Add in depth comment about module naming when used without pkg

As in whenever `Context.cancel()` is not (runtime internally) called
(i.e. `._cancel_called` is not set), we can attempt to detect the parent
`trio` nursery/cancel-scope that is the source. Emit the report with
a `.cancel()` level and attempt to repr in "sclang" form as well as
unhide the stack frame for debug/traceback-in.

docs/README.rst

@@ -3,8 +3,8 @@
 |gh_actions|
 |docs|
 
-``tractor`` is a `structured concurrent`_, multi-processing_ runtime
+``tractor`` is a `structured concurrent`_, (optionally
-built on trio_.
+distributed_) multi-processing_ runtime built on trio_.
 
 Fundamentally, ``tractor`` gives you parallelism via
 ``trio``-"*actors*": independent Python processes (aka
@@ -17,11 +17,20 @@ 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`_"
-but likely *does not* look like what *you* probably think an "actor
+but likely **does not** look like what **you** probably *think* an "actor
-model" looks like, and that's *intentional*.
+model" looks like, and that's **intentional**.
 
-The first step to grok ``tractor`` is to get the basics of ``trio`` down.
+
-A great place to start is the `trio docs`_ and this `blog post`_.
+Where do i start!?
+------------------
+The first step to grok ``tractor`` is to get an intermediate
+knowledge of ``trio`` and **structured concurrency** B)
+
+Some great places to start are,
+- the seminal `blog post`_
+- obviously the `trio docs`_
+- wikipedia's nascent SC_ page
+- the fancy diagrams @ libdill-docs_
 
 
 Features
@@ -593,6 +602,7 @@ matrix seems too hip, we're also mostly all in the the `trio gitter
 channel`_!
 
 .. _structured concurrent: https://trio.discourse.group/t/concise-definition-of-structured-concurrency/228
+.. _distributed: https://en.wikipedia.org/wiki/Distributed_computing
 .. _multi-processing: https://en.wikipedia.org/wiki/Multiprocessing
 .. _trio: https://github.com/python-trio/trio
 .. _nurseries: https://vorpus.org/blog/notes-on-structured-concurrency-or-go-statement-considered-harmful/#nurseries-a-structured-replacement-for-go-statements
@@ -611,8 +621,9 @@ channel`_!
 .. _trio docs: https://trio.readthedocs.io/en/latest/
 .. _blog post: https://vorpus.org/blog/notes-on-structured-concurrency-or-go-statement-considered-harmful/
 .. _structured concurrency: https://en.wikipedia.org/wiki/Structured_concurrency
+.. _SC: https://en.wikipedia.org/wiki/Structured_concurrency
+.. _libdill-docs: https://sustrik.github.io/libdill/structured-concurrency.html
 .. _structured chadcurrency: https://en.wikipedia.org/wiki/Structured_concurrency
-.. _structured concurrency: https://en.wikipedia.org/wiki/Structured_concurrency
 .. _unrequirements: https://en.wikipedia.org/wiki/Actor_model#Direct_communication_and_asynchrony
 .. _async generators: https://www.python.org/dev/peps/pep-0525/
 .. _trio-parallel: https://github.com/richardsheridan/trio-parallel

examples/advanced_faults/ipc_failure_during_stream.py

@@ -6,53 +6,59 @@ been an outage) and we want to ensure that despite being in debug mode
 actor tree will eventually be cancelled without leaving any zombies.
 
 '''
-import trio
+from contextlib import asynccontextmanager as acm
+from functools import partial
+
 from tractor import (
     open_nursery,
     context,
     Context,
+    ContextCancelled,
     MsgStream,
+    _testing,
 )
+import trio
+import pytest
 
 
-async def break_channel_silently_then_error(
+async def break_ipc_then_error(
     stream: MsgStream,
+    break_ipc_with: str|None = None,
+    pre_close: bool = False,
 ):
+    await _testing.break_ipc(
+        stream=stream,
+        method=break_ipc_with,
+        pre_close=pre_close,
+    )
     async for msg in stream:
         await stream.send(msg)
 
-        # XXX: close the channel right after an error is raised
+    assert 0
-        # purposely breaking the IPC transport to make sure the parent
-        # doesn't get stuck in debug or hang on the connection join.
-        # this more or less simulates an infinite msg-receive hang on
-        # the other end.
-        await stream._ctx.chan.send(None)
-        assert 0
 
 
-async def close_stream_and_error(
+async def iter_ipc_stream(
     stream: MsgStream,
+    break_ipc_with: str|None = None,
+    pre_close: bool = False,
 ):
     async for msg in stream:
         await stream.send(msg)
 
-        # wipe out channel right before raising
-        await stream._ctx.chan.send(None)
-        await stream.aclose()
-        assert 0
-
 
 @context
 async def recv_and_spawn_net_killers(
 
     ctx: Context,
-    break_ipc_after: bool | int = False,
+    break_ipc_after: bool|int = False,
+    pre_close: bool = False,
 
 ) -> None:
     '''
     Receive stream msgs and spawn some IPC killers mid-stream.
 
     '''
+    broke_ipc: bool = False
     await ctx.started()
     async with (
         ctx.open_stream() as stream,
@@ -60,27 +66,58 @@ async def recv_and_spawn_net_killers(
     ):
         async for i in stream:
             print(f'child echoing {i}')
-            await stream.send(i)
+            if not broke_ipc:
+                await stream.send(i)
+            else:
+                await trio.sleep(0.01)
+
             if (
                 break_ipc_after
-                and i > break_ipc_after
+                and
+                i >= break_ipc_after
             ):
-                '#################################\n'
+                broke_ipc = True
-                'Simulating child-side IPC BREAK!\n'
+                n.start_soon(
-                '#################################'
+                    iter_ipc_stream,
-                n.start_soon(break_channel_silently_then_error, stream)
+                    stream,
-                n.start_soon(close_stream_and_error, stream)
+                )
+                n.start_soon(
+                    partial(
+                        break_ipc_then_error,
+                        stream=stream,
+                        pre_close=pre_close,
+                    )
+                )
+
+
+@acm
+async def stuff_hangin_ctlc(timeout: float = 1) -> None:
+
+    with trio.move_on_after(timeout) as cs:
+        yield timeout
+
+    if cs.cancelled_caught:
+        # pretend to be a user seeing no streaming action
+        # thinking it's a hang, and then hitting ctl-c..
+        print(
+            f"i'm a user on the PARENT side and thingz hangin "
+            f'after timeout={timeout} ???\n\n'
+            'MASHING CTlR-C..!?\n'
+        )
+        raise KeyboardInterrupt
 
 
 async def main(
     debug_mode: bool = False,
     start_method: str = 'trio',
+    loglevel: str = 'cancel',
 
     # by default we break the parent IPC first (if configured to break
     # at all), but this can be changed so the child does first (even if
     # both are set to break).
-    break_parent_ipc_after: int | bool = False,
+    break_parent_ipc_after: int|bool = False,
-    break_child_ipc_after: int | bool = False,
+    break_child_ipc_after: int|bool = False,
+    pre_close: bool = False,
 
 ) -> None:
 
@@ -91,60 +128,129 @@ async def main(
             # NOTE: even debugger is used we shouldn't get
             # a hang since it never engages due to broken IPC
             debug_mode=debug_mode,
-            loglevel='warning',
+            loglevel=loglevel,
 
         ) as an,
     ):
+        sub_name: str = 'chitty_hijo'
         portal = await an.start_actor(
-            'chitty_hijo',
+            sub_name,
             enable_modules=[__name__],
         )
 
-        async with portal.open_context(
+        async with (
-            recv_and_spawn_net_killers,
+            stuff_hangin_ctlc(timeout=2) as timeout,
-            break_ipc_after=break_child_ipc_after,
+            _testing.expect_ctxc(
+                yay=(
+                    break_parent_ipc_after
+                    or break_child_ipc_after
+                ),
+                # TODO: we CAN'T remove this right?
+                # since we need the ctxc to bubble up from either
+                # the stream API after the `None` msg is sent
+                # (which actually implicitly cancels all remote
+                # tasks in the hijo) or from simluated
+                # KBI-mash-from-user
+                # or should we expect that a KBI triggers the ctxc
+                # and KBI in an eg?
+                reraise=True,
+            ),
 
-        ) as (ctx, sent):
+            portal.open_context(
+                recv_and_spawn_net_killers,
+                break_ipc_after=break_child_ipc_after,
+                pre_close=pre_close,
+            ) as (ctx, sent),
+        ):
+            rx_eoc: bool = False
+            ipc_break_sent: bool = False
             async with ctx.open_stream() as stream:
                 for i in range(1000):
 
                     if (
                         break_parent_ipc_after
-                        and i > break_parent_ipc_after
+                        and
+                        i > break_parent_ipc_after
+                        and
+                        not ipc_break_sent
                     ):
                         print(
                             '#################################\n'
-                            'Simulating parent-side IPC BREAK!\n'
+                            'Simulating PARENT-side IPC BREAK!\n'
-                            '#################################'
+                            '#################################\n'
                         )
-                        await stream._ctx.chan.send(None)
+
+                        # TODO: other methods? see break func above.
+                        # await stream._ctx.chan.send(None)
+                        # await stream._ctx.chan.transport.stream.send_eof()
+                        await stream._ctx.chan.transport.stream.aclose()
+                        ipc_break_sent = True
 
                     # it actually breaks right here in the
-                    # mp_spawn/forkserver backends and thus the zombie
+                    # mp_spawn/forkserver backends and thus the
-                    # reaper never even kicks in?
+                    # zombie reaper never even kicks in?
-                    print(f'parent sending {i}')
+                    try:
-                    await stream.send(i)
+                        print(f'parent sending {i}')
+                        await stream.send(i)
+                    except ContextCancelled as ctxc:
+                        print(
+                            'parent received ctxc on `stream.send()`\n'
+                            f'{ctxc}\n'
+                        )
+                        assert 'root' in ctxc.canceller
+                        assert sub_name in ctx.canceller
 
-                    with trio.move_on_after(2) as cs:
+                        # TODO: is this needed or no?
+                        raise
 
+                    except trio.ClosedResourceError:
+                        # NOTE: don't send if we already broke the
+                        # connection to avoid raising a closed-error
+                        # such that we drop through to the ctl-c
+                        # mashing by user.
+                        await trio.sleep(0.01)
+
+                    # timeout: int = 1
+                    # with trio.move_on_after(timeout) as cs:
+                    async with stuff_hangin_ctlc() as timeout:
+                        print(
+                            f'PARENT `stream.receive()` with timeout={timeout}\n'
+                        )
                         # NOTE: in the parent side IPC failure case this
                         # will raise an ``EndOfChannel`` after the child
                         # is killed and sends a stop msg back to it's
                         # caller/this-parent.
-                        rx = await stream.receive()
+                        try:
+                            rx = await stream.receive()
+                            print(
+                                "I'm a happy PARENT user and echoed to me is\n"
+                                f'{rx}\n'
+                            )
+                        except trio.EndOfChannel:
+                            rx_eoc: bool = True
+                            print('MsgStream got EoC for PARENT')
+                            raise
 
-                        print(f"I'm a happy user and echoed to me is {rx}")
+            print(
+                'Streaming finished and we got Eoc.\n'
+                'Canceling `.open_context()` in root with\n'
+                'CTlR-C..'
+            )
+            if rx_eoc:
+                assert stream.closed
+                try:
+                    await stream.send(i)
+                    pytest.fail('stream not closed?')
+                except (
+                    trio.ClosedResourceError,
+                    trio.EndOfChannel,
+                ) as send_err:
+                    if rx_eoc:
+                        assert send_err is stream._eoc
+                    else:
+                        assert send_err is stream._closed
 
-                    if cs.cancelled_caught:
+            raise KeyboardInterrupt
-                        # pretend to be a user seeing no streaming action
-                        # thinking it's a hang, and then hitting ctl-c..
-                        print("YOO i'm a user anddd thingz hangin..")
-
-                print(
-                    "YOO i'm mad send side dun but thingz hangin..\n"
-                    'MASHING CTlR-C Ctl-c..'
-                )
-                raise KeyboardInterrupt
 
 
 if __name__ == '__main__':

examples/debugging/asyncio_bp.py

@@ -0,0 +1,122 @@
+import asyncio
+
+import trio
+import tractor
+from tractor import (
+    to_asyncio,
+    Portal,
+)
+
+
+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 = True,
+):
+
+    # 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 = True,
+
+) -> None:
+
+    async with tractor.open_nursery(
+        debug_mode=True,
+        maybe_enable_greenback=True,
+        # loglevel='devx',
+    ) as n:
+        ptl: Portal = await n.start_actor(
+            'aio_daemon',
+            enable_modules=[__name__],
+            infect_asyncio=True,
+            debug_mode=True,
+            # loglevel='cancel',
+        )
+
+        async with ptl.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 ptl.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)

examples/debugging/debug_mode_hang.py

@@ -0,0 +1,9 @@
+'''
+Reproduce a bug where enabling debug mode for a sub-actor actually causes
+a hang on teardown...
+
+'''
+import asyncio
+
+import trio
+import tractor

examples/debugging/multi_daemon_subactors.py

@@ -4,9 +4,15 @@ import trio
 
 async def breakpoint_forever():
     "Indefinitely re-enter debugger in child actor."
-    while True:
+    try:
-        yield 'yo'
+        while True:
-        await tractor.breakpoint()
+            yield 'yo'
+            await tractor.breakpoint()
+    except BaseException:
+        tractor.log.get_console_log().exception(
+            'Cancelled while trying to enter pause point!'
+        )
+        raise
 
 
 async def name_error():
@@ -19,7 +25,8 @@ async def main():
     """
     async with tractor.open_nursery(
         debug_mode=True,
-        loglevel='error',
+        # loglevel='cancel',
+        # loglevel='devx',
     ) as n:
 
         p0 = await n.start_actor('bp_forever', enable_modules=[__name__])
@@ -32,7 +39,7 @@ async def main():
             try:
                 await p1.run(name_error)
             except tractor.RemoteActorError as rae:
-                assert rae.type is NameError
+                assert rae.boxed_type is NameError
 
             async for i in stream:
 

examples/debugging/multi_nested_subactors_error_up_through_nurseries.py

@@ -45,6 +45,7 @@ async def spawn_until(depth=0):
             )
 
 
+# TODO: notes on the new boxed-relayed errors through proxy actors
 async def main():
     """The main ``tractor`` routine.
 

examples/debugging/multi_subactors.py

@@ -38,6 +38,7 @@ async def main():
     """
     async with tractor.open_nursery(
         debug_mode=True,
+        # loglevel='runtime',
     ) as n:
 
         # Spawn both actors, don't bother with collecting results

examples/debugging/per_actor_debug.py

@@ -23,5 +23,6 @@ async def main():
             n.start_soon(debug_actor.run, die)
             n.start_soon(crash_boi.run, die)
 
+
 if __name__ == '__main__':
     trio.run(main)

examples/debugging/pm_in_subactor.py

@@ -0,0 +1,56 @@
+import trio
+import tractor
+
+
+@tractor.context
+async def name_error(
+    ctx: tractor.Context,
+):
+    '''
+    Raise a `NameError`, catch it and enter `.post_mortem()`, then
+    expect the `._rpc._invoke()` crash handler to also engage.
+
+    '''
+    try:
+        getattr(doggypants)  # noqa (on purpose)
+    except NameError:
+        await tractor.post_mortem()
+        raise
+
+
+async def main():
+    '''
+    Test 3 `PdbREPL` entries:
+      - one in the child due to manual `.post_mortem()`,
+      - another in the child due to runtime RPC crash handling.
+      - final one here in parent from the RAE.
+
+    '''
+    # XXX NOTE: ideally the REPL arrives at this frame in the parent
+    # ONE UP FROM the inner ctx block below!
+    async with tractor.open_nursery(
+        debug_mode=True,
+        # loglevel='cancel',
+    ) as an:
+        p: tractor.Portal = await an.start_actor(
+            'child',
+            enable_modules=[__name__],
+        )
+
+        # XXX should raise `RemoteActorError[NameError]`
+        # AND be the active frame when REPL enters!
+        try:
+            async with p.open_context(name_error) as (ctx, first):
+                assert first
+        except tractor.RemoteActorError as rae:
+            assert rae.boxed_type is NameError
+
+            # manually handle in root's parent task
+            await tractor.post_mortem()
+            raise
+        else:
+            raise RuntimeError('IPC ctx should have remote errored!?')
+
+
+if __name__ == '__main__':
+    trio.run(main)

examples/debugging/root_actor_breakpoint_forever.py

@@ -2,10 +2,13 @@ import trio
 import tractor
 
 
-async def main():
+async def main(
+    registry_addrs: tuple[str, int]|None = None
+):
 
     async with tractor.open_root_actor(
         debug_mode=True,
+        # loglevel='runtime',
     ):
         while True:
             await tractor.breakpoint()

examples/debugging/shield_hang_in_sub.py

@@ -0,0 +1,81 @@
+'''
+Verify we can dump a `stackscope` tree on a hang.
+
+'''
+import os
+import signal
+
+import trio
+import tractor
+
+@tractor.context
+async def start_n_shield_hang(
+    ctx: tractor.Context,
+):
+    # actor: tractor.Actor = tractor.current_actor()
+
+    # sync to parent-side task
+    await ctx.started(os.getpid())
+
+    print('Entering shield sleep..')
+    with trio.CancelScope(shield=True):
+        await trio.sleep_forever()  # in subactor
+
+    # XXX NOTE ^^^ since this shields, we expect
+    # the zombie reaper (aka T800) to engage on
+    # SIGINT from the user and eventually hard-kill
+    # this subprocess!
+
+
+async def main(
+    from_test: bool = False,
+) -> None:
+
+    async with (
+        tractor.open_nursery(
+            debug_mode=True,
+            enable_stack_on_sig=True,
+            # maybe_enable_greenback=False,
+            loglevel='devx',
+        ) as an,
+    ):
+
+        ptl: tractor.Portal  = await an.start_actor(
+            'hanger',
+            enable_modules=[__name__],
+            debug_mode=True,
+        )
+        async with ptl.open_context(
+            start_n_shield_hang,
+        ) as (ctx, cpid):
+
+            _, proc, _ = an._children[ptl.chan.uid]
+            assert cpid == proc.pid
+
+            print(
+                'Yo my child hanging..?\n'
+                'Sending SIGUSR1 to see a tree-trace!\n'
+            )
+
+            # XXX simulate the wrapping test's "user actions"
+            # (i.e. if a human didn't run this manually but wants to
+            # know what they should do to reproduce test behaviour)
+            if from_test:
+                os.kill(
+                    cpid,
+                    signal.SIGUSR1,
+                )
+
+                # simulate user cancelling program
+                await trio.sleep(0.5)
+                os.kill(
+                    os.getpid(),
+                    signal.SIGINT,
+                )
+            else:
+                # actually let user send the ctl-c
+                await trio.sleep_forever()  # in root
+
+
+if __name__ == '__main__':
+    trio.run(main)

examples/debugging/shielded_pause.py

@@ -0,0 +1,88 @@
+import trio
+import tractor
+
+
+async def cancellable_pause_loop(
+    task_status: trio.TaskStatus[trio.CancelScope] = trio.TASK_STATUS_IGNORED
+):
+    with trio.CancelScope() as cs:
+        task_status.started(cs)
+        for _ in range(3):
+            try:
+                # ON first entry, there is no level triggered
+                # cancellation yet, so this cp does a parent task
+                # ctx-switch so that this scope raises for the NEXT
+                # checkpoint we hit.
+                await trio.lowlevel.checkpoint()
+                await tractor.pause()
+
+                cs.cancel()
+
+                # parent should have called `cs.cancel()` by now
+                await trio.lowlevel.checkpoint()
+
+            except trio.Cancelled:
+                print('INSIDE SHIELDED PAUSE')
+                await tractor.pause(shield=True)
+        else:
+            # should raise it again, bubbling up to parent
+            print('BUBBLING trio.Cancelled to parent task-nursery')
+            await trio.lowlevel.checkpoint()
+
+
+async def pm_on_cancelled():
+    async with trio.open_nursery() as tn:
+        tn.cancel_scope.cancel()
+        try:
+            await trio.sleep_forever()
+        except trio.Cancelled:
+            # should also raise `Cancelled` since
+            # we didn't pass `shield=True`.
+            try:
+                await tractor.post_mortem(hide_tb=False)
+            except trio.Cancelled as taskc:
+
+                # should enter just fine, in fact it should
+                # be debugging the internals of the previous
+                # sin-shield call above Bo
+                await tractor.post_mortem(
+                    hide_tb=False,
+                    shield=True,
+                )
+                raise taskc
+
+        else:
+            raise RuntimeError('Dint cancel as expected!?')
+
+
+async def cancelled_before_pause(
+):
+    '''
+    Verify that using a shielded pause works despite surrounding
+    cancellation called state in the calling task.
+
+    '''
+    async with trio.open_nursery() as tn:
+        cs: trio.CancelScope = await tn.start(cancellable_pause_loop)
+        await trio.sleep(0.1)
+
+    assert cs.cancelled_caught
+
+    await pm_on_cancelled()
+
+
+async def main():
+    async with tractor.open_nursery(
+        debug_mode=True,
+    ) as n:
+        portal: tractor.Portal = await n.run_in_actor(
+            cancelled_before_pause,
+        )
+        await portal.result()
+
+        # ensure the same works in the root actor!
+        await pm_on_cancelled()
+
+
+if __name__ == '__main__':
+    trio.run(main)

examples/debugging/subactor_breakpoint.py

@@ -3,17 +3,20 @@ import tractor
 
 
 async def breakpoint_forever():
-    """Indefinitely re-enter debugger in child actor.
+    '''
-    """
+    Indefinitely re-enter debugger in child actor.
+
+    '''
     while True:
         await trio.sleep(0.1)
-        await tractor.breakpoint()
+        await tractor.pause()
 
 
 async def main():
 
     async with tractor.open_nursery(
         debug_mode=True,
+        loglevel='cancel',
     ) as n:
 
         portal = await n.run_in_actor(

examples/debugging/subactor_error.py

@@ -3,16 +3,26 @@ import tractor
 
 
 async def name_error():
-    getattr(doggypants)
+    getattr(doggypants)  # noqa (on purpose)
 
 
 async def main():
     async with tractor.open_nursery(
         debug_mode=True,
-    ) as n:
+        # loglevel='transport',
+    ) as an:
 
-        portal = await n.run_in_actor(name_error)
+        # TODO: ideally the REPL arrives at this frame in the parent,
-        await portal.result()
+        # ABOVE the @api_frame of `Portal.run_in_actor()` (which
+        # should eventually not even be a portal method ... XD)
+        # await tractor.pause()
+        p: tractor.Portal = await an.run_in_actor(name_error)
+
+        # with this style, should raise on this line
+        await p.result()
+
+        # with this alt style should raise at `open_nusery()`
+        # return await p.result()
 
 
 if __name__ == '__main__':

examples/debugging/sync_bp.py

@@ -0,0 +1,169 @@
+from functools import partial
+import time
+
+import trio
+import tractor
+
+# TODO: only import these when not running from test harness?
+# can we detect `pexpect` usage maybe?
+# from tractor.devx._debug import (
+#     get_lock,
+#     get_debug_req,
+# )
+
+
+def sync_pause(
+    use_builtin: bool = False,
+    error: bool = False,
+    hide_tb: bool = True,
+    pre_sleep: float|None = None,
+):
+    if pre_sleep:
+        time.sleep(pre_sleep)
+
+    if use_builtin:
+        breakpoint(hide_tb=hide_tb)
+
+    else:
+        # TODO: maybe for testing some kind of cm style interface
+        # where the `._set_trace()` call doesn't happen until block
+        # exit?
+        # assert get_lock().ctx_in_debug is None
+        # assert get_debug_req().repl is None
+        tractor.pause_from_sync()
+        # assert get_debug_req().repl is None
+
+    if error:
+        raise RuntimeError('yoyo sync code error')
+
+
+@tractor.context
+async def start_n_sync_pause(
+    ctx: tractor.Context,
+):
+    actor: tractor.Actor = tractor.current_actor()
+
+    # sync to parent-side task
+    await ctx.started()
+
+    print(f'Entering `sync_pause()` in subactor: {actor.uid}\n')
+    sync_pause()
+    print(f'Exited `sync_pause()` in subactor: {actor.uid}\n')
+
+
+async def main() -> None:
+    async with (
+        tractor.open_nursery(
+            debug_mode=True,
+            maybe_enable_greenback=True,
+            enable_stack_on_sig=True,
+            # loglevel='warning',
+            # loglevel='devx',
+        ) as an,
+        trio.open_nursery() as tn,
+    ):
+        # just from root task
+        sync_pause()
+
+        p: tractor.Portal  = await an.start_actor(
+            'subactor',
+            enable_modules=[__name__],
+            # infect_asyncio=True,
+            debug_mode=True,
+        )
+
+        # TODO: 3 sub-actor usage cases:
+        # -[x] via a `.open_context()`
+        # -[ ] via a `.run_in_actor()` call
+        # -[ ] via a `.run()`
+        # -[ ] via a `.to_thread.run_sync()` in subactor
+        async with p.open_context(
+            start_n_sync_pause,
+        ) as (ctx, first):
+            assert first is None
+
+            # TODO: handle bg-thread-in-root-actor special cases!
+            #
+            # there are a couple very subtle situations possible here
+            # and they are likely to become more important as cpython
+            # moves to support no-GIL.
+            #
+            # Cases:
+            # 1. root-actor bg-threads that call `.pause_from_sync()`
+            #   whilst an in-tree subactor also is using ` .pause()`.
+            # |_ since the root-actor bg thread can not
+            #   `Lock._debug_lock.acquire_nowait()` without running
+            #   a `trio.Task`, AND because the
+            #   `PdbREPL.set_continue()` is called from that
+            #   bg-thread, we can not `._debug_lock.release()`
+            #   either!
+            #  |_ this results in no actor-tree `Lock` being used
+            #    on behalf of the bg-thread and thus the subactor's
+            #    task and the thread trying to to use stdio
+            #    simultaneously which results in the classic TTY
+            #    clobbering!
+            #
+            # 2. mutiple sync-bg-threads that call
+            #   `.pause_from_sync()` where one is scheduled via
+            #   `Nursery.start_soon(to_thread.run_sync)` in a bg
+            #   task.
+            #
+            #   Due to the GIL, the threads never truly try to step
+            #   through the REPL simultaneously, BUT their `logging`
+            #   and traceback outputs are interleaved since the GIL
+            #   (seemingly) on every REPL-input from the user
+            #   switches threads..
+            #
+            #   Soo, the context switching semantics of the GIL
+            #   result in a very confusing and messy interaction UX
+            #   since eval and (tb) print output is NOT synced to
+            #   each REPL-cycle (like we normally make it via
+            #   a `.set_continue()` callback triggering the
+            #   `Lock.release()`). Ideally we can solve this
+            #   usability issue NOW because this will of course be
+            #   that much more important when eventually there is no
+            #   GIL!
+
+            # XXX should cause double REPL entry and thus TTY
+            # clobbering due to case 1. above!
+            tn.start_soon(
+                partial(
+                    trio.to_thread.run_sync,
+                    partial(
+                        sync_pause,
+                        use_builtin=False,
+                        # pre_sleep=0.5,
+                    ),
+                    abandon_on_cancel=True,
+                    thread_name='start_soon_root_bg_thread',
+                )
+            )
+
+            await tractor.pause()
+
+            # XXX should cause double REPL entry and thus TTY
+            # clobbering due to case 2. above!
+            await trio.to_thread.run_sync(
+                partial(
+                    sync_pause,
+                    # NOTE this already works fine since in the new
+                    # thread the `breakpoint()` built-in is never
+                    # overloaded, thus NO locking is used, HOWEVER
+                    # the case 2. from above still exists!
+                    use_builtin=True,
+                ),
+                # TODO: with this `False` we can hang!??!
+                # abandon_on_cancel=False,
+                abandon_on_cancel=True,
+                thread_name='inline_root_bg_thread',
+            )
+
+        await ctx.cancel()
+
+        # TODO: case where we cancel from trio-side while asyncio task
+        # has debugger lock?
+        await p.cancel_actor()
+
+
+if __name__ == '__main__':
+    trio.run(main)

examples/full_fledged_streaming_service.py

@@ -1,6 +1,11 @@
 import time
 import trio
 import tractor
+from tractor import (
+    ActorNursery,
+    MsgStream,
+    Portal,
+)
 
 
 # this is the first 2 actors, streamer_1 and streamer_2
@@ -12,14 +17,18 @@ async def stream_data(seed):
 
 # this is the third actor; the aggregator
 async def aggregate(seed):
-    """Ensure that the two streams we receive match but only stream
+    '''
+    Ensure that the two streams we receive match but only stream
     a single set of values to the parent.
-    """
+
-    async with tractor.open_nursery() as nursery:
+    '''
-        portals = []
+    an: ActorNursery
+    async with tractor.open_nursery() as an:
+        portals: list[Portal] = []
         for i in range(1, 3):
-            # fork point
+
-            portal = await nursery.start_actor(
+            # fork/spawn call
+            portal = await an.start_actor(
                 name=f'streamer_{i}',
                 enable_modules=[__name__],
             )
@@ -43,7 +52,11 @@ async def aggregate(seed):
         async with trio.open_nursery() as n:
 
             for portal in portals:
-                n.start_soon(push_to_chan, portal, send_chan.clone())
+                n.start_soon(
+                    push_to_chan,
+                    portal,
+                    send_chan.clone(),
+                )
 
             # close this local task's reference to send side
             await send_chan.aclose()
@@ -60,26 +73,36 @@ async def aggregate(seed):
 
             print("FINISHED ITERATING in aggregator")
 
-        await nursery.cancel()
+        await an.cancel()
         print("WAITING on `ActorNursery` to finish")
     print("AGGREGATOR COMPLETE!")
 
 
-# this is the main actor and *arbiter*
+async def main() -> list[int]:
-async def main():
+    '''
-    # a nursery which spawns "actors"
+    This is the "root" actor's main task's entrypoint.
+
+    By default (and if not otherwise specified) that root process
+    also acts as a "registry actor" / "registrar" on the localhost
+    for the purposes of multi-actor "service discovery".
+
+    '''
+    # yes, a nursery which spawns `trio`-"actors" B)
+    an: ActorNursery
     async with tractor.open_nursery(
-        arbiter_addr=('127.0.0.1', 1616)
+        loglevel='cancel',
-    ) as nursery:
+        debug_mode=True,
+    ) as an:
 
         seed = int(1e3)
         pre_start = time.time()
 
-        portal = await nursery.start_actor(
+        portal: Portal = await an.start_actor(
             name='aggregator',
             enable_modules=[__name__],
         )
 
+        stream: MsgStream
         async with portal.open_stream_from(
             aggregate,
             seed=seed,
@@ -88,11 +111,12 @@ async def main():
             start = time.time()
             # the portal call returns exactly what you'd expect
             # as if the remote "aggregate" function was called locally
-            result_stream = []
+            result_stream: list[int] = []
             async for value in stream:
                 result_stream.append(value)
 
-        await portal.cancel_actor()
+        cancelled: bool = await portal.cancel_actor()
+        assert cancelled
 
         print(f"STREAM TIME = {time.time() - start}")
         print(f"STREAM + SPAWN TIME = {time.time() - pre_start}")

examples/multihost/client.py

@@ -0,0 +1,63 @@
+import tractor
+import trio
+
+
+log = tractor.log.get_console_log(
+    _root_name='my_app',
+    name='client',
+)
+_loglevel: str = 'cancel'
+
+
+async def client_main():
+
+    # enable console logging for our custom app's logger
+    tractor.log.get_console_log(
+        level=_loglevel,
+        _root_name='my_app',
+        name='client',
+    )
+
+    # presuming you can get a ref to the target server RPC-ctx func,
+    # pass it directly as our rpc-ctx endpoint below.
+    from server import proxy_request
+    #
+    # NOTE, see he equiv note in `server.py` explaining why this will
+    # render more or less to `'server:proxy_request'` according to
+    # `tractor.msg.NamespacePath.from_ref(proxy_request)`
+
+    async with (
+        tractor.open_root_actor(
+            name='web_requester',
+            registry_addrs=[('127.0.0.1', 1616)],
+            enable_modules=[],  # since this isn't a service actor
+            loglevel=_loglevel,
+        ),
+
+        # use discovery api to find the server actor on your net
+        # (NOTE, in which case the below registry addr would have to
+        # be the public IP of that host!)
+        # tractor.find_actor(
+        #     name='web_proxier',
+        #     registry_addrs=[('127.0.0.1', 1616)],
+        # ) as portal,
+
+        tractor.wait_for_actor(
+            name='web_proxier',
+            registry_addr=('127.0.0.1', 1616),
+        ) as portal,
+
+        # open an RPC context with the remote actor, thus spawning
+        # a new task implemented as the function defined in the
+        # server code.
+        portal.open_context(
+            proxy_request,
+            address='https://github.com',
+        ) as (ctx, first),
+    ):
+        resp: dict = await ctx.result()
+        print(resp)
+
+
+if __name__ == '__main__':
+    trio.run(client_main)

examples/multihost/server.py

@@ -0,0 +1,91 @@
+import httpx
+import tractor
+import trio
+
+log = tractor.log.get_console_log(
+    _root_name='my_app',
+    name='server_thingy',
+)
+
+
+@tractor.context
+async def proxy_request(
+    ctx: tractor.Context,
+    address: str,
+):
+    log.info(
+        'Rxed client request\n'
+        f'{address}\n'
+    )
+    async with httpx.AsyncClient() as client:
+        await ctx.started()  # signal the remote task has started its client
+        log.info(
+            'Opened `httpx` client..'
+        )
+
+        resp: httpx.Response = await client.get(address)  # do the proxied request, get response.
+        log.info(
+            'Got response..\n'
+            f'{resp}\n'
+        )
+
+        # only breaking this up to clarify that you didn't have to only return a single result you could have opened
+        # a long lived stream to avoid task spawning overhead in this service actor.. but more on that later..
+        #
+        # NOTEs, cast to `str` here since we can't serialize the
+        # response type for the wire directly, at least no without
+        # a custom `msgspec.Decoder`!!
+        return str(resp)
+
+        # return resp
+        # ^TODO, various typed msging options:
+        # -[ ] try returning just the `resp` verbatim => should raise
+        #    an MTE
+        # -[ ] try defining a custom `Response` msg to proxy the orig
+        #     types fields and/or a decoder to serialize it?
+
+
+async def main():
+
+    # enable console logging for our custom app's logger
+    tractor.log.get_console_log(
+        level='info',
+        _root_name='my_app',
+        name='server_thingy',
+    )
+
+    # since (originally) this is run as a script, we will end up with
+    # `__name__ == '__main__'` so to ensure the rpc request from the
+    # client isn't blocked by `tractor.ModuleNotFound`, we want to just
+    # use the explicit file-as-module name.. why u ask?
+    this_mod: str = 'server'
+    # WELP, when the `Portal.open_context()` api (used in
+    # `client.py`) requests the RPC-ctx ep it will send
+    # a `str`-like-ptr encoding the func-ref in form expected by
+    # `pkgutil.resolve_name()`.
+    #
+    # Since the client's local namespace reference/path to this
+    # `.server.py` mod will be from a direct manual import, that
+    # `proxy_request()`-ref will render as `'server:proxy_request'`
+    # (as delivered from `NamespacePath.from_ref()` since that's how
+    # `.open_context()` serializes the func's-ref for IPC transit).
+    # SO, we need to be sure we "enable" this module name so that the
+    # nsp maps to an enabled module in the `Actor._mods: dict`.
+
+    async with tractor.open_root_actor(
+        name='web_proxier',
+        registry_addrs=[('127.0.0.1', 1616)],
+        enable_modules=[this_mod],
+        loglevel='info',
+    ):
+        # just block waiting for a peer actor to connect and open an
+        # RPC context using the above proxy endpoint.
+        log.info(
+            'proxy server up bby!\n'
+            'waiting to serve some requests..\n'
+        )
+        await trio.sleep_forever()
+
+
+if __name__ == '__main__':
+    trio.run(main)

examples/parallelism/concurrent_actors_primes.py

@@ -8,7 +8,10 @@ This uses no extra threads, fancy semaphores or futures; all we need
 is ``tractor``'s channels.
 
 """
-from contextlib import asynccontextmanager
+from contextlib import (
+    asynccontextmanager as acm,
+    aclosing,
+)
 from typing import Callable
 import itertools
 import math
@@ -16,7 +19,6 @@ import time
 
 import tractor
 import trio
-from async_generator import aclosing
 
 
 PRIMES = [
@@ -44,7 +46,7 @@ async def is_prime(n):
     return True
 
 
-@asynccontextmanager
+@acm
 async def worker_pool(workers=4):
     """Though it's a trivial special case for ``tractor``, the well
     known "worker pool" seems to be the defacto "but, I want this

examples/rpc_bidir_streaming.py

@@ -13,7 +13,7 @@ async def simple_rpc(
 
     '''
     # signal to parent that we're up much like
-    # ``trio_typing.TaskStatus.started()``
+    # ``trio.TaskStatus.started()``
     await ctx.started(data + 1)
 
     async with ctx.open_stream() as stream:

examples/service_discovery.py

@@ -9,7 +9,7 @@ async def main(service_name):
     async with tractor.open_nursery() as an:
         await an.start_actor(service_name)
 
-        async with tractor.get_arbiter('127.0.0.1', 1616) as portal:
+        async with tractor.get_registry('127.0.0.1', 1616) as portal:
             print(f"Arbiter is listening on {portal.channel}")
 
         async with tractor.wait_for_actor(service_name) as sockaddr:

pyproject.toml

@@ -1,3 +1,72 @@
+[build-system]
+requires = ["poetry-core"]
+build-backend = "poetry.core.masonry.api"
+
+# ------ - ------
+
+[tool.poetry]
+name = "tractor"
+version = "0.1.0a6dev0"
+description='structured concurrent `trio`-"actors"'
+authors = ["Tyler Goodlet <goodboy_foss@protonmail.com>"]
+license = "AGPlv3"
+readme = "docs/README.rst"
+
+# TODO: do we need this xontrib loader at all given pep420
+# and xonsh's xontrib global-autoload-via-setuptools?
+# https://xon.sh/tutorial_xontrib.html#authoring-xontribs
+packages = [
+  {include = 'tractor' },
+  # {include = 'tractor.experimental' },
+  # {include = 'tractor.trionics' },
+  # {include = 'tractor.msg' },
+  # {include = 'tractor.devx' },
+]
+
+# ------ - ------
+
+[tool.poetry.dependencies]
+python = "^3.11"
+
+# trio runtime related
+# proper range spec:
+# https://packaging.python.org/en/latest/discussions/install-requires-vs-requirements/#id5
+trio='^0.24'
+tricycle = "^0.4.1"
+trio-typing = "^0.10.0"
+
+msgspec='^0.18.5'  # interchange
+wrapt = "^1.16.0"  # decorators
+colorlog = "^6.8.2"  # logging
+
+# built-in multi-actor `pdb` REPL
+pdbp = "^1.5.0"
+
+
+# TODO: distributed transport using
+# linux kernel networking
+# 'pyroute2
+
+# ------ - ------
+
+[tool.poetry.group.dev]
+optional = false
+[tool.poetry.group.dev.dependencies]
+# testing
+pytest = "^8.2.0"
+pexpect = "^4.9.0"
+
+# .devx tooling
+greenback = "^1.2.1"
+stackscope = "^0.2.2"
+
+# (light) xonsh usage/integration
+xontrib-vox = "^0.0.1"
+prompt-toolkit = "^3.0.43"
+xonsh-vox-tabcomplete = "^0.5"
+
+# ------ - ------
+
 [tool.towncrier]
 package = "tractor"
 filename = "NEWS.rst"
@@ -26,3 +95,47 @@ all_bullets = true
   directory = "trivial"
   name = "Trivial/Internal Changes"
   showcontent = true
+
+# ------ - ------
+
+[tool.pytest.ini_options]
+minversion = '6.0'
+testpaths = [
+  'tests'
+]
+addopts = [
+  # TODO: figure out why this isn't working..
+  '--rootdir=./tests',
+
+  '--import-mode=importlib',
+  # don't show frickin captured logs AGAIN in the report..
+  '--show-capture=no',
+]
+log_cli = false
+
+# TODO: maybe some of these layout choices?
+# https://docs.pytest.org/en/8.0.x/explanation/goodpractices.html#choosing-a-test-layout-import-rules
+# pythonpath = "src"
+
+# ------ - ------
+
+[project]
+keywords = [
+  'trio',
+  'async',
+  'concurrency',
+  'structured concurrency',
+  'actor model',
+  'distributed',
+  'multiprocessing'
+]
+classifiers = [
+  "Development Status :: 3 - Alpha",
+  "Operating System :: POSIX :: Linux",
+  "Framework :: Trio",
+  "License :: OSI Approved :: GNU Affero General Public License v3 or later (AGPLv3+)",
+  "Programming Language :: Python :: Implementation :: CPython",
+  "Programming Language :: Python :: 3 :: Only",
+  "Programming Language :: Python :: 3.11",
+  "Topic :: System :: Distributed Computing",
+]

requirements-test.txt

@@ -6,3 +6,4 @@ mypy
 trio_typing
 pexpect
 towncrier
+numpy

setup.py

@@ -26,7 +26,7 @@ with open('docs/README.rst', encoding='utf-8') as f:
 setup(
     name="tractor",
     version='0.1.0a6dev0',  # alpha zone
-    description='structured concurrrent `trio`-"actors"',
+    description='structured concurrent `trio`-"actors"',
     long_description=readme,
     license='AGPLv3',
     author='Tyler Goodlet',
@@ -36,41 +36,44 @@ setup(
     platforms=['linux', 'windows'],
     packages=[
         'tractor',
-        'tractor.experimental',
+        'tractor.experimental',  # wacky ideas
-        'tractor.trionics',
+        'tractor.trionics',  # trio extensions
+        'tractor.msg',  # lowlevel data types
+        'tractor.devx',  # "dev-experience"
     ],
     install_requires=[
 
         # trio related
         # proper range spec:
         # https://packaging.python.org/en/latest/discussions/install-requires-vs-requirements/#id5
-        'trio >= 0.22',
+        'trio >= 0.24',
-        'async_generator',
+
-        'trio_typing',
+        # 'async_generator',  # in stdlib mostly!
-        'exceptiongroup',
+        # 'trio_typing',  # trio==0.23.0 has type hints!
+        # 'exceptiongroup',  # in stdlib as of 3.11!
 
         # tooling
+        'stackscope',
         'tricycle',
         'trio_typing',
         'colorlog',
         'wrapt',
 
         # IPC serialization
-        'msgspec',
+        'msgspec>=0.18.5',
 
         # debug mode REPL
         'pdbp',
 
+        # TODO: distributed transport using
+        # linux kernel networking
+        # 'pyroute2',
+
         # pip ref docs on these specs:
         # https://pip.pypa.io/en/stable/reference/requirement-specifiers/#examples
         # and pep:
         # https://peps.python.org/pep-0440/#version-specifiers
 
-        # windows deps workaround for ``pdbpp``
-        # https://github.com/pdbpp/pdbpp/issues/498
-        # https://github.com/pdbpp/fancycompleter/issues/37
-        'pyreadline3 ; platform_system == "Windows"',
-
     ],
     tests_require=['pytest'],
     python_requires=">=3.10",

tests/conftest.py

@@ -7,94 +7,19 @@ import os
 import random
 import signal
 import platform
-import pathlib
 import time
-import inspect
-from functools import partial, wraps
 
 import pytest
-import trio
 import tractor
+from tractor._testing import (
+    examples_dir as examples_dir,
+    tractor_test as tractor_test,
+    expect_ctxc as expect_ctxc,
+)
 
+# TODO: include wtv plugin(s) we build in `._testing.pytest`?
 pytest_plugins = ['pytester']
 
-
-def tractor_test(fn):
-    """
-    Use:
-
-    @tractor_test
-    async def test_whatever():
-        await ...
-
-    If fixtures:
-
-        - ``arb_addr`` (a socket addr tuple where arbiter is listening)
-        - ``loglevel`` (logging level passed to tractor internals)
-        - ``start_method`` (subprocess spawning backend)
-
-    are defined in the `pytest` fixture space they will be automatically
-    injected to tests declaring these funcargs.
-    """
-    @wraps(fn)
-    def wrapper(
-        *args,
-        loglevel=None,
-        arb_addr=None,
-        start_method=None,
-        **kwargs
-    ):
-        # __tracebackhide__ = True
-
-        if 'arb_addr' in inspect.signature(fn).parameters:
-            # injects test suite fixture value to test as well
-            # as `run()`
-            kwargs['arb_addr'] = arb_addr
-
-        if 'loglevel' in inspect.signature(fn).parameters:
-            # allows test suites to define a 'loglevel' fixture
-            # that activates the internal logging
-            kwargs['loglevel'] = loglevel
-
-        if start_method is None:
-            if platform.system() == "Windows":
-                start_method = 'trio'
-
-        if 'start_method' in inspect.signature(fn).parameters:
-            # set of subprocess spawning backends
-            kwargs['start_method'] = start_method
-
-        if kwargs:
-
-            # use explicit root actor start
-
-            async def _main():
-                async with tractor.open_root_actor(
-                    # **kwargs,
-                    arbiter_addr=arb_addr,
-                    loglevel=loglevel,
-                    start_method=start_method,
-
-                    # TODO: only enable when pytest is passed --pdb
-                    # debug_mode=True,
-
-                ):
-                    await fn(*args, **kwargs)
-
-            main = _main
-
-        else:
-            # use implicit root actor start
-            main = partial(fn, *args, **kwargs)
-
-        return trio.run(main)
-
-    return wrapper
-
-
-_arb_addr = '127.0.0.1', random.randint(1000, 9999)
-
-
 # Sending signal.SIGINT on subprocess fails on windows. Use CTRL_* alternatives
 if platform.system() == 'Windows':
     _KILL_SIGNAL = signal.CTRL_BREAK_EVENT
@@ -114,41 +39,45 @@ no_windows = pytest.mark.skipif(
 )
 
 
-def repodir() -> pathlib.Path:
-    '''
-    Return the abspath to the repo directory.
-
-    '''
-    # 2 parents up to step up through tests/<repo_dir>
-    return pathlib.Path(__file__).parent.parent.absolute()
-
-
-def examples_dir() -> pathlib.Path:
-    '''
-    Return the abspath to the examples directory as `pathlib.Path`.
-
-    '''
-    return repodir() / 'examples'
-
-
 def pytest_addoption(parser):
     parser.addoption(
-        "--ll", action="store", dest='loglevel',
+        "--ll",
+        action="store",
+        dest='loglevel',
         default='ERROR', help="logging level to set when testing"
     )
 
     parser.addoption(
-        "--spawn-backend", action="store", dest='spawn_backend',
+        "--spawn-backend",
+        action="store",
+        dest='spawn_backend',
         default='trio',
         help="Processing spawning backend to use for test run",
     )
 
+    parser.addoption(
+        "--tpdb", "--debug-mode",
+        action="store_true",
+        dest='tractor_debug_mode',
+        # default=False,
+        help=(
+            'Enable a flag that can be used by tests to to set the '
+            '`debug_mode: bool` for engaging the internal '
+            'multi-proc debugger sys.'
+        ),
+    )
+
 
 def pytest_configure(config):
     backend = config.option.spawn_backend
     tractor._spawn.try_set_start_method(backend)
 
 
+@pytest.fixture(scope='session')
+def debug_mode(request):
+    return request.config.option.tractor_debug_mode
+
+
 @pytest.fixture(scope='session', autouse=True)
 def loglevel(request):
     orig = tractor.log._default_loglevel
@@ -168,14 +97,35 @@ _ci_env: bool = os.environ.get('CI', False)
 
 @pytest.fixture(scope='session')
 def ci_env() -> bool:
-    """Detect CI envoirment.
+    '''
-    """
+    Detect CI envoirment.
+
+    '''
     return _ci_env
 
 
+# TODO: also move this to `._testing` for now?
+# -[ ] possibly generalize and re-use for multi-tree spawning
+#    along with the new stuff for multi-addrs in distribute_dis
+#    branch?
+#
+# choose randomly at import time
+_reg_addr: tuple[str, int] = (
+    '127.0.0.1',
+    random.randint(1000, 9999),
+)
+
+
 @pytest.fixture(scope='session')
-def arb_addr():
+def reg_addr() -> tuple[str, int]:
-    return _arb_addr
+
+    # globally override the runtime to the per-test-session-dynamic
+    # addr so that all tests never conflict with any other actor
+    # tree using the default.
+    from tractor import _root
+    _root._default_lo_addrs = [_reg_addr]
+
+    return _reg_addr
 
 
 def pytest_generate_tests(metafunc):
@@ -212,34 +162,40 @@ def sig_prog(proc, sig):
     assert ret
 
 
+# TODO: factor into @cm and move to `._testing`?
 @pytest.fixture
 def daemon(
     loglevel: str,
     testdir,
-    arb_addr: tuple[str, int],
+    reg_addr: tuple[str, int],
 ):
     '''
-    Run a daemon actor as a "remote arbiter".
+    Run a daemon root actor as a separate actor-process tree and
+    "remote registrar" for discovery-protocol related tests.
 
     '''
     if loglevel in ('trace', 'debug'):
-        # too much logging will lock up the subproc (smh)
+        # XXX: too much logging will lock up the subproc (smh)
-        loglevel = 'info'
+        loglevel: str = 'info'
 
-    cmdargs = [
+    code: str = (
-        sys.executable, '-c',
+            "import tractor; "
-        "import tractor; tractor.run_daemon([], registry_addr={}, loglevel={})"
+            "tractor.run_daemon([], registry_addrs={reg_addrs}, loglevel={ll})"
-        .format(
+    ).format(
-            arb_addr,
+        reg_addrs=str([reg_addr]),
-            "'{}'".format(loglevel) if loglevel else None)
+        ll="'{}'".format(loglevel) if loglevel else None,
+    )
+    cmd: list[str] = [
+        sys.executable,
+        '-c', code,
     ]
-    kwargs = dict()
+    kwargs = {}
     if platform.system() == 'Windows':
         # without this, tests hang on windows forever
         kwargs['creationflags'] = subprocess.CREATE_NEW_PROCESS_GROUP
 
     proc = testdir.popen(
-        cmdargs,
+        cmd,
         stdout=subprocess.PIPE,
         stderr=subprocess.PIPE,
         **kwargs,

tests/devx/conftest.py

@@ -0,0 +1,168 @@
+'''
+`tractor.devx.*` tooling sub-pkg test space.
+
+'''
+from typing import (
+    Callable,
+)
+
+import pytest
+from pexpect.exceptions import (
+    TIMEOUT,
+)
+from pexpect.spawnbase import SpawnBase
+from tractor._testing import (
+    mk_cmd,
+)
+
+
+@pytest.fixture
+def spawn(
+    start_method,
+    testdir: pytest.Testdir,
+    reg_addr: tuple[str, int],
+
+) -> Callable[[str], None]:
+    '''
+    Use the `pexpect` module shipped via `testdir.spawn()` to
+    run an `./examples/..` script by name.
+
+    '''
+    if start_method != 'trio':
+        pytest.skip(
+            '`pexpect` based tests only supported on `trio` backend'
+        )
+
+    def _spawn(
+        cmd: str,
+        **mkcmd_kwargs,
+    ):
+        return testdir.spawn(
+            cmd=mk_cmd(
+                cmd,
+                **mkcmd_kwargs,
+            ),
+            expect_timeout=3,
+        )
+
+    # such that test-dep can pass input script name.
+    return _spawn
+
+
+@pytest.fixture(
+    params=[False, True],
+    ids='ctl-c={}'.format,
+)
+def ctlc(
+    request,
+    ci_env: bool,
+
+) -> bool:
+
+    use_ctlc = request.param
+
+    node = request.node
+    markers = node.own_markers
+    for mark in markers:
+        if mark.name == 'has_nested_actors':
+            pytest.skip(
+                f'Test {node} has nested actors and fails with Ctrl-C.\n'
+                f'The test can sometimes run fine locally but until'
+                ' we solve' 'this issue this CI test will be xfail:\n'
+                'https://github.com/goodboy/tractor/issues/320'
+            )
+
+    if use_ctlc:
+        # XXX: disable pygments highlighting for auto-tests
+        # since some envs (like actions CI) will struggle
+        # the the added color-char encoding..
+        from tractor.devx._debug import TractorConfig
+        TractorConfig.use_pygements = False
+
+    yield use_ctlc
+
+
+def expect(
+    child,
+
+    # normally a `pdb` prompt by default
+    patt: str,
+
+    **kwargs,
+
+) -> None:
+    '''
+    Expect wrapper that prints last seen console
+    data before failing.
+
+    '''
+    try:
+        child.expect(
+            patt,
+            **kwargs,
+        )
+    except TIMEOUT:
+        before = str(child.before.decode())
+        print(before)
+        raise
+
+
+def in_prompt_msg(
+    child: SpawnBase,
+    parts: list[str],
+
+    pause_on_false: bool = False,
+    err_on_false: bool = False,
+    print_prompt_on_false: bool = True,
+
+) -> bool:
+    '''
+    Predicate check if (the prompt's) std-streams output has all
+    `str`-parts in it.
+
+    Can be used in test asserts for bulk matching expected
+    log/REPL output for a given `pdb` interact point.
+
+    '''
+    __tracebackhide__: bool = False
+
+    before: str = str(child.before.decode())
+    for part in parts:
+        if part not in before:
+            if pause_on_false:
+                import pdbp
+                pdbp.set_trace()
+
+            if print_prompt_on_false:
+                print(before)
+
+            if err_on_false:
+                raise ValueError(
+                    f'Could not find pattern in `before` output?\n'
+                    f'part: {part!r}\n'
+                )
+            return False
+
+    return True
+
+
+# TODO: todo support terminal color-chars stripping so we can match
+# against call stack frame output from the the 'll' command the like!
+# -[ ] SO answer for stipping ANSI codes: https://stackoverflow.com/a/14693789
+def assert_before(
+    child: SpawnBase,
+    patts: list[str],
+
+    **kwargs,
+
+) -> None:
+    __tracebackhide__: bool = False
+
+    assert in_prompt_msg(
+        child=child,
+        parts=patts,
+
+        # since this is an "assert" helper ;)
+        err_on_false=True,
+        **kwargs
+    )

tests/devx/test_tooling.py

@@ -0,0 +1,120 @@
+'''
+That "native" runtime-hackin toolset better be dang useful!
+
+Verify the funtion of a variety of "developer-experience" tools we
+offer from the `.devx` sub-pkg:
+
+- use of the lovely `stackscope` for dumping actor `trio`-task trees
+  during operation and hangs.
+
+TODO:
+- demonstration of `CallerInfo` call stack frame filtering such that
+  for logging and REPL purposes a user sees exactly the layers needed
+  when debugging a problem inside the stack vs. in their app.
+
+'''
+import os
+import signal
+
+from .conftest import (
+    expect,
+    assert_before,
+    # in_prompt_msg,
+)
+
+
+def test_shield_pause(
+    spawn,
+):
+    '''
+    Verify the `tractor.pause()/.post_mortem()` API works inside an
+    already cancelled `trio.CancelScope` and that you can step to the
+    next checkpoint wherein the cancelled will get raised.
+
+    '''
+    child = spawn(
+        'shield_hang_in_sub'
+    )
+    expect(
+        child,
+        'Yo my child hanging..?',
+    )
+    assert_before(
+        child,
+        [
+            'Entering shield sleep..',
+            'Enabling trace-trees on `SIGUSR1` since `stackscope` is installed @',
+        ]
+    )
+
+    print(
+        'Sending SIGUSR1 to see a tree-trace!',
+    )
+    os.kill(
+        child.pid,
+        signal.SIGUSR1,
+    )
+    expect(
+        child,
+        # end-of-tree delimiter
+        "------ \('root', ",
+    )
+
+    assert_before(
+        child,
+        [
+            'Trying to dump `stackscope` tree..',
+            'Dumping `stackscope` tree for actor',
+            "('root'",  # uid line
+
+            # parent block point (non-shielded)
+            'await trio.sleep_forever()  # in root',
+        ]
+    )
+
+    # expect(
+    #     child,
+    #     # relay to the sub should be reported
+    #     'Relaying `SIGUSR1`[10] to sub-actor',
+    # )
+
+    expect(
+        child,
+        # end-of-tree delimiter
+        "------ \('hanger', ",
+    )
+    assert_before(
+        child,
+        [
+            # relay to the sub should be reported
+            'Relaying `SIGUSR1`[10] to sub-actor',
+
+            "('hanger'",  # uid line
+
+            # hanger LOC where it's shield-halted
+            'await trio.sleep_forever()  # in subactor',
+        ]
+    )
+    # breakpoint()
+
+    # simulate the user sending a ctl-c to the hanging program.
+    # this should result in the terminator kicking in since
+    # the sub is shield blocking and can't respond to SIGINT.
+    os.kill(
+        child.pid,
+        signal.SIGINT,
+    )
+    expect(
+        child,
+        'Shutting down actor runtime',
+        timeout=6,
+    )
+    assert_before(
+        child,
+        [
+            'raise KeyboardInterrupt',
+            # 'Shutting down actor runtime',
+            '#T-800 deployed to collect zombie B0',
+            "'--uid', \"('hanger',",
+        ]
+    )

tests/test_advanced_faults.py

@@ -3,22 +3,30 @@ Sketchy network blackoutz, ugly byzantine gens, puedes eschuchar la
 cancelacion?..
 
 '''
+import itertools
 from functools import partial
+from types import ModuleType
 
 import pytest
 from _pytest.pathlib import import_path
 import trio
 import tractor
-
+from tractor._testing import (
-from conftest import (
     examples_dir,
+    break_ipc,
 )
 
 
 @pytest.mark.parametrize(
-    'debug_mode',
+    'pre_aclose_msgstream',
-    [False, True],
+    [
-    ids=['no_debug_mode', 'debug_mode'],
+        False,
+        True,
+    ],
+    ids=[
+        'no_msgstream_aclose',
+        'pre_aclose_msgstream',
+    ],
 )
 @pytest.mark.parametrize(
     'ipc_break',
@@ -63,8 +71,10 @@ from conftest import (
 )
 def test_ipc_channel_break_during_stream(
     debug_mode: bool,
+    loglevel: str,
     spawn_backend: str,
-    ipc_break: dict | None,
+    ipc_break: dict|None,
+    pre_aclose_msgstream: bool,
 ):
     '''
     Ensure we can have an IPC channel break its connection during
@@ -81,72 +91,152 @@ def test_ipc_channel_break_during_stream(
 
         # non-`trio` spawners should never hit the hang condition that
         # requires the user to do ctl-c to cancel the actor tree.
-        expect_final_exc = trio.ClosedResourceError
+        # expect_final_exc = trio.ClosedResourceError
+        expect_final_exc = tractor.TransportClosed
 
-    mod = import_path(
+    mod: ModuleType = import_path(
-        examples_dir() / 'advanced_faults' / 'ipc_failure_during_stream.py',
+        examples_dir() / 'advanced_faults'
+        / 'ipc_failure_during_stream.py',
         root=examples_dir(),
+        consider_namespace_packages=False,
     )
 
-    expect_final_exc = KeyboardInterrupt
+    # by def we expect KBI from user after a simulated "hang
-
+    # period" wherein the user eventually hits ctl-c to kill the
-    # when ONLY the child breaks we expect the parent to get a closed
+    # root-actor tree.
-    # resource error on the next `MsgStream.receive()` and then fail out
+    expect_final_exc: BaseException = KeyboardInterrupt
-    # and cancel the child from there.
     if (
-
+        # only expect EoC if trans is broken on the child side,
-        # only child breaks
+        ipc_break['break_child_ipc_after'] is not False
-        (
+        # AND we tell the child to call `MsgStream.aclose()`.
-            ipc_break['break_child_ipc_after']
+        and pre_aclose_msgstream
-            and ipc_break['break_parent_ipc_after'] is False
-        )
-
-        # both break but, parent breaks first
-        or (
-            ipc_break['break_child_ipc_after'] is not False
-            and (
-                ipc_break['break_parent_ipc_after']
-                > ipc_break['break_child_ipc_after']
-            )
-        )
-
     ):
-        expect_final_exc = trio.ClosedResourceError
+        # expect_final_exc = trio.EndOfChannel
+        # ^XXX NOPE! XXX^ since now `.open_stream()` absorbs this
+        # gracefully!
+        expect_final_exc = KeyboardInterrupt
 
-    # when the parent IPC side dies (even if the child's does as well
+    # NOTE when ONLY the child breaks or it breaks BEFORE the
-    # but the child fails BEFORE the parent) we expect the channel to be
+    # parent we expect the parent to get a closed resource error
-    # sent a stop msg from the child at some point which will signal the
+    # on the next `MsgStream.receive()` and then fail out and
-    # parent that the stream has been terminated.
+    # cancel the child from there.
-    # NOTE: when the parent breaks "after" the child you get this same
+    #
-    # case as well, the child breaks the IPC channel with a stop msg
+    # ONLY CHILD breaks
-    # before any closure takes place.
+    if (
+        ipc_break['break_child_ipc_after']
+        and
+        ipc_break['break_parent_ipc_after'] is False
+    ):
+        # NOTE: we DO NOT expect this any more since
+        # the child side's channel will be broken silently
+        # and nothing on the parent side will indicate this!
+        # expect_final_exc = trio.ClosedResourceError
+
+        # NOTE: child will send a 'stop' msg before it breaks
+        # the transport channel BUT, that will be absorbed by the
+        # `ctx.open_stream()` block and thus the `.open_context()`
+        # should hang, after which the test script simulates
+        # a user sending ctl-c by raising a KBI.
+        if pre_aclose_msgstream:
+            expect_final_exc = KeyboardInterrupt
+
+            # XXX OLD XXX
+            # if child calls `MsgStream.aclose()` then expect EoC.
+            # ^ XXX not any more ^ since eoc is always absorbed
+            # gracefully and NOT bubbled to the `.open_context()`
+            # block!
+            # expect_final_exc = trio.EndOfChannel
+
+    # BOTH but, CHILD breaks FIRST
     elif (
-        # only parent breaks
+        ipc_break['break_child_ipc_after'] is not False
-        (
+        and (
             ipc_break['break_parent_ipc_after']
-            and ipc_break['break_child_ipc_after'] is False
+            > ipc_break['break_child_ipc_after']
-        )
-
-        # both break but, child breaks first
-        or (
-            ipc_break['break_parent_ipc_after'] is not False
-            and (
-                ipc_break['break_child_ipc_after']
-                > ipc_break['break_parent_ipc_after']
-            )
         )
     ):
-        expect_final_exc = trio.EndOfChannel
+        if pre_aclose_msgstream:
+            expect_final_exc = KeyboardInterrupt
 
-    with pytest.raises(expect_final_exc):
+    # NOTE when the parent IPC side dies (even if the child does as well
-        trio.run(
+    # but the child fails BEFORE the parent) we always expect the
-            partial(
+    # IPC layer to raise a closed-resource, NEVER do we expect
-                mod.main,
+    # a stop msg since the parent-side ctx apis will error out
-                debug_mode=debug_mode,
+    # IMMEDIATELY before the child ever sends any 'stop' msg.
-                start_method=spawn_backend,
+    #
-                **ipc_break,
+    # ONLY PARENT breaks
+    elif (
+        ipc_break['break_parent_ipc_after']
+        and
+        ipc_break['break_child_ipc_after'] is False
+    ):
+        # expect_final_exc = trio.ClosedResourceError
+        expect_final_exc = tractor.TransportClosed
+
+    # BOTH but, PARENT breaks FIRST
+    elif (
+        ipc_break['break_parent_ipc_after'] is not False
+        and (
+            ipc_break['break_child_ipc_after']
+            >
+            ipc_break['break_parent_ipc_after']
+        )
+    ):
+        # expect_final_exc = trio.ClosedResourceError
+        expect_final_exc = tractor.TransportClosed
+
+    with pytest.raises(
+        expected_exception=(
+            expect_final_exc,
+            ExceptionGroup,
+        ),
+    ) as excinfo:
+        try:
+            trio.run(
+                partial(
+                    mod.main,
+                    debug_mode=debug_mode,
+                    start_method=spawn_backend,
+                    loglevel=loglevel,
+                    pre_close=pre_aclose_msgstream,
+                    **ipc_break,
+                )
+            )
+        except KeyboardInterrupt as _kbi:
+            kbi = _kbi
+            if expect_final_exc is not KeyboardInterrupt:
+                pytest.fail(
+                    'Rxed unexpected KBI !?\n'
+                    f'{repr(kbi)}'
+                )
+
+            raise
+
+        except tractor.TransportClosed as _tc:
+            tc = _tc
+            if expect_final_exc is KeyboardInterrupt:
+                pytest.fail(
+                    'Unexpected transport failure !?\n'
+                    f'{repr(tc)}'
+                )
+            cause: Exception = tc.__cause__
+            assert (
+                type(cause) is trio.ClosedResourceError
+                and
+                cause.args[0] == 'another task closed this fd'
+            )
+            raise
+
+    # get raw instance from pytest wrapper
+    value = excinfo.value
+    if isinstance(value, ExceptionGroup):
+        value = next(
+            itertools.dropwhile(
+                lambda exc: not isinstance(exc, expect_final_exc),
+                value.exceptions,
             )
         )
+        assert value
 
 
 @tractor.context
@@ -155,9 +245,15 @@ async def break_ipc_after_started(
 ) -> None:
     await ctx.started()
     async with ctx.open_stream() as stream:
-        await stream.aclose()
+
-        await trio.sleep(0.2)
+        # TODO: make a test which verifies the error
-        await ctx.chan.send(None)
+        # for this, i.e. raises a `MsgTypeError`
+        # await ctx.chan.send(None)
+
+        await break_ipc(
+            stream=stream,
+            pre_close=True,
+        )
         print('child broke IPC and terminating')
 
 
@@ -169,25 +265,29 @@ def test_stream_closed_right_after_ipc_break_and_zombie_lord_engages():
 
     '''
     async def main():
-        async with tractor.open_nursery() as n:
+        with trio.fail_after(3):
-            portal = await n.start_actor(
+            async with tractor.open_nursery() as n:
-                'ipc_breaker',
+                portal = await n.start_actor(
-                enable_modules=[__name__],
+                    'ipc_breaker',
-            )
+                    enable_modules=[__name__],
+                )
 
-            with trio.move_on_after(1):
+                with trio.move_on_after(1):
-                async with (
+                    async with (
-                    portal.open_context(
+                        portal.open_context(
-                        break_ipc_after_started
+                            break_ipc_after_started
-                    ) as (ctx, sent),
+                        ) as (ctx, sent),
-                ):
+                    ):
-                    async with ctx.open_stream():
+                        async with ctx.open_stream():
-                        await trio.sleep(0.5)
+                            await trio.sleep(0.5)
 
-                    print('parent waiting on context')
+                        print('parent waiting on context')
 
-            print('parent exited context')
+                print(
-            raise KeyboardInterrupt
+                    'parent exited context\n'
+                    'parent raising KBI..\n'
+                )
+                raise KeyboardInterrupt
 
     with pytest.raises(KeyboardInterrupt):
         trio.run(main)

tests/test_advanced_streaming.py

@@ -6,6 +6,7 @@ from collections import Counter
 import itertools
 import platform
 
+import pytest
 import trio
 import tractor
 
@@ -143,8 +144,16 @@ def test_dynamic_pub_sub():
 
     try:
         trio.run(main)
-    except trio.TooSlowError:
+    except (
-        pass
+        trio.TooSlowError,
+        ExceptionGroup,
+    ) as err:
+        if isinstance(err, ExceptionGroup):
+            for suberr in err.exceptions:
+                if isinstance(suberr, trio.TooSlowError):
+                    break
+            else:
+                pytest.fail('Never got a `TooSlowError` ?')
 
 
 @tractor.context
@@ -298,44 +307,69 @@ async def inf_streamer(
 
     async with (
         ctx.open_stream() as stream,
-        trio.open_nursery() as n,
+        trio.open_nursery() as tn,
     ):
-        async def bail_on_sentinel():
+        async def close_stream_on_sentinel():
             async for msg in stream:
                 if msg == 'done':
+                    print(
+                        'streamer RXed "done" sentinel msg!\n'
+                        'CLOSING `MsgStream`!'
+                    )
                     await stream.aclose()
                 else:
                     print(f'streamer received {msg}')
+            else:
+                print('streamer exited recv loop')
 
         # start termination detector
-        n.start_soon(bail_on_sentinel)
+        tn.start_soon(close_stream_on_sentinel)
 
-        for val in itertools.count():
+        cap: int = 10000  # so that we don't spin forever when bug..
+        for val in range(cap):
             try:
+                print(f'streamer sending {val}')
                 await stream.send(val)
+                if val > cap:
+                    raise RuntimeError(
+                        'Streamer never cancelled by setinel?'
+                    )
+                await trio.sleep(0.001)
+
+            # close out the stream gracefully
             except trio.ClosedResourceError:
-                # close out the stream gracefully
+                print('transport closed on streamer side!')
+                assert stream.closed
                 break
+        else:
+            raise RuntimeError(
+                'Streamer not cancelled before finished sending?'
+            )
 
-    print('terminating streamer')
+    print('streamer exited .open_streamer() block')
 
 
-def test_local_task_fanout_from_stream():
+def test_local_task_fanout_from_stream(
+    debug_mode: bool,
+):
     '''
     Single stream with multiple local consumer tasks using the
     ``MsgStream.subscribe()` api.
 
-    Ensure all tasks receive all values after stream completes sending.
+    Ensure all tasks receive all values after stream completes
+    sending.
 
     '''
-    consumers = 22
+    consumers: int = 22
 
     async def main():
 
         counts = Counter()
 
-        async with tractor.open_nursery() as tn:
+        async with tractor.open_nursery(
-            p = await tn.start_actor(
+            debug_mode=debug_mode,
+        ) as tn:
+            p: tractor.Portal = await tn.start_actor(
                 'inf_streamer',
                 enable_modules=[__name__],
             )
@@ -343,7 +377,6 @@ def test_local_task_fanout_from_stream():
                 p.open_context(inf_streamer) as (ctx, _),
                 ctx.open_stream() as stream,
             ):
-
                 async def pull_and_count(name: str):
                     # name = trio.lowlevel.current_task().name
                     async with stream.subscribe() as recver:
@@ -352,7 +385,7 @@ def test_local_task_fanout_from_stream():
                             tractor.trionics.BroadcastReceiver
                         )
                         async for val in recver:
-                            # print(f'{name}: {val}')
+                            print(f'bx {name} rx: {val}')
                             counts[name] += 1
 
                         print(f'{name} bcaster ended')
@@ -362,10 +395,14 @@ def test_local_task_fanout_from_stream():
                 with trio.fail_after(3):
                     async with trio.open_nursery() as nurse:
                         for i in range(consumers):
-                            nurse.start_soon(pull_and_count, i)
+                            nurse.start_soon(
+                                pull_and_count,
+                                i,
+                            )
 
+                        # delay to let bcast consumers pull msgs
                         await trio.sleep(0.5)
-                        print('\nterminating')
+                        print('terminating nursery of bcast rxer consumers!')
                         await stream.send('done')
 
             print('closed stream connection')

tests/test_cancellation.py

@@ -8,15 +8,13 @@ import platform
 import time
 from itertools import repeat
 
-from exceptiongroup import (
-    BaseExceptionGroup,
-    ExceptionGroup,
-)
 import pytest
 import trio
 import tractor
-
+from tractor._testing import (
-from conftest import tractor_test, no_windows
+    tractor_test,
+)
+from conftest import no_windows
 
 
 def is_win():
@@ -47,17 +45,19 @@ async def do_nuthin():
     ],
     ids=['no_args', 'unexpected_args'],
 )
-def test_remote_error(arb_addr, args_err):
+def test_remote_error(reg_addr, args_err):
-    """Verify an error raised in a subactor that is propagated
+    '''
+    Verify an error raised in a subactor that is propagated
     to the parent nursery, contains the underlying boxed builtin
     error type info and causes cancellation and reraising all the
     way up the stack.
-    """
+
+    '''
     args, errtype = args_err
 
     async def main():
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
         ) as nursery:
 
             # on a remote type error caused by bad input args
@@ -65,7 +65,9 @@ def test_remote_error(arb_addr, args_err):
             # an exception group outside the nursery since the error
             # here and the far end task error are one in the same?
             portal = await nursery.run_in_actor(
-                assert_err, name='errorer', **args
+                assert_err,
+                name='errorer',
+                **args
             )
 
             # get result(s) from main task
@@ -75,7 +77,7 @@ def test_remote_error(arb_addr, args_err):
                 # of this actor nursery.
                 await portal.result()
             except tractor.RemoteActorError as err:
-                assert err.type == errtype
+                assert err.boxed_type == errtype
                 print("Look Maa that actor failed hard, hehh")
                 raise
 
@@ -84,20 +86,33 @@ def test_remote_error(arb_addr, args_err):
         with pytest.raises(tractor.RemoteActorError) as excinfo:
             trio.run(main)
 
-        assert excinfo.value.type == errtype
+        assert excinfo.value.boxed_type == errtype
 
     else:
-        # the root task will also error on the `.result()` call
+        # the root task will also error on the `Portal.result()`
-        # so we expect an error from there AND the child.
+        # call so we expect an error from there AND the child.
-        with pytest.raises(BaseExceptionGroup) as excinfo:
+        # |_ tho seems like on new `trio` this doesn't always
+        #    happen?
+        with pytest.raises((
+            BaseExceptionGroup,
+            tractor.RemoteActorError,
+        )) as excinfo:
             trio.run(main)
 
-        # ensure boxed errors
+        # ensure boxed errors are `errtype`
-        for exc in excinfo.value.exceptions:
+        err: BaseException = excinfo.value
-            assert exc.type == errtype
+        if isinstance(err, BaseExceptionGroup):
+            suberrs: list[BaseException] = err.exceptions
+        else:
+            suberrs: list[BaseException] = [err]
+
+        for exc in suberrs:
+            assert exc.boxed_type == errtype
 
 
-def test_multierror(arb_addr):
+def test_multierror(
+    reg_addr: tuple[str, int],
+):
     '''
     Verify we raise a ``BaseExceptionGroup`` out of a nursery where
     more then one actor errors.
@@ -105,7 +120,7 @@ def test_multierror(arb_addr):
     '''
     async def main():
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
         ) as nursery:
 
             await nursery.run_in_actor(assert_err, name='errorer1')
@@ -115,7 +130,7 @@ def test_multierror(arb_addr):
             try:
                 await portal2.result()
             except tractor.RemoteActorError as err:
-                assert err.type == AssertionError
+                assert err.boxed_type == AssertionError
                 print("Look Maa that first actor failed hard, hehh")
                 raise
 
@@ -130,14 +145,14 @@ def test_multierror(arb_addr):
 @pytest.mark.parametrize(
     'num_subactors', range(25, 26),
 )
-def test_multierror_fast_nursery(arb_addr, start_method, num_subactors, delay):
+def test_multierror_fast_nursery(reg_addr, start_method, num_subactors, delay):
     """Verify we raise a ``BaseExceptionGroup`` out of a nursery where
     more then one actor errors and also with a delay before failure
     to test failure during an ongoing spawning.
     """
     async def main():
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
         ) as nursery:
 
             for i in range(num_subactors):
@@ -167,7 +182,7 @@ def test_multierror_fast_nursery(arb_addr, start_method, num_subactors, delay):
 
     for exc in exceptions:
         assert isinstance(exc, tractor.RemoteActorError)
-        assert exc.type == AssertionError
+        assert exc.boxed_type == AssertionError
 
 
 async def do_nothing():
@@ -175,15 +190,20 @@ async def do_nothing():
 
 
 @pytest.mark.parametrize('mechanism', ['nursery_cancel', KeyboardInterrupt])
-def test_cancel_single_subactor(arb_addr, mechanism):
+def test_cancel_single_subactor(reg_addr, mechanism):
-    """Ensure a ``ActorNursery.start_actor()`` spawned subactor
+    '''
+    Ensure a ``ActorNursery.start_actor()`` spawned subactor
     cancels when the nursery is cancelled.
-    """
+
+    '''
     async def spawn_actor():
-        """Spawn an actor that blocks indefinitely.
+        '''
-        """
+        Spawn an actor that blocks indefinitely then cancel via
+        either `ActorNursery.cancel()` or an exception raise.
+
+        '''
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
         ) as nursery:
 
             portal = await nursery.start_actor(
@@ -303,7 +323,7 @@ async def test_some_cancels_all(num_actors_and_errs, start_method, loglevel):
                         await portal.run(func, **kwargs)
 
                     except tractor.RemoteActorError as err:
-                        assert err.type == err_type
+                        assert err.boxed_type == err_type
                         # we only expect this first error to propogate
                         # (all other daemons are cancelled before they
                         # can be scheduled)
@@ -322,11 +342,11 @@ async def test_some_cancels_all(num_actors_and_errs, start_method, loglevel):
             assert len(err.exceptions) == num_actors
             for exc in err.exceptions:
                 if isinstance(exc, tractor.RemoteActorError):
-                    assert exc.type == err_type
+                    assert exc.boxed_type == err_type
                 else:
                     assert isinstance(exc, trio.Cancelled)
         elif isinstance(err, tractor.RemoteActorError):
-            assert err.type == err_type
+            assert err.boxed_type == err_type
 
         assert n.cancelled is True
         assert not n._children
@@ -405,7 +425,7 @@ async def test_nested_multierrors(loglevel, start_method):
                     elif isinstance(subexc, tractor.RemoteActorError):
                         # on windows it seems we can't exactly be sure wtf
                         # will happen..
-                        assert subexc.type in (
+                        assert subexc.boxed_type in (
                             tractor.RemoteActorError,
                             trio.Cancelled,
                             BaseExceptionGroup,
@@ -415,7 +435,7 @@ async def test_nested_multierrors(loglevel, start_method):
                         for subsub in subexc.exceptions:
 
                             if subsub in (tractor.RemoteActorError,):
-                                subsub = subsub.type
+                                subsub = subsub.boxed_type
 
                             assert type(subsub) in (
                                 trio.Cancelled,
@@ -430,16 +450,16 @@ async def test_nested_multierrors(loglevel, start_method):
                     # we get back the (sent) cancel signal instead
                     if is_win():
                         if isinstance(subexc, tractor.RemoteActorError):
-                            assert subexc.type in (
+                            assert subexc.boxed_type in (
                                 BaseExceptionGroup,
                                 tractor.RemoteActorError
                             )
                         else:
                             assert isinstance(subexc, BaseExceptionGroup)
                     else:
-                        assert subexc.type is ExceptionGroup
+                        assert subexc.boxed_type is ExceptionGroup
                 else:
-                    assert subexc.type in (
+                    assert subexc.boxed_type in (
                         tractor.RemoteActorError,
                         trio.Cancelled
                     )

tests/test_caps_based_msging.py

@@ -0,0 +1,917 @@
+'''
+Low-level functional audits for our
+"capability based messaging"-spec feats.
+
+B~)
+
+'''
+import typing
+from typing import (
+    Any,
+    Type,
+    Union,
+)
+
+from msgspec import (
+    structs,
+    msgpack,
+    Struct,
+    ValidationError,
+)
+import pytest
+
+import tractor
+from tractor import (
+    _state,
+    MsgTypeError,
+    Context,
+)
+from tractor.msg import (
+    _codec,
+    _ctxvar_MsgCodec,
+
+    NamespacePath,
+    MsgCodec,
+    mk_codec,
+    apply_codec,
+    current_codec,
+)
+from tractor.msg.types import (
+    _payload_msgs,
+    log,
+    PayloadMsg,
+    Started,
+    mk_msg_spec,
+)
+import trio
+
+
+def mk_custom_codec(
+    pld_spec: Union[Type]|Any,
+    add_hooks: bool,
+
+) -> MsgCodec:
+    '''
+    Create custom `msgpack` enc/dec-hooks and set a `Decoder`
+    which only loads `pld_spec` (like `NamespacePath`) types.
+
+    '''
+    uid: tuple[str, str] = tractor.current_actor().uid
+
+    # XXX NOTE XXX: despite defining `NamespacePath` as a type
+    # field on our `PayloadMsg.pld`, we still need a enc/dec_hook() pair
+    # to cast to/from that type on the wire. See the docs:
+    # https://jcristharif.com/msgspec/extending.html#mapping-to-from-native-types
+
+    def enc_nsp(obj: Any) -> Any:
+        print(f'{uid} ENC HOOK')
+        match obj:
+            case NamespacePath():
+                print(
+                    f'{uid}: `NamespacePath`-Only ENCODE?\n'
+                    f'obj-> `{obj}`: {type(obj)}\n'
+                )
+                # if type(obj) != NamespacePath:
+                #     breakpoint()
+                return str(obj)
+
+        print(
+            f'{uid}\n'
+            'CUSTOM ENCODE\n'
+            f'obj-arg-> `{obj}`: {type(obj)}\n'
+        )
+        logmsg: str = (
+            f'{uid}\n'
+            'FAILED ENCODE\n'
+            f'obj-> `{obj}: {type(obj)}`\n'
+        )
+        raise NotImplementedError(logmsg)
+
+    def dec_nsp(
+        obj_type: Type,
+        obj: Any,
+
+    ) -> Any:
+        print(
+            f'{uid}\n'
+            'CUSTOM DECODE\n'
+            f'type-arg-> {obj_type}\n'
+            f'obj-arg-> `{obj}`: {type(obj)}\n'
+        )
+        nsp = None
+
+        if (
+            obj_type is NamespacePath
+            and isinstance(obj, str)
+            and ':' in obj
+        ):
+            nsp = NamespacePath(obj)
+            # TODO: we could built a generic handler using
+            # JUST matching the obj_type part?
+            # nsp = obj_type(obj)
+
+        if nsp:
+            print(f'Returning NSP instance: {nsp}')
+            return nsp
+
+        logmsg: str = (
+            f'{uid}\n'
+            'FAILED DECODE\n'
+            f'type-> {obj_type}\n'
+            f'obj-arg-> `{obj}`: {type(obj)}\n\n'
+            f'current codec:\n'
+            f'{current_codec()}\n'
+        )
+        # TODO: figure out the ignore subsys for this!
+        # -[ ] option whether to defense-relay backc the msg
+        #   inside an `Invalid`/`Ignore`
+        # -[ ] how to make this handling pluggable such that a
+        #   `Channel`/`MsgTransport` can intercept and process
+        #   back msgs either via exception handling or some other
+        #   signal?
+        log.warning(logmsg)
+        # NOTE: this delivers the invalid
+        # value up to `msgspec`'s decoding
+        # machinery for error raising.
+        return obj
+        # raise NotImplementedError(logmsg)
+
+    nsp_codec: MsgCodec = mk_codec(
+        ipc_pld_spec=pld_spec,
+
+        # NOTE XXX: the encode hook MUST be used no matter what since
+        # our `NamespacePath` is not any of a `Any` native type nor
+        # a `msgspec.Struct` subtype - so `msgspec` has no way to know
+        # how to encode it unless we provide the custom hook.
+        #
+        # AGAIN that is, regardless of whether we spec an
+        # `Any`-decoded-pld the enc has no knowledge (by default)
+        # how to enc `NamespacePath` (nsp), so we add a custom
+        # hook to do that ALWAYS.
+        enc_hook=enc_nsp if add_hooks else None,
+
+        # XXX NOTE: pretty sure this is mutex with the `type=` to
+        # `Decoder`? so it won't work in tandem with the
+        # `ipc_pld_spec` passed above?
+        dec_hook=dec_nsp if add_hooks else None,
+    )
+    return nsp_codec
+
+
+def chk_codec_applied(
+    expect_codec: MsgCodec,
+    enter_value: MsgCodec|None = None,
+
+) -> MsgCodec:
+    '''
+    buncha sanity checks ensuring that the IPC channel's
+    context-vars are set to the expected codec and that are
+    ctx-var wrapper APIs match the same.
+
+    '''
+    # TODO: play with tricyle again, bc this is supposed to work
+    # the way we want?
+    #
+    # TreeVar
+    # task: trio.Task = trio.lowlevel.current_task()
+    # curr_codec = _ctxvar_MsgCodec.get_in(task)
+
+    # ContextVar
+    # task_ctx: Context = task.context
+    # assert _ctxvar_MsgCodec in task_ctx
+    # curr_codec: MsgCodec = task.context[_ctxvar_MsgCodec]
+
+    # NOTE: currently we use this!
+    # RunVar
+    curr_codec: MsgCodec = current_codec()
+    last_read_codec = _ctxvar_MsgCodec.get()
+    # assert curr_codec is last_read_codec
+
+    assert (
+        (same_codec := expect_codec) is
+        # returned from `mk_codec()`
+
+        # yielded value from `apply_codec()`
+
+        # read from current task's `contextvars.Context`
+        curr_codec is
+        last_read_codec
+
+        # the default `msgspec` settings
+        is not _codec._def_msgspec_codec
+        is not _codec._def_tractor_codec
+    )
+
+    if enter_value:
+        enter_value is same_codec
+
+
+def iter_maybe_sends(
+    send_items: dict[Union[Type], Any] | list[tuple],
+    ipc_pld_spec: Union[Type] | Any,
+    add_codec_hooks: bool,
+
+    codec: MsgCodec|None = None,
+
+) -> tuple[Any, bool]:
+
+    if isinstance(send_items, dict):
+        send_items = send_items.items()
+
+    for (
+        send_type_spec,
+        send_value,
+    ) in send_items:
+
+        expect_roundtrip: bool = False
+
+        # values-to-typespec santiy
+        send_type = type(send_value)
+        assert send_type == send_type_spec or (
+            (subtypes := getattr(send_type_spec, '__args__', None))
+            and send_type in subtypes
+        )
+
+        spec_subtypes: set[Union[Type]] = (
+             getattr(
+                 ipc_pld_spec,
+                 '__args__',
+                 {ipc_pld_spec,},
+             )
+        )
+        send_in_spec: bool = (
+            send_type == ipc_pld_spec
+            or (
+                ipc_pld_spec != Any
+                and  # presume `Union` of types
+                send_type in spec_subtypes
+            )
+            or (
+                ipc_pld_spec == Any
+                and
+                send_type != NamespacePath
+            )
+        )
+        expect_roundtrip = (
+            send_in_spec
+            # any spec should support all other
+            # builtin py values that we send
+            # except our custom nsp type which
+            # we should be able to send as long
+            # as we provide the custom codec hooks.
+            or (
+                ipc_pld_spec == Any
+                and
+                send_type == NamespacePath
+                and
+                add_codec_hooks
+            )
+        )
+
+        if codec is not None:
+            # XXX FIRST XXX ensure roundtripping works
+            # before touching any IPC primitives/APIs.
+            wire_bytes: bytes = codec.encode(
+                Started(
+                    cid='blahblah',
+                    pld=send_value,
+                )
+            )
+            # NOTE: demonstrates the decoder loading
+            # to via our native SCIPP msg-spec
+            # (structurred-conc-inter-proc-protocol)
+            # implemented as per,
+            try:
+                msg: Started = codec.decode(wire_bytes)
+                if not expect_roundtrip:
+                    pytest.fail(
+                        f'NOT-EXPECTED able to roundtrip value given spec:\n'
+                        f'ipc_pld_spec -> {ipc_pld_spec}\n'
+                        f'value -> {send_value}: {send_type}\n'
+                    )
+
+                pld = msg.pld
+                assert pld == send_value
+
+            except ValidationError:
+                if expect_roundtrip:
+                    pytest.fail(
+                        f'EXPECTED to roundtrip value given spec:\n'
+                        f'ipc_pld_spec -> {ipc_pld_spec}\n'
+                        f'value -> {send_value}: {send_type}\n'
+                    )
+
+        yield (
+            str(send_type),
+            send_value,
+            expect_roundtrip,
+        )
+
+
+def dec_type_union(
+    type_names: list[str],
+) -> Type:
+    '''
+    Look up types by name, compile into a list and then create and
+    return a `typing.Union` from the full set.
+
+    '''
+    import importlib
+    types: list[Type] = []
+    for type_name in type_names:
+        for mod in [
+            typing,
+            importlib.import_module(__name__),
+        ]:
+            if type_ref := getattr(
+                mod,
+                type_name,
+                False,
+            ):
+                types.append(type_ref)
+
+    # special case handling only..
+    # ipc_pld_spec: Union[Type] = eval(
+    #     pld_spec_str,
+    #     {},  # globals
+    #     {'typing': typing},  # locals
+    # )
+
+    return Union[*types]
+
+
+def enc_type_union(
+    union_or_type: Union[Type]|Type,
+) -> list[str]:
+    '''
+    Encode a type-union or single type to a list of type-name-strings
+    ready for IPC interchange.
+
+    '''
+    type_strs: list[str] = []
+    for typ in getattr(
+        union_or_type,
+        '__args__',
+        {union_or_type,},
+    ):
+        type_strs.append(typ.__qualname__)
+
+    return type_strs
+
+
+@tractor.context
+async def send_back_values(
+    ctx: Context,
+    expect_debug: bool,
+    pld_spec_type_strs: list[str],
+    add_hooks: bool,
+    started_msg_bytes: bytes,
+    expect_ipc_send: dict[str, tuple[Any, bool]],
+
+) -> None:
+    '''
+    Setup up a custom codec to load instances of `NamespacePath`
+    and ensure we can round trip a func ref with our parent.
+
+    '''
+    uid: tuple = tractor.current_actor().uid
+
+    # debug mode sanity check (prolly superfluous but, meh)
+    assert expect_debug == _state.debug_mode()
+
+    # init state in sub-actor should be default
+    chk_codec_applied(
+        expect_codec=_codec._def_tractor_codec,
+    )
+
+    # load pld spec from input str
+    ipc_pld_spec = dec_type_union(
+        pld_spec_type_strs,
+    )
+    pld_spec_str = str(ipc_pld_spec)
+
+    # same as on parent side config.
+    nsp_codec: MsgCodec = mk_custom_codec(
+        pld_spec=ipc_pld_spec,
+        add_hooks=add_hooks,
+    )
+    with (
+        apply_codec(nsp_codec) as codec,
+    ):
+        chk_codec_applied(
+            expect_codec=nsp_codec,
+            enter_value=codec,
+        )
+
+        print(
+            f'{uid}: attempting `Started`-bytes DECODE..\n'
+        )
+        try:
+            msg: Started = nsp_codec.decode(started_msg_bytes)
+            expected_pld_spec_str: str = msg.pld
+            assert pld_spec_str == expected_pld_spec_str
+
+        # TODO: maybe we should add our own wrapper error so as to
+        # be interchange-lib agnostic?
+        # -[ ] the error type is wtv is raised from the hook so we
+        #   could also require a type-class of errors for
+        #   indicating whether the hook-failure can be handled by
+        #   a nasty-dialog-unprot sub-sys?
+        except ValidationError:
+
+            # NOTE: only in the `Any` spec case do we expect this to
+            # work since otherwise no spec covers a plain-ol'
+            # `.pld: str`
+            if pld_spec_str == 'Any':
+                raise
+            else:
+                print(
+                    f'{uid}: (correctly) unable to DECODE `Started`-bytes\n'
+                    f'{started_msg_bytes}\n'
+                )
+
+        iter_send_val_items = iter(expect_ipc_send.values())
+        sent: list[Any] = []
+        for send_value, expect_send in iter_send_val_items:
+            try:
+                print(
+                    f'{uid}: attempting to `.started({send_value})`\n'
+                    f'=> expect_send: {expect_send}\n'
+                    f'SINCE, ipc_pld_spec: {ipc_pld_spec}\n'
+                    f'AND, codec: {codec}\n'
+                )
+                await ctx.started(send_value)
+                sent.append(send_value)
+                if not expect_send:
+
+                    # XXX NOTE XXX THIS WON'T WORK WITHOUT SPECIAL
+                    # `str` handling! or special debug mode IPC
+                    # msgs!
+                    await tractor.pause()
+
+                    raise RuntimeError(
+                        f'NOT-EXPECTED able to roundtrip value given spec:\n'
+                        f'ipc_pld_spec -> {ipc_pld_spec}\n'
+                        f'value -> {send_value}: {type(send_value)}\n'
+                    )
+
+                break  # move on to streaming block..
+
+            except tractor.MsgTypeError:
+                await tractor.pause()
+
+                if expect_send:
+                    raise RuntimeError(
+                        f'EXPECTED to `.started()` value given spec:\n'
+                        f'ipc_pld_spec -> {ipc_pld_spec}\n'
+                        f'value -> {send_value}: {type(send_value)}\n'
+                    )
+
+        async with ctx.open_stream() as ipc:
+            print(
+                f'{uid}: Entering streaming block to send remaining values..'
+            )
+
+            for send_value, expect_send in iter_send_val_items:
+                send_type: Type = type(send_value)
+                print(
+                    '------ - ------\n'
+                    f'{uid}: SENDING NEXT VALUE\n'
+                    f'ipc_pld_spec: {ipc_pld_spec}\n'
+                    f'expect_send: {expect_send}\n'
+                    f'val: {send_value}\n'
+                    '------ - ------\n'
+                )
+                try:
+                    await ipc.send(send_value)
+                    print(f'***\n{uid}-CHILD sent {send_value!r}\n***\n')
+                    sent.append(send_value)
+
+                    # NOTE: should only raise above on
+                    # `.started()` or a `Return`
+                    # if not expect_send:
+                    #     raise RuntimeError(
+                    #         f'NOT-EXPECTED able to roundtrip value given spec:\n'
+                    #         f'ipc_pld_spec -> {ipc_pld_spec}\n'
+                    #         f'value -> {send_value}: {send_type}\n'
+                    #     )
+
+                except ValidationError:
+                    print(f'{uid} FAILED TO SEND {send_value}!')
+
+                    # await tractor.pause()
+                    if expect_send:
+                        raise RuntimeError(
+                            f'EXPECTED to roundtrip value given spec:\n'
+                            f'ipc_pld_spec -> {ipc_pld_spec}\n'
+                            f'value -> {send_value}: {send_type}\n'
+                        )
+                    # continue
+
+            else:
+                print(
+                    f'{uid}: finished sending all values\n'
+                    'Should be exiting stream block!\n'
+                )
+
+        print(f'{uid}: exited streaming block!')
+
+        # TODO: this won't be true bc in streaming phase we DO NOT
+        # msgspec check outbound msgs!
+        # -[ ] once we implement the receiver side `InvalidMsg`
+        #   then we can expect it here?
+        # assert (
+        #     len(sent)
+        #     ==
+        #     len([val
+        #          for val, expect in
+        #          expect_ipc_send.values()
+        #          if expect is True])
+        # )
+
+
+def ex_func(*args):
+    print(f'ex_func({args})')
+
+
+@pytest.mark.parametrize(
+    'ipc_pld_spec',
+    [
+        Any,
+        NamespacePath,
+        NamespacePath|None,  # the "maybe" spec Bo
+    ],
+    ids=[
+        'any_type',
+        'nsp_type',
+        'maybe_nsp_type',
+    ]
+)
+@pytest.mark.parametrize(
+    'add_codec_hooks',
+    [
+        True,
+        False,
+    ],
+    ids=['use_codec_hooks', 'no_codec_hooks'],
+)
+def test_codec_hooks_mod(
+    debug_mode: bool,
+    ipc_pld_spec: Union[Type]|Any,
+    # send_value: None|str|NamespacePath,
+    add_codec_hooks: bool,
+):
+    '''
+    Audit the `.msg.MsgCodec` override apis details given our impl
+    uses `contextvars` to accomplish per `trio` task codec
+    application around an inter-proc-task-comms context.
+
+    '''
+    async def main():
+        nsp = NamespacePath.from_ref(ex_func)
+        send_items: dict[Union, Any] = {
+            Union[None]: None,
+            Union[NamespacePath]: nsp,
+            Union[str]: str(nsp),
+        }
+
+        # init default state for actor
+        chk_codec_applied(
+            expect_codec=_codec._def_tractor_codec,
+        )
+
+        async with tractor.open_nursery(
+            debug_mode=debug_mode,
+        ) as an:
+            p: tractor.Portal = await an.start_actor(
+                'sub',
+                enable_modules=[__name__],
+            )
+
+            # TODO: 2 cases:
+            # - codec not modified -> decode nsp as `str`
+            # - codec modified with hooks -> decode nsp as
+            #   `NamespacePath`
+            nsp_codec: MsgCodec = mk_custom_codec(
+                pld_spec=ipc_pld_spec,
+                add_hooks=add_codec_hooks,
+            )
+            with apply_codec(nsp_codec) as codec:
+                chk_codec_applied(
+                    expect_codec=nsp_codec,
+                    enter_value=codec,
+                )
+
+                expect_ipc_send: dict[str, tuple[Any, bool]] = {}
+
+                report: str = (
+                    'Parent report on send values with\n'
+                    f'ipc_pld_spec: {ipc_pld_spec}\n'
+                    '       ------ - ------\n'
+                )
+                for val_type_str, val, expect_send in iter_maybe_sends(
+                    send_items,
+                    ipc_pld_spec,
+                    add_codec_hooks=add_codec_hooks,
+                ):
+                    report += (
+                        f'send_value: {val}: {type(val)} '
+                        f'=> expect_send: {expect_send}\n'
+                    )
+                    expect_ipc_send[val_type_str] = (val, expect_send)
+
+                print(
+                    report +
+                    '       ------ - ------\n'
+                )
+                assert len(expect_ipc_send) == len(send_items)
+                # now try over real IPC with a the subactor
+                # expect_ipc_rountrip: bool = True
+                expected_started = Started(
+                    cid='cid',
+                    pld=str(ipc_pld_spec),
+                )
+                # build list of values we expect to receive from
+                # the subactor.
+                expect_to_send: list[Any] = [
+                    val
+                    for val, expect_send in expect_ipc_send.values()
+                    if expect_send
+                ]
+
+                pld_spec_type_strs: list[str] = enc_type_union(ipc_pld_spec)
+
+                # XXX should raise an mte (`MsgTypeError`)
+                # when `add_codec_hooks == False` bc the input
+                # `expect_ipc_send` kwarg has a nsp which can't be
+                # serialized!
+                #
+                # TODO:can we ensure this happens from the
+                # `Return`-side (aka the sub) as well?
+                if not add_codec_hooks:
+                    try:
+                        async with p.open_context(
+                            send_back_values,
+                            expect_debug=debug_mode,
+                            pld_spec_type_strs=pld_spec_type_strs,
+                            add_hooks=add_codec_hooks,
+                            started_msg_bytes=nsp_codec.encode(expected_started),
+
+                            # XXX NOTE bc we send a `NamespacePath` in this kwarg
+                            expect_ipc_send=expect_ipc_send,
+
+                        ) as (ctx, first):
+                            pytest.fail('ctx should fail to open without custom enc_hook!?')
+
+                    # this test passes bc we can go no further!
+                    except MsgTypeError:
+                        # teardown nursery
+                        await p.cancel_actor()
+                        return
+
+                # TODO: send the original nsp here and
+                # test with `limit_msg_spec()` above?
+                # await tractor.pause()
+                print('PARENT opening IPC ctx!\n')
+                async with (
+
+                    # XXX should raise an mte (`MsgTypeError`)
+                    # when `add_codec_hooks == False`..
+                    p.open_context(
+                        send_back_values,
+                        expect_debug=debug_mode,
+                        pld_spec_type_strs=pld_spec_type_strs,
+                        add_hooks=add_codec_hooks,
+                        started_msg_bytes=nsp_codec.encode(expected_started),
+                        expect_ipc_send=expect_ipc_send,
+                    ) as (ctx, first),
+
+                    ctx.open_stream() as ipc,
+                ):
+                    # ensure codec is still applied across
+                    # `tractor.Context` + its embedded nursery.
+                    chk_codec_applied(
+                        expect_codec=nsp_codec,
+                        enter_value=codec,
+                    )
+                    print(
+                        'root: ENTERING CONTEXT BLOCK\n'
+                        f'type(first): {type(first)}\n'
+                        f'first: {first}\n'
+                    )
+                    expect_to_send.remove(first)
+
+                    # TODO: explicit values we expect depending on
+                    # codec config!
+                    # assert first == first_val
+                    # assert first == f'{__name__}:ex_func'
+
+                    async for next_sent in ipc:
+                        print(
+                            'Parent: child sent next value\n'
+                            f'{next_sent}: {type(next_sent)}\n'
+                        )
+                        if expect_to_send:
+                            expect_to_send.remove(next_sent)
+                        else:
+                            print('PARENT should terminate stream loop + block!')
+
+                    # all sent values should have arrived!
+                    assert not expect_to_send
+
+            await p.cancel_actor()
+
+    trio.run(main)
+
+
+def chk_pld_type(
+    payload_spec: Type[Struct]|Any,
+    pld: Any,
+
+    expect_roundtrip: bool|None = None,
+
+) -> bool:
+
+    pld_val_type: Type = type(pld)
+
+    # TODO: verify that the overridden subtypes
+    # DO NOT have modified type-annots from original!
+    # 'Start',  .pld: FuncSpec
+    # 'StartAck',  .pld: IpcCtxSpec
+    # 'Stop',  .pld: UNSEt
+    # 'Error',  .pld: ErrorData
+
+    codec: MsgCodec = mk_codec(
+        # NOTE: this ONLY accepts `PayloadMsg.pld` fields of a specified
+        # type union.
+        ipc_pld_spec=payload_spec,
+    )
+
+    # make a one-off dec to compare with our `MsgCodec` instance
+    # which does the below `mk_msg_spec()` call internally
+    ipc_msg_spec: Union[Type[Struct]]
+    msg_types: list[PayloadMsg[payload_spec]]
+    (
+        ipc_msg_spec,
+        msg_types,
+    ) = mk_msg_spec(
+        payload_type_union=payload_spec,
+    )
+    _enc = msgpack.Encoder()
+    _dec = msgpack.Decoder(
+        type=ipc_msg_spec or Any,  # like `PayloadMsg[Any]`
+    )
+
+    assert (
+        payload_spec
+        ==
+        codec.pld_spec
+    )
+
+    # assert codec.dec == dec
+    #
+    # ^-XXX-^ not sure why these aren't "equal" but when cast
+    # to `str` they seem to match ?? .. kk
+
+    assert (
+        str(ipc_msg_spec)
+        ==
+        str(codec.msg_spec)
+        ==
+        str(_dec.type)
+        ==
+        str(codec.dec.type)
+    )
+
+    # verify the boxed-type for all variable payload-type msgs.
+    if not msg_types:
+        breakpoint()
+
+    roundtrip: bool|None = None
+    pld_spec_msg_names: list[str] = [
+        td.__name__ for td in _payload_msgs
+    ]
+    for typedef in msg_types:
+
+        skip_runtime_msg: bool = typedef.__name__ not in pld_spec_msg_names
+        if skip_runtime_msg:
+            continue
+
+        pld_field = structs.fields(typedef)[1]
+        assert pld_field.type is payload_spec # TODO-^ does this need to work to get all subtypes to adhere?
+
+        kwargs: dict[str, Any] = {
+            'cid': '666',
+            'pld': pld,
+        }
+        enc_msg: PayloadMsg = typedef(**kwargs)
+
+        _wire_bytes: bytes = _enc.encode(enc_msg)
+        wire_bytes: bytes = codec.enc.encode(enc_msg)
+        assert _wire_bytes == wire_bytes
+
+        ve: ValidationError|None = None
+        try:
+            dec_msg = codec.dec.decode(wire_bytes)
+            _dec_msg = _dec.decode(wire_bytes)
+
+            # decoded msg and thus payload should be exactly same!
+            assert (roundtrip := (
+                _dec_msg
+                ==
+                dec_msg
+                ==
+                enc_msg
+            ))
+
+            if (
+                expect_roundtrip is not None
+                and expect_roundtrip != roundtrip
+            ):
+                breakpoint()
+
+            assert (
+                pld
+                ==
+                dec_msg.pld
+                ==
+                enc_msg.pld
+            )
+            # assert (roundtrip := (_dec_msg == enc_msg))
+
+        except ValidationError as _ve:
+            ve = _ve
+            roundtrip: bool = False
+            if pld_val_type is payload_spec:
+                raise ValueError(
+                   'Got `ValidationError` despite type-var match!?\n'
+                    f'pld_val_type: {pld_val_type}\n'
+                    f'payload_type: {payload_spec}\n'
+                ) from ve
+
+            else:
+                # ow we good cuz the pld spec mismatched.
+                print(
+                    'Got expected `ValidationError` since,\n'
+                    f'{pld_val_type} is not {payload_spec}\n'
+                )
+        else:
+            if (
+                payload_spec is not Any
+                and
+                pld_val_type is not payload_spec
+            ):
+                raise ValueError(
+                   'DID NOT `ValidationError` despite expected type match!?\n'
+                    f'pld_val_type: {pld_val_type}\n'
+                    f'payload_type: {payload_spec}\n'
+                )
+
+    # full code decode should always be attempted!
+    if roundtrip is None:
+        breakpoint()
+
+    return roundtrip
+
+
+def test_limit_msgspec():
+
+    async def main():
+        async with tractor.open_root_actor(
+            debug_mode=True
+        ):
+
+            # ensure we can round-trip a boxing `PayloadMsg`
+            assert chk_pld_type(
+                payload_spec=Any,
+                pld=None,
+                expect_roundtrip=True,
+            )
+
+            # verify that a mis-typed payload value won't decode
+            assert not chk_pld_type(
+                payload_spec=int,
+                pld='doggy',
+            )
+
+            # parametrize the boxed `.pld` type as a custom-struct
+            # and ensure that parametrization propagates
+            # to all payload-msg-spec-able subtypes!
+            class CustomPayload(Struct):
+                name: str
+                value: Any
+
+            assert not chk_pld_type(
+                payload_spec=CustomPayload,
+                pld='doggy',
+            )
+
+            assert chk_pld_type(
+                payload_spec=CustomPayload,
+                pld=CustomPayload(name='doggy', value='urmom')
+            )
+
+            # yah, we can `.pause_from_sync()` now!
+            # breakpoint()
+
+    trio.run(main)

tests/test_child_manages_service_nursery.py

@@ -6,14 +6,15 @@ sub-sub-actor daemons.
 '''
 from typing import Optional
 import asyncio
-from contextlib import asynccontextmanager as acm
+from contextlib import (
+    asynccontextmanager as acm,
+    aclosing,
+)
 
 import pytest
 import trio
-from trio_typing import TaskStatus
 import tractor
 from tractor import RemoteActorError
-from async_generator import aclosing
 
 
 async def aio_streamer(
@@ -141,7 +142,7 @@ async def open_actor_local_nursery(
 )
 def test_actor_managed_trio_nursery_task_error_cancels_aio(
     asyncio_mode: bool,
-    arb_addr
+    reg_addr: tuple,
 ):
     '''
     Verify that a ``trio`` nursery created managed in a child actor
@@ -170,4 +171,4 @@ def test_actor_managed_trio_nursery_task_error_cancels_aio(
 
     # verify boxed error
     err = excinfo.value
-    assert isinstance(err.type(), NameError)
+    assert err.boxed_type is NameError

tests/test_clustering.py

@@ -5,9 +5,7 @@ import trio
 import tractor
 from tractor import open_actor_cluster
 from tractor.trionics import gather_contexts
-
+from tractor._testing import tractor_test
-from conftest import tractor_test
-
 
 MESSAGE = 'tractoring at full speed'
 
@@ -49,7 +47,7 @@ async def worker(
     await ctx.started()
 
     async with ctx.open_stream(
-        backpressure=True,
+        allow_overruns=True,
     ) as stream:
 
         # TODO: this with the below assert causes a hang bug?

tests/test_discovery.py

@@ -9,25 +9,24 @@ import itertools
 
 import pytest
 import tractor
+from tractor._testing import tractor_test
 import trio
 
-from conftest import tractor_test
-
 
 @tractor_test
-async def test_reg_then_unreg(arb_addr):
+async def test_reg_then_unreg(reg_addr):
     actor = tractor.current_actor()
     assert actor.is_arbiter
     assert len(actor._registry) == 1  # only self is registered
 
     async with tractor.open_nursery(
-        arbiter_addr=arb_addr,
+        registry_addrs=[reg_addr],
     ) as n:
 
         portal = await n.start_actor('actor', enable_modules=[__name__])
         uid = portal.channel.uid
 
-        async with tractor.get_arbiter(*arb_addr) as aportal:
+        async with tractor.get_registry(*reg_addr) as aportal:
             # this local actor should be the arbiter
             assert actor is aportal.actor
 
@@ -53,15 +52,27 @@ async def hi():
     return the_line.format(tractor.current_actor().name)
 
 
-async def say_hello(other_actor):
+async def say_hello(
+    other_actor: str,
+    reg_addr: tuple[str, int],
+):
     await trio.sleep(1)  # wait for other actor to spawn
-    async with tractor.find_actor(other_actor) as portal:
+    async with tractor.find_actor(
+        other_actor,
+        registry_addrs=[reg_addr],
+    ) as portal:
         assert portal is not None
         return await portal.run(__name__, 'hi')
 
 
-async def say_hello_use_wait(other_actor):
+async def say_hello_use_wait(
-    async with tractor.wait_for_actor(other_actor) as portal:
+    other_actor: str,
+    reg_addr: tuple[str, int],
+):
+    async with tractor.wait_for_actor(
+        other_actor,
+        registry_addr=reg_addr,
+    ) as portal:
         assert portal is not None
         result = await portal.run(__name__, 'hi')
         return result
@@ -69,21 +80,29 @@ async def say_hello_use_wait(other_actor):
 
 @tractor_test
 @pytest.mark.parametrize('func', [say_hello, say_hello_use_wait])
-async def test_trynamic_trio(func, start_method, arb_addr):
+async def test_trynamic_trio(
-    """Main tractor entry point, the "master" process (for now
+    func,
-    acts as the "director").
+    start_method,
-    """
+    reg_addr,
+):
+    '''
+    Root actor acting as the "director" and running one-shot-task-actors
+    for the directed subs.
+
+    '''
     async with tractor.open_nursery() as n:
         print("Alright... Action!")
 
         donny = await n.run_in_actor(
             func,
             other_actor='gretchen',
+            reg_addr=reg_addr,
             name='donny',
         )
         gretchen = await n.run_in_actor(
             func,
             other_actor='donny',
+            reg_addr=reg_addr,
             name='gretchen',
         )
         print(await gretchen.result())
@@ -131,7 +150,7 @@ async def unpack_reg(actor_or_portal):
 
 
 async def spawn_and_check_registry(
-    arb_addr: tuple,
+    reg_addr: tuple,
     use_signal: bool,
     remote_arbiter: bool = False,
     with_streaming: bool = False,
@@ -139,9 +158,9 @@ async def spawn_and_check_registry(
 ) -> None:
 
     async with tractor.open_root_actor(
-        arbiter_addr=arb_addr,
+        registry_addrs=[reg_addr],
     ):
-        async with tractor.get_arbiter(*arb_addr) as portal:
+        async with tractor.get_registry(*reg_addr) as portal:
             # runtime needs to be up to call this
             actor = tractor.current_actor()
 
@@ -213,17 +232,19 @@ async def spawn_and_check_registry(
 def test_subactors_unregister_on_cancel(
     start_method,
     use_signal,
-    arb_addr,
+    reg_addr,
     with_streaming,
 ):
-    """Verify that cancelling a nursery results in all subactors
+    '''
+    Verify that cancelling a nursery results in all subactors
     deregistering themselves with the arbiter.
-    """
+
+    '''
     with pytest.raises(KeyboardInterrupt):
         trio.run(
             partial(
                 spawn_and_check_registry,
-                arb_addr,
+                reg_addr,
                 use_signal,
                 remote_arbiter=False,
                 with_streaming=with_streaming,
@@ -237,7 +258,7 @@ def test_subactors_unregister_on_cancel_remote_daemon(
     daemon,
     start_method,
     use_signal,
-    arb_addr,
+    reg_addr,
     with_streaming,
 ):
     """Verify that cancelling a nursery results in all subactors
@@ -248,7 +269,7 @@ def test_subactors_unregister_on_cancel_remote_daemon(
         trio.run(
             partial(
                 spawn_and_check_registry,
-                arb_addr,
+                reg_addr,
                 use_signal,
                 remote_arbiter=True,
                 with_streaming=with_streaming,
@@ -262,7 +283,7 @@ async def streamer(agen):
 
 
 async def close_chans_before_nursery(
-    arb_addr: tuple,
+    reg_addr: tuple,
     use_signal: bool,
     remote_arbiter: bool = False,
 ) -> None:
@@ -275,9 +296,9 @@ async def close_chans_before_nursery(
         entries_at_end = 1
 
     async with tractor.open_root_actor(
-        arbiter_addr=arb_addr,
+        registry_addrs=[reg_addr],
     ):
-        async with tractor.get_arbiter(*arb_addr) as aportal:
+        async with tractor.get_registry(*reg_addr) as aportal:
             try:
                 get_reg = partial(unpack_reg, aportal)
 
@@ -329,7 +350,7 @@ async def close_chans_before_nursery(
 def test_close_channel_explicit(
     start_method,
     use_signal,
-    arb_addr,
+    reg_addr,
 ):
     """Verify that closing a stream explicitly and killing the actor's
     "root nursery" **before** the containing nursery tears down also
@@ -339,7 +360,7 @@ def test_close_channel_explicit(
         trio.run(
             partial(
                 close_chans_before_nursery,
-                arb_addr,
+                reg_addr,
                 use_signal,
                 remote_arbiter=False,
             ),
@@ -351,7 +372,7 @@ def test_close_channel_explicit_remote_arbiter(
     daemon,
     start_method,
     use_signal,
-    arb_addr,
+    reg_addr,
 ):
     """Verify that closing a stream explicitly and killing the actor's
     "root nursery" **before** the containing nursery tears down also
@@ -361,7 +382,7 @@ def test_close_channel_explicit_remote_arbiter(
         trio.run(
             partial(
                 close_chans_before_nursery,
-                arb_addr,
+                reg_addr,
                 use_signal,
                 remote_arbiter=True,
             ),

tests/test_docs_examples.py

@@ -11,8 +11,7 @@ import platform
 import shutil
 
 import pytest
-
+from tractor._testing import (
-from conftest import (
     examples_dir,
 )
 
@@ -20,8 +19,8 @@ from conftest import (
 @pytest.fixture
 def run_example_in_subproc(
     loglevel: str,
-    testdir,
+    testdir: pytest.Testdir,
-    arb_addr: tuple[str, int],
+    reg_addr: tuple[str, int],
 ):
 
     @contextmanager

tests/test_infected_asyncio.py

@@ -2,21 +2,33 @@
 The hipster way to force SC onto the stdlib's "async": 'infection mode'.
 
 '''
-from typing import Optional, Iterable, Union
 import asyncio
 import builtins
+from contextlib import ExitStack
 import itertools
 import importlib
+import os
+from pathlib import Path
+import signal
+from typing import (
+    Callable,
+    Iterable,
+    Union,
+)
 
-from exceptiongroup import BaseExceptionGroup
 import pytest
 import trio
 import tractor
 from tractor import (
+    current_actor,
+    Actor,
     to_asyncio,
     RemoteActorError,
+    ContextCancelled,
+    _state,
 )
 from tractor.trionics import BroadcastReceiver
+from tractor._testing import expect_ctxc
 
 
 async def sleep_and_err(
@@ -24,8 +36,8 @@ async def sleep_and_err(
 
     # just signature placeholders for compat with
     # ``to_asyncio.open_channel_from()``
-    to_trio: Optional[trio.MemorySendChannel] = None,
+    to_trio: trio.MemorySendChannel|None = None,
-    from_trio: Optional[asyncio.Queue] = None,
+    from_trio: asyncio.Queue|None = None,
 
 ):
     if to_trio:
@@ -35,7 +47,7 @@ async def sleep_and_err(
     assert 0
 
 
-async def sleep_forever():
+async def aio_sleep_forever():
     await asyncio.sleep(float('inf'))
 
 
@@ -43,10 +55,10 @@ async def trio_cancels_single_aio_task():
 
     # spawn an ``asyncio`` task to run a func and return result
     with trio.move_on_after(.2):
-        await tractor.to_asyncio.run_task(sleep_forever)
+        await tractor.to_asyncio.run_task(aio_sleep_forever)
 
 
-def test_trio_cancels_aio_on_actor_side(arb_addr):
+def test_trio_cancels_aio_on_actor_side(reg_addr):
     '''
     Spawn an infected actor that is cancelled by the ``trio`` side
     task using std cancel scope apis.
@@ -54,7 +66,7 @@ def test_trio_cancels_aio_on_actor_side(arb_addr):
     '''
     async def main():
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr
+            registry_addrs=[reg_addr]
         ) as n:
             await n.run_in_actor(
                 trio_cancels_single_aio_task,
@@ -65,14 +77,22 @@ def test_trio_cancels_aio_on_actor_side(arb_addr):
 
 
 async def asyncio_actor(
-
     target: str,
-    expect_err: Optional[Exception] = None
+    expect_err: Exception|None = None
 
 ) -> None:
 
-    assert tractor.current_actor().is_infected_aio()
+    # ensure internal runtime state is consistent
-    target = globals()[target]
+    actor: Actor = tractor.current_actor()
+    assert (
+        actor.is_infected_aio()
+        and
+        actor._infected_aio
+        and
+        _state._runtime_vars['_is_infected_aio']
+    )
+
+    target: Callable = globals()[target]
 
     if '.' in expect_err:
         modpath, _, name = expect_err.rpartition('.')
@@ -93,7 +113,7 @@ async def asyncio_actor(
         raise
 
 
-def test_aio_simple_error(arb_addr):
+def test_aio_simple_error(reg_addr):
     '''
     Verify a simple remote asyncio error propagates back through trio
     to the parent actor.
@@ -102,7 +122,7 @@ def test_aio_simple_error(arb_addr):
     '''
     async def main():
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr
+            registry_addrs=[reg_addr]
         ) as n:
             await n.run_in_actor(
                 asyncio_actor,
@@ -111,15 +131,26 @@ def test_aio_simple_error(arb_addr):
                 infect_asyncio=True,
             )
 
-    with pytest.raises(RemoteActorError) as excinfo:
+    with pytest.raises(
+        expected_exception=(RemoteActorError, ExceptionGroup),
+    ) as excinfo:
         trio.run(main)
 
     err = excinfo.value
+
+    # might get multiple `trio.Cancelled`s as well inside an inception
+    if isinstance(err, ExceptionGroup):
+        err = next(itertools.dropwhile(
+            lambda exc: not isinstance(exc, tractor.RemoteActorError),
+            err.exceptions
+        ))
+        assert err
+
     assert isinstance(err, RemoteActorError)
-    assert err.type == AssertionError
+    assert err.boxed_type is AssertionError
 
 
-def test_tractor_cancels_aio(arb_addr):
+def test_tractor_cancels_aio(reg_addr):
     '''
     Verify we can cancel a spawned asyncio task gracefully.
 
@@ -128,7 +159,7 @@ def test_tractor_cancels_aio(arb_addr):
         async with tractor.open_nursery() as n:
             portal = await n.run_in_actor(
                 asyncio_actor,
-                target='sleep_forever',
+                target='aio_sleep_forever',
                 expect_err='trio.Cancelled',
                 infect_asyncio=True,
             )
@@ -138,7 +169,7 @@ def test_tractor_cancels_aio(arb_addr):
     trio.run(main)
 
 
-def test_trio_cancels_aio(arb_addr):
+def test_trio_cancels_aio(reg_addr):
     '''
     Much like the above test with ``tractor.Portal.cancel_actor()``
     except we just use a standard ``trio`` cancellation api.
@@ -152,7 +183,7 @@ def test_trio_cancels_aio(arb_addr):
             async with tractor.open_nursery() as n:
                 await n.run_in_actor(
                     asyncio_actor,
-                    target='sleep_forever',
+                    target='aio_sleep_forever',
                     expect_err='trio.Cancelled',
                     infect_asyncio=True,
                 )
@@ -183,17 +214,18 @@ async def trio_ctx(
             # spawn another asyncio task for the cuck of it.
             n.start_soon(
                 tractor.to_asyncio.run_task,
-                sleep_forever,
+                aio_sleep_forever,
             )
             await trio.sleep_forever()
 
 
 @pytest.mark.parametrize(
-    'parent_cancels', [False, True],
+    'parent_cancels',
+    ['context', 'actor', False],
     ids='parent_actor_cancels_child={}'.format
 )
 def test_context_spawns_aio_task_that_errors(
-    arb_addr,
+    reg_addr,
     parent_cancels: bool,
 ):
     '''
@@ -213,26 +245,53 @@ def test_context_spawns_aio_task_that_errors(
                     # debug_mode=True,
                     loglevel='cancel',
                 )
-                async with p.open_context(
+                async with (
-                    trio_ctx,
+                    expect_ctxc(
-                ) as (ctx, first):
+                        yay=parent_cancels == 'actor',
+                    ),
+                    p.open_context(
+                        trio_ctx,
+                    ) as (ctx, first),
+                ):
 
                     assert first == 'start'
 
-                    if parent_cancels:
+                    if parent_cancels == 'actor':
                         await p.cancel_actor()
 
-                    await trio.sleep_forever()
+                    elif parent_cancels == 'context':
+                        await ctx.cancel()
 
-    with pytest.raises(RemoteActorError) as excinfo:
+                    else:
-        trio.run(main)
+                        await trio.sleep_forever()
+
+                async with expect_ctxc(
+                    yay=parent_cancels == 'actor',
+                ):
+                    await ctx.result()
+
+                if parent_cancels == 'context':
+                    # to tear down sub-acor
+                    await p.cancel_actor()
+
+        return ctx.outcome
 
-    err = excinfo.value
-    assert isinstance(err, RemoteActorError)
     if parent_cancels:
-        assert err.type == trio.Cancelled
+        # bc the parent made the cancel request,
+        # 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:
-        assert err.type == AssertionError
+        expect = RemoteActorError
+        with pytest.raises(expect) as excinfo:
+            trio.run(main)
+
+        err = excinfo.value
+        assert isinstance(err, expect)
+        assert err.boxed_type is AssertionError
 
 
 async def aio_cancel():
@@ -241,29 +300,53 @@ async def aio_cancel():
 
     '''
     await asyncio.sleep(0.5)
-    task = asyncio.current_task()
 
     # cancel and enter sleep
+    task = asyncio.current_task()
     task.cancel()
-    await sleep_forever()
+    await aio_sleep_forever()
 
 
-def test_aio_cancelled_from_aio_causes_trio_cancelled(arb_addr):
+def test_aio_cancelled_from_aio_causes_trio_cancelled(reg_addr):
+    '''
+    When the `asyncio.Task` cancels itself the `trio` side cshould
+    also cancel and teardown and relay the cancellation cross-process
+    to the caller (parent).
 
+    '''
     async def main():
-        async with tractor.open_nursery() as n:
+
-            await n.run_in_actor(
+        an: tractor.ActorNursery
+        async with tractor.open_nursery() as an:
+            p: tractor.Portal = await an.run_in_actor(
                 asyncio_actor,
                 target='aio_cancel',
                 expect_err='tractor.to_asyncio.AsyncioCancelled',
                 infect_asyncio=True,
             )
+            # NOTE: normally the `an.__aexit__()` waits on the
+            # portal's result but we do it explicitly here
+            # to avoid indent levels.
+            with trio.fail_after(1):
+                await p.wait_for_result()
 
-    with pytest.raises(RemoteActorError) as excinfo:
+    with pytest.raises(
+        expected_exception=(RemoteActorError, ExceptionGroup),
+    ) as excinfo:
         trio.run(main)
 
-    # ensure boxed error is correct
+    # might get multiple `trio.Cancelled`s as well inside an inception
-    assert excinfo.value.type == to_asyncio.AsyncioCancelled
+    err: RemoteActorError|ExceptionGroup = excinfo.value
+    if isinstance(err, ExceptionGroup):
+        err = next(itertools.dropwhile(
+            lambda exc: not isinstance(exc, tractor.RemoteActorError),
+            err.exceptions
+        ))
+        assert err
+
+    # relayed boxed error should be our `trio`-task's
+    # cancel-signal-proxy-equivalent of `asyncio.CancelledError`.
+    assert err.boxed_type == to_asyncio.AsyncioCancelled
 
 
 # TODO: verify open_channel_from will fail on this..
@@ -304,7 +387,6 @@ async def push_from_aio_task(
 
 
 async def stream_from_aio(
-
     exit_early: bool = False,
     raise_err: bool = False,
     aio_raise_err: bool = False,
@@ -385,7 +467,7 @@ async def stream_from_aio(
     'fan_out', [False, True],
     ids='fan_out_w_chan_subscribe={}'.format
 )
-def test_basic_interloop_channel_stream(arb_addr, fan_out):
+def test_basic_interloop_channel_stream(reg_addr, fan_out):
     async def main():
         async with tractor.open_nursery() as n:
             portal = await n.run_in_actor(
@@ -393,13 +475,14 @@ def test_basic_interloop_channel_stream(arb_addr, fan_out):
                 infect_asyncio=True,
                 fan_out=fan_out,
             )
+            # should raise RAE diectly
             await portal.result()
 
     trio.run(main)
 
 
 # TODO: parametrize the above test and avoid the duplication here?
-def test_trio_error_cancels_intertask_chan(arb_addr):
+def test_trio_error_cancels_intertask_chan(reg_addr):
     async def main():
         async with tractor.open_nursery() as n:
             portal = await n.run_in_actor(
@@ -410,15 +493,14 @@ def test_trio_error_cancels_intertask_chan(arb_addr):
             # should trigger remote actor error
             await portal.result()
 
-    with pytest.raises(BaseExceptionGroup) as excinfo:
+    with pytest.raises(RemoteActorError) as excinfo:
         trio.run(main)
 
-    # ensure boxed errors
+    # ensure boxed error type
-    for exc in excinfo.value.exceptions:
+    excinfo.value.boxed_type is Exception
-        assert exc.type == Exception
 
 
-def test_trio_closes_early_and_channel_exits(arb_addr):
+def test_trio_closes_early_and_channel_exits(reg_addr):
     async def main():
         async with tractor.open_nursery() as n:
             portal = await n.run_in_actor(
@@ -426,14 +508,14 @@ def test_trio_closes_early_and_channel_exits(arb_addr):
                 exit_early=True,
                 infect_asyncio=True,
             )
-            # should trigger remote actor error
+            # should raise RAE diectly
             await portal.result()
 
     # should be a quiet exit on a simple channel exit
     trio.run(main)
 
 
-def test_aio_errors_and_channel_propagates_and_closes(arb_addr):
+def test_aio_errors_and_channel_propagates_and_closes(reg_addr):
     async def main():
         async with tractor.open_nursery() as n:
             portal = await n.run_in_actor(
@@ -441,15 +523,17 @@ def test_aio_errors_and_channel_propagates_and_closes(arb_addr):
                 aio_raise_err=True,
                 infect_asyncio=True,
             )
-            # should trigger remote actor error
+            # should trigger RAE directly, not an eg.
             await portal.result()
 
-    with pytest.raises(BaseExceptionGroup) as excinfo:
+    with pytest.raises(
+        # NOTE: bc we directly wait on `Portal.result()` instead
+        # of capturing it inside the `ActorNursery` machinery.
+        expected_exception=RemoteActorError,
+    ) as excinfo:
         trio.run(main)
 
-    # ensure boxed errors
+    excinfo.value.boxed_type is Exception
-    for exc in excinfo.value.exceptions:
-        assert exc.type == Exception
 
 
 @tractor.context
@@ -510,7 +594,7 @@ async def trio_to_aio_echo_server(
     ids='raise_error={}'.format,
 )
 def test_echoserver_detailed_mechanics(
-    arb_addr,
+    reg_addr,
     raise_error_mid_stream,
 ):
 
@@ -550,7 +634,8 @@ def test_echoserver_detailed_mechanics(
                             pass
                         else:
                             pytest.fail(
-                                "stream wasn't stopped after sentinel?!")
+                                'stream not stopped after sentinel ?!'
+                            )
 
             # TODO: the case where this blocks and
             # is cancelled by kbi or out of task cancellation
@@ -562,3 +647,273 @@ def test_echoserver_detailed_mechanics(
 
     else:
         trio.run(main)
+
+
+
+@tractor.context
+async def manage_file(
+    ctx: tractor.Context,
+    tmp_path_str: str,
+    send_sigint_to: str,
+    trio_side_is_shielded: bool = True,
+    bg_aio_task: bool = False,
+):
+    '''
+    Start an `asyncio` task that just sleeps after registering a context
+    with `Actor.lifetime_stack`. Trigger a SIGINT to kill the actor tree
+    and ensure the stack is closed in the infected mode child.
+
+    To verify the teardown state just write a tmpfile to the `testdir`
+    and delete it on actor close.
+
+    '''
+
+    tmp_path: Path = Path(tmp_path_str)
+    tmp_file: Path = tmp_path / f'{" ".join(ctx._actor.uid)}.file'
+
+    # create a the tmp file and tell the parent where it's at
+    assert not tmp_file.is_file()
+    tmp_file.touch()
+
+    stack: ExitStack = current_actor().lifetime_stack
+    stack.callback(tmp_file.unlink)
+
+    await ctx.started((
+        str(tmp_file),
+        os.getpid(),
+    ))
+
+    # expect to be cancelled from here!
+    try:
+
+        # NOTE: turns out you don't even need to sched an aio task
+        # since the original issue, even though seemingly was due to
+        # the guest-run being abandoned + a `._debug.pause()` inside
+        # `._runtime._async_main()` (which was originally trying to
+        # debug the `.lifetime_stack` not closing), IS NOT actually
+        # the core issue?
+        #
+        # further notes:
+        #
+        # - `trio` only issues the " RuntimeWarning: Trio guest run
+        #   got abandoned without properly finishing... weird stuff
+        #   might happen" IFF you DO run a asyncio task here, BUT
+        # - the original issue of the `.lifetime_stack` not closing
+        #   will still happen even if you don't run an `asyncio` task
+        #   here even though the "abandon" messgage won't be shown..
+        #
+        # => ????? honestly i'm lost but it seems to be some issue
+        #   with `asyncio` and SIGINT..
+        #
+        # honestly, this REALLY reminds me why i haven't used
+        # `asyncio` by choice in years.. XD
+        #
+        async with trio.open_nursery() as tn:
+            if bg_aio_task:
+                tn.start_soon(
+                    tractor.to_asyncio.run_task,
+                    aio_sleep_forever,
+                )
+
+            # XXX don't-need/doesn't-make-a-diff right
+            # since we're already doing it from parent?
+            # if send_sigint_to == 'child':
+            #     os.kill(
+            #         os.getpid(),
+            #         signal.SIGINT,
+            #     )
+
+            # XXX spend a half sec doing shielded checkpointing to
+            # ensure that despite the `trio`-side task ignoring the
+            # SIGINT, the `asyncio` side won't abandon the guest-run!
+            if trio_side_is_shielded:
+                with trio.CancelScope(shield=True):
+                    for i in range(5):
+                        await trio.sleep(0.1)
+
+            await trio.sleep_forever()
+
+    # signalled manually at the OS level (aka KBI) by the parent actor.
+    except KeyboardInterrupt:
+        print('child raised KBI..')
+        assert tmp_file.exists()
+        raise
+
+    raise RuntimeError('shoulda received a KBI?')
+
+
+@pytest.mark.parametrize(
+    'trio_side_is_shielded',
+    [
+        False,
+        True,
+    ],
+    ids=[
+        'trio_side_no_shielding',
+        'trio_side_does_shielded_work',
+    ],
+)
+@pytest.mark.parametrize(
+    'send_sigint_to',
+    [
+        'child',
+        'parent',
+    ],
+    ids='send_SIGINT_to={}'.format,
+)
+@pytest.mark.parametrize(
+    'bg_aio_task',
+    [
+        False,
+
+        # NOTE: (and see notes in `manage_file()` above as well) if
+        # we FOR SURE SPAWN AN AIO TASK in the child it seems the
+        # "silent-abandon" case (as is described in detail in
+        # `to_asyncio.run_as_asyncio_guest()`) does not happen and
+        # `asyncio`'s loop will at least abandon the `trio` side
+        # loudly? .. prolly the state-spot to start looking for
+        # a soln that results in NO ABANDONMENT.. XD
+        True,
+    ],
+    ids=[
+        'bg_aio_task',
+        'just_trio_slee',
+    ],
+)
+@pytest.mark.parametrize(
+    'wait_for_ctx',
+    [
+        False,
+        True,
+    ],
+    ids=[
+        'raise_KBI_in_rent',
+        'wait_for_ctx',
+    ],
+)
+def test_sigint_closes_lifetime_stack(
+    tmp_path: Path,
+    wait_for_ctx: bool,
+    bg_aio_task: bool,
+    trio_side_is_shielded: bool,
+    debug_mode: bool,
+    send_sigint_to: str,
+):
+    '''
+    Ensure that an infected child can use the `Actor.lifetime_stack`
+    to make a file on boot and it's automatically cleaned up by the
+    actor-lifetime-linked exit stack closure.
+
+    '''
+    async def main():
+        try:
+            an: tractor.ActorNursery
+            async with tractor.open_nursery(
+                debug_mode=debug_mode,
+            ) as an:
+                p: tractor.Portal = await an.start_actor(
+                    'file_mngr',
+                    enable_modules=[__name__],
+                    infect_asyncio=True,
+                )
+                async with p.open_context(
+                    manage_file,
+                    tmp_path_str=str(tmp_path),
+                    send_sigint_to=send_sigint_to,
+                    bg_aio_task=bg_aio_task,
+                    trio_side_is_shielded=trio_side_is_shielded,
+                ) as (ctx, first):
+
+                    path_str, cpid = first
+                    tmp_file: Path = Path(path_str)
+                    assert tmp_file.exists()
+
+                    # XXX originally to simulate what (hopefully)
+                    # the below now triggers.. had to manually
+                    # trigger a SIGINT from a ctl-c in the root.
+                    # await trio.sleep_forever()
+
+                    # XXX NOTE XXX signal infected-`asyncio` child to
+                    # OS-cancel with SIGINT; this should trigger the
+                    # bad `asyncio` cancel behaviour that can cause
+                    # a guest-run abandon as was seen causing
+                    # shm-buffer leaks in `piker`'s live quote stream
+                    # susbys!
+                    #
+                    await trio.sleep(.2)
+                    pid: int = (
+                        cpid if send_sigint_to == 'child'
+                        else os.getpid()
+                    )
+                    os.kill(
+                        pid,
+                        signal.SIGINT,
+                    )
+
+                    # XXX CASE 1: without the bug fixed, in
+                    # the non-KBI-raised-in-parent case, this
+                    # timeout should trigger!
+                    if wait_for_ctx:
+                        print('waiting for ctx outcome in parent..')
+                        try:
+                            with trio.fail_after(1):
+                                await ctx.wait_for_result()
+                        except tractor.ContextCancelled as ctxc:
+                            assert ctxc.canceller == ctx.chan.uid
+                            raise
+
+                    # XXX CASE 2: this seems to be the source of the
+                    # original issue which exhibited BEFORE we put
+                    # a `Actor.cancel_soon()` inside
+                    # `run_as_asyncio_guest()`..
+                    else:
+                        raise KeyboardInterrupt
+
+                pytest.fail('should have raised some kinda error?!?')
+
+        except (
+            KeyboardInterrupt,
+            ContextCancelled,
+        ):
+            # XXX CASE 2: without the bug fixed, in the
+            # KBI-raised-in-parent case, the actor teardown should
+            # never get run (silently abaondoned by `asyncio`..) and
+            # thus the file should leak!
+            assert not tmp_file.exists()
+            assert ctx.maybe_error
+
+    trio.run(main)
+
+
+# TODO: debug_mode tests once we get support for `asyncio`!
+#
+# -[ ] need tests to wrap both scripts:
+#   - [ ] infected_asyncio_echo_server.py
+#   - [ ] debugging/asyncio_bp.py
+#  -[ ] consider moving ^ (some of) these ^ to `test_debugger`?
+#
+# -[ ] missing impl outstanding includes:
+#  - [x] for sync pauses we need to ensure we open yet another
+#    `greenback` portal in the asyncio task
+#    => completed using `.bestow_portal(task)` inside
+#     `.to_asyncio._run_asyncio_task()` right?
+#   -[ ] translation func to get from `asyncio` task calling to 
+#     `._debug.wait_for_parent_stdin_hijack()` which does root
+#     call to do TTY locking.
+#
+def test_sync_breakpoint():
+    '''
+    Verify we can do sync-func/code breakpointing using the
+    `breakpoint()` builtin inside infected mode actors.
+
+    '''
+    pytest.xfail('This support is not implemented yet!')
+
+
+def test_debug_mode_crash_handling():
+    '''
+    Verify mult-actor crash handling works with a combo of infected-`asyncio`-mode
+    and normal `trio` actors despite nested process trees.
+
+    '''
+    pytest.xfail('This support is not implemented yet!')

tests/test_legacy_one_way_streaming.py

@@ -9,7 +9,7 @@ import trio
 import tractor
 import pytest
 
-from conftest import tractor_test
+from tractor._testing import tractor_test
 
 
 def test_must_define_ctx():
@@ -38,10 +38,13 @@ async def async_gen_stream(sequence):
     assert cs.cancelled_caught
 
 
+# TODO: deprecated either remove entirely
+# or re-impl in terms of `MsgStream` one-sides
+# wrapper, but at least remove `Portal.open_stream_from()`
 @tractor.stream
 async def context_stream(
     ctx: tractor.Context,
-    sequence
+    sequence: list[int],
 ):
     for i in sequence:
         await ctx.send_yield(i)
@@ -55,7 +58,7 @@ async def context_stream(
 
 
 async def stream_from_single_subactor(
-    arb_addr,
+    reg_addr,
     start_method,
     stream_func,
 ):
@@ -64,7 +67,7 @@ async def stream_from_single_subactor(
     # only one per host address, spawns an actor if None
 
     async with tractor.open_nursery(
-        arbiter_addr=arb_addr,
+        registry_addrs=[reg_addr],
         start_method=start_method,
     ) as nursery:
 
@@ -115,13 +118,13 @@ async def stream_from_single_subactor(
 @pytest.mark.parametrize(
     'stream_func', [async_gen_stream, context_stream]
 )
-def test_stream_from_single_subactor(arb_addr, start_method, stream_func):
+def test_stream_from_single_subactor(reg_addr, start_method, stream_func):
     """Verify streaming from a spawned async generator.
     """
     trio.run(
         partial(
             stream_from_single_subactor,
-            arb_addr,
+            reg_addr,
             start_method,
             stream_func=stream_func,
         ),
@@ -225,14 +228,14 @@ async def a_quadruple_example():
         return result_stream
 
 
-async def cancel_after(wait, arb_addr):
+async def cancel_after(wait, reg_addr):
-    async with tractor.open_root_actor(arbiter_addr=arb_addr):
+    async with tractor.open_root_actor(registry_addrs=[reg_addr]):
         with trio.move_on_after(wait):
             return await a_quadruple_example()
 
 
 @pytest.fixture(scope='module')
-def time_quad_ex(arb_addr, ci_env, spawn_backend):
+def time_quad_ex(reg_addr, ci_env, spawn_backend):
     if spawn_backend == 'mp':
         """no idea but the  mp *nix runs are flaking out here often...
         """
@@ -240,7 +243,7 @@ def time_quad_ex(arb_addr, ci_env, spawn_backend):
 
     timeout = 7 if platform.system() in ('Windows', 'Darwin') else 4
     start = time.time()
-    results = trio.run(cancel_after, timeout, arb_addr)
+    results = trio.run(cancel_after, timeout, reg_addr)
     diff = time.time() - start
     assert results
     return results, diff
@@ -260,14 +263,14 @@ def test_a_quadruple_example(time_quad_ex, ci_env, spawn_backend):
     list(map(lambda i: i/10, range(3, 9)))
 )
 def test_not_fast_enough_quad(
-    arb_addr, time_quad_ex, cancel_delay, ci_env, spawn_backend
+    reg_addr, time_quad_ex, cancel_delay, ci_env, spawn_backend
 ):
     """Verify we can cancel midway through the quad example and all actors
     cancel gracefully.
     """
     results, diff = time_quad_ex
     delay = max(diff - cancel_delay, 0)
-    results = trio.run(cancel_after, delay, arb_addr)
+    results = trio.run(cancel_after, delay, reg_addr)
     system = platform.system()
     if system in ('Windows', 'Darwin') and results is not None:
         # In CI envoirments it seems later runs are quicker then the first
@@ -280,7 +283,7 @@ def test_not_fast_enough_quad(
 
 @tractor_test
 async def test_respawn_consumer_task(
-    arb_addr,
+    reg_addr,
     spawn_backend,
     loglevel,
 ):

tests/test_local.py

@@ -7,7 +7,7 @@ import pytest
 import trio
 import tractor
 
-from conftest import tractor_test
+from tractor._testing import tractor_test
 
 
 @pytest.mark.trio
@@ -24,7 +24,7 @@ async def test_no_runtime():
 
 
 @tractor_test
-async def test_self_is_registered(arb_addr):
+async def test_self_is_registered(reg_addr):
     "Verify waiting on the arbiter to register itself using the standard api."
     actor = tractor.current_actor()
     assert actor.is_arbiter
@@ -34,20 +34,20 @@ async def test_self_is_registered(arb_addr):
 
 
 @tractor_test
-async def test_self_is_registered_localportal(arb_addr):
+async def test_self_is_registered_localportal(reg_addr):
     "Verify waiting on the arbiter to register itself using a local portal."
     actor = tractor.current_actor()
     assert actor.is_arbiter
-    async with tractor.get_arbiter(*arb_addr) as portal:
+    async with tractor.get_registry(*reg_addr) as portal:
         assert isinstance(portal, tractor._portal.LocalPortal)
 
         with trio.fail_after(0.2):
             sockaddr = await portal.run_from_ns(
                     'self', 'wait_for_actor', name='root')
-            assert sockaddr[0] == arb_addr
+            assert sockaddr[0] == reg_addr
 
 
-def test_local_actor_async_func(arb_addr):
+def test_local_actor_async_func(reg_addr):
     """Verify a simple async function in-process.
     """
     nums = []
@@ -55,7 +55,7 @@ def test_local_actor_async_func(arb_addr):
     async def print_loop():
 
         async with tractor.open_root_actor(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
         ):
             # arbiter is started in-proc if dne
             assert tractor.current_actor().is_arbiter

tests/test_multi_program.py

@@ -7,8 +7,10 @@ import time
 import pytest
 import trio
 import tractor
-from conftest import (
+from tractor._testing import (
     tractor_test,
+)
+from conftest import (
     sig_prog,
     _INT_SIGNAL,
     _INT_RETURN_CODE,
@@ -28,9 +30,9 @@ def test_abort_on_sigint(daemon):
 
 
 @tractor_test
-async def test_cancel_remote_arbiter(daemon, arb_addr):
+async def test_cancel_remote_arbiter(daemon, reg_addr):
     assert not tractor.current_actor().is_arbiter
-    async with tractor.get_arbiter(*arb_addr) as portal:
+    async with tractor.get_registry(*reg_addr) as portal:
         await portal.cancel_actor()
 
     time.sleep(0.1)
@@ -39,16 +41,16 @@ async def test_cancel_remote_arbiter(daemon, arb_addr):
 
     # no arbiter socket should exist
     with pytest.raises(OSError):
-        async with tractor.get_arbiter(*arb_addr) as portal:
+        async with tractor.get_registry(*reg_addr) as portal:
             pass
 
 
-def test_register_duplicate_name(daemon, arb_addr):
+def test_register_duplicate_name(daemon, reg_addr):
 
     async def main():
 
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
         ) as n:
 
             assert not tractor.current_actor().is_arbiter

tests/test_pldrx_limiting.py

@@ -0,0 +1,364 @@
+'''
+Audit sub-sys APIs from `.msg._ops`
+mostly for ensuring correct `contextvars`
+related settings around IPC contexts.
+
+'''
+from contextlib import (
+    asynccontextmanager as acm,
+)
+
+from msgspec import (
+    Struct,
+)
+import pytest
+import trio
+
+import tractor
+from tractor import (
+    Context,
+    MsgTypeError,
+    current_ipc_ctx,
+    Portal,
+)
+from tractor.msg import (
+    _ops as msgops,
+    Return,
+)
+from tractor.msg import (
+    _codec,
+)
+from tractor.msg.types import (
+    log,
+)
+
+
+class PldMsg(
+    Struct,
+
+    # TODO: with multiple structs in-spec we need to tag them!
+    # -[ ] offer a built-in `PldMsg` type to inherit from which takes
+    #      case of these details?
+    #
+    # https://jcristharif.com/msgspec/structs.html#tagged-unions
+    # tag=True,
+    # tag_field='msg_type',
+):
+    field: str
+
+
+maybe_msg_spec = PldMsg|None
+
+
+@acm
+async def maybe_expect_raises(
+    raises: BaseException|None = None,
+    ensure_in_message: list[str]|None = None,
+    post_mortem: bool = False,
+    timeout: int = 3,
+) -> None:
+    '''
+    Async wrapper for ensuring errors propagate from the inner scope.
+
+    '''
+    if tractor._state.debug_mode():
+        timeout += 999
+
+    with trio.fail_after(timeout):
+        try:
+            yield
+        except BaseException as _inner_err:
+            inner_err = _inner_err
+            # wasn't-expected to error..
+            if raises is None:
+                raise
+
+            else:
+                assert type(inner_err) is raises
+
+                # maybe check for error txt content
+                if ensure_in_message:
+                    part: str
+                    err_repr: str = repr(inner_err)
+                    for part in ensure_in_message:
+                        for i, arg in enumerate(inner_err.args):
+                            if part in err_repr:
+                                break
+                        # if part never matches an arg, then we're
+                        # missing a match.
+                        else:
+                            raise ValueError(
+                                'Failed to find error message content?\n\n'
+                                f'expected: {ensure_in_message!r}\n'
+                                f'part: {part!r}\n\n'
+                                f'{inner_err.args}'
+                        )
+
+                if post_mortem:
+                    await tractor.post_mortem()
+
+        else:
+            if raises:
+                raise RuntimeError(
+                    f'Expected a {raises.__name__!r} to be raised?'
+                )
+
+
+@tractor.context(
+    pld_spec=maybe_msg_spec,
+)
+async def child(
+    ctx: Context,
+    started_value: int|PldMsg|None,
+    return_value: str|None,
+    validate_pld_spec: bool,
+    raise_on_started_mte: bool = True,
+
+) -> None:
+    '''
+    Call ``Context.started()`` more then once (an error).
+
+    '''
+    expect_started_mte: bool = started_value == 10
+
+    # sanaity check that child RPC context is the current one
+    curr_ctx: Context = current_ipc_ctx()
+    assert ctx is curr_ctx
+
+    rx: msgops.PldRx = ctx._pld_rx
+    curr_pldec: _codec.MsgDec = rx.pld_dec
+
+    ctx_meta: dict = getattr(
+        child,
+        '_tractor_context_meta',
+        None,
+    )
+    if ctx_meta:
+        assert (
+            ctx_meta['pld_spec']
+            is curr_pldec.spec
+            is curr_pldec.pld_spec
+        )
+
+    # 2 cases: hdndle send-side and recv-only validation
+    # - when `raise_on_started_mte == True`, send validate
+    # - else, parent-recv-side only validation
+    mte: MsgTypeError|None = None
+    try:
+        await ctx.started(
+            value=started_value,
+            validate_pld_spec=validate_pld_spec,
+        )
+
+    except MsgTypeError as _mte:
+        mte = _mte
+        log.exception('started()` raised an MTE!\n')
+        if not expect_started_mte:
+            raise RuntimeError(
+                'Child-ctx-task SHOULD NOT HAVE raised an MTE for\n\n'
+                f'{started_value!r}\n'
+            )
+
+        boxed_div: str = '------ - ------'
+        assert boxed_div not in mte._message
+        assert boxed_div not in mte.tb_str
+        assert boxed_div not in repr(mte)
+        assert boxed_div not in str(mte)
+        mte_repr: str = repr(mte)
+        for line in mte.message.splitlines():
+            assert line in mte_repr
+
+        # since this is a *local error* there should be no
+        # boxed traceback content!
+        assert not mte.tb_str
+
+        # propagate to parent?
+        if raise_on_started_mte:
+            raise
+
+    # no-send-side-error fallthrough
+    if (
+        validate_pld_spec
+        and
+        expect_started_mte
+    ):
+        raise RuntimeError(
+            'Child-ctx-task SHOULD HAVE raised an MTE for\n\n'
+            f'{started_value!r}\n'
+        )
+
+    assert (
+        not expect_started_mte
+        or
+        not validate_pld_spec
+    )
+
+    # if wait_for_parent_to_cancel:
+    #     ...
+    #
+    # ^-TODO-^ logic for diff validation policies on each side:
+    #
+    # -[ ] ensure that if we don't validate on the send
+    #   side, that we are eventually error-cancelled by our
+    #   parent due to the bad `Started` payload!
+    # -[ ] the boxed error should be srced from the parent's
+    #   runtime NOT ours!
+    # -[ ] we should still error on bad `return_value`s
+    #   despite the parent not yet error-cancelling us?
+    #   |_ how do we want the parent side to look in that
+    #     case?
+    #     -[ ] maybe the equiv of "during handling of the
+    #       above error another occurred" for the case where
+    #       the parent sends a MTE to this child and while
+    #       waiting for the child to terminate it gets back
+    #       the MTE for this case?
+    #
+
+    # XXX should always fail on recv side since we can't
+    # really do much else beside terminate and relay the
+    # msg-type-error from this RPC task ;)
+    return return_value
+
+
+@pytest.mark.parametrize(
+    'return_value',
+    [
+        'yo',
+        None,
+    ],
+    ids=[
+        'return[invalid-"yo"]',
+        'return[valid-None]',
+    ],
+)
+@pytest.mark.parametrize(
+    'started_value',
+    [
+        10,
+        PldMsg(field='yo'),
+    ],
+    ids=[
+        'Started[invalid-10]',
+        'Started[valid-PldMsg]',
+    ],
+)
+@pytest.mark.parametrize(
+    'pld_check_started_value',
+    [
+        True,
+        False,
+    ],
+    ids=[
+        'check-started-pld',
+        'no-started-pld-validate',
+    ],
+)
+def test_basic_payload_spec(
+    debug_mode: bool,
+    loglevel: str,
+    return_value: str|None,
+    started_value: int|PldMsg,
+    pld_check_started_value: bool,
+):
+    '''
+    Validate the most basic `PldRx` msg-type-spec semantics around
+    a IPC `Context` endpoint start, started-sync, and final return
+    value depending on set payload types and the currently applied
+    pld-spec.
+
+    '''
+    invalid_return: bool = return_value == 'yo'
+    invalid_started: bool = started_value == 10
+
+    async def main():
+        async with tractor.open_nursery(
+            debug_mode=debug_mode,
+            loglevel=loglevel,
+        ) as an:
+            p: Portal = await an.start_actor(
+                'child',
+                enable_modules=[__name__],
+            )
+
+            # since not opened yet.
+            assert current_ipc_ctx() is None
+
+            if invalid_started:
+                msg_type_str: str = 'Started'
+                bad_value: int = 10
+            elif invalid_return:
+                msg_type_str: str = 'Return'
+                bad_value: str = 'yo'
+            else:
+                # XXX but should never be used below then..
+                msg_type_str: str = ''
+                bad_value: str = ''
+
+            maybe_mte: MsgTypeError|None = None
+            should_raise: Exception|None = (
+                MsgTypeError if (
+                    invalid_return
+                    or
+                    invalid_started
+                ) else None
+            )
+            async with (
+                maybe_expect_raises(
+                    raises=should_raise,
+                    ensure_in_message=[
+                        f"invalid `{msg_type_str}` msg payload",
+                        f'{bad_value}',
+                        f'has type {type(bad_value)!r}',
+                        'not match type-spec',
+                        f'`{msg_type_str}.pld: PldMsg|NoneType`',
+                    ],
+                    # only for debug
+                    # post_mortem=True,
+                ),
+                p.open_context(
+                    child,
+                    return_value=return_value,
+                    started_value=started_value,
+                    validate_pld_spec=pld_check_started_value,
+                ) as (ctx, first),
+            ):
+                # now opened with 'child' sub
+                assert current_ipc_ctx() is ctx
+
+                assert type(first) is PldMsg
+                assert first.field == 'yo'
+
+                try:
+                    res: None|PldMsg = await ctx.result(hide_tb=False)
+                    assert res is None
+                except MsgTypeError as mte:
+                    maybe_mte = mte
+                    if not invalid_return:
+                        raise
+
+                    # expected this invalid `Return.pld` so audit
+                    # the error state + meta-data
+                    assert mte.expected_msg_type is Return
+                    assert mte.cid == ctx.cid
+                    mte_repr: str = repr(mte)
+                    for line in mte.message.splitlines():
+                        assert line in mte_repr
+
+                    assert mte.tb_str
+                    # await tractor.pause(shield=True)
+
+                    # verify expected remote mte deats
+                    assert ctx._local_error is None
+                    assert (
+                        mte is
+                        ctx._remote_error is
+                        ctx.maybe_error is
+                        ctx.outcome
+                    )
+
+            if should_raise is None:
+                assert maybe_mte is None
+
+            await p.cancel_actor()
+
+    trio.run(main)

tests/test_pubsub.py

@@ -5,8 +5,7 @@ import pytest
 import trio
 import tractor
 from tractor.experimental import msgpub
-
+from tractor._testing import tractor_test
-from conftest import tractor_test
 
 
 def test_type_checks():
@@ -160,7 +159,7 @@ async def test_required_args(callwith_expecterror):
 )
 def test_multi_actor_subs_arbiter_pub(
     loglevel,
-    arb_addr,
+    reg_addr,
     pub_actor,
 ):
     """Try out the neato @pub decorator system.
@@ -170,7 +169,7 @@ def test_multi_actor_subs_arbiter_pub(
     async def main():
 
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
             enable_modules=[__name__],
         ) as n:
 
@@ -255,12 +254,12 @@ def test_multi_actor_subs_arbiter_pub(
 
 def test_single_subactor_pub_multitask_subs(
     loglevel,
-    arb_addr,
+    reg_addr,
 ):
     async def main():
 
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
             enable_modules=[__name__],
         ) as n:
 

tests/test_resource_cache.py

@@ -34,7 +34,6 @@ def test_resource_only_entered_once(key_on):
     global _resource
     _resource = 0
 
-    kwargs = {}
     key = None
     if key_on == 'key_value':
         key = 'some_common_key'
@@ -139,7 +138,7 @@ def test_open_local_sub_to_stream():
     N local tasks using ``trionics.maybe_open_context():``.
 
     '''
-    timeout = 3 if platform.system() != "Windows" else 10
+    timeout: float = 3.6 if platform.system() != "Windows" else 10
 
     async def main():
 

tests/test_rpc.py

@@ -1,6 +1,8 @@
-"""
+'''
-RPC related
+RPC (or maybe better labelled as "RTS: remote task scheduling"?)
-"""
+related API and error checks.
+
+'''
 import itertools
 
 import pytest
@@ -13,9 +15,19 @@ async def sleep_back_actor(
     func_name,
     func_defined,
     exposed_mods,
+    *,
+    reg_addr: tuple,
 ):
     if actor_name:
-        async with tractor.find_actor(actor_name) as portal:
+        async with tractor.find_actor(
+            actor_name,
+            # NOTE: must be set manually since
+            # the subactor doesn't have the reg_addr
+            # fixture code run in it!
+            # TODO: maybe we should just set this once in the
+            # _state mod and derive to all children?
+            registry_addrs=[reg_addr],
+        ) as portal:
             try:
                 await portal.run(__name__, func_name)
             except tractor.RemoteActorError as err:
@@ -24,7 +36,7 @@ async def sleep_back_actor(
                 if not exposed_mods:
                     expect = tractor.ModuleNotExposed
 
-                assert err.type is expect
+                assert err.boxed_type is expect
                 raise
     else:
         await trio.sleep(float('inf'))
@@ -42,14 +54,25 @@ async def short_sleep():
         (['tmp_mod'], 'import doggy', ModuleNotFoundError),
         (['tmp_mod'], '4doggy', SyntaxError),
     ],
-    ids=['no_mods', 'this_mod', 'this_mod_bad_func', 'fail_to_import',
+    ids=[
-         'fail_on_syntax'],
+        'no_mods',
+        'this_mod',
+        'this_mod_bad_func',
+        'fail_to_import',
+        'fail_on_syntax',
+    ],
 )
-def test_rpc_errors(arb_addr, to_call, testdir):
+def test_rpc_errors(
-    """Test errors when making various RPC requests to an actor
+    reg_addr,
+    to_call,
+    testdir,
+):
+    '''
+    Test errors when making various RPC requests to an actor
     that either doesn't have the requested module exposed or doesn't define
     the named function.
-    """
+
+    '''
     exposed_mods, funcname, inside_err = to_call
     subactor_exposed_mods = []
     func_defined = globals().get(funcname, False)
@@ -77,8 +100,13 @@ def test_rpc_errors(arb_addr, to_call, testdir):
 
         # spawn a subactor which calls us back
         async with tractor.open_nursery(
-            arbiter_addr=arb_addr,
+            registry_addrs=[reg_addr],
             enable_modules=exposed_mods.copy(),
+
+            # NOTE: will halt test in REPL if uncommented, so only
+            # do that if actually debugging subactor but keep it
+            # disabled for the test.
+            # debug_mode=True,
         ) as n:
 
             actor = tractor.current_actor()
@@ -95,6 +123,7 @@ def test_rpc_errors(arb_addr, to_call, testdir):
                 exposed_mods=exposed_mods,
                 func_defined=True if func_defined else False,
                 enable_modules=subactor_exposed_mods,
+                reg_addr=reg_addr,
             )
 
     def run():
@@ -105,18 +134,20 @@ def test_rpc_errors(arb_addr, to_call, testdir):
         run()
     else:
         # underlying errors aren't propagated upwards (yet)
-        with pytest.raises(remote_err) as err:
+        with pytest.raises(
+            expected_exception=(remote_err, ExceptionGroup),
+        ) as err:
             run()
 
         # get raw instance from pytest wrapper
         value = err.value
 
         # might get multiple `trio.Cancelled`s as well inside an inception
-        if isinstance(value, trio.MultiError):
+        if isinstance(value, ExceptionGroup):
             value = next(itertools.dropwhile(
                 lambda exc: not isinstance(exc, tractor.RemoteActorError),
                 value.exceptions
             ))
 
         if getattr(value, 'type', None):
-            assert value.type is inside_err
+            assert value.boxed_type is inside_err

tests/test_runtime.py

@@ -8,7 +8,7 @@ import pytest
 import trio
 import tractor
 
-from conftest import tractor_test
+from tractor._testing import tractor_test
 
 
 _file_path: str = ''
@@ -64,7 +64,8 @@ async def test_lifetime_stack_wipes_tmpfile(
 
     except (
         tractor.RemoteActorError,
-        tractor.BaseExceptionGroup,
+        # tractor.BaseExceptionGroup,
+        BaseExceptionGroup,
     ):
         pass
 

tests/test_shm.py

@@ -0,0 +1,167 @@
+"""
+Shared mem primitives and APIs.
+
+"""
+import uuid
+
+# import numpy
+import pytest
+import trio
+import tractor
+from tractor._shm import (
+    open_shm_list,
+    attach_shm_list,
+)
+
+
+@tractor.context
+async def child_attach_shml_alot(
+    ctx: tractor.Context,
+    shm_key: str,
+) -> None:
+
+    await ctx.started(shm_key)
+
+    # now try to attach a boatload of times in a loop..
+    for _ in range(1000):
+        shml = attach_shm_list(
+            key=shm_key,
+            readonly=False,
+        )
+        assert shml.shm.name == shm_key
+        await trio.sleep(0.001)
+
+
+def test_child_attaches_alot():
+    async def main():
+        async with tractor.open_nursery() as an:
+
+            # allocate writeable list in parent
+            key = f'shml_{uuid.uuid4()}'
+            shml = open_shm_list(
+                key=key,
+            )
+
+            portal = await an.start_actor(
+                'shm_attacher',
+                enable_modules=[__name__],
+            )
+
+            async with (
+                portal.open_context(
+                    child_attach_shml_alot,
+                    shm_key=shml.key,
+                ) as (ctx, start_val),
+            ):
+                assert start_val == key
+                await ctx.result()
+
+            await portal.cancel_actor()
+
+    trio.run(main)
+
+
+@tractor.context
+async def child_read_shm_list(
+    ctx: tractor.Context,
+    shm_key: str,
+    use_str: bool,
+    frame_size: int,
+) -> None:
+
+    # attach in child
+    shml = attach_shm_list(
+        key=shm_key,
+        # dtype=str if use_str else float,
+    )
+    await ctx.started(shml.key)
+
+    async with ctx.open_stream() as stream:
+        async for i in stream:
+            print(f'(child): reading shm list index: {i}')
+
+            if use_str:
+                expect = str(float(i))
+            else:
+                expect = float(i)
+
+            if frame_size == 1:
+                val = shml[i]
+                assert expect == val
+                print(f'(child): reading value: {val}')
+            else:
+                frame = shml[i - frame_size:i]
+                print(f'(child): reading frame: {frame}')
+
+
+@pytest.mark.parametrize(
+    'use_str',
+    [False, True],
+    ids=lambda i: f'use_str_values={i}',
+)
+@pytest.mark.parametrize(
+    'frame_size',
+    [1, 2**6, 2**10],
+    ids=lambda i: f'frame_size={i}',
+)
+def test_parent_writer_child_reader(
+    use_str: bool,
+    frame_size: int,
+):
+
+    async def main():
+        async with tractor.open_nursery(
+            # debug_mode=True,
+        ) as an:
+
+            portal = await an.start_actor(
+                'shm_reader',
+                enable_modules=[__name__],
+                debug_mode=True,
+            )
+
+            # allocate writeable list in parent
+            key = 'shm_list'
+            seq_size = int(2 * 2 ** 10)
+            shml = open_shm_list(
+                key=key,
+                size=seq_size,
+                dtype=str if use_str else float,
+                readonly=False,
+            )
+
+            async with (
+                portal.open_context(
+                    child_read_shm_list,
+                    shm_key=key,
+                    use_str=use_str,
+                    frame_size=frame_size,
+                ) as (ctx, sent),
+
+                ctx.open_stream() as stream,
+            ):
+
+                assert sent == key
+
+                for i in range(seq_size):
+
+                    val = float(i)
+                    if use_str:
+                        val = str(val)
+
+                    # print(f'(parent): writing {val}')
+                    shml[i] = val
+
+                    # only on frame fills do we
+                    # signal to the child that a frame's
+                    # worth is ready.
+                    if (i % frame_size) == 0:
+                        print(f'(parent): signalling frame full on {val}')
+                        await stream.send(i)
+                else:
+                    print(f'(parent): signalling final frame on {val}')
+                    await stream.send(i)
+
+            await portal.cancel_actor()
+
+    trio.run(main)

tests/test_spawning.py

@@ -2,13 +2,15 @@
 Spawning basics
 
 """
-from typing import Optional
+from typing import (
+    Any,
+)
 
 import pytest
 import trio
 import tractor
 
-from conftest import tractor_test
+from tractor._testing import tractor_test
 
 data_to_pass_down = {'doggy': 10, 'kitty': 4}
 
@@ -16,24 +18,21 @@ data_to_pass_down = {'doggy': 10, 'kitty': 4}
 async def spawn(
     is_arbiter: bool,
     data: dict,
-    arb_addr: tuple[str, int],
+    reg_addr: tuple[str, int],
 ):
     namespaces = [__name__]
 
     await trio.sleep(0.1)
 
     async with tractor.open_root_actor(
-        arbiter_addr=arb_addr,
+        arbiter_addr=reg_addr,
     ):
-
         actor = tractor.current_actor()
         assert actor.is_arbiter == is_arbiter
         data = data_to_pass_down
 
         if actor.is_arbiter:
-
+            async with tractor.open_nursery() as nursery:
-            async with tractor.open_nursery(
-            ) as nursery:
 
                 # forks here
                 portal = await nursery.run_in_actor(
@@ -41,7 +40,7 @@ async def spawn(
                     is_arbiter=False,
                     name='sub-actor',
                     data=data,
-                    arb_addr=arb_addr,
+                    reg_addr=reg_addr,
                     enable_modules=namespaces,
                 )
 
@@ -55,12 +54,14 @@ async def spawn(
             return 10
 
 
-def test_local_arbiter_subactor_global_state(arb_addr):
+def test_local_arbiter_subactor_global_state(
+    reg_addr,
+):
     result = trio.run(
         spawn,
         True,
         data_to_pass_down,
-        arb_addr,
+        reg_addr,
     )
     assert result == 10
 
@@ -94,7 +95,9 @@ async def test_movie_theatre_convo(start_method):
         await portal.cancel_actor()
 
 
-async def cellar_door(return_value: Optional[str]):
+async def cellar_door(
+    return_value: str|None,
+):
     return return_value
 
 
@@ -104,16 +107,18 @@ async def cellar_door(return_value: Optional[str]):
 )
 @tractor_test
 async def test_most_beautiful_word(
-    start_method,
+    start_method: str,
-    return_value
+    return_value: Any,
+    debug_mode: bool,
 ):
     '''
     The main ``tractor`` routine.
 
     '''
     with trio.fail_after(1):
-        async with tractor.open_nursery() as n:
+        async with tractor.open_nursery(
-
+            debug_mode=debug_mode,
+        ) as n:
             portal = await n.run_in_actor(
                 cellar_door,
                 return_value=return_value,
@@ -140,7 +145,7 @@ async def check_loglevel(level):
 def test_loglevel_propagated_to_subactor(
     start_method,
     capfd,
-    arb_addr,
+    reg_addr,
 ):
     if start_method == 'mp_forkserver':
         pytest.skip(
@@ -152,7 +157,7 @@ def test_loglevel_propagated_to_subactor(
         async with tractor.open_nursery(
             name='arbiter',
             start_method=start_method,
-            arbiter_addr=arb_addr,
+            arbiter_addr=reg_addr,
 
         ) as tn:
             await tn.run_in_actor(

tests/test_task_broadcasting.py

@@ -66,13 +66,13 @@ async def ensure_sequence(
 async def open_sequence_streamer(
 
     sequence: list[int],
-    arb_addr: tuple[str, int],
+    reg_addr: tuple[str, int],
     start_method: str,
 
 ) -> tractor.MsgStream:
 
     async with tractor.open_nursery(
-        arbiter_addr=arb_addr,
+        arbiter_addr=reg_addr,
         start_method=start_method,
     ) as tn:
 
@@ -86,14 +86,14 @@ async def open_sequence_streamer(
         ) as (ctx, first):
 
             assert first is None
-            async with ctx.open_stream(backpressure=True) as stream:
+            async with ctx.open_stream(allow_overruns=True) as stream:
                 yield stream
 
         await portal.cancel_actor()
 
 
 def test_stream_fan_out_to_local_subscriptions(
-    arb_addr,
+    reg_addr,
     start_method,
 ):
 
@@ -103,7 +103,7 @@ def test_stream_fan_out_to_local_subscriptions(
 
         async with open_sequence_streamer(
             sequence,
-            arb_addr,
+            reg_addr,
             start_method,
         ) as stream:
 
@@ -138,7 +138,7 @@ def test_stream_fan_out_to_local_subscriptions(
     ]
 )
 def test_consumer_and_parent_maybe_lag(
-    arb_addr,
+    reg_addr,
     start_method,
     task_delays,
 ):
@@ -150,7 +150,7 @@ def test_consumer_and_parent_maybe_lag(
 
         async with open_sequence_streamer(
             sequence,
-            arb_addr,
+            reg_addr,
             start_method,
         ) as stream:
 
@@ -211,7 +211,7 @@ def test_consumer_and_parent_maybe_lag(
 
 
 def test_faster_task_to_recv_is_cancelled_by_slower(
-    arb_addr,
+    reg_addr,
     start_method,
 ):
     '''
@@ -225,7 +225,7 @@ def test_faster_task_to_recv_is_cancelled_by_slower(
 
         async with open_sequence_streamer(
             sequence,
-            arb_addr,
+            reg_addr,
             start_method,
 
         ) as stream:
@@ -302,7 +302,7 @@ def test_subscribe_errors_after_close():
 
 
 def test_ensure_slow_consumers_lag_out(
-    arb_addr,
+    reg_addr,
     start_method,
 ):
     '''This is a pure local task test; no tractor
@@ -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 backpressured entries in the underlying
+                # all no_overruns entries in the underlying
-                # channel should have been copied into the caster
+                # channel should have been copied into the bcaster
                 # queue trailing-window
                 async for i in rx:
                     print(f'bped: {i}')

tests/test_trioisms.py

@@ -5,7 +5,7 @@ want to see changed.
 '''
 import pytest
 import trio
-from trio_typing import TaskStatus
+from trio import TaskStatus
 
 
 @pytest.mark.parametrize(

tractor/__init__.py

@@ -15,72 +15,53 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 """
-tractor: structured concurrent "actors".
+tractor: structured concurrent ``trio``-"actors".
 
 """
-from exceptiongroup import BaseExceptionGroup
+from ._clustering import (
-
+    open_actor_cluster as open_actor_cluster,
-from ._clustering import open_actor_cluster
+)
-from ._ipc import Channel
+from ._context import (
+    Context as Context,  # the type
+    context as context,  # a func-decorator
+)
 from ._streaming import (
-    Context,
+    MsgStream as MsgStream,
-    MsgStream,
+    stream as stream,
-    stream,
-    context,
 )
 from ._discovery import (
-    get_arbiter,
+    get_registry as get_registry,
-    find_actor,
+    find_actor as find_actor,
-    wait_for_actor,
+    wait_for_actor as wait_for_actor,
-    query_actor,
+    query_actor as query_actor,
+)
+from ._supervise import (
+    open_nursery as open_nursery,
+    ActorNursery as ActorNursery,
 )
-from ._supervise import open_nursery
 from ._state import (
-    current_actor,
+    current_actor as current_actor,
-    is_root_process,
+    is_root_process as is_root_process,
+    current_ipc_ctx as current_ipc_ctx,
 )
 from ._exceptions import (
-    RemoteActorError,
+    ContextCancelled as ContextCancelled,
-    ModuleNotExposed,
+    ModuleNotExposed as ModuleNotExposed,
-    ContextCancelled,
+    MsgTypeError as MsgTypeError,
+    RemoteActorError as RemoteActorError,
+    TransportClosed as TransportClosed,
 )
-from ._debug import (
+from .devx import (
-    breakpoint,
+    breakpoint as breakpoint,
-    post_mortem,
+    pause as pause,
+    pause_from_sync as pause_from_sync,
+    post_mortem as post_mortem,
 )
-from . import msg
+from . import msg as msg
 from ._root import (
-    run_daemon,
+    run_daemon as run_daemon,
-    open_root_actor,
+    open_root_actor as open_root_actor,
 )
-from ._portal import Portal
+from ._ipc import Channel as Channel
-from ._runtime import Actor
+from ._portal import Portal as Portal
-
+from ._runtime import Actor as Actor
-
-__all__ = [
-    'Actor',
-    'Channel',
-    'Context',
-    'ContextCancelled',
-    'ModuleNotExposed',
-    'MsgStream',
-    'BaseExceptionGroup',
-    'Portal',
-    'RemoteActorError',
-    'breakpoint',
-    'context',
-    'current_actor',
-    'find_actor',
-    'get_arbiter',
-    'is_root_process',
-    'msg',
-    'open_actor_cluster',
-    'open_nursery',
-    'open_root_actor',
-    'post_mortem',
-    'query_actor',
-    'run_daemon',
-    'stream',
-    'to_asyncio',
-    'wait_for_actor',
-]

tractor/_child.py

@@ -18,8 +18,6 @@
 This is the "bootloader" for actors started using the native trio backend.
 
 """
-import sys
-import trio
 import argparse
 
 from ast import literal_eval
@@ -37,9 +35,8 @@ def parse_ipaddr(arg):
     return (str(host), int(port))
 
 
-from ._entry import _trio_main
-
 if __name__ == "__main__":
+    __tracebackhide__: bool = True
 
     parser = argparse.ArgumentParser()
     parser.add_argument("--uid", type=parse_uid)

tractor/_debug.py

@@ -1,922 +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/>.
-
-"""
-Multi-core debugging for da peeps!
-
-"""
-from __future__ import annotations
-import bdb
-import os
-import sys
-import signal
-from functools import (
-    partial,
-    cached_property,
-)
-from contextlib import asynccontextmanager as acm
-from typing import (
-    Any,
-    Optional,
-    Callable,
-    AsyncIterator,
-    AsyncGenerator,
-)
-from types import FrameType
-
-import pdbp
-import tractor
-import trio
-from trio_typing import TaskStatus
-
-from .log import get_logger
-from ._discovery import get_root
-from ._state import (
-    is_root_process,
-    debug_mode,
-)
-from ._exceptions import (
-    is_multi_cancelled,
-    ContextCancelled,
-)
-from ._ipc import Channel
-
-log = get_logger(__name__)
-
-
-__all__ = ['breakpoint', 'post_mortem']
-
-
-class Lock:
-    '''
-    Actor global debug lock state.
-
-    Mostly to avoid a lot of ``global`` declarations for now XD.
-
-    '''
-    repl: MultiActorPdb | None = None
-    # placeholder for function to set a ``trio.Event`` on debugger exit
-    # pdb_release_hook: Optional[Callable] = None
-
-    _trio_handler: Callable[
-        [int, Optional[FrameType]], Any
-    ] | int | None = None
-
-    # actor-wide variable pointing to current task name using debugger
-    local_task_in_debug: str | None = None
-
-    # NOTE: set by the current task waiting on the root tty lock from
-    # the CALLER side of the `lock_tty_for_child()` context entry-call
-    # and must be cancelled if this actor is cancelled via IPC
-    # request-message otherwise deadlocks with the parent actor may
-    # ensure
-    _debugger_request_cs: Optional[trio.CancelScope] = None
-
-    # NOTE: set only in the root actor for the **local** root spawned task
-    # which has acquired the lock (i.e. this is on the callee side of
-    # the `lock_tty_for_child()` context entry).
-    _root_local_task_cs_in_debug: Optional[trio.CancelScope] = None
-
-    # actor tree-wide actor uid that supposedly has the tty lock
-    global_actor_in_debug: Optional[tuple[str, str]] = None
-
-    local_pdb_complete: Optional[trio.Event] = None
-    no_remote_has_tty: Optional[trio.Event] = None
-
-    # lock in root actor preventing multi-access to local tty
-    _debug_lock: trio.StrictFIFOLock = trio.StrictFIFOLock()
-
-    _orig_sigint_handler: Optional[Callable] = None
-    _blocked: set[tuple[str, str]] = set()
-
-    @classmethod
-    def shield_sigint(cls):
-        cls._orig_sigint_handler = signal.signal(
-            signal.SIGINT,
-            shield_sigint_handler,
-        )
-
-    @classmethod
-    def unshield_sigint(cls):
-        # always restore ``trio``'s sigint handler. see notes below in
-        # the pdb factory about the nightmare that is that code swapping
-        # out the handler when the repl activates...
-        signal.signal(signal.SIGINT, cls._trio_handler)
-        cls._orig_sigint_handler = None
-
-    @classmethod
-    def release(cls):
-        try:
-            cls._debug_lock.release()
-        except RuntimeError:
-            # uhhh makes no sense but been seeing the non-owner
-            # release error even though this is definitely the task
-            # that locked?
-            owner = cls._debug_lock.statistics().owner
-            if owner:
-                raise
-
-        # actor-local state, irrelevant for non-root.
-        cls.global_actor_in_debug = None
-        cls.local_task_in_debug = None
-
-        try:
-            # sometimes the ``trio`` might already be terminated in
-            # which case this call will raise.
-            if cls.local_pdb_complete is not None:
-                cls.local_pdb_complete.set()
-        finally:
-            # restore original sigint handler
-            cls.unshield_sigint()
-            cls.repl = None
-
-
-class TractorConfig(pdbp.DefaultConfig):
-    '''
-    Custom ``pdbp`` goodness :surfer:
-
-    '''
-    use_pygments: bool = True
-    sticky_by_default: bool = False
-    enable_hidden_frames: bool = False
-
-    # much thanks @mdmintz for the hot tip!
-    # fixes line spacing issue when resizing terminal B)
-    truncate_long_lines: bool = False
-
-
-class MultiActorPdb(pdbp.Pdb):
-    '''
-    Add teardown hooks to the regular ``pdbp.Pdb``.
-
-    '''
-    # override the pdbp config with our coolio one
-    DefaultConfig = TractorConfig
-
-    # def preloop(self):
-    #     print('IN PRELOOP')
-    #     super().preloop()
-
-    # TODO: figure out how to disallow recursive .set_trace() entry
-    # since that'll cause deadlock for us.
-    def set_continue(self):
-        try:
-            super().set_continue()
-        finally:
-            Lock.release()
-
-    def set_quit(self):
-        try:
-            super().set_quit()
-        finally:
-            Lock.release()
-
-    # XXX NOTE: we only override this because apparently the stdlib pdb
-    # bois likes to touch the SIGINT handler as much as i like to touch
-    # my d$%&.
-    def _cmdloop(self):
-        self.cmdloop()
-
-    @cached_property
-    def shname(self) -> str | None:
-        '''
-        Attempt to return the login shell name with a special check for
-        the infamous `xonsh` since it seems to have some issues much
-        different from std shells when it comes to flushing the prompt?
-
-        '''
-        # SUPER HACKY and only really works if `xonsh` is not used
-        # before spawning further sub-shells..
-        shpath = os.getenv('SHELL', None)
-
-        if shpath:
-            if (
-                os.getenv('XONSH_LOGIN', default=False)
-                or 'xonsh' in shpath
-            ):
-                return 'xonsh'
-
-            return os.path.basename(shpath)
-
-        return None
-
-
-@acm
-async def _acquire_debug_lock_from_root_task(
-    uid: tuple[str, str]
-
-) -> AsyncIterator[trio.StrictFIFOLock]:
-    '''
-    Acquire a root-actor local FIFO lock which tracks mutex access of
-    the process tree's global debugger breakpoint.
-
-    This lock avoids tty clobbering (by preventing multiple processes
-    reading from stdstreams) and ensures multi-actor, sequential access
-    to the ``pdb`` repl.
-
-    '''
-    task_name = trio.lowlevel.current_task().name
-
-    log.runtime(
-        f"Attempting to acquire TTY lock, remote task: {task_name}:{uid}"
-    )
-
-    we_acquired = False
-
-    try:
-        log.runtime(
-            f"entering lock checkpoint, remote task: {task_name}:{uid}"
-        )
-        we_acquired = True
-
-        # NOTE: if the surrounding cancel scope from the
-        # `lock_tty_for_child()` caller is cancelled, this line should
-        # unblock and NOT leave us in some kind of
-        # a "child-locked-TTY-but-child-is-uncontactable-over-IPC"
-        # condition.
-        await Lock._debug_lock.acquire()
-
-        if Lock.no_remote_has_tty is None:
-            # mark the tty lock as being in use so that the runtime
-            # can try to avoid clobbering any connection from a child
-            # that's currently relying on it.
-            Lock.no_remote_has_tty = trio.Event()
-
-        Lock.global_actor_in_debug = uid
-        log.runtime(f"TTY lock acquired, remote task: {task_name}:{uid}")
-
-        # NOTE: critical section: this yield is unshielded!
-
-        # IF we received a cancel during the shielded lock entry of some
-        # next-in-queue requesting task, then the resumption here will
-        # result in that ``trio.Cancelled`` being raised to our caller
-        # (likely from ``lock_tty_for_child()`` below)!  In
-        # this case the ``finally:`` below should trigger and the
-        # surrounding caller side context should cancel normally
-        # relaying back to the caller.
-
-        yield Lock._debug_lock
-
-    finally:
-        if (
-            we_acquired
-            and Lock._debug_lock.locked()
-        ):
-            Lock._debug_lock.release()
-
-        # IFF there are no more requesting tasks queued up fire, the
-        # "tty-unlocked" event thereby alerting any monitors of the lock that
-        # we are now back in the "tty unlocked" state. This is basically
-        # and edge triggered signal around an empty queue of sub-actor
-        # tasks that may have tried to acquire the lock.
-        stats = Lock._debug_lock.statistics()
-        if (
-            not stats.owner
-        ):
-            log.runtime(f"No more tasks waiting on tty lock! says {uid}")
-            if Lock.no_remote_has_tty is not None:
-                Lock.no_remote_has_tty.set()
-                Lock.no_remote_has_tty = None
-
-        Lock.global_actor_in_debug = None
-
-        log.runtime(
-            f"TTY lock released, remote task: {task_name}:{uid}"
-        )
-
-
-@tractor.context
-async def lock_tty_for_child(
-
-    ctx: tractor.Context,
-    subactor_uid: tuple[str, str]
-
-) -> str:
-    '''
-    Lock the TTY in the root process of an actor tree in a new
-    inter-actor-context-task such that the ``pdbp`` debugger console
-    can be mutex-allocated to the calling sub-actor for REPL control
-    without interference by other processes / threads.
-
-    NOTE: this task must be invoked in the root process of the actor
-    tree. It is meant to be invoked as an rpc-task and should be
-    highly reliable at releasing the mutex complete!
-
-    '''
-    task_name = trio.lowlevel.current_task().name
-
-    if tuple(subactor_uid) in Lock._blocked:
-        log.warning(
-            f'Actor {subactor_uid} is blocked from acquiring debug lock\n'
-            f"remote task: {task_name}:{subactor_uid}"
-        )
-        ctx._enter_debugger_on_cancel = False
-        await ctx.cancel(f'Debug lock blocked for {subactor_uid}')
-        return 'pdb_lock_blocked'
-
-    # TODO: when we get to true remote debugging
-    # this will deliver stdin data?
-
-    log.debug(
-        "Attempting to acquire TTY lock\n"
-        f"remote task: {task_name}:{subactor_uid}"
-    )
-
-    log.debug(f"Actor {subactor_uid} is WAITING on stdin hijack lock")
-    Lock.shield_sigint()
-
-    try:
-        with (
-            trio.CancelScope(shield=True) as debug_lock_cs,
-        ):
-            Lock._root_local_task_cs_in_debug = debug_lock_cs
-            async with _acquire_debug_lock_from_root_task(subactor_uid):
-
-                # indicate to child that we've locked stdio
-                await ctx.started('Locked')
-                log.debug(
-                    f"Actor {subactor_uid} acquired stdin hijack lock"
-                )
-
-                # wait for unlock pdb by child
-                async with ctx.open_stream() as stream:
-                    assert await stream.receive() == 'pdb_unlock'
-
-        return "pdb_unlock_complete"
-
-    finally:
-        Lock._root_local_task_cs_in_debug = None
-        Lock.unshield_sigint()
-
-
-async def wait_for_parent_stdin_hijack(
-    actor_uid: tuple[str, str],
-    task_status: TaskStatus[trio.CancelScope] = trio.TASK_STATUS_IGNORED
-):
-    '''
-    Connect to the root actor via a ``Context`` and invoke a task which
-    locks a root-local TTY lock: ``lock_tty_for_child()``; this func
-    should be called in a new task from a child actor **and never the
-    root*.
-
-    This function is used by any sub-actor to acquire mutex access to
-    the ``pdb`` REPL and thus the root's TTY for interactive debugging
-    (see below inside ``_breakpoint()``). It can be used to ensure that
-    an intermediate nursery-owning actor does not clobber its children
-    if they are in debug (see below inside
-    ``maybe_wait_for_debugger()``).
-
-    '''
-    with trio.CancelScope(shield=True) as cs:
-        Lock._debugger_request_cs = cs
-
-        try:
-            async with get_root() as portal:
-
-                # this syncs to child's ``Context.started()`` call.
-                async with portal.open_context(
-
-                    tractor._debug.lock_tty_for_child,
-                    subactor_uid=actor_uid,
-
-                ) as (ctx, val):
-
-                    log.debug('locked context')
-                    assert val == 'Locked'
-
-                    async with ctx.open_stream() as stream:
-                        # unblock local caller
-
-                        try:
-                            assert Lock.local_pdb_complete
-                            task_status.started(cs)
-                            await Lock.local_pdb_complete.wait()
-
-                        finally:
-                            # TODO: shielding currently can cause hangs...
-                            # with trio.CancelScope(shield=True):
-                            await stream.send('pdb_unlock')
-
-                        # sync with callee termination
-                        assert await ctx.result() == "pdb_unlock_complete"
-
-                log.debug('exitting child side locking task context')
-
-        except ContextCancelled:
-            log.warning('Root actor cancelled debug lock')
-            raise
-
-        finally:
-            Lock.local_task_in_debug = None
-            log.debug('Exiting debugger from child')
-
-
-def mk_mpdb() -> tuple[MultiActorPdb, Callable]:
-
-    pdb = MultiActorPdb()
-    # signal.signal = pdbp.hideframe(signal.signal)
-
-    Lock.shield_sigint()
-
-    # XXX: These are the important flags mentioned in
-    # https://github.com/python-trio/trio/issues/1155
-    # which resolve the traceback spews to console.
-    pdb.allow_kbdint = True
-    pdb.nosigint = True
-
-    return pdb, Lock.unshield_sigint
-
-
-async def _breakpoint(
-
-    debug_func,
-
-    # TODO:
-    # shield: bool = False
-
-) -> None:
-    '''
-    Breakpoint entry for engaging debugger instance sync-interaction,
-    from async code, executing in actor runtime (task).
-
-    '''
-    __tracebackhide__ = True
-    actor = tractor.current_actor()
-    pdb, undo_sigint = mk_mpdb()
-    task_name = trio.lowlevel.current_task().name
-
-    # TODO: is it possible to debug a trio.Cancelled except block?
-    # right now it seems like we can kinda do with by shielding
-    # around ``tractor.breakpoint()`` but not if we move the shielded
-    # scope here???
-    # with trio.CancelScope(shield=shield):
-    #     await trio.lowlevel.checkpoint()
-
-    if (
-        not Lock.local_pdb_complete
-        or Lock.local_pdb_complete.is_set()
-    ):
-        Lock.local_pdb_complete = trio.Event()
-
-    # TODO: need a more robust check for the "root" actor
-    if (
-        not is_root_process()
-        and actor._parent_chan  # a connected child
-    ):
-
-        if Lock.local_task_in_debug:
-
-            # Recurrence entry case: this task already has the lock and
-            # is likely recurrently entering a breakpoint
-            if Lock.local_task_in_debug == task_name:
-                # noop on recurrent entry case but we want to trigger
-                # a checkpoint to allow other actors error-propagate and
-                # potetially avoid infinite re-entries in some subactor.
-                await trio.lowlevel.checkpoint()
-                return
-
-            # if **this** actor is already in debug mode block here
-            # waiting for the control to be released - this allows
-            # support for recursive entries to `tractor.breakpoint()`
-            log.warning(f"{actor.uid} already has a debug lock, waiting...")
-
-            await Lock.local_pdb_complete.wait()
-            await trio.sleep(0.1)
-
-        # mark local actor as "in debug mode" to avoid recurrent
-        # entries/requests to the root process
-        Lock.local_task_in_debug = task_name
-
-        # this **must** be awaited by the caller and is done using the
-        # root nursery so that the debugger can continue to run without
-        # being restricted by the scope of a new task nursery.
-
-        # TODO: if we want to debug a trio.Cancelled triggered exception
-        # we have to figure out how to avoid having the service nursery
-        # cancel on this task start? I *think* this works below:
-        # ```python
-        #   actor._service_n.cancel_scope.shield = shield
-        # ```
-        # but not entirely sure if that's a sane way to implement it?
-        try:
-            with trio.CancelScope(shield=True):
-                await actor._service_n.start(
-                    wait_for_parent_stdin_hijack,
-                    actor.uid,
-                )
-                Lock.repl = pdb
-        except RuntimeError:
-            Lock.release()
-
-            if actor._cancel_called:
-                # service nursery won't be usable and we
-                # don't want to lock up the root either way since
-                # we're in (the midst of) cancellation.
-                return
-
-            raise
-
-    elif is_root_process():
-
-        # we also wait in the root-parent for any child that
-        # may have the tty locked prior
-        # TODO: wait, what about multiple root tasks acquiring it though?
-        if Lock.global_actor_in_debug == actor.uid:
-            # re-entrant root process already has it: noop.
-            return
-
-        # XXX: since we need to enter pdb synchronously below,
-        # we have to release the lock manually from pdb completion
-        # callbacks. Can't think of a nicer way then this atm.
-        if Lock._debug_lock.locked():
-            log.warning(
-                'Root actor attempting to shield-acquire active tty lock'
-                f' owned by {Lock.global_actor_in_debug}')
-
-            # must shield here to avoid hitting a ``Cancelled`` and
-            # a child getting stuck bc we clobbered the tty
-            with trio.CancelScope(shield=True):
-                await Lock._debug_lock.acquire()
-        else:
-            # may be cancelled
-            await Lock._debug_lock.acquire()
-
-        Lock.global_actor_in_debug = actor.uid
-        Lock.local_task_in_debug = task_name
-        Lock.repl = pdb
-
-    try:
-        # block here one (at the appropriate frame *up*) where
-        # ``breakpoint()`` was awaited and begin handling stdio.
-        log.debug("Entering the synchronous world of pdb")
-        debug_func(actor, pdb)
-
-    except bdb.BdbQuit:
-        Lock.release()
-        raise
-
-    # XXX: apparently we can't do this without showing this frame
-    # in the backtrace on first entry to the REPL? Seems like an odd
-    # behaviour that should have been fixed by now. This is also why
-    # we scrapped all the @cm approaches that were tried previously.
-    # finally:
-    #     __tracebackhide__ = True
-    #     # frame = sys._getframe()
-    #     # last_f = frame.f_back
-    #     # last_f.f_globals['__tracebackhide__'] = True
-    #     # signal.signal = pdbp.hideframe(signal.signal)
-
-
-def shield_sigint_handler(
-    signum: int,
-    frame: 'frame',  # type: ignore # noqa
-    # pdb_obj: Optional[MultiActorPdb] = None,
-    *args,
-
-) -> None:
-    '''
-    Specialized, debugger-aware SIGINT handler.
-
-    In childred we always ignore to avoid deadlocks since cancellation
-    should always be managed by the parent supervising actor. The root
-    is always cancelled on ctrl-c.
-
-    '''
-    __tracebackhide__ = True
-
-    uid_in_debug = Lock.global_actor_in_debug
-
-    actor = tractor.current_actor()
-    # print(f'{actor.uid} in HANDLER with ')
-
-    def do_cancel():
-        # If we haven't tried to cancel the runtime then do that instead
-        # of raising a KBI (which may non-gracefully destroy
-        # a ``trio.run()``).
-        if not actor._cancel_called:
-            actor.cancel_soon()
-
-        # If the runtime is already cancelled it likely means the user
-        # hit ctrl-c again because teardown didn't full take place in
-        # which case we do the "hard" raising of a local KBI.
-        else:
-            raise KeyboardInterrupt
-
-    any_connected = False
-
-    if uid_in_debug is not None:
-        # try to see if the supposed (sub)actor in debug still
-        # has an active connection to *this* actor, and if not
-        # it's likely they aren't using the TTY lock / debugger
-        # and we should propagate SIGINT normally.
-        chans = actor._peers.get(tuple(uid_in_debug))
-        if chans:
-            any_connected = any(chan.connected() for chan in chans)
-            if not any_connected:
-                log.warning(
-                    'A global actor reported to be in debug '
-                    'but no connection exists for this child:\n'
-                    f'{uid_in_debug}\n'
-                    'Allowing SIGINT propagation..'
-                )
-                return do_cancel()
-
-    # only set in the actor actually running the REPL
-    pdb_obj = Lock.repl
-
-    # root actor branch that reports whether or not a child
-    # has locked debugger.
-    if (
-        is_root_process()
-        and uid_in_debug is not None
-
-        # XXX: only if there is an existing connection to the
-        # (sub-)actor in debug do we ignore SIGINT in this
-        # parent! Otherwise we may hang waiting for an actor
-        # which has already terminated to unlock.
-        and any_connected
-    ):
-        # we are root and some actor is in debug mode
-        # if uid_in_debug is not None:
-
-        if pdb_obj:
-            name = uid_in_debug[0]
-            if name != 'root':
-                log.pdb(
-                    f"Ignoring SIGINT, child in debug mode: `{uid_in_debug}`"
-                )
-
-            else:
-                log.pdb(
-                    "Ignoring SIGINT while in debug mode"
-                )
-    elif (
-        is_root_process()
-    ):
-        if pdb_obj:
-            log.pdb(
-                "Ignoring SIGINT since debug mode is enabled"
-            )
-
-        if (
-            Lock._root_local_task_cs_in_debug
-            and not Lock._root_local_task_cs_in_debug.cancel_called
-        ):
-            Lock._root_local_task_cs_in_debug.cancel()
-
-            # revert back to ``trio`` handler asap!
-            Lock.unshield_sigint()
-
-    # child actor that has locked the debugger
-    elif not is_root_process():
-
-        chan: Channel = actor._parent_chan
-        if not chan or not chan.connected():
-            log.warning(
-                'A global actor reported to be in debug '
-                'but no connection exists for its parent:\n'
-                f'{uid_in_debug}\n'
-                'Allowing SIGINT propagation..'
-            )
-            return do_cancel()
-
-        task = Lock.local_task_in_debug
-        if (
-            task
-            and pdb_obj
-        ):
-            log.pdb(
-                f"Ignoring SIGINT while task in debug mode: `{task}`"
-            )
-
-        # TODO: how to handle the case of an intermediary-child actor
-        # that **is not** marked in debug mode? See oustanding issue:
-        # https://github.com/goodboy/tractor/issues/320
-        # elif debug_mode():
-
-    else:  # XXX: shouldn't ever get here?
-        print("WTFWTFWTF")
-        raise KeyboardInterrupt
-
-    # NOTE: currently (at least on ``fancycompleter`` 0.9.2)
-    # it looks to be that the last command that was run (eg. ll)
-    # will be repeated by default.
-
-    # maybe redraw/print last REPL output to console since
-    # we want to alert the user that more input is expect since
-    # nothing has been done dur to ignoring sigint.
-    if (
-        pdb_obj  # only when this actor has a REPL engaged
-    ):
-        # XXX: yah, mega hack, but how else do we catch this madness XD
-        if pdb_obj.shname == 'xonsh':
-            pdb_obj.stdout.write(pdb_obj.prompt)
-
-        pdb_obj.stdout.flush()
-
-        # TODO: make this work like sticky mode where if there is output
-        # detected as written to the tty we redraw this part underneath
-        # and erase the past draw of this same bit above?
-        # pdb_obj.sticky = True
-        # pdb_obj._print_if_sticky()
-
-        # also see these links for an approach from ``ptk``:
-        # https://github.com/goodboy/tractor/issues/130#issuecomment-663752040
-        # https://github.com/prompt-toolkit/python-prompt-toolkit/blob/c2c6af8a0308f9e5d7c0e28cb8a02963fe0ce07a/prompt_toolkit/patch_stdout.py
-
-        # XXX LEGACY: lol, see ``pdbpp`` issue:
-        # https://github.com/pdbpp/pdbpp/issues/496
-
-
-def _set_trace(
-    actor: tractor.Actor | None = None,
-    pdb: MultiActorPdb | None = None,
-):
-    __tracebackhide__ = True
-    actor = actor or tractor.current_actor()
-
-    # start 2 levels up in user code
-    frame: Optional[FrameType] = sys._getframe()
-    if frame:
-        frame = frame.f_back  # type: ignore
-
-    if (
-        frame
-        and pdb
-        and actor is not None
-    ):
-        log.pdb(f"\nAttaching pdb to actor: {actor.uid}\n")
-        # no f!#$&* idea, but when we're in async land
-        # we need 2x frames up?
-        frame = frame.f_back
-
-    else:
-        pdb, undo_sigint = mk_mpdb()
-
-        # we entered the global ``breakpoint()`` built-in from sync
-        # code?
-        Lock.local_task_in_debug = 'sync'
-
-    pdb.set_trace(frame=frame)
-
-
-breakpoint = partial(
-    _breakpoint,
-    _set_trace,
-)
-
-
-def _post_mortem(
-    actor: tractor.Actor,
-    pdb: MultiActorPdb,
-
-) -> None:
-    '''
-    Enter the ``pdbpp`` port mortem entrypoint using our custom
-    debugger instance.
-
-    '''
-    log.pdb(f"\nAttaching to pdb in crashed actor: {actor.uid}\n")
-
-    # TODO: you need ``pdbpp`` master (at least this commit
-    # https://github.com/pdbpp/pdbpp/commit/b757794857f98d53e3ebbe70879663d7d843a6c2)
-    # to fix this and avoid the hang it causes. See issue:
-    # https://github.com/pdbpp/pdbpp/issues/480
-    # TODO: help with a 3.10+ major release if/when it arrives.
-
-    pdbp.xpm(Pdb=lambda: pdb)
-
-
-post_mortem = partial(
-    _breakpoint,
-    _post_mortem,
-)
-
-
-async def _maybe_enter_pm(err):
-    if (
-        debug_mode()
-
-        # NOTE: don't enter debug mode recursively after quitting pdb
-        # Iow, don't re-enter the repl if the `quit` command was issued
-        # by the user.
-        and not isinstance(err, bdb.BdbQuit)
-
-        # XXX: if the error is the likely result of runtime-wide
-        # cancellation, we don't want to enter the debugger since
-        # there's races between when the parent actor has killed all
-        # comms and when the child tries to contact said parent to
-        # acquire the tty lock.
-
-        # Really we just want to mostly avoid catching KBIs here so there
-        # might be a simpler check we can do?
-        and not is_multi_cancelled(err)
-    ):
-        log.debug("Actor crashed, entering debug mode")
-        try:
-            await post_mortem()
-        finally:
-            Lock.release()
-            return True
-
-    else:
-        return False
-
-
-@acm
-async def acquire_debug_lock(
-    subactor_uid: tuple[str, str],
-) -> AsyncGenerator[None, tuple]:
-    '''
-    Grab root's debug lock on entry, release on exit.
-
-    This helper is for actor's who don't actually need
-    to acquired the debugger but want to wait until the
-    lock is free in the process-tree root.
-
-    '''
-    if not debug_mode():
-        yield None
-        return
-
-    async with trio.open_nursery() as n:
-        cs = await n.start(
-            wait_for_parent_stdin_hijack,
-            subactor_uid,
-        )
-        yield None
-        cs.cancel()
-
-
-async def maybe_wait_for_debugger(
-    poll_steps: int = 2,
-    poll_delay: float = 0.1,
-    child_in_debug: bool = False,
-
-) -> None:
-
-    if (
-        not debug_mode()
-        and not child_in_debug
-    ):
-        return
-
-    if (
-        is_root_process()
-    ):
-        # If we error in the root but the debugger is
-        # engaged we don't want to prematurely kill (and
-        # thus clobber access to) the local tty since it
-        # will make the pdb repl unusable.
-        # Instead try to wait for pdb to be released before
-        # tearing down.
-
-        sub_in_debug = None
-
-        for _ in range(poll_steps):
-
-            if Lock.global_actor_in_debug:
-                sub_in_debug = tuple(Lock.global_actor_in_debug)
-
-            log.debug('Root polling for debug')
-
-            with trio.CancelScope(shield=True):
-                await trio.sleep(poll_delay)
-
-                # TODO: could this make things more deterministic?  wait
-                # to see if a sub-actor task will be scheduled and grab
-                # the tty lock on the next tick?
-                # XXX: doesn't seem to work
-                # await trio.testing.wait_all_tasks_blocked(cushion=0)
-
-                debug_complete = Lock.no_remote_has_tty
-                if (
-                    (debug_complete and
-                     not debug_complete.is_set())
-                ):
-                    log.debug(
-                        'Root has errored but pdb is in use by '
-                        f'child {sub_in_debug}\n'
-                        'Waiting on tty lock to release..')
-
-                    await debug_complete.wait()
-
-                await trio.sleep(poll_delay)
-                continue
-        else:
-            log.debug(
-                    'Root acquired TTY LOCK'
-            )

tractor/_discovery.py

@@ -15,50 +15,71 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 """
-Actor discovery API.
+Discovery (protocols) API for automatic addressing and location
+management of (service) actors.
 
 """
+from __future__ import annotations
 from typing import (
-    Optional,
-    Union,
     AsyncGenerator,
+    AsyncContextManager,
+    TYPE_CHECKING,
 )
 from contextlib import asynccontextmanager as acm
 
+from tractor.log import get_logger
+from .trionics import gather_contexts
 from ._ipc import _connect_chan, Channel
 from ._portal import (
     Portal,
     open_portal,
     LocalPortal,
 )
-from ._state import current_actor, _runtime_vars
+from ._state import (
+    current_actor,
+    _runtime_vars,
+)
+
+if TYPE_CHECKING:
+    from ._runtime import Actor
+
+
+log = get_logger(__name__)
 
 
 @acm
-async def get_arbiter(
+async def get_registry(
-
     host: str,
     port: int,
 
-) -> AsyncGenerator[Union[Portal, LocalPortal], None]:
+) -> AsyncGenerator[
-    '''Return a portal instance connected to a local or remote
+    Portal | LocalPortal | None,
-    arbiter.
+    None,
+]:
     '''
-    actor = current_actor()
+    Return a portal instance connected to a local or remote
+    registry-service actor; if a connection already exists re-use it
+    (presumably to call a `.register_actor()` registry runtime RPC
+    ep).
 
-    if not actor:
+    '''
-        raise RuntimeError("No actor instance has been defined yet?")
+    actor: Actor = current_actor()
-
+    if actor.is_registrar:
-    if actor.is_arbiter:
         # we're already the arbiter
         # (likely a re-entrant call from the arbiter actor)
-        yield LocalPortal(actor, Channel((host, port)))
+        yield LocalPortal(
+            actor,
+            Channel((host, port))
+        )
     else:
-        async with _connect_chan(host, port) as chan:
+        # TODO: try to look pre-existing connection from
+        # `Actor._peers` and use it instead?
+        async with (
+            _connect_chan(host, port) as chan,
+            open_portal(chan) as regstr_ptl,
+        ):
+            yield regstr_ptl
 
-            async with open_portal(chan) as arb_portal:
-
-                yield arb_portal
 
 
 @acm
@@ -66,51 +87,125 @@ async def get_root(
     **kwargs,
 ) -> AsyncGenerator[Portal, None]:
 
+    # TODO: rename mailbox to `_root_maddr` when we finally
+    # add and impl libp2p multi-addrs?
     host, port = _runtime_vars['_root_mailbox']
     assert host is not None
 
-    async with _connect_chan(host, port) as chan:
+    async with (
-        async with open_portal(chan, **kwargs) as portal:
+        _connect_chan(host, port) as chan,
-            yield portal
+        open_portal(chan, **kwargs) as portal,
+    ):
+        yield portal
+
+
+def get_peer_by_name(
+    name: str,
+    # uuid: str|None = None,
+
+) -> list[Channel]|None:  # at least 1
+    '''
+    Scan for an existing connection (set) to a named actor
+    and return any channels from `Actor._peers`.
+
+    This is an optimization method over querying the registrar for
+    the same info.
+
+    '''
+    actor: Actor = current_actor()
+    to_scan: dict[tuple, list[Channel]] = actor._peers.copy()
+    pchan: Channel|None = actor._parent_chan
+    if pchan:
+        to_scan[pchan.uid].append(pchan)
+
+    for aid, chans in to_scan.items():
+        _, peer_name = aid
+        if name == peer_name:
+            if not chans:
+                log.warning(
+                    'No IPC chans for matching peer {peer_name}\n'
+                )
+                continue
+            return chans
+
+    return None
 
 
 @acm
 async def query_actor(
     name: str,
-    arbiter_sockaddr: Optional[tuple[str, int]] = None,
+    regaddr: tuple[str, int]|None = None,
 
-) -> AsyncGenerator[tuple[str, int], None]:
+) -> AsyncGenerator[
+    tuple[str, int]|None,
+    None,
+]:
     '''
-    Simple address lookup for a given actor name.
+    Lookup a transport address (by actor name) via querying a registrar
+    listening @ `regaddr`.
 
-    Returns the (socket) address or ``None``.
+    Returns the transport protocol (socket) address or `None` if no
+    entry under that name exists.
 
     '''
-    actor = current_actor()
+    actor: Actor = current_actor()
-    async with get_arbiter(
+    if (
-        *arbiter_sockaddr or actor._arb_addr
+        name == 'registrar'
-    ) as arb_portal:
+        and actor.is_registrar
+    ):
+        raise RuntimeError(
+            'The current actor IS the registry!?'
+        )
 
-        sockaddr = await arb_portal.run_from_ns(
+    maybe_peers: list[Channel]|None = get_peer_by_name(name)
+    if maybe_peers:
+        yield maybe_peers[0].raddr
+        return
+
+    reg_portal: Portal
+    regaddr: tuple[str, int] = regaddr or actor.reg_addrs[0]
+    async with get_registry(*regaddr) as reg_portal:
+        # TODO: return portals to all available actors - for now
+        # just the last one that registered
+        sockaddr: tuple[str, int] = await reg_portal.run_from_ns(
             'self',
             'find_actor',
             name=name,
         )
+        yield sockaddr
 
-        # TODO: return portals to all available actors - for now just
-        # the last one that registered
-        if name == 'arbiter' and actor.is_arbiter:
-            raise RuntimeError("The current actor is the arbiter")
 
-        yield sockaddr if sockaddr else None
+@acm
+async def maybe_open_portal(
+    addr: tuple[str, int],
+    name: str,
+):
+    async with query_actor(
+        name=name,
+        regaddr=addr,
+    ) as sockaddr:
+        pass
+
+    if sockaddr:
+        async with _connect_chan(*sockaddr) as chan:
+            async with open_portal(chan) as portal:
+                yield portal
+    else:
+        yield None
 
 
 @acm
 async def find_actor(
     name: str,
-    arbiter_sockaddr: tuple[str, int] | None = None
+    registry_addrs: list[tuple[str, int]]|None = None,
 
-) -> AsyncGenerator[Optional[Portal], None]:
+    only_first: bool = True,
+    raise_on_none: bool = False,
+
+) -> AsyncGenerator[
+    Portal | list[Portal] | None,
+    None,
+]:
     '''
     Ask the arbiter to find actor(s) by name.
 
@@ -118,39 +213,102 @@ async def find_actor(
     known to the arbiter.
 
     '''
-    async with query_actor(
+    # optimization path, use any pre-existing peer channel
-        name=name,
+    maybe_peers: list[Channel]|None = get_peer_by_name(name)
-        arbiter_sockaddr=arbiter_sockaddr,
+    if maybe_peers and only_first:
-    ) as sockaddr:
+        async with open_portal(maybe_peers[0]) as peer_portal:
+            yield peer_portal
+            return
 
-        if sockaddr:
+    if not registry_addrs:
-            async with _connect_chan(*sockaddr) as chan:
+        # XXX NOTE: make sure to dynamically read the value on
-                async with open_portal(chan) as portal:
+        # every call since something may change it globally (eg.
-                    yield portal
+        # like in our discovery test suite)!
-        else:
+        from . import _root
+        registry_addrs = (
+            _runtime_vars['_registry_addrs']
+            or
+            _root._default_lo_addrs
+        )
+
+    maybe_portals: list[
+        AsyncContextManager[tuple[str, int]]
+    ] = list(
+        maybe_open_portal(
+            addr=addr,
+            name=name,
+        )
+        for addr in registry_addrs
+    )
+    portals: list[Portal]
+    async with gather_contexts(
+        mngrs=maybe_portals,
+    ) as portals:
+        # log.runtime(
+        #     'Gathered portals:\n'
+        #     f'{portals}'
+        # )
+        # NOTE: `gather_contexts()` will return a
+        # `tuple[None, None, ..., None]` if no contact
+        # can be made with any regstrar at any of the
+        # N provided addrs!
+        if not any(portals):
+            if raise_on_none:
+                raise RuntimeError(
+                    f'No actor "{name}" found registered @ {registry_addrs}'
+                )
             yield None
+            return
+
+        portals: list[Portal] = list(portals)
+        if only_first:
+            yield portals[0]
+
+        else:
+            # TODO: currently this may return multiple portals
+            # given there are multi-homed or multiple registrars..
+            # SO, we probably need de-duplication logic?
+            yield portals
 
 
 @acm
 async def wait_for_actor(
     name: str,
-    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 at least one peer actor to register `name` with the
+    registrar, yield a `Portal to the first registree.
 
-    A portal to the first registered actor is returned.
+    '''
-    """
+    actor: Actor = current_actor()
-    actor = current_actor()
 
-    async with get_arbiter(
+    # optimization path, use any pre-existing peer channel
-        *arbiter_sockaddr or actor._arb_addr,
+    maybe_peers: list[Channel]|None = get_peer_by_name(name)
-    ) as arb_portal:
+    if maybe_peers:
-        sockaddrs = await arb_portal.run_from_ns(
+        async with open_portal(maybe_peers[0]) as peer_portal:
+            yield peer_portal
+            return
+
+    regaddr: tuple[str, int] = (
+        registry_addr
+        or
+        actor.reg_addrs[0]
+    )
+    # TODO: use `.trionics.gather_contexts()` like
+    # above in `find_actor()` as well?
+    reg_portal: Portal
+    async with get_registry(*regaddr) as reg_portal:
+        sockaddrs = await reg_portal.run_from_ns(
             'self',
             'wait_for_actor',
             name=name,
         )
-        sockaddr = sockaddrs[-1]
+
+        # get latest registered addr by default?
+        # TODO: offer multi-portal yields in multi-homed case?
+        sockaddr: tuple[str, int] = sockaddrs[-1]
 
         async with _connect_chan(*sockaddr) as chan:
             async with open_portal(chan) as portal:

tractor/_entry.py

@@ -20,6 +20,9 @@ Sub-process entry points.
 """
 from __future__ import annotations
 from functools import partial
+import multiprocessing as mp
+import os
+import textwrap
 from typing import (
     Any,
     TYPE_CHECKING,
@@ -32,6 +35,7 @@ from .log import (
     get_logger,
 )
 from . import _state
+from .devx import _debug
 from .to_asyncio import run_as_asyncio_guest
 from ._runtime import (
     async_main,
@@ -47,8 +51,8 @@ log = get_logger(__name__)
 
 def _mp_main(
 
-    actor: Actor,  # type: ignore
+    actor: Actor,
-    accept_addr: tuple[str, int],
+    accept_addrs: list[tuple[str, int]],
     forkserver_info: tuple[Any, Any, Any, Any, Any],
     start_method: SpawnMethodKey,
     parent_addr: tuple[str, int] | None = None,
@@ -56,29 +60,31 @@ def _mp_main(
 
 ) -> None:
     '''
-    The routine called *after fork* which invokes a fresh ``trio.run``
+    The routine called *after fork* which invokes a fresh `trio.run()`
 
     '''
     actor._forkserver_info = forkserver_info
     from ._spawn import try_set_start_method
-    spawn_ctx = try_set_start_method(start_method)
+    spawn_ctx: mp.context.BaseContext = try_set_start_method(start_method)
+    assert spawn_ctx
 
     if actor.loglevel is not None:
         log.info(
-            f"Setting loglevel for {actor.uid} to {actor.loglevel}")
+            f'Setting loglevel for {actor.uid} to {actor.loglevel}'
+        )
         get_console_log(actor.loglevel)
 
-    assert spawn_ctx
+    # TODO: use scops headers like for `trio` below!
+    # (well after we libify it maybe..)
     log.info(
-        f"Started new {spawn_ctx.current_process()} for {actor.uid}")
+        f'Started new {spawn_ctx.current_process()} for {actor.uid}'
-
+    #     f"parent_addr is {parent_addr}"
-    _state._current_actor = actor
+    )
-
+    _state._current_actor: Actor = actor
-    log.debug(f"parent_addr is {parent_addr}")
     trio_main = partial(
         async_main,
-        actor,
+        actor=actor,
-        accept_addr,
+        accept_addrs=accept_addrs,
         parent_addr=parent_addr
     )
     try:
@@ -91,12 +97,114 @@ def _mp_main(
         pass  # handle it the same way trio does?
 
     finally:
-        log.info(f"Actor {actor.uid} terminated")
+        log.info(
+            f'`mp`-subactor {actor.uid} exited'
+        )
+
+
+# TODO: move this func to some kinda `.devx._conc_lang.py` eventually
+# as we work out our multi-domain state-flow-syntax!
+def nest_from_op(
+    input_op: str,
+    #
+    # ?TODO? an idea for a syntax to the state of concurrent systems
+    # as a "3-domain" (execution, scope, storage) model and using
+    # a minimal ascii/utf-8 operator-set.
+    #
+    # try not to take any of this seriously yet XD
+    #
+    # > is a "play operator" indicating (CPU bound)
+    #   exec/work/ops required at the "lowest level computing"
+    #
+    # execution primititves (tasks, threads, actors..) denote their
+    # lifetime with '(' and ')' since parentheses normally are used
+    # in many langs to denote function calls.
+    #
+    # starting = (
+    # >(  opening/starting; beginning of the thread-of-exec (toe?)
+    # (>  opened/started,  (finished spawning toe)
+    # |_<Task: blah blah..>  repr of toe, in py these look like <objs>
+    #
+    # >) closing/exiting/stopping,
+    # )> closed/exited/stopped,
+    # |_<Task: blah blah..>
+    #   [OR <), )< ?? ]
+    #
+    # ending = )
+    # >c) cancelling to close/exit
+    # c)> cancelled (caused close), OR?
+    #  |_<Actor: ..>
+    #   OR maybe "<c)" which better indicates the cancel being
+    #   "delivered/returned" / returned" to LHS?
+    #
+    # >x)  erroring to eventuall exit
+    # x)>  errored and terminated
+    #  |_<Actor: ...>
+    #
+    # scopes: supers/nurseries, IPC-ctxs, sessions, perms, etc.
+    # >{  opening
+    # {>  opened
+    # }>  closed
+    # >}  closing
+    #
+    # storage: like queues, shm-buffers, files, etc..
+    # >[  opening
+    # [>  opened
+    #  |_<FileObj: ..>
+    #
+    # >]  closing
+    # ]>  closed
+
+    # IPC ops: channels, transports, msging
+    # =>  req msg
+    # <=  resp msg
+    # <=> 2-way streaming (of msgs)
+    # <-  recv 1 msg
+    # ->  send 1 msg
+    #
+    # TODO: still not sure on R/L-HS approach..?
+    # =>(  send-req to exec start (task, actor, thread..)
+    # (<=  recv-req to ^
+    #
+    # (<=  recv-req ^
+    # <=(  recv-resp opened remote exec primitive
+    # <=)  recv-resp closed
+    #
+    # )<=c req to stop due to cancel
+    # c=>) req to stop due to cancel
+    #
+    # =>{  recv-req to open
+    # <={  send-status that it closed
+
+    tree_str: str,
+
+    # NOTE: so move back-from-the-left of the `input_op` by
+    # this amount.
+    back_from_op: int = 0,
+) -> str:
+    '''
+    Depth-increment the input (presumably hierarchy/supervision)
+    input "tree string" below the provided `input_op` execution
+    operator, so injecting a `"\n|_{input_op}\n"`and indenting the
+    `tree_str` to nest content aligned with the ops last char.
+
+    '''
+    return (
+        f'{input_op}\n'
+        +
+        textwrap.indent(
+            tree_str,
+            prefix=(
+                len(input_op)
+                -
+                (back_from_op + 1)
+            ) * ' ',
+        )
+    )
 
 
 def _trio_main(
-
+    actor: Actor,
-    actor: Actor,  # type: ignore
     *,
     parent_addr: tuple[str, int] | None = None,
     infect_asyncio: bool = False,
@@ -106,33 +214,73 @@ def _trio_main(
     Entry point for a `trio_run_in_process` subactor.
 
     '''
-    log.info(f"Started new trio process for {actor.uid}")
+    _debug.hide_runtime_frames()
-
-    if actor.loglevel is not None:
-        log.info(
-            f"Setting loglevel for {actor.uid} to {actor.loglevel}")
-        get_console_log(actor.loglevel)
-
-    log.info(
-        f"Started {actor.uid}")
 
     _state._current_actor = actor
-
-    log.debug(f"parent_addr is {parent_addr}")
     trio_main = partial(
         async_main,
         actor,
         parent_addr=parent_addr
     )
 
+    if actor.loglevel is not None:
+        get_console_log(actor.loglevel)
+        actor_info: str = (
+            f'|_{actor}\n'
+            f'  uid: {actor.uid}\n'
+            f'  pid: {os.getpid()}\n'
+            f'  parent_addr: {parent_addr}\n'
+            f'  loglevel: {actor.loglevel}\n'
+        )
+        log.info(
+            'Starting new `trio` subactor:\n'
+            +
+            nest_from_op(
+                input_op='>(',  # see syntax ideas above
+                tree_str=actor_info,
+                back_from_op=1,
+            )
+        )
+    logmeth = log.info
+    exit_status: str = (
+        'Subactor exited\n'
+        +
+        nest_from_op(
+            input_op=')>',  # like a "closed-to-play"-icon from super perspective
+            tree_str=actor_info,
+            back_from_op=1,
+        )
+    )
     try:
         if infect_asyncio:
             actor._infected_aio = True
             run_as_asyncio_guest(trio_main)
         else:
             trio.run(trio_main)
+
     except KeyboardInterrupt:
-        log.warning(f"Actor {actor.uid} received KBI")
+        logmeth = log.cancel
+        exit_status: str = (
+            'Actor received KBI (aka an OS-cancel)\n'
+            +
+            nest_from_op(
+                input_op='c)>',  # closed due to cancel (see above)
+                tree_str=actor_info,
+            )
+        )
+    except BaseException as err:
+        logmeth = log.error
+        exit_status: str = (
+            'Main actor task exited due to crash?\n'
+            +
+            nest_from_op(
+                input_op='x)>',  # closed by error
+                tree_str=actor_info,
+            )
+        )
+        # NOTE since we raise a tb will already be shown on the
+        # console, thus we do NOT use `.exception()` above.
+        raise err
 
     finally:
-        log.info(f"Actor {actor.uid} terminated")
+        logmeth(exit_status)

tractor/_ipc.py

@@ -19,38 +19,64 @@ Inter-process comms abstractions
 
 """
 from __future__ import annotations
-import platform
-import struct
-import typing
 from collections.abc import (
     AsyncGenerator,
     AsyncIterator,
 )
+from contextlib import (
+    asynccontextmanager as acm,
+    contextmanager as cm,
+)
+import platform
+from pprint import pformat
+import struct
+import typing
 from typing import (
     Any,
+    Callable,
     runtime_checkable,
-    Optional,
     Protocol,
     Type,
     TypeVar,
 )
 
-from tricycle import BufferedReceiveStream
 import msgspec
+from tricycle import BufferedReceiveStream
 import trio
-from async_generator import asynccontextmanager
 
-from .log import get_logger
+from tractor.log import get_logger
-from ._exceptions import TransportClosed
+from tractor._exceptions import (
+    MsgTypeError,
+    pack_from_raise,
+    TransportClosed,
+    _mk_send_mte,
+    _mk_recv_mte,
+)
+from tractor.msg import (
+    _ctxvar_MsgCodec,
+    # _codec,  XXX see `self._codec` sanity/debug checks
+    MsgCodec,
+    types as msgtypes,
+    pretty_struct,
+)
+
 log = get_logger(__name__)
 
-
 _is_windows = platform.system() == 'Windows'
-log = get_logger(__name__)
 
 
-def get_stream_addrs(stream: trio.SocketStream) -> tuple:
+def get_stream_addrs(
-    # should both be IP sockets
+    stream: trio.SocketStream
+) -> tuple[
+    tuple[str, int],  # local
+    tuple[str, int],  # remote
+]:
+    '''
+    Return the `trio` streaming transport prot's socket-addrs for
+    both the local and remote sides as a pair.
+
+    '''
+    # rn, should both be IP sockets
     lsockname = stream.socket.getsockname()
     rsockname = stream.socket.getpeername()
     return (
@@ -59,16 +85,22 @@ def get_stream_addrs(stream: trio.SocketStream) -> tuple:
     )
 
 
-MsgType = TypeVar("MsgType")
+# from tractor.msg.types import MsgType
-
+# ?TODO? this should be our `Union[*msgtypes.__spec__]` alias now right..?
-# TODO: consider using a generic def and indexing with our eventual
+# => BLEH, except can't bc prots must inherit typevar or param-spec
-# msg definition/types?
+#   vars..
-# - https://docs.python.org/3/library/typing.html#typing.Protocol
+MsgType = TypeVar('MsgType')
-# - https://jcristharif.com/msgspec/usage.html#structs
 
 
+# TODO: break up this mod into a subpkg so we can start adding new
+# backends and move this type stuff into a dedicated file.. Bo
+#
 @runtime_checkable
 class MsgTransport(Protocol[MsgType]):
+#
+# ^-TODO-^ consider using a generic def and indexing with our
+# eventual msg definition/types?
+# - https://docs.python.org/3/library/typing.html#typing.Protocol
 
     stream: trio.SocketStream
     drained: list[MsgType]
@@ -103,20 +135,37 @@ class MsgTransport(Protocol[MsgType]):
         ...
 
 
-# TODO: not sure why we have to inherit here, but it seems to be an
+# TODO: typing oddity.. not sure why we have to inherit here, but it
-# issue with ``get_msg_transport()`` returning a ``Type[Protocol]``;
+# seems to be an issue with `get_msg_transport()` returning
-# probably should make a `mypy` issue?
+# a `Type[Protocol]`; probably should make a `mypy` issue?
 class MsgpackTCPStream(MsgTransport):
     '''
     A ``trio.SocketStream`` delivering ``msgpack`` formatted data
     using the ``msgspec`` codec lib.
 
     '''
+    layer_key: int = 4
+    name_key: str = 'tcp'
+
+    # TODO: better naming for this?
+    # -[ ] check how libp2p does naming for such things?
+    codec_key: str = 'msgpack'
+
     def __init__(
         self,
         stream: trio.SocketStream,
         prefix_size: int = 4,
 
+        # XXX optionally provided codec pair for `msgspec`:
+        # https://jcristharif.com/msgspec/extending.html#mapping-to-from-native-types
+        #
+        # TODO: define this as a `Codec` struct which can be
+        # overriden dynamically by the application/runtime?
+        codec: tuple[
+            Callable[[Any], Any]|None,  # coder
+            Callable[[type, Any], Any]|None,  # decoder
+        ]|None = None,
+
     ) -> None:
 
         self.stream = stream
@@ -126,30 +175,44 @@ class MsgpackTCPStream(MsgTransport):
         self._laddr, self._raddr = get_stream_addrs(stream)
 
         # create read loop instance
-        self._agen = self._iter_packets()
+        self._aiter_pkts = self._iter_packets()
         self._send_lock = trio.StrictFIFOLock()
 
         # public i guess?
         self.drained: list[dict] = []
 
-        self.recv_stream = BufferedReceiveStream(transport_stream=stream)
+        self.recv_stream = BufferedReceiveStream(
+            transport_stream=stream
+        )
         self.prefix_size = prefix_size
 
-        # TODO: struct aware messaging coders
+        # allow for custom IPC msg interchange format
-        self.encode = msgspec.msgpack.Encoder().encode
+        # dynamic override Bo
-        self.decode = msgspec.msgpack.Decoder().decode  # dict[str, Any])
+        self._task = trio.lowlevel.current_task()
+
+        # XXX for ctxvar debug only!
+        # self._codec: MsgCodec = (
+        #     codec
+        #     or
+        #     _codec._ctxvar_MsgCodec.get()
+        # )
 
     async def _iter_packets(self) -> AsyncGenerator[dict, None]:
-        '''Yield packets from the underlying stream.
+        '''
+        Yield `bytes`-blob decoded packets from the underlying TCP
+        stream using the current task's `MsgCodec`.
+
+        This is a streaming routine implemented as an async generator
+        func (which was the original design, but could be changed?)
+        and is allocated by a `.__call__()` inside `.__init__()` where
+        it is assigned to the `._aiter_pkts` attr.
 
         '''
-        import msgspec  # noqa
         decodes_failed: int = 0
 
         while True:
             try:
-                header = await self.recv_stream.receive_exactly(4)
+                header: bytes = await self.recv_stream.receive_exactly(4)
-
             except (
                 ValueError,
                 ConnectionResetError,
@@ -158,25 +221,122 @@ class MsgpackTCPStream(MsgTransport):
                 # seem to be getting racy failures here on
                 # arbiter/registry name subs..
                 trio.BrokenResourceError,
-            ):
-                raise TransportClosed(
-                    f'transport {self} was already closed prior ro read'
-                )
 
+            ) as trans_err:
+
+                loglevel = 'transport'
+                match trans_err:
+                    # case (
+                    #     ConnectionResetError()
+                    # ):
+                    #     loglevel = 'transport'
+
+                    # peer actor (graceful??) TCP EOF but `tricycle`
+                    # seems to raise a 0-bytes-read?
+                    case ValueError() if (
+                        'unclean EOF' in trans_err.args[0]
+                    ):
+                        pass
+
+                    # peer actor (task) prolly shutdown quickly due
+                    # to cancellation
+                    case trio.BrokenResourceError() if (
+                        'Connection reset by peer' in trans_err.args[0]
+                    ):
+                        pass
+
+                    # unless the disconnect condition falls under "a
+                    # normal operation breakage" we usualy console warn
+                    # about it.
+                    case _:
+                        loglevel: str = 'warning'
+
+
+                raise TransportClosed(
+                    message=(
+                        f'IPC transport already closed by peer\n'
+                        f'x)> {type(trans_err)}\n'
+                        f' |_{self}\n'
+                    ),
+                    loglevel=loglevel,
+                ) from trans_err
+
+            # XXX definitely can happen if transport is closed
+            # manually by another `trio.lowlevel.Task` in the
+            # same actor; we use this in some simulated fault
+            # testing for ex, but generally should never happen
+            # under normal operation!
+            #
+            # NOTE: as such we always re-raise this error from the
+            #       RPC msg loop!
+            except trio.ClosedResourceError as closure_err:
+                raise TransportClosed(
+                    message=(
+                        f'IPC transport already manually closed locally?\n'
+                        f'x)> {type(closure_err)} \n'
+                        f' |_{self}\n'
+                    ),
+                    loglevel='error',
+                    raise_on_report=(
+                        closure_err.args[0] == 'another task closed this fd'
+                        or
+                        closure_err.args[0] in ['another task closed this fd']
+                    ),
+                ) from closure_err
+
+            # graceful TCP EOF disconnect
             if header == b'':
                 raise TransportClosed(
-                    f'transport {self} was already closed prior ro read'
+                    message=(
+                        f'IPC transport already gracefully closed\n'
+                        f')>\n'
+                        f'|_{self}\n'
+                    ),
+                    loglevel='transport',
+                    # cause=???  # handy or no?
                 )
 
+            size: int
             size, = struct.unpack("<I", header)
 
             log.transport(f'received header {size}')  # type: ignore
-
+            msg_bytes: bytes = await self.recv_stream.receive_exactly(size)
-            msg_bytes = await self.recv_stream.receive_exactly(size)
 
             log.transport(f"received {msg_bytes}")  # type: ignore
             try:
-                yield self.decode(msg_bytes)
+                # NOTE: lookup the `trio.Task.context`'s var for
+                # the current `MsgCodec`.
+                codec: MsgCodec = _ctxvar_MsgCodec.get()
+
+                # XXX for ctxvar debug only!
+                # if self._codec.pld_spec != codec.pld_spec:
+                #     assert (
+                #         task := trio.lowlevel.current_task()
+                #     ) is not self._task
+                #     self._task = task
+                #     self._codec = codec
+                #     log.runtime(
+                #         f'Using new codec in {self}.recv()\n'
+                #         f'codec: {self._codec}\n\n'
+                #         f'msg_bytes: {msg_bytes}\n'
+                #     )
+                yield codec.decode(msg_bytes)
+
+            # XXX NOTE: since the below error derives from
+            # `DecodeError` we need to catch is specially
+            # and always raise such that spec violations
+            # are never allowed to be caught silently!
+            except msgspec.ValidationError as verr:
+                msgtyperr: MsgTypeError = _mk_recv_mte(
+                    msg=msg_bytes,
+                    codec=codec,
+                    src_validation_error=verr,
+                )
+                # XXX deliver up to `Channel.recv()` where
+                # a re-raise and `Error`-pack can inject the far
+                # end actor `.uid`.
+                yield msgtyperr
+
             except (
                 msgspec.DecodeError,
                 UnicodeDecodeError,
@@ -186,30 +346,96 @@ class MsgpackTCPStream(MsgTransport):
                     # do with a channel drop - hope that receiving from the
                     # channel will raise an expected error and bubble up.
                     try:
-                        msg_str: str | bytes = msg_bytes.decode()
+                        msg_str: str|bytes = msg_bytes.decode()
                     except UnicodeDecodeError:
                         msg_str = msg_bytes
 
-                    log.error(
+                    log.exception(
-                        '`msgspec` failed to decode!?\n'
+                        'Failed to decode msg?\n'
-                        'dumping bytes:\n'
+                        f'{codec}\n\n'
-                        f'{msg_str!r}'
+                        'Rxed bytes from wire:\n\n'
+                        f'{msg_str!r}\n'
                     )
                     decodes_failed += 1
                 else:
                     raise
 
-    async def send(self, msg: Any) -> None:
+    async def send(
+        self,
+        msg: msgtypes.MsgType,
+
+        strict_types: bool = True,
+        hide_tb: bool = False,
+
+    ) -> None:
+        '''
+        Send a msgpack encoded py-object-blob-as-msg over TCP.
+
+        If `strict_types == True` then a `MsgTypeError` will be raised on any
+        invalid msg type
+
+        '''
+        __tracebackhide__: bool = hide_tb
+
+        # XXX see `trio._sync.AsyncContextManagerMixin` for details
+        # on the `.acquire()`/`.release()` sequencing..
         async with self._send_lock:
 
-            bytes_data: bytes = self.encode(msg)
+            # NOTE: lookup the `trio.Task.context`'s var for
+            # the current `MsgCodec`.
+            codec: MsgCodec = _ctxvar_MsgCodec.get()
+
+            # XXX for ctxvar debug only!
+            # if self._codec.pld_spec != codec.pld_spec:
+            #     self._codec = codec
+            #     log.runtime(
+            #         f'Using new codec in {self}.send()\n'
+            #         f'codec: {self._codec}\n\n'
+            #         f'msg: {msg}\n'
+            #     )
+
+            if type(msg) not in msgtypes.__msg_types__:
+                if strict_types:
+                    raise _mk_send_mte(
+                        msg,
+                        codec=codec,
+                    )
+                else:
+                    log.warning(
+                        'Sending non-`Msg`-spec msg?\n\n'
+                        f'{msg}\n'
+                    )
+
+            try:
+                bytes_data: bytes = codec.encode(msg)
+            except TypeError as _err:
+                typerr = _err
+                msgtyperr: MsgTypeError = _mk_send_mte(
+                    msg,
+                    codec=codec,
+                    message=(
+                        f'IPC-msg-spec violation in\n\n'
+                        f'{pretty_struct.Struct.pformat(msg)}'
+                    ),
+                    src_type_error=typerr,
+                )
+                raise msgtyperr from typerr
 
             # supposedly the fastest says,
             # https://stackoverflow.com/a/54027962
             size: bytes = struct.pack("<I", len(bytes_data))
-
             return await self.stream.send_all(size + bytes_data)
 
+        # ?TODO? does it help ever to dynamically show this
+        # frame?
+        # try:
+        #     <the-above_code>
+        # except BaseException as _err:
+        #     err = _err
+        #     if not isinstance(err, MsgTypeError):
+        #         __tracebackhide__: bool = False
+        #     raise
+
     @property
     def laddr(self) -> tuple[str, int]:
         return self._laddr
@@ -219,7 +445,7 @@ class MsgpackTCPStream(MsgTransport):
         return self._raddr
 
     async def recv(self) -> Any:
-        return await self._agen.asend(None)
+        return await self._aiter_pkts.asend(None)
 
     async def drain(self) -> AsyncIterator[dict]:
         '''
@@ -236,7 +462,7 @@ class MsgpackTCPStream(MsgTransport):
                 yield msg
 
     def __aiter__(self):
-        return self._agen
+        return self._aiter_pkts
 
     def connected(self) -> bool:
         return self.stream.socket.fileno() != -1
@@ -267,7 +493,7 @@ class Channel:
     def __init__(
 
         self,
-        destaddr: Optional[tuple[str, int]],
+        destaddr: tuple[str, int]|None,
 
         msg_transport_type_key: tuple[str, str] = ('msgpack', 'tcp'),
 
@@ -285,18 +511,31 @@ class Channel:
 
         # Either created in ``.connect()`` or passed in by
         # user in ``.from_stream()``.
-        self._stream: Optional[trio.SocketStream] = None
+        self._stream: trio.SocketStream|None = None
-        self.msgstream: Optional[MsgTransport] = None
+        self._transport: MsgTransport|None = None
 
         # set after handshake - always uid of far end
-        self.uid: Optional[tuple[str, str]] = None
+        self.uid: tuple[str, str]|None = None
 
-        self._agen = self._aiter_recv()
+        self._aiter_msgs = self._iter_msgs()
-        self._exc: Optional[Exception] = None  # set if far end actor errors
+        self._exc: Exception|None = None  # set if far end actor errors
         self._closed: bool = False
-        # flag set on ``Portal.cancel_actor()`` indicating
+
-        # remote (peer) cancellation of the far end actor runtime.
+        # flag set by ``Portal.cancel_actor()`` indicating remote
-        self._cancel_called: bool = False  # set on ``Portal.cancel_actor()``
+        # (possibly peer) cancellation of the far end actor
+        # runtime.
+        self._cancel_called: bool = False
+
+    @property
+    def msgstream(self) -> MsgTransport:
+        log.info(
+            '`Channel.msgstream` is an old name, use `._transport`'
+        )
+        return self._transport
+
+    @property
+    def transport(self) -> MsgTransport:
+        return self._transport
 
     @classmethod
     def from_stream(
@@ -307,37 +546,78 @@ class Channel:
     ) -> Channel:
 
         src, dst = get_stream_addrs(stream)
-        chan = Channel(destaddr=dst, **kwargs)
+        chan = Channel(
+            destaddr=dst,
+            **kwargs,
+        )
 
         # set immediately here from provided instance
-        chan._stream = stream
+        chan._stream: trio.SocketStream = stream
         chan.set_msg_transport(stream)
         return chan
 
     def set_msg_transport(
         self,
         stream: trio.SocketStream,
-        type_key: Optional[tuple[str, str]] = None,
+        type_key: tuple[str, str]|None = None,
+
+        # XXX optionally provided codec pair for `msgspec`:
+        # https://jcristharif.com/msgspec/extending.html#mapping-to-from-native-types
+        codec: MsgCodec|None = None,
 
     ) -> MsgTransport:
-        type_key = type_key or self._transport_key
+        type_key = (
-        self.msgstream = get_msg_transport(type_key)(stream)
+            type_key
-        return self.msgstream
+            or
+            self._transport_key
+        )
+        # get transport type, then
+        self._transport = get_msg_transport(
+            type_key
+        # instantiate an instance of the msg-transport
+        )(
+            stream,
+            codec=codec,
+        )
+        return self._transport
 
+    @cm
+    def apply_codec(
+        self,
+        codec: MsgCodec,
+
+    ) -> None:
+        '''
+        Temporarily override the underlying IPC msg codec for
+        dynamic enforcement of messaging schema.
+
+        '''
+        orig: MsgCodec = self._transport.codec
+        try:
+            self._transport.codec = codec
+            yield
+        finally:
+            self._transport.codec = orig
+
+    # TODO: do a .src/.dst: str for maddrs?
     def __repr__(self) -> str:
-        if self.msgstream:
+        if not self._transport:
-            return repr(
+            return '<Channel with inactive transport?>'
-                self.msgstream.stream.socket._sock).replace(  # type: ignore
+
-                        "socket.socket", "Channel")
+        return repr(
-        return object.__repr__(self)
+            self._transport.stream.socket._sock
+        ).replace(  # type: ignore
+            "socket.socket",
+            "Channel",
+        )
 
     @property
-    def laddr(self) -> Optional[tuple[str, int]]:
+    def laddr(self) -> tuple[str, int]|None:
-        return self.msgstream.laddr if self.msgstream else None
+        return self._transport.laddr if self._transport else None
 
     @property
-    def raddr(self) -> Optional[tuple[str, int]]:
+    def raddr(self) -> tuple[str, int]|None:
-        return self.msgstream.raddr if self.msgstream else None
+        return self._transport.raddr if self._transport else None
 
     async def connect(
         self,
@@ -356,26 +636,62 @@ class Channel:
             *destaddr,
             **kwargs
         )
-        msgstream = self.set_msg_transport(stream)
+        transport = self.set_msg_transport(stream)
 
         log.transport(
-            f'Opened channel[{type(msgstream)}]: {self.laddr} -> {self.raddr}'
+            f'Opened channel[{type(transport)}]: {self.laddr} -> {self.raddr}'
         )
-        return msgstream
+        return transport
 
-    async def send(self, item: Any) -> None:
+    # TODO: something like,
+    # `pdbp.hideframe_on(errors=[MsgTypeError])`
+    # instead of the `try/except` hack we have rn..
+    # seems like a pretty useful thing to have in general
+    # along with being able to filter certain stack frame(s / sets)
+    # possibly based on the current log-level?
+    async def send(
+        self,
+        payload: Any,
 
-        log.transport(f"send `{item}`")  # type: ignore
+        hide_tb: bool = False,
-        assert self.msgstream
 
-        await self.msgstream.send(item)
+    ) -> None:
+        '''
+        Send a coded msg-blob over the transport.
+
+        '''
+        __tracebackhide__: bool = hide_tb
+        try:
+            log.transport(
+                '=> send IPC msg:\n\n'
+                f'{pformat(payload)}\n'
+            )
+            # assert self._transport  # but why typing?
+            await self._transport.send(
+                payload,
+                hide_tb=hide_tb,
+            )
+        except BaseException as _err:
+            err = _err  # bind for introspection
+            if not isinstance(_err, MsgTypeError):
+                # assert err
+                __tracebackhide__: bool = False
+            else:
+                assert err.cid
+
+            raise
 
     async def recv(self) -> Any:
-        assert self.msgstream
+        assert self._transport
-        return await self.msgstream.recv()
+        return await self._transport.recv()
 
+        # TODO: auto-reconnect features like 0mq/nanomsg?
+        # -[ ] implement it manually with nods to SC prot
+        #      possibly on multiple transport backends?
+        #  -> seems like that might be re-inventing scalability
+        #     prots tho no?
         # try:
-        #     return await self.msgstream.recv()
+        #     return await self._transport.recv()
         # except trio.BrokenResourceError:
         #     if self._autorecon:
         #         await self._reconnect()
@@ -388,8 +704,8 @@ class Channel:
             f'Closing channel to {self.uid} '
             f'{self.laddr} -> {self.raddr}'
         )
-        assert self.msgstream
+        assert self._transport
-        await self.msgstream.stream.aclose()
+        await self._transport.stream.aclose()
         self._closed = True
 
     async def __aenter__(self):
@@ -400,8 +716,11 @@ class Channel:
         await self.aclose(*args)
 
     def __aiter__(self):
-        return self._agen
+        return self._aiter_msgs
 
+    # ?TODO? run any reconnection sequence?
+    # -[ ] prolly should be impl-ed as deco-API?
+    #
     # async def _reconnect(self) -> None:
     #     """Handle connection failures by polling until a reconnect can be
     #     established.
@@ -419,7 +738,6 @@ class Channel:
     #             else:
     #                 log.transport("Stream connection re-established!")
 
-    #                 # TODO: run any reconnection sequence
     #                 # on_recon = self._recon_seq
     #                 # if on_recon:
     #                 #     await on_recon(self)
@@ -433,23 +751,42 @@ class Channel:
     #                     " for re-establishment")
     #             await trio.sleep(1)
 
-    async def _aiter_recv(
+    async def _iter_msgs(
         self
     ) -> AsyncGenerator[Any, None]:
         '''
-        Async iterate items from underlying stream.
+        Yield `MsgType` IPC msgs decoded and deliverd from
+        an underlying `MsgTransport` protocol.
+
+        This is a streaming routine alo implemented as an async-gen
+        func (same a `MsgTransport._iter_pkts()`) gets allocated by
+        a `.__call__()` inside `.__init__()` where it is assigned to
+        the `._aiter_msgs` attr.
 
         '''
-        assert self.msgstream
+        assert self._transport
         while True:
             try:
-                async for item in self.msgstream:
+                async for msg in self._transport:
-                    yield item
+                    match msg:
-                    # sent = yield item
+                        # NOTE: if transport/interchange delivers
-                    # if sent is not None:
+                        # a type error, we pack it with the far
-                    #     # optimization, passing None through all the
+                        # end peer `Actor.uid` and relay the
-                    #     # time is pointless
+                        # `Error`-msg upward to the `._rpc` stack
-                    #     await self.msgstream.send(sent)
+                        # for normal RAE handling.
+                        case MsgTypeError():
+                            yield pack_from_raise(
+                                local_err=msg,
+                                cid=msg.cid,
+
+                                # XXX we pack it here bc lower
+                                # layers have no notion of an
+                                # actor-id ;)
+                                src_uid=self.uid,
+                            )
+                        case _:
+                            yield msg
+
             except trio.BrokenResourceError:
 
                 # if not self._autorecon:
@@ -462,12 +799,14 @@ class Channel:
             #     continue
 
     def connected(self) -> bool:
-        return self.msgstream.connected() if self.msgstream else False
+        return self._transport.connected() if self._transport else False
 
 
-@asynccontextmanager
+@acm
 async def _connect_chan(
-    host: str, port: int
+    host: str,
+    port: int
+
 ) -> typing.AsyncGenerator[Channel, None]:
     '''
     Create and connect a channel with disconnect on context manager
@@ -477,4 +816,5 @@ async def _connect_chan(
     chan = Channel((host, port))
     await chan.connect()
     yield chan
-    await chan.aclose()
+    with trio.CancelScope(shield=True):
+        await chan.aclose()

tractor/_multiaddr.py

@@ -0,0 +1,151 @@
+# 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/>.
+
+'''
+Multiaddress parser and utils according the spec(s) defined by
+`libp2p` and used in dependent project such as `ipfs`:
+
+- https://docs.libp2p.io/concepts/fundamentals/addressing/
+- https://github.com/libp2p/specs/blob/master/addressing/README.md
+
+'''
+from typing import Iterator
+
+from bidict import bidict
+
+# TODO: see if we can leverage libp2p ecosys projects instead of
+# rolling our own (parser) impls of the above addressing specs:
+# - https://github.com/libp2p/py-libp2p
+# - https://docs.libp2p.io/concepts/nat/circuit-relay/#relay-addresses
+# prots: bidict[int, str] = bidict({
+prots: bidict[int, str] = {
+    'ipv4': 3,
+    'ipv6': 3,
+    'wg': 3,
+
+    'tcp': 4,
+    'udp': 4,
+
+    # TODO: support the next-gen shite Bo
+    # 'quic': 4,
+    # 'ssh': 7,  # via rsyscall bootstrapping
+}
+
+prot_params: dict[str, tuple[str]] = {
+    'ipv4': ('addr',),
+    'ipv6': ('addr',),
+    'wg': ('addr', 'port', 'pubkey'),
+
+    'tcp': ('port',),
+    'udp': ('port',),
+
+    # 'quic': ('port',),
+    # 'ssh': ('port',),
+}
+
+
+def iter_prot_layers(
+    multiaddr: str,
+) -> Iterator[
+    tuple[
+        int,
+        list[str]
+    ]
+]:
+    '''
+    Unpack a libp2p style "multiaddress" into multiple "segments"
+    for each "layer" of the protocoll stack (in OSI terms).
+
+    '''
+    tokens: list[str] = multiaddr.split('/')
+    root, tokens = tokens[0], tokens[1:]
+    assert not root  # there is a root '/' on LHS
+    itokens = iter(tokens)
+
+    prot: str | None = None
+    params: list[str] = []
+    for token in itokens:
+        # every prot path should start with a known
+        # key-str.
+        if token in prots:
+            if prot is None:
+                prot: str = token
+            else:
+                yield prot, params
+                prot = token
+
+            params = []
+
+        elif token not in prots:
+            params.append(token)
+
+    else:
+        yield prot, params
+
+
+def parse_maddr(
+    multiaddr: str,
+) -> dict[str, str | int | dict]:
+    '''
+    Parse a libp2p style "multiaddress" into its distinct protocol
+    segments where each segment is of the form:
+
+        `../<protocol>/<param0>/<param1>/../<paramN>`
+
+    and is loaded into a (order preserving) `layers: dict[str,
+    dict[str, Any]` which holds each protocol-layer-segment of the
+    original `str` path as a separate entry according to its approx
+    OSI "layer number".
+
+    Any `paramN` in the path must be distinctly defined by a str-token in the
+    (module global) `prot_params` table.
+
+    For eg. for wireguard which requires an address, port number and publickey
+    the protocol params are specified as the entry:
+
+        'wg': ('addr', 'port', 'pubkey'),
+
+    and are thus parsed from a maddr in that order:
+        `'/wg/1.1.1.1/51820/<pubkey>'`
+
+    '''
+    layers: dict[str, str | int | dict] = {}
+    for (
+        prot_key,
+        params,
+    ) in iter_prot_layers(multiaddr):
+
+        layer: int = prots[prot_key]  # OSI layer used for sorting
+        ep: dict[str, int | str] = {'layer': layer}
+        layers[prot_key] = ep
+
+        # TODO; validation and resolving of names:
+        # - each param via a validator provided as part of the
+        #   prot_params def? (also see `"port"` case below..)
+        # - do a resolv step that will check addrs against
+        #   any loaded network.resolv: dict[str, str]
+        rparams: list = list(reversed(params))
+        for key in prot_params[prot_key]:
+            val: str | int = rparams.pop()
+
+            # TODO: UGHH, dunno what we should do for validation
+            # here, put it in the params spec somehow?
+            if key == 'port':
+                val = int(val)
+
+            ep[key] = val
+
+    return layers

tractor/_portal.py

@@ -15,73 +15,70 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 '''
-Memory boundary "Portals": an API for structured
+Memory "portal" contruct.
-concurrency linked tasks running in disparate memory domains.
+
+"Memory portals" are both an API and set of IPC wrapping primitives
+for managing structured concurrency "cancel-scope linked" tasks
+running in disparate virtual memory domains - at least in different
+OS processes, possibly on different (hardware) hosts.
 
 '''
 from __future__ import annotations
+from contextlib import asynccontextmanager as acm
 import importlib
 import inspect
 from typing import (
-    Any, Optional,
+    Any,
-    Callable, AsyncGenerator,
+    Callable,
-    Type,
+    AsyncGenerator,
+    TYPE_CHECKING,
 )
 from functools import partial
 from dataclasses import dataclass
-from pprint import pformat
 import warnings
 
 import trio
-from async_generator import asynccontextmanager
 
 from .trionics import maybe_open_nursery
-from ._state import current_actor
+from ._state import (
+    current_actor,
+)
 from ._ipc import Channel
 from .log import get_logger
-from .msg import NamespacePath
+from .msg import (
+    # Error,
+    PayloadMsg,
+    NamespacePath,
+    Return,
+)
 from ._exceptions import (
-    unpack_error,
+    # unpack_error,
     NoResult,
-    ContextCancelled,
+)
+from ._context import (
+    Context,
+    open_context_from_portal,
 )
 from ._streaming import (
-    Context,
     MsgStream,
 )
 
+if TYPE_CHECKING:
+    from ._runtime import Actor
 
 log = get_logger(__name__)
 
 
-def _unwrap_msg(
-    msg: dict[str, Any],
-    channel: Channel
-
-) -> Any:
-    __tracebackhide__ = True
-    try:
-        return msg['return']
-    except KeyError:
-        # internal error should never get here
-        assert msg.get('cid'), "Received internal error at portal?"
-        raise unpack_error(msg, channel) from None
-
-
-class MessagingError(Exception):
-    'Some kind of unexpected SC messaging dialog issue'
-
-
 class Portal:
     '''
-    A 'portal' to a(n) (remote) ``Actor``.
+    A 'portal' to a memory-domain-separated `Actor`.
 
     A portal is "opened" (and eventually closed) by one side of an
     inter-actor communication context. The side which opens the portal
     is equivalent to a "caller" in function parlance and usually is
     either the called actor's parent (in process tree hierarchy terms)
     or a client interested in scheduling work to be done remotely in a
-    far process.
+    process which has a separate (virtual) memory domain.
 
     The portal api allows the "caller" actor to invoke remote routines
     and receive results through an underlying ``tractor.Channel`` as
@@ -91,22 +88,45 @@ class Portal:
     like having a "portal" between the seperate actor memory spaces.
 
     '''
-    # the timeout for a remote cancel request sent to
+    # global timeout for remote cancel requests sent to
-    # a(n) (peer) actor.
+    # connected (peer) actors.
-    cancel_timeout = 0.5
+    cancel_timeout: float = 0.5
 
-    def __init__(self, channel: Channel) -> None:
+    def __init__(
-        self.channel = channel
+        self,
+        channel: Channel,
+    ) -> None:
+
+        self._chan: Channel = channel
         # during the portal's lifetime
-        self._result_msg: Optional[dict] = None
+        self._final_result_pld: Any|None = None
+        self._final_result_msg: PayloadMsg|None = None
 
         # 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: Optional[Context] = None
+        self._expect_result_ctx: Context|None = None
         self._streams: set[MsgStream] = set()
-        self.actor = current_actor()
+        self.actor: Actor = current_actor()
 
+    @property
+    def chan(self) -> Channel:
+        return self._chan
+
+    @property
+    def channel(self) -> Channel:
+        '''
+        Proxy to legacy attr name..
+
+        Consider the shorter `Portal.chan` instead of `.channel` ;)
+        '''
+        log.debug(
+            'Consider the shorter `Portal.chan` instead of `.channel` ;)'
+        )
+        return self.chan
+
+    # TODO: factor this out into a `.highlevel` API-wrapper that uses
+    # a single `.open_context()` call underneath.
     async def _submit_for_result(
         self,
         ns: str,
@@ -114,32 +134,34 @@ class Portal:
         **kwargs
     ) -> None:
 
-        assert self._expect_result is None, \
+        if self._expect_result_ctx is not None:
-                "A pending main result has already been submitted"
+            raise RuntimeError(
+                'A pending main result has already been submitted'
+            )
 
-        self._expect_result = await self.actor.start_remote_task(
+        self._expect_result_ctx: Context = await self.actor.start_remote_task(
             self.channel,
-            ns,
+            nsf=NamespacePath(f'{ns}:{func}'),
-            func,
+            kwargs=kwargs,
-            kwargs
+            portal=self,
         )
 
-    async def _return_once(
+    # TODO: we should deprecate this API right? since if we remove
+    # `.run_in_actor()` (and instead move it to a `.highlevel`
+    # wrapper api (around a single `.open_context()` call) we don't
+    # really have any notion of a "main" remote task any more?
+    #
+    # @api_frame
+    async def wait_for_result(
         self,
-        ctx: Context,
+        hide_tb: bool = True,
-
+    ) -> Any:
-    ) -> dict[str, Any]:
-
-        assert ctx._remote_func_type == 'asyncfunc'  # single response
-        msg = await ctx._recv_chan.receive()
-        return msg
-
-    async def result(self) -> Any:
         '''
-        Return the result(s) from the remote actor's "main" task.
+        Return the final result delivered by a `Return`-msg from the
+        remote peer actor's "main" task's `return` statement.
 
         '''
-        # __tracebackhide__ = True
+        __tracebackhide__: bool = hide_tb
         # Check for non-rpc errors slapped on the
         # channel for which we always raise
         exc = self.channel._exc
@@ -147,7 +169,7 @@ class Portal:
             raise exc
 
         # not expecting a "main" result
-        if self._expect_result is None:
+        if self._expect_result_ctx is None:
             log.warning(
                 f"Portal for {self.channel.uid} not expecting a final"
                 " result?\nresult() should only be called if subactor"
@@ -155,14 +177,41 @@ class Portal:
             return NoResult
 
         # expecting a "main" result
-        assert self._expect_result
+        assert self._expect_result_ctx
 
-        if self._result_msg is None:
+        if self._final_result_msg is None:
-            self._result_msg = await self._return_once(
+            try:
-                self._expect_result
+                (
-            )
+                    self._final_result_msg,
+                    self._final_result_pld,
+                ) = await self._expect_result_ctx._pld_rx.recv_msg_w_pld(
+                    ipc=self._expect_result_ctx,
+                    expect_msg=Return,
+                )
+            except BaseException as err:
+                # TODO: wrap this into `@api_frame` optionally with
+                # some kinda filtering mechanism like log levels?
+                __tracebackhide__: bool = False
+                raise err
 
-        return _unwrap_msg(self._result_msg, self.channel)
+        return self._final_result_pld
+
+    # TODO: factor this out into a `.highlevel` API-wrapper that uses
+    # a single `.open_context()` call underneath.
+    async def result(
+        self,
+        *args,
+        **kwargs,
+    ) -> Any|Exception:
+        typname: str = type(self).__name__
+        log.warning(
+            f'`{typname}.result()` is DEPRECATED!\n'
+            f'Use `{typname}.wait_for_result()` instead!\n'
+        )
+        return await self.wait_for_result(
+            *args,
+            **kwargs,
+        )
 
     async def _cancel_streams(self):
         # terminate all locally running async generator
@@ -193,30 +242,60 @@ class Portal:
 
     ) -> bool:
         '''
-        Cancel the actor on the other end of this portal.
+        Cancel the actor runtime (and thus process) on the far
+        end of this portal.
+
+        **NOTE** THIS CANCELS THE ENTIRE RUNTIME AND THE
+        SUBPROCESS, it DOES NOT just cancel the remote task. If you
+        want to have a handle to cancel a remote ``tri.Task`` look
+        at `.open_context()` and the definition of
+        `._context.Context.cancel()` which CAN be used for this
+        purpose.
 
         '''
-        if not self.channel.connected():
+        __runtimeframe__: int = 1  # noqa
-            log.cancel("This channel is already closed can't cancel")
+
+        chan: Channel = self.channel
+        if not chan.connected():
+            log.runtime(
+                'This channel is already closed, skipping cancel request..'
+            )
             return False
 
+        reminfo: str = (
+            f'c)=> {self.channel.uid}\n'
+            f'  |_{chan}\n'
+        )
         log.cancel(
-            f"Sending actor cancel request to {self.channel.uid} on "
+            f'Requesting actor-runtime cancel for peer\n\n'
-            f"{self.channel}")
+            f'{reminfo}'
-
+        )
-        self.channel._cancel_called = True
 
+        # XXX the one spot we set it?
+        self.channel._cancel_called: bool = True
         try:
             # send cancel cmd - might not get response
-            # XXX: sure would be nice to make this work with a proper shield
+            # XXX: sure would be nice to make this work with
-            with trio.move_on_after(timeout or self.cancel_timeout) as cs:
+            # a proper shield
-                cs.shield = True
+            with trio.move_on_after(
-
+                timeout
-                await self.run_from_ns('self', 'cancel')
+                or
+                self.cancel_timeout
+            ) as cs:
+                cs.shield: bool = True
+                await self.run_from_ns(
+                    'self',
+                    'cancel',
+                )
                 return True
 
             if cs.cancelled_caught:
-                log.cancel(f"May have failed to cancel {self.channel.uid}")
+                # may timeout and we never get an ack (obvi racy)
+                # but that doesn't mean it wasn't cancelled.
+                log.debug(
+                    'May have failed to cancel peer?\n'
+                    f'{reminfo}'
+                )
 
             # if we get here some weird cancellation case happened
             return False
@@ -225,11 +304,15 @@ class Portal:
             trio.ClosedResourceError,
             trio.BrokenResourceError,
         ):
-            log.cancel(
+            log.debug(
-                f"{self.channel} for {self.channel.uid} was already "
+                'IPC chan for actor already closed or broken?\n\n'
-                "closed or broken?")
+                f'{self.channel.uid}\n'
+                f' |_{self.channel}\n'
+            )
             return False
 
+    # TODO: do we still need this for low level `Actor`-runtime
+    # method calls or can we also remove it?
     async def run_from_ns(
         self,
         namespace_path: str,
@@ -246,27 +329,35 @@ class Portal:
 
         Note::
 
-            A special namespace `self` can be used to invoke `Actor`
+          A special namespace `self` can be used to invoke `Actor`
-            instance methods in the remote runtime. Currently this
+          instance methods in the remote runtime. Currently this
-            should only be used solely for ``tractor`` runtime
+          should only ever be used for `Actor` (method) runtime
-            internals.
+          internals!
 
         '''
-        ctx = await self.actor.start_remote_task(
+        __runtimeframe__: int = 1  # noqa
-            self.channel,
+        nsf = NamespacePath(
-            namespace_path,
+            f'{namespace_path}:{function_name}'
-            function_name,
+        )
-            kwargs,
+        ctx: Context = await self.actor.start_remote_task(
+            chan=self.channel,
+            nsf=nsf,
+            kwargs=kwargs,
+            portal=self,
+        )
+        return await ctx._pld_rx.recv_pld(
+            ipc=ctx,
+            expect_msg=Return,
         )
-        ctx._portal = self
-        msg = await self._return_once(ctx)
-        return _unwrap_msg(msg, self.channel)
 
+    # TODO: factor this out into a `.highlevel` API-wrapper that uses
+    # a single `.open_context()` call underneath.
     async def run(
         self,
         func: str,
-        fn_name: Optional[str] = None,
+        fn_name: str|None = None,
         **kwargs
+
     ) -> Any:
         '''
         Submit a remote function to be scheduled and run by actor, in
@@ -276,6 +367,8 @@ class Portal:
         remote rpc task or a local async generator instance.
 
         '''
+        __runtimeframe__: int = 1  # noqa
+
         if isinstance(func, str):
             warnings.warn(
                 "`Portal.run(namespace: str, funcname: str)` is now"
@@ -285,8 +378,9 @@ class Portal:
                 DeprecationWarning,
                 stacklevel=2,
             )
-            fn_mod_path = func
+            fn_mod_path: str = func
             assert isinstance(fn_name, str)
+            nsf = NamespacePath(f'{fn_mod_path}:{fn_name}')
 
         else:  # function reference was passed directly
             if (
@@ -299,27 +393,36 @@ class Portal:
                 raise TypeError(
                     f'{func} must be a non-streaming async function!')
 
-            fn_mod_path, fn_name = NamespacePath.from_ref(func).to_tuple()
+            nsf = NamespacePath.from_ref(func)
 
         ctx = await self.actor.start_remote_task(
             self.channel,
-            fn_mod_path,
+            nsf=nsf,
-            fn_name,
+            kwargs=kwargs,
-            kwargs,
+            portal=self,
         )
-        ctx._portal = self
+        return await ctx._pld_rx.recv_pld(
-        return _unwrap_msg(
+            ipc=ctx,
-            await self._return_once(ctx),
+            expect_msg=Return,
-            self.channel,
         )
 
-    @asynccontextmanager
+    # TODO: factor this out into a `.highlevel` API-wrapper that uses
+    # a single `.open_context()` call underneath.
+    @acm
     async def open_stream_from(
         self,
         async_gen_func: Callable,  # typing: ignore
         **kwargs,
 
     ) -> AsyncGenerator[MsgStream, None]:
+        '''
+        Legacy one-way streaming API.
+
+        TODO: re-impl on top `Portal.open_context()` + an async gen
+        around `Context.open_stream()`.
+
+        '''
+        __runtimeframe__: int = 1  # noqa
 
         if not inspect.isasyncgenfunction(async_gen_func):
             if not (
@@ -329,15 +432,12 @@ class Portal:
                 raise TypeError(
                     f'{async_gen_func} must be an async generator function!')
 
-        fn_mod_path, fn_name = NamespacePath.from_ref(
+        ctx: Context = await self.actor.start_remote_task(
-            async_gen_func).to_tuple()
-        ctx = await self.actor.start_remote_task(
             self.channel,
-            fn_mod_path,
+            nsf=NamespacePath.from_ref(async_gen_func),
-            fn_name,
+            kwargs=kwargs,
-            kwargs
+            portal=self,
         )
-        ctx._portal = self
 
         # ensure receive-only stream entrypoint
         assert ctx._remote_func_type == 'asyncgen'
@@ -345,13 +445,14 @@ class Portal:
         try:
             # deliver receive only stream
             async with MsgStream(
-                ctx, ctx._recv_chan,
+                ctx=ctx,
-            ) as rchan:
+                rx_chan=ctx._rx_chan,
-                self._streams.add(rchan)
+            ) as stream:
-                yield rchan
+                self._streams.add(stream)
+                ctx._stream = stream
+                yield stream
 
         finally:
-
             # cancel the far end task on consumer close
             # NOTE: this is a special case since we assume that if using
             # this ``.open_fream_from()`` api, the stream is one a one
@@ -370,177 +471,14 @@ class Portal:
 
             # XXX: should this always be done?
             # await recv_chan.aclose()
-            self._streams.remove(rchan)
+            self._streams.remove(stream)
 
-    @asynccontextmanager
+    # NOTE: impl is found in `._context`` mod to make
-    async def open_context(
+    # reading/groking the details simpler code-org-wise. This
-
+    # method does not have to be used over that `@acm` module func
-        self,
+    # directly, it is for conventience and from the original API
-        func: Callable,
+    # design.
-        **kwargs,
+    open_context = open_context_from_portal
-
-    ) -> AsyncGenerator[tuple[Context, Any], None]:
-        '''
-        Open an inter-actor task context.
-
-        This is a synchronous API which allows for deterministic
-        setup/teardown of a remote task. The yielded ``Context`` further
-        allows for opening bidirectional streams, explicit cancellation
-        and synchronized final result collection. See ``tractor.Context``.
-
-        '''
-        # conduct target func method structural checks
-        if not inspect.iscoroutinefunction(func) and (
-            getattr(func, '_tractor_contex_function', False)
-        ):
-            raise TypeError(
-                f'{func} must be an async generator function!')
-
-        fn_mod_path, fn_name = NamespacePath.from_ref(func).to_tuple()
-
-        ctx = await self.actor.start_remote_task(
-            self.channel,
-            fn_mod_path,
-            fn_name,
-            kwargs
-        )
-
-        assert ctx._remote_func_type == 'context'
-        msg = await ctx._recv_chan.receive()
-
-        try:
-            # the "first" value here is delivered by the callee's
-            # ``Context.started()`` call.
-            first = msg['started']
-            ctx._started_called = True
-
-        except KeyError:
-            assert msg.get('cid'), ("Received internal error at context?")
-
-            if msg.get('error'):
-                # raise kerr from unpack_error(msg, self.channel)
-                raise unpack_error(msg, self.channel) from None
-            else:
-                raise MessagingError(
-                    f'Context for {ctx.cid} was expecting a `started` message'
-                    f' but received a non-error msg:\n{pformat(msg)}'
-                )
-
-        _err: Optional[BaseException] = None
-        ctx._portal = self
-
-        uid = self.channel.uid
-        cid = ctx.cid
-        etype: Optional[Type[BaseException]] = None
-
-        # deliver context instance and .started() msg value in open tuple.
-        try:
-            async with trio.open_nursery() as scope_nursery:
-                ctx._scope_nursery = scope_nursery
-
-                # do we need this?
-                # await trio.lowlevel.checkpoint()
-
-                yield ctx, first
-
-        except ContextCancelled as err:
-            _err = err
-            if not ctx._cancel_called:
-                # context was cancelled at the far end but was
-                # not part of this end requesting that cancel
-                # so raise for the local task to respond and handle.
-                raise
-
-            # if the context was cancelled by client code
-            # then we don't need to raise since user code
-            # is expecting this and the block should exit.
-            else:
-                log.debug(f'Context {ctx} cancelled gracefully')
-
-        except (
-            BaseException,
-
-            # more specifically, we need to handle these but not
-            # sure it's worth being pedantic:
-            # Exception,
-            # trio.Cancelled,
-            # KeyboardInterrupt,
-
-        ) as err:
-            etype = type(err)
-            # the context cancels itself on any cancel
-            # causing error.
-
-            if ctx.chan.connected():
-                log.cancel(
-                    'Context cancelled for task, sending cancel request..\n'
-                    f'task:{cid}\n'
-                    f'actor:{uid}'
-                )
-                await ctx.cancel()
-            else:
-                log.warning(
-                    'IPC connection for context is broken?\n'
-                    f'task:{cid}\n'
-                    f'actor:{uid}'
-                )
-
-            raise
-
-        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'
-                    f'task: {cid}\n'
-                    f'actor: {uid}'
-                )
-                result = await ctx.result()
-                log.runtime(
-                    f'Context {fn_name} returned '
-                    f'value from callee `{result}`'
-                )
-
-            # though it should be impossible for any tasks
-            # operating *in* this scope to have survived
-            # we tear down the runtime feeder chan last
-            # to avoid premature stream clobbers.
-            if ctx._recv_chan is not None:
-                # should we encapsulate this in the context api?
-                await ctx._recv_chan.aclose()
-
-            if etype:
-                if ctx._cancel_called:
-                    log.cancel(
-                        f'Context {fn_name} cancelled by caller with\n{etype}'
-                    )
-                elif _err is not None:
-                    log.cancel(
-                        f'Context for task cancelled by callee with {etype}\n'
-                        f'target: `{fn_name}`\n'
-                        f'task:{cid}\n'
-                        f'actor:{uid}'
-                    )
-            # XXX: (MEGA IMPORTANT) if this is a root opened process we
-            # wait for any immediate child in debug before popping the
-            # context from the runtime msg loop otherwise inside
-            # ``Actor._push_result()`` the msg will be discarded and in
-            # the case where that msg is global debugger unlock (via
-            # a "stop" msg for a stream), this can result in a deadlock
-            # where the root is waiting on the lock to clear but the
-            # child has already cleared it and clobbered IPC.
-            from ._debug import maybe_wait_for_debugger
-            await maybe_wait_for_debugger()
-
-            # remove the context from runtime tracking
-            self.actor._contexts.pop(
-                (self.channel.uid, ctx.cid),
-                None,
-            )
 
 
 @dataclass
@@ -555,7 +493,12 @@ class LocalPortal:
     actor: 'Actor'  # type: ignore # noqa
     channel: Channel
 
-    async def run_from_ns(self, ns: str, func_name: str, **kwargs) -> Any:
+    async def run_from_ns(
+        self,
+        ns: str,
+        func_name: str,
+        **kwargs,
+    ) -> Any:
         '''
         Run a requested local function from a namespace path and
         return it's result.
@@ -566,11 +509,11 @@ class LocalPortal:
         return await func(**kwargs)
 
 
-@asynccontextmanager
+@acm
 async def open_portal(
 
     channel: Channel,
-    nursery: Optional[trio.Nursery] = None,
+    tn: trio.Nursery|None = None,
     start_msg_loop: bool = True,
     shield: bool = False,
 
@@ -578,15 +521,19 @@ async def open_portal(
     '''
     Open a ``Portal`` through the provided ``channel``.
 
-    Spawns a background task to handle message processing (normally
+    Spawns a background task to handle RPC processing, normally
-    done by the actor-runtime implicitly).
+    done by the actor-runtime implicitly via a call to
+    `._rpc.process_messages()`. just after connection establishment.
 
     '''
     actor = current_actor()
     assert actor
-    was_connected = False
+    was_connected: bool = False
 
-    async with maybe_open_nursery(nursery, shield=shield) as nursery:
+    async with maybe_open_nursery(
+        tn,
+        shield=shield,
+    ) as tn:
 
         if not channel.connected():
             await channel.connect()
@@ -595,10 +542,10 @@ async def open_portal(
         if channel.uid is None:
             await actor._do_handshake(channel)
 
-        msg_loop_cs: Optional[trio.CancelScope] = None
+        msg_loop_cs: trio.CancelScope|None = None
         if start_msg_loop:
             from ._runtime import process_messages
-            msg_loop_cs = await nursery.start(
+            msg_loop_cs = await tn.start(
                 partial(
                     process_messages,
                     actor,
@@ -615,12 +562,10 @@ async def open_portal(
             await portal.aclose()
 
             if was_connected:
-                # gracefully signal remote channel-msg loop
+                await channel.aclose()
-                await channel.send(None)
-                # await channel.aclose()
 
             # cancel background msg loop task
-            if msg_loop_cs:
+            if msg_loop_cs is not None:
                 msg_loop_cs.cancel()
 
-            nursery.cancel_scope.cancel()
+            tn.cancel_scope.cancel()

tractor/_root.py

@@ -18,26 +18,28 @@
 Root actor runtime ignition(s).
 
 '''
-from contextlib import asynccontextmanager
+from contextlib import asynccontextmanager as acm
 from functools import partial
 import importlib
+import inspect
 import logging
+import os
 import signal
 import sys
-import os
+from typing import Callable
-import typing
 import warnings
 
 
-from exceptiongroup import BaseExceptionGroup
 import trio
 
 from ._runtime import (
     Actor,
     Arbiter,
+    # TODO: rename and make a non-actor subtype?
+    # Arbiter as Registry,
     async_main,
 )
-from . import _debug
+from .devx import _debug
 from . import _spawn
 from . import _state
 from . import log
@@ -46,60 +48,120 @@ from ._exceptions import is_multi_cancelled
 
 
 # set at startup and after forks
-_default_arbiter_host: str = '127.0.0.1'
+_default_host: str = '127.0.0.1'
-_default_arbiter_port: int = 1616
+_default_port: int = 1616
+
+# default registry always on localhost
+_default_lo_addrs: list[tuple[str, int]] = [(
+    _default_host,
+    _default_port,
+)]
 
 
 logger = log.get_logger('tractor')
 
 
-@asynccontextmanager
+@acm
 async def open_root_actor(
 
     *,
     # defaults are above
-    arbiter_addr: tuple[str, int] | None = None,
+    registry_addrs: list[tuple[str, int]]|None = None,
 
     # defaults are above
-    registry_addr: tuple[str, int] | None = None,
+    arbiter_addr: tuple[str, int]|None = None,
 
-    name: str | None = 'root',
+    name: str|None = 'root',
 
     # either the `multiprocessing` start method:
     # https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods
     # OR `trio` (the new default).
-    start_method: _spawn.SpawnMethodKey | None = None,
+    start_method: _spawn.SpawnMethodKey|None = None,
 
     # enables the multi-process debugger support
     debug_mode: bool = False,
+    maybe_enable_greenback: bool = True,  # `.pause_from_sync()/breakpoint()` support
+    enable_stack_on_sig: bool = False,
 
     # internal logging
-    loglevel: str | None = None,
+    loglevel: str|None = None,
 
-    enable_modules: list | None = None,
+    enable_modules: list|None = None,
-    rpc_module_paths: list | None = None,
+    rpc_module_paths: list|None = None,
 
-) -> typing.Any:
+    # NOTE: allow caller to ensure that only one registry exists
+    # and that this call creates it.
+    ensure_registry: bool = False,
+
+    hide_tb: bool = True,
+
+) -> Actor:
     '''
     Runtime init entry point for ``tractor``.
 
     '''
+    __tracebackhide__: bool = hide_tb
+    _debug.hide_runtime_frames()
+
+    # TODO: stick this in a `@cm` defined in `devx._debug`?
+    #
     # Override the global debugger hook to make it play nice with
     # ``trio``, see much discussion in:
     # https://github.com/python-trio/trio/issues/1155#issuecomment-742964018
-    builtin_bp_handler = sys.breakpointhook
+    builtin_bp_handler: Callable = sys.breakpointhook
-    orig_bp_path: str | None = os.environ.get('PYTHONBREAKPOINT', None)
+    orig_bp_path: str|None = os.environ.get(
-    os.environ['PYTHONBREAKPOINT'] = 'tractor._debug._set_trace'
+        'PYTHONBREAKPOINT',
+        None,
+    )
+    if (
+        debug_mode
+        and maybe_enable_greenback
+        and (
+            maybe_mod := await _debug.maybe_init_greenback(
+                raise_not_found=False,
+            )
+        )
+    ):
+        logger.info(
+            f'Found `greenback` installed @ {maybe_mod}\n'
+            'Enabling `tractor.pause_from_sync()` support!\n'
+        )
+        os.environ['PYTHONBREAKPOINT'] = (
+            'tractor.devx._debug._sync_pause_from_builtin'
+        )
+        _state._runtime_vars['use_greenback'] = True
+
+    else:
+        # TODO: disable `breakpoint()` by default (without
+        # `greenback`) since it will break any multi-actor
+        # usage by a clobbered TTY's stdstreams!
+        def block_bps(*args, **kwargs):
+            raise RuntimeError(
+                'Trying to use `breakpoint()` eh?\n\n'
+                'Welp, `tractor` blocks `breakpoint()` built-in calls by default!\n'
+                'If you need to use it please install `greenback` and set '
+                '`debug_mode=True` when opening the runtime '
+                '(either via `.open_nursery()` or `open_root_actor()`)\n'
+            )
+
+        sys.breakpointhook = block_bps
+        # lol ok,
+        # https://docs.python.org/3/library/sys.html#sys.breakpointhook
+        os.environ['PYTHONBREAKPOINT'] = "0"
 
     # attempt to retreive ``trio``'s sigint handler and stash it
     # on our debugger lock state.
-    _debug.Lock._trio_handler = signal.getsignal(signal.SIGINT)
+    _debug.DebugStatus._trio_handler = signal.getsignal(signal.SIGINT)
 
     # mark top most level process as root actor
     _state._runtime_vars['_is_root'] = True
 
     # caps based rpc list
-    enable_modules = enable_modules or []
+    enable_modules = (
+        enable_modules
+        or
+        []
+    )
 
     if rpc_module_paths:
         warnings.warn(
@@ -115,29 +177,34 @@ async def open_root_actor(
 
     if arbiter_addr is not None:
         warnings.warn(
-            '`arbiter_addr` is now deprecated and has been renamed to'
+            '`arbiter_addr` is now deprecated\n'
-            '`registry_addr`.\nUse that instead..',
+            'Use `registry_addrs: list[tuple]` instead..',
             DeprecationWarning,
             stacklevel=2,
         )
+        registry_addrs = [arbiter_addr]
 
-    registry_addr = (host, port) = (
+    registry_addrs: list[tuple[str, int]] = (
-        registry_addr
+        registry_addrs
-        or arbiter_addr
+        or
-        or (
+        _default_lo_addrs
-            _default_arbiter_host,
-            _default_arbiter_port,
-        )
     )
+    assert registry_addrs
 
-    loglevel = (loglevel or log._default_loglevel).upper()
+    loglevel = (
+        loglevel
+        or log._default_loglevel
+    ).upper()
 
-    if debug_mode and _spawn._spawn_method == 'trio':
+    if (
+        debug_mode
+        and _spawn._spawn_method == 'trio'
+    ):
         _state._runtime_vars['_debug_mode'] = True
 
-        # expose internal debug module to every actor allowing
+        # expose internal debug module to every actor allowing for
-        # for use of ``await tractor.breakpoint()``
+        # use of ``await tractor.pause()``
-        enable_modules.append('tractor._debug')
+        enable_modules.append('tractor.devx._debug')
 
         # if debug mode get's enabled *at least* use that level of
         # logging for some informative console prompts.
@@ -150,97 +217,178 @@ async def open_root_actor(
         ):
             loglevel = 'PDB'
 
+
     elif debug_mode:
         raise RuntimeError(
             "Debug mode is only supported for the `trio` backend!"
         )
 
-    log.get_console_log(loglevel)
+    assert loglevel
+    _log = log.get_console_log(loglevel)
+    assert _log
 
-    try:
+    # TODO: factor this into `.devx._stackscope`!!
-        # make a temporary connection to see if an arbiter exists,
+    if (
-        # if one can't be made quickly we assume none exists.
+        debug_mode
-        arbiter_found = False
+        and
+        enable_stack_on_sig
+    ):
+        from .devx._stackscope import enable_stack_on_sig
+        enable_stack_on_sig()
 
-        # TODO: this connect-and-bail forces us to have to carefully
+    # closed into below ping task-func
-        # rewrap TCP 104-connection-reset errors as EOF so as to avoid
+    ponged_addrs: list[tuple[str, int]] = []
-        # propagating cancel-causing errors to the channel-msg loop
-        # machinery.  Likely it would be better to eventually have
-        # a "discovery" protocol with basic handshake instead.
-        with trio.move_on_after(1):
-            async with _connect_chan(host, port):
-                arbiter_found = True
 
-    except OSError:
+    async def ping_tpt_socket(
-        # TODO: make this a "discovery" log level?
+        addr: tuple[str, int],
-        logger.warning(f"No actor registry found @ {host}:{port}")
+        timeout: float = 1,
+    ) -> None:
+        '''
+        Attempt temporary connection to see if a registry is
+        listening at the requested address by a tranport layer
+        ping.
 
-    # create a local actor and start up its main routine/task
+        If a connection can't be made quickly we assume none no
-    if arbiter_found:
+        server is listening at that addr.
+
+        '''
+        try:
+            # TODO: this connect-and-bail forces us to have to
+            # carefully rewrap TCP 104-connection-reset errors as
+            # EOF so as to avoid propagating cancel-causing errors
+            # to the channel-msg loop machinery. Likely it would
+            # be better to eventually have a "discovery" protocol
+            # with basic handshake instead?
+            with trio.move_on_after(timeout):
+                async with _connect_chan(*addr):
+                    ponged_addrs.append(addr)
+
+        except OSError:
+            # TODO: make this a "discovery" log level?
+            logger.info(
+                f'No actor registry found @ {addr}\n'
+            )
+
+    async with trio.open_nursery() as tn:
+        for addr in registry_addrs:
+            tn.start_soon(
+                ping_tpt_socket,
+                tuple(addr),  # TODO: just drop this requirement?
+            )
+
+    trans_bind_addrs: list[tuple[str, int]] = []
+
+    # Create a new local root-actor instance which IS NOT THE
+    # REGISTRAR
+    if ponged_addrs:
+        if ensure_registry:
+            raise RuntimeError(
+                 f'Failed to open `{name}`@{ponged_addrs}: '
+                'registry socket(s) already bound'
+            )
 
         # we were able to connect to an arbiter
-        logger.info(f"Arbiter seems to exist @ {host}:{port}")
+        logger.info(
+            f'Registry(s) seem(s) to exist @ {ponged_addrs}'
+        )
 
         actor = Actor(
-            name or 'anonymous',
+            name=name or 'anonymous',
-            arbiter_addr=registry_addr,
+            registry_addrs=ponged_addrs,
             loglevel=loglevel,
             enable_modules=enable_modules,
         )
-        host, port = (host, 0)
+        # DO NOT use the registry_addrs as the transport server
+        # addrs for this new non-registar, root-actor.
+        for host, port in ponged_addrs:
+            # NOTE: zero triggers dynamic OS port allocation
+            trans_bind_addrs.append((host, 0))
 
+    # Start this local actor as the "registrar", aka a regular
+    # actor who manages the local registry of "mailboxes" of
+    # other process-tree-local sub-actors.
     else:
-        # start this local actor as the arbiter (aka a regular actor who
-        # manages the local registry of "mailboxes")
 
-        # Note that if the current actor is the arbiter it is desirable
+        # NOTE that if the current actor IS THE REGISTAR, the
-        # for it to stay up indefinitely until a re-election process has
+        # following init steps are taken:
-        # taken place - which is not implemented yet FYI).
+        # - the tranport layer server is bound to each (host, port)
+        #   pair defined in provided registry_addrs, or the default.
+        trans_bind_addrs = registry_addrs
+
+        # - it is normally desirable for any registrar to stay up
+        #   indefinitely until either all registered (child/sub)
+        #   actors are terminated (via SC supervision) or,
+        #   a re-election process has taken place. 
+        # NOTE: all of ^ which is not implemented yet - see:
+        # https://github.com/goodboy/tractor/issues/216
+        # https://github.com/goodboy/tractor/pull/348
+        # https://github.com/goodboy/tractor/issues/296
 
         actor = Arbiter(
-            name or 'arbiter',
+            name or 'registrar',
-            arbiter_addr=registry_addr,
+            registry_addrs=registry_addrs,
             loglevel=loglevel,
             enable_modules=enable_modules,
         )
 
+    # Start up main task set via core actor-runtime nurseries.
     try:
         # assign process-local actor
         _state._current_actor = actor
 
         # start local channel-server and fake the portal API
         # NOTE: this won't block since we provide the nursery
-        logger.info(f"Starting local {actor} @ {host}:{port}")
+        ml_addrs_str: str = '\n'.join(
+            f'@{addr}' for addr in trans_bind_addrs
+        )
+        logger.info(
+            f'Starting local {actor.uid} on the following transport addrs:\n'
+            f'{ml_addrs_str}'
+        )
 
         # start the actor runtime in a new task
         async with trio.open_nursery() as nursery:
 
-            # ``_runtime.async_main()`` creates an internal nursery and
+            # ``_runtime.async_main()`` creates an internal nursery
-            # thus blocks here until the entire underlying actor tree has
+            # and blocks here until any underlying actor(-process)
-            # terminated thereby conducting structured concurrency.
+            # tree has terminated thereby conducting so called
-
+            # "end-to-end" structured concurrency throughout an
+            # entire hierarchical python sub-process set; all
+            # "actor runtime" primitives are SC-compat and thus all
+            # transitively spawned actors/processes must be as
+            # well.
             await nursery.start(
                 partial(
                     async_main,
                     actor,
-                    accept_addr=(host, port),
+                    accept_addrs=trans_bind_addrs,
                     parent_addr=None
                 )
             )
             try:
                 yield actor
-
             except (
                 Exception,
                 BaseExceptionGroup,
             ) as err:
+                # XXX NOTE XXX see equiv note inside
+                # `._runtime.Actor._stream_handler()` where in the
+                # non-root or root-that-opened-this-mahually case we
+                # wait for the local actor-nursery to exit before
+                # exiting the transport channel handler.
+                entered: bool = await _debug._maybe_enter_pm(
+                    err,
+                    api_frame=inspect.currentframe(),
+                )
+                if (
+                    not entered
+                    and
+                    not is_multi_cancelled(err)
+                ):
+                    logger.exception('Root actor crashed\n')
 
-                entered = await _debug._maybe_enter_pm(err)
+                # ALWAYS re-raise any error bubbled up from the
-
+                # runtime!
-                if not entered and not is_multi_cancelled(err):
-                    logger.exception("Root actor crashed:")
-
-                # always re-raise
                 raise
 
             finally:
@@ -253,18 +401,29 @@ async def open_root_actor(
                 #     for an in nurseries:
                 #         tempn.start_soon(an.exited.wait)
 
-                logger.cancel("Shutting down root actor")
+                logger.info(
-                await actor.cancel()
+                    'Closing down root actor'
+                )
+                await actor.cancel(None)  # self cancel
     finally:
         _state._current_actor = None
+        _state._last_actor_terminated = actor
 
-        # restore breakpoint hook state
+        # restore built-in `breakpoint()` hook state
-        sys.breakpointhook = builtin_bp_handler
+        if (
-        if orig_bp_path is not None:
+            debug_mode
-            os.environ['PYTHONBREAKPOINT'] = orig_bp_path
+            and
-        else:
+            maybe_enable_greenback
-            # clear env back to having no entry
+        ):
-            os.environ.pop('PYTHONBREAKPOINT')
+            if builtin_bp_handler is not None:
+                sys.breakpointhook = builtin_bp_handler
+
+            if orig_bp_path is not None:
+                os.environ['PYTHONBREAKPOINT'] = orig_bp_path
+
+            else:
+                # clear env back to having no entry
+                os.environ.pop('PYTHONBREAKPOINT', None)
 
         logger.runtime("Root actor terminated")
 
@@ -274,10 +433,7 @@ def run_daemon(
 
     # runtime kwargs
     name: str | None = 'root',
-    registry_addr: tuple[str, int] = (
+    registry_addrs: list[tuple[str, int]] = _default_lo_addrs,
-        _default_arbiter_host,
-        _default_arbiter_port,
-    ),
 
     start_method: str | None = None,
     debug_mode: bool = False,
@@ -301,7 +457,7 @@ def run_daemon(
     async def _main():
 
         async with open_root_actor(
-            registry_addr=registry_addr,
+            registry_addrs=registry_addrs,
             name=name,
             start_method=start_method,
             debug_mode=debug_mode,

tractor/_shm.py

@@ -0,0 +1,833 @@
+# 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/>.
+
+"""
+SC friendly shared memory management geared at real-time
+processing.
+
+Support for ``numpy`` compatible array-buffers is provided but is
+considered optional within the context of this runtime-library.
+
+"""
+from __future__ import annotations
+from sys import byteorder
+import time
+from typing import Optional
+from multiprocessing import shared_memory as shm
+from multiprocessing.shared_memory import (
+    SharedMemory,
+    ShareableList,
+)
+
+from msgspec import Struct
+import tractor
+
+from .log import get_logger
+
+
+_USE_POSIX = getattr(shm, '_USE_POSIX', False)
+if _USE_POSIX:
+    from _posixshmem import shm_unlink
+
+
+try:
+    import numpy as np
+    from numpy.lib import recfunctions as rfn
+    # import nptyping
+except ImportError:
+    pass
+
+
+log = get_logger(__name__)
+
+
+def disable_mantracker():
+    '''
+    Disable all ``multiprocessing``` "resource tracking" machinery since
+    it's an absolute multi-threaded mess of non-SC madness.
+
+    '''
+    from multiprocessing import resource_tracker as mantracker
+
+    # Tell the "resource tracker" thing to fuck off.
+    class ManTracker(mantracker.ResourceTracker):
+        def register(self, name, rtype):
+            pass
+
+        def unregister(self, name, rtype):
+            pass
+
+        def ensure_running(self):
+            pass
+
+    # "know your land and know your prey"
+    # https://www.dailymotion.com/video/x6ozzco
+    mantracker._resource_tracker = ManTracker()
+    mantracker.register = mantracker._resource_tracker.register
+    mantracker.ensure_running = mantracker._resource_tracker.ensure_running
+    mantracker.unregister = mantracker._resource_tracker.unregister
+    mantracker.getfd = mantracker._resource_tracker.getfd
+
+
+disable_mantracker()
+
+
+class SharedInt:
+    '''
+    Wrapper around a single entry shared memory array which
+    holds an ``int`` value used as an index counter.
+
+    '''
+    def __init__(
+        self,
+        shm: SharedMemory,
+    ) -> None:
+        self._shm = shm
+
+    @property
+    def value(self) -> int:
+        return int.from_bytes(self._shm.buf, byteorder)
+
+    @value.setter
+    def value(self, value) -> None:
+        self._shm.buf[:] = value.to_bytes(self._shm.size, byteorder)
+
+    def destroy(self) -> None:
+        if _USE_POSIX:
+            # We manually unlink to bypass all the "resource tracker"
+            # nonsense meant for non-SC systems.
+            name = self._shm.name
+            try:
+                shm_unlink(name)
+            except FileNotFoundError:
+                # might be a teardown race here?
+                log.warning(f'Shm for {name} already unlinked?')
+
+
+class NDToken(Struct, frozen=True):
+    '''
+    Internal represenation of a shared memory ``numpy`` array "token"
+    which can be used to key and load a system (OS) wide shm entry
+    and correctly read the array by type signature.
+
+    This type is msg safe.
+
+    '''
+    shm_name: str  # this servers as a "key" value
+    shm_first_index_name: str
+    shm_last_index_name: str
+    dtype_descr: tuple
+    size: int  # in struct-array index / row terms
+
+    # TODO: use nptyping here on dtypes
+    @property
+    def dtype(self) -> list[tuple[str, str, tuple[int, ...]]]:
+        return np.dtype(
+            list(
+                map(tuple, self.dtype_descr)
+            )
+        ).descr
+
+    def as_msg(self):
+        return self.to_dict()
+
+    @classmethod
+    def from_msg(cls, msg: dict) -> NDToken:
+        if isinstance(msg, NDToken):
+            return msg
+
+        # TODO: native struct decoding
+        # return _token_dec.decode(msg)
+
+        msg['dtype_descr'] = tuple(map(tuple, msg['dtype_descr']))
+        return NDToken(**msg)
+
+
+# _token_dec = msgspec.msgpack.Decoder(NDToken)
+
+# TODO: this api?
+# _known_tokens = tractor.ActorVar('_shm_tokens', {})
+# _known_tokens = tractor.ContextStack('_known_tokens', )
+# _known_tokens = trio.RunVar('shms', {})
+
+# TODO: this should maybe be provided via
+# a `.trionics.maybe_open_context()` wrapper factory?
+# process-local store of keys to tokens
+_known_tokens: dict[str, NDToken] = {}
+
+
+def get_shm_token(key: str) -> NDToken | None:
+    '''
+    Convenience func to check if a token
+    for the provided key is known by this process.
+
+    Returns either the ``numpy`` token or a string for a shared list.
+
+    '''
+    return _known_tokens.get(key)
+
+
+def _make_token(
+    key: str,
+    size: int,
+    dtype: np.dtype,
+
+) -> NDToken:
+    '''
+    Create a serializable token that can be used
+    to access a shared array.
+
+    '''
+    return NDToken(
+        shm_name=key,
+        shm_first_index_name=key + "_first",
+        shm_last_index_name=key + "_last",
+        dtype_descr=tuple(np.dtype(dtype).descr),
+        size=size,
+    )
+
+
+class ShmArray:
+    '''
+    A shared memory ``numpy.ndarray`` API.
+
+    An underlying shared memory buffer is allocated based on
+    a user specified ``numpy.ndarray``. This fixed size array
+    can be read and written to by pushing data both onto the "front"
+    or "back" of a set index range. The indexes for the "first" and
+    "last" index are themselves stored in shared memory (accessed via
+    ``SharedInt`` interfaces) values such that multiple processes can
+    interact with the same array using a synchronized-index.
+
+    '''
+    def __init__(
+        self,
+        shmarr: np.ndarray,
+        first: SharedInt,
+        last: SharedInt,
+        shm: SharedMemory,
+        # readonly: bool = True,
+    ) -> None:
+        self._array = shmarr
+
+        # indexes for first and last indices corresponding
+        # to fille data
+        self._first = first
+        self._last = last
+
+        self._len = len(shmarr)
+        self._shm = shm
+        self._post_init: bool = False
+
+        # pushing data does not write the index (aka primary key)
+        self._write_fields: list[str] | None = None
+        dtype = shmarr.dtype
+        if dtype.fields:
+            self._write_fields = list(shmarr.dtype.fields.keys())[1:]
+
+    # TODO: ringbuf api?
+
+    @property
+    def _token(self) -> NDToken:
+        return NDToken(
+            shm_name=self._shm.name,
+            shm_first_index_name=self._first._shm.name,
+            shm_last_index_name=self._last._shm.name,
+            dtype_descr=tuple(self._array.dtype.descr),
+            size=self._len,
+        )
+
+    @property
+    def token(self) -> dict:
+        """Shared memory token that can be serialized and used by
+        another process to attach to this array.
+        """
+        return self._token.as_msg()
+
+    @property
+    def index(self) -> int:
+        return self._last.value % self._len
+
+    @property
+    def array(self) -> np.ndarray:
+        '''
+        Return an up-to-date ``np.ndarray`` view of the
+        so-far-written data to the underlying shm buffer.
+
+        '''
+        a = self._array[self._first.value:self._last.value]
+
+        # first, last = self._first.value, self._last.value
+        # a = self._array[first:last]
+
+        # TODO: eventually comment this once we've not seen it in the
+        # wild in a long time..
+        # XXX: race where first/last indexes cause a reader
+        # to load an empty array..
+        if len(a) == 0 and self._post_init:
+            raise RuntimeError('Empty array race condition hit!?')
+            # breakpoint()
+
+        return a
+
+    def ustruct(
+        self,
+        fields: Optional[list[str]] = None,
+
+        # type that all field values will be cast to
+        # in the returned view.
+        common_dtype: np.dtype = float,
+
+    ) -> np.ndarray:
+
+        array = self._array
+
+        if fields:
+            selection = array[fields]
+            # fcount = len(fields)
+        else:
+            selection = array
+            # fcount = len(array.dtype.fields)
+
+        # XXX: manual ``.view()`` attempt that also doesn't work.
+        # uview = selection.view(
+        #     dtype='<f16',
+        # ).reshape(-1, 4, order='A')
+
+        # assert len(selection) == len(uview)
+
+        u = rfn.structured_to_unstructured(
+            selection,
+            # dtype=float,
+            copy=True,
+        )
+
+        # unstruct = np.ndarray(u.shape, dtype=a.dtype, buffer=shm.buf)
+        # array[:] = a[:]
+        return u
+        # return ShmArray(
+        #     shmarr=u,
+        #     first=self._first,
+        #     last=self._last,
+        #     shm=self._shm
+        # )
+
+    def last(
+        self,
+        length: int = 1,
+
+    ) -> np.ndarray:
+        '''
+        Return the last ``length``'s worth of ("row") entries from the
+        array.
+
+        '''
+        return self.array[-length:]
+
+    def push(
+        self,
+        data: np.ndarray,
+
+        field_map: Optional[dict[str, str]] = None,
+        prepend: bool = False,
+        update_first: bool = True,
+        start: int | None = None,
+
+    ) -> int:
+        '''
+        Ring buffer like "push" to append data
+        into the buffer and return updated "last" index.
+
+        NB: no actual ring logic yet to give a "loop around" on overflow
+        condition, lel.
+
+        '''
+        length = len(data)
+
+        if prepend:
+            index = (start or self._first.value) - length
+
+            if index < 0:
+                raise ValueError(
+                    f'Array size of {self._len} was overrun during prepend.\n'
+                    f'You have passed {abs(index)} too many datums.'
+                )
+
+        else:
+            index = start if start is not None else self._last.value
+
+        end = index + length
+
+        if field_map:
+            src_names, dst_names = zip(*field_map.items())
+        else:
+            dst_names = src_names = self._write_fields
+
+        try:
+            self._array[
+                list(dst_names)
+            ][index:end] = data[list(src_names)][:]
+
+            # NOTE: there was a race here between updating
+            # the first and last indices and when the next reader
+            # tries to access ``.array`` (which due to the index
+            # overlap will be empty). Pretty sure we've fixed it now
+            # but leaving this here as a reminder.
+            if (
+                prepend
+                and update_first
+                and length
+            ):
+                assert index < self._first.value
+
+            if (
+                index < self._first.value
+                and update_first
+            ):
+                assert prepend, 'prepend=True not passed but index decreased?'
+                self._first.value = index
+
+            elif not prepend:
+                self._last.value = end
+
+            self._post_init = True
+            return end
+
+        except ValueError as err:
+            if field_map:
+                raise
+
+            # should raise if diff detected
+            self.diff_err_fields(data)
+            raise err
+
+    def diff_err_fields(
+        self,
+        data: np.ndarray,
+    ) -> None:
+        # reraise with any field discrepancy
+        our_fields, their_fields = (
+            set(self._array.dtype.fields),
+            set(data.dtype.fields),
+        )
+
+        only_in_ours = our_fields - their_fields
+        only_in_theirs = their_fields - our_fields
+
+        if only_in_ours:
+            raise TypeError(
+                f"Input array is missing field(s): {only_in_ours}"
+            )
+        elif only_in_theirs:
+            raise TypeError(
+                f"Input array has unknown field(s): {only_in_theirs}"
+            )
+
+    # TODO: support "silent" prepends that don't update ._first.value?
+    def prepend(
+        self,
+        data: np.ndarray,
+    ) -> int:
+        end = self.push(data, prepend=True)
+        assert end
+
+    def close(self) -> None:
+        self._first._shm.close()
+        self._last._shm.close()
+        self._shm.close()
+
+    def destroy(self) -> None:
+        if _USE_POSIX:
+            # We manually unlink to bypass all the "resource tracker"
+            # nonsense meant for non-SC systems.
+            shm_unlink(self._shm.name)
+
+        self._first.destroy()
+        self._last.destroy()
+
+    def flush(self) -> None:
+        # TODO: flush to storage backend like markestore?
+        ...
+
+
+def open_shm_ndarray(
+    size: int,
+    key: str | None = None,
+    dtype: np.dtype | None = None,
+    append_start_index: int | None = None,
+    readonly: bool = False,
+
+) -> ShmArray:
+    '''
+    Open a memory shared ``numpy`` using the standard library.
+
+    This call unlinks (aka permanently destroys) the buffer on teardown
+    and thus should be used from the parent-most accessor (process).
+
+    '''
+    # create new shared mem segment for which we
+    # have write permission
+    a = np.zeros(size, dtype=dtype)
+    a['index'] = np.arange(len(a))
+
+    shm = SharedMemory(
+        name=key,
+        create=True,
+        size=a.nbytes
+    )
+    array = np.ndarray(
+        a.shape,
+        dtype=a.dtype,
+        buffer=shm.buf
+    )
+    array[:] = a[:]
+    array.setflags(write=int(not readonly))
+
+    token = _make_token(
+        key=key,
+        size=size,
+        dtype=dtype,
+    )
+
+    # create single entry arrays for storing an first and last indices
+    first = SharedInt(
+        shm=SharedMemory(
+            name=token.shm_first_index_name,
+            create=True,
+            size=4,  # std int
+        )
+    )
+
+    last = SharedInt(
+        shm=SharedMemory(
+            name=token.shm_last_index_name,
+            create=True,
+            size=4,  # std int
+        )
+    )
+
+    # Start the "real-time" append-updated (or "pushed-to") section
+    # after some start index: ``append_start_index``. This allows appending
+    # from a start point in the array which isn't the 0 index and looks
+    # something like,
+    # -------------------------
+    # |              |        i
+    # _________________________
+    # <-------------> <------->
+    #  history         real-time
+    #
+    # Once fully "prepended", the history section will leave the
+    # ``ShmArray._start.value: int = 0`` and the yet-to-be written
+    # real-time section will start at ``ShmArray.index: int``.
+
+    # this sets the index to nearly 2/3rds into the the length of
+    # the buffer leaving at least a "days worth of second samples"
+    # for the real-time section.
+    if append_start_index is None:
+        append_start_index = round(size * 0.616)
+
+    last.value = first.value = append_start_index
+
+    shmarr = ShmArray(
+        array,
+        first,
+        last,
+        shm,
+    )
+
+    assert shmarr._token == token
+    _known_tokens[key] = shmarr.token
+
+    # "unlink" created shm on process teardown by
+    # pushing teardown calls onto actor context stack
+    stack = tractor.current_actor().lifetime_stack
+    stack.callback(shmarr.close)
+    stack.callback(shmarr.destroy)
+
+    return shmarr
+
+
+def attach_shm_ndarray(
+    token: tuple[str, str, tuple[str, str]],
+    readonly: bool = True,
+
+) -> ShmArray:
+    '''
+    Attach to an existing shared memory array previously
+    created by another process using ``open_shared_array``.
+
+    No new shared mem is allocated but wrapper types for read/write
+    access are constructed.
+
+    '''
+    token = NDToken.from_msg(token)
+    key = token.shm_name
+
+    if key in _known_tokens:
+        assert NDToken.from_msg(_known_tokens[key]) == token, "WTF"
+
+    # XXX: ugh, looks like due to the ``shm_open()`` C api we can't
+    # actually place files in a subdir, see discussion here:
+    # https://stackoverflow.com/a/11103289
+
+    # attach to array buffer and view as per dtype
+    _err: Optional[Exception] = None
+    for _ in range(3):
+        try:
+            shm = SharedMemory(
+                name=key,
+                create=False,
+            )
+            break
+        except OSError as oserr:
+            _err = oserr
+            time.sleep(0.1)
+    else:
+        if _err:
+            raise _err
+
+    shmarr = np.ndarray(
+        (token.size,),
+        dtype=token.dtype,
+        buffer=shm.buf
+    )
+    shmarr.setflags(write=int(not readonly))
+
+    first = SharedInt(
+        shm=SharedMemory(
+            name=token.shm_first_index_name,
+            create=False,
+            size=4,  # std int
+        ),
+    )
+    last = SharedInt(
+        shm=SharedMemory(
+            name=token.shm_last_index_name,
+            create=False,
+            size=4,  # std int
+        ),
+    )
+
+    # make sure we can read
+    first.value
+
+    sha = ShmArray(
+        shmarr,
+        first,
+        last,
+        shm,
+    )
+    # read test
+    sha.array
+
+    # Stash key -> token knowledge for future queries
+    # via `maybe_opepn_shm_array()` but only after we know
+    # we can attach.
+    if key not in _known_tokens:
+        _known_tokens[key] = token
+
+    # "close" attached shm on actor teardown
+    tractor.current_actor().lifetime_stack.callback(sha.close)
+
+    return sha
+
+
+def maybe_open_shm_ndarray(
+    key: str,  # unique identifier for segment
+    size: int,
+    dtype: np.dtype | None = None,
+    append_start_index: int = 0,
+    readonly: bool = True,
+
+) -> tuple[ShmArray, bool]:
+    '''
+    Attempt to attach to a shared memory block using a "key" lookup
+    to registered blocks in the users overall "system" registry
+    (presumes you don't have the block's explicit token).
+
+    This function is meant to solve the problem of discovering whether
+    a shared array token has been allocated or discovered by the actor
+    running in **this** process. Systems where multiple actors may seek
+    to access a common block can use this function to attempt to acquire
+    a token as discovered by the actors who have previously stored
+    a "key" -> ``NDToken`` map in an actor local (aka python global)
+    variable.
+
+    If you know the explicit ``NDToken`` for your memory segment instead
+    use ``attach_shm_array``.
+
+    '''
+    try:
+        # see if we already know this key
+        token = _known_tokens[key]
+        return (
+            attach_shm_ndarray(
+                token=token,
+                readonly=readonly,
+            ),
+            False,  # not newly opened
+        )
+    except KeyError:
+        log.warning(f"Could not find {key} in shms cache")
+        if dtype:
+            token = _make_token(
+                key,
+                size=size,
+                dtype=dtype,
+            )
+        else:
+
+            try:
+                return (
+                    attach_shm_ndarray(
+                        token=token,
+                        readonly=readonly,
+                    ),
+                    False,
+                )
+            except FileNotFoundError:
+                log.warning(f"Could not attach to shm with token {token}")
+
+        # This actor does not know about memory
+        # associated with the provided "key".
+        # Attempt to open a block and expect
+        # to fail if a block has been allocated
+        # on the OS by someone else.
+        return (
+            open_shm_ndarray(
+                key=key,
+                size=size,
+                dtype=dtype,
+                append_start_index=append_start_index,
+                readonly=readonly,
+            ),
+            True,
+        )
+
+
+class ShmList(ShareableList):
+    '''
+    Carbon copy of ``.shared_memory.ShareableList`` with a few
+    enhancements:
+
+    - readonly mode via instance var flag  `._readonly: bool`
+    - ``.__getitem__()`` accepts ``slice`` inputs
+    - exposes the underlying buffer "name" as a ``.key: str``
+
+    '''
+    def __init__(
+        self,
+        sequence: list | None = None,
+        *,
+        name: str | None = None,
+        readonly: bool = True
+
+    ) -> None:
+        self._readonly = readonly
+        self._key = name
+        return super().__init__(
+            sequence=sequence,
+            name=name,
+        )
+
+    @property
+    def key(self) -> str:
+        return self._key
+
+    @property
+    def readonly(self) -> bool:
+        return self._readonly
+
+    def __setitem__(
+        self,
+        position,
+        value,
+
+    ) -> None:
+
+        # mimick ``numpy`` error
+        if self._readonly:
+            raise ValueError('assignment destination is read-only')
+
+        return super().__setitem__(position, value)
+
+    def __getitem__(
+        self,
+        indexish,
+    ) -> list:
+
+        # NOTE: this is a non-writeable view (copy?) of the buffer
+        # in a new list instance.
+        if isinstance(indexish, slice):
+            return list(self)[indexish]
+
+        return super().__getitem__(indexish)
+
+    # TODO: should we offer a `.array` and `.push()` equivalent
+    # to the `ShmArray`?
+    # currently we have the following limitations:
+    # - can't write slices of input using traditional slice-assign
+    #   syntax due to the ``ShareableList.__setitem__()`` implementation.
+    # - ``list(shmlist)`` returns a non-mutable copy instead of
+    #   a writeable view which would be handier numpy-style ops.
+
+
+def open_shm_list(
+    key: str,
+    sequence: list | None = None,
+    size: int = int(2 ** 10),
+    dtype: float | int | bool | str | bytes | None = float,
+    readonly: bool = True,
+
+) -> ShmList:
+
+    if sequence is None:
+        default = {
+            float: 0.,
+            int: 0,
+            bool: True,
+            str: 'doggy',
+            None: None,
+        }[dtype]
+        sequence = [default] * size
+
+    shml = ShmList(
+        sequence=sequence,
+        name=key,
+        readonly=readonly,
+    )
+
+    # "close" attached shm on actor teardown
+    try:
+        actor = tractor.current_actor()
+        actor.lifetime_stack.callback(shml.shm.close)
+        actor.lifetime_stack.callback(shml.shm.unlink)
+    except RuntimeError:
+        log.warning('tractor runtime not active, skipping teardown steps')
+
+    return shml
+
+
+def attach_shm_list(
+    key: str,
+    readonly: bool = False,
+
+) -> ShmList:
+
+    return ShmList(
+        name=key,
+        readonly=readonly,
+    )

tractor/_spawn.py

@@ -19,6 +19,7 @@ Machinery for actor process spawning using multiple backends.
 
 """
 from __future__ import annotations
+import multiprocessing as mp
 import sys
 import platform
 from typing import (
@@ -30,30 +31,32 @@ from typing import (
     TYPE_CHECKING,
 )
 
-from exceptiongroup import BaseExceptionGroup
 import trio
-from trio_typing import TaskStatus
+from trio import TaskStatus
 
-from ._debug import (
+from tractor.devx import (
     maybe_wait_for_debugger,
     acquire_debug_lock,
 )
-from ._state import (
+from tractor._state import (
     current_actor,
     is_main_process,
     is_root_process,
     debug_mode,
+    _runtime_vars,
+)
+from tractor.log import get_logger
+from tractor._portal import Portal
+from tractor._runtime import Actor
+from tractor._entry import _mp_main
+from tractor._exceptions import ActorFailure
+from tractor.msg.types import (
+    SpawnSpec,
 )
-from .log import get_logger
-from ._portal import Portal
-from ._runtime import Actor
-from ._entry import _mp_main
-from ._exceptions import ActorFailure
 
 
 if TYPE_CHECKING:
     from ._supervise import ActorNursery
-    import multiprocessing as mp
     ProcessType = TypeVar('ProcessType', mp.Process, trio.Process)
 
 log = get_logger('tractor')
@@ -70,7 +73,6 @@ _spawn_method: SpawnMethodKey = 'trio'
 
 if platform.system() == 'Windows':
 
-    import multiprocessing as mp
     _ctx = mp.get_context("spawn")
 
     async def proc_waiter(proc: mp.Process) -> None:
@@ -141,11 +143,13 @@ async def exhaust_portal(
     '''
     __tracebackhide__ = True
     try:
-        log.debug(f"Waiting on final result from {actor.uid}")
+        log.debug(
+            f'Waiting on final result from {actor.uid}'
+        )
 
         # XXX: streams should never be reaped here since they should
         # always be established and shutdown using a context manager api
-        final = await portal.result()
+        final: Any = await portal.wait_for_result()
 
     except (
         Exception,
@@ -153,13 +157,23 @@ async def exhaust_portal(
     ) as err:
         # we reraise in the parent task via a ``BaseExceptionGroup``
         return err
+
     except trio.Cancelled as err:
         # lol, of course we need this too ;P
         # TODO: merge with above?
-        log.warning(f"Cancelled result waiter for {portal.actor.uid}")
+        log.warning(
+            'Cancelled portal result waiter task:\n'
+            f'uid: {portal.channel.uid}\n'
+            f'error: {err}\n'
+        )
         return err
+
     else:
-        log.debug(f"Returning final result: {final}")
+        log.debug(
+            f'Returning final result from portal:\n'
+            f'uid: {portal.channel.uid}\n'
+            f'result: {final}\n'
+        )
         return final
 
 
@@ -171,41 +185,75 @@ async def cancel_on_completion(
 
 ) -> None:
     '''
-    Cancel actor gracefully once it's "main" portal's
+    Cancel actor gracefully once its "main" portal's
     result arrives.
 
-    Should only be called for actors spawned with `run_in_actor()`.
+    Should only be called for actors spawned via the
+    `Portal.run_in_actor()` API.
+
+    => and really this API will be deprecated and should be
+    re-implemented as a `.hilevel.one_shot_task_nursery()`..)
 
     '''
     # if this call errors we store the exception for later
     # in ``errors`` which will be reraised inside
     # an exception group and we still send out a cancel request
-    result = await exhaust_portal(portal, actor)
+    result: Any|Exception = await exhaust_portal(
+        portal,
+        actor,
+    )
     if isinstance(result, Exception):
-        errors[actor.uid] = result
+        errors[actor.uid]: Exception = result
-        log.warning(
+        log.cancel(
-            f"Cancelling {portal.channel.uid} after error {result}"
+            'Cancelling subactor runtime due to error:\n\n'
+            f'Portal.cancel_actor() => {portal.channel.uid}\n\n'
+            f'error: {result}\n'
         )
 
     else:
         log.runtime(
-            f"Cancelling {portal.channel.uid} gracefully "
+            'Cancelling subactor gracefully:\n\n'
-            f"after result {result}")
+            f'Portal.cancel_actor() => {portal.channel.uid}\n\n'
+            f'result: {result}\n'
+        )
 
     # cancel the process now that we have a final result
     await portal.cancel_actor()
 
 
-async def do_hard_kill(
+async def hard_kill(
     proc: trio.Process,
-    terminate_after: int = 3,
+
+    terminate_after: int = 1.6,
+    # NOTE: for mucking with `.pause()`-ing inside the runtime
+    # whilst also hacking on it XD
+    # terminate_after: int = 99999,
 
 ) -> None:
+    '''
+    Un-gracefully terminate an OS level `trio.Process` after timeout.
+
+    Used in 2 main cases:
+
+    - "unknown remote runtime state": a hanging/stalled actor that
+      isn't responding after sending a (graceful) runtime cancel
+      request via an IPC msg.
+    - "cancelled during spawn": a process who's actor runtime was
+      cancelled before full startup completed (such that
+      cancel-request-handling machinery was never fully
+      initialized) and thus a "cancel request msg" is never going
+      to be handled.
+
+    '''
+    log.cancel(
+        'Terminating sub-proc\n'
+        f'>x)\n'
+        f' |_{proc}\n'
+    )
     # 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: code below was copied verbatim from the now deprecated
@@ -216,6 +264,9 @@ async def do_hard_kill(
         # and wait for it to exit. If cancelled, kills the process and
         # waits for it to finish exiting before propagating the
         # cancellation.
+        #
+        # This code was originally triggred by ``proc.__aexit__()``
+        # but now must be called manually.
         with trio.CancelScope(shield=True):
             if proc.stdin is not None:
                 await proc.stdin.aclose()
@@ -231,16 +282,25 @@ async def do_hard_kill(
                 with trio.CancelScope(shield=True):
                     await proc.wait()
 
+    # XXX NOTE XXX: zombie squad dispatch:
+    # (should ideally never, but) If we do get here it means
+    # graceful termination of a process failed and we need to
+    # resort to OS level signalling to interrupt and cancel the
+    # (presumably stalled or hung) actor. Since we never allow
+    # zombies (as a feature) we ask the OS to do send in the
+    # removal swad as the last resort.
     if cs.cancelled_caught:
-        # XXX: should pretty much never get here unless we have
+        # TODO: toss in the skynet-logo face as ascii art?
-        # to move the bits from ``proc.__aexit__()`` out and
+        log.critical(
-        # into here.
+            # 'Well, the #ZOMBIE_LORD_IS_HERE# to collect\n'
-        log.critical(f"#ZOMBIE_LORD_IS_HERE: {proc}")
+            '#T-800 deployed to collect zombie B0\n'
+            f'>x)\n'
+            f' |_{proc}\n'
+        )
         proc.kill()
 
 
-async def soft_wait(
+async def soft_kill(
-
     proc: ProcessType,
     wait_func: Callable[
         [ProcessType],
@@ -249,15 +309,40 @@ async def soft_wait(
     portal: Portal,
 
 ) -> None:
-    # Wait for proc termination but **dont' yet** call
+    '''
-    # ``trio.Process.__aexit__()`` (it tears down stdio
+    Wait for proc termination but **don't yet** teardown
-    # which will kill any waiting remote pdb trace).
+    std-streams since it will clobber any ongoing pdb REPL
-    # This is a "soft" (cancellable) join/reap.
+    session.
-    uid = portal.channel.uid
+
+    This is our "soft"/graceful, and thus itself also cancellable,
+    join/reap on an actor-runtime-in-process shutdown; it is
+    **not** the same as a "hard kill" via an OS signal (for that
+    see `.hard_kill()`).
+
+    '''
+    uid: tuple[str, str] = portal.channel.uid
     try:
-        log.cancel(f'Soft waiting on actor:\n{uid}')
+        log.cancel(
+            'Soft killing sub-actor via portal request\n'
+            f'c)> {portal.chan.uid}\n'
+            f' |_{proc}\n'
+        )
+        # wait on sub-proc to signal termination
         await wait_func(proc)
+
     except trio.Cancelled:
+        with trio.CancelScope(shield=True):
+            await maybe_wait_for_debugger(
+                child_in_debug=_runtime_vars.get(
+                    '_debug_mode', False
+                ),
+                header_msg=(
+                    'Delaying `soft_kill()` subproc reaper while debugger locked..\n'
+                ),
+                # TODO: need a diff value then default?
+                # poll_steps=9999999,
+            )
+
         # if cancelled during a soft wait, cancel the child
         # actor before entering the hard reap sequence
         # below. This means we try to do a graceful teardown
@@ -268,22 +353,29 @@ async def soft_wait(
 
             async def cancel_on_proc_deth():
                 '''
-                Cancel the actor cancel request if we detect that
+                "Cancel-the-cancel" request: if we detect that the
-                that the process terminated.
+                underlying sub-process exited prior to
+                a `Portal.cancel_actor()` call completing .
 
                 '''
                 await wait_func(proc)
                 n.cancel_scope.cancel()
 
+            # start a task to wait on the termination of the
+            # process by itself waiting on a (caller provided) wait
+            # function which should unblock when the target process
+            # has terminated.
             n.start_soon(cancel_on_proc_deth)
+
+            # send the actor-runtime a cancel request.
             await portal.cancel_actor()
 
             if proc.poll() is None:  # type: ignore
                 log.warning(
-                    'Actor still alive after cancel request:\n'
+                    'Subactor still alive after cancel request?\n\n'
-                    f'{uid}'
+                    f'uid: {uid}\n'
+                    f'|_{proc}\n'
                 )
-
                 n.cancel_scope.cancel()
         raise
 
@@ -295,7 +387,7 @@ async def new_proc(
     errors: dict[tuple[str, str], Exception],
 
     # passed through to actor main
-    bind_addr: tuple[str, int],
+    bind_addrs: list[tuple[str, int]],
     parent_addr: tuple[str, int],
     _runtime_vars: dict[str, Any],  # serialized and sent to _child
 
@@ -307,7 +399,7 @@ async def new_proc(
 ) -> None:
 
     # lookup backend spawning target
-    target = _methods[_spawn_method]
+    target: Callable = _methods[_spawn_method]
 
     # mark the new actor with the global spawn method
     subactor._spawn_method = _spawn_method
@@ -317,7 +409,7 @@ async def new_proc(
         actor_nursery,
         subactor,
         errors,
-        bind_addr,
+        bind_addrs,
         parent_addr,
         _runtime_vars,  # run time vars
         infect_asyncio=infect_asyncio,
@@ -332,7 +424,7 @@ async def trio_proc(
     errors: dict[tuple[str, str], Exception],
 
     # passed through to actor main
-    bind_addr: tuple[str, int],
+    bind_addrs: list[tuple[str, int]],
     parent_addr: tuple[str, int],
     _runtime_vars: dict[str, Any],  # serialized and sent to _child
     *,
@@ -375,19 +467,21 @@ async def trio_proc(
         spawn_cmd.append("--asyncio")
 
     cancelled_during_spawn: bool = False
-    proc: trio.Process | None = None
+    proc: trio.Process|None = None
     try:
         try:
-            # TODO: needs ``trio_typing`` patch?
+            proc: trio.Process = await trio.lowlevel.open_process(spawn_cmd)
-            proc = await trio.lowlevel.open_process(spawn_cmd)
+            log.runtime(
-
+                'Started new child\n'
-            log.runtime(f"Started {proc}")
+                f'|_{proc}\n'
+            )
 
             # wait for actor to spawn and connect back to us
             # channel should have handshake completed by the
             # local actor by the time we get a ref to it
             event, chan = await actor_nursery._actor.wait_for_peer(
-                subactor.uid)
+                subactor.uid
+            )
 
         except trio.Cancelled:
             cancelled_during_spawn = True
@@ -416,18 +510,20 @@ async def trio_proc(
             portal,
         )
 
-        # send additional init params
+        # send a "spawning specification" which configures the
-        await chan.send({
+        # initial runtime state of the child.
-            "_parent_main_data": subactor._parent_main_data,
+        await chan.send(
-            "enable_modules": subactor.enable_modules,
+            SpawnSpec(
-            "_arb_addr": subactor._arb_addr,
+                _parent_main_data=subactor._parent_main_data,
-            "bind_host": bind_addr[0],
+                enable_modules=subactor.enable_modules,
-            "bind_port": bind_addr[1],
+                reg_addrs=subactor.reg_addrs,
-            "_runtime_vars": _runtime_vars,
+                bind_addrs=bind_addrs,
-        })
+                _runtime_vars=_runtime_vars,
+            )
+        )
 
         # track subactor in current nursery
-        curr_actor = current_actor()
+        curr_actor: Actor = current_actor()
         curr_actor._actoruid2nursery[subactor.uid] = actor_nursery
 
         # resume caller at next checkpoint now that child is up
@@ -449,7 +545,7 @@ async def trio_proc(
             # This is a "soft" (cancellable) join/reap which
             # will remote cancel the actor on a ``trio.Cancelled``
             # condition.
-            await soft_wait(
+            await soft_kill(
                 proc,
                 trio.Process.wait,
                 portal
@@ -457,9 +553,11 @@ async def trio_proc(
 
             # cancel result waiter that may have been spawned in
             # tandem if not done already
-            log.warning(
+            log.cancel(
-                "Cancelling existing result waiter task for "
+                'Cancelling portal result reaper task\n'
-                f"{subactor.uid}")
+                f'>c)\n'
+                f' |_{subactor.uid}\n'
+            )
             nursery.cancel_scope.cancel()
 
     finally:
@@ -467,9 +565,13 @@ async def trio_proc(
         # 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}')
+            log.cancel(
-            with trio.CancelScope(shield=True):
+                f'Hard reap sequence starting for subactor\n'
+                f'>x)\n'
+                f' |_{subactor}@{subactor.uid}\n'
+            )
 
+            with trio.CancelScope(shield=True):
                 # don't clobber an ongoing pdb
                 if cancelled_during_spawn:
                     # Try again to avoid TTY clobbering.
@@ -477,22 +579,40 @@ async def trio_proc(
                         with trio.move_on_after(0.5):
                             await proc.wait()
 
-                if is_root_process():
+                await maybe_wait_for_debugger(
-                    # TODO: solve the following issue where we need
+                    child_in_debug=_runtime_vars.get(
-                    # to do a similar wait like this but in an
+                        '_debug_mode', False
-                    # "intermediary" parent actor that itself isn't
+                    ),
-                    # in debug but has a child that is, and we need
+                    header_msg=(
-                    # to hold off on relaying SIGINT until that child
+                        'Delaying subproc reaper while debugger locked..\n'
-                    # is complete.
+                    ),
-                    # https://github.com/goodboy/tractor/issues/320
+
-                    await maybe_wait_for_debugger(
+                    # TODO: need a diff value then default?
-                        child_in_debug=_runtime_vars.get(
+                    # poll_steps=9999999,
-                            '_debug_mode', False),
+                )
-                    )
+                # TODO: solve the following issue where we need
+                # to do a similar wait like this but in an
+                # "intermediary" parent actor that itself isn't
+                # in debug but has a child that is, and we need
+                # to hold off on relaying SIGINT until that child
+                # is complete.
+                # https://github.com/goodboy/tractor/issues/320
+                # -[ ] we need to handle non-root parent-actors specially
+                # by somehow determining if a child is in debug and then
+                # avoiding cancel/kill of said child by this
+                # (intermediary) parent until such a time as the root says
+                # the pdb lock is released and we are good to tear down
+                # (our children)..
+                #
+                # -[ ] so maybe something like this where we try to
+                #     acquire the lock and get notified of who has it,
+                #     check that uid against our known children?
+                # this_uid: tuple[str, str] = current_actor().uid
+                # await acquire_debug_lock(this_uid)
 
                 if proc.poll() is None:
                     log.cancel(f"Attempting to hard kill {proc}")
-                    await do_hard_kill(proc)
+                    await hard_kill(proc)
 
                 log.debug(f"Joined {proc}")
         else:
@@ -510,7 +630,7 @@ async def mp_proc(
     subactor: Actor,
     errors: dict[tuple[str, str], Exception],
     # passed through to actor main
-    bind_addr: tuple[str, int],
+    bind_addrs: list[tuple[str, int]],
     parent_addr: tuple[str, int],
     _runtime_vars: dict[str, Any],  # serialized and sent to _child
     *,
@@ -568,7 +688,7 @@ async def mp_proc(
         target=_mp_main,
         args=(
             subactor,
-            bind_addr,
+            bind_addrs,
             fs_info,
             _spawn_method,
             parent_addr,
@@ -636,7 +756,7 @@ async def mp_proc(
             # This is a "soft" (cancellable) join/reap which
             # will remote cancel the actor on a ``trio.Cancelled``
             # condition.
-            await soft_wait(
+            await soft_kill(
                 proc,
                 proc_waiter,
                 portal

tractor/_state.py

@@ -18,46 +18,127 @@
 Per process state
 
 """
+from __future__ import annotations
+from contextvars import (
+    ContextVar,
+)
 from typing import (
-    Optional,
     Any,
+    TYPE_CHECKING,
 )
 
-import trio
+from trio.lowlevel import current_task
 
-from ._exceptions import NoRuntime
+if TYPE_CHECKING:
+    from ._runtime import Actor
+    from ._context import Context
 
 
-_current_actor: Optional['Actor'] = None  # type: ignore # noqa
+_current_actor: Actor|None = None  # type: ignore # noqa
+_last_actor_terminated: Actor|None = None
+
+# TODO: mk this a `msgspec.Struct`!
 _runtime_vars: dict[str, Any] = {
     '_debug_mode': False,
     '_is_root': False,
-    '_root_mailbox': (None, None)
+    '_root_mailbox': (None, None),
+    '_registry_addrs': [],
+
+    '_is_infected_aio': False,
+
+    # for `tractor.pause_from_sync()` & `breakpoint()` support
+    'use_greenback': False,
 }
 
 
-def current_actor(err_on_no_runtime: bool = True) -> 'Actor':  # type: ignore # noqa
+def last_actor() -> Actor|None:
-    """Get the process-local actor instance.
+    '''
-    """
+    Try to return last active `Actor` singleton
-    if _current_actor is None and err_on_no_runtime:
+    for this process.
-        raise NoRuntime("No local actor has been initialized yet")
+
+    For case where runtime already exited but someone is asking
+    about the "last" actor probably to get its `.uid: tuple`.
+
+    '''
+    return _last_actor_terminated
+
+
+def current_actor(
+    err_on_no_runtime: bool = True,
+) -> Actor:
+    '''
+    Get the process-local actor instance.
+
+    '''
+    if (
+        err_on_no_runtime
+        and
+        _current_actor is None
+    ):
+        msg: str = 'No local actor has been initialized yet?\n'
+        from ._exceptions import NoRuntime
+
+        if last := last_actor():
+            msg += (
+                f'Apparently the lact active actor was\n'
+                f'|_{last}\n'
+                f'|_{last.uid}\n'
+            )
+        # no actor runtime has (as of yet) ever been started for
+        # this process.
+        else:
+            msg += (
+                # 'No last actor found?\n'
+                '\nDid you forget to call one of,\n'
+                '- `tractor.open_root_actor()`\n'
+                '- `tractor.open_nursery()`\n'
+            )
+
+        raise NoRuntime(msg)
 
     return _current_actor
 
 
 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'])
 
 
 def is_root_process() -> bool:
     return _runtime_vars['_is_root']
+
+
+_ctxvar_Context: ContextVar[Context] = ContextVar(
+    'ipc_context',
+    default=None,
+)
+
+
+def current_ipc_ctx(
+    error_on_not_set: bool = False,
+) -> Context|None:
+    ctx: Context = _ctxvar_Context.get()
+
+    if (
+        not ctx
+        and error_on_not_set
+    ):
+        from ._exceptions import InternalError
+        raise InternalError(
+            'No IPC context has been allocated for this task yet?\n'
+            f'|_{current_task()}\n'
+        )
+    return ctx

tractor/_supervise.py

@@ -21,22 +21,22 @@
 from contextlib import asynccontextmanager as acm
 from functools import partial
 import inspect
-from typing import (
+from pprint import pformat
-    Optional,
+from typing import TYPE_CHECKING
-    TYPE_CHECKING,
-)
 import typing
 import warnings
 
-from exceptiongroup import BaseExceptionGroup
 import trio
 
-from ._debug import maybe_wait_for_debugger
+from .devx._debug import maybe_wait_for_debugger
 from ._state import current_actor, is_main_process
 from .log import get_logger, get_loglevel
 from ._runtime import Actor
 from ._portal import Portal
-from ._exceptions import is_multi_cancelled
+from ._exceptions import (
+    is_multi_cancelled,
+    ContextCancelled,
+)
 from ._root import open_root_actor
 from . import _state
 from . import _spawn
@@ -80,54 +80,85 @@ class ActorNursery:
     '''
     def __init__(
         self,
+        # TODO: maybe def these as fields of a struct looking type?
         actor: Actor,
         ria_nursery: trio.Nursery,
         da_nursery: trio.Nursery,
         errors: dict[tuple[str, str], BaseException],
+
     ) -> None:
         # self.supervisor = supervisor  # TODO
         self._actor: Actor = actor
-        self._ria_nursery = ria_nursery
+
+        # TODO: rename to `._tn` for our conventional "task-nursery"
         self._da_nursery = da_nursery
+
         self._children: dict[
             tuple[str, str],
             tuple[
                 Actor,
                 trio.Process | mp.Process,
-                Optional[Portal],
+                Portal | None,
             ]
         ] = {}
-        # portals spawned with ``run_in_actor()`` are
+
-        # cancelled when their "main" result arrives
-        self._cancel_after_result_on_exit: set = set()
         self.cancelled: bool = False
         self._join_procs = trio.Event()
         self._at_least_one_child_in_debug: bool = False
         self.errors = errors
+        self._scope_error: BaseException|None = None
         self.exited = trio.Event()
 
+        # NOTE: when no explicit call is made to
+        # `.open_root_actor()` by application code,
+        # `.open_nursery()` will implicitly call it to start the
+        # actor-tree runtime. In this case we mark ourselves as
+        # such so that runtime components can be aware for logging
+        # and syncing purposes to any actor opened nurseries.
+        self._implicit_runtime_started: bool = False
+
+        # TODO: remove the `.run_in_actor()` API and thus this 2ndary
+        # nursery when that API get's moved outside this primitive!
+        self._ria_nursery = ria_nursery
+        # portals spawned with ``run_in_actor()`` are
+        # cancelled when their "main" result arrives
+        self._cancel_after_result_on_exit: set = set()
+
     async def start_actor(
         self,
         name: str,
+
         *,
-        bind_addr: tuple[str, int] = _default_bind_addr,
+
-        rpc_module_paths: list[str] | None = None,
+        bind_addrs: list[tuple[str, int]] = [_default_bind_addr],
-        enable_modules: list[str] | None = None,
+        rpc_module_paths: list[str]|None = None,
-        loglevel: str | None = None,  # set log level per subactor
+        enable_modules: list[str]|None = None,
-        nursery: trio.Nursery | None = None,
+        loglevel: str|None = None,  # set log level per subactor
-        debug_mode: Optional[bool] | None = None,
+        debug_mode: bool|None = None,
         infect_asyncio: bool = False,
+
+        # TODO: ideally we can rm this once we no longer have
+        # a `._ria_nursery` since the dependent APIs have been
+        # removed!
+        nursery: trio.Nursery|None = None,
+
     ) -> Portal:
         '''
         Start a (daemon) actor: an process that has no designated
         "main task" besides the runtime.
 
         '''
-        loglevel = loglevel or self._actor.loglevel or get_loglevel()
+        __runtimeframe__: int = 1  # noqa
+        loglevel: str = (
+            loglevel
+            or self._actor.loglevel
+            or get_loglevel()
+        )
 
         # configure and pass runtime state
         _rtv = _state._runtime_vars.copy()
         _rtv['_is_root'] = False
+        _rtv['_is_infected_aio'] = infect_asyncio
 
         # allow setting debug policy per actor
         if debug_mode is not None:
@@ -150,14 +181,16 @@ class ActorNursery:
             # modules allowed to invoked funcs from
             enable_modules=enable_modules,
             loglevel=loglevel,
-            arbiter_addr=current_actor()._arb_addr,
+
+            # verbatim relay this actor's registrar addresses
+            registry_addrs=current_actor().reg_addrs,
         )
         parent_addr = self._actor.accept_addr
         assert parent_addr
 
         # start a task to spawn a process
         # blocks until process has been started and a portal setup
-        nursery = nursery or self._da_nursery
+        nursery: trio.Nursery = nursery or self._da_nursery
 
         # XXX: the type ignore is actually due to a `mypy` bug
         return await nursery.start(  # type: ignore
@@ -167,21 +200,29 @@ class ActorNursery:
                 self,
                 subactor,
                 self.errors,
-                bind_addr,
+                bind_addrs,
                 parent_addr,
                 _rtv,  # run time vars
                 infect_asyncio=infect_asyncio,
             )
         )
 
+    # TODO: DEPRECATE THIS:
+    # -[ ] impl instead as a hilevel wrapper on
+    #   top of a `@context` style invocation.
+    #  |_ dynamic @context decoration on child side
+    #  |_ implicit `Portal.open_context() as (ctx, first):`
+    #    and `return first` on parent side.
+    #  |_ mention how it's similar to `trio-parallel` API?
+    # -[ ] use @api_frame on the wrapper
     async def run_in_actor(
         self,
 
         fn: typing.Callable,
         *,
 
-        name: Optional[str] = None,
+        name: str | None = None,
-        bind_addr: tuple[str, int] = _default_bind_addr,
+        bind_addrs: tuple[str, int] = [_default_bind_addr],
         rpc_module_paths: list[str] | None = None,
         enable_modules: list[str] | None = None,
         loglevel: str | None = None,  # set log level per subactor
@@ -190,25 +231,28 @@ class ActorNursery:
         **kwargs,  # explicit args to ``fn``
 
     ) -> Portal:
-        """Spawn a new actor, run a lone task, then terminate the actor and
+        '''
+        Spawn a new actor, run a lone task, then terminate the actor and
         return its result.
 
         Actors spawned using this method are kept alive at nursery teardown
         until the task spawned by executing ``fn`` completes at which point
         the actor is terminated.
-        """
+
-        mod_path = fn.__module__
+        '''
+        __runtimeframe__: int = 1  # noqa
+        mod_path: str = fn.__module__
 
         if name is None:
             # use the explicit function name if not provided
             name = fn.__name__
 
-        portal = await self.start_actor(
+        portal: Portal = await self.start_actor(
             name,
             enable_modules=[mod_path] + (
                 enable_modules or rpc_module_paths or []
             ),
-            bind_addr=bind_addr,
+            bind_addrs=bind_addrs,
             loglevel=loglevel,
             # use the run_in_actor nursery
             nursery=self._ria_nursery,
@@ -232,21 +276,42 @@ class ActorNursery:
         )
         return portal
 
-    async def cancel(self, hard_kill: bool = False) -> None:
+    # @api_frame
-        """Cancel this nursery by instructing each subactor to cancel
+    async def cancel(
-        itself and wait for all subactors to terminate.
+        self,
+        hard_kill: bool = False,
 
-        If ``hard_killl`` is set to ``True`` then kill the processes
+    ) -> None:
-        directly without any far end graceful ``trio`` cancellation.
+        '''
-        """
+        Cancel this actor-nursery by instructing each subactor's
+        runtime to cancel and wait for all underlying sub-processes
+        to terminate.
+
+        If `hard_kill` is set then kill the processes directly using
+        the spawning-backend's API/OS-machinery without any attempt
+        at (graceful) `trio`-style cancellation using our
+        `Actor.cancel()`.
+
+        '''
+        __runtimeframe__: int = 1  # noqa
         self.cancelled = True
 
-        log.cancel(f"Cancelling nursery in {self._actor.uid}")
+        # TODO: impl a repr for spawn more compact
+        # then `._children`..
+        children: dict = self._children
+        child_count: int = len(children)
+        msg: str = f'Cancelling actor nursery with {child_count} children\n'
         with trio.move_on_after(3) as cs:
+            async with trio.open_nursery() as tn:
 
-            async with trio.open_nursery() as nursery:
+                subactor: Actor
-
+                proc: trio.Process
-                for subactor, proc, portal in self._children.values():
+                portal: Portal
+                for (
+                    subactor,
+                    proc,
+                    portal,
+                ) in children.values():
 
                     # TODO: are we ever even going to use this or
                     # is the spawning backend responsible for such
@@ -258,12 +323,13 @@ class ActorNursery:
                         if portal is None:  # actor hasn't fully spawned yet
                             event = self._actor._peer_connected[subactor.uid]
                             log.warning(
-                                f"{subactor.uid} wasn't finished spawning?")
+                                f"{subactor.uid} never 't finished spawning?"
+                            )
 
                             await event.wait()
 
                             # channel/portal should now be up
-                            _, _, portal = self._children[subactor.uid]
+                            _, _, portal = children[subactor.uid]
 
                             # XXX should be impossible to get here
                             # unless method was called from within
@@ -280,14 +346,24 @@ class ActorNursery:
                         # spawn cancel tasks for each sub-actor
                         assert portal
                         if portal.channel.connected():
-                            nursery.start_soon(portal.cancel_actor)
+                            tn.start_soon(portal.cancel_actor)
 
+                log.cancel(msg)
         # if we cancelled the cancel (we hung cancelling remote actors)
         # then hard kill all sub-processes
         if cs.cancelled_caught:
             log.error(
-                f"Failed to cancel {self}\nHard killing process tree!")
+                f'Failed to cancel {self}?\n'
-            for subactor, proc, portal in self._children.values():
+                'Hard killing underlying subprocess tree!\n'
+            )
+            subactor: Actor
+            proc: trio.Process
+            portal: Portal
+            for (
+                subactor,
+                proc,
+                portal,
+            ) in children.values():
                 log.warning(f"Hard killing process {proc}")
                 proc.terminate()
 
@@ -298,11 +374,15 @@ class ActorNursery:
 @acm
 async def _open_and_supervise_one_cancels_all_nursery(
     actor: Actor,
+    tb_hide: bool = False,
 
 ) -> typing.AsyncGenerator[ActorNursery, None]:
 
-    # TODO: yay or nay?
+    # normally don't need to show user by default
-    __tracebackhide__ = True
+    __tracebackhide__: bool = tb_hide
+
+    outer_err: BaseException|None = None
+    inner_err: BaseException|None = None
 
     # the collection of errors retreived from spawned sub-actors
     errors: dict[tuple[str, str], BaseException] = {}
@@ -312,7 +392,7 @@ async def _open_and_supervise_one_cancels_all_nursery(
     # handling errors that are generated by the inner nursery in
     # a supervisor strategy **before** blocking indefinitely to wait for
     # actors spawned in "daemon mode" (aka started using
-    # ``ActorNursery.start_actor()``).
+    # `ActorNursery.start_actor()`).
 
     # errors from this daemon actor nursery bubble up to caller
     async with trio.open_nursery() as da_nursery:
@@ -327,7 +407,7 @@ async def _open_and_supervise_one_cancels_all_nursery(
             # the above "daemon actor" nursery will be notified.
             async with trio.open_nursery() as ria_nursery:
 
-                anursery = ActorNursery(
+                an = ActorNursery(
                     actor,
                     ria_nursery,
                     da_nursery,
@@ -336,18 +416,19 @@ async def _open_and_supervise_one_cancels_all_nursery(
                 try:
                     # spawning of actors happens in the caller's scope
                     # after we yield upwards
-                    yield anursery
+                    yield an
 
                     # When we didn't error in the caller's scope,
                     # signal all process-monitor-tasks to conduct
                     # the "hard join phase".
                     log.runtime(
-                        f"Waiting on subactors {anursery._children} "
+                        'Waiting on subactors to complete:\n'
-                        "to complete"
+                        f'{pformat(an._children)}\n'
                     )
-                    anursery._join_procs.set()
+                    an._join_procs.set()
 
-                except BaseException as inner_err:
+                except BaseException as _inner_err:
+                    inner_err = _inner_err
                     errors[actor.uid] = inner_err
 
                     # If we error in the root but the debugger is
@@ -357,37 +438,60 @@ async def _open_and_supervise_one_cancels_all_nursery(
                     # Instead try to wait for pdb to be released before
                     # tearing down.
                     await maybe_wait_for_debugger(
-                        child_in_debug=anursery._at_least_one_child_in_debug
+                        child_in_debug=an._at_least_one_child_in_debug
                     )
 
                     # if the caller's scope errored then we activate our
                     # one-cancels-all supervisor strategy (don't
                     # worry more are coming).
-                    anursery._join_procs.set()
+                    an._join_procs.set()
 
-                    # XXX: hypothetically an error could be
+                    # XXX NOTE XXX: hypothetically an error could
-                    # raised and then a cancel signal shows up
+                    # be raised and then a cancel signal shows up
                     # slightly after in which case the `else:`
                     # block here might not complete?  For now,
                     # shield both.
                     with trio.CancelScope(shield=True):
-                        etype = type(inner_err)
+                        etype: type = type(inner_err)
                         if etype in (
                             trio.Cancelled,
-                            KeyboardInterrupt
+                            KeyboardInterrupt,
                         ) or (
                             is_multi_cancelled(inner_err)
                         ):
                             log.cancel(
-                                f"Nursery for {current_actor().uid} "
+                                f'Actor-nursery cancelled by {etype}\n\n'
-                                f"was cancelled with {etype}")
+
+                                f'{current_actor().uid}\n'
+                                f' |_{an}\n\n'
+
+                                # TODO: show tb str?
+                                # f'{tb_str}'
+                            )
+                        elif etype in {
+                            ContextCancelled,
+                        }:
+                            log.cancel(
+                                'Actor-nursery caught remote cancellation\n\n'
+
+                                f'{inner_err.tb_str}'
+                            )
                         else:
                             log.exception(
-                                f"Nursery for {current_actor().uid} "
+                                'Nursery errored with:\n'
-                                f"errored with")
+
+                                # TODO: same thing as in
+                                # `._invoke()` to compute how to
+                                # place this div-line in the
+                                # middle of the above msg
+                                # content..
+                                # -[ ] prolly helper-func it too
+                                #   in our `.log` module..
+                                # '------ - ------'
+                            )
 
                         # cancel all subactors
-                        await anursery.cancel()
+                        await an.cancel()
 
             # ria_nursery scope end
 
@@ -402,24 +506,30 @@ async def _open_and_supervise_one_cancels_all_nursery(
             Exception,
             BaseExceptionGroup,
             trio.Cancelled
+        ) as _outer_err:
+            outer_err = _outer_err
 
-        ) as err:
+            an._scope_error = outer_err or inner_err
 
             # XXX: yet another guard before allowing the cancel
             # sequence in case a (single) child is in debug.
             await maybe_wait_for_debugger(
-                child_in_debug=anursery._at_least_one_child_in_debug
+                child_in_debug=an._at_least_one_child_in_debug
             )
 
             # If actor-local error was raised while waiting on
             # ".run_in_actor()" actors then we also want to cancel all
             # remaining sub-actors (due to our lone strategy:
             # one-cancels-all).
-            log.cancel(f"Nursery cancelling due to {err}")
+            if an._children:
-            if anursery._children:
+                log.cancel(
+                    'Actor-nursery cancelling due error type:\n'
+                    f'{outer_err}\n'
+                )
                 with trio.CancelScope(shield=True):
-                    await anursery.cancel()
+                    await an.cancel()
             raise
+
         finally:
             # No errors were raised while awaiting ".run_in_actor()"
             # actors but those actors may have returned remote errors as
@@ -428,9 +538,9 @@ async def _open_and_supervise_one_cancels_all_nursery(
             # collected in ``errors`` so cancel all actors, summarize
             # all errors and re-raise.
             if errors:
-                if anursery._children:
+                if an._children:
                     with trio.CancelScope(shield=True):
-                        await anursery.cancel()
+                        await an.cancel()
 
                 # use `BaseExceptionGroup` as needed
                 if len(errors) > 1:
@@ -441,11 +551,19 @@ async def _open_and_supervise_one_cancels_all_nursery(
                 else:
                     raise list(errors.values())[0]
 
+            # show frame on any (likely) internal error
+            if (
+                not an.cancelled
+                and an._scope_error
+            ):
+                __tracebackhide__: bool = False
+
         # da_nursery scope end - nursery checkpoint
     # final exit
 
 
 @acm
+# @api_frame
 async def open_nursery(
     **kwargs,
 
@@ -465,19 +583,21 @@ async def open_nursery(
     which cancellation scopes correspond to each spawned subactor set.
 
     '''
-    implicit_runtime = False
+    __tracebackhide__: bool = True
-
+    implicit_runtime: bool = False
-    actor = current_actor(err_on_no_runtime=False)
+    actor: Actor = current_actor(err_on_no_runtime=False)
-
+    an: ActorNursery|None = None
     try:
-        if actor is None and is_main_process():
+        if (
-
+            actor is None
+            and is_main_process()
+        ):
             # if we are the parent process start the
             # actor runtime implicitly
             log.info("Starting actor runtime!")
 
             # mark us for teardown on exit
-            implicit_runtime = True
+            implicit_runtime: bool = True
 
             async with open_root_actor(**kwargs) as actor:
                 assert actor is current_actor()
@@ -485,24 +605,54 @@ async def open_nursery(
                 try:
                     async with _open_and_supervise_one_cancels_all_nursery(
                         actor
-                    ) as anursery:
+                    ) as an:
-                        yield anursery
+
+                        # NOTE: mark this nursery as having
+                        # implicitly started the root actor so
+                        # that `._runtime` machinery can avoid
+                        # certain teardown synchronization
+                        # blocking/waits and any associated (warn)
+                        # logging when it's known that this
+                        # nursery shouldn't be exited before the
+                        # root actor is.
+                        an._implicit_runtime_started = True
+                        yield an
                 finally:
-                    anursery.exited.set()
+                    # XXX: this event will be set after the root actor
+                    # runtime is already torn down, so we want to
+                    # avoid any blocking on it.
+                    an.exited.set()
 
         else:  # sub-nursery case
 
             try:
                 async with _open_and_supervise_one_cancels_all_nursery(
                     actor
-                ) as anursery:
+                ) as an:
-                    yield anursery
+                    yield an
             finally:
-                anursery.exited.set()
+                an.exited.set()
 
     finally:
-        log.debug("Nursery teardown complete")
+        # show frame on any internal runtime-scope error
+        if (
+            an
+            and not an.cancelled
+            and an._scope_error
+        ):
+            __tracebackhide__: bool = False
+
+        msg: str = (
+            'Actor-nursery exited\n'
+            f'|_{an}\n'
+        )
 
-        # shutdown runtime if it was started
         if implicit_runtime:
-            log.info("Shutting down actor tree")
+            # shutdown runtime if it was started and report noisly
+            # that we're did so.
+            msg += '=> Shutting down actor runtime <=\n'
+            log.info(msg)
+
+        else:
+            # keep noise low during std operation.
+            log.runtime(msg)

tractor/_testing/__init__.py

@@ -0,0 +1,96 @@
+# 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/>.
+
+'''
+Various helpers/utils for auditing your `tractor` app and/or the
+core runtime.
+
+'''
+from contextlib import asynccontextmanager as acm
+import pathlib
+
+import tractor
+from .pytest import (
+    tractor_test as tractor_test
+)
+from .fault_simulation import (
+    break_ipc as break_ipc,
+)
+
+
+def repodir() -> pathlib.Path:
+    '''
+    Return the abspath to the repo directory.
+
+    '''
+    # 2 parents up to step up through tests/<repo_dir>
+    return pathlib.Path(
+        __file__
+
+    # 3 .parents bc:
+    # <._testing-pkg>.<tractor-pkg>.<git-repo-dir>
+    # /$HOME/../<tractor-repo-dir>/tractor/_testing/__init__.py
+    ).parent.parent.parent.absolute()
+
+
+def examples_dir() -> pathlib.Path:
+    '''
+    Return the abspath to the examples directory as `pathlib.Path`.
+
+    '''
+    return repodir() / 'examples'
+
+
+def mk_cmd(
+    ex_name: str,
+    exs_subpath: str = 'debugging',
+) -> str:
+    '''
+    Generate a shell command suitable to pass to ``pexpect.spawn()``.
+
+    '''
+    script_path: pathlib.Path = (
+        examples_dir()
+        / exs_subpath
+        / f'{ex_name}.py'
+    )
+    return ' '.join([
+        'python',
+        str(script_path)
+    ])
+
+
+@acm
+async def expect_ctxc(
+    yay: bool,
+    reraise: bool = False,
+) -> None:
+    '''
+    Small acm to catch `ContextCancelled` errors when expected
+    below it in a `async with ()` block.
+
+    '''
+    if yay:
+        try:
+            yield
+            raise RuntimeError('Never raised ctxc?')
+        except tractor.ContextCancelled:
+            if reraise:
+                raise
+            else:
+                return
+    else:
+        yield

tractor/_testing/fault_simulation.py

@@ -0,0 +1,92 @@
+# 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/>.
+
+'''
+`pytest` utils helpers and plugins for testing `tractor`'s runtime
+and applications.
+
+'''
+
+from tractor import (
+    MsgStream,
+)
+
+async def break_ipc(
+    stream: MsgStream,
+    method: str|None = None,
+    pre_close: bool = False,
+
+    def_method: str = 'socket_close',
+
+) -> None:
+    '''
+    XXX: close the channel right after an error is raised
+    purposely breaking the IPC transport to make sure the parent
+    doesn't get stuck in debug or hang on the connection join.
+    this more or less simulates an infinite msg-receive hang on
+    the other end.
+
+    '''
+    # close channel via IPC prot msging before
+    # any transport breakage
+    if pre_close:
+        await stream.aclose()
+
+    method: str = method or def_method
+    print(
+        '#################################\n'
+        'Simulating CHILD-side IPC BREAK!\n'
+        f'method: {method}\n'
+        f'pre `.aclose()`: {pre_close}\n'
+        '#################################\n'
+    )
+
+    match method:
+        case 'socket_close':
+            await stream._ctx.chan.transport.stream.aclose()
+
+        case 'socket_eof':
+            # NOTE: `trio` does the following underneath this
+            # call in `src/trio/_highlevel_socket.py`:
+            # `Stream.socket.shutdown(tsocket.SHUT_WR)`
+            await stream._ctx.chan.transport.stream.send_eof()
+
+        # TODO: remove since now this will be invalid with our
+        # new typed msg spec?
+        # case 'msg':
+        #     await stream._ctx.chan.send(None)
+
+        # TODO: the actual real-world simulated cases like
+        # transport layer hangs and/or lower layer 2-gens type
+        # scenarios..
+        #
+        # -[ ] already have some issues for this general testing
+        # area:
+        #  - https://github.com/goodboy/tractor/issues/97
+        #  - https://github.com/goodboy/tractor/issues/124
+        #   - PR from @guille:
+        #     https://github.com/goodboy/tractor/pull/149
+        # case 'hang':
+        # TODO: framework research:
+        #
+        # - https://github.com/GuoTengda1993/pynetem
+        # - https://github.com/shopify/toxiproxy
+        # - https://manpages.ubuntu.com/manpages/trusty/man1/wirefilter.1.html
+
+        case _:
+            raise RuntimeError(
+                f'IPC break method unsupported: {method}'
+            )

tractor/_testing/pytest.py

@@ -0,0 +1,113 @@
+# 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/>.
+
+'''
+`pytest` utils helpers and plugins for testing `tractor`'s runtime
+and applications.
+
+'''
+from functools import (
+    partial,
+    wraps,
+)
+import inspect
+import platform
+
+import tractor
+import trio
+
+
+def tractor_test(fn):
+    '''
+    Decorator for async test funcs to present them as "native"
+    looking sync funcs runnable by `pytest` using `trio.run()`.
+
+    Use:
+
+    @tractor_test
+    async def test_whatever():
+        await ...
+
+    If fixtures:
+
+        - ``reg_addr`` (a socket addr tuple where arbiter is listening)
+        - ``loglevel`` (logging level passed to tractor internals)
+        - ``start_method`` (subprocess spawning backend)
+
+    are defined in the `pytest` fixture space they will be automatically
+    injected to tests declaring these funcargs.
+    '''
+    @wraps(fn)
+    def wrapper(
+        *args,
+        loglevel=None,
+        reg_addr=None,
+        start_method: str|None = None,
+        debug_mode: bool = False,
+        **kwargs
+    ):
+        # __tracebackhide__ = True
+
+        # NOTE: inject ant test func declared fixture
+        # names by manually checking!
+        if 'reg_addr' in inspect.signature(fn).parameters:
+            # injects test suite fixture value to test as well
+            # as `run()`
+            kwargs['reg_addr'] = reg_addr
+
+        if 'loglevel' in inspect.signature(fn).parameters:
+            # allows test suites to define a 'loglevel' fixture
+            # that activates the internal logging
+            kwargs['loglevel'] = loglevel
+
+        if start_method is None:
+            if platform.system() == "Windows":
+                start_method = 'trio'
+
+        if 'start_method' in inspect.signature(fn).parameters:
+            # set of subprocess spawning backends
+            kwargs['start_method'] = start_method
+
+        if 'debug_mode' in inspect.signature(fn).parameters:
+            # set of subprocess spawning backends
+            kwargs['debug_mode'] = debug_mode
+
+
+        if kwargs:
+
+            # use explicit root actor start
+            async def _main():
+                async with tractor.open_root_actor(
+                    # **kwargs,
+                    registry_addrs=[reg_addr] if reg_addr else None,
+                    loglevel=loglevel,
+                    start_method=start_method,
+
+                    # TODO: only enable when pytest is passed --pdb
+                    debug_mode=debug_mode,
+
+                ):
+                    await fn(*args, **kwargs)
+
+            main = _main
+
+        else:
+            # use implicit root actor start
+            main = partial(fn, *args, **kwargs)
+
+        return trio.run(main)
+
+    return wrapper

tractor/devx/__init__.py

@@ -0,0 +1,43 @@
+# 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/>.
+
+"""
+Runtime "developer experience" utils and addons to aid our
+(advanced) users and core devs in building distributed applications
+and working with/on the actor runtime.
+
+"""
+from ._debug import (
+    maybe_wait_for_debugger as maybe_wait_for_debugger,
+    acquire_debug_lock as acquire_debug_lock,
+    breakpoint as breakpoint,
+    pause as pause,
+    pause_from_sync as pause_from_sync,
+    sigint_shield as sigint_shield,
+    open_crash_handler as open_crash_handler,
+    maybe_open_crash_handler as maybe_open_crash_handler,
+    maybe_init_greenback as maybe_init_greenback,
+    post_mortem as post_mortem,
+    mk_pdb as mk_pdb,
+)
+from ._stackscope import (
+    enable_stack_on_sig as enable_stack_on_sig,
+)
+from .pformat import (
+    add_div as add_div,
+    pformat_caller_frame as pformat_caller_frame,
+    pformat_boxed_tb as pformat_boxed_tb,
+)

tractor/devx/_frame_stack.py

@@ -0,0 +1,288 @@
+# 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/>.
+
+'''
+Tools for code-object annotation, introspection and mutation
+as it pertains to improving the grok-ability of our runtime!
+
+'''
+from __future__ import annotations
+from functools import partial
+import inspect
+from types import (
+    FrameType,
+    FunctionType,
+    MethodType,
+    # CodeType,
+)
+from typing import (
+    Any,
+    Callable,
+    Type,
+)
+
+from tractor.msg import (
+    pretty_struct,
+    NamespacePath,
+)
+import wrapt
+
+
+# TODO: yeah, i don't love this and we should prolly just
+# write a decorator that actually keeps a stupid ref to the func
+# obj..
+def get_class_from_frame(fr: FrameType) -> (
+    FunctionType
+    |MethodType
+):
+    '''
+    Attempt to get the function (or method) reference
+    from a given `FrameType`.
+
+    Verbatim from an SO:
+    https://stackoverflow.com/a/2220759
+
+    '''
+    args, _, _, value_dict = inspect.getargvalues(fr)
+
+    # we check the first parameter for the frame function is
+    # named 'self'
+    if (
+        len(args)
+        and
+        # TODO: other cases for `@classmethod` etc..?)
+        args[0] == 'self'
+    ):
+        # in that case, 'self' will be referenced in value_dict
+        instance: object = value_dict.get('self')
+        if instance:
+          # return its class
+          return getattr(
+              instance,
+              '__class__',
+              None,
+          )
+
+    # return None otherwise
+    return None
+
+
+def get_ns_and_func_from_frame(
+    frame: FrameType,
+) -> Callable:
+    '''
+    Return the corresponding function object reference from
+    a `FrameType`, and return it and it's parent namespace `dict`.
+
+    '''
+    ns: dict[str, Any]
+
+    # for a method, go up a frame and lookup the name in locals()
+    if '.' in (qualname := frame.f_code.co_qualname):
+        cls_name, _, func_name = qualname.partition('.')
+        ns = frame.f_back.f_locals[cls_name].__dict__
+
+    else:
+        func_name: str = frame.f_code.co_name
+        ns = frame.f_globals
+
+    return (
+        ns,
+        ns[func_name],
+    )
+
+
+def func_ref_from_frame(
+    frame: FrameType,
+) -> Callable:
+    func_name: str = frame.f_code.co_name
+    try:
+        return frame.f_globals[func_name]
+    except KeyError:
+        cls: Type|None = get_class_from_frame(frame)
+        if cls:
+            return getattr(
+                cls,
+                func_name,
+            )
+
+
+class CallerInfo(pretty_struct.Struct):
+    # https://docs.python.org/dev/reference/datamodel.html#frame-objects
+    # https://docs.python.org/dev/library/inspect.html#the-interpreter-stack
+    _api_frame: FrameType
+
+    @property
+    def api_frame(self) -> FrameType:
+        try:
+            self._api_frame.clear()
+        except RuntimeError:
+            # log.warning(
+            print(
+                f'Frame {self._api_frame} for {self.api_func} is still active!'
+            )
+
+        return self._api_frame
+
+    _api_func: Callable
+
+    @property
+    def api_func(self) -> Callable:
+        return self._api_func
+
+    _caller_frames_up: int|None = 1
+    _caller_frame: FrameType|None = None  # cached after first stack scan
+
+    @property
+    def api_nsp(self) -> NamespacePath|None:
+        func: FunctionType = self.api_func
+        if func:
+            return NamespacePath.from_ref(func)
+
+        return '<unknown>'
+
+    @property
+    def caller_frame(self) -> FrameType:
+
+        # if not already cached, scan up stack explicitly by
+        # configured count.
+        if not self._caller_frame:
+            if self._caller_frames_up:
+                for _ in range(self._caller_frames_up):
+                    caller_frame: FrameType|None = self.api_frame.f_back
+
+                if not caller_frame:
+                    raise ValueError(
+                        'No frame exists {self._caller_frames_up} up from\n'
+                        f'{self.api_frame} @ {self.api_nsp}\n'
+                    )
+
+            self._caller_frame = caller_frame
+
+        return self._caller_frame
+
+    @property
+    def caller_nsp(self) -> NamespacePath|None:
+        func: FunctionType = self.api_func
+        if func:
+            return NamespacePath.from_ref(func)
+
+        return '<unknown>'
+
+
+def find_caller_info(
+    dunder_var: str = '__runtimeframe__',
+    iframes:int = 1,
+    check_frame_depth: bool = True,
+
+) -> CallerInfo|None:
+    '''
+    Scan up the callstack for a frame with a `dunder_var: str` variable
+    and return the `iframes` frames above it.
+
+    By default we scan for a `__runtimeframe__` scope var which
+    denotes a `tractor` API above which (one frame up) is "user
+    app code" which "called into" the `tractor` method or func.
+
+    TODO: ex with `Portal.open_context()`
+
+    '''
+    # TODO: use this instead?
+    # https://docs.python.org/3/library/inspect.html#inspect.getouterframes
+    frames: list[inspect.FrameInfo] = inspect.stack()
+    for fi in frames:
+        assert (
+            fi.function
+            ==
+            fi.frame.f_code.co_name
+        )
+        this_frame: FrameType = fi.frame
+        dunder_val: int|None = this_frame.f_locals.get(dunder_var)
+        if dunder_val:
+            go_up_iframes: int = (
+                dunder_val  # could be 0 or `True` i guess?
+                or
+                iframes
+            )
+            rt_frame: FrameType = fi.frame
+            call_frame = rt_frame
+            for i in range(go_up_iframes):
+                call_frame = call_frame.f_back
+
+            return CallerInfo(
+                _api_frame=rt_frame,
+                _api_func=func_ref_from_frame(rt_frame),
+                _caller_frames_up=go_up_iframes,
+            )
+
+    return None
+
+
+_frame2callerinfo_cache: dict[FrameType, CallerInfo] = {}
+
+
+# TODO: -[x] move all this into new `.devx._code`!
+# -[ ] consider rename to _callstack?
+# -[ ] prolly create a `@runtime_api` dec?
+#   |_ @api_frame seems better?
+# -[ ] ^- make it capture and/or accept buncha optional
+#     meta-data like a fancier version of `@pdbp.hideframe`.
+#
+def api_frame(
+    wrapped: Callable|None = None,
+    *,
+    caller_frames_up: int = 1,
+
+) -> Callable:
+
+    # handle the decorator called WITHOUT () case,
+    # i.e. just @api_frame, NOT @api_frame(extra=<blah>)
+    if wrapped is None:
+        return partial(
+            api_frame,
+            caller_frames_up=caller_frames_up,
+        )
+
+    @wrapt.decorator
+    async def wrapper(
+        wrapped: Callable,
+        instance: object,
+        args: tuple,
+        kwargs: dict,
+    ):
+        # maybe cache the API frame for this call
+        global _frame2callerinfo_cache
+        this_frame: FrameType = inspect.currentframe()
+        api_frame: FrameType = this_frame.f_back
+
+        if not _frame2callerinfo_cache.get(api_frame):
+            _frame2callerinfo_cache[api_frame] = CallerInfo(
+                _api_frame=api_frame,
+                _api_func=wrapped,
+                _caller_frames_up=caller_frames_up,
+            )
+
+        return wrapped(*args, **kwargs)
+
+    # annotate the function as a "api function", meaning it is
+    # a function for which the function above it in the call stack should be
+    # non-`tractor` code aka "user code".
+    #
+    # in the global frame cache for easy lookup from a given
+    # func-instance
+    wrapped._call_infos: dict[FrameType, CallerInfo] = _frame2callerinfo_cache
+    wrapped.__api_func__: bool = True
+    return wrapper(wrapped)

tractor/devx/_stackscope.py

@@ -0,0 +1,239 @@
+# tractor: structured concurrent "actors".
+# Copyright 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 functools import partial
+from threading import (
+    current_thread,
+    Thread,
+    RLock,
+)
+import multiprocessing as mp
+from signal import (
+    signal,
+    getsignal,
+    SIGUSR1,
+)
+# import traceback
+from types import ModuleType
+from typing import (
+    Callable,
+    TYPE_CHECKING,
+)
+
+import trio
+from tractor import (
+    _state,
+    log as logmod,
+)
+
+log = logmod.get_logger(__name__)
+
+
+if TYPE_CHECKING:
+    from tractor._spawn import ProcessType
+    from tractor import (
+        Actor,
+        ActorNursery,
+    )
+
+
+@trio.lowlevel.disable_ki_protection
+def dump_task_tree() -> None:
+    '''
+    Do a classic `stackscope.extract()` task-tree dump to console at
+    `.devx()` level.
+
+    '''
+    import stackscope
+    tree_str: str = str(
+        stackscope.extract(
+            trio.lowlevel.current_root_task(),
+            recurse_child_tasks=True
+        )
+    )
+    actor: Actor = _state.current_actor()
+    thr: Thread = current_thread()
+    log.devx(
+        f'Dumping `stackscope` tree for actor\n'
+        f'{actor.uid}:\n'
+        f'|_{mp.current_process()}\n'
+        f'  |_{thr}\n'
+        f'    |_{actor}\n\n'
+
+        # start-of-trace-tree delimiter (mostly for testing)
+        '------ - ------\n'
+        '\n'
+        +
+        f'{tree_str}\n'
+        +
+        # end-of-trace-tree delimiter (mostly for testing)
+        f'\n'
+        f'------ {actor.uid!r} ------\n'
+    )
+    # TODO: can remove this right?
+    # -[ ] was original code from author
+    #
+    # print(
+    #     'DUMPING FROM PRINT\n'
+    #     +
+    #     content
+    # )
+    # import logging
+    # try:
+    #     with open("/dev/tty", "w") as tty:
+    #         tty.write(tree_str)
+    # except BaseException:
+    #     logging.getLogger(
+    #         "task_tree"
+    #     ).exception("Error printing task tree")
+
+_handler_lock = RLock()
+_tree_dumped: bool = False
+
+
+def dump_tree_on_sig(
+    sig: int,
+    frame: object,
+
+    relay_to_subs: bool = True,
+
+) -> None:
+    global _tree_dumped, _handler_lock
+    with _handler_lock:
+        if _tree_dumped:
+            log.warning(
+                'Already dumped for this actor...??'
+            )
+            return
+
+        _tree_dumped = True
+
+        # actor: Actor = _state.current_actor()
+        log.devx(
+            'Trying to dump `stackscope` tree..\n'
+        )
+        try:
+            dump_task_tree()
+            # await actor._service_n.start_soon(
+            #     partial(
+            #         trio.to_thread.run_sync,
+            #         dump_task_tree,
+            #     )
+            # )
+            # trio.lowlevel.current_trio_token().run_sync_soon(
+            #     dump_task_tree
+            # )
+
+        except RuntimeError:
+            log.exception(
+                'Failed to dump `stackscope` tree..\n'
+            )
+            # not in async context -- print a normal traceback
+            # traceback.print_stack()
+            raise
+
+        except BaseException:
+            log.exception(
+                'Failed to dump `stackscope` tree..\n'
+            )
+            raise
+
+        log.devx(
+            'Supposedly we dumped just fine..?'
+        )
+
+    if not relay_to_subs:
+        return
+
+    an: ActorNursery
+    for an in _state.current_actor()._actoruid2nursery.values():
+        subproc: ProcessType
+        subactor: Actor
+        for subactor, subproc, _ in an._children.values():
+            log.warning(
+                f'Relaying `SIGUSR1`[{sig}] to sub-actor\n'
+                f'{subactor}\n'
+                f' |_{subproc}\n'
+            )
+
+            # bc of course stdlib can't have a std API.. XD
+            match subproc:
+                case trio.Process():
+                    subproc.send_signal(sig)
+
+                case mp.Process():
+                    subproc._send_signal(sig)
+
+
+def enable_stack_on_sig(
+    sig: int = SIGUSR1,
+) -> ModuleType:
+    '''
+    Enable `stackscope` tracing on reception of a signal; by
+    default this is SIGUSR1.
+
+    HOT TIP: a task/ctx-tree dump can be triggered from a shell with
+    fancy cmds.
+
+    For ex. from `bash` using `pgrep` and cmd-sustitution
+    (https://www.gnu.org/software/bash/manual/bash.html#Command-Substitution)
+    you could use:
+
+    >> kill -SIGUSR1 $(pgrep -f '<cmd>')
+
+    Or with with `xonsh` (which has diff capture-from-subproc syntax)
+
+    >> kill -SIGUSR1 @$(pgrep -f '<cmd>')
+
+    '''
+    try:
+        import stackscope
+    except ImportError:
+        log.warning(
+            '`stackscope` not installed for use in debug mode!'
+        )
+        return None
+
+    handler: Callable|int = getsignal(sig)
+    if handler is dump_tree_on_sig:
+        log.devx(
+            'A `SIGUSR1` handler already exists?\n'
+            f'|_ {handler!r}\n'
+        )
+        return
+
+    signal(
+        sig,
+        dump_tree_on_sig,
+    )
+    log.devx(
+        'Enabling trace-trees on `SIGUSR1` '
+        'since `stackscope` is installed @ \n'
+        f'{stackscope!r}\n\n'
+        f'With `SIGUSR1` handler\n'
+        f'|_{dump_tree_on_sig}\n'
+    )
+    return stackscope

tractor/devx/cli.py

@@ -0,0 +1,129 @@
+# 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/>.
+
+"""
+CLI framework extensions for hacking on the actor runtime.
+
+Currently popular frameworks supported are:
+
+  - `typer` via the `@callback` API
+
+"""
+from __future__ import annotations
+from typing import (
+    Any,
+    Callable,
+)
+from typing_extensions import Annotated
+
+import typer
+
+
+_runtime_vars: dict[str, Any] = {}
+
+
+def load_runtime_vars(
+    ctx: typer.Context,
+    callback: Callable,
+    pdb: bool = False,  # --pdb
+    ll: Annotated[
+        str,
+        typer.Option(
+            '--loglevel',
+            '-l',
+            help='BigD logging level',
+        ),
+    ] = 'cancel',  # -l info
+):
+    '''
+    Maybe engage crash handling with `pdbp` when code inside
+    a `typer` CLI endpoint cmd raises.
+
+    To use this callback simply take your `app = typer.Typer()` instance
+    and decorate this function with it like so:
+
+    .. code:: python
+
+        from tractor.devx import cli
+
+        app = typer.Typer()
+
+        # manual decoration to hook into `click`'s context system!
+        cli.load_runtime_vars = app.callback(
+            invoke_without_command=True,
+        )
+
+    And then you can use the now augmented `click` CLI context as so,
+
+    .. code:: python
+
+        @app.command(
+            context_settings={
+                "allow_extra_args": True,
+                "ignore_unknown_options": True,
+            }
+        )
+        def my_cli_cmd(
+            ctx: typer.Context,
+        ):
+            rtvars: dict = ctx.runtime_vars
+            pdb: bool = rtvars['pdb']
+
+            with tractor.devx.cli.maybe_open_crash_handler(pdb=pdb):
+                trio.run(
+                    partial(
+                        my_tractor_main_task_func,
+                        debug_mode=pdb,
+                        loglevel=rtvars['ll'],
+                    )
+                )
+
+    which will enable log level and debug mode globally for the entire
+    `tractor` + `trio` runtime thereafter!
+
+    Bo
+
+    '''
+    global _runtime_vars
+    _runtime_vars |= {
+        'pdb': pdb,
+        'll': ll,
+    }
+
+    ctx.runtime_vars: dict[str, Any] = _runtime_vars
+    print(
+        f'`typer` sub-cmd: {ctx.invoked_subcommand}\n'
+        f'`tractor` runtime vars: {_runtime_vars}'
+    )
+
+    # XXX NOTE XXX: hackzone.. if no sub-cmd is specified (the
+    # default if the user just invokes `bigd`) then we simply
+    # invoke the sole `_bigd()` cmd passing in the "parent"
+    # typer.Context directly to that call since we're treating it
+    # as a "non sub-command" or wtv..
+    # TODO: ideally typer would have some kinda built-in way to get
+    # this behaviour without having to construct and manually
+    # invoke our own cmd..
+    if (
+        ctx.invoked_subcommand is None
+        or ctx.invoked_subcommand == callback.__name__
+    ):
+        cmd: typer.core.TyperCommand = typer.core.TyperCommand(
+            name='bigd',
+            callback=callback,
+        )
+        ctx.params = {'ctx': ctx}
+        cmd.invoke(ctx)

tractor/devx/pformat.py

@@ -0,0 +1,168 @@
+# 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/>.
+
+'''
+Pretty formatters for use throughout the code base.
+Mostly handy for logging and exception message content.
+
+'''
+import textwrap
+import traceback
+
+from trio import CancelScope
+
+
+def add_div(
+    message: str,
+    div_str: str = '------ - ------',
+
+) -> str:
+    '''
+    Add a "divider string" to the input `message` with
+    a little math to center it underneath.
+
+    '''
+    div_offset: int = (
+        round(len(message)/2)+1
+        -
+        round(len(div_str)/2)+1
+    )
+    div_str: str = (
+        '\n' + ' '*div_offset + f'{div_str}\n'
+    )
+    return div_str
+
+
+def pformat_boxed_tb(
+    tb_str: str,
+    fields_str: str|None = None,
+    field_prefix: str = ' |_',
+
+    tb_box_indent: int|None = None,
+    tb_body_indent: int = 1,
+
+) -> str:
+    '''
+    Create a "boxed" looking traceback string.
+
+    Useful for emphasizing traceback text content as being an
+    embedded attribute of some other object (like
+    a `RemoteActorError` or other boxing remote error shuttle
+    container).
+
+    Any other parent/container "fields" can be passed in the
+    `fields_str` input along with other prefix/indent settings.
+
+    '''
+    if (
+        fields_str
+        and
+        field_prefix
+    ):
+        fields: str = textwrap.indent(
+            fields_str,
+            prefix=field_prefix,
+        )
+    else:
+        fields = fields_str or ''
+
+    tb_body = tb_str
+    if tb_body_indent:
+        tb_body: str = textwrap.indent(
+            tb_str,
+            prefix=tb_body_indent * ' ',
+        )
+
+    tb_box: str = (
+        f'|\n'
+        f' ------ - ------\n'
+        f'{tb_body}'
+        f' ------ - ------\n'
+        f'_|\n'
+    )
+    tb_box_indent: str = (
+        tb_box_indent
+        or
+        1
+
+        # (len(field_prefix))
+        # ? ^-TODO-^ ? if you wanted another indent level
+    )
+    if tb_box_indent > 0:
+        tb_box: str = textwrap.indent(
+            tb_box,
+            prefix=tb_box_indent * ' ',
+        )
+
+    return (
+        fields
+        +
+        tb_box
+    )
+
+
+def pformat_caller_frame(
+    stack_limit: int = 1,
+    box_tb: bool = True,
+) -> str:
+    '''
+    Capture and return the traceback text content from
+    `stack_limit` call frames up.
+
+    '''
+    tb_str: str = (
+        '\n'.join(
+            traceback.format_stack(limit=stack_limit)
+        )
+    )
+    if box_tb:
+        tb_str: str = pformat_boxed_tb(
+            tb_str=tb_str,
+            field_prefix='  ',
+            indent='',
+        )
+    return tb_str
+
+
+def pformat_cs(
+    cs: CancelScope,
+    var_name: str = 'cs',
+    field_prefix: str = ' |_',
+) -> str:
+    '''
+    Pretty format info about a `trio.CancelScope` including most
+    of its public state and `._cancel_status`.
+
+    The output can be modified to show a "var name" for the
+    instance as a field prefix, just a simple str before each
+    line more or less.
+
+    '''
+
+    fields: str = textwrap.indent(
+        (
+            f'cancel_called = {cs.cancel_called}\n'
+            f'cancelled_caught = {cs.cancelled_caught}\n'
+            f'_cancel_status = {cs._cancel_status}\n'
+            f'shield = {cs.shield}\n'
+        ),
+        prefix=field_prefix,
+    )
+    return (
+        f'{var_name}: {cs}\n'
+        +
+        fields
+    )

tractor/experimental/_pubsub.py

@@ -31,13 +31,13 @@ from typing import (
     Callable,
 )
 from functools import partial
-from async_generator import aclosing
+from contextlib import aclosing
 
 import trio
 import wrapt
 
 from ..log import get_logger
-from .._streaming import Context
+from .._context import Context
 
 
 __all__ = ['pub']
@@ -148,7 +148,8 @@ 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
@@ -227,7 +228,8 @@ 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

@@ -21,6 +21,11 @@ Log like a forester!
 from collections.abc import Mapping
 import sys
 import logging
+from logging import (
+    LoggerAdapter,
+    Logger,
+    StreamHandler,
+)
 import colorlog  # type: ignore
 
 import trio
@@ -48,17 +53,20 @@ LOG_FORMAT = (
 
 DATE_FORMAT = '%b %d %H:%M:%S'
 
-LEVELS = {
+# FYI, ERROR is 40
+# TODO: use a `bidict` to avoid the :155 check?
+CUSTOM_LEVELS: dict[str, int] = {
     'TRANSPORT': 5,
     'RUNTIME': 15,
-    'CANCEL': 16,
+    'DEVX': 17,
+    'CANCEL': 22,
     'PDB': 500,
 }
-
 STD_PALETTE = {
     'CRITICAL': 'red',
     'ERROR': 'red',
     'PDB': 'white',
+    'DEVX': 'cyan',
     'WARNING': 'yellow',
     'INFO': 'green',
     'CANCEL': 'yellow',
@@ -75,13 +83,18 @@ BOLD_PALETTE = {
 
 # TODO: this isn't showing the correct '{filename}'
 # as it did before..
-class StackLevelAdapter(logging.LoggerAdapter):
+class StackLevelAdapter(LoggerAdapter):
 
     def transport(
         self,
         msg: str,
 
     ) -> None:
+        '''
+        IPC transport level msg IO; generally anything below
+        `._ipc.Channel` and friends.
+
+        '''
         return self.log(5, msg)
 
     def runtime(
@@ -94,22 +107,68 @@ class StackLevelAdapter(logging.LoggerAdapter):
         self,
         msg: str,
     ) -> None:
-        return self.log(16, msg)
+        '''
+        Cancellation sequencing, mostly for runtime reporting.
+
+        '''
+        return self.log(
+            level=22,
+            msg=msg,
+            # stacklevel=4,
+        )
 
     def pdb(
         self,
         msg: str,
     ) -> None:
+        '''
+        `pdb`-REPL (debugger) related statuses.
+
+        '''
         return self.log(500, msg)
 
-    def log(self, level, msg, *args, **kwargs):
+    def devx(
-        """
+        self,
+        msg: str,
+    ) -> None:
+        '''
+        "Developer experience" sub-sys statuses.
+
+        '''
+        return self.log(17, msg)
+
+    def log(
+        self,
+        level,
+        msg,
+        *args,
+        **kwargs,
+    ):
+        '''
         Delegate a log call to the underlying logger, after adding
         contextual information from this adapter instance.
-        """
+
+        NOTE: all custom level methods (above) delegate to this!
+
+        '''
         if self.isEnabledFor(level):
+            stacklevel: int = 3
+            if (
+                level in CUSTOM_LEVELS.values()
+            ):
+                stacklevel: int = 4
+
             # msg, kwargs = self.process(msg, kwargs)
-            self._log(level, msg, args, **kwargs)
+            self._log(
+                level=level,
+                msg=msg,
+                args=args,
+                # NOTE: not sure how this worked before but, it
+                # seems with our custom level methods defined above
+                # we do indeed (now) require another stack level??
+                stacklevel=stacklevel,
+                **kwargs,
+            )
 
     # LOL, the stdlib doesn't allow passing through ``stacklevel``..
     def _log(
@@ -122,12 +181,15 @@ class StackLevelAdapter(logging.LoggerAdapter):
         stack_info=False,
 
         # XXX: bit we added to show fileinfo from actual caller.
-        # this level then ``.log()`` then finally the caller's level..
+        # - this level
-        stacklevel=3,
+        # - then ``.log()``
+        # - then finally the caller's level..
+        stacklevel=4,
     ):
-        """
+        '''
         Low-level log implementation, proxied to allow nested logger adapters.
-        """
+
+        '''
         return self.logger._log(
             level,
             msg,
@@ -139,8 +201,30 @@ class StackLevelAdapter(logging.LoggerAdapter):
         )
 
 
+# TODO IDEAs:
+# -[ ] move to `.devx.pformat`?
+# -[ ] do per task-name and actor-name color coding
+# -[ ] unique color per task-id and actor-uuid
+def pformat_task_uid(
+    id_part: str = 'tail'
+):
+    '''
+    Return `str`-ified unique for a `trio.Task` via a combo of its
+    `.name: str` and `id()` truncated output.
+
+    '''
+    task: trio.Task = trio.lowlevel.current_task()
+    tid: str = str(id(task))
+    if id_part == 'tail':
+        tid_part: str = tid[-6:]
+    else:
+        tid_part: str = tid[:6]
+
+    return f'{task.name}[{tid_part}]'
+
+
 _conc_name_getters = {
-    'task': lambda: trio.lowlevel.current_task().name,
+    'task': pformat_task_uid,
     'actor': lambda: current_actor(),
     'actor_name': lambda: current_actor().name,
     'actor_uid': lambda: current_actor().uid[1][:6],
@@ -148,7 +232,10 @@ _conc_name_getters = {
 
 
 class ActorContextInfo(Mapping):
-    "Dyanmic lookup for local actor and task names"
+    '''
+    Dyanmic lookup for local actor and task names.
+
+    '''
     _context_keys = (
         'task',
         'actor',
@@ -179,17 +266,42 @@ def get_logger(
     '''Return the package log or a sub-logger for ``name`` if provided.
 
     '''
+    log: Logger
     log = rlog = logging.getLogger(_root_name)
 
-    if name and name != _proj_name:
+    if (
+        name
+        and name != _proj_name
+    ):
 
-        # handling for modules that use ``get_logger(__name__)`` to
+        # NOTE: for handling for modules that use ``get_logger(__name__)``
-        # avoid duplicate project-package token in msg output
+        # we make the following stylistic choice:
-        rname, _, tail = name.partition('.')
+        # - always avoid duplicate project-package token
-        if rname == _root_name:
+        #   in msg output: i.e. tractor.tractor _ipc.py in header
-            name = tail
+        #   looks ridiculous XD
+        # - never show the leaf module name in the {name} part
+        #   since in python the {filename} is always this same
+        #   module-file.
+
+        sub_name: None | str = None
+        rname, _, sub_name = name.partition('.')
+        pkgpath, _, modfilename = sub_name.rpartition('.')
+
+        # NOTE: for tractor itself never include the last level
+        # module key in the name such that something like: eg.
+        # 'tractor.trionics._broadcast` only includes the first
+        # 2 tokens in the (coloured) name part.
+        if rname == 'tractor':
+            sub_name = pkgpath
+
+        if _root_name in sub_name:
+            duplicate, _, sub_name = sub_name.partition('.')
+
+        if not sub_name:
+            log = rlog
+        else:
+            log = rlog.getChild(sub_name)
 
-        log = rlog.getChild(name)
         log.level = rlog.level
 
     # add our actor-task aware adapter which will dynamically look up
@@ -197,7 +309,7 @@ def get_logger(
     logger = StackLevelAdapter(log, ActorContextInfo())
 
     # additional levels
-    for name, val in LEVELS.items():
+    for name, val in CUSTOM_LEVELS.items():
         logging.addLevelName(val, name)
 
         # ensure customs levels exist as methods
@@ -209,7 +321,7 @@ def get_logger(
 def get_console_log(
     level: str | None = None,
     **kwargs,
-) -> logging.LoggerAdapter:
+) -> LoggerAdapter:
     '''Get the package logger and enable a handler which writes to stderr.
 
     Yeah yeah, i know we can use ``DictConfig``. You do it.
@@ -220,13 +332,21 @@ def get_console_log(
     if not level:
         return log
 
-    log.setLevel(level.upper() if not isinstance(level, int) else level)
+    log.setLevel(
+        level.upper()
+        if not isinstance(level, int)
+        else level
+    )
 
     if not any(
         handler.stream == sys.stderr  # type: ignore
-        for handler in logger.handlers if getattr(handler, 'stream', None)
+        for handler in logger.handlers if getattr(
+            handler,
+            'stream',
+            None,
+        )
     ):
-        handler = logging.StreamHandler()
+        handler = StreamHandler()
         formatter = colorlog.ColoredFormatter(
             LOG_FORMAT,
             datefmt=DATE_FORMAT,
@@ -242,3 +362,23 @@ def get_console_log(
 
 def get_loglevel() -> str:
     return _default_loglevel
+
+
+# global module logger for tractor itself
+log = get_logger('tractor')
+
+
+def at_least_level(
+    log: Logger|LoggerAdapter,
+    level: int|str,
+) -> bool:
+    '''
+    Predicate to test if a given level is active.
+
+    '''
+    if isinstance(level, str):
+        level: int = CUSTOM_LEVELS[level.upper()]
+
+    if log.getEffectiveLevel() <= level:
+        return True
+    return False

tractor/msg.py

@@ -1,80 +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/>.
-
-'''
-Built-in messaging patterns, types, APIs and helpers.
-
-'''
-
-# TODO: integration with our ``enable_modules: list[str]`` caps sys.
-
-# ``pkgutil.resolve_name()`` internally uses
-# ``importlib.import_module()`` which can be filtered by inserting
-# a ``MetaPathFinder`` into ``sys.meta_path`` (which we could do before
-# entering the ``_runtime.process_messages()`` loop).
-# - https://github.com/python/cpython/blob/main/Lib/pkgutil.py#L645
-# - https://stackoverflow.com/questions/1350466/preventing-python-code-from-importing-certain-modules
-#   - https://stackoverflow.com/a/63320902
-#   - https://docs.python.org/3/library/sys.html#sys.meta_path
-
-# the new "Implicit Namespace Packages" might be relevant?
-# - https://www.python.org/dev/peps/pep-0420/
-
-# add implicit serialized message type support so that paths can be
-# handed directly to IPC primitives such as streams and `Portal.run()`
-# calls:
-# - via ``msgspec``:
-#   - https://jcristharif.com/msgspec/api.html#struct
-#   - https://jcristharif.com/msgspec/extending.html
-# via ``msgpack-python``:
-# - https://github.com/msgpack/msgpack-python#packingunpacking-of-custom-data-type
-
-from __future__ import annotations
-from pkgutil import resolve_name
-
-
-class NamespacePath(str):
-    '''
-    A serializeable description of a (function) Python object location
-    described by the target's module path and namespace key meant as
-    a message-native "packet" to allows actors to point-and-load objects
-    by absolute reference.
-
-    '''
-    _ref: object = None
-
-    def load_ref(self) -> object:
-        if self._ref is None:
-            self._ref = resolve_name(self)
-        return self._ref
-
-    def to_tuple(
-        self,
-
-    ) -> tuple[str, str]:
-        ref = self.load_ref()
-        return ref.__module__, getattr(ref, '__name__', '')
-
-    @classmethod
-    def from_ref(
-        cls,
-        ref,
-
-    ) -> NamespacePath:
-        return cls(':'.join(
-            (ref.__module__,
-             getattr(ref, '__name__', ''))
-        ))

tractor/msg/__init__.py

@@ -0,0 +1,73 @@
+# 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/>.
+
+'''
+Built-in messaging patterns, types, APIs and helpers.
+
+'''
+from typing import (
+    TypeAlias,
+)
+from .ptr import (
+    NamespacePath as NamespacePath,
+)
+from .pretty_struct import (
+    Struct as Struct,
+)
+from ._codec import (
+    _def_msgspec_codec as _def_msgspec_codec,
+    _ctxvar_MsgCodec as _ctxvar_MsgCodec,
+
+    apply_codec as apply_codec,
+    mk_codec as mk_codec,
+    MsgCodec as MsgCodec,
+    MsgDec as MsgDec,
+    current_codec as current_codec,
+)
+# currently can't bc circular with `._context`
+# from ._ops import (
+#     PldRx as PldRx,
+#     _drain_to_final_msg as _drain_to_final_msg,
+# )
+
+from .types import (
+    PayloadMsg as PayloadMsg,
+
+    Aid as Aid,
+    SpawnSpec as SpawnSpec,
+
+    Start as Start,
+    StartAck as StartAck,
+
+    Started as Started,
+    Yield as Yield,
+    Stop as Stop,
+    Return as Return,
+    CancelAck as CancelAck,
+
+    Error as Error,
+
+    # type-var for `.pld` field
+    PayloadT as PayloadT,
+
+    # full msg class set from above as list
+    __msg_types__ as __msg_types__,
+
+    # type-alias for union of all msgs
+    MsgType as MsgType,
+)
+
+__msg_spec__: TypeAlias = MsgType

tractor/msg/_codec.py

@@ -0,0 +1,660 @@
+# 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/>.
+
+'''
+IPC msg interchange codec management.
+
+Supported backend libs:
+- `msgspec.msgpack`
+
+ToDo: backends we prolly should offer:
+
+- see project/lib list throughout GH issue discussion comments:
+  https://github.com/goodboy/tractor/issues/196
+
+- `capnproto`: https://capnproto.org/rpc.html
+   - https://capnproto.org/language.html#language-reference
+
+'''
+from __future__ import annotations
+from contextlib import (
+    contextmanager as cm,
+)
+from contextvars import (
+    ContextVar,
+    Token,
+)
+import textwrap
+from typing import (
+    Any,
+    Callable,
+    Type,
+    TYPE_CHECKING,
+    Union,
+)
+from types import ModuleType
+
+import msgspec
+from msgspec import (
+    msgpack,
+    Raw,
+)
+# TODO: see notes below from @mikenerone..
+# from tricycle import TreeVar
+
+from tractor.msg.pretty_struct import Struct
+from tractor.msg.types import (
+    mk_msg_spec,
+    MsgType,
+)
+from tractor.log import get_logger
+
+if TYPE_CHECKING:
+    from tractor._context import Context
+
+log = get_logger(__name__)
+
+
+# TODO: unify with `MsgCodec` by making `._dec` part this?
+class MsgDec(Struct):
+    '''
+    An IPC msg (payload) decoder.
+
+    Normally used to decode only a payload: `MsgType.pld:
+    PayloadT` field before delivery to IPC consumer code.
+
+    '''
+    _dec: msgpack.Decoder
+
+    @property
+    def dec(self) -> msgpack.Decoder:
+        return self._dec
+
+    def __repr__(self) -> str:
+
+        speclines: str = self.spec_str
+
+        # in multi-typed spec case we stick the list
+        # all on newlines after the |__pld_spec__:,
+        # OW it's prolly single type spec-value
+        # so just leave it on same line.
+        if '\n' in speclines:
+            speclines: str = '\n' + textwrap.indent(
+                speclines,
+                prefix=' '*3,
+            )
+
+        body: str = textwrap.indent(
+            f'|_dec_hook: {self.dec.dec_hook}\n'
+            f'|__pld_spec__: {speclines}\n',
+            prefix=' '*2,
+        )
+        return (
+            f'<{type(self).__name__}(\n'
+            f'{body}'
+            ')>'
+        )
+
+    # struct type unions
+    # https://jcristharif.com/msgspec/structs.html#tagged-unions
+    #
+    # ^-TODO-^: make a wrapper type for this such that alt
+    # backends can be represented easily without a `Union` needed,
+    # AND so that we have better support for wire transport.
+    #
+    # -[ ] maybe `FieldSpec` is a good name since msg-spec
+    #   better applies to a `MsgType[FieldSpec]`?
+    #
+    # -[ ] both as part of the `.open_context()` call AND as part of the
+    #     immediate ack-reponse (see similar below)
+    #     we should do spec matching and fail if anything is awry?
+    #
+    # -[ ] eventually spec should be generated/parsed from the
+    #     type-annots as # desired in GH issue:
+    #     https://github.com/goodboy/tractor/issues/365
+    #
+    # -[ ] semantics of the mismatch case
+    #   - when caller-callee specs we should raise
+    #    a `MsgTypeError` or `MsgSpecError` or similar?
+    #
+    # -[ ] wrapper types for both spec types such that we can easily
+    #     IPC transport them?
+    #     - `TypeSpec: Union[Type]`
+    #      * also a `.__contains__()` for doing `None in
+    #      TypeSpec[None|int]` since rn you need to do it on
+    #      `.__args__` for unions..
+    #     - `MsgSpec: Union[MsgType]
+    #
+    # -[ ] auto-genning this from new (in 3.12) type parameter lists Bo
+    # |_ https://docs.python.org/3/reference/compound_stmts.html#type-params
+    # |_ historical pep 695: https://peps.python.org/pep-0695/
+    # |_ full lang spec: https://typing.readthedocs.io/en/latest/spec/
+    # |_ on annotation scopes:
+    #    https://docs.python.org/3/reference/executionmodel.html#annotation-scopes
+    # |_ 3.13 will have subscriptable funcs Bo
+    #    https://peps.python.org/pep-0718/
+    @property
+    def spec(self) -> Union[Type[Struct]]:
+        # NOTE: defined and applied inside `mk_codec()`
+        return self._dec.type
+
+    # no difference, as compared to a `MsgCodec` which defines the
+    # `MsgType.pld: PayloadT` part of its spec separately
+    pld_spec = spec
+
+    # TODO: would get moved into `FieldSpec.__str__()` right?
+    @property
+    def spec_str(self) -> str:
+        return pformat_msgspec(
+            codec=self,
+            join_char='|',
+        )
+
+    pld_spec_str = spec_str
+
+    def decode(
+        self,
+        raw: Raw|bytes,
+    ) -> Any:
+        return self._dec.decode(raw)
+
+    @property
+    def hook(self) -> Callable|None:
+        return self._dec.dec_hook
+
+
+def mk_dec(
+    spec: Union[Type[Struct]]|Any = Any,
+    dec_hook: Callable|None = None,
+
+) -> MsgDec:
+
+    return MsgDec(
+        _dec=msgpack.Decoder(
+            type=spec,  # like `MsgType[Any]`
+            dec_hook=dec_hook,
+        )
+    )
+
+
+def mk_msgspec_table(
+    dec: msgpack.Decoder,
+    msg: MsgType|None = None,
+
+) -> dict[str, MsgType]|str:
+    '''
+    Fill out a `dict` of `MsgType`s keyed by name
+    for a given input `msgspec.msgpack.Decoder`
+    as defined by its `.type: Union[Type]` setting.
+
+    If `msg` is provided, only deliver a `dict` with a single
+    entry for that type.
+
+    '''
+    msgspec: Union[Type]|Type = dec.type
+
+    if not (msgtypes := getattr(msgspec, '__args__', False)):
+        msgtypes = [msgspec]
+
+    msgt_table: dict[str, MsgType] = {
+        msgt: str(msgt.__name__)
+        for msgt in msgtypes
+    }
+    if msg:
+        msgt: MsgType = type(msg)
+        str_repr: str = msgt_table[msgt]
+        return {msgt: str_repr}
+
+    return msgt_table
+
+
+def pformat_msgspec(
+    codec: MsgCodec|MsgDec,
+    msg: MsgType|None = None,
+    join_char: str = '\n',
+
+) -> str:
+    dec: msgpack.Decoder = getattr(codec, 'dec', codec)
+    return join_char.join(
+        mk_msgspec_table(
+            dec=dec,
+            msg=msg,
+        ).values()
+    )
+
+# TODO: overall IPC msg-spec features (i.e. in this mod)!
+#
+# -[ ] API changes towards being interchange lib agnostic!
+#   -[ ] capnproto has pre-compiled schema for eg..
+#    * https://capnproto.org/language.html
+#    * http://capnproto.github.io/pycapnp/quickstart.html
+#     * https://github.com/capnproto/pycapnp/blob/master/examples/addressbook.capnp
+#
+# -[ ] struct aware messaging coders as per:
+#   -[x] https://github.com/goodboy/tractor/issues/36
+#   -[ ] https://github.com/goodboy/tractor/issues/196
+#   -[ ] https://github.com/goodboy/tractor/issues/365
+#
+class MsgCodec(Struct):
+    '''
+    A IPC msg interchange format lib's encoder + decoder pair.
+
+    Pretty much nothing more then delegation to underlying
+    `msgspec.<interchange-protocol>.Encoder/Decoder`s for now.
+
+    '''
+    _enc: msgpack.Encoder
+    _dec: msgpack.Decoder
+    _pld_spec: Type[Struct]|Raw|Any
+
+    def __repr__(self) -> str:
+        speclines: str = textwrap.indent(
+            pformat_msgspec(codec=self),
+            prefix=' '*3,
+        )
+        body: str = textwrap.indent(
+            f'|_lib = {self.lib.__name__!r}\n'
+            f'|_enc_hook: {self.enc.enc_hook}\n'
+            f'|_dec_hook: {self.dec.dec_hook}\n'
+            f'|_pld_spec: {self.pld_spec_str}\n'
+            # f'|\n'
+            f'|__msg_spec__:\n'
+            f'{speclines}\n',
+            prefix=' '*2,
+        )
+        return (
+            f'<{type(self).__name__}(\n'
+            f'{body}'
+            ')>'
+        )
+
+    @property
+    def pld_spec(self) -> Type[Struct]|Raw|Any:
+        return self._pld_spec
+
+    @property
+    def pld_spec_str(self) -> str:
+
+        # TODO: could also use match: instead?
+        spec: Union[Type]|Type = self.pld_spec
+
+        # `typing.Union` case
+        if getattr(spec, '__args__', False):
+            return str(spec)
+
+        # just a single type
+        else:
+            return spec.__name__
+
+    # struct type unions
+    # https://jcristharif.com/msgspec/structs.html#tagged-unions
+    @property
+    def msg_spec(self) -> Union[Type[Struct]]:
+        # NOTE: defined and applied inside `mk_codec()`
+        return self._dec.type
+
+    # TODO: some way to make `pretty_struct.Struct` use this
+    # wrapped field over the `.msg_spec` one?
+    @property
+    def msg_spec_str(self) -> str:
+        return pformat_msgspec(self.msg_spec)
+
+    lib: ModuleType = msgspec
+
+    # TODO: use `functools.cached_property` for these ?
+    # https://docs.python.org/3/library/functools.html#functools.cached_property
+    @property
+    def enc(self) -> msgpack.Encoder:
+        return self._enc
+
+    # TODO: reusing encode buffer for perf?
+    # https://jcristharif.com/msgspec/perf-tips.html#reusing-an-output-buffer
+    _buf: bytearray = bytearray()
+
+    def encode(
+        self,
+        py_obj: Any,
+
+        use_buf: bool = False,
+        # ^-XXX-^ uhh why am i getting this?
+        # |_BufferError: Existing exports of data: object cannot be re-sized
+
+    ) -> bytes:
+        '''
+        Encode input python objects to `msgpack` bytes for
+        transfer on a tranport protocol connection.
+
+        When `use_buf == True` use the output buffer optimization:
+        https://jcristharif.com/msgspec/perf-tips.html#reusing-an-output-buffer
+
+        '''
+        if use_buf:
+            self._enc.encode_into(py_obj, self._buf)
+            return self._buf
+        else:
+            return self._enc.encode(py_obj)
+
+    @property
+    def dec(self) -> msgpack.Decoder:
+        return self._dec
+
+    def decode(
+        self,
+        msg: bytes,
+    ) -> Any:
+        '''
+        Decode received `msgpack` bytes into a local python object
+        with special `msgspec.Struct` (or other type) handling
+        determined by the 
+
+        '''
+        # https://jcristharif.com/msgspec/usage.html#typed-decoding
+        return self._dec.decode(msg)
+
+
+# [x] TODO: a sub-decoder system as well? => No!
+#
+# -[x] do we still want to try and support the sub-decoder with
+# `.Raw` technique in the case that the `Generic` approach gives
+# future grief?
+# => NO, since we went with the `PldRx` approach instead B)
+#
+# IF however you want to see the code that was staged for this
+# from wayyy back, see the pure removal commit.
+
+
+def mk_codec(
+    # struct type unions set for `Decoder`
+    # https://jcristharif.com/msgspec/structs.html#tagged-unions
+    ipc_pld_spec: Union[Type[Struct]]|Any = Any,
+
+    # TODO: offering a per-msg(-field) type-spec such that
+    # the fields can be dynamically NOT decoded and left as `Raw`
+    # values which are later loaded by a sub-decoder specified
+    # by `tag_field: str` value key?
+    # payload_msg_specs: dict[
+    #     str,  # tag_field value as sub-decoder key
+    #     Union[Type[Struct]]  # `MsgType.pld` type spec
+    # ]|None = None,
+
+    libname: str = 'msgspec',
+
+    # proxy as `Struct(**kwargs)` for ad-hoc type extensions
+    # https://jcristharif.com/msgspec/extending.html#mapping-to-from-native-types
+    # ------ - ------
+    dec_hook: Callable|None = None,
+    enc_hook: Callable|None = None,
+    # ------ - ------
+    #
+    # Encoder:
+    # write_buffer_size=write_buffer_size,
+    #
+    # Decoder:
+    # ext_hook: ext_hook_sig
+
+) -> MsgCodec:
+    '''
+    Convenience factory for creating codecs eventually meant
+    to be interchange lib agnostic (i.e. once we support more then just
+    `msgspec` ;).
+
+    '''
+    # (manually) generate a msg-payload-spec for all relevant
+    # god-boxing-msg subtypes, parameterizing the `PayloadMsg.pld: PayloadT`
+    # for the decoder such that all sub-type msgs in our SCIPP
+    # will automatically decode to a type-"limited" payload (`Struct`)
+    # object (set).
+    (
+        ipc_msg_spec,
+        msg_types,
+    ) = mk_msg_spec(
+        payload_type_union=ipc_pld_spec,
+    )
+    assert len(ipc_msg_spec.__args__) == len(msg_types)
+    assert ipc_msg_spec
+
+    # TODO: use this shim instead?
+    # bc.. unification, err somethin?
+    # dec: MsgDec = mk_dec(
+    #     spec=ipc_msg_spec,
+    #     dec_hook=dec_hook,
+    # )
+
+    dec = msgpack.Decoder(
+        type=ipc_msg_spec,
+        dec_hook=dec_hook,
+    )
+    enc = msgpack.Encoder(
+       enc_hook=enc_hook,
+    )
+
+    codec = MsgCodec(
+        _enc=enc,
+        _dec=dec,
+        _pld_spec=ipc_pld_spec,
+    )
+
+    # sanity on expected backend support
+    assert codec.lib.__name__ == libname
+
+    return codec
+
+
+# instance of the default `msgspec.msgpack` codec settings, i.e.
+# no custom structs, hooks or other special types.
+_def_msgspec_codec: MsgCodec = mk_codec(ipc_pld_spec=Any)
+
+# The built-in IPC `Msg` spec.
+# Our composing "shuttle" protocol which allows `tractor`-app code
+# to use any `msgspec` supported type as the `PayloadMsg.pld` payload,
+# https://jcristharif.com/msgspec/supported-types.html
+#
+_def_tractor_codec: MsgCodec = mk_codec(
+    # TODO: use this for debug mode locking prot?
+    # ipc_pld_spec=Any,
+    ipc_pld_spec=Raw,
+)
+# TODO: IDEALLY provides for per-`trio.Task` specificity of the
+# IPC msging codec used by the transport layer when doing
+# `Channel.send()/.recv()` of wire data.
+
+# ContextVar-TODO: DIDN'T WORK, kept resetting in every new task to default!?
+# _ctxvar_MsgCodec: ContextVar[MsgCodec] = ContextVar(
+
+# TreeVar-TODO: DIDN'T WORK, kept resetting in every new embedded nursery
+# even though it's supposed to inherit from a parent context ???
+#
+# _ctxvar_MsgCodec: TreeVar[MsgCodec] = TreeVar(
+#
+# ^-NOTE-^: for this to work see the mods by @mikenerone from `trio` gitter:
+#
+# 22:02:54 <mikenerone> even for regular contextvars, all you have to do is:
+#    `task: Task = trio.lowlevel.current_task()`
+#    `task.parent_nursery.parent_task.context.run(my_ctx_var.set, new_value)`
+#
+# From a comment in his prop code he couldn't share outright:
+# 1. For every TreeVar set in the current task (which covers what
+#    we need from SynchronizerFacade), walk up the tree until the
+#    root or finding one where the TreeVar is already set, setting
+#    it in all of the contexts along the way.
+# 2. For each of those, we also forcibly set the values that are
+#    pending for child nurseries that have not yet accessed the
+#    TreeVar.
+# 3. We similarly set the pending values for the child nurseries
+#    of the *current* task.
+#
+_ctxvar_MsgCodec: ContextVar[MsgCodec] = ContextVar(
+    'msgspec_codec',
+    default=_def_tractor_codec,
+)
+
+
+@cm
+def apply_codec(
+    codec: MsgCodec,
+
+    ctx: Context|None = None,
+
+) -> MsgCodec:
+    '''
+    Dynamically apply a `MsgCodec` to the current task's runtime
+    context such that all (of a certain class of payload
+    containing i.e. `MsgType.pld: PayloadT`) IPC msgs are
+    processed with it for that task.
+
+    Uses a `contextvars.ContextVar` to ensure the scope of any
+    codec setting matches the current `Context` or
+    `._rpc.process_messages()` feeder task's prior setting without
+    mutating any surrounding scope.
+
+    When a `ctx` is supplied, only mod its `Context.pld_codec`.
+
+    matches the `@cm` block and DOES NOT change to the original
+    (default) value in new tasks (as it does for `ContextVar`).
+
+    '''
+    __tracebackhide__: bool = True
+
+    if ctx is not None:
+        var: ContextVar = ctx._var_pld_codec
+    else:
+        # use IPC channel-connection "global" codec
+        var: ContextVar = _ctxvar_MsgCodec
+
+    orig: MsgCodec = var.get()
+
+    assert orig is not codec
+    if codec.pld_spec is None:
+        breakpoint()
+
+    log.info(
+        'Applying new msg-spec codec\n\n'
+        f'{codec}\n'
+    )
+    token: Token = var.set(codec)
+
+    # ?TODO? for TreeVar approach which copies from the
+    # cancel-scope of the prior value, NOT the prior task
+    # See the docs:
+    # - https://tricycle.readthedocs.io/en/latest/reference.html#tree-variables
+    # - https://github.com/oremanj/tricycle/blob/master/tricycle/_tests/test_tree_var.py
+    #   ^- see docs for @cm `.being()` API
+    # with _ctxvar_MsgCodec.being(codec):
+    #     new = _ctxvar_MsgCodec.get()
+    #     assert new is codec
+    #     yield codec
+
+    try:
+        yield var.get()
+    finally:
+        var.reset(token)
+        log.info(
+            'Reverted to last msg-spec codec\n\n'
+            f'{orig}\n'
+        )
+        assert var.get() is orig
+
+
+def current_codec() -> MsgCodec:
+    '''
+    Return the current `trio.Task.context`'s value
+    for `msgspec_codec` used by `Channel.send/.recv()`
+    for wire serialization.
+
+    '''
+    return _ctxvar_MsgCodec.get()
+
+
+@cm
+def limit_msg_spec(
+    payload_spec: Union[Type[Struct]],
+
+    # TODO: don't need this approach right?
+    # -> related to the `MsgCodec._payload_decs` stuff above..
+    # tagged_structs: list[Struct]|None = None,
+
+    **codec_kwargs,
+
+) -> MsgCodec:
+    '''
+    Apply a `MsgCodec` that will natively decode the SC-msg set's
+    `PayloadMsg.pld: Union[Type[Struct]]` payload fields using
+    tagged-unions of `msgspec.Struct`s from the `payload_types`
+    for all IPC contexts in use by the current `trio.Task`.
+
+    '''
+    __tracebackhide__: bool = True
+    curr_codec: MsgCodec = current_codec()
+    msgspec_codec: MsgCodec = mk_codec(
+        ipc_pld_spec=payload_spec,
+        **codec_kwargs,
+    )
+    with apply_codec(msgspec_codec) as applied_codec:
+        assert applied_codec is msgspec_codec
+        yield msgspec_codec
+
+    assert curr_codec is current_codec()
+
+
+# XXX: msgspec won't allow this with non-struct custom types
+# like `NamespacePath`!@!
+# @cm
+# def extend_msg_spec(
+#     payload_spec: Union[Type[Struct]],
+
+# ) -> MsgCodec:
+#     '''
+#     Extend the current `MsgCodec.pld_spec` (type set) by extending
+#     the payload spec to **include** the types specified by
+#     `payload_spec`.
+
+#     '''
+#     codec: MsgCodec = current_codec()
+#     pld_spec: Union[Type] = codec.pld_spec
+#     extended_spec: Union[Type] = pld_spec|payload_spec
+
+#     with limit_msg_spec(payload_types=extended_spec) as ext_codec:
+#         # import pdbp; pdbp.set_trace()
+#         assert ext_codec.pld_spec == extended_spec
+#         yield ext_codec
+
+
+# TODO: make something similar to this inside `._codec` such that
+# user can just pass a type table of some sort?
+# -[ ] we would need to decode all msgs to `pretty_struct.Struct`
+#     and then call `.to_dict()` on them?
+# -[x] we're going to need to re-impl all the stuff changed in the
+#    runtime port such that it can handle dicts or `Msg`s?
+#
+# def mk_dict_msg_codec_hooks() -> tuple[Callable, Callable]:
+#     '''
+#     Deliver a `enc_hook()`/`dec_hook()` pair which does
+#     manual convertion from our above native `Msg` set
+#     to `dict` equivalent (wire msgs) in order to keep legacy compat
+#     with the original runtime implementation.
+#
+#     Note: this is is/was primarly used while moving the core
+#     runtime over to using native `Msg`-struct types wherein we
+#     start with the send side emitting without loading
+#     a typed-decoder and then later flipping the switch over to
+#     load to the native struct types once all runtime usage has
+#     been adjusted appropriately.
+#
+#     '''
+#     return (
+#         # enc_to_dict,
+#         dec_from_dict,
+#     )

tractor/msg/_ops.py

@@ -0,0 +1,842 @@
+# 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/>.
+
+'''
+Near-application abstractions for `MsgType.pld: PayloadT|Raw`
+delivery, filtering and type checking as well as generic
+operational helpers for processing transaction flows.
+
+'''
+from __future__ import annotations
+from contextlib import (
+    asynccontextmanager as acm,
+    contextmanager as cm,
+)
+from typing import (
+    Any,
+    Callable,
+    Type,
+    TYPE_CHECKING,
+    Union,
+)
+# ------ - ------
+from msgspec import (
+    msgpack,
+    Raw,
+    Struct,
+    ValidationError,
+)
+import trio
+# ------ - ------
+from tractor.log import get_logger
+from tractor._exceptions import (
+    MessagingError,
+    InternalError,
+    _raise_from_unexpected_msg,
+    MsgTypeError,
+    _mk_recv_mte,
+    pack_error,
+)
+from tractor._state import current_ipc_ctx
+from ._codec import (
+    mk_dec,
+    MsgDec,
+    MsgCodec,
+    current_codec,
+)
+from .types import (
+    CancelAck,
+    Error,
+    MsgType,
+    PayloadT,
+    Return,
+    Started,
+    Stop,
+    Yield,
+    pretty_struct,
+)
+
+
+if TYPE_CHECKING:
+    from tractor._context import Context
+    from tractor._streaming import MsgStream
+
+
+log = get_logger(__name__)
+
+
+_def_any_pldec: MsgDec[Any] = mk_dec()
+
+
+class PldRx(Struct):
+    '''
+    A "msg payload receiver".
+
+    The pairing of a "feeder" `trio.abc.ReceiveChannel` and an
+    interchange-specific (eg. msgpack) payload field decoder. The
+    validation/type-filtering rules are runtime mutable and allow
+    type constraining the set of `MsgType.pld: Raw|PayloadT`
+    values at runtime, per IPC task-context.
+
+    This abstraction, being just below "user application code",
+    allows for the equivalent of our `MsgCodec` (used for
+    typer-filtering IPC dialog protocol msgs against a msg-spec)
+    but with granular control around payload delivery (i.e. the
+    data-values user code actually sees and uses (the blobs that
+    are "shuttled" by the wrapping dialog prot) such that invalid
+    `.pld: Raw` can be decoded and handled by IPC-primitive user
+    code (i.e. that operates on `Context` and `Msgstream` APIs)
+    without knowledge of the lower level `Channel`/`MsgTransport`
+    primitives nor the `MsgCodec` in use. Further, lazily decoding
+    payload blobs allows for topical (and maybe intentionally
+    "partial") encryption of msg field subsets.
+
+    '''
+    # TODO: better to bind it here?
+    # _rx_mc: trio.MemoryReceiveChannel
+    _pld_dec: MsgDec
+    _ctx: Context|None = None
+    _ipc: Context|MsgStream|None = None
+
+    @property
+    def pld_dec(self) -> MsgDec:
+        return self._pld_dec
+
+    # TODO: a better name?
+    # -[ ] when would this be used as it avoids needingn to pass the
+    #   ipc prim to every method
+    @cm
+    def wraps_ipc(
+        self,
+        ipc_prim: Context|MsgStream,
+
+    ) -> PldRx:
+        '''
+        Apply this payload receiver to an IPC primitive type, one
+        of `Context` or `MsgStream`.
+
+        '''
+        self._ipc = ipc_prim
+        try:
+            yield self
+        finally:
+            self._ipc = None
+
+    @cm
+    def limit_plds(
+        self,
+        spec: Union[Type[Struct]],
+        **dec_kwargs,
+
+    ) -> MsgDec:
+        '''
+        Type-limit the loadable msg payloads via an applied
+        `MsgDec` given an input spec, revert to prior decoder on
+        exit.
+
+        '''
+        orig_dec: MsgDec = self._pld_dec
+        limit_dec: MsgDec = mk_dec(
+            spec=spec,
+            **dec_kwargs,
+        )
+        try:
+            self._pld_dec = limit_dec
+            yield limit_dec
+        finally:
+            self._pld_dec = orig_dec
+
+    @property
+    def dec(self) -> msgpack.Decoder:
+        return self._pld_dec.dec
+
+    def recv_pld_nowait(
+        self,
+        # TODO: make this `MsgStream` compat as well, see above^
+        # ipc_prim: Context|MsgStream,
+        ipc: Context|MsgStream,
+
+        ipc_msg: MsgType|None = None,
+        expect_msg: Type[MsgType]|None = None,
+        hide_tb: bool = False,
+        **dec_pld_kwargs,
+
+    ) -> Any|Raw:
+        __tracebackhide__: bool = hide_tb
+
+        msg: MsgType = (
+            ipc_msg
+            or
+
+            # sync-rx msg from underlying IPC feeder (mem-)chan
+            ipc._rx_chan.receive_nowait()
+        )
+        return self.decode_pld(
+            msg,
+            ipc=ipc,
+            expect_msg=expect_msg,
+            hide_tb=hide_tb,
+            **dec_pld_kwargs,
+        )
+
+    async def recv_pld(
+        self,
+        ipc: Context|MsgStream,
+        ipc_msg: MsgType|None = None,
+        expect_msg: Type[MsgType]|None = None,
+        hide_tb: bool = True,
+
+        **dec_pld_kwargs,
+
+    ) -> Any|Raw:
+        '''
+        Receive a `MsgType`, then decode and return its `.pld` field.
+
+        '''
+        __tracebackhide__: bool = hide_tb
+        msg: MsgType = (
+            ipc_msg
+            or
+            # async-rx msg from underlying IPC feeder (mem-)chan
+            await ipc._rx_chan.receive()
+        )
+        return self.decode_pld(
+            msg=msg,
+            ipc=ipc,
+            expect_msg=expect_msg,
+            **dec_pld_kwargs,
+        )
+
+    def decode_pld(
+        self,
+        msg: MsgType,
+        ipc: Context|MsgStream,
+        expect_msg: Type[MsgType]|None,
+
+        raise_error: bool = True,
+        hide_tb: bool = True,
+
+        # XXX for special (default?) case of send side call with
+        # `Context.started(validate_pld_spec=True)`
+        is_started_send_side: bool = False,
+
+    ) -> PayloadT|Raw:
+        '''
+        Decode a msg's payload field: `MsgType.pld: PayloadT|Raw` and
+        return the value or raise an appropriate error.
+
+        '''
+        __tracebackhide__: bool = hide_tb
+        src_err: BaseException|None = None
+        match msg:
+            # payload-data shuttle msg; deliver the `.pld` value
+            # directly to IPC (primitive) client-consumer code.
+            case (
+                Started(pld=pld)  # sync phase
+                |Yield(pld=pld)  # streaming phase
+                |Return(pld=pld)  # termination phase
+            ):
+                try:
+                    pld: PayloadT = self._pld_dec.decode(pld)
+                    log.runtime(
+                        'Decoded msg payload\n\n'
+                        f'{msg}\n'
+                        f'where payload decoded as\n'
+                        f'|_pld={pld!r}\n'
+                    )
+                    return pld
+
+                # XXX pld-value type failure
+                except ValidationError as valerr:
+                    # pack mgterr into error-msg for
+                    # reraise below; ensure remote-actor-err
+                    # info is displayed nicely?
+                    mte: MsgTypeError = _mk_recv_mte(
+                        msg=msg,
+                        codec=self.pld_dec,
+                        src_validation_error=valerr,
+                        is_invalid_payload=True,
+                        expected_msg=expect_msg,
+                    )
+                    # NOTE: just raise the MTE inline instead of all
+                    # the pack-unpack-repack non-sense when this is
+                    # a "send side" validation error.
+                    if is_started_send_side:
+                        raise mte
+
+                    # NOTE: the `.message` is automatically
+                    # transferred into the message as long as we
+                    # define it as a `Error.message` field.
+                    err_msg: Error = pack_error(
+                        exc=mte,
+                        cid=msg.cid,
+                        src_uid=(
+                            ipc.chan.uid
+                            if not is_started_send_side
+                            else ipc._actor.uid
+                        ),
+                    )
+                    mte._ipc_msg = err_msg
+
+                    # XXX override the `msg` passed to
+                    # `_raise_from_unexpected_msg()` (below) so so
+                    # that we're effectively able to use that same
+                    # func to unpack and raise an "emulated remote
+                    # `Error`" of this local MTE.
+                    msg = err_msg
+                    # XXX NOTE: so when the `_raise_from_unexpected_msg()`
+                    # raises the boxed `err_msg` from above it raises
+                    # it from the above caught interchange-lib
+                    # validation error.
+                    src_err = valerr
+
+            # a runtime-internal RPC endpoint response.
+            # always passthrough since (internal) runtime
+            # responses are generally never exposed to consumer
+            # code.
+            case CancelAck(
+                pld=bool(cancelled)
+            ):
+                return cancelled
+
+            case Error():
+                src_err = MessagingError(
+                    'IPC ctx dialog terminated without `Return`-ing a result\n'
+                    f'Instead it raised {msg.boxed_type_str!r}!'
+                )
+                # XXX NOTE XXX another super subtle runtime-y thing..
+                #
+                # - when user code (transitively) calls into this
+                #   func (usually via a `Context/MsgStream` API) we
+                #   generally want errors to propagate immediately
+                #   and directly so that the user can define how it
+                #   wants to handle them.
+                #
+                #  HOWEVER,
+                #
+                # - for certain runtime calling cases, we don't want to
+                #   directly raise since the calling code might have
+                #   special logic around whether to raise the error
+                #   or supress it silently (eg. a `ContextCancelled`
+                #   received from the far end which was requested by
+                #   this side, aka a self-cancel).
+                #
+                # SO, we offer a flag to control this.
+                if not raise_error:
+                    return src_err
+
+            case Stop(cid=cid):
+                ctx: Context = getattr(ipc, 'ctx', ipc)
+                message: str = (
+                    f'{ctx.side!r}-side of ctx received stream-`Stop` from '
+                    f'{ctx.peer_side!r} peer ?\n'
+                    f'|_cid: {cid}\n\n'
+
+                    f'{pretty_struct.pformat(msg)}\n'
+                )
+                if ctx._stream is None:
+                    explain: str = (
+                        f'BUT, no `MsgStream` (was) open(ed) on this '
+                        f'{ctx.side!r}-side of the IPC ctx?\n'
+                        f'Maybe check your code for streaming phase race conditions?\n'
+                    )
+                    log.warning(
+                        message
+                        +
+                        explain
+                    )
+                    # let caller decide what to do when only one
+                    # side opened a stream, don't raise.
+                    return msg
+
+                else:
+                    explain: str = (
+                        'Received a `Stop` when it should NEVER be possible!?!?\n'
+                    )
+                    # TODO: this is constructed inside
+                    # `_raise_from_unexpected_msg()` but maybe we
+                    # should pass it in?
+                    # src_err = trio.EndOfChannel(explain)
+                    src_err = None
+
+            case _:
+                src_err = InternalError(
+                    'Invalid IPC msg ??\n\n'
+                    f'{msg}\n'
+                )
+
+        # TODO: maybe use the new `.add_note()` from 3.11?
+        # |_https://docs.python.org/3.11/library/exceptions.html#BaseException.add_note
+        #
+        # fallthrough and raise from `src_err`
+        try:
+            _raise_from_unexpected_msg(
+                ctx=getattr(ipc, 'ctx', ipc),
+                msg=msg,
+                src_err=src_err,
+                log=log,
+                expect_msg=expect_msg,
+                hide_tb=hide_tb,
+            )
+        except UnboundLocalError:
+            # XXX if there's an internal lookup error in the above
+            # code (prolly on `src_err`) we want to show this frame
+            # in the tb!
+            __tracebackhide__: bool = False
+            raise
+
+    dec_msg = decode_pld
+
+    async def recv_msg_w_pld(
+        self,
+        ipc: Context|MsgStream,
+        expect_msg: MsgType,
+
+        # NOTE: generally speaking only for handling `Stop`-msgs that
+        # arrive during a call to `drain_to_final_msg()` above!
+        passthrough_non_pld_msgs: bool = True,
+        hide_tb: bool = True,
+        **kwargs,
+
+    ) -> tuple[MsgType, PayloadT]:
+        '''
+        Retrieve the next avail IPC msg, decode it's payload, and return
+        the pair of refs.
+
+        '''
+        __tracebackhide__: bool = hide_tb
+        msg: MsgType = await ipc._rx_chan.receive()
+
+        if passthrough_non_pld_msgs:
+            match msg:
+                case Stop():
+                    return msg, None
+
+        # TODO: is there some way we can inject the decoded
+        # payload into an existing output buffer for the original
+        # msg instance?
+        pld: PayloadT = self.decode_pld(
+            msg,
+            ipc=ipc,
+            expect_msg=expect_msg,
+            hide_tb=hide_tb,
+            **kwargs,
+        )
+        return msg, pld
+
+
+@cm
+def limit_plds(
+    spec: Union[Type[Struct]],
+    **dec_kwargs,
+
+) -> MsgDec:
+    '''
+    Apply a `MsgCodec` that will natively decode the SC-msg set's
+    `PayloadMsg.pld: Union[Type[Struct]]` payload fields using
+    tagged-unions of `msgspec.Struct`s from the `payload_types`
+    for all IPC contexts in use by the current `trio.Task`.
+
+    '''
+    __tracebackhide__: bool = True
+    try:
+        curr_ctx: Context = current_ipc_ctx()
+        rx: PldRx = curr_ctx._pld_rx
+        orig_pldec: MsgDec = rx.pld_dec
+
+        with rx.limit_plds(
+            spec=spec,
+            **dec_kwargs,
+        ) as pldec:
+            log.runtime(
+                'Applying payload-decoder\n\n'
+                f'{pldec}\n'
+            )
+            yield pldec
+    finally:
+        log.runtime(
+            'Reverted to previous payload-decoder\n\n'
+            f'{orig_pldec}\n'
+        )
+        # sanity on orig settings
+        assert rx.pld_dec is orig_pldec
+
+
+@acm
+async def maybe_limit_plds(
+    ctx: Context,
+    spec: Union[Type[Struct]]|None = None,
+    dec_hook: Callable|None = None,
+    **kwargs,
+
+) -> MsgDec|None:
+    '''
+    Async compat maybe-payload type limiter.
+
+    Mostly for use inside other internal `@acm`s such that a separate
+    indent block isn't needed when an async one is already being
+    used.
+
+    '''
+    if (
+        spec is None
+        and
+        dec_hook is None
+    ):
+        yield None
+        return
+
+    # sanity check on IPC scoping
+    curr_ctx: Context = current_ipc_ctx()
+    assert ctx is curr_ctx
+
+    with ctx._pld_rx.limit_plds(
+        spec=spec,
+        dec_hook=dec_hook,
+        **kwargs,
+    ) as msgdec:
+        yield msgdec
+
+    # when the applied spec is unwound/removed, the same IPC-ctx
+    # should still be in scope.
+    curr_ctx: Context = current_ipc_ctx()
+    assert ctx is curr_ctx
+
+
+async def drain_to_final_msg(
+    ctx: Context,
+
+    hide_tb: bool = True,
+    msg_limit: int = 6,
+
+) -> tuple[
+    Return|None,
+    list[MsgType]
+]:
+    '''
+    Drain IPC msgs delivered to the underlying IPC context's
+    rx-mem-chan (i.e. from `Context._rx_chan`) in search for a final
+    `Return` or `Error` msg.
+
+    Deliver the `Return` + preceding drained msgs (`list[MsgType]`)
+    as a pair unless an `Error` is found, in which unpack and raise
+    it.
+
+    The motivation here is to always capture any remote error relayed
+    by the remote peer task during a ctxc condition.
+
+    For eg. a ctxc-request may be sent to the peer as part of the
+    local task's (request for) cancellation but then that same task
+    **also errors** before executing the teardown in the
+    `Portal.open_context().__aexit__()` block. In such error-on-exit
+    cases we want to always capture and raise any delivered remote
+    error (like an expected ctxc-ACK) as part of the final
+    `ctx.wait_for_result()` teardown sequence such that the
+    `Context.outcome` related state always reflect what transpired
+    even after ctx closure and the `.open_context()` block exit.
+
+    '''
+    __tracebackhide__: bool = hide_tb
+    raise_overrun: bool = not ctx._allow_overruns
+
+    # wait for a final context result by collecting (but
+    # basically ignoring) any bi-dir-stream msgs still in transit
+    # from the far end.
+    pre_result_drained: list[MsgType] = []
+    result_msg: Return|Error|None = None
+    while not (
+        ctx.maybe_error
+        and not ctx._final_result_is_set()
+    ):
+        try:
+            # receive all msgs, scanning for either a final result
+            # or error; the underlying call should never raise any
+            # remote error directly!
+            msg, pld = await ctx._pld_rx.recv_msg_w_pld(
+                ipc=ctx,
+                expect_msg=Return,
+                raise_error=False,
+                hide_tb=hide_tb,
+            )
+            # ^-TODO-^ some bad ideas?
+            # -[ ] wrap final outcome .receive() in a scope so
+            #     it can be cancelled out of band if needed?
+            # |_with trio.CancelScope() as res_cs:
+            #       ctx._res_scope = res_cs
+            #       msg: dict = await ctx._rx_chan.receive()
+            #   if res_cs.cancelled_caught:
+            #
+            # -[ ] make sure pause points work here for REPLing
+            #   the runtime itself; i.e. ensure there's no hangs!
+            # |_from tractor.devx._debug import pause
+            #   await pause()
+
+        # NOTE: we get here if the far end was
+        # `ContextCancelled` in 2 cases:
+        # 1. we requested the cancellation and thus
+        #    SHOULD NOT raise that far end error,
+        # 2. WE DID NOT REQUEST that cancel and thus
+        #    SHOULD RAISE HERE!
+        except trio.Cancelled as _taskc:
+            taskc: trio.Cancelled = _taskc
+
+            # report when the cancellation wasn't (ostensibly) due to
+            # RPC operation, some surrounding parent cancel-scope.
+            if not ctx._scope.cancel_called:
+                task: trio.lowlevel.Task = trio.lowlevel.current_task()
+                rent_n: trio.Nursery = task.parent_nursery
+                if (
+                    (local_cs := rent_n.cancel_scope).cancel_called
+                ):
+                    log.cancel(
+                        'RPC-ctx cancelled by local-parent scope during drain!\n\n'
+                        f'c}}>\n'
+                        f' |_{rent_n}\n'
+                        f'   |_.cancel_scope = {local_cs}\n'
+                        f'   |_>c}}\n'
+                        f'      |_{ctx.pformat(indent=" "*9)}'
+                        # ^TODO, some (other) simpler repr here?
+                    )
+                    __tracebackhide__: bool = False
+
+            # CASE 2: mask the local cancelled-error(s)
+            # only when we are sure the remote error is
+            # the source cause of this local task's
+            # cancellation.
+            ctx.maybe_raise(
+                hide_tb=hide_tb,
+                from_src_exc=taskc,
+                # ?TODO? when *should* we use this?
+            )
+
+            # CASE 1: we DID request the cancel we simply
+            # continue to bubble up as normal.
+            raise taskc
+
+        match msg:
+
+            # final result arrived!
+            case Return():
+                log.runtime(
+                    'Context delivered final draining msg:\n'
+                    f'{pretty_struct.pformat(msg)}'
+                )
+                ctx._result: Any = pld
+                result_msg = msg
+                break
+
+            # far end task is still streaming to us so discard
+            # and report depending on local ctx state.
+            case Yield():
+                pre_result_drained.append(msg)
+                if (
+                    (ctx._stream.closed
+                     and (reason := 'stream was already closed')
+                    )
+                    or (ctx.cancel_acked
+                        and (reason := 'ctx cancelled other side')
+                    )
+                    or (ctx._cancel_called
+                        and (reason := 'ctx called `.cancel()`')
+                    )
+                    or (len(pre_result_drained) > msg_limit
+                        and (reason := f'"yield" limit={msg_limit}')
+                    )
+                ):
+                    log.cancel(
+                        'Cancelling `MsgStream` drain since '
+                        f'{reason}\n\n'
+                        f'<= {ctx.chan.uid}\n'
+                        f'  |_{ctx._nsf}()\n\n'
+                        f'=> {ctx._task}\n'
+                        f'  |_{ctx._stream}\n\n'
+
+                        f'{pretty_struct.pformat(msg)}\n'
+                    )
+                    break
+
+                # drain up to the `msg_limit` hoping to get
+                # a final result or error/ctxc.
+                else:
+                    log.warning(
+                        'Ignoring "yield" msg during `ctx.result()` drain..\n'
+                        f'<= {ctx.chan.uid}\n'
+                        f'  |_{ctx._nsf}()\n\n'
+                        f'=> {ctx._task}\n'
+                        f'  |_{ctx._stream}\n\n'
+
+                        f'{pretty_struct.pformat(msg)}\n'
+                    )
+                    continue
+
+            # stream terminated, but no result yet..
+            #
+            # TODO: work out edge cases here where
+            # a stream is open but the task also calls
+            # this?
+            # -[ ] should be a runtime error if a stream is open right?
+            # Stop()
+            case Stop():
+                pre_result_drained.append(msg)
+                log.runtime(  # normal/expected shutdown transaction
+                    'Remote stream terminated due to "stop" msg:\n\n'
+                    f'{pretty_struct.pformat(msg)}\n'
+                )
+                continue
+
+            # remote error msg, likely already handled inside
+            # `Context._deliver_msg()`
+            case Error():
+                # TODO: can we replace this with `ctx.maybe_raise()`?
+                # -[ ]  would this be handier for this case maybe?
+                # |_async with maybe_raise_on_exit() as raises:
+                #       if raises:
+                #           log.error('some msg about raising..')
+                #
+                re: Exception|None = ctx._remote_error
+                if re:
+                    assert msg is ctx._cancel_msg
+                    # NOTE: this solved a super duper edge case XD
+                    # this was THE super duper edge case of:
+                    # - local task opens a remote task,
+                    # - requests remote cancellation of far end
+                    #   ctx/tasks,
+                    # - needs to wait for the cancel ack msg
+                    #   (ctxc) or some result in the race case
+                    #   where the other side's task returns
+                    #   before the cancel request msg is ever
+                    #   rxed and processed,
+                    # - here this surrounding drain loop (which
+                    #   iterates all ipc msgs until the ack or
+                    #   an early result arrives) was NOT exiting
+                    #   since we are the edge case: local task
+                    #   does not re-raise any ctxc it receives
+                    #   IFF **it** was the cancellation
+                    #   requester..
+                    #
+                    # XXX will raise if necessary but ow break
+                    # from loop presuming any supressed error
+                    # (ctxc) should terminate the context!
+                    ctx._maybe_raise_remote_err(
+                        re,
+                        # NOTE: obvi we don't care if we
+                        # overran the far end if we're already
+                        # waiting on a final result (msg).
+                        # raise_overrun_from_self=False,
+                        raise_overrun_from_self=raise_overrun,
+                    )
+                    result_msg = msg
+                    break  # OOOOOF, yeah obvi we need this..
+
+                else:
+                    # bubble the original src key error
+                    raise
+
+            # XXX should pretty much never get here unless someone
+            # overrides the default `MsgType` spec.
+            case _:
+                pre_result_drained.append(msg)
+                # It's definitely an internal error if any other
+                # msg type without a`'cid'` field arrives here!
+                report: str = (
+                    f'Invalid or unknown msg type {type(msg)!r}!?\n'
+                )
+                if not msg.cid:
+                    report += (
+                        '\nWhich also has no `.cid` field?\n'
+                    )
+
+                raise MessagingError(
+                    report
+                    +
+                    f'\n{msg}\n'
+                )
+
+    else:
+        log.cancel(
+            'Skipping `MsgStream` drain since final outcome is set\n\n'
+            f'{ctx.outcome}\n'
+        )
+
+    return (
+        result_msg,
+        pre_result_drained,
+    )
+
+
+def validate_payload_msg(
+    pld_msg: Started|Yield|Return,
+    pld_value: PayloadT,
+    ipc: Context|MsgStream,
+
+    raise_mte: bool = True,
+    strict_pld_parity: bool = False,
+    hide_tb: bool = True,
+
+) -> MsgTypeError|None:
+    '''
+    Validate a `PayloadMsg.pld` value with the current
+    IPC ctx's `PldRx` and raise an appropriate `MsgTypeError`
+    on failure.
+
+    '''
+    __tracebackhide__: bool = hide_tb
+    codec: MsgCodec = current_codec()
+    msg_bytes: bytes = codec.encode(pld_msg)
+    try:
+        roundtripped: Started = codec.decode(msg_bytes)
+        ctx: Context = getattr(ipc, 'ctx', ipc)
+        pld: PayloadT = ctx.pld_rx.decode_pld(
+            msg=roundtripped,
+            ipc=ipc,
+            expect_msg=Started,
+            hide_tb=hide_tb,
+            is_started_send_side=True,
+        )
+        if (
+            strict_pld_parity
+            and
+            pld != pld_value
+        ):
+            # TODO: make that one a mod func too..
+            diff = pretty_struct.Struct.__sub__(
+                roundtripped,
+                pld_msg,
+            )
+            complaint: str = (
+                'Started value does not match after roundtrip?\n\n'
+                f'{diff}'
+            )
+            raise ValidationError(complaint)
+
+    # raise any msg type error NO MATTER WHAT!
+    except ValidationError as verr:
+        try:
+            mte: MsgTypeError = _mk_recv_mte(
+                msg=roundtripped,
+                codec=codec,
+                src_validation_error=verr,
+                verb_header='Trying to send ',
+                is_invalid_payload=True,
+            )
+        except BaseException:
+            __tracebackhide__: bool = False
+            raise
+
+        if not raise_mte:
+            return mte
+
+        raise mte from verr

tractor/msg/pretty_struct.py

@@ -0,0 +1,292 @@
+# 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/>.
+
+'''
+Prettified version of `msgspec.Struct` for easier console grokin.
+
+'''
+from __future__ import annotations
+from collections import UserList
+from typing import (
+    Any,
+    Iterator,
+)
+
+from msgspec import (
+    msgpack,
+    Struct as _Struct,
+    structs,
+)
+from pprint import (
+    saferepr,
+)
+
+from tractor.log import get_logger
+
+log = get_logger()
+# TODO: auto-gen type sig for input func both for
+# type-msgs and logging of RPC tasks?
+# taken and modified from:
+# https://stackoverflow.com/a/57110117
+# import inspect
+# from typing import List
+
+# def my_function(input_1: str, input_2: int) -> list[int]:
+#     pass
+
+# def types_of(func):
+#     specs = inspect.getfullargspec(func)
+#     return_type = specs.annotations['return']
+#     input_types = [t.__name__ for s, t in specs.annotations.items() if s != 'return']
+#     return f'{func.__name__}({": ".join(input_types)}) -> {return_type}'
+
+# types_of(my_function)
+
+
+class DiffDump(UserList):
+    '''
+    Very simple list delegator that repr() dumps (presumed) tuple
+    elements of the form `tuple[str, Any, Any]` in a nice
+    multi-line readable form for analyzing `Struct` diffs.
+
+    '''
+    def __repr__(self) -> str:
+        if not len(self):
+            return super().__repr__()
+
+        # format by displaying item pair's ``repr()`` on multiple,
+        # indented lines such that they are more easily visually
+        # comparable when printed to console when printed to
+        # console.
+        repstr: str = '[\n'
+        for k, left, right in self:
+            repstr += (
+                f'({k},\n'
+                f'\t{repr(left)},\n'
+                f'\t{repr(right)},\n'
+                ')\n'
+            )
+        repstr += ']\n'
+        return repstr
+
+
+def iter_fields(struct: Struct) -> Iterator[
+    tuple[
+        structs.FieldIinfo,
+        str,
+        Any,
+    ]
+]:
+    '''
+    Iterate over all non-@property fields of this struct.
+
+    '''
+    fi: structs.FieldInfo
+    for fi in structs.fields(struct):
+        key: str = fi.name
+        val: Any = getattr(struct, key)
+        yield (
+            fi,
+            key,
+            val,
+        )
+
+
+def pformat(
+    struct: Struct,
+    field_indent: int = 2,
+    indent: int = 0,
+
+) -> str:
+    '''
+    Recursion-safe `pprint.pformat()` style formatting of
+    a `msgspec.Struct` for sane reading by a human using a REPL.
+
+    '''
+    # global whitespace indent
+    ws: str = ' '*indent
+
+    # field whitespace indent
+    field_ws: str = ' '*(field_indent + indent)
+
+    # qtn: str = ws + struct.__class__.__qualname__
+    qtn: str = struct.__class__.__qualname__
+
+    obj_str: str = ''  # accumulator
+    fi: structs.FieldInfo
+    k: str
+    v: Any
+    for fi, k, v in iter_fields(struct):
+
+        # TODO: how can we prefer `Literal['option1',  'option2,
+        # ..]` over .__name__ == `Literal` but still get only the
+        # latter for simple types like `str | int | None` etc..?
+        ft: type = fi.type
+        typ_name: str = getattr(ft, '__name__', str(ft))
+
+        # recurse to get sub-struct's `.pformat()` output Bo
+        if isinstance(v, Struct):
+            val_str: str =  v.pformat(
+                indent=field_indent + indent,
+                field_indent=indent + field_indent,
+            )
+
+        else:  # the `pprint` recursion-safe format:
+            # https://docs.python.org/3.11/library/pprint.html#pprint.saferepr
+            try:
+                val_str: str = saferepr(v)
+            except Exception:
+                log.exception(
+                    'Failed to `saferepr({type(struct)})` !?\n'
+                )
+            return _Struct.__repr__(struct)
+
+        # TODO: LOLOL use `textwrap.indent()` instead dawwwwwg!
+        obj_str += (field_ws + f'{k}: {typ_name} = {val_str},\n')
+
+    return (
+        f'{qtn}(\n'
+        f'{obj_str}'
+        f'{ws})'
+    )
+
+
+class Struct(
+    _Struct,
+
+    # https://jcristharif.com/msgspec/structs.html#tagged-unions
+    # tag='pikerstruct',
+    # tag=True,
+):
+    '''
+    A "human friendlier" (aka repl buddy) struct subtype.
+
+    '''
+    def to_dict(
+        self,
+        include_non_members: bool = True,
+
+    ) -> dict:
+        '''
+        Like it sounds.. direct delegation to:
+        https://jcristharif.com/msgspec/api.html#msgspec.structs.asdict
+
+        BUT, by default we pop all non-member (aka not defined as
+        struct fields) fields by default.
+
+        '''
+        asdict: dict = structs.asdict(self)
+        if include_non_members:
+            return asdict
+
+        # only return a dict of the struct members
+        # which were provided as input, NOT anything
+        # added as type-defined `@property` methods!
+        sin_props: dict = {}
+        fi: structs.FieldInfo
+        for fi, k, v in iter_fields(self):
+            sin_props[k] = asdict[k]
+
+        return sin_props
+
+    pformat = pformat
+    # __repr__ = pformat
+    # __str__ = __repr__ = pformat
+    # TODO: use a pprint.PrettyPrinter instance around ONLY rendering
+    # inside a known tty?
+    # def __repr__(self) -> str:
+    #     ...
+    def __repr__(self) -> str:
+        try:
+            return pformat(self)
+        except Exception:
+            log.exception(
+                f'Failed to `pformat({type(self)})` !?\n'
+            )
+            return _Struct.__repr__(self)
+
+    def copy(
+        self,
+        update: dict | None = None,
+
+    ) -> Struct:
+        '''
+        Validate-typecast all self defined fields, return a copy of
+        us with all such fields.
+
+        NOTE: This is kinda like the default behaviour in
+        `pydantic.BaseModel` except a copy of the object is
+        returned making it compat with `frozen=True`.
+
+        '''
+        if update:
+            for k, v in update.items():
+                setattr(self, k, v)
+
+        # NOTE: roundtrip serialize to validate
+        # - enode to msgpack binary format,
+        # - decode that back to a struct.
+        return msgpack.Decoder(type=type(self)).decode(
+            msgpack.Encoder().encode(self)
+        )
+
+    def typecast(
+        self,
+
+        # TODO: allow only casting a named subset?
+        # fields: set[str] | None = None,
+
+    ) -> None:
+        '''
+        Cast all fields using their declared type annotations
+        (kinda like what `pydantic` does by default).
+
+        NOTE: this of course won't work on frozen types, use
+        ``.copy()`` above in such cases.
+
+        '''
+        # https://jcristharif.com/msgspec/api.html#msgspec.structs.fields
+        fi: structs.FieldInfo
+        for fi in structs.fields(self):
+            setattr(
+                self,
+                fi.name,
+                fi.type(getattr(self, fi.name)),
+            )
+
+    def __sub__(
+        self,
+        other: Struct,
+
+    ) -> DiffDump[tuple[str, Any, Any]]:
+        '''
+        Compare fields/items key-wise and return a ``DiffDump``
+        for easy visual REPL comparison B)
+
+        '''
+        diffs: DiffDump[tuple[str, Any, Any]] = DiffDump()
+        for fi in structs.fields(self):
+            attr_name: str = fi.name
+            ours: Any = getattr(self, attr_name)
+            theirs: Any = getattr(other, attr_name)
+            if ours != theirs:
+                diffs.append((
+                    attr_name,
+                    ours,
+                    theirs,
+                ))
+
+        return diffs

tractor/msg/ptr.py

@@ -0,0 +1,139 @@
+# 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/>.
+
+'''
+IPC-compat cross-mem-boundary object pointer.
+
+'''
+
+# TODO: integration with our ``enable_modules: list[str]`` caps sys.
+
+# ``pkgutil.resolve_name()`` internally uses
+# ``importlib.import_module()`` which can be filtered by inserting
+# a ``MetaPathFinder`` into ``sys.meta_path`` (which we could do before
+# entering the ``_runtime.process_messages()`` loop).
+# - https://github.com/python/cpython/blob/main/Lib/pkgutil.py#L645
+# - https://stackoverflow.com/questions/1350466/preventing-python-code-from-importing-certain-modules
+#   - https://stackoverflow.com/a/63320902
+#   - https://docs.python.org/3/library/sys.html#sys.meta_path
+
+# the new "Implicit Namespace Packages" might be relevant?
+# - https://www.python.org/dev/peps/pep-0420/
+
+# add implicit serialized message type support so that paths can be
+# handed directly to IPC primitives such as streams and `Portal.run()`
+# calls:
+# - via ``msgspec``:
+#   - https://jcristharif.com/msgspec/api.html#struct
+#   - https://jcristharif.com/msgspec/extending.html
+# via ``msgpack-python``:
+# - https://github.com/msgpack/msgpack-python#packingunpacking-of-custom-data-type
+
+from __future__ import annotations
+from inspect import (
+    isfunction,
+    ismethod,
+)
+from pkgutil import resolve_name
+
+
+class NamespacePath(str):
+    '''
+    A serializeable `str`-subtype implementing a "namespace
+    pointer" to any Python object reference (like a function)
+    using the same format as the built-in `pkgutil.resolve_name()`
+    system.
+
+    A value describes a target's module-path and namespace-key
+    separated by a ':' and thus can be easily used as
+    a IPC-message-native reference-type allowing memory isolated
+    actors to point-and-load objects via a minimal `str` value.
+
+    '''
+    _ref: object | type | None = None
+
+    # TODO: support providing the ns instance in
+    # order to support 'self.<meth>` style to make
+    # `Portal.run_from_ns()` work!
+    # _ns: ModuleType|type|None = None
+
+    def load_ref(self) -> object | type:
+        if self._ref is None:
+            self._ref = resolve_name(self)
+        return self._ref
+
+    @staticmethod
+    def _mk_fqnp(
+        ref: type|object,
+    ) -> tuple[str, str]:
+        '''
+        Generate a minial `str` pair which describes a python
+        object's namespace path and object/type name.
+
+        In more precise terms something like:
+          - 'py.namespace.path:object_name',
+          - eg.'tractor.msg:NamespacePath' will be the ``str`` form
+            of THIS type XD
+
+        '''
+        if isfunction(ref):
+            name: str = getattr(ref, '__name__')
+            mod_name: str = ref.__module__
+
+        elif ismethod(ref):
+            # build out the path manually i guess..?
+            # TODO: better way?
+            name: str = '.'.join([
+                type(ref.__self__).__name__,
+                ref.__func__.__name__,
+            ])
+            mod_name: str = ref.__self__.__module__
+
+        else:  # object or other?
+            # isinstance(ref, object)
+            # and not isfunction(ref)
+            name: str = type(ref).__name__
+            mod_name: str = ref.__module__
+
+        # TODO: return static value direactly?
+        #
+        # fully qualified namespace path, tuple.
+        fqnp: tuple[str, str] = (
+            mod_name,
+            name,
+        )
+        return fqnp
+
+    @classmethod
+    def from_ref(
+        cls,
+        ref: type|object,
+
+    ) -> NamespacePath:
+
+        fqnp: tuple[str, str] = cls._mk_fqnp(ref)
+        return cls(':'.join(fqnp))
+
+    def to_tuple(
+        self,
+
+        # TODO: could this work re `self:<meth>` case from above?
+        # load_ref: bool = True,
+
+    ) -> tuple[str, str]:
+        return self._mk_fqnp(
+            self.load_ref()
+        )

tractor/msg/types.py

@@ -0,0 +1,730 @@
+# 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/>.
+
+'''
+Define our strictly typed IPC message spec for the SCIPP:
+
+that is,
+
+the "Structurred-Concurrency-Inter-Process-(dialog)-(un)Protocol".
+
+'''
+from __future__ import annotations
+import types
+from typing import (
+    Any,
+    Generic,
+    Literal,
+    Type,
+    TypeVar,
+    TypeAlias,
+    Union,
+)
+
+from msgspec import (
+    defstruct,
+    # field,
+    Raw,
+    Struct,
+    # UNSET,
+    # UnsetType,
+)
+
+from tractor.msg import (
+    pretty_struct,
+)
+from tractor.log import get_logger
+
+
+log = get_logger('tractor.msgspec')
+
+# type variable for the boxed payload field `.pld`
+PayloadT = TypeVar('PayloadT')
+
+
+class PayloadMsg(
+    Struct,
+    Generic[PayloadT],
+
+    # https://jcristharif.com/msgspec/structs.html#tagged-unions
+    tag=True,
+    tag_field='msg_type',
+
+    # https://jcristharif.com/msgspec/structs.html#field-ordering
+    # kw_only=True,
+
+    # https://jcristharif.com/msgspec/structs.html#equality-and-order
+    # order=True,
+
+    # https://jcristharif.com/msgspec/structs.html#encoding-decoding-as-arrays
+    # as_array=True,
+):
+    '''
+    An abstract payload boxing/shuttling IPC msg type.
+
+    Boxes data-values passed to/from user code
+
+    (i.e. any values passed by `tractor` application code using any of
+
+      |_ `._streaming.MsgStream.send/receive()`
+      |_ `._context.Context.started/result()`
+      |_ `._ipc.Channel.send/recv()`
+
+     aka our "IPC primitive APIs")
+
+    as message "payloads" set to the `.pld` field and uses
+    `msgspec`'s "tagged unions" feature to support a subset of our
+    "SC-transitive shuttle protocol" specification with
+    a `msgspec.Struct` inheritance tree.
+
+    '''
+    cid: str  # call/context-id
+    # ^-TODO-^: more explicit type?
+    # -[ ] use UNSET here?
+    #  https://jcristharif.com/msgspec/supported-types.html#unset
+    #
+    # -[ ] `uuid.UUID` which has multi-protocol support
+    #  https://jcristharif.com/msgspec/supported-types.html#uuid
+
+    # The msg's "payload" (spelled without vowels):
+    # https://en.wikipedia.org/wiki/Payload_(computing)
+    pld: Raw
+
+    # ^-NOTE-^ inherited from any `PayloadMsg` (and maybe type
+    # overriden via the `._ops.limit_plds()` API), but by default is
+    # parameterized to be `Any`.
+    #
+    # XXX this `Union` must strictly NOT contain `Any` if
+    # a limited msg-type-spec is intended, such that when
+    # creating and applying a new `MsgCodec` its 
+    # `.decoder: Decoder` is configured with a `Union[Type[Struct]]` which
+    # restricts the allowed payload content (this `.pld` field) 
+    # by type system defined loading constraints B)
+    #
+    # TODO: could also be set to `msgspec.Raw` if the sub-decoders
+    # approach is preferred over the generic parameterization 
+    # approach as take by `mk_msg_spec()` below.
+
+
+# TODO: complete rename
+Msg = PayloadMsg
+
+
+class Aid(
+    Struct,
+    tag=True,
+    tag_field='msg_type',
+):
+    '''
+    Actor-identity msg.
+
+    Initial contact exchange enabling an actor "mailbox handshake"
+    delivering the peer identity (and maybe eventually contact)
+    info.
+
+    Used by discovery protocol to register actors as well as
+    conduct the initial comms (capability) filtering.
+
+    '''
+    name: str
+    uuid: str
+    # TODO: use built-in support for UUIDs?
+    # -[ ] `uuid.UUID` which has multi-protocol support
+    #  https://jcristharif.com/msgspec/supported-types.html#uuid
+
+
+class SpawnSpec(
+    pretty_struct.Struct,
+    tag=True,
+    tag_field='msg_type',
+):
+    '''
+    Initial runtime spec handed down from a spawning parent to its
+    child subactor immediately following first contact via an
+    `Aid` msg.
+
+    '''
+    # TODO: similar to the `Start` kwargs spec needed below, we need
+    # a hard `Struct` def for all of these fields!
+    _parent_main_data: dict
+    _runtime_vars: dict[str, Any]
+
+    # module import capability
+    enable_modules: dict[str, str]
+
+    # TODO: not just sockaddr pairs?
+    # -[ ] abstract into a `TransportAddr` type?
+    reg_addrs: list[tuple[str, int]]
+    bind_addrs: list[tuple[str, int]]
+
+
+# TODO: caps based RPC support in the payload?
+#
+# -[ ] integration with our ``enable_modules: list[str]`` caps sys.
+#   ``pkgutil.resolve_name()`` internally uses
+#   ``importlib.import_module()`` which can be filtered by
+#   inserting a ``MetaPathFinder`` into ``sys.meta_path`` (which
+#   we could do before entering the ``Actor._process_messages()``
+#   loop)?
+#   - https://github.com/python/cpython/blob/main/Lib/pkgutil.py#L645
+#   - https://stackoverflow.com/questions/1350466/preventing-python-code-from-importing-certain-modules
+#   - https://stackoverflow.com/a/63320902
+#   - https://docs.python.org/3/library/sys.html#sys.meta_path
+#
+# -[ ] can we combine .ns + .func into a native `NamespacePath` field?
+#
+# -[ ] better name, like `Call/TaskInput`?
+#
+# -[ ] XXX a debugger lock msg transaction with payloads like,
+#   child -> `.pld: DebugLock` -> root
+#   child <- `.pld: DebugLocked` <- root
+#   child -> `.pld: DebugRelease` -> root
+#
+#   WHY => when a pld spec is provided it might not allow for
+#   debug mode msgs as they currently are (using plain old `pld.
+#   str` payloads) so we only when debug_mode=True we need to
+#   union in this debugger payload set?
+#
+#   mk_msg_spec(
+#       MyPldSpec,
+#       debug_mode=True,
+#   ) -> (
+#       Union[MyPldSpec]
+#      | Union[DebugLock, DebugLocked, DebugRelease]
+#   )
+
+# class Params(
+#     Struct,
+#     Generic[PayloadT],
+# ):
+#     spec: PayloadT|ParamSpec
+#     inputs: InputsT|dict[str, Any]
+
+    # TODO: for eg. we could stringently check the target
+    # task-func's type sig and enforce it?
+    # as an example for an IPTC,
+    # @tractor.context
+    # async def send_back_nsp(
+    #     ctx: Context,
+    #     expect_debug: bool,
+    #     pld_spec_str: str,
+    #     add_hooks: bool,
+    #     started_msg_dict: dict,
+    # ) -> <WhatHere!>:
+
+    # TODO: figure out which of the `typing` feats we want to
+    # support:
+    # - plain ol `ParamSpec`:
+    #   https://docs.python.org/3/library/typing.html#typing.ParamSpec
+    # - new in 3.12 type parameter lists Bo
+    # |_ https://docs.python.org/3/reference/compound_stmts.html#type-params
+    # |_ historical pep 695: https://peps.python.org/pep-0695/
+    # |_ full lang spec: https://typing.readthedocs.io/en/latest/spec/
+    # |_ on annotation scopes:
+    #    https://docs.python.org/3/reference/executionmodel.html#annotation-scopes
+    # spec: ParamSpec[
+    #     expect_debug: bool,
+    #     pld_spec_str: str,
+    #     add_hooks: bool,
+    #     started_msg_dict: dict,
+    # ]
+
+
+# TODO: possibly sub-type for runtime method requests?
+# -[ ] `Runtime(Start)` with a `.ns: str = 'self' or
+#     we can just enforce any such method as having a strict
+#     ns for calling funcs, namely the `Actor` instance?
+class Start(
+    Struct,
+    tag=True,
+    tag_field='msg_type',
+):
+    '''
+    Initial request to remotely schedule an RPC `trio.Task` via
+    `Actor.start_remote_task()`.
+
+    It is called by all the following public APIs:
+
+    - `ActorNursery.run_in_actor()`
+
+    - `Portal.run()`
+          `|_.run_from_ns()`
+          `|_.open_stream_from()`
+          `|_._submit_for_result()`
+
+    - `Context.open_context()`
+
+    '''
+    cid: str
+
+    ns: str
+    func: str
+
+    # TODO: make this a sub-struct which can be further
+    # type-limited, maybe `Inputs`?
+    # => SEE ABOVE <=
+    kwargs: dict[str, Any]
+    uid: tuple[str, str]  # (calling) actor-id
+
+    # TODO: enforcing a msg-spec in terms `Msg.pld`
+    # parameterizable msgs to be used in the appls IPC dialog.
+    # => SEE `._codec.MsgDec` for more <=
+    pld_spec: str = str(Any)
+
+
+class StartAck(
+    Struct,
+    tag=True,
+    tag_field='msg_type',
+):
+    '''
+    Init response to a `Cmd` request indicating the far
+    end's RPC spec, namely its callable "type".
+
+    '''
+    cid: str
+    # TODO: maybe better names for all these?
+    # -[ ] obvi ^ would need sync with `._rpc`
+    functype: Literal[
+        'asyncfunc',
+        'asyncgen',
+        'context',  # TODO: the only one eventually?
+    ]
+
+    # import typing
+    # eval(str(Any), {}, {'typing': typing})
+    # started_spec: str = str(Any)
+    # return_spec
+
+
+class Started(
+    PayloadMsg,
+    Generic[PayloadT],
+):
+    '''
+    Packet to shuttle the "first value" delivered by
+    `Context.started(value: Any)` from a `@tractor.context`
+    decorated IPC endpoint.
+
+    '''
+    pld: PayloadT|Raw
+
+
+# TODO: cancel request dedicated msg?
+# -[ ] instead of using our existing `Start`?
+#
+# class Cancel:
+#     cid: str
+
+
+class Yield(
+    PayloadMsg,
+    Generic[PayloadT],
+):
+    '''
+    Per IPC transmission of a value from `await MsgStream.send(<value>)`.
+
+    '''
+    pld: PayloadT|Raw
+
+
+class Stop(
+    Struct,
+    tag=True,
+    tag_field='msg_type',
+):
+    '''
+    Stream termination signal much like an IPC version 
+    of `StopAsyncIteration`.
+
+    '''
+    cid: str
+    # TODO: do we want to support a payload on stop?
+    # pld: UnsetType = UNSET
+
+
+# TODO: is `Result` or `Out[come]` a better name?
+class Return(
+    PayloadMsg,
+    Generic[PayloadT],
+):
+    '''
+    Final `return <value>` from a remotely scheduled
+    func-as-`trio.Task`.
+
+    '''
+    pld: PayloadT|Raw
+
+
+class CancelAck(
+    PayloadMsg,
+    Generic[PayloadT],
+):
+    '''
+    Deliver the `bool` return-value from a cancellation `Actor`
+    method scheduled via and prior RPC request.
+
+    - `Actor.cancel()`
+       `|_.cancel_soon()`
+       `|_.cancel_rpc_tasks()`
+       `|_._cancel_task()`
+       `|_.cancel_server()`
+
+    RPCs to these methods must **always** be able to deliver a result
+    despite the currently configured IPC msg spec such that graceful
+    cancellation is always functional in the runtime.
+
+    '''
+    pld: bool
+
+
+# TODO: unify this with `._exceptions.RemoteActorError`
+# such that we can have a msg which is both raisable and
+# IPC-wire ready?
+# B~o
+class Error(
+    Struct,
+    tag=True,
+    tag_field='msg_type',
+
+    # TODO may omit defaults?
+    # https://jcristharif.com/msgspec/structs.html#omitting-default-values
+    # omit_defaults=True,
+):
+    '''
+    A pkt that wraps `RemoteActorError`s for relay and raising.
+
+    Fields are 1-to-1 meta-data as needed originally by
+    `RemoteActorError.msgdata: dict` but now are defined here.
+
+    Note: this msg shuttles `ContextCancelled` and `StreamOverrun`
+    as well is used to rewrap any `MsgTypeError` for relay-reponse
+    to bad `Yield.pld` senders during an IPC ctx's streaming dialog
+    phase.
+
+    '''
+    src_uid: tuple[str, str]
+    src_type_str: str
+    boxed_type_str: str
+    relay_path: list[tuple[str, str]]
+
+    # normally either both are provided or just
+    # a message for certain special cases where
+    # we pack a message for a locally raised
+    # mte or ctxc.
+    message: str|None = None
+    tb_str: str = ''
+
+    # TODO: only optionally include sub-type specfic fields?
+    # -[ ] use UNSET or don't include them via `omit_defaults` (see
+    #      inheritance-line options above)
+    #
+    # `ContextCancelled` reports the src cancelling `Actor.uid`
+    canceller: tuple[str, str]|None = None
+
+    # `StreamOverrun`-specific src `Actor.uid`
+    sender: tuple[str, str]|None = None
+
+    # `MsgTypeError` meta-data
+    cid: str|None = None
+    # when the receiver side fails to decode a delivered
+    # `PayloadMsg`-subtype; one and/or both the msg-struct instance
+    # and `Any`-decoded to `dict` of the msg are set and relayed
+    # (back to the sender) for introspection.
+    _bad_msg: Started|Yield|Return|None = None
+    _bad_msg_as_dict: dict|None = None
+
+
+def from_dict_msg(
+    dict_msg: dict,
+
+    msgT: MsgType|None = None,
+    tag_field: str = 'msg_type',
+    use_pretty: bool = False,
+
+) -> MsgType:
+    '''
+    Helper to build a specific `MsgType` struct from a "vanilla"
+    decoded `dict`-ified equivalent of the msg: i.e. if the
+    `msgpack.Decoder.type == Any`, the default when using
+    `msgspec.msgpack` and not "typed decoding" using
+    `msgspec.Struct`.
+
+    '''
+    msg_type_tag_field: str = (
+        msgT.__struct_config__.tag_field
+        if msgT is not None
+        else tag_field
+    )
+    # XXX ensure tag field is removed
+    msgT_name: str = dict_msg.pop(msg_type_tag_field)
+    msgT: MsgType = _msg_table[msgT_name]
+    if use_pretty:
+        msgT = defstruct(
+            name=msgT_name,
+            fields=[
+                (key, fi.type)
+                for fi, key, _
+                in pretty_struct.iter_fields(msgT)
+            ],
+            bases=(
+                pretty_struct.Struct,
+                msgT,
+            ),
+        )
+    return msgT(**dict_msg)
+
+# TODO: should be make a set of cancel msgs?
+# -[ ] a version of `ContextCancelled`?
+#     |_ and/or with a scope field?
+# -[ ] or, a full `ActorCancelled`?
+#
+# class Cancelled(MsgType):
+#     cid: str
+#
+# -[ ] what about overruns?
+#
+# class Overrun(MsgType):
+#     cid: str
+
+_runtime_msgs: list[Struct] = [
+
+    # identity handshake on first IPC `Channel` contact.
+    Aid,
+
+    # parent-to-child spawn specification passed as 2nd msg after
+    # handshake ONLY after child connects back to parent.
+    SpawnSpec,
+
+    # inter-actor RPC initiation
+    Start,  # schedule remote task-as-func
+    StartAck,  # ack the schedule request
+
+    # emission from `MsgStream.aclose()`
+    Stop,
+
+    # `Return` sub-type that we always accept from
+    # runtime-internal cancel endpoints
+    CancelAck,
+
+    # box remote errors, normally subtypes
+    # of `RemoteActorError`.
+    Error,
+]
+
+# the no-outcome-yet IAC (inter-actor-communication) sub-set which
+# can be `PayloadMsg.pld` payload field type-limited by application code
+# using `apply_codec()` and `limit_msg_spec()`.
+_payload_msgs: list[PayloadMsg] = [
+    # first <value> from `Context.started(<value>)`
+    Started,
+
+    # any <value> sent via `MsgStream.send(<value>)`
+    Yield,
+
+    # the final value returned from a `@context` decorated
+    # IPC endpoint.
+    Return,
+]
+
+# built-in SC shuttle protocol msg type set in
+# approx order of the IPC txn-state spaces.
+__msg_types__: list[MsgType] = (
+    _runtime_msgs
+    +
+    _payload_msgs
+)
+
+
+_msg_table: dict[str, MsgType] = {
+    msgT.__name__: msgT
+    for msgT in __msg_types__
+}
+
+# TODO: use new type declaration syntax for msg-type-spec
+# https://docs.python.org/3/library/typing.html#type-aliases
+# https://docs.python.org/3/reference/simple_stmts.html#type
+MsgType: TypeAlias = Union[*__msg_types__]
+
+
+def mk_msg_spec(
+    payload_type_union: Union[Type] = Any,
+
+    spec_build_method: Literal[
+        'indexed_generics',  # works
+        'defstruct',
+        'types_new_class',
+
+    ] = 'indexed_generics',
+
+) -> tuple[
+    Union[MsgType],
+    list[MsgType],
+]:
+    '''
+    Create a payload-(data-)type-parameterized IPC message specification.
+
+    Allows generating IPC msg types from the above builtin set
+    with a payload (field) restricted data-type, the `Msg.pld: PayloadT`.
+
+    This allows runtime-task contexts to use the python type system
+    to limit/filter payload values as determined by the input
+    `payload_type_union: Union[Type]`.
+
+    Notes: originally multiple approaches for constructing the
+    type-union passed to `msgspec` were attempted as selected via the
+    `spec_build_method`, but it turns out only the defaul method
+    'indexed_generics' seems to work reliably in all use cases. As
+    such, the others will likely be removed in the near future.
+
+    '''
+    submsg_types: list[MsgType] = Msg.__subclasses__()
+    bases: tuple = (
+        # XXX NOTE XXX the below generic-parameterization seems to
+        # be THE ONLY way to get this to work correctly in terms
+        # of getting ValidationError on a roundtrip?
+        Msg[payload_type_union],
+        Generic[PayloadT],
+    )
+    defstruct_bases: tuple = (
+        Msg, # [payload_type_union],
+        # Generic[PayloadT],
+        # ^-XXX-^: not allowed? lul..
+    )
+    ipc_msg_types: list[Msg] = []
+
+    idx_msg_types: list[Msg] = []
+    defs_msg_types: list[Msg] = []
+    nc_msg_types: list[Msg] = []
+
+    for msgtype in __msg_types__:
+
+        # for the NON-payload (user api) type specify-able
+        # msgs types, we simply aggregate the def as is
+        # for inclusion in the output type `Union`.
+        if msgtype not in _payload_msgs:
+            ipc_msg_types.append(msgtype)
+            continue
+
+        # check inheritance sanity
+        assert msgtype in submsg_types
+
+        # TODO: wait why do we need the dynamic version here?
+        # XXX ANSWER XXX -> BC INHERITANCE.. don't work w generics..
+        #
+        # NOTE previously bc msgtypes WERE NOT inheritting
+        # directly the `Generic[PayloadT]` type, the manual method
+        # of generic-paraming with `.__class_getitem__()` wasn't
+        # working..
+        #
+        # XXX but bc i changed that to make every subtype inherit
+        # it, this manual "indexed parameterization" method seems
+        # to work?
+        #
+        # -[x] paraming the `PayloadT` values via `Generic[T]`
+        #   does work it seems but WITHOUT inheritance of generics
+        #
+        # -[-] is there a way to get it to work at module level
+        #   just using inheritance or maybe a metaclass?
+        #  => thot that `defstruct` might work, but NOPE, see
+        #   below..
+        #
+        idxed_msg_type: Msg = msgtype[payload_type_union]
+        idx_msg_types.append(idxed_msg_type)
+
+        # TODO: WHY do we need to dynamically generate the
+        # subtype-msgs here to ensure the `.pld` parameterization
+        # propagates as well as works at all in terms of the
+        # `msgpack.Decoder()`..?
+        #
+        # dynamically create the payload type-spec-limited msg set.
+        newclass_msgtype: Type = types.new_class(
+            name=msgtype.__name__,
+            bases=bases,
+            kwds={},
+        )
+        nc_msg_types.append(
+            newclass_msgtype[payload_type_union]
+        )
+
+        # with `msgspec.structs.defstruct`
+        # XXX ALSO DOESN'T WORK
+        defstruct_msgtype = defstruct(
+            name=msgtype.__name__,
+            fields=[
+                ('cid', str),
+
+                # XXX doesn't seem to work..
+                # ('pld', PayloadT),
+
+                ('pld', payload_type_union),
+            ],
+            bases=defstruct_bases,
+        )
+        defs_msg_types.append(defstruct_msgtype)
+
+        # assert index_paramed_msg_type == manual_paramed_msg_subtype
+
+        # paramed_msg_type = manual_paramed_msg_subtype
+
+        # ipc_payload_msgs_type_union |= index_paramed_msg_type
+
+    idx_spec: Union[Type[Msg]] = Union[*idx_msg_types]
+    def_spec: Union[Type[Msg]] = Union[*defs_msg_types]
+    nc_spec: Union[Type[Msg]] = Union[*nc_msg_types]
+
+    specs: dict[str, Union[Type[Msg]]] = {
+        'indexed_generics': idx_spec,
+        'defstruct': def_spec,
+        'types_new_class': nc_spec,
+    }
+    msgtypes_table: dict[str, list[Msg]] = {
+        'indexed_generics': idx_msg_types,
+        'defstruct': defs_msg_types,
+        'types_new_class': nc_msg_types,
+    }
+
+    # XXX lol apparently type unions can't ever
+    # be equal eh?
+    # TODO: grok the diff here better..
+    #
+    # assert (
+    #     idx_spec
+    #     ==
+    #     nc_spec
+    #     ==
+    #     def_spec
+    # )
+    # breakpoint()
+
+    pld_spec: Union[Type] = specs[spec_build_method]
+    runtime_spec: Union[Type] = Union[*ipc_msg_types]
+    ipc_spec = pld_spec | runtime_spec
+    log.runtime(
+        'Generating new IPC msg-spec\n'
+        f'{ipc_spec}\n'
+    )
+    assert (
+        ipc_spec
+        and
+        ipc_spec is not Any
+    )
+    return (
+        ipc_spec,
+        msgtypes_table[spec_build_method]
+        +
+        ipc_msg_types,
+    )

tractor/to_asyncio.py

@@ -18,34 +18,44 @@
 Infection apis for ``asyncio`` loops running ``trio`` using guest mode.
 
 '''
+from __future__ import annotations
 import asyncio
 from asyncio.exceptions import CancelledError
 from contextlib import asynccontextmanager as acm
 from dataclasses import dataclass
 import inspect
+import traceback
 from typing import (
     Any,
     Callable,
     AsyncIterator,
     Awaitable,
-    Optional,
 )
 
-import trio
+import tractor
-from outcome import Error
+from tractor._exceptions import AsyncioCancelled
-
+from tractor._state import (
-from .log import get_logger
+    debug_mode,
-from ._state import current_actor
+)
-from ._exceptions import AsyncioCancelled
+from tractor.devx import _debug
-from .trionics._broadcast import (
+from tractor.log import get_logger
+from tractor.trionics._broadcast import (
     broadcast_receiver,
     BroadcastReceiver,
 )
+import trio
+from outcome import (
+    Error,
+    Outcome,
+)
 
 log = get_logger(__name__)
 
 
-__all__ = ['run_task', 'run_as_asyncio_guest']
+__all__ = [
+    'run_task',
+    'run_as_asyncio_guest',
+]
 
 
 @dataclass
@@ -65,9 +75,9 @@ class LinkedTaskChannel(trio.abc.Channel):
     _trio_exited: bool = False
 
     # set after ``asyncio.create_task()``
-    _aio_task: Optional[asyncio.Task] = None
+    _aio_task: asyncio.Task|None = None
-    _aio_err: Optional[BaseException] = None
+    _aio_err: BaseException|None = None
-    _broadcaster: Optional[BroadcastReceiver] = None
+    _broadcaster: BroadcastReceiver|None = None
 
     async def aclose(self) -> None:
         await self._from_aio.aclose()
@@ -149,17 +159,20 @@ def _run_asyncio_task(
     *,
     qsize: int = 1,
     provide_channels: bool = False,
+    hide_tb: bool = False,
     **kwargs,
 
 ) -> LinkedTaskChannel:
     '''
     Run an ``asyncio`` async function or generator in a task, return
-    or stream the result back to ``trio``.
+    or stream the result back to the caller `trio.lowleve.Task`.
 
     '''
-    __tracebackhide__ = True
+    __tracebackhide__: bool = hide_tb
-    if not current_actor().is_infected_aio():
+    if not tractor.current_actor().is_infected_aio():
-        raise RuntimeError("`infect_asyncio` mode is not enabled!?")
+        raise RuntimeError(
+            "`infect_asyncio` mode is not enabled!?"
+        )
 
     # ITC (inter task comms), these channel/queue names are mostly from
     # ``asyncio``'s perspective.
@@ -167,7 +180,6 @@ def _run_asyncio_task(
     to_trio, from_aio = trio.open_memory_channel(qsize)  # type: ignore
 
     args = tuple(inspect.getfullargspec(func).args)
-
     if getattr(func, '_tractor_steam_function', None):
         # the assumption is that the target async routine accepts the
         # send channel then it intends to yield more then one return
@@ -188,7 +200,7 @@ def _run_asyncio_task(
 
     cancel_scope = trio.CancelScope()
     aio_task_complete = trio.Event()
-    aio_err: Optional[BaseException] = None
+    aio_err: BaseException|None = None
 
     chan = LinkedTaskChannel(
         aio_q,  # asyncio.Queue
@@ -217,8 +229,15 @@ def _run_asyncio_task(
         try:
             result = await coro
         except BaseException as aio_err:
-            log.exception('asyncio task errored')
             chan._aio_err = aio_err
+            if isinstance(aio_err, CancelledError):
+                log.runtime(
+                    '`asyncio` task was cancelled..\n'
+                )
+            else:
+                log.exception(
+                    '`asyncio` task errored\n'
+                )
             raise
 
         else:
@@ -247,37 +266,69 @@ def _run_asyncio_task(
     if not inspect.isawaitable(coro):
         raise TypeError(f"No support for invoking {coro}")
 
-    task = asyncio.create_task(
+    task: asyncio.Task = asyncio.create_task(
         wait_on_coro_final_result(
             to_trio,
             coro,
             aio_task_complete
         )
     )
-    chan._aio_task = task
+    chan._aio_task: asyncio.Task = task
+
+    # XXX TODO XXX get this actually workin.. XD
+    # -[ ] we need logic to setup `greenback` for `asyncio`-side task
+    #     REPLing.. which should normally be nearly the same as for
+    #     `trio`?
+    # -[ ] add to a new `.devx._greenback.maybe_init_for_asyncio()`?
+    if (
+        debug_mode()
+        and
+        (greenback := _debug.maybe_import_greenback(
+            force_reload=True,
+            raise_not_found=False,
+        ))
+    ):
+        greenback.bestow_portal(task)
 
     def cancel_trio(task: asyncio.Task) -> None:
         '''
-        Cancel the calling ``trio`` task on error.
+        Cancel the calling `trio` task on error.
 
         '''
         nonlocal chan
-        aio_err = chan._aio_err
+        aio_err: BaseException|None = chan._aio_err
-        task_err: Optional[BaseException] = None
+        task_err: BaseException|None = None
 
-        # only to avoid ``asyncio`` complaining about uncaptured
+        # only to avoid `asyncio` complaining about uncaptured
         # task exceptions
         try:
-            task.exception()
+            res: Any = task.result()
         except BaseException as terr:
-            task_err = terr
+            task_err: BaseException = terr
 
+            msg: str = (
+                'Infected `asyncio` task {etype_str}\n'
+            )
             if isinstance(terr, CancelledError):
-                log.cancel(f'`asyncio` task cancelled: {task.get_name()}')
+                msg += (
+                    f'c)>\n'
+                    f' |_{task}\n'
+                )
+                log.cancel(
+                    msg.format(etype_str='cancelled')
+                )
             else:
-                log.exception(f'`asyncio` task: {task.get_name()} errored')
+                msg += (
+                    f'x)>\n'
+                    f' |_{task}\n'
+                )
+                log.exception(
+                    msg.format(etype_str='errored')
+                )
 
-            assert type(terr) is type(aio_err), 'Asyncio task error mismatch?'
+            assert type(terr) is type(aio_err), (
+                '`asyncio` task error mismatch?!?'
+            )
 
         if aio_err is not None:
             # XXX: uhh is this true?
@@ -290,27 +341,47 @@ def _run_asyncio_task(
             # We might want to change this in the future though.
             from_aio.close()
 
-            if type(aio_err) is CancelledError:
+            if task_err is None:
-                log.cancel("infected task was cancelled")
-
-                # TODO: show that the cancellation originated
-                # from the ``trio`` side? right?
-                # if cancel_scope.cancelled:
-                #     raise aio_err from err
-
-            elif task_err is None:
                 assert aio_err
-                aio_err.with_traceback(aio_err.__traceback__)
+                # wait, wut?
-                log.error('infected task errorred')
+                # aio_err.with_traceback(aio_err.__traceback__)
 
-            # XXX: alway cancel the scope on error
+            # TODO: show when cancellation originated
-            # in case the trio task is blocking
+            # from each side more pedantically?
-            # on a checkpoint.
+            # elif (
+            #     type(aio_err) is CancelledError
+            #     and  # trio was the cause?
+            #     cancel_scope.cancel_called
+            # ):
+            #     log.cancel(
+            #         'infected task was cancelled by `trio`-side'
+            #     )
+            #     raise aio_err from task_err
+
+            # XXX: if not already, alway cancel the scope
+            # on a task error in case the trio task is blocking on
+            # a checkpoint.
             cancel_scope.cancel()
 
-            # raise any ``asyncio`` side error.
+            if (
+                task_err
+                and
+                aio_err is not task_err
+            ):
+                raise aio_err from task_err
+
+            # raise any `asyncio` side error.
             raise aio_err
 
+        log.info(
+            '`trio` received final result from {task}\n'
+            f'|_{res}\n'
+        )
+        # TODO: do we need this?
+        # if task_err:
+        #     cancel_scope.cancel()
+        #     raise task_err
+
     task.add_done_callback(cancel_trio)
     return chan
 
@@ -329,15 +400,17 @@ async def translate_aio_errors(
     '''
     trio_task = trio.lowlevel.current_task()
 
-    aio_err: Optional[BaseException] = None
+    aio_err: BaseException|None = None
 
     # TODO: make thisi a channel method?
     def maybe_raise_aio_err(
-        err: Optional[Exception] = None
+        err: Exception|None = None
     ) -> None:
         aio_err = chan._aio_err
         if (
-            aio_err is not None and
+            aio_err is not None
+            and
+            # not isinstance(aio_err, CancelledError)
             type(aio_err) != CancelledError
         ):
             # always raise from any captured asyncio error
@@ -369,13 +442,17 @@ async def translate_aio_errors(
     ):
         aio_err = chan._aio_err
         if (
-            task.cancelled() and
+            task.cancelled()
+            and
             type(aio_err) is CancelledError
         ):
-            # if an underlying ``asyncio.CancelledError`` triggered this
+            # if an underlying `asyncio.CancelledError` triggered this
             # channel close, raise our (non-``BaseException``) wrapper
             # error: ``AsyncioCancelled`` from that source error.
-            raise AsyncioCancelled from aio_err
+            raise AsyncioCancelled(
+                f'Task cancelled\n'
+                f'|_{task}\n'
+            ) from aio_err
 
         else:
             raise
@@ -418,8 +495,8 @@ async def run_task(
 
 ) -> Any:
     '''
-    Run an ``asyncio`` async function or generator in a task, return
+    Run an `asyncio` async function or generator in a task, return
-    or stream the result back to ``trio``.
+    or stream the result back to `trio`.
 
     '''
     # simple async func
@@ -477,11 +554,124 @@ async def open_channel_from(
                 chan._to_trio.close()
 
 
-def run_as_asyncio_guest(
+class AsyncioRuntimeTranslationError(RuntimeError):
+    '''
+    We failed to correctly relay runtime semantics and/or maintain SC
+    supervision rules cross-event-loop.
 
+    '''
+
+
+def run_trio_task_in_future(
+    async_fn,
+    *args,
+) -> asyncio.Future:
+    '''
+    Run an async-func as a `trio` task from an `asyncio.Task` wrapped
+    in a `asyncio.Future` which is returned to the caller.
+
+    Another astounding feat by the great @oremanj !!
+
+    Bo
+
+    '''
+    result_future = asyncio.Future()
+    cancel_scope = trio.CancelScope()
+    finished: bool = False
+
+    # monkey-patch the future's `.cancel()` meth to
+    # allow cancellation relay to `trio`-task.
+    cancel_message: str|None = None
+    orig_cancel = result_future.cancel
+
+    def wrapped_cancel(
+        msg: str|None = None,
+    ):
+        nonlocal cancel_message
+        if finished:
+            # We're being called back after the task completed
+            if msg is not None:
+                return orig_cancel(msg)
+            elif cancel_message is not None:
+                return orig_cancel(cancel_message)
+            else:
+                return orig_cancel()
+
+        if result_future.done():
+            return False
+
+        # Forward cancellation to the Trio task, don't mark
+        # future as cancelled until it completes
+        cancel_message = msg
+        cancel_scope.cancel()
+        return True
+
+    result_future.cancel = wrapped_cancel
+
+    async def trio_task() -> None:
+        nonlocal finished
+        try:
+            with cancel_scope:
+                try:
+                    # TODO: type this with new tech in 3.13
+                    result: Any = await async_fn(*args)
+                finally:
+                    finished = True
+
+            # Propagate result or cancellation to the Future
+            if cancel_scope.cancelled_caught:
+                result_future.cancel()
+
+            elif not result_future.cancelled():
+                result_future.set_result(result)
+
+        except BaseException as exc:
+            # the result future gets all the non-Cancelled
+            # exceptions. Any Cancelled need to keep propagating
+            # out of this stack frame in order to reach the cancel
+            # scope for which they're intended.
+            cancelled: BaseException|None
+            rest: BaseException|None
+            if isinstance(exc, BaseExceptionGroup):
+                cancelled, rest = exc.split(trio.Cancelled)
+
+            elif isinstance(exc, trio.Cancelled):
+                cancelled, rest = exc, None
+
+            else:
+                cancelled, rest = None, exc
+
+            if not result_future.cancelled():
+                if rest:
+                    result_future.set_exception(rest)
+                else:
+                    result_future.cancel()
+
+            if cancelled:
+                raise cancelled
+
+    trio.lowlevel.spawn_system_task(
+        trio_task,
+        name=async_fn,
+    )
+    return result_future
+
+
+def run_as_asyncio_guest(
     trio_main: Callable,
+    # ^-NOTE-^ when spawned with `infected_aio=True` this func is
+    # normally `Actor._async_main()` as is passed by some boostrap
+    # entrypoint like `._entry._trio_main()`.
+
+    _sigint_loop_pump_delay: float = 0,
 
 ) -> None:
+# ^-TODO-^ technically whatever `trio_main` returns.. we should
+# try to use func-typevar-params at leaast by 3.13!
+# -[ ] https://typing.readthedocs.io/en/latest/spec/callables.html#callback-protocols
+# -[ ] https://peps.python.org/pep-0646/#using-type-variable-tuples-in-functions
+# -[ ] https://typing.readthedocs.io/en/latest/spec/callables.html#unpack-for-keyword-arguments
+# -[ ] https://peps.python.org/pep-0718/
     '''
     Entry for an "infected ``asyncio`` actor".
 
@@ -507,37 +697,213 @@ def run_as_asyncio_guest(
     # :)
 
     async def aio_main(trio_main):
+        '''
+        Main `asyncio.Task` which calls
+        `trio.lowlevel.start_guest_run()` to "infect" the `asyncio`
+        event-loop by embedding the `trio` scheduler allowing us to
+        boot the `tractor` runtime and connect back to our parent.
 
+        '''
         loop = asyncio.get_running_loop()
-        trio_done_fut = asyncio.Future()
+        trio_done_fute = asyncio.Future()
+        startup_msg: str = (
+            'Starting `asyncio` guest-loop-run\n'
+            '-> got running loop\n'
+            '-> built a `trio`-done future\n'
+        )
+
+        # TODO: shoudn't this be done in the guest-run trio task?
+        # if debug_mode():
+        #     # XXX make it obvi we know this isn't supported yet!
+        #     log.error(
+        #         'Attempting to enter unsupported `greenback` init '
+        #         'from `asyncio` task..'
+        #     )
+        #     await _debug.maybe_init_greenback(
+        #         force_reload=True,
+        #     )
 
         def trio_done_callback(main_outcome):
+            log.runtime(
+                f'`trio` guest-run finishing with outcome\n'
+                f'>) {main_outcome}\n'
+                f'|_{trio_done_fute}\n'
+            )
 
             if isinstance(main_outcome, Error):
-                error = main_outcome.error
+                error: BaseException = main_outcome.error
-                trio_done_fut.set_exception(error)
 
-                # TODO: explicit asyncio tb?
+                # show an dedicated `asyncio`-side tb from the error
-                # traceback.print_exception(error)
+                tb_str: str = ''.join(traceback.format_exception(error))
-
+                log.exception(
-                # XXX: do we need this?
+                    'Guest-run errored!?\n\n'
-                # actor.cancel_soon()
+                    f'{main_outcome}\n'
+                    f'{error}\n\n'
+                    f'{tb_str}\n'
+                )
+                trio_done_fute.set_exception(error)
 
+                # raise inline
                 main_outcome.unwrap()
+
             else:
-                trio_done_fut.set_result(main_outcome)
+                trio_done_fute.set_result(main_outcome)
-                log.runtime(f"trio_main finished: {main_outcome!r}")
+
+            log.info(
+                f'`trio` guest-run finished with outcome\n'
+                f')>\n'
+                f'|_{trio_done_fute}\n'
+            )
+
+        startup_msg += (
+            f'-> created {trio_done_callback!r}\n'
+            f'-> scheduling `trio_main`: {trio_main!r}\n'
+        )
 
         # start the infection: run trio on the asyncio loop in "guest mode"
-        log.info(f"Infecting asyncio process with {trio_main}")
+        log.runtime(
+            f'{startup_msg}\n\n'
+            +
+            'Infecting `asyncio`-process with a `trio` guest-run!\n'
+        )
 
         trio.lowlevel.start_guest_run(
             trio_main,
             run_sync_soon_threadsafe=loop.call_soon_threadsafe,
             done_callback=trio_done_callback,
         )
-        # ``.unwrap()`` will raise here on error
+        fute_err: BaseException|None = None
-        return (await trio_done_fut).unwrap()
+        try:
+            out: Outcome = await asyncio.shield(trio_done_fute)
+
+            # NOTE will raise (via `Error.unwrap()`) from any
+            # exception packed into the guest-run's `main_outcome`.
+            return out.unwrap()
+
+        except (
+            # XXX special SIGINT-handling is required since
+            # `asyncio.shield()`-ing seems to NOT handle that case as
+            # per recent changes in 3.11:
+            # https://docs.python.org/3/library/asyncio-runner.html#handling-keyboard-interruption
+            #
+            # NOTE: further, apparently ONLY need to handle this
+            # special SIGINT case since all other `asyncio`-side
+            # errors can be processed via our `chan._aio_err`
+            # relaying (right?); SIGINT seems to be totally diff
+            # error path in `asyncio`'s runtime..?
+            asyncio.CancelledError,
+
+        ) as _fute_err:
+            fute_err = _fute_err
+            err_message: str = (
+                'main `asyncio` task '
+            )
+            if isinstance(fute_err, asyncio.CancelledError):
+                err_message += 'was cancelled!\n'
+            else:
+                err_message += f'errored with {out.error!r}\n'
+
+            actor: tractor.Actor = tractor.current_actor()
+            log.exception(
+                err_message
+                +
+                'Cancelling `trio`-side `tractor`-runtime..\n'
+                f'c)>\n'
+                f'  |_{actor}.cancel_soon()\n'
+            )
+
+            # XXX WARNING XXX the next LOCs are super important, since
+            # without them, we can get guest-run abandonment cases
+            # where `asyncio` will not schedule or wait on the `trio`
+            # guest-run task before final shutdown! This is
+            # particularly true if the `trio` side has tasks doing
+            # shielded work when a SIGINT condition occurs.
+            #
+            # We now have the
+            # `test_infected_asyncio.test_sigint_closes_lifetime_stack()`
+            # suite to ensure we do not suffer this issues
+            # (hopefully) ever again.
+            #
+            # The original abandonment issue surfaced as 2 different
+            # race-condition dependent types scenarios all to do with
+            # `asyncio` handling SIGINT from the system:
+            #
+            # - "silent-abandon" (WORST CASE):
+            #  `asyncio` abandons the `trio` guest-run task silently
+            #  and no `trio`-guest-run or `tractor`-actor-runtime
+            #  teardown happens whatsoever..
+            #
+            # - "loud-abandon" (BEST-ish CASE):
+            #   the guest run get's abaondoned "loudly" with `trio`
+            #   reporting a console traceback and further tbs of all
+            #   the (failed) GC-triggered shutdown routines which
+            #   thankfully does get dumped to console..
+            #
+            # The abandonment is most easily reproduced if the `trio`
+            # side has tasks doing shielded work where those tasks
+            # ignore the normal `Cancelled` condition and continue to
+            # run, but obviously `asyncio` isn't aware of this and at
+            # some point bails on the guest-run unless we take manual
+            # intervention..
+            #
+            # To repeat, *WITHOUT THIS* stuff below the guest-run can
+            # get race-conditionally abandoned!!
+            #
+            # XXX SOLUTION XXX
+            # ------ - ------
+            # XXX FIRST PART:
+            # ------ - ------
+            # the obvious fix to the "silent-abandon" case is to
+            # explicitly cancel the actor runtime such that no
+            # runtime tasks are even left unaware that the guest-run
+            # should be terminated due to OS cancellation.
+            #
+            actor.cancel_soon()
+
+            # ------ - ------
+            # XXX SECOND PART:
+            # ------ - ------
+            # Pump the `asyncio` event-loop to allow
+            # `trio`-side to `trio`-guest-run to complete and
+            # teardown !!
+            #
+            # oh `asyncio`, how i don't miss you at all XD
+            while not trio_done_fute.done():
+                log.runtime(
+                    'Waiting on main guest-run `asyncio` task to complete..\n'
+                    f'|_trio_done_fut: {trio_done_fute}\n'
+                )
+                await asyncio.sleep(_sigint_loop_pump_delay)
+
+                # XXX is there any alt API/approach like the internal
+                # call below but that doesn't block indefinitely..?
+                # loop._run_once()
+
+            try:
+                return trio_done_fute.result()
+            except asyncio.exceptions.InvalidStateError as state_err:
+
+                # XXX be super dupere noisy about abandonment issues!
+                aio_task: asyncio.Task = asyncio.current_task()
+                message: str = (
+                    'The `asyncio`-side task likely exited before the '
+                    '`trio`-side guest-run completed!\n\n'
+                )
+                if fute_err:
+                    message += (
+                        f'The main {aio_task}\n'
+                        f'STOPPED due to {type(fute_err)}\n\n'
+                    )
+
+                message += (
+                    f'Likely something inside our guest-run-as-task impl is '
+                    f'not effectively waiting on the `trio`-side to complete ?!\n'
+                    f'This code -> {aio_main!r}\n\n'
+
+                    'Below you will likely see a '
+                    '"RuntimeWarning: Trio guest run got abandoned.." !!\n'
+                )
+                raise AsyncioRuntimeTranslationError(message) from state_err
 
     # might as well if it's installed.
     try:
@@ -545,6 +911,8 @@ def run_as_asyncio_guest(
         loop = uvloop.new_event_loop()
         asyncio.set_event_loop(loop)
     except ImportError:
-        pass
+        log.runtime('`uvloop` not available..')
 
-    return asyncio.run(aio_main(trio_main))
+    return asyncio.run(
+        aio_main(trio_main),
+    )

tractor/trionics/__init__.py

@@ -19,22 +19,13 @@ Sugary patterns for trio + tractor designs.
 
 '''
 from ._mngrs import (
-    gather_contexts,
+    gather_contexts as gather_contexts,
-    maybe_open_context,
+    maybe_open_context as maybe_open_context,
-    maybe_open_nursery,
+    maybe_open_nursery as maybe_open_nursery,
 )
 from ._broadcast import (
-    broadcast_receiver,
+    AsyncReceiver as AsyncReceiver,
-    BroadcastReceiver,
+    broadcast_receiver as broadcast_receiver,
-    Lagged,
+    BroadcastReceiver as BroadcastReceiver,
+    Lagged as Lagged,
 )
-
-
-__all__ = [
-    'gather_contexts',
-    'broadcast_receiver',
-    'BroadcastReceiver',
-    'Lagged',
-    'maybe_open_context',
-    'maybe_open_nursery',
-]

tractor/trionics/_broadcast.py

@@ -25,8 +25,15 @@ from collections import deque
 from contextlib import asynccontextmanager
 from functools import partial
 from operator import ne
-from typing import Optional, Callable, Awaitable, Any, AsyncIterator, Protocol
+from typing import (
-from typing import Generic, TypeVar
+    Callable,
+    Awaitable,
+    Any,
+    AsyncIterator,
+    Protocol,
+    Generic,
+    TypeVar,
+)
 
 import trio
 from trio._core._run import Task
@@ -37,6 +44,11 @@ from tractor.log import get_logger
 
 log = get_logger(__name__)
 
+# TODO: use new type-vars syntax from 3.12
+# https://realpython.com/python312-new-features/#dedicated-type-variable-syntax
+# https://docs.python.org/3/whatsnew/3.12.html#whatsnew312-pep695
+# https://docs.python.org/3/reference/simple_stmts.html#type
+#
 # A regular invariant generic type
 T = TypeVar("T")
 
@@ -102,7 +114,7 @@ class BroadcastState(Struct):
 
     # broadcast event to wake up all sleeping consumer tasks
     # on a newly produced value from the sender.
-    recv_ready: Optional[tuple[int, trio.Event]] = None
+    recv_ready: tuple[int, trio.Event]|None = None
 
     # if a ``trio.EndOfChannel`` is received on any
     # consumer all consumers should be placed in this state
@@ -144,11 +156,12 @@ class BroadcastState(Struct):
 
 class BroadcastReceiver(ReceiveChannel):
     '''
-    A memory receive channel broadcaster which is non-lossy for the
+    A memory receive channel broadcaster which is non-lossy for
-    fastest consumer.
+    the fastest consumer.
 
-    Additional consumer tasks can receive all produced values by registering
+    Additional consumer tasks can receive all produced values by
-    with ``.subscribe()`` and receiving from the new instance it delivers.
+    registering with ``.subscribe()`` and receiving from the new
+    instance it delivers.
 
     '''
     def __init__(
@@ -156,7 +169,7 @@ class BroadcastReceiver(ReceiveChannel):
 
         rx_chan: AsyncReceiver,
         state: BroadcastState,
-        receive_afunc: Optional[Callable[[], Awaitable[Any]]] = None,
+        receive_afunc: Callable[[], Awaitable[Any]]|None = None,
         raise_on_lag: bool = True,
 
     ) -> None:
@@ -444,7 +457,7 @@ def broadcast_receiver(
 
     recv_chan: AsyncReceiver,
     max_buffer_size: int,
-    receive_afunc: Optional[Callable[[], Awaitable[Any]]] = None,
+    receive_afunc: Callable[[], Awaitable[Any]]|None = None,
     raise_on_lag: bool = True,
 
 ) -> BroadcastReceiver:

tractor/trionics/_mngrs.py

@@ -18,8 +18,12 @@
 Async context manager primitives with hard ``trio``-aware semantics
 
 '''
-from contextlib import asynccontextmanager as acm
+from __future__ import annotations
+from contextlib import (
+    asynccontextmanager as acm,
+)
 import inspect
+from types import ModuleType
 from typing import (
     Any,
     AsyncContextManager,
@@ -30,13 +34,15 @@ from typing import (
     Optional,
     Sequence,
     TypeVar,
+    TYPE_CHECKING,
 )
 
 import trio
-from trio_typing import TaskStatus
+from tractor._state import current_actor
+from tractor.log import get_logger
 
-from .._state import current_actor
+if TYPE_CHECKING:
-from ..log import get_logger
+    from tractor import ActorNursery
 
 
 log = get_logger(__name__)
@@ -47,8 +53,10 @@ T = TypeVar("T")
 
 @acm
 async def maybe_open_nursery(
-    nursery: trio.Nursery | None = None,
+    nursery: trio.Nursery|ActorNursery|None = None,
     shield: bool = False,
+    lib: ModuleType = trio,
+
 ) -> AsyncGenerator[trio.Nursery, Any]:
     '''
     Create a new nursery if None provided.
@@ -59,17 +67,17 @@ async def maybe_open_nursery(
     if nursery is not None:
         yield nursery
     else:
-        async with trio.open_nursery() as nursery:
+        async with lib.open_nursery() as nursery:
             nursery.cancel_scope.shield = shield
             yield nursery
 
 
 async def _enter_and_wait(
-
     mngr: AsyncContextManager[T],
     unwrapped: dict[int, T],
     all_entered: trio.Event,
     parent_exit: trio.Event,
+    seed: int,
 
 ) -> None:
     '''
@@ -80,7 +88,10 @@ async def _enter_and_wait(
     async with mngr as value:
         unwrapped[id(mngr)] = value
 
-        if all(unwrapped.values()):
+        if all(
+            val != seed
+            for val in unwrapped.values()
+        ):
             all_entered.set()
 
         await parent_exit.wait()
@@ -88,23 +99,34 @@ async def _enter_and_wait(
 
 @acm
 async def gather_contexts(
-
     mngrs: Sequence[AsyncContextManager[T]],
 
-) -> AsyncGenerator[tuple[Optional[T], ...], None]:
+) -> AsyncGenerator[
+    tuple[
+        T | None,
+        ...
+    ],
+    None,
+]:
     '''
-    Concurrently enter a sequence of async context managers, each in
+    Concurrently enter a sequence of async context managers (acms),
-    a separate ``trio`` task and deliver the unwrapped values in the
+    each from a separate `trio` task and deliver the unwrapped
-    same order once all managers have entered. On exit all contexts are
+    `yield`-ed values in the same order once all managers have entered.
-    subsequently and concurrently exited.
 
-    This function is somewhat similar to common usage of
+    On exit, all acms are subsequently and concurrently exited.
-    ``contextlib.AsyncExitStack.enter_async_context()`` (in a loop) in
+
-    combo with ``asyncio.gather()`` except the managers are concurrently
+    This function is somewhat similar to a batch of non-blocking
-    entered and exited, and cancellation just works.
+    calls to `contextlib.AsyncExitStack.enter_async_context()`
+    (inside a loop) *in combo with* a `asyncio.gather()` to get the
+    `.__aenter__()`-ed values, except the managers are both
+    concurrently entered and exited and *cancellation just works*(R).
 
     '''
-    unwrapped: dict[int, Optional[T]] = {}.fromkeys(id(mngr) for mngr in mngrs)
+    seed: int = id(mngrs)
+    unwrapped: dict[int, T | None] = {}.fromkeys(
+        (id(mngr) for mngr in mngrs),
+        seed,
+    )
 
     all_entered = trio.Event()
     parent_exit = trio.Event()
@@ -116,8 +138,9 @@ async def gather_contexts(
 
     if not mngrs:
         raise ValueError(
-            'input mngrs is empty?\n'
+            '`.trionics.gather_contexts()` input mngrs is empty?\n'
-            'Did try to use inline generator syntax?'
+            'Did try to use inline generator syntax?\n'
+            'Use a non-lazy iterator or sequence type intead!'
         )
 
     async with trio.open_nursery() as n:
@@ -128,6 +151,7 @@ async def gather_contexts(
                 unwrapped,
                 all_entered,
                 parent_exit,
+                seed,
             )
 
         # deliver control once all managers have started up
@@ -168,7 +192,7 @@ class _Cache:
         cls,
         mng,
         ctx_key: tuple,
-        task_status: TaskStatus[T] = trio.TASK_STATUS_IGNORED,
+        task_status: trio.TaskStatus[T] = trio.TASK_STATUS_IGNORED,
 
     ) -> None:
         async with mng as value:
@@ -195,9 +219,10 @@ async def maybe_open_context(
 
 ) -> AsyncIterator[tuple[bool, T]]:
     '''
-    Maybe open a context manager if there is not already a _Cached
+    Maybe open an async-context-manager (acm) if there is not already
-    version for the provided ``key`` for *this* actor. Return the
+    a `_Cached` version for the provided (input) `key` for *this* actor.
-    _Cached instance on a _Cache hit.
+
+    Return the `_Cached` instance on a _Cache hit.
 
     '''
     fid = id(acm_func)
@@ -209,6 +234,7 @@ async def maybe_open_context(
 
     # yielded output
     yielded: Any = None
+    lock_registered: bool = False
 
     # Lock resource acquisition around task racing  / ``trio``'s
     # scheduler protocol.
@@ -216,6 +242,7 @@ async def maybe_open_context(
     # to allow re-entrant use cases where one `maybe_open_context()`
     # wrapped factor may want to call into another.
     lock = _Cache.locks.setdefault(fid, trio.Lock())
+    lock_registered: bool = True
     await lock.acquire()
 
     # XXX: one singleton nursery per actor and we want to
@@ -237,7 +264,7 @@ async def maybe_open_context(
         yielded = _Cache.values[ctx_key]
 
     except KeyError:
-        log.info(f'Allocating new {acm_func} for {ctx_key}')
+        log.debug(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}'
@@ -254,8 +281,16 @@ async def maybe_open_context(
         yield False, yielded
 
     else:
-        log.info(f'Reusing _Cached resource for {ctx_key}')
         _Cache.users += 1
+        log.runtime(
+            f'Re-using cached resource for user {_Cache.users}\n\n'
+            f'{ctx_key!r} -> {type(yielded)}\n'
+
+            # TODO: make this work with values but without
+            # `msgspec.Struct` causing frickin crashes on field-type
+            # lookups..
+            # f'{ctx_key!r} -> {yielded!r}\n'
+        )
         lock.release()
         yield True, yielded
 
@@ -265,7 +300,7 @@ async def maybe_open_context(
         if yielded is not None:
             # if no more consumers, teardown the client
             if _Cache.users <= 0:
-                log.info(f'De-allocating resource for {ctx_key}')
+                log.debug(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.
@@ -275,4 +310,9 @@ async def maybe_open_context(
                     _, no_more_users = entry
                     no_more_users.set()
 
-                _Cache.locks.pop(fid)
+                if lock_registered:
+                    maybe_lock = _Cache.locks.pop(fid, None)
+                    if maybe_lock is None:
+                        log.error(
+                            f'Resource lock for {fid} ALREADY POPPED?'
+                        )