                     await trio.sleep_forever()
 
-        return await ctx.result()
+    with pytest.raises(RemoteActorError) as excinfo:
+        trio.run(main)
 
+    err = excinfo.value
+    assert isinstance(err, RemoteActorError)
     if parent_cancels:
-        # bc the parent made the cancel request,
+        assert err.type == trio.Cancelled
-        # the error is not raised locally but instead
-        # the context is exited silently
-        res = trio.run(main)
-        assert isinstance(res, ContextCancelled)
-        assert 'root' in res.canceller[0]
-
     else:
-        expect = RemoteActorError
-        with pytest.raises(expect) as excinfo:
-            trio.run(main)
-
-        err = excinfo.value
-        assert isinstance(err, expect)
         assert err.type == AssertionError
 
 

tests/test_task_broadcasting.py

@@ -86,7 +86,7 @@ async def open_sequence_streamer(
         ) as (ctx, first):
 
             assert first is None
-            async with ctx.open_stream(allow_overruns=True) as stream:
+            async with ctx.open_stream(backpressure=True) as stream:
                 yield stream
 
         await portal.cancel_actor()
@@ -413,8 +413,8 @@ def test_ensure_slow_consumers_lag_out(
                     seq = brx._state.subs[brx.key]
                     assert seq == len(brx._state.queue) - 1
 
-                # all no_overruns entries in the underlying
+                # all backpressured entries in the underlying
-                # channel should have been copied into the bcaster
+                # channel should have been copied into the caster
                 # queue trailing-window
                 async for i in rx:
                     print(f'bped: {i}')

tractor/__init__.py

@@ -15,20 +15,18 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 """
-tractor: structured concurrent ``trio``-"actors".
+tractor: structured concurrent "actors".
 
 """
 from exceptiongroup import BaseExceptionGroup
 
 from ._clustering import open_actor_cluster
 from ._ipc import Channel
-from ._context import (
-    Context,
-    context,
-)
 from ._streaming import (
+    Context,
     MsgStream,
     stream,
+    context,
 )
 from ._discovery import (
     get_arbiter,

tractor/_context.py

@@ -1,771 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-
-'''
-The fundamental cross process SC abstraction: an inter-actor,
-cancel-scope linked task "context".
-
-A ``Context`` is very similar to the ``trio.Nursery.cancel_scope`` built
-into each ``trio.Nursery`` except it links the lifetimes of memory space
-disjoint, parallel executing tasks in separate actors.
-
-'''
-from __future__ import annotations
-from collections import deque
-from contextlib import asynccontextmanager as acm
-from dataclasses import (
-    dataclass,
-    field,
-)
-from functools import partial
-import inspect
-from pprint import pformat
-from typing import (
-    Any,
-    Callable,
-    AsyncGenerator,
-    TYPE_CHECKING,
-)
-import warnings
-
-import trio
-
-from ._exceptions import (
-    unpack_error,
-    pack_error,
-    ContextCancelled,
-    StreamOverrun,
-)
-from .log import get_logger
-from ._ipc import Channel
-from ._streaming import MsgStream
-from ._state import current_actor
-
-if TYPE_CHECKING:
-    from ._portal import Portal
-
-
-log = get_logger(__name__)
-
-
-@dataclass
-class Context:
-    '''
-    An inter-actor, ``trio``-task communication context.
-
-    NB: This class should never be instatiated directly, it is delivered
-    by either,
-     - runtime machinery to a remotely started task or,
-     - by entering ``Portal.open_context()``.
-
-     and is always constructed using ``mkt_context()``.
-
-    Allows maintaining task or protocol specific state between
-    2 communicating, parallel executing actor tasks. A unique context is
-    allocated on each side of any task RPC-linked msg dialog, for
-    every request to a remote actor from a portal. On the "callee"
-    side a context is always allocated inside ``._runtime._invoke()``.
-
-    A context can be cancelled and (possibly eventually restarted) from
-    either side of the underlying IPC channel, it can also open task
-    oriented message streams,  and acts more or less as an IPC aware
-    inter-actor-task ``trio.CancelScope``.
-
-    '''
-    chan: Channel
-    cid: str
-
-    # these are the "feeder" channels for delivering
-    # message values to the local task from the runtime
-    # msg processing loop.
-    _recv_chan: trio.MemoryReceiveChannel
-    _send_chan: trio.MemorySendChannel
-
-    _remote_func_type: str | None = None
-
-    # only set on the caller side
-    _portal: Portal | None = None    # type: ignore # noqa
-    _result: Any | int = None
-    _remote_error: BaseException | None = None
-
-    # cancellation state
-    _cancel_called: bool = False
-    _cancel_called_remote: tuple | None = None
-    _cancel_msg: str | None = None
-    _scope: trio.CancelScope | None = None
-    _enter_debugger_on_cancel: bool = True
-
-    @property
-    def cancel_called(self) -> bool:
-        '''
-        Records whether cancellation has been requested for this context
-        by either an explicit call to  ``.cancel()`` or an implicit call
-        due to an error caught inside the ``Portal.open_context()``
-        block.
-
-        '''
-        return self._cancel_called
-
-    @property
-    def cancel_called_remote(self) -> tuple[str, str] | None:
-        '''
-        ``Actor.uid`` of the remote actor who's task was cancelled
-        causing this side of the context to also be cancelled.
-
-        '''
-        remote_uid = self._cancel_called_remote
-        if remote_uid:
-            return tuple(remote_uid)
-
-    @property
-    def cancelled_caught(self) -> bool:
-        return self._scope.cancelled_caught
-
-    # init and streaming state
-    _started_called: bool = False
-    _started_received: bool = False
-    _stream_opened: bool = False
-
-    # overrun handling machinery
-    # NOTE: none of this provides "backpressure" to the remote
-    # task, only an ability to not lose messages when the local
-    # task is configured to NOT transmit ``StreamOverrun``s back
-    # to the other side.
-    _overflow_q: deque[dict] = field(
-        default_factory=partial(
-            deque,
-            maxlen=616,
-        )
-    )
-    _scope_nursery: trio.Nursery | None = None
-    _in_overrun: bool = False
-    _allow_overruns: bool = False
-
-    async def send_yield(
-        self,
-        data: Any,
-
-    ) -> None:
-
-        warnings.warn(
-            "`Context.send_yield()` is now deprecated. "
-            "Use ``MessageStream.send()``. ",
-            DeprecationWarning,
-            stacklevel=2,
-        )
-        await self.chan.send({'yield': data, 'cid': self.cid})
-
-    async def send_stop(self) -> None:
-        await self.chan.send({'stop': True, 'cid': self.cid})
-
-    async def _maybe_cancel_and_set_remote_error(
-        self,
-        error_msg: dict[str, Any],
-
-    ) -> None:
-        '''
-        (Maybe) 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.
-
-        '''
-        # If this is an error message from a context opened by
-        # ``Portal.open_context()`` we want to interrupt any ongoing
-        # (child) tasks within that context to be notified of the remote
-        # error relayed here.
-        #
-        # The reason we may want to raise the remote error immediately
-        # is that there is no guarantee the associated local task(s)
-        # will attempt to read from any locally opened stream any time
-        # soon.
-        #
-        # NOTE: this only applies when
-        # ``Portal.open_context()`` has been called since it is assumed
-        # (currently) that other portal APIs (``Portal.run()``,
-        # ``.run_in_actor()``) do their own error checking at the point
-        # of the call and result processing.
-        error = unpack_error(
-            error_msg,
-            self.chan,
-        )
-
-        # XXX: set the remote side's error so that after we cancel
-        # whatever task is the opener of this context it can raise
-        # that error as the reason.
-        self._remote_error = error
-
-        if (
-            isinstance(error, ContextCancelled)
-        ):
-            log.cancel(
-                'Remote task-context sucessfully cancelled for '
-                f'{self.chan.uid}:{self.cid}'
-            )
-
-            if self._cancel_called:
-                # this is an expected cancel request response message
-                # and we don't need to raise it in scope since it will
-                # potentially override a real error
-                return
-        else:
-            log.error(
-                f'Remote context error for {self.chan.uid}:{self.cid}:\n'
-                f'{error_msg["error"]["tb_str"]}'
-            )
-        # TODO: tempted to **not** do this by-reraising in a
-        # nursery and instead cancel a surrounding scope, detect
-        # the cancellation, then lookup the error that was set?
-        # YES! this is way better and simpler!
-        if (
-            self._scope
-        ):
-            # from trio.testing import wait_all_tasks_blocked
-            # await wait_all_tasks_blocked()
-            self._cancel_called_remote = self.chan.uid
-            self._scope.cancel()
-
-            # NOTE: this usage actually works here B)
-            # from ._debug import breakpoint
-            # await breakpoint()
-
-        # XXX: this will break early callee results sending
-        # since when `.result()` is finally called, this
-        # chan will be closed..
-        # if self._recv_chan:
-        #     await self._recv_chan.aclose()
-
-    async def cancel(
-        self,
-        msg: str | None = None,
-        timeout: float = 0.5,
-        # timeout: float = 1000,
-
-    ) -> None:
-        '''
-        Cancel this inter-actor-task context.
-
-        Request that the far side cancel it's current linked context,
-        Timeout quickly in an attempt to sidestep 2-generals...
-
-        '''
-        side = 'caller' if self._portal else 'callee'
-        if msg:
-            assert side == 'callee', 'Only callee side can provide cancel msg'
-
-        log.cancel(f'Cancelling {side} side of context to {self.chan.uid}')
-
-        self._cancel_called = True
-        # await _debug.breakpoint()
-        # breakpoint()
-
-        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(timeout) as cs:
-                # cs.shield = True
-                log.cancel(
-                    f"Cancelling stream {cid} to "
-                    f"{self._portal.channel.uid}")
-
-                # NOTE: we're telling the far end actor to cancel a task
-                # corresponding to *this actor*. The far end local channel
-                # instance is passed to `Actor._cancel_task()` implicitly.
-                await self._portal.run_from_ns(
-                    'self',
-                    '_cancel_task',
-                    cid=cid,
-                )
-                # print("EXITING CANCEL CALL")
-
-            if cs.cancelled_caught:
-                # XXX: there's no way to know if the remote task was indeed
-                # cancelled in the case where the connection is broken or
-                # some other network error occurred.
-                # if not self._portal.channel.connected():
-                if not self.chan.connected():
-                    log.cancel(
-                        "May have failed to cancel remote task "
-                        f"{cid} for {self._portal.channel.uid}")
-                else:
-                    log.cancel(
-                        "Timed out on cancelling remote task "
-                        f"{cid} for {self._portal.channel.uid}")
-
-        # callee side remote task
-        else:
-            self._cancel_msg = msg
-
-            # 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
-            assert self._scope
-            self._scope.cancel()
-
-    @acm
-    async def open_stream(
-
-        self,
-        allow_overruns: bool | None = False,
-        msg_buffer_size: int | None = None,
-
-    ) -> 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.
-
-        # 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!'
-            )
-
-        if not self._portal and not self._started_called:
-            raise RuntimeError(
-                'Context.started()` must be called before opening a stream'
-            )
-
-        # NOTE: in one way streaming this only happens on the
-        # caller side inside `Actor.start_remote_task()` 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.
-        ctx = actor.get_context(
-            self.chan,
-            self.cid,
-            msg_buffer_size=msg_buffer_size,
-            allow_overruns=allow_overruns,
-        )
-        ctx._allow_overruns = allow_overruns
-        assert ctx is self
-
-        # 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 ctx._recv_chan._closed:
-            raise trio.ClosedResourceError(
-                'The underlying channel for this stream was already closed!?')
-
-        async with MsgStream(
-            ctx=self,
-            rx_chan=ctx._recv_chan,
-        ) as stream:
-
-            if self._portal:
-                self._portal._streams.add(stream)
-
-            try:
-                self._stream_opened = True
-
-                # XXX: do we need this?
-                # ensure we aren't cancelled before yielding the stream
-                # await trio.lowlevel.checkpoint()
-                yield stream
-
-                # NOTE: Make the stream "one-shot use".  On exit, signal
-                # ``trio.EndOfChannel``/``StopAsyncIteration`` to the
-                # far end.
-                await stream.aclose()
-
-            finally:
-                if self._portal:
-                    try:
-                        self._portal._streams.remove(stream)
-                    except KeyError:
-                        log.warning(
-                            f'Stream was already destroyed?\n'
-                            f'actor: {self.chan.uid}\n'
-                            f'ctx id: {self.cid}'
-                        )
-
-    def _maybe_raise_remote_err(
-        self,
-        err: Exception,
-    ) -> None:
-        # NOTE: whenever the context's "opener" side (task) **is**
-        # the side which requested the cancellation (likekly via
-        # ``Context.cancel()``), we don't want to re-raise that
-        # cancellation signal locally (would be akin to
-        # a ``trio.Nursery`` nursery raising ``trio.Cancelled``
-        # whenever  ``CancelScope.cancel()`` was called) and instead
-        # silently reap the expected cancellation "error"-msg.
-        # if 'pikerd' in err.msgdata['tb_str']:
-        #     # from . import _debug
-        #     # await _debug.breakpoint()
-        #     breakpoint()
-
-        if (
-            isinstance(err, ContextCancelled)
-            and (
-                self._cancel_called
-                or self.chan._cancel_called
-                or tuple(err.canceller) == current_actor().uid
-            )
-        ):
-            return err
-
-        raise err  # from None
-
-    async def result(self) -> Any | Exception:
-        '''
-        From some (caller) side task, wait for and return the final
-        result from the remote (callee) side's task.
-
-        This provides a mechanism for one task running in some actor to wait
-        on another task at the other side, in some other actor, to terminate.
-
-        If the remote task is still in a streaming state (it is delivering
-        values from inside a ``Context.open_stream():`` block, then those
-        msgs are drained but discarded since it is presumed this side of
-        the context has already finished with its own streaming logic.
-
-        If the remote context (or its containing actor runtime) was
-        canceled, either by a local task calling one of
-        ``Context.cancel()`` or `Portal.cancel_actor()``, we ignore the
-        received ``ContextCancelled`` exception if the context or
-        underlying IPC channel is marked as having been "cancel called".
-        This is similar behavior to using ``trio.Nursery.cancel()``
-        wherein tasks which raise ``trio.Cancel`` are silently reaped;
-        the main different in this API is in the "cancel called" case,
-        instead of just not raising, we also return the exception *as
-        the result* since client code may be interested in the details
-        of the remote cancellation.
-
-        '''
-        assert self._portal, "Context.result() can not be called from callee!"
-        assert self._recv_chan
-
-        # from . import _debug
-        # await _debug.breakpoint()
-
-        re = self._remote_error
-        if re:
-            self._maybe_raise_remote_err(re)
-            return re
-
-        if (
-            self._result == id(self)
-            and not self._remote_error
-            and 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']
-
-                    # NOTE: we don't need to do this right?
-                    # XXX: only close the rx mem chan AFTER
-                    # a final result is retreived.
-                    # if self._recv_chan:
-                    #     await self._recv_chan.aclose()
-
-                    break
-                except KeyError:  # as msgerr:
-
-                    if 'yield' in msg:
-                        # far end task is still streaming to us so discard
-                        log.warning(f'Discarding stream delivered {msg}')
-                        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?")
-
-                    err = unpack_error(
-                        msg,
-                        self._portal.channel
-                    )  # from msgerr
-
-                    err = self._maybe_raise_remote_err(err)
-                    self._remote_err = err
-
-        return self._remote_error or self._result
-
-    async def started(
-        self,
-        value: Any | None = None
-
-    ) -> None:
-        '''
-        Indicate to calling actor's task that this linked context
-        has started and send ``value`` to the other side.
-
-        On the calling side ``value`` is the second item delivered
-        in the tuple returned by ``Portal.open_context()``.
-
-        '''
-        if self._portal:
-            raise RuntimeError(
-                f"Caller side context {self} can not call started!")
-
-        elif self._started_called:
-            raise RuntimeError(
-                f"called 'started' twice on context with {self.chan.uid}")
-
-        await self.chan.send({'started': value, 'cid': self.cid})
-        self._started_called = True
-
-    # TODO: do we need a restart api?
-    # async def restart(self) -> None:
-    #     pass
-
-    async def _drain_overflows(
-        self,
-    ) -> None:
-        '''
-        Private task spawned to push newly received msgs to the local
-        task which getting overrun by the remote side.
-
-        In order to not block the rpc msg loop, but also not discard
-        msgs received in this context, we need to async push msgs in
-        a new task which only runs for as long as the local task is in
-        an overrun state.
-
-        '''
-        self._in_overrun = True
-        try:
-            while self._overflow_q:
-                # NOTE: these msgs should never be errors since we always do
-                # the check prior to checking if we're in an overrun state
-                # inside ``.deliver_msg()``.
-                msg = self._overflow_q.popleft()
-                try:
-                    await self._send_chan.send(msg)
-                except trio.BrokenResourceError:
-                    log.warning(
-                        f"{self._send_chan} consumer is already closed"
-                    )
-                    return
-                except trio.Cancelled:
-                    # we are obviously still in overrun
-                    # but the context is being closed anyway
-                    # so we just warn that there are un received
-                    # msgs still..
-                    self._overflow_q.appendleft(msg)
-                    fmt_msgs = ''
-                    for msg in self._overflow_q:
-                        fmt_msgs += f'{pformat(msg)}\n'
-
-                    log.warning(
-                        f'Context for {self.cid} is being closed while '
-                        'in an overrun state!\n'
-                        'Discarding the following msgs:\n'
-                        f'{fmt_msgs}\n'
-                    )
-                    raise
-
-        finally:
-            # task is now finished with the backlog so mark us as
-            # no longer in backlog.
-            self._in_overrun = False
-
-    async def _deliver_msg(
-        self,
-        msg: dict,
-
-        draining: bool = False,
-
-    ) -> bool:
-
-        cid = self.cid
-        chan = self.chan
-        uid = chan.uid
-        send_chan: trio.MemorySendChannel = self._send_chan
-
-        log.runtime(
-            f"Delivering {msg} from {uid} to caller {cid}"
-        )
-
-        error = msg.get('error')
-        if error:
-            await self._maybe_cancel_and_set_remote_error(msg)
-
-        if (
-            self._in_overrun
-        ):
-            self._overflow_q.append(msg)
-            return False
-
-        try:
-            send_chan.send_nowait(msg)
-            return True
-            # if an error is deteced we should always
-            # expect it to be raised by any context (stream)
-            # consumer task
-
-        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")
-            return False
-
-        # NOTE XXX: by default we do **not** maintain context-stream
-        # backpressure and instead opt to relay stream overrun errors to
-        # the sender; the main motivation is that using bp can block the
-        # msg handling loop which calls into this method!
-        except trio.WouldBlock:
-            # XXX: always push an error even if the local
-            # receiver is in overrun state.
-            # await self._maybe_cancel_and_set_remote_error(msg)
-
-            local_uid = current_actor().uid
-            lines = [
-                f'OVERRUN on actor-task context {cid}@{local_uid}!\n'
-                # TODO: put remote task name here if possible?
-                f'remote sender actor: {uid}',
-                # TODO: put task func name here and maybe an arrow
-                # from sender to overrunner?
-                # f'local task {self.func_name}'
-            ]
-            if not self._stream_opened:
-                lines.insert(
-                    1,
-                    f'\n*** No stream open on `{local_uid[0]}` side! ***\n'
-                )
-
-            text = '\n'.join(lines)
-
-            # XXX: lul, this really can't be backpressure since any
-            # blocking here will block the entire msg loop rpc sched for
-            # a whole channel.. maybe we should rename it?
-            if self._allow_overruns:
-                text += f'\nStarting overflow queuing task on msg: {msg}'
-                log.warning(text)
-                if (
-                    not self._in_overrun
-                ):
-                    self._overflow_q.append(msg)
-                    n = self._scope_nursery
-                    assert not n.child_tasks
-                    try:
-                        n.start_soon(
-                            self._drain_overflows,
-                        )
-                    except RuntimeError:
-                        # if the nursery is already cancelled due to
-                        # this context exiting or in error, we ignore
-                        # the nursery error since we never expected
-                        # anything different.
-                        return False
-            else:
-                try:
-                    raise StreamOverrun(text)
-                except StreamOverrun as err:
-                    err_msg = pack_error(err)
-                    err_msg['cid'] = cid
-                    try:
-                        await chan.send(err_msg)
-                    except trio.BrokenResourceError:
-                        # XXX: local consumer has closed their side
-                        # so cancel the far end streaming task
-                        log.warning(f"{chan} is already closed")
-
-            return False
-
-
-def mk_context(
-    chan: Channel,
-    cid: str,
-    msg_buffer_size: int = 2**6,
-
-    **kwargs,
-
-) -> Context:
-    '''
-    Internal factory to create an inter-actor task ``Context``.
-
-    This is called by internals and should generally never be called
-    by user code.
-
-    '''
-    send_chan: trio.MemorySendChannel
-    recv_chan: trio.MemoryReceiveChannel
-    send_chan, recv_chan = trio.open_memory_channel(msg_buffer_size)
-
-    ctx = Context(
-        chan,
-        cid,
-        _send_chan=send_chan,
-        _recv_chan=recv_chan,
-        **kwargs,
-    )
-    ctx._result: int | Any = id(ctx)
-    return ctx
-
-
-def context(func: Callable) -> Callable:
-    '''
-    Mark an async function as a streaming routine with ``@context``.
-
-    '''
-    # TODO: apply whatever solution ``mypy`` ends up picking for this:
-    # https://github.com/python/mypy/issues/2087#issuecomment-769266912
-    func._tractor_context_function = True  # type: ignore
-
-    sig = inspect.signature(func)
-    params = sig.parameters
-    if 'ctx' not in params:
-        raise TypeError(
-            "The first argument to the context function "
-            f"{func.__name__} must be `ctx: tractor.Context`"
-        )
-    return func

tractor/_debug.py

@@ -54,18 +54,6 @@ from ._exceptions import (
 )
 from ._ipc import Channel
 
-
-# TODO: we can drop this now yah?
-# try:
-#     # wtf: only exported when installed in dev mode?
-#     import pdbp
-# except ImportError:
-#     # pdbpp is installed in regular mode...it monkey patches stuff
-#     import pdb
-#     xpm = getattr(pdb, 'xpm', None)
-#     assert xpm, "pdbpp is not installed?"  # type: ignore
-#     pdbpp = pdb
-
 log = get_logger(__name__)
 
 

tractor/_discovery.py

@@ -41,10 +41,8 @@ async def get_arbiter(
     port: int,
 
 ) -> 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()
 
@@ -136,16 +134,12 @@ async def find_actor(
 @acm
 async def wait_for_actor(
     name: str,
-    arbiter_sockaddr: tuple[str, int] | None = None,
+    arbiter_sockaddr: tuple[str, int] | None = None
-    # registry_addr: tuple[str, int] | None = None,
-
 ) -> AsyncGenerator[Portal, None]:
-    '''
+    """Wait on an actor to register with the arbiter.
-    Wait on an actor to register with the arbiter.
 
     A portal to the first registered actor is returned.
-
+    """
-    '''
     actor = current_actor()
 
     async with get_arbiter(

tractor/_entry.py

@@ -132,7 +132,7 @@ def _trio_main(
         else:
             trio.run(trio_main)
     except KeyboardInterrupt:
-        log.cancel(f"Actor {actor.uid} received KBI")
+        log.warning(f"Actor {actor.uid} received KBI")
 
     finally:
         log.info(f"Actor {actor.uid} terminated")

tractor/_exceptions.py

@@ -18,18 +18,18 @@
 Our classy exception set.
 
 """
-import builtins
-import importlib
 from typing import (
     Any,
+    Optional,
     Type,
 )
+import importlib
+import builtins
 import traceback
 
 import exceptiongroup as eg
 import trio
 
-from ._state import current_actor
 
 _this_mod = importlib.import_module(__name__)
 
@@ -44,7 +44,7 @@ class RemoteActorError(Exception):
     def __init__(
         self,
         message: str,
-        suberror_type: Type[BaseException] | None = None,
+        suberror_type: Optional[Type[BaseException]] = None,
         **msgdata
 
     ) -> None:
@@ -53,36 +53,21 @@ class RemoteActorError(Exception):
         self.type = suberror_type
         self.msgdata = msgdata
 
-    @property
-    def src_actor_uid(self) -> tuple[str, str] | None:
-        return self.msgdata.get('src_actor_uid')
-
 
 class InternalActorError(RemoteActorError):
-    '''
+    """Remote internal ``tractor`` error indicating
-    Remote internal ``tractor`` error indicating
     failure of some primitive or machinery.
-
+    """
-    '''
-
-
-class ContextCancelled(RemoteActorError):
-    '''
-    Inter-actor task context was cancelled by either a call to
-    ``Portal.cancel_actor()`` or ``Context.cancel()``.
-
-    '''
-    @property
-    def canceller(self) -> tuple[str, str] | None:
-        value = self.msgdata.get('canceller')
-        if value:
-            return tuple(value)
 
 
 class TransportClosed(trio.ClosedResourceError):
     "Underlying channel transport was closed prior to use"
 
 
+class ContextCancelled(RemoteActorError):
+    "Inter-actor task context cancelled itself on the callee side."
+
+
 class NoResult(RuntimeError):
     "No final result is expected for this actor"
 
@@ -121,17 +106,13 @@ def pack_error(
     else:
         tb_str = traceback.format_exc()
 
-    error_msg = {
+    return {
-        'tb_str': tb_str,
+        'error': {
-        'type_str': type(exc).__name__,
+            'tb_str': tb_str,
-        'src_actor_uid': current_actor().uid,
+            'type_str': type(exc).__name__,
+        }
     }
 
-    if isinstance(exc, ContextCancelled):
-        error_msg.update(exc.msgdata)
-
-    return {'error': error_msg}
-
 
 def unpack_error(
 
@@ -155,7 +136,7 @@ def unpack_error(
 
     if type_name == 'ContextCancelled':
         err_type = ContextCancelled
-        suberror_type = RemoteActorError
+        suberror_type = trio.Cancelled
 
     else:  # try to lookup a suitable local error type
         for ns in [

tractor/_portal.py

@@ -45,8 +45,10 @@ from ._exceptions import (
     NoResult,
     ContextCancelled,
 )
-from ._context import Context
+from ._streaming import (
-from ._streaming import MsgStream
+    Context,
+    MsgStream,
+)
 
 
 log = get_logger(__name__)
@@ -101,7 +103,7 @@ class Portal:
         # When set to a ``Context`` (when _submit_for_result is called)
         # it is expected that ``result()`` will be awaited at some
         # point.
-        self._expect_result: Context | None = None
+        self._expect_result: Optional[Context] = None
         self._streams: set[MsgStream] = set()
         self.actor = current_actor()
 
@@ -207,10 +209,7 @@ class Portal:
         try:
             # send cancel cmd - might not get response
             # XXX: sure would be nice to make this work with a proper shield
-            with trio.move_on_after(
+            with trio.move_on_after(timeout or self.cancel_timeout) as cs:
-                timeout
-                or self.cancel_timeout
-            ) as cs:
                 cs.shield = True
 
                 await self.run_from_ns('self', 'cancel')
@@ -331,9 +330,7 @@ class Portal:
                     f'{async_gen_func} must be an async generator function!')
 
         fn_mod_path, fn_name = NamespacePath.from_ref(
-            async_gen_func
+            async_gen_func).to_tuple()
-        ).to_tuple()
-
         ctx = await self.actor.start_remote_task(
             self.channel,
             fn_mod_path,
@@ -399,16 +396,13 @@ class Portal:
             raise TypeError(
                 f'{func} must be an async generator function!')
 
-        # TODO: i think from here onward should probably
-        # just be factored into an `@acm` inside a new
-        # a new `_context.py` mod.
         fn_mod_path, fn_name = NamespacePath.from_ref(func).to_tuple()
 
         ctx = await self.actor.start_remote_task(
             self.channel,
             fn_mod_path,
             fn_name,
-            kwargs,
+            kwargs
         )
 
         assert ctx._remote_func_type == 'context'
@@ -432,47 +426,29 @@ class Portal:
                     f' but received a non-error msg:\n{pformat(msg)}'
                 )
 
-        _err: BaseException | None = None
+        _err: Optional[BaseException] = None
-        ctx._portal: Portal = self
+        ctx._portal = self
 
-        uid: tuple = self.channel.uid
+        uid = self.channel.uid
-        cid: str = ctx.cid
+        cid = ctx.cid
-        etype: Type[BaseException] | None = None
+        etype: Optional[Type[BaseException]] = None
 
-        # deliver context instance and .started() msg value in enter
+        # deliver context instance and .started() msg value in open tuple.
-        # tuple.
         try:
-            async with trio.open_nursery() as nurse:
+            async with trio.open_nursery() as scope_nursery:
-                ctx._scope_nursery = nurse
+                ctx._scope_nursery = scope_nursery
-                ctx._scope = nurse.cancel_scope
+
+                # do we need this?
+                # await trio.lowlevel.checkpoint()
 
                 yield ctx, first
 
-                # when in allow_ovveruns mode there may be lingering
-                # overflow sender tasks remaining?
-                if nurse.child_tasks:
-                    # ensure we are in overrun state with
-                    # ``._allow_overruns=True`` bc otherwise
-                    # there should be no tasks in this nursery!
-                    if (
-                        not ctx._allow_overruns
-                        or len(nurse.child_tasks) > 1
-                    ):
-                        raise RuntimeError(
-                            'Context has sub-tasks but is '
-                            'not in `allow_overruns=True` Mode!?'
-                        )
-                    ctx._scope.cancel()
-
         except ContextCancelled as err:
             _err = err
-
-            # swallow and mask cross-actor task context cancels that
-            # were initiated by *this* side's task.
             if not ctx._cancel_called:
-                # XXX: this should NEVER happen!
+                # context was cancelled at the far end but was
-                # from ._debug import breakpoint
+                # not part of this end requesting that cancel
-                # await breakpoint()
+                # so raise for the local task to respond and handle.
                 raise
 
             # if the context was cancelled by client code
@@ -492,17 +468,17 @@ class Portal:
 
         ) as err:
             etype = type(err)
+            # the context cancels itself on any cancel
+            # causing error.
 
-            # cancel ourselves on any error.
+            if ctx.chan.connected():
-            log.cancel(
+                log.cancel(
-                'Context cancelled for task, sending cancel request..\n'
+                    'Context cancelled for task, sending cancel request..\n'
-                f'task:{cid}\n'
+                    f'task:{cid}\n'
-                f'actor:{uid}'
+                    f'actor:{uid}'
-            )
+                )
-            try:
-
                 await ctx.cancel()
-            except trio.BrokenResourceError:
+            else:
                 log.warning(
                     'IPC connection for context is broken?\n'
                     f'task:{cid}\n'
@@ -511,7 +487,12 @@ class Portal:
 
             raise
 
-        else:
+        finally:
+            # in the case where a runtime nursery (due to internal bug)
+            # or a remote actor transmits an error we want to be
+            # sure we get the error the underlying feeder mem chan.
+            # if it's not raised here it *should* be raised from the
+            # msg loop nursery right?
             if ctx.chan.connected():
                 log.info(
                     'Waiting on final context-task result for\n'
@@ -524,7 +505,6 @@ class Portal:
                     f'value from callee `{result}`'
                 )
 
-        finally:
             # though it should be impossible for any tasks
             # operating *in* this scope to have survived
             # we tear down the runtime feeder chan last

tractor/_root.py

@@ -254,9 +254,7 @@ async def open_root_actor(
                 #         tempn.start_soon(an.exited.wait)
 
                 logger.cancel("Shutting down root actor")
-                await actor.cancel(
+                await actor.cancel()
-                    requesting_uid=actor.uid,
-                )
     finally:
         _state._current_actor = None
 

tractor/_runtime.py

@@ -28,11 +28,9 @@ import inspect
 import signal
 import sys
 from typing import (
-    Any,
+    Any, Optional,
+    Union, TYPE_CHECKING,
     Callable,
-    Optional,
-    Union,
-    TYPE_CHECKING,
 )
 import uuid
 from types import ModuleType
@@ -46,10 +44,7 @@ import trio  # type: ignore
 from trio_typing import TaskStatus
 
 from ._ipc import Channel
-from ._context import (
+from ._streaming import Context
-    mk_context,
-    Context,
-)
 from .log import get_logger
 from ._exceptions import (
     pack_error,
@@ -58,6 +53,7 @@ from ._exceptions import (
     is_multi_cancelled,
     ContextCancelled,
     TransportClosed,
+    StreamOverrun,
 )
 from . import _debug
 from ._discovery import get_arbiter
@@ -83,7 +79,7 @@ async def _invoke(
 
     is_rpc: bool = True,
     task_status: TaskStatus[
-        Union[Context, BaseException]
+        Union[trio.CancelScope, BaseException]
     ] = trio.TASK_STATUS_IGNORED,
 ):
     '''
@@ -103,14 +99,7 @@ async def _invoke(
     # activated cancel scope ref
     cs: Optional[trio.CancelScope] = None
 
-    ctx = actor.get_context(
+    ctx = actor.get_context(chan, cid)
-        chan,
-        cid,
-        # We shouldn't ever need to pass this through right?
-        # it's up to the soon-to-be called rpc task to
-        # open the stream with this option.
-        # allow_overruns=True,
-    )
     context: bool = False
 
     if getattr(func, '_tractor_stream_function', False):
@@ -149,10 +138,7 @@ async def _invoke(
         ):
             raise TypeError(f'{func} must be an async function!')
 
-        try:
+        coro = func(**kwargs)
-            coro = func(**kwargs)
-        except TypeError:
-            raise
 
         if inspect.isasyncgen(coro):
             await chan.send({'functype': 'asyncgen', 'cid': cid})
@@ -164,8 +150,7 @@ async def _invoke(
             # of the async gen in order to be sure the cancel
             # is propagated!
             with cancel_scope as cs:
-                ctx._scope = cs
+                task_status.started(cs)
-                task_status.started(ctx)
                 async with aclosing(coro) as agen:
                     async for item in agen:
                         # TODO: can we send values back in here?
@@ -191,8 +176,7 @@ async def _invoke(
             # manualy construct the response dict-packet-responses as
             # above
             with cancel_scope as cs:
-                ctx._scope = cs
+                task_status.started(cs)
-                task_status.started(ctx)
                 await coro
 
             if not cs.cancelled_caught:
@@ -205,26 +189,19 @@ async def _invoke(
             await chan.send({'functype': 'context', 'cid': cid})
 
             try:
-                async with trio.open_nursery() as nurse:
+                async with trio.open_nursery() as scope_nursery:
-                    ctx._scope_nursery = nurse
+                    ctx._scope_nursery = scope_nursery
-                    ctx._scope = nurse.cancel_scope
+                    cs = scope_nursery.cancel_scope
-                    task_status.started(ctx)
+                    task_status.started(cs)
                     res = await coro
                     await chan.send({'return': res, 'cid': cid})
 
-            # XXX: do we ever trigger this block any more?
+            except BaseExceptionGroup:
-            except (
-                BaseExceptionGroup,
-                trio.Cancelled,
-            ):
                 # if a context error was set then likely
                 # thei multierror was raised due to that
-                if ctx._remote_error is not None:
+                if ctx._error is not None:
-                    raise ctx._remote_error
+                    raise ctx._error from None
 
-                # maybe TODO: pack in ``trio.Cancelled.__traceback__`` here
-                # so they can be unwrapped and displayed on the caller
-                # side?
                 raise
 
             finally:
@@ -236,67 +213,38 @@ async def _invoke(
                 # associated child isn't in debug any more
                 await _debug.maybe_wait_for_debugger()
                 ctx = actor._contexts.pop((chan.uid, cid))
+
                 if ctx:
                     log.runtime(
                         f'Context entrypoint {func} was terminated:\n{ctx}'
                     )
 
-            if ctx.cancelled_caught:
+            assert cs
+            if cs.cancelled_caught:
 
-                # first check for and raise any remote error
+                # TODO: pack in ``trio.Cancelled.__traceback__`` here
-                # before raising any context cancelled case
+                # so they can be unwrapped and displayed on the caller
-                # so that real remote errors don't get masked as
+                # side!
-                # ``ContextCancelled``s.
-                re = ctx._remote_error
-                if re:
-                    ctx._maybe_raise_remote_err(re)
 
                 fname = func.__name__
-                cs: trio.CancelScope = ctx._scope
+                if ctx._cancel_called:
-                if cs.cancel_called:
+                    msg = f'`{fname}()` cancelled itself'
-                    canceller = ctx._cancel_called_remote
-                    # await _debug.breakpoint()
 
-                    # NOTE / TODO: if we end up having
+                elif cs.cancel_called:
-                    # ``Actor._cancel_task()`` call
+                    msg = (
-                    # ``Context.cancel()`` directly, we're going to
+                        f'`{fname}()` was remotely cancelled by its caller '
-                    # need to change this logic branch since it will
+                        f'{ctx.chan.uid}'
-                    # always enter..
-                    if ctx._cancel_called:
-                        msg = f'`{fname}()`@{actor.uid} cancelled itself'
-
-                    else:
-                        msg = (
-                            f'`{fname}()`@{actor.uid} '
-                            'was remotely cancelled by '
-                        )
-
-                    # if the channel which spawned the ctx is the
-                    # one that cancelled it then we report that, vs.
-                    # it being some other random actor that for ex.
-                    # some actor who calls `Portal.cancel_actor()`
-                    # and by side-effect cancels this ctx.
-                    if canceller == ctx.chan.uid:
-                        msg += f'its caller {canceller}'
-                    else:
-                        msg += f'remote actor {canceller}'
-
-                    # TODO: does this ever get set any more or can
-                    # we remove it?
-                    if ctx._cancel_msg:
-                        msg += f' with msg:\n{ctx._cancel_msg}'
-
-                    # task-contex was either cancelled by request using
-                    # ``Portal.cancel_actor()`` or ``Context.cancel()``
-                    # on the far end, or it was cancelled by the local
-                    # (callee) task, so relay this cancel signal to the
-                    # other side.
-                    raise ContextCancelled(
-                        msg,
-                        suberror_type=trio.Cancelled,
-                        canceller=canceller,
                     )
 
+                if ctx._cancel_msg:
+                    msg += f' with msg:\n{ctx._cancel_msg}'
+
+                # task-contex was cancelled so relay to the cancel to caller
+                raise ContextCancelled(
+                    msg,
+                    suberror_type=trio.Cancelled,
+                )
+
         else:
             # regular async function
             try:
@@ -311,17 +259,12 @@ async def _invoke(
                     )
 
             with cancel_scope as cs:
-                ctx._scope = cs
+                task_status.started(cs)
-                task_status.started(ctx)
                 result = await coro
-                fname = func.__name__
+                log.cancel(f'result: {result}')
-                log.runtime(f'{fname}() result: {result}')
                 if not failed_resp:
                     # only send result if we know IPC isn't down
-                    await chan.send(
+                    await chan.send({'return': result, 'cid': cid})
-                        {'return': result,
-                         'cid': cid}
-                    )
 
     except (
         Exception,
@@ -364,7 +307,6 @@ async def _invoke(
         # always ship errors back to caller
         err_msg = pack_error(err, tb=tb)
         err_msg['cid'] = cid
-
         try:
             await chan.send(err_msg)
 
@@ -381,21 +323,14 @@ async def _invoke(
                 f"Failed to ship error to caller @ {chan.uid} !?"
             )
 
-        # error is probably from above coro running code *not from the
+        if cs is None:
-        # underlyingn rpc invocation* since a scope was never allocated
+            # error is from above code not from rpc invocation
-        # around actual coroutine await.
-        if ctx._scope is None:
-            # we don't ever raise directly here to allow the
-            # msg-loop-scheduler to continue running for this
-            # channel.
             task_status.started(err)
 
     finally:
         # RPC task bookeeping
         try:
-            ctx, func, is_complete = actor._rpc_tasks.pop(
+            scope, func, is_complete = actor._rpc_tasks.pop((chan, cid))
-                (chan, cid)
-            )
             is_complete.set()
 
         except KeyError:
@@ -404,9 +339,6 @@ async def _invoke(
                 # cancel scope will not have been inserted yet
                 log.warning(
                     f"Task {func} likely errored or cancelled before start")
-            else:
-                log.cancel(f'{func.__name__}({kwargs}) failed?')
-
         finally:
             if not actor._rpc_tasks:
                 log.runtime("All RPC tasks have completed")
@@ -505,7 +437,6 @@ class Actor:
         self.uid = (name, uid or str(uuid.uuid4()))
 
         self._cancel_complete = trio.Event()
-        self._cancel_called_remote: tuple[str, tuple] | None = None
         self._cancel_called: bool = False
 
         # retreive and store parent `__main__` data which
@@ -544,7 +475,7 @@ class Actor:
         # (chan, cid) -> (cancel_scope, func)
         self._rpc_tasks: dict[
             tuple[Channel, str],
-            tuple[Context, Callable, trio.Event]
+            tuple[trio.CancelScope, Callable, trio.Event]
         ] = {}
 
         # map {actor uids -> Context}
@@ -719,8 +650,8 @@ class Actor:
             if (
                 local_nursery
             ):
-                if chan._cancel_called:
+
-                    log.cancel(f"Waiting on cancel request to peer {chan.uid}")
+                log.cancel(f"Waiting on cancel request to peer {chan.uid}")
                 # XXX: this is a soft wait on the channel (and its
                 # underlying transport protocol) to close from the
                 # remote peer side since we presume that any channel
@@ -853,15 +784,75 @@ class Actor:
                 f'\n{msg}')
             return
 
-        return await ctx._deliver_msg(msg)
+        send_chan = ctx._send_chan
+
+        log.runtime(f"Delivering {msg} from {chan.uid} to caller {cid}")
+
+        # XXX: we do **not** maintain backpressure and instead
+        # opt to relay stream overrun errors to the sender.
+        try:
+            send_chan.send_nowait(msg)
+            # if an error is deteced we should always
+            # expect it to be raised by any context (stream)
+            # consumer task
+            await ctx._maybe_raise_from_remote_msg(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")
+            return
+
+        except trio.WouldBlock:
+            # XXX: always push an error even if the local
+            # receiver is in overrun state.
+            await ctx._maybe_raise_from_remote_msg(msg)
+
+            uid = chan.uid
+            lines = [
+                'Task context stream was overrun',
+                f'local task: {cid} @ {self.uid}',
+                f'remote sender: {uid}',
+            ]
+            if not ctx._stream_opened:
+                lines.insert(
+                    1,
+                    f'\n*** No stream open on `{self.uid[0]}` side! ***\n'
+                )
+            text = '\n'.join(lines)
+
+            if ctx._backpressure:
+                log.warning(text)
+                try:
+                    await send_chan.send(msg)
+                except trio.BrokenResourceError:
+                    # XXX: local consumer has closed their side
+                    # so cancel the far end streaming task
+                    log.warning(f"{chan} is already closed")
+            else:
+                try:
+                    raise StreamOverrun(text) from None
+                except StreamOverrun as err:
+                    err_msg = pack_error(err)
+                    err_msg['cid'] = cid
+                    try:
+                        await chan.send(err_msg)
+                    except trio.BrokenResourceError:
+                        # XXX: local consumer has closed their side
+                        # so cancel the far end streaming task
+                        log.warning(f"{chan} is already closed")
 
     def get_context(
         self,
         chan: Channel,
         cid: str,
-
+        msg_buffer_size: Optional[int] = None,
-        msg_buffer_size: int | None = None,
-        allow_overruns: bool = False,
 
     ) -> Context:
         '''
@@ -877,7 +868,6 @@ class Actor:
         assert actor_uid
         try:
             ctx = self._contexts[(actor_uid, cid)]
-            ctx._allow_overruns = allow_overruns
 
             # adjust buffer size if specified
             state = ctx._send_chan._state  # type: ignore
@@ -885,11 +875,15 @@ class Actor:
                 state.max_buffer_size = msg_buffer_size
 
         except KeyError:
-            ctx = mk_context(
+            send_chan: trio.MemorySendChannel
+            recv_chan: trio.MemoryReceiveChannel
+            send_chan, recv_chan = trio.open_memory_channel(
+                msg_buffer_size or self.msg_buffer_size)
+            ctx = Context(
                 chan,
                 cid,
-                msg_buffer_size=msg_buffer_size or self.msg_buffer_size,
+                _send_chan=send_chan,
-                _allow_overruns=allow_overruns,
+                _recv_chan=recv_chan,
             )
             self._contexts[(actor_uid, cid)] = ctx
 
@@ -901,8 +895,7 @@ class Actor:
         ns: str,
         func: str,
         kwargs: dict,
-        msg_buffer_size: int | None = None,
+        msg_buffer_size: Optional[int] = None,
-        allow_overruns: bool = False,
 
     ) -> Context:
         '''
@@ -916,16 +909,9 @@ class Actor:
         '''
         cid = str(uuid.uuid4())
         assert chan.uid
-        ctx = self.get_context(
+        ctx = self.get_context(chan, cid, msg_buffer_size=msg_buffer_size)
-            chan,
-            cid,
-            msg_buffer_size=msg_buffer_size,
-            allow_overruns=allow_overruns,
-        )
         log.runtime(f"Sending cmd to {chan.uid}: {ns}.{func}({kwargs})")
-        await chan.send(
+        await chan.send({'cmd': (ns, func, kwargs, self.uid, cid)})
-            {'cmd': (ns, func, kwargs, self.uid, cid)}
-        )
 
         # Wait on first response msg and validate; this should be
         # immediate.
@@ -935,11 +921,7 @@ class Actor:
         if 'error' in first_msg:
             raise unpack_error(first_msg, chan)
 
-        elif functype not in (
+        elif functype not in ('asyncfunc', 'asyncgen', 'context'):
-            'asyncfunc',
-            'asyncgen',
-            'context',
-        ):
             raise ValueError(f"{first_msg} is an invalid response packet?")
 
         ctx._remote_func_type = functype
@@ -998,7 +980,7 @@ class Actor:
             log.warning(
                 f"Failed to connect to parent @ {parent_addr},"
                 " closing server")
-            await self.cancel(requesting_uid=self.uid)
+            await self.cancel()
             raise
 
     async def _serve_forever(
@@ -1051,11 +1033,7 @@ class Actor:
         assert self._service_n
         self._service_n.start_soon(self.cancel)
 
-    async def cancel(
+    async def cancel(self) -> bool:
-        self,
-        requesting_uid: tuple[str, str],
-
-    ) -> bool:
         '''
         Cancel this actor's runtime.
 
@@ -1069,7 +1047,6 @@ class Actor:
 
         '''
         log.cancel(f"{self.uid} is trying to cancel")
-        self._cancel_called_remote: tuple = requesting_uid
         self._cancel_called = True
 
         # cancel all ongoing rpc tasks
@@ -1083,7 +1060,7 @@ class Actor:
                 dbcs.cancel()
 
             # kill all ongoing tasks
-            await self.cancel_rpc_tasks(requesting_uid=requesting_uid)
+            await self.cancel_rpc_tasks()
 
             # stop channel server
             self.cancel_server()
@@ -1109,13 +1086,7 @@ class Actor:
     #         for n in root.child_nurseries:
     #             n.cancel_scope.cancel()
 
-    async def _cancel_task(
+    async def _cancel_task(self, cid, chan):
-        self,
-        cid: str,
-        chan: Channel,
-
-        requesting_uid: tuple[str, str] | None = None,
-    ) -> bool:
         '''
         Cancel a local task by call-id / channel.
 
@@ -1130,51 +1101,35 @@ class Actor:
         try:
             # this ctx based lookup ensures the requested task to
             # be cancelled was indeed spawned by a request from this channel
-            ctx, func, is_complete = self._rpc_tasks[(chan, cid)]
+            scope, func, is_complete = self._rpc_tasks[(chan, cid)]
-            scope = ctx._scope
         except KeyError:
             log.cancel(f"{cid} has already completed/terminated?")
-            return True
+            return
 
         log.cancel(
             f"Cancelling task:\ncid: {cid}\nfunc: {func}\n"
             f"peer: {chan.uid}\n")
 
-        if (
-            ctx._cancel_called_remote is None
-            and requesting_uid
-        ):
-            ctx._cancel_called_remote: tuple = requesting_uid
-
         # don't allow cancelling this function mid-execution
         # (is this necessary?)
         if func is self._cancel_task:
-            return True
+            return
 
-        # TODO: shouldn't we eventually be calling ``Context.cancel()``
-        # directly here instead (since that method can handle both
-        # side's calls into it?
         scope.cancel()
 
         # wait for _invoke to mark the task complete
         log.runtime(
-            'Waiting on task to cancel:\n'
+            f"Waiting on task to cancel:\ncid: {cid}\nfunc: {func}\n"
-            f'cid: {cid}\nfunc: {func}\n'
+            f"peer: {chan.uid}\n")
-            f'peer: {chan.uid}\n'
-        )
         await is_complete.wait()
 
         log.runtime(
             f"Sucessfully cancelled task:\ncid: {cid}\nfunc: {func}\n"
             f"peer: {chan.uid}\n")
 
-        return True
-
     async def cancel_rpc_tasks(
         self,
-        only_chan: Channel | None = None,
+        only_chan: Optional[Channel] = None,
-        requesting_uid: tuple[str, str] | None = None,
-
     ) -> None:
         '''
         Cancel all existing RPC responder tasks using the cancel scope
@@ -1186,7 +1141,7 @@ class Actor:
             log.cancel(f"Cancelling all {len(tasks)} rpc tasks:\n{tasks} ")
             for (
                 (chan, cid),
-                (ctx, func, is_complete),
+                (scope, func, is_complete),
             ) in tasks.copy().items():
                 if only_chan is not None:
                     if only_chan != chan:
@@ -1194,11 +1149,7 @@ class Actor:
 
                 # TODO: this should really done in a nursery batch
                 if func != self._cancel_task:
-                    await self._cancel_task(
+                    await self._cancel_task(cid, chan)
-                        cid,
-                        chan,
-                        requesting_uid=requesting_uid,
-                    )
 
             log.cancel(
                 f"Waiting for remaining rpc tasks to complete {tasks}")
@@ -1284,8 +1235,8 @@ async def async_main(
     Actor runtime entrypoint; start the IPC channel server, maybe connect
     back to the parent, and startup all core machinery tasks.
 
-    A "root" (or "top-level") nursery for this actor is opened here and
+    A "root-most" (or "top-level") nursery for this actor is opened here
-    when cancelled/terminated effectively closes the actor's "runtime".
+    and when cancelled effectively cancels the actor.
 
     '''
     # attempt to retreive ``trio``'s sigint handler and stash it
@@ -1379,15 +1330,13 @@ async def async_main(
                         )
                     )
                 log.runtime("Waiting on service nursery to complete")
-            log.runtime(
+            log.runtime("Service nursery complete")
-                "Service nursery complete\n"
+            log.runtime("Waiting on root nursery to complete")
-                "Waiting on root nursery to complete"
-            )
 
         # Blocks here as expected until the root nursery is
         # killed (i.e. this actor is cancelled or signalled by the parent)
     except Exception as err:
-        log.runtime("Closing all actor lifetime contexts")
+        log.info("Closing all actor lifetime contexts")
         actor.lifetime_stack.close()
 
         if not registered_with_arbiter:
@@ -1408,14 +1357,7 @@ async def async_main(
             await try_ship_error_to_parent(actor._parent_chan, err)
 
         # always!
-        match err:
+        log.exception("Actor errored:")
-            case ContextCancelled():
-                log.cancel(
-                    f'Actor: {actor.uid} was task-context-cancelled with,\n'
-                    f'str(err)'
-                )
-            case _:
-                log.exception("Actor errored:")
         raise
 
     finally:
@@ -1482,16 +1424,15 @@ async def process_messages(
 
 ) -> bool:
     '''
-    This is the per-channel, low level RPC task scheduler loop.
+    Process messages for the IPC transport channel async-RPC style.
 
-    Receive multiplexed RPC request messages from some remote process,
+    Receive multiplexed RPC requests, spawn handler tasks and deliver
-    spawn handler tasks depending on request type and deliver responses
+    responses over or boxed errors back to the "caller" task.
-    or boxed errors back to the remote caller (task).
 
     '''
     # TODO: once https://github.com/python-trio/trio/issues/467 gets
     # worked out we'll likely want to use that!
-    msg: dict | None = None
+    msg = None
     nursery_cancelled_before_task: bool = False
 
     log.runtime(f"Entering msg loop for {chan} from {chan.uid}")
@@ -1513,10 +1454,7 @@ async def process_messages(
 
                     for (channel, cid) in actor._rpc_tasks.copy():
                         if channel is chan:
-                            await actor._cancel_task(
+                            await actor._cancel_task(cid, channel)
-                                cid,
-                                channel,
-                            )
 
                     log.runtime(
                             f"Msg loop signalled to terminate for"
@@ -1530,14 +1468,12 @@ async def process_messages(
                 cid = msg.get('cid')
                 if cid:
                     # deliver response to local caller/waiter
-                    # via its per-remote-context memory channel.
                     await actor._push_result(chan, cid, msg)
 
                     log.runtime(
                         f"Waiting on next msg for {chan} from {chan.uid}")
                     continue
 
-                # TODO: implement with ``match:`` syntax?
                 # process command request
                 try:
                     ns, funcname, kwargs, actorid, cid = msg['cmd']
@@ -1557,12 +1493,13 @@ async def process_messages(
                     f"{ns}.{funcname}({kwargs})")
 
                 if ns == 'self':
-                    if funcname == 'cancel':
+                    func = getattr(actor, funcname)
-                        func = actor.cancel
-                        kwargs['requesting_uid'] = chan.uid
 
-                        # don't start entire actor runtime cancellation
+                    if funcname == 'cancel':
-                        # if this actor is currently in debug mode!
+
+                        # don't start entire actor runtime
+                        # cancellation if this actor is in debug
+                        # mode
                         pdb_complete = _debug.Lock.local_pdb_complete
                         if pdb_complete:
                             await pdb_complete.wait()
@@ -1574,56 +1511,43 @@ async def process_messages(
                             # msg loop and break out into
                             # ``async_main()``
                             log.cancel(
-                                "Actor runtime for was remotely cancelled "
+                                f"Actor {actor.uid} was remotely cancelled "
                                 f"by {chan.uid}"
                             )
                             await _invoke(
-                                actor,
+                                actor, cid, chan, func, kwargs, is_rpc=False
-                                cid,
-                                chan,
-                                func,
-                                kwargs,
-                                is_rpc=False,
                             )
 
-                        log.cancel(
-                            f'Cancelling msg loop for {chan.uid}'
-                        )
                         loop_cs.cancel()
                         break
 
                     if funcname == '_cancel_task':
-                        func = actor._cancel_task
 
                         # we immediately start the runtime machinery
                         # shutdown
-                        # with trio.CancelScope(shield=True):
+                        with trio.CancelScope(shield=True):
-                        kwargs['chan'] = chan
+                            # actor.cancel() was called so kill this
-                        target_cid = kwargs['cid']
+                            # msg loop and break out into
-                        kwargs['requesting_uid'] = chan.uid
+                            # ``async_main()``
-                        log.cancel(
+                            kwargs['chan'] = chan
-                            f'Remote request to cancel task\n'
+                            log.cancel(
-                            f'remote actor: {chan.uid}\n'
+                                f'Remote request to cancel task\n'
-                            f'task: {target_cid}'
+                                f'remote actor: {chan.uid}\n'
-                        )
+                                f'task: {cid}'
-                        try:
-                            await _invoke(
-                                actor,
-                                cid,
-                                chan,
-                                func,
-                                kwargs,
-                                is_rpc=False,
                             )
-                        except BaseException:
+                            try:
-                            log.exception("failed to cancel task?")
+                                await _invoke(
-
+                                    actor,
-                        continue
+                                    cid,
-                    else:
+                                    chan,
-                        # normally registry methods, eg.
+                                    func,
-                        # ``.register_actor()`` etc.
+                                    kwargs,
-                        func = getattr(actor, funcname)
+                                    is_rpc=False,
+                                )
+                            except BaseException:
+                                log.exception("failed to cancel task?")
 
+                            continue
                 else:
                     # complain to client about restricted modules
                     try:
@@ -1638,49 +1562,34 @@ async def process_messages(
                 log.runtime(f"Spawning task for {func}")
                 assert actor._service_n
                 try:
-                    ctx: Context = await actor._service_n.start(
+                    cs = await actor._service_n.start(
-                        partial(
+                        partial(_invoke, actor, cid, chan, func, kwargs),
-                            _invoke,
-                            actor,
-                            cid,
-                            chan,
-                            func,
-                            kwargs,
-                        ),
                         name=funcname,
                     )
-
                 except (
                     RuntimeError,
                     BaseExceptionGroup,
                 ):
                     # avoid reporting a benign race condition
                     # during actor runtime teardown.
-                    nursery_cancelled_before_task: bool = True
+                    nursery_cancelled_before_task = True
                     break
 
-                # in the lone case where a ``Context`` is not
+                # never allow cancelling cancel requests (results in
-                # delivered, it's likely going to be a locally
+                # deadlock and other weird behaviour)
-                # scoped exception from ``_invoke()`` itself.
+                # if func != actor.cancel:
-                if isinstance(ctx, Exception):
+                if isinstance(cs, Exception):
                     log.warning(
                         f"Task for RPC func {func} failed with"
-                        f"{ctx}"
+                        f"{cs}")
-                    )
-                    continue
-
                 else:
                     # mark that we have ongoing rpc tasks
                     actor._ongoing_rpc_tasks = trio.Event()
                     log.runtime(f"RPC func is {func}")
-
                     # store cancel scope such that the rpc task can be
                     # cancelled gracefully if requested
                     actor._rpc_tasks[(chan, cid)] = (
-                        ctx,
+                        cs, func, trio.Event())
-                        func,
-                        trio.Event(),
-                    )
 
                 log.runtime(
                     f"Waiting on next msg for {chan} from {chan.uid}")
@@ -1721,15 +1630,7 @@ async def process_messages(
         else:
             # ship any "internal" exception (i.e. one from internal
             # machinery not from an rpc task) to parent
-            match err:
+            log.exception("Actor errored:")
-                case ContextCancelled():
-                    log.cancel(
-                        f'Actor: {actor.uid} was context-cancelled with,\n'
-                        f'str(err)'
-                    )
-                case _:
-                    log.exception("Actor errored:")
-
             if actor._parent_chan:
                 await try_ship_error_to_parent(actor._parent_chan, err)
 
@@ -1741,8 +1642,7 @@ async def process_messages(
         # msg debugging for when he machinery is brokey
         log.runtime(
             f"Exiting msg loop for {chan} from {chan.uid} "
-            f"with last msg:\n{msg}"
+            f"with last msg:\n{msg}")
-        )
 
     # transport **was not** disconnected
     return False

tractor/_spawn.py

@@ -23,13 +23,12 @@ import sys
 import platform
 from typing import (
     Any,
+    Awaitable,
     Literal,
-    Optional,
     Callable,
     TypeVar,
     TYPE_CHECKING,
 )
-from collections.abc import Awaitable
 
 from exceptiongroup import BaseExceptionGroup
 import trio
@@ -60,7 +59,7 @@ if TYPE_CHECKING:
 log = get_logger('tractor')
 
 # placeholder for an mp start context if so using that backend
-_ctx: Optional[mp.context.BaseContext] = None
+_ctx: mp.context.BaseContext | None = None
 SpawnMethodKey = Literal[
     'trio',  # supported on all platforms
     'mp_spawn',
@@ -86,7 +85,7 @@ else:
 def try_set_start_method(
     key: SpawnMethodKey
 
-) -> Optional[mp.context.BaseContext]:
+) -> mp.context.BaseContext | None:
     '''
     Attempt to set the method for process starting, aka the "actor
     spawning backend".
@@ -200,16 +199,37 @@ async def cancel_on_completion(
 async def do_hard_kill(
     proc: trio.Process,
     terminate_after: int = 3,
+
 ) -> 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.
+    log.debug(f"Terminating {proc}")
     with trio.move_on_after(terminate_after) as cs:
 
-        # NOTE: This ``__aexit__()`` shields internally.
+        # NOTE: code below was copied verbatim from the now deprecated
-        async with proc:  # calls ``trio.Process.aclose()``
+        # (in 0.20.0) ``trio._subrocess.Process.aclose()``, orig doc
-            log.debug(f"Terminating {proc}")
+        # string:
+        #
+        # Close any pipes we have to the process (both input and output)
+        # and wait for it to exit. If cancelled, kills the process and
+        # waits for it to finish exiting before propagating the
+        # cancellation.
+        with trio.CancelScope(shield=True):
+            if proc.stdin is not None:
+                await proc.stdin.aclose()
+            if proc.stdout is not None:
+                await proc.stdout.aclose()
+            if proc.stderr is not None:
+                await proc.stderr.aclose()
+        try:
+            await proc.wait()
+        finally:
+            if proc.returncode is None:
+                proc.kill()
+                with trio.CancelScope(shield=True):
+                    await proc.wait()
 
     if cs.cancelled_caught:
         # XXX: should pretty much never get here unless we have
@@ -355,12 +375,11 @@ async def trio_proc(
         spawn_cmd.append("--asyncio")
 
     cancelled_during_spawn: bool = False
-    proc: Optional[trio.Process] = None
+    proc: trio.Process | None = None
     try:
         try:
             # TODO: needs ``trio_typing`` patch?
-            proc = await trio.lowlevel.open_process(    # type: ignore
+            proc = await trio.lowlevel.open_process(spawn_cmd)
-                spawn_cmd)
 
             log.runtime(f"Started {proc}")
 
@@ -438,14 +457,14 @@ async def trio_proc(
 
             # cancel result waiter that may have been spawned in
             # tandem if not done already
-            log.cancel(
+            log.warning(
                 "Cancelling existing result waiter task for "
                 f"{subactor.uid}")
             nursery.cancel_scope.cancel()
 
     finally:
-        # The "hard" reap since no actor zombies are allowed!
+        # XXX NOTE XXX: The "hard" reap since no actor zombies are
-        # XXX: do this **after** cancellation/tearfown to avoid
+        # allowed! Do this **after** cancellation/teardown to avoid
         # killing the process too early.
         if proc:
             log.cancel(f'Hard reap sequence starting for {subactor.uid}')

tractor/_state.py

@@ -23,6 +23,11 @@ from typing import (
     Any,
 )
 
+import trio
+
+from ._exceptions import NoRuntime
+
+
 _current_actor: Optional['Actor'] = None  # type: ignore # noqa
 _runtime_vars: dict[str, Any] = {
     '_debug_mode': False,
@@ -32,11 +37,8 @@ _runtime_vars: dict[str, Any] = {
 
 
 def current_actor(err_on_no_runtime: bool = True) -> 'Actor':  # type: ignore # noqa
-    '''
+    """Get the process-local actor instance.
-    Get the process-local actor instance.
+    """
-
-    '''
-    from ._exceptions import NoRuntime
     if _current_actor is None and err_on_no_runtime:
         raise NoRuntime("No local actor has been initialized yet")
 
@@ -44,20 +46,16 @@ def current_actor(err_on_no_runtime: bool = True) -> 'Actor':  # type: ignore #
 
 
 def is_main_process() -> bool:
-    '''
+    """Bool determining if this actor is running in the top-most process.
-    Bool determining if this actor is running in the top-most process.
+    """
-
-    '''
     import multiprocessing as mp
     return mp.current_process().name == 'MainProcess'
 
 
 def debug_mode() -> bool:
-    '''
+    """Bool determining if "debug mode" is on which enables
-    Bool determining if "debug mode" is on which enables
     remote subactor pdb entry on crashes.
-
+    """
-    '''
     return bool(_runtime_vars['_debug_mode'])
 
 

tractor/_streaming.py

@@ -14,36 +14,31 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
-'''
+"""
 Message stream types and APIs.
 
-The machinery and types behind ``Context.open_stream()``
+"""
-
-'''
 from __future__ import annotations
 import inspect
-from contextlib import asynccontextmanager as acm
+from contextlib import asynccontextmanager
+from dataclasses import dataclass
 from typing import (
     Any,
+    Optional,
     Callable,
-    AsyncIterator,
+    AsyncGenerator,
-    TYPE_CHECKING,
+    AsyncIterator
 )
+
 import warnings
 
 import trio
 
-from ._exceptions import (
+from ._ipc import Channel
-    unpack_error,
+from ._exceptions import unpack_error, ContextCancelled
-)
+from ._state import current_actor
 from .log import get_logger
-from .trionics import (
+from .trionics import broadcast_receiver, BroadcastReceiver
-    broadcast_receiver,
-    BroadcastReceiver,
-)
-
-if TYPE_CHECKING:
-    from ._context import Context
 
 
 log = get_logger(__name__)
@@ -75,9 +70,9 @@ class MsgStream(trio.abc.Channel):
     '''
     def __init__(
         self,
-        ctx: Context,  # typing: ignore # noqa
+        ctx: 'Context',  # typing: ignore # noqa
         rx_chan: trio.MemoryReceiveChannel,
-        _broadcaster: BroadcastReceiver | None = None,
+        _broadcaster: Optional[BroadcastReceiver] = None,
 
     ) -> None:
         self._ctx = ctx
@@ -280,7 +275,7 @@ class MsgStream(trio.abc.Channel):
         # still need to consume msgs that are "in transit" from the far
         # end (eg. for ``Context.result()``).
 
-    @acm
+    @asynccontextmanager
     async def subscribe(
         self,
 
@@ -340,8 +335,8 @@ class MsgStream(trio.abc.Channel):
         Send a message over this stream to the far end.
 
         '''
-        if self._ctx._remote_error:
+        if self._ctx._error:
-            raise self._ctx._remote_error  # from None
+            raise self._ctx._error  # from None
 
         if self._closed:
             raise trio.ClosedResourceError('This stream was already closed')
@@ -349,11 +344,371 @@ class MsgStream(trio.abc.Channel):
         await self._ctx.chan.send({'yield': data, 'cid': self._ctx.cid})
 
 
-def stream(func: Callable) -> Callable:
+@dataclass
+class Context:
     '''
-    Mark an async function as a streaming routine with ``@stream``.
+    An inter-actor, ``trio`` task communication context.
+
+    NB: This class should never be instatiated directly, it is delivered
+    by either runtime machinery to a remotely started task or by entering
+    ``Portal.open_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, open task oriented
+    message streams and acts as an IPC aware inter-actor-task cancel
+    scope.
 
     '''
+    chan: Channel
+    cid: str
+
+    # these are the "feeder" channels for delivering
+    # message values to the local task from the runtime
+    # msg processing loop.
+    _recv_chan: trio.MemoryReceiveChannel
+    _send_chan: trio.MemorySendChannel
+
+    _remote_func_type: Optional[str] = None
+
+    # only set on the caller side
+    _portal: Optional['Portal'] = None    # type: ignore # noqa
+    _result: Optional[Any] = False
+    _error: Optional[BaseException] = None
+
+    # status flags
+    _cancel_called: bool = False
+    _cancel_msg: Optional[str] = None
+    _enter_debugger_on_cancel: bool = True
+    _started_called: bool = False
+    _started_received: bool = False
+    _stream_opened: bool = False
+
+    # only set on the callee side
+    _scope_nursery: Optional[trio.Nursery] = None
+
+    _backpressure: bool = False
+
+    async def send_yield(self, data: Any) -> None:
+
+        warnings.warn(
+            "`Context.send_yield()` is now deprecated. "
+            "Use ``MessageStream.send()``. ",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        await self.chan.send({'yield': data, 'cid': self.cid})
+
+    async def send_stop(self) -> None:
+        await self.chan.send({'stop': True, 'cid': self.cid})
+
+    async def _maybe_raise_from_remote_msg(
+        self,
+        msg: dict[str, Any],
+
+    ) -> None:
+        '''
+        (Maybe) 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.
+
+        '''
+        error = msg.get('error')
+        if error:
+            # If this is an error message from a context opened by
+            # ``Portal.open_context()`` we want to interrupt any ongoing
+            # (child) tasks within that context to be notified of the remote
+            # error relayed here.
+            #
+            # The reason we may want to raise the remote error immediately
+            # is that there is no guarantee the associated local task(s)
+            # will attempt to read from any locally opened stream any time
+            # soon.
+            #
+            # NOTE: this only applies when
+            # ``Portal.open_context()`` has been called since it is assumed
+            # (currently) that other portal APIs (``Portal.run()``,
+            # ``.run_in_actor()``) do their own error checking at the point
+            # of the call and result processing.
+            log.error(
+                f'Remote context error for {self.chan.uid}:{self.cid}:\n'
+                f'{msg["error"]["tb_str"]}'
+            )
+            error = unpack_error(msg, self.chan)
+            if (
+                isinstance(error, ContextCancelled) and
+                self._cancel_called
+            ):
+                # this is an expected cancel request response message
+                # and we don't need to raise it in scope since it will
+                # potentially override a real error
+                return
+
+            self._error = error
+
+            # TODO: tempted to **not** do this by-reraising in a
+            # nursery and instead cancel a surrounding scope, detect
+            # the cancellation, then lookup the error that was set?
+            if self._scope_nursery:
+
+                async def raiser():
+                    raise self._error from None
+
+                # from trio.testing import wait_all_tasks_blocked
+                # await wait_all_tasks_blocked()
+                if not self._scope_nursery._closed:  # type: ignore
+                    self._scope_nursery.start_soon(raiser)
+
+    async def cancel(
+        self,
+        msg: Optional[str] = None,
+
+    ) -> None:
+        '''
+        Cancel this inter-actor-task context.
+
+        Request that the far side cancel it's current linked context,
+        Timeout quickly in an attempt to sidestep 2-generals...
+
+        '''
+        side = 'caller' if self._portal else 'callee'
+        if msg:
+            assert side == 'callee', 'Only callee side can provide cancel msg'
+
+        log.cancel(f'Cancelling {side} side of context to {self.chan.uid}')
+
+        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:
+                cs.shield = True
+                log.cancel(
+                    f"Cancelling stream {cid} to "
+                    f"{self._portal.channel.uid}")
+
+                # NOTE: we're telling the far end actor to cancel a task
+                # corresponding to *this actor*. The far end local channel
+                # instance is passed to `Actor._cancel_task()` implicitly.
+                await self._portal.run_from_ns('self', '_cancel_task', cid=cid)
+
+            if cs.cancelled_caught:
+                # XXX: there's no way to know if the remote task was indeed
+                # cancelled in the case where the connection is broken or
+                # some other network error occurred.
+                # if not self._portal.channel.connected():
+                if not self.chan.connected():
+                    log.cancel(
+                        "May have failed to cancel remote task "
+                        f"{cid} for {self._portal.channel.uid}")
+                else:
+                    log.cancel(
+                        "Timed out on cancelling remote task "
+                        f"{cid} for {self._portal.channel.uid}")
+
+        # callee side remote task
+        else:
+            self._cancel_msg = msg
+
+            # 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
+            assert self._scope_nursery
+            self._scope_nursery.cancel_scope.cancel()
+
+        if self._recv_chan:
+            await self._recv_chan.aclose()
+
+    @asynccontextmanager
+    async def open_stream(
+
+        self,
+        backpressure: Optional[bool] = True,
+        msg_buffer_size: Optional[int] = None,
+
+    ) -> 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.
+
+        # 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!'
+            )
+
+        if not self._portal and not self._started_called:
+            raise RuntimeError(
+                'Context.started()` must be called before opening a stream'
+            )
+
+        # NOTE: in one way streaming this only happens on the
+        # caller side inside `Actor.start_remote_task()` 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.
+        ctx = actor.get_context(
+            self.chan,
+            self.cid,
+            msg_buffer_size=msg_buffer_size,
+        )
+        ctx._backpressure = backpressure
+        assert ctx is self
+
+        # 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 ctx._recv_chan._closed:
+            raise trio.ClosedResourceError(
+                'The underlying channel for this stream was already closed!?')
+
+        async with MsgStream(
+            ctx=self,
+            rx_chan=ctx._recv_chan,
+        ) as stream:
+
+            if self._portal:
+                self._portal._streams.add(stream)
+
+            try:
+                self._stream_opened = True
+
+                # XXX: do we need this?
+                # ensure we aren't cancelled before yielding the stream
+                # await trio.lowlevel.checkpoint()
+                yield stream
+
+                # NOTE: Make the stream "one-shot use".  On exit, signal
+                # ``trio.EndOfChannel``/``StopAsyncIteration`` to the
+                # far end.
+                await stream.aclose()
+
+            finally:
+                if self._portal:
+                    try:
+                        self._portal._streams.remove(stream)
+                    except KeyError:
+                        log.warning(
+                            f'Stream was already destroyed?\n'
+                            f'actor: {self.chan.uid}\n'
+                            f'ctx id: {self.cid}'
+                        )
+
+    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 as msgerr:
+
+                        if 'yield' in msg:
+                            # far end task is still streaming to us so discard
+                            log.warning(f'Discarding stream delivered {msg}')
+                            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
+                        ) from msgerr
+
+        return self._result
+
+    async def started(
+        self,
+        value: Optional[Any] = None
+
+    ) -> None:
+        '''
+        Indicate to calling actor's task that this linked context
+        has started and send ``value`` to the other side.
+
+        On the calling side ``value`` is the second item delivered
+        in the tuple returned by ``Portal.open_context()``.
+
+        '''
+        if self._portal:
+            raise RuntimeError(
+                f"Caller side context {self} can not call started!")
+
+        elif self._started_called:
+            raise RuntimeError(
+                f"called 'started' twice on context with {self.chan.uid}")
+
+        await self.chan.send({'started': value, 'cid': self.cid})
+        self._started_called = True
+
+    # TODO: do we need a restart api?
+    # async def restart(self) -> None:
+    #     pass
+
+
+def stream(func: Callable) -> Callable:
+    """Mark an async function as a streaming routine with ``@stream``.
+
+    """
+    # 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
@@ -379,3 +734,22 @@ def stream(func: Callable) -> Callable:
             "(Or ``to_trio`` if using ``asyncio`` in guest mode)."
         )
     return func
+
+
+def context(func: Callable) -> Callable:
+    """Mark an async function as a streaming routine with ``@context``.
+
+    """
+    # annotate
+    # TODO: apply whatever solution ``mypy`` ends up picking for this:
+    # https://github.com/python/mypy/issues/2087#issuecomment-769266912
+    func._tractor_context_function = True  # type: ignore
+
+    sig = inspect.signature(func)
+    params = sig.parameters
+    if 'ctx' not in params:
+        raise TypeError(
+            "The first argument to the context function "
+            f"{func.__name__} must be `ctx: tractor.Context`"
+        )
+    return func

tractor/experimental/_pubsub.py

@@ -37,7 +37,7 @@ import trio
 import wrapt
 
 from ..log import get_logger
-from .._context import Context
+from .._streaming import Context
 
 
 __all__ = ['pub']
@@ -148,8 +148,7 @@ def pub(
     *,
     tasks: set[str] = set(),
 ):
-    '''
+    """Publisher async generator decorator.
-    Publisher async generator decorator.
 
     A publisher can be called multiple times from different actors but
     will only spawn a finite set of internal tasks to stream values to
@@ -228,8 +227,7 @@ def pub(
     running in a single actor to stream data to an arbitrary number of
     subscribers. If you are ok to have a new task running for every call
     to ``pub_service()`` then probably don't need this.
-
+    """
-    '''
     global _pubtask2lock
 
     # handle the decorator not called with () case

tractor/log.py

@@ -82,10 +82,6 @@ class StackLevelAdapter(logging.LoggerAdapter):
         msg: str,
 
     ) -> None:
-        '''
-        IPC level msg-ing.
-
-        '''
         return self.log(5, msg)
 
     def runtime(
@@ -98,20 +94,12 @@ class StackLevelAdapter(logging.LoggerAdapter):
         self,
         msg: str,
     ) -> None:
-        '''
-        Cancellation logging, mostly for runtime reporting.
-
-        '''
         return self.log(16, msg)
 
     def pdb(
         self,
         msg: str,
     ) -> None:
-        '''
-        Debugger logging.
-
-        '''
         return self.log(500, msg)
 
     def log(self, level, msg, *args, **kwargs):

tractor/trionics/_mngrs.py

@@ -237,7 +237,7 @@ async def maybe_open_context(
         yielded = _Cache.values[ctx_key]
 
     except KeyError:
-        log.debug(f'Allocating new {acm_func} for {ctx_key}')
+        log.info(f'Allocating new {acm_func} for {ctx_key}')
         mngr = acm_func(**kwargs)
         resources = _Cache.resources
         assert not resources.get(ctx_key), f'Resource exists? {ctx_key}'
@@ -265,7 +265,7 @@ async def maybe_open_context(
         if yielded is not None:
             # if no more consumers, teardown the client
             if _Cache.users <= 0:
-                log.debug(f'De-allocating resource for {ctx_key}')
+                log.info(f'De-allocating resource for {ctx_key}')
 
                 # XXX: if we're cancelled we the entry may have never
                 # been entered since the nursery task was killed.