WIP, "revertible" or "dynamic" multicast streams

TODO, write up the deats, prolly by distilling (todo) notes from
`tests/test_resource_cache.py::test_open_local_sub_to_stream` comments!

tests/devx/test_debugger.py

@@ -317,7 +317,6 @@ def test_subactor_breakpoint(
 
     assert in_prompt_msg(
         child, [
-        'MessagingError:',
         'RemoteActorError:',
          "('breakpoint_forever'",
          'bdb.BdbQuit',

tests/devx/test_tooling.py

@@ -121,9 +121,11 @@ def test_shield_pause(
         child.pid,
         signal.SIGINT,
     )
+    from tractor._supervise import _shutdown_msg
     expect(
         child,
-        'Shutting down actor runtime',
+        # 'Shutting down actor runtime',
+        _shutdown_msg,
         timeout=6,
     )
     assert_before(

tests/test_inter_peer_cancellation.py

@@ -410,7 +410,6 @@ def test_peer_canceller(
     '''
     async def main():
         async with tractor.open_nursery(
-            # NOTE: to halt the peer tasks on ctxc, uncomment this.
             debug_mode=debug_mode,
         ) as an:
             canceller: Portal = await an.start_actor(

tests/test_resource_cache.py

@@ -72,11 +72,13 @@ def test_resource_only_entered_once(key_on):
         with trio.move_on_after(0.5):
             async with (
                 tractor.open_root_actor(),
-                trio.open_nursery() as n,
+                trio.open_nursery() as tn,
             ):
-
                 for i in range(10):
-                    n.start_soon(enter_cached_mngr, f'task_{i}')
+                    tn.start_soon(
+                        enter_cached_mngr,
+                        f'task_{i}',
+                    )
                     await trio.sleep(0.001)
 
     trio.run(main)
@@ -98,23 +100,34 @@ async def streamer(
 
 
 @acm
-async def open_stream() -> Awaitable[tractor.MsgStream]:
+async def open_stream() -> Awaitable[
-
+    tuple[
+        tractor.ActorNursery,
+        tractor.MsgStream,
+    ]
+]:
     try:
         async with tractor.open_nursery() as an:
             portal = await an.start_actor(
                 'streamer',
                 enable_modules=[__name__],
             )
-            async with (
+            try:
-                portal.open_context(streamer) as (ctx, first),
+                async with (
-                ctx.open_stream() as stream,
+                    portal.open_context(streamer) as (ctx, first),
-            ):
+                    ctx.open_stream() as stream,
-                yield stream
+                ):
+                    print('Entered open_stream() caller')
+                    yield an, stream
+                    print('Exited open_stream() caller')
 
-            print('Cancelling streamer')
+            finally:
-            await portal.cancel_actor()
+                print(
-            print('Cancelled streamer')
+                    'Cancelling streamer with,\n'
+                    '=> `Portal.cancel_actor()`'
+                )
+                await portal.cancel_actor()
+                print('Cancelled streamer')
 
     except Exception as err:
         print(
@@ -130,8 +143,12 @@ async def maybe_open_stream(taskname: str):
     async with tractor.trionics.maybe_open_context(
         # NOTE: all secondary tasks should cache hit on the same key
         acm_func=open_stream,
-    ) as (cache_hit, stream):
+    ) as (
-
+        cache_hit,
+        (an, stream)
+    ):
+        # when the actor + portal + ctx + stream has already been
+        # allocated we want to just bcast to this task.
         if cache_hit:
             print(f'{taskname} loaded from cache')
 
@@ -139,10 +156,43 @@ async def maybe_open_stream(taskname: str):
             # if this feed is already allocated by the first
             # task that entereed
             async with stream.subscribe() as bstream:
-                yield bstream
+                yield an, bstream
+                print(
+                    f'cached task exited\n'
+                    f')>\n'
+                    f' |_{taskname}\n'
+                )
+
+            # we should always unreg the "cloned" bcrc for this
+            # consumer-task
+            assert id(bstream) not in bstream._state.subs
+
         else:
             # yield the actual stream
-            yield stream
+            try:
+                yield an, stream
+            finally:
+                print(
+                    f'NON-cached task exited\n'
+                    f')>\n'
+                    f' |_{taskname}\n'
+                )
+
+        first_bstream = stream._broadcaster
+        bcrx_state = first_bstream._state
+        subs: dict[int, int] = bcrx_state.subs
+        if len(subs) == 1:
+            assert id(first_bstream) in subs
+            # ^^TODO! the bcrx should always de-allocate all subs,
+            # including the implicit first one allocated on entry
+            # by the first subscribing peer task, no?
+            #
+            # -[ ] adjust `MsgStream.subscribe()` to do this mgmt!
+            #  |_ allows reverting `MsgStream.receive()` to the
+            #    non-bcaster method.
+            #  |_ we can decide whether to reset `._broadcaster`?
+            #
+            # await tractor.pause(shield=True)
 
 
 def test_open_local_sub_to_stream(
@@ -159,16 +209,24 @@ def test_open_local_sub_to_stream(
 
     if debug_mode:
         timeout = 999
+        print(f'IN debug_mode, setting large timeout={timeout!r}..')
 
     async def main():
 
         full = list(range(1000))
+        an: tractor.ActorNursery|None = None
+        num_tasks: int = 10
 
         async def get_sub_and_pull(taskname: str):
 
+            nonlocal an
+
             stream: tractor.MsgStream
             async with (
-                maybe_open_stream(taskname) as stream,
+                maybe_open_stream(taskname) as (
+                    an,
+                    stream,
+                ),
             ):
                 if '0' in taskname:
                     assert isinstance(stream, tractor.MsgStream)
@@ -180,34 +238,70 @@ def test_open_local_sub_to_stream(
 
                 first = await stream.receive()
                 print(f'{taskname} started with value {first}')
-                seq = []
+                seq: list[int] = []
                 async for msg in stream:
                     seq.append(msg)
 
                 assert set(seq).issubset(set(full))
+
+            # end of @acm block
             print(f'{taskname} finished')
 
+        root: tractor.Actor
         with trio.fail_after(timeout) as cs:
             # TODO: turns out this isn't multi-task entrant XD
             # We probably need an indepotent entry semantic?
             async with tractor.open_root_actor(
                 debug_mode=debug_mode,
-            ):
+                # maybe_enable_greenback=True,
+                #
+                # ^TODO? doesn't seem to mk breakpoint() usage work
+                # bc each bg task needs to open a portal??
+                # - [ ] we should consider making this part of
+                #      our taskman defaults?
+                #   |_see https://github.com/goodboy/tractor/pull/363
+                #
+            ) as root:
+                assert root.is_registrar
+
                 async with (
                     trio.open_nursery() as tn,
                 ):
-                    for i in range(10):
+                    for i in range(num_tasks):
                         tn.start_soon(
                             get_sub_and_pull,
                             f'task_{i}',
                         )
                         await trio.sleep(0.001)
 
-                print('all consumer tasks finished')
+                print('all consumer tasks finished!')
+
+                # ?XXX, ensure actor-nursery is shutdown or we might
+                # hang here due to a minor task deadlock/race-condition?
+                #
+                # - seems that all we need is a checkpoint to ensure
+                #   the last suspended task, which is inside
+                #   `.maybe_open_context()`, can do the
+                #   `Portal.cancel_actor()` call?
+                #
+                # - if that bg task isn't resumed, then this blocks
+                #   timeout might hit before that?
+                #
+                if root.ipc_server.has_peers():
+                    await trio.lowlevel.checkpoint()
+
+                    # alt approach, cancel the entire `an`
+                    # await tractor.pause()
+                    # await an.cancel()
+
+            # end of runtime scope
+            print('root actor terminated.')
 
         if cs.cancelled_caught:
             pytest.fail(
                 'Should NOT time out in `open_root_actor()` ?'
             )
 
+        print('exiting main.')
+
     trio.run(main)

tests/test_task_broadcasting.py

@@ -67,7 +67,6 @@ async def ensure_sequence(
 
 @acm
 async def open_sequence_streamer(
-
     sequence: list[int],
     reg_addr: tuple[str, int],
     start_method: str,
@@ -96,39 +95,43 @@ async def open_sequence_streamer(
 
 
 def test_stream_fan_out_to_local_subscriptions(
-    reg_addr,
+    debug_mode: bool,
+    reg_addr: tuple,
     start_method,
 ):
 
     sequence = list(range(1000))
 
     async def main():
+        with trio.fail_after(9):
+            async with open_sequence_streamer(
+                sequence,
+                reg_addr,
+                start_method,
+            ) as stream:
 
-        async with open_sequence_streamer(
+                async with (
-            sequence,
+                    collapse_eg(),
-            reg_addr,
+                    trio.open_nursery() as tn,
-            start_method,
+                ):
-        ) as stream:
+                    for i in range(10):
+                        tn.start_soon(
+                            ensure_sequence,
+                            stream,
+                            sequence.copy(),
+                            name=f'consumer_{i}',
+                        )
 
-            async with trio.open_nursery() as n:
+                    await stream.send(tuple(sequence))
-                for i in range(10):
-                    n.start_soon(
-                        ensure_sequence,
-                        stream,
-                        sequence.copy(),
-                        name=f'consumer_{i}',
-                    )
 
-                await stream.send(tuple(sequence))
+                    async for value in stream:
+                        print(f'source stream rx: {value}')
+                        assert value == sequence[0]
+                        sequence.remove(value)
 
-                async for value in stream:
+                        if not sequence:
-                    print(f'source stream rx: {value}')
+                            # fully consumed
-                    assert value == sequence[0]
+                            break
-                    sequence.remove(value)
-
-                    if not sequence:
-                        # fully consumed
-                        break
 
     trio.run(main)
 
@@ -151,67 +154,69 @@ def test_consumer_and_parent_maybe_lag(
         sequence = list(range(300))
         parent_delay, sub_delay = task_delays
 
-        async with open_sequence_streamer(
+        # TODO, maybe mak a cm-deco for main()s?
-            sequence,
+        with trio.fail_after(3):
-            reg_addr,
+            async with open_sequence_streamer(
-            start_method,
+                sequence,
-        ) as stream:
+                reg_addr,
+                start_method,
+            ) as stream:
 
-            try:
+                try:
-                async with (
+                    async with (
-                    collapse_eg(),
+                        collapse_eg(),
-                    trio.open_nursery() as tn,
+                        trio.open_nursery() as tn,
-                ):
+                    ):
 
-                    tn.start_soon(
+                        tn.start_soon(
-                        ensure_sequence,
+                            ensure_sequence,
-                        stream,
+                            stream,
-                        sequence.copy(),
+                            sequence.copy(),
-                        sub_delay,
+                            sub_delay,
-                        name='consumer_task',
+                            name='consumer_task',
-                    )
+                        )
 
-                    await stream.send(tuple(sequence))
+                        await stream.send(tuple(sequence))
 
-                    # async for value in stream:
+                        # async for value in stream:
-                    lagged = False
+                        lagged = False
-                    lag_count = 0
+                        lag_count = 0
 
-                    while True:
+                        while True:
-                        try:
+                            try:
-                            value = await stream.receive()
+                                value = await stream.receive()
-                            print(f'source stream rx: {value}')
+                                print(f'source stream rx: {value}')
 
-                            if lagged:
+                                if lagged:
-                                # re set the sequence starting at our last
+                                    # re set the sequence starting at our last
-                                # value
+                                    # value
-                                sequence = sequence[sequence.index(value) + 1:]
+                                    sequence = sequence[sequence.index(value) + 1:]
-                            else:
+                                else:
-                                assert value == sequence[0]
+                                    assert value == sequence[0]
-                                sequence.remove(value)
+                                    sequence.remove(value)
 
-                            lagged = False
+                                lagged = False
 
-                        except Lagged:
+                            except Lagged:
-                            lagged = True
+                                lagged = True
-                            print(f'source stream lagged after {value}')
+                                print(f'source stream lagged after {value}')
-                            lag_count += 1
+                                lag_count += 1
-                            continue
+                                continue
 
-                        # lag the parent
+                            # lag the parent
-                        await trio.sleep(parent_delay)
+                            await trio.sleep(parent_delay)
 
-                        if not sequence:
+                            if not sequence:
-                            # fully consumed
+                                # fully consumed
-                            break
+                                break
-                    print(f'parent + source stream lagged: {lag_count}')
+                        print(f'parent + source stream lagged: {lag_count}')
 
-                    if parent_delay > sub_delay:
+                        if parent_delay > sub_delay:
-                        assert lag_count > 0
+                            assert lag_count > 0
 
-            except Lagged:
+                except Lagged:
-                # child was lagged
+                    # child was lagged
-                assert parent_delay < sub_delay
+                    assert parent_delay < sub_delay
 
     trio.run(main)
 
@@ -285,7 +290,11 @@ def test_faster_task_to_recv_is_cancelled_by_slower(
 
 
 def test_subscribe_errors_after_close():
+    '''
+    Verify after calling `BroadcastReceiver.aclose()` you can't
+    "re-open" it via `.subscribe()`.
 
+    '''
     async def main():
 
         size = 1
@@ -293,6 +302,8 @@ def test_subscribe_errors_after_close():
         async with broadcast_receiver(rx, size) as brx:
             pass
 
+        assert brx.key not in brx._state.subs
+
         try:
             # open and close
             async with brx.subscribe():
@@ -302,7 +313,7 @@ def test_subscribe_errors_after_close():
             assert brx.key not in brx._state.subs
 
         else:
-            assert 0
+            pytest.fail('brx.subscribe() never raised!?')
 
     trio.run(main)
 

tractor/_context.py

@@ -101,6 +101,9 @@ from ._state import (
     debug_mode,
     _ctxvar_Context,
 )
+from .trionics import (
+    collapse_eg,
+)
 # ------ - ------
 if TYPE_CHECKING:
     from ._portal import Portal
@@ -740,6 +743,8 @@ class Context:
             # cancelled, NOT their reported canceller. IOW in the
             # latter case we're cancelled by someone else getting
             # cancelled.
+            #
+            # !TODO, switching to `Actor.aid` here!
             if (canc := error.canceller) == self._actor.uid:
                 whom: str = 'us'
                 self._canceller = canc
@@ -940,7 +945,7 @@ class Context:
         self.cancel_called = True
 
         header: str = (
-            f'Cancelling ctx from {side.upper()}-side\n'
+            f'Cancelling ctx from {side!r}-side\n'
         )
         reminfo: str = (
             # ' =>\n'
@@ -948,7 +953,7 @@ class Context:
             f'\n'
             f'c)=> {self.chan.uid}\n'
             f'   |_[{self.dst_maddr}\n'
-            f'     >>{self.repr_rpc}\n'
+            f'     >> {self.repr_rpc}\n'
             # f'    >> {self._nsf}() -> {codec}[dict]:\n\n'
             # TODO: pull msg-type from spec re #320
         )
@@ -2023,10 +2028,8 @@ async def open_context_from_portal(
     ctxc_from_callee: ContextCancelled|None = None
     try:
         async with (
-            trio.open_nursery(
+            collapse_eg(),
-                strict_exception_groups=False,
+            trio.open_nursery() as tn,
-            ) as tn,
-
             msgops.maybe_limit_plds(
                 ctx=ctx,
                 spec=ctx_meta.get('pld_spec'),

tractor/_discovery.py

@@ -28,7 +28,10 @@ from typing import (
 from contextlib import asynccontextmanager as acm
 
 from tractor.log import get_logger
-from .trionics import gather_contexts
+from .trionics import (
+    gather_contexts,
+    collapse_eg,
+)
 from .ipc import _connect_chan, Channel
 from ._addr import (
     UnwrappedAddress,
@@ -87,7 +90,6 @@ async def get_registry(
             yield regstr_ptl
 
 
-
 @acm
 async def get_root(
     **kwargs,
@@ -253,9 +255,12 @@ async def find_actor(
         for addr in registry_addrs
     )
     portals: list[Portal]
-    async with gather_contexts(
+    async with (
-        mngrs=maybe_portals,
+        collapse_eg(),
-    ) as portals:
+        gather_contexts(
+            mngrs=maybe_portals,
+        ) as portals,
+    ):
         # log.runtime(
         #     'Gathered portals:\n'
         #     f'{portals}'

tractor/_entry.py

@@ -21,7 +21,7 @@ Sub-process entry points.
 from __future__ import annotations
 from functools import partial
 import multiprocessing as mp
-import os
+# import os
 from typing import (
     Any,
     TYPE_CHECKING,
@@ -38,6 +38,7 @@ from .devx import (
     _frame_stack,
     pformat,
 )
+# from .msg import pretty_struct
 from .to_asyncio import run_as_asyncio_guest
 from ._addr import UnwrappedAddress
 from ._runtime import (
@@ -127,20 +128,13 @@ def _trio_main(
 
     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'
+            f'Starting `trio` subactor from parent @ '
+            f'{parent_addr}\n'
             +
             pformat.nest_from_op(
                 input_op='>(',  # see syntax ideas above
-                text=actor_info,
+                text=f'{actor}',
-                nest_indent=2,  # since "complete"
             )
         )
     logmeth = log.info
@@ -149,7 +143,7 @@ def _trio_main(
         +
         pformat.nest_from_op(
             input_op=')>',  # like a "closed-to-play"-icon from super perspective
-            text=actor_info,
+            text=f'{actor}',
             nest_indent=1,
         )
     )
@@ -167,7 +161,7 @@ def _trio_main(
             +
             pformat.nest_from_op(
                 input_op='c)>',  # closed due to cancel (see above)
-                text=actor_info,
+                text=f'{actor}',
             )
         )
     except BaseException as err:
@@ -177,7 +171,7 @@ def _trio_main(
             +
             pformat.nest_from_op(
                 input_op='x)>',  # closed by error
-                text=actor_info,
+                text=f'{actor}',
             )
         )
         # NOTE since we raise a tb will already be shown on the

tractor/_portal.py

@@ -39,7 +39,10 @@ import warnings
 
 import trio
 
-from .trionics import maybe_open_nursery
+from .trionics import (
+    maybe_open_nursery,
+    collapse_eg,
+)
 from ._state import (
     current_actor,
 )
@@ -115,6 +118,10 @@ class Portal:
 
     @property
     def chan(self) -> Channel:
+        '''
+        Ref to this ctx's underlying `tractor.ipc.Channel`.
+
+        '''
         return self._chan
 
     @property
@@ -174,10 +181,17 @@ class Portal:
 
         # not expecting a "main" result
         if self._expect_result_ctx is None:
+            peer_id: str = f'{self.channel.aid.reprol()!r}'
             log.warning(
-                f"Portal for {self.channel.aid} not expecting a final"
+                f'Portal to peer {peer_id} will not deliver a final result?\n'
-                " result?\nresult() should only be called if subactor"
+                f'\n'
-                " was spawned with `ActorNursery.run_in_actor()`")
+                f'Context.result() can only be called by the parent of '
+                f'a sub-actor when it was spawned with '
+                f'`ActorNursery.run_in_actor()`'
+                f'\n'
+                f'Further this `ActorNursery`-method-API will deprecated in the'
+                f'near fututre!\n'
+            )
             return NoResult
 
         # expecting a "main" result
@@ -210,6 +224,7 @@ class Portal:
         typname: str = type(self).__name__
         log.warning(
             f'`{typname}.result()` is DEPRECATED!\n'
+            f'\n'
             f'Use `{typname}.wait_for_result()` instead!\n'
         )
         return await self.wait_for_result(
@@ -221,8 +236,10 @@ class Portal:
         # terminate all locally running async generator
         # IPC calls
         if self._streams:
-            log.cancel(
+            peer_id: str = f'{self.channel.aid.reprol()!r}'
-                f"Cancelling all streams with {self.channel.aid}")
+            report: str = (
+                f'Cancelling all msg-streams with {peer_id}\n'
+            )
             for stream in self._streams.copy():
                 try:
                     await stream.aclose()
@@ -231,10 +248,18 @@ class Portal:
                     # (unless of course at some point down the road we
                     # won't expect this to always be the case or need to
                     # detect it for respawning purposes?)
-                    log.debug(f"{stream} was already closed.")
+                    report += (
+                        f'->) {stream!r} already closed\n'
+                    )
+
+            log.cancel(report)
 
     async def aclose(self):
-        log.debug(f"Closing {self}")
+        log.debug(
+            f'Closing portal\n'
+            f'>}}\n'
+            f'|_{self}\n'
+        )
         # TODO: once we move to implementing our own `ReceiveChannel`
         # (including remote task cancellation inside its `.aclose()`)
         # we'll need to .aclose all those channels here
@@ -260,23 +285,22 @@ class Portal:
         __runtimeframe__: int = 1  # noqa
 
         chan: Channel = self.channel
+        peer_id: str = f'{self.channel.aid.reprol()!r}'
         if not chan.connected():
             log.runtime(
-                'This channel is already closed, skipping cancel request..'
+                'Peer {peer_id} is already disconnected\n'
+                '-> skipping cancel request..\n'
             )
             return False
 
-        reminfo: str = (
-            f'c)=> {self.channel.aid}\n'
-            f'  |_{chan}\n'
-        )
         log.cancel(
-            f'Requesting actor-runtime cancel for peer\n\n'
+            f'Sending actor-runtime-cancel-req to peer\n'
-            f'{reminfo}'
+            f'\n'
+            f'c)=> {peer_id}\n'
         )
 
         # XXX the one spot we set it?
-        self.channel._cancel_called: bool = True
+        chan._cancel_called: bool = True
         try:
             # send cancel cmd - might not get response
             # XXX: sure would be nice to make this work with
@@ -297,8 +321,9 @@ class Portal:
                 # 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'May have failed to cancel peer?\n'
-                    f'{reminfo}'
+                    f'\n'
+                    f'c)=?> {peer_id}\n'
                 )
 
             # if we get here some weird cancellation case happened
@@ -316,22 +341,22 @@ class Portal:
 
             TransportClosed,
         ) as tpt_err:
-            report: str = (
+            ipc_borked_report: str = (
-                f'IPC chan for actor already closed or broken?\n\n'
+                f'IPC for actor already closed/broken?\n\n'
-                f'{self.channel.aid}\n'
+                f'\n'
-                f' |_{self.channel}\n'
+                f'c)=x> {peer_id}\n'
             )
             match tpt_err:
                 case TransportClosed():
-                    log.debug(report)
+                    log.debug(ipc_borked_report)
                 case _:
-                    report += (
+                    ipc_borked_report += (
                         f'\n'
                         f'Unhandled low-level transport-closed/error during\n'
                         f'Portal.cancel_actor()` request?\n'
                         f'<{type(tpt_err).__name__}( {tpt_err} )>\n'
                     )
-                    log.warning(report)
+                    log.warning(ipc_borked_report)
 
             return False
 
@@ -488,10 +513,13 @@ class Portal:
                 with trio.CancelScope(shield=True):
                     await ctx.cancel()
 
-            except trio.ClosedResourceError:
+            except trio.ClosedResourceError as cre:
                 # if the far end terminates before we send a cancel the
                 # underlying transport-channel may already be closed.
-                log.cancel(f'Context {ctx} was already closed?')
+                log.cancel(
+                    f'Context.cancel() -> {cre!r}\n'
+                    f'cid: {ctx.cid!r} already closed?\n'
+                )
 
             # XXX: should this always be done?
             # await recv_chan.aclose()
@@ -558,14 +586,13 @@ async def open_portal(
     assert actor
     was_connected: bool = False
 
-    async with maybe_open_nursery(
+    async with (
-        tn,
+        collapse_eg(),
-        shield=shield,
+        maybe_open_nursery(
-        strict_exception_groups=False,
+            tn,
-        # ^XXX^ TODO? soo roll our own then ??
+            shield=shield,
-        # -> since we kinda want the "if only one `.exception` then
+        ) as tn,
-        # just raise that" interface?
+    ):
-    ) as tn:
 
         if not channel.connected():
             await channel.connect()

tractor/_root.py

@@ -37,16 +37,11 @@ import warnings
 
 import trio
 
-from ._runtime import (
+from . import _runtime
-    Actor,
-    Arbiter,
-    # TODO: rename and make a non-actor subtype?
-    # Arbiter as Registry,
-    async_main,
-)
 from .devx import (
     debug,
     _frame_stack,
+    pformat as _pformat,
 )
 from . import _spawn
 from . import _state
@@ -63,6 +58,7 @@ from ._addr import (
 )
 from .trionics import (
     is_multi_cancelled,
+    collapse_eg,
 )
 from ._exceptions import (
     RuntimeFailure,
@@ -101,7 +97,7 @@ async def maybe_block_bp(
     ):
         logger.info(
             f'Found `greenback` installed @ {maybe_mod}\n'
-            'Enabling `tractor.pause_from_sync()` support!\n'
+            f'Enabling `tractor.pause_from_sync()` support!\n'
         )
         os.environ['PYTHONBREAKPOINT'] = (
             'tractor.devx.debug._sync_pause_from_builtin'
@@ -196,13 +192,19 @@ async def open_root_actor(
     # read-only state to sublayers?
     # extra_rt_vars: dict|None = None,
 
-) -> Actor:
+) -> _runtime.Actor:
     '''
-    Runtime init entry point for ``tractor``.
+    Initialize the `tractor` runtime by starting a "root actor" in
+    a parent-most Python process.
+
+    All (disjoint) actor-process-trees-as-programs are created via
+    this entrypoint.
 
     '''
     # XXX NEVER allow nested actor-trees!
-    if already_actor := _state.current_actor(err_on_no_runtime=False):
+    if already_actor := _state.current_actor(
+        err_on_no_runtime=False,
+    ):
         rtvs: dict[str, Any] = _state._runtime_vars
         root_mailbox: list[str, int] = rtvs['_root_mailbox']
         registry_addrs: list[list[str, int]] = rtvs['_registry_addrs']
@@ -272,14 +274,20 @@ async def open_root_actor(
                 DeprecationWarning,
                 stacklevel=2,
             )
-            registry_addrs = [arbiter_addr]
+            uw_reg_addrs = [arbiter_addr]
 
-        if not registry_addrs:
+        uw_reg_addrs = registry_addrs
-            registry_addrs: list[UnwrappedAddress] = default_lo_addrs(
+        if not uw_reg_addrs:
+            uw_reg_addrs: list[UnwrappedAddress] = default_lo_addrs(
                 enable_transports
             )
 
-        assert registry_addrs
+        # must exist by now since all below code is dependent
+        assert uw_reg_addrs
+        registry_addrs: list[Address] = [
+            wrap_address(uw_addr)
+            for uw_addr in uw_reg_addrs
+        ]
 
         loglevel = (
             loglevel
@@ -328,10 +336,10 @@ async def open_root_actor(
             enable_stack_on_sig()
 
         # closed into below ping task-func
-        ponged_addrs: list[UnwrappedAddress] = []
+        ponged_addrs: list[Address] = []
 
         async def ping_tpt_socket(
-            addr: UnwrappedAddress,
+            addr: Address,
             timeout: float = 1,
         ) -> None:
             '''
@@ -351,17 +359,22 @@ async def open_root_actor(
                 # be better to eventually have a "discovery" protocol
                 # with basic handshake instead?
                 with trio.move_on_after(timeout):
-                    async with _connect_chan(addr):
+                    async with _connect_chan(addr.unwrap()):
                         ponged_addrs.append(addr)
 
             except OSError:
-                # TODO: make this a "discovery" log level?
+                # ?TODO, make this a "discovery" log level?
                 logger.info(
-                    f'No actor registry found @ {addr}\n'
+                    f'No root-actor registry found @ {addr!r}\n'
                 )
 
+        # !TODO, this is basically just another (abstract)
+        # happy-eyeballs, so we should try for formalize it somewhere
+        # in a `.[_]discovery` ya?
+        #
         async with trio.open_nursery() as tn:
-            for addr in registry_addrs:
+            for uw_addr in uw_reg_addrs:
+                addr: Address = wrap_address(uw_addr)
                 tn.start_soon(
                     ping_tpt_socket,
                     addr,
@@ -383,31 +396,35 @@ async def open_root_actor(
                 f'Registry(s) seem(s) to exist @ {ponged_addrs}'
             )
 
-            actor = Actor(
+            actor = _runtime.Actor(
                 name=name or 'anonymous',
                 uuid=mk_uuid(),
                 registry_addrs=ponged_addrs,
                 loglevel=loglevel,
                 enable_modules=enable_modules,
             )
-            # DO NOT use the registry_addrs as the transport server
+            # **DO NOT** use the registry_addrs as the
-            # addrs for this new non-registar, root-actor.
+            # ipc-transport-server's bind-addrs as this is
+            # a new NON-registrar, ROOT-actor.
+            #
+            # XXX INSTEAD, bind random addrs using the same tpt
+            # proto.
             for addr in ponged_addrs:
-                waddr: Address = wrap_address(addr)
                 trans_bind_addrs.append(
-                    waddr.get_random(bindspace=waddr.bindspace)
+                    addr.get_random(
+                        bindspace=addr.bindspace,
+                    )
                 )
 
         # 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:
-
             # NOTE that if the current actor IS THE REGISTAR, the
             # following init steps are taken:
             # - the tranport layer server is bound to each addr
             #   pair defined in provided registry_addrs, or the default.
-            trans_bind_addrs = registry_addrs
+            trans_bind_addrs = uw_reg_addrs
 
             # - it is normally desirable for any registrar to stay up
             #   indefinitely until either all registered (child/sub)
@@ -418,7 +435,8 @@ async def open_root_actor(
             # https://github.com/goodboy/tractor/pull/348
             # https://github.com/goodboy/tractor/issues/296
 
-            actor = Arbiter(
+            # TODO: rename as `RootActor` or is that even necessary?
+            actor = _runtime.Arbiter(
                 name=name or 'registrar',
                 uuid=mk_uuid(),
                 registry_addrs=registry_addrs,
@@ -430,6 +448,16 @@ async def open_root_actor(
             # `.trio.run()`.
             actor._infected_aio = _state._runtime_vars['_is_infected_aio']
 
+        # NOTE, only set the loopback addr for the
+        # process-tree-global "root" mailbox since all sub-actors
+        # should be able to speak to their root actor over that
+        # channel.
+        raddrs: list[Address] = _state._runtime_vars['_root_addrs']
+        raddrs.extend(trans_bind_addrs)
+        # TODO, remove once we have also removed all usage;
+        # eventually all (root-)registry apis should expect > 1 addr.
+        _state._runtime_vars['_root_mailbox'] = raddrs[0]
+
         # Start up main task set via core actor-runtime nurseries.
         try:
             # assign process-local actor
@@ -437,21 +465,27 @@ async def open_root_actor(
 
             # start local channel-server and fake the portal API
             # NOTE: this won't block since we provide the nursery
-            ml_addrs_str: str = '\n'.join(
+            report: str = f'Starting actor-runtime for {actor.aid.reprol()!r}\n'
-                f'@{addr}' for addr in trans_bind_addrs
+            if reg_addrs := actor.registry_addrs:
-            )
+                report += (
-            logger.info(
+                    '-> Opening new registry @ '
-                f'Starting local {actor.uid} on the following transport addrs:\n'
+                    +
-                f'{ml_addrs_str}'
+                    '\n'.join(
-            )
+                        f'{addr}' for addr in reg_addrs
+                    )
+                )
+            logger.info(f'{report}\n')
 
-            # start the actor runtime in a new task
+            # start runtime in a bg sub-task, yield to caller.
-            async with trio.open_nursery(
+            async with (
-                strict_exception_groups=False,
+                collapse_eg(),
-                # ^XXX^ TODO? instead unpack any RAE as per "loose" style?
+                trio.open_nursery() as root_tn,
-            ) as nursery:
 
-                # ``_runtime.async_main()`` creates an internal nursery
+                # XXX, finally-footgun below?
+                # -> see note on why shielding.
+                # maybe_raise_from_masking_exc(),
+            ):
+                # `_runtime.async_main()` creates an internal nursery
                 # and blocks here until any underlying actor(-process)
                 # tree has terminated thereby conducting so called
                 # "end-to-end" structured concurrency throughout an
@@ -459,9 +493,9 @@ async def open_root_actor(
                 # "actor runtime" primitives are SC-compat and thus all
                 # transitively spawned actors/processes must be as
                 # well.
-                await nursery.start(
+                await root_tn.start(
                     partial(
-                        async_main,
+                        _runtime.async_main,
                         actor,
                         accept_addrs=trans_bind_addrs,
                         parent_addr=None
@@ -509,7 +543,7 @@ async def open_root_actor(
                     raise
 
                 finally:
-                    # NOTE: not sure if we'll ever need this but it's
+                    # NOTE/TODO?, not sure if we'll ever need this but it's
                     # possibly better for even more determinism?
                     # logger.cancel(
                     #     f'Waiting on {len(nurseries)} nurseries in root..')
@@ -518,12 +552,21 @@ async def open_root_actor(
                     #     for an in nurseries:
                     #         tempn.start_soon(an.exited.wait)
 
+                    op_nested_actor_repr: str = _pformat.nest_from_op(
+                        input_op='>) ',
+                        text=actor.pformat(),
+                        nest_prefix='|_',
+                    )
                     logger.info(
                         f'Closing down root actor\n'
-                        f'>)\n'
+                        f'{op_nested_actor_repr}'
-                        f'|_{actor}\n'
                     )
-                    await actor.cancel(None)  # self cancel
+                    # XXX, THIS IS A *finally-footgun*!
+                    # -> though already shields iternally it can
+                    # taskc here and mask underlying errors raised in
+                    # the try-block above?
+                    with trio.CancelScope(shield=True):
+                        await actor.cancel(None)  # self cancel
         finally:
             # revert all process-global runtime state
             if (
@@ -536,10 +579,16 @@ async def open_root_actor(
             _state._current_actor = None
             _state._last_actor_terminated = actor
 
-            logger.runtime(
+            sclang_repr: str = _pformat.nest_from_op(
+                input_op=')>',
+                text=actor.pformat(),
+                nest_prefix='|_',
+                nest_indent=1,
+            )
+
+            logger.info(
                 f'Root actor terminated\n'
-                f')>\n'
+                f'{sclang_repr}'
-                f' |_{actor}\n'
             )
 
 

tractor/_rpc.py

@@ -64,6 +64,7 @@ from .trionics import (
 from .devx import (
     debug,
     add_div,
+    pformat as _pformat,
 )
 from . import _state
 from .log import get_logger
@@ -72,7 +73,7 @@ from .msg import (
     MsgCodec,
     PayloadT,
     NamespacePath,
-    # pretty_struct,
+    pretty_struct,
     _ops as msgops,
 )
 from tractor.msg.types import (
@@ -220,11 +221,18 @@ async def _invoke_non_context(
             task_status.started(ctx)
             result = await coro
             fname: str = func.__name__
+
+            op_nested_task: str = _pformat.nest_from_op(
+                input_op=f')> cid: {ctx.cid!r}',
+                text=f'{ctx._task}',
+                nest_indent=1,  # under >
+            )
             log.runtime(
-                'RPC complete:\n'
+                f'RPC task complete\n'
-                f'task: {ctx._task}\n'
+                f'\n'
-                f'|_cid={ctx.cid}\n'
+                f'{op_nested_task}\n'
-                f'|_{fname}() -> {pformat(result)}\n'
+                f'\n'
+                f')> {fname}() -> {pformat(result)}\n'
             )
 
             # NOTE: only send result if we know IPC isn't down
@@ -664,7 +672,8 @@ async def _invoke(
                 ctx._result = res
                 log.runtime(
                     f'Sending result msg and exiting {ctx.side!r}\n'
-                    f'{return_msg}\n'
+                    f'\n'
+                    f'{pretty_struct.pformat(return_msg)}\n'
                 )
                 await chan.send(return_msg)
 
@@ -756,7 +765,6 @@ async def _invoke(
             BaseExceptionGroup,
             BaseException,
             trio.Cancelled,
-
         ) as _scope_err:
             scope_err = _scope_err
             if (
@@ -832,12 +840,12 @@ async def _invoke(
                 else:
                     descr_str += f'\n{merr!r}\n'
             else:
-                descr_str += f'\nand final result {ctx.outcome!r}\n'
+                descr_str += f'\nwith final result {ctx.outcome!r}\n'
 
             logmeth(
-                message
+                f'{message}\n'
-                +
+                f'\n'
-                descr_str
+                f'{descr_str}\n'
             )
 
 
@@ -1004,8 +1012,6 @@ async def process_messages(
                         cid=cid,
                         kwargs=kwargs,
                     ):
-                        kwargs |= {'req_chan': chan}
-
                         # XXX NOTE XXX don't start entire actor
                         # runtime cancellation if this actor is
                         # currently in debug mode!
@@ -1024,14 +1030,14 @@ async def process_messages(
                                 cid,
                                 chan,
                                 actor.cancel,
-                                kwargs,
+                                kwargs | {'req_chan': chan},
                                 is_rpc=False,
                                 return_msg_type=CancelAck,
                             )
 
                         log.runtime(
-                            'Cancelling IPC transport msg-loop with peer:\n'
+                            'Cancelling RPC-msg-loop with peer\n'
-                            f'|_{chan}\n'
+                            f'->c}} {chan.aid.reprol()}@[{chan.maddr}]\n'
                         )
                         loop_cs.cancel()
                         break
@@ -1044,7 +1050,7 @@ async def process_messages(
                     ):
                         target_cid: str = kwargs['cid']
                         kwargs |= {
-                            'requesting_uid': chan.uid,
+                            'requesting_aid': chan.aid,
                             'ipc_msg': msg,
 
                             # XXX NOTE! ONLY the rpc-task-owning
@@ -1080,21 +1086,34 @@ async def process_messages(
                         ns=ns,
                         func=funcname,
                         kwargs=kwargs,  # type-spec this? see `msg.types`
-                        uid=actorid,
+                        uid=actor_uuid,
                     ):
+                        if actor_uuid != chan.aid.uid:
+                            raise RuntimeError(
+                                f'IPC <Start> msg <-> chan.aid mismatch!?\n'
+                                f'Channel.aid = {chan.aid!r}\n'
+                                f'Start.uid = {actor_uuid!r}\n'
+                            )
+                        # await debug.pause()
+                        op_repr: str = 'Start <=) '
+                        req_repr: str = _pformat.nest_from_op(
+                            input_op=op_repr,
+                            op_suffix='',
+                            nest_prefix='',
+                            text=f'{chan}',
+
+                            nest_indent=len(op_repr)-1,
+                            rm_from_first_ln='<',
+                            # ^XXX, subtract -1 to account for
+                            # <Channel
+                            # ^_chevron to be stripped
+                        )
                         start_status: str = (
-                            'Handling RPC `Start` request\n'
+                            'Handling RPC request\n'
-                            f'<= peer: {actorid}\n\n'
+                            f'{req_repr}\n'
-                            f'  |_{chan}\n'
+                            f'\n'
-                            f'  |_cid: {cid}\n\n'
+                            f'->{{ ipc-context-id: {cid!r}\n'
-                            # f'  |_{ns}.{funcname}({kwargs})\n'
+                            f'->{{ nsp for fn: `{ns}.{funcname}({kwargs})`\n'
-                            f'>> {actor.uid}\n'
-                            f'  |_{actor}\n'
-                            f'   -> nsp: `{ns}.{funcname}({kwargs})`\n'
-
-                            # f'  |_{ns}.{funcname}({kwargs})\n\n'
-
-                            # f'{pretty_struct.pformat(msg)}\n'
                         )
 
                         # runtime-internal endpoint: `Actor.<funcname>`
@@ -1123,10 +1142,6 @@ async def process_messages(
                                 await chan.send(err_msg)
                                 continue
 
-                        start_status += (
-                            f'   -> func: {func}\n'
-                        )
-
                         # schedule a task for the requested RPC function
                         # in the actor's main "service nursery".
                         #
@@ -1134,7 +1149,7 @@ async def process_messages(
                         # supervision isolation? would avoid having to
                         # manage RPC tasks individually in `._rpc_tasks`
                         # table?
-                        start_status += '   -> scheduling new task..\n'
+                        start_status += '->( scheduling new task..\n'
                         log.runtime(start_status)
                         try:
                             ctx: Context = await actor._service_n.start(
@@ -1218,12 +1233,24 @@ async def process_messages(
             # END-OF `async for`:
             # IPC disconnected via `trio.EndOfChannel`, likely
             # due to a (graceful) `Channel.aclose()`.
+
+            chan_op_repr: str = '<=x] '
+            chan_repr: str = _pformat.nest_from_op(
+                input_op=chan_op_repr,
+                op_suffix='',
+                nest_prefix='',
+                text=chan.pformat(),
+                nest_indent=len(chan_op_repr)-1,
+                rm_from_first_ln='<',
+            )
             log.runtime(
-                f'channel for {chan.uid} disconnected, cancelling RPC tasks\n'
+                f'IPC channel disconnected\n'
-                f'|_{chan}\n'
+                f'{chan_repr}\n'
+                f'\n'
+                f'->c) cancelling RPC tasks.\n'
             )
             await actor.cancel_rpc_tasks(
-                req_uid=actor.uid,
+                req_aid=actor.aid,
                 # a "self cancel" in terms of the lifetime of the
                 # IPC connection which is presumed to be the
                 # source of any requests for spawned tasks.
@@ -1295,13 +1322,37 @@ async def process_messages(
     finally:
         # msg debugging for when he machinery is brokey
         if msg is None:
-            message: str = 'Exiting IPC msg loop without receiving a msg?'
+            message: str = 'Exiting RPC-loop without receiving a msg?'
         else:
+            task_op_repr: str = ')>'
+            task: trio.Task = trio.lowlevel.current_task()
+
+            # maybe add cancelled opt prefix
+            if task._cancel_status.effectively_cancelled:
+                task_op_repr = 'c' + task_op_repr
+
+            task_repr: str = _pformat.nest_from_op(
+                input_op=task_op_repr,
+                text=f'{task!r}',
+                nest_indent=1,
+            )
+            # chan_op_repr: str = '<=} '
+            # chan_repr: str = _pformat.nest_from_op(
+            #     input_op=chan_op_repr,
+            #     op_suffix='',
+            #     nest_prefix='',
+            #     text=chan.pformat(),
+            #     nest_indent=len(chan_op_repr)-1,
+            #     rm_from_first_ln='<',
+            # )
             message: str = (
-                'Exiting IPC msg loop with final msg\n\n'
+                f'Exiting RPC-loop with final msg\n'
-                f'<= peer: {chan.uid}\n'
+                f'\n'
-                f'  |_{chan}\n\n'
+                # f'{chan_repr}\n'
-                # f'{pretty_struct.pformat(msg)}'
+                f'{task_repr}\n'
+                f'\n'
+                f'{pretty_struct.pformat(msg)}'
+                f'\n'
             )
 
         log.runtime(message)

tractor/_runtime.py

@@ -55,6 +55,7 @@ from typing import (
     TYPE_CHECKING,
 )
 import uuid
+import textwrap
 from types import ModuleType
 import warnings
 
@@ -73,6 +74,9 @@ from tractor.msg import (
     pretty_struct,
     types as msgtypes,
 )
+from .trionics import (
+    collapse_eg,
+)
 from .ipc import (
     Channel,
     # IPCServer,  # causes cycles atm..
@@ -97,7 +101,10 @@ from ._exceptions import (
     MsgTypeError,
     unpack_error,
 )
-from .devx import debug
+from .devx import (
+    debug,
+    pformat as _pformat
+)
 from ._discovery import get_registry
 from ._portal import Portal
 from . import _state
@@ -206,7 +213,7 @@ class Actor:
         *,
         enable_modules: list[str] = [],
         loglevel: str|None = None,
-        registry_addrs: list[UnwrappedAddress]|None = None,
+        registry_addrs: list[Address]|None = None,
         spawn_method: str|None = None,
 
         # TODO: remove!
@@ -227,7 +234,7 @@ class Actor:
 
         # state
         self._cancel_complete = trio.Event()
-        self._cancel_called_by_remote: tuple[str, tuple]|None = None
+        self._cancel_called_by: tuple[str, tuple]|None = None
         self._cancel_called: bool = False
 
         # retreive and store parent `__main__` data which
@@ -249,11 +256,12 @@ class Actor:
         if arbiter_addr is not None:
             warnings.warn(
                 '`Actor(arbiter_addr=<blah>)` is now deprecated.\n'
-                'Use `registry_addrs: list[tuple]` instead.',
+                'Use `registry_addrs: list[Address]` instead.',
                 DeprecationWarning,
                 stacklevel=2,
             )
-            registry_addrs: list[UnwrappedAddress] = [arbiter_addr]
+
+            registry_addrs: list[Address] = [wrap_address(arbiter_addr)]
 
         # marked by the process spawning backend at startup
         # will be None for the parent most process started manually
@@ -292,8 +300,10 @@ class Actor:
         # input via the validator.
         self._reg_addrs: list[UnwrappedAddress] = []
         if registry_addrs:
-            self.reg_addrs: list[UnwrappedAddress] = registry_addrs
+            _state._runtime_vars['_registry_addrs'] = self.reg_addrs = [
-            _state._runtime_vars['_registry_addrs'] = registry_addrs
+                addr.unwrap()
+                for addr in registry_addrs
+            ]
 
     @property
     def aid(self) -> msgtypes.Aid:
@@ -339,46 +349,125 @@ class Actor:
     def pid(self) -> int:
         return self._aid.pid
 
-    def pformat(self) -> str:
+    @property
-        ds: str = '='
+    def repr_state(self) -> str:
-        parent_uid: tuple|None = None
+        if self.cancel_complete:
-        if rent_chan := self._parent_chan:
+            return 'cancelled'
-            parent_uid = rent_chan.uid
+
+        elif canceller := self.cancel_caller:
+                return f' and cancel-called by {canceller}'
+
+        else:
+            return 'running'
+
+    def pformat(
+        self,
+        ds: str = ': ',
+        indent: int = 0,
+        privates: bool = False,
+    ) -> str:
+
+        fmtstr: str = f'|_id: {self.aid.reprol()!r}\n'
+        if privates:
+            aid_nest_prefix: str = '|_aid='
+            aid_field_repr: str = _pformat.nest_from_op(
+                input_op='',
+                text=pretty_struct.pformat(
+                    struct=self.aid,
+                    field_indent=2,
+                ),
+                op_suffix='',
+                nest_prefix=aid_nest_prefix,
+                nest_indent=0,
+            )
+            fmtstr: str = f'{aid_field_repr}'
+
+        if rent_chan := self._parent_chan:
+            fmtstr += (
+                f"|_parent{ds}{rent_chan.aid.reprol()}\n"
+            )
 
-        peers: list = []
         server: _server.IPCServer = self.ipc_server
         if server:
-            peers: list[tuple] = list(server._peer_connected)
+            if privates:
+                server_repr: str = self._ipc_server.pformat(
+                    privates=privates,
+                )
+                # create field ln as a key-header indented under
+                # and up to the section's key prefix.
+                # ^XXX if we were to indent `repr(Server)` to
+                # '<key>: '
+                #  _here_^
+                server_repr: str = _pformat.nest_from_op(
+                    input_op='',  # nest as sub-obj
+                    op_suffix='',
+                    text=server_repr,
+                )
+                fmtstr += (
+                    f"{server_repr}"
+                )
+            else:
+                fmtstr += (
+                    f'|_ipc: {server.repr_state!r}\n'
+                )
 
-        fmtstr: str = (
+        fmtstr += (
-            f' |_id: {self.aid!r}\n'
+            f'|_rpc: {len(self._rpc_tasks)} active tasks\n'
-            # f"   aid{ds}{self.aid!r}\n"
-            f"   parent{ds}{parent_uid}\n"
-            f'\n'
-            f' |_ipc: {len(peers)!r} connected peers\n'
-            f"   peers{ds}{peers!r}\n"
-            f"   ipc_server{ds}{self._ipc_server}\n"
-            f'\n'
-            f' |_rpc: {len(self._rpc_tasks)} tasks\n'
-            f"   ctxs{ds}{len(self._contexts)}\n"
-            f'\n'
-            f' |_runtime: ._task{ds}{self._task!r}\n'
-            f'   _spawn_method{ds}{self._spawn_method}\n'
-            f'   _actoruid2nursery{ds}{self._actoruid2nursery}\n'
-            f'   _forkserver_info{ds}{self._forkserver_info}\n'
-            f'\n'
-            f' |_state: "TODO: .repr_state()"\n'
-            f'   _cancel_complete{ds}{self._cancel_complete}\n'
-            f'   _cancel_called_by_remote{ds}{self._cancel_called_by_remote}\n'
-            f'   _cancel_called{ds}{self._cancel_called}\n'
         )
-        return (
+
-            '<Actor(\n'
+        # TODO, actually fix the .repr_state impl/output?
-            +
+        # append ipc-ctx state summary
-            fmtstr
+        # ctxs: dict = self._contexts
-            +
+        # if ctxs:
-            ')>\n'
+        #     ctx_states: dict[str, int] = {}
+        #     for ctx in self._contexts.values():
+        #         ctx_state: str = ctx.repr_state
+        #         cnt = ctx_states.setdefault(ctx_state, 0)
+        #         ctx_states[ctx_state] = cnt + 1
+
+        #     fmtstr += (
+        #         f"  ctxs{ds}{ctx_states}\n"
+        #     )
+
+        # runtime-state
+        task_name: str = '<dne>'
+        if task := self._task:
+            task_name: str = task.name
+        fmtstr += (
+            # TODO, this just like ctx?
+            f'|_state: {self.repr_state!r}\n'
+            f'  task: {task_name}\n'
+            f'  loglevel: {self.loglevel!r}\n'
+            f'  subactors_spawned: {len(self._actoruid2nursery)}\n'
         )
+        if not _state.is_root_process():
+            fmtstr += f'  spawn_method: {self._spawn_method!r}\n'
+
+        if privates:
+            fmtstr += (
+                # f'  actoruid2nursery{ds}{self._actoruid2nursery}\n'
+                f'  cancel_complete{ds}{self._cancel_complete}\n'
+                f'  cancel_called_by_remote{ds}{self._cancel_called_by}\n'
+                f'  cancel_called{ds}{self._cancel_called}\n'
+            )
+
+        if fmtstr:
+            fmtstr: str = textwrap.indent(
+                text=fmtstr,
+                prefix=' '*(1 + indent),
+            )
+
+        _repr: str = (
+            f'<{type(self).__name__}(\n'
+            f'{fmtstr}'
+            f')>\n'
+        )
+        if indent:
+            _repr: str = textwrap.indent(
+                text=_repr,
+                prefix=' '*indent,
+            )
+        return _repr
 
     __repr__ = pformat
 
@@ -386,7 +475,11 @@ class Actor:
     def reg_addrs(self) -> list[UnwrappedAddress]:
         '''
         List of (socket) addresses for all known (and contactable)
-        registry actors.
+        registry-service actors in "unwrapped" (i.e. IPC interchange
+        wire-compat) form.
+
+        If you are looking for the "wrapped" address form, use
+        `.registry_addrs` instead.
 
         '''
         return self._reg_addrs
@@ -405,8 +498,14 @@ class Actor:
 
         self._reg_addrs = addrs
 
+    @property
+    def registry_addrs(self) -> list[Address]:
+        return [wrap_address(uw_addr)
+                for uw_addr in self.reg_addrs]
+
     def load_modules(
         self,
+
     ) -> None:
         '''
         Load explicitly enabled python modules from local fs after
@@ -453,6 +552,14 @@ class Actor:
             )
             raise
 
+    # ?TODO, factor this meth-iface into a new `.rpc` subsys primitive?
+    # - _get_rpc_func(),
+    # - _deliver_ctx_payload(),
+    # - get_context(),
+    # - start_remote_task(),
+    # - cancel_rpc_tasks(),
+    # - _cancel_task(),
+    #
     def _get_rpc_func(self, ns, funcname):
         '''
         Try to lookup and return a target RPC func from the
@@ -496,11 +603,11 @@ class Actor:
         queue.
 
         '''
-        uid: tuple[str, str] = chan.uid
+        aid: msgtypes.Aid = chan.aid
-        assert uid, f"`chan.uid` can't be {uid}"
+        assert aid, f"`chan.aid` can't be {aid}"
         try:
             ctx: Context = self._contexts[(
-                uid,
+                aid.uid,
                 cid,
 
                 # TODO: how to determine this tho?
@@ -511,7 +618,7 @@ class Actor:
                 'Ignoring invalid IPC msg!?\n'
                 f'Ctx seems to not/no-longer exist??\n'
                 f'\n'
-                f'<=? {uid}\n'
+                f'<=? {aid.reprol()!r}\n'
                 f'  |_{pretty_struct.pformat(msg)}\n'
             )
             match msg:
@@ -560,6 +667,7 @@ class Actor:
           msging session's lifetime.
 
         '''
+        # ?TODO, use Aid here as well?
         actor_uid = chan.uid
         assert actor_uid
         try:
@@ -908,6 +1016,22 @@ class Actor:
             None,  # self cancel all rpc tasks
         )
 
+    @property
+    def cancel_complete(self) -> bool:
+        return self._cancel_complete.is_set()
+
+    @property
+    def cancel_called(self) -> bool:
+        '''
+        Was this actor requested to cancel by a remote peer actor.
+
+        '''
+        return self._cancel_called_by is not None
+
+    @property
+    def cancel_caller(self) -> msgtypes.Aid|None:
+        return self._cancel_called_by
+
     async def cancel(
         self,
 
@@ -932,20 +1056,18 @@ class Actor:
 
         '''
         (
-            requesting_uid,
+            requesting_aid,  # Aid
-            requester_type,
+            requester_type,  # str
             req_chan,
             log_meth,
         ) = (
-            req_chan.uid,
+            req_chan.aid,
             'peer',
             req_chan,
             log.cancel,
-
         ) if req_chan else (
-
             # a self cancel of ALL rpc tasks
-            self.uid,
+            self.aid,
             'self',
             self,
             log.runtime,
@@ -953,14 +1075,14 @@ class Actor:
         # TODO: just use the new `Context.repr_rpc: str` (and
         # other) repr fields instead of doing this all manual..
         msg: str = (
-            f'Actor-runtime cancel request from {requester_type}\n\n'
+            f'Actor-runtime cancel request from {requester_type!r}\n'
-            f'<=c) {requesting_uid}\n'
-            f'  |_{self}\n'
             f'\n'
+            f'<=c)\n'
+            f'{self}'
         )
 
         # TODO: what happens here when we self-cancel tho?
-        self._cancel_called_by_remote: tuple = requesting_uid
+        self._cancel_called_by: tuple = requesting_aid
         self._cancel_called = True
 
         # cancel all ongoing rpc tasks
@@ -988,7 +1110,7 @@ class Actor:
 
             # self-cancel **all** ongoing RPC tasks
             await self.cancel_rpc_tasks(
-                req_uid=requesting_uid,
+                req_aid=requesting_aid,
                 parent_chan=None,
             )
 
@@ -1005,19 +1127,11 @@ class Actor:
         self._cancel_complete.set()
         return True
 
-    # XXX: hard kill logic if needed?
-    # def _hard_mofo_kill(self):
-    #     # If we're the root actor or zombied kill everything
-    #     if self._parent_chan is None:  # TODO: more robust check
-    #         root = trio.lowlevel.current_root_task()
-    #         for n in root.child_nurseries:
-    #             n.cancel_scope.cancel()
-
     async def _cancel_task(
         self,
         cid: str,
         parent_chan: Channel,
-        requesting_uid: tuple[str, str]|None,
+        requesting_aid: msgtypes.Aid|None,
 
         ipc_msg: dict|None|bool = False,
 
@@ -1055,7 +1169,7 @@ class Actor:
             log.runtime(
                 'Cancel request for invalid RPC task.\n'
                 'The task likely already completed or was never started!\n\n'
-                f'<= canceller: {requesting_uid}\n'
+                f'<= canceller: {requesting_aid}\n'
                 f'=> {cid}@{parent_chan.uid}\n'
                 f'  |_{parent_chan}\n'
             )
@@ -1063,9 +1177,12 @@ class Actor:
 
         log.cancel(
             'Rxed cancel request for RPC task\n'
-            f'<=c) {requesting_uid}\n'
+            f'{ctx._task!r} <=c) {requesting_aid}\n'
-            f' |_{ctx._task}\n'
+            f'|_>> {ctx.repr_rpc}\n'
-            f'    >> {ctx.repr_rpc}\n'
+
+            # f'|_{ctx._task}\n'
+            # f'   >> {ctx.repr_rpc}\n'
+
             # f'=> {ctx._task}\n'
             # f'  >> Actor._cancel_task() => {ctx._task}\n'
             # f'  |_ {ctx._task}\n\n'
@@ -1086,9 +1203,9 @@ class Actor:
         )
         if (
             ctx._canceller is None
-            and requesting_uid
+            and requesting_aid
         ):
-            ctx._canceller: tuple = requesting_uid
+            ctx._canceller: tuple = requesting_aid.uid
 
         # TODO: pack the RPC `{'cmd': <blah>}` msg into a ctxc and
         # then raise and pack it here?
@@ -1114,7 +1231,7 @@ class Actor:
 
         # wait for _invoke to mark the task complete
         flow_info: str = (
-            f'<= canceller: {requesting_uid}\n'
+            f'<= canceller: {requesting_aid}\n'
             f'=> ipc-parent: {parent_chan}\n'
             f'|_{ctx}\n'
         )
@@ -1131,7 +1248,7 @@ class Actor:
 
     async def cancel_rpc_tasks(
         self,
-        req_uid: tuple[str, str],
+        req_aid: msgtypes.Aid,
 
         # NOTE: when None is passed we cancel **all** rpc
         # tasks running in this actor!
@@ -1148,7 +1265,7 @@ class Actor:
         if not tasks:
             log.runtime(
                 'Actor has no cancellable RPC tasks?\n'
-                f'<= canceller: {req_uid}\n'
+                f'<= canceller: {req_aid.reprol()}\n'
             )
             return
 
@@ -1188,7 +1305,7 @@ class Actor:
         )
         log.cancel(
             f'Cancelling {descr} RPC tasks\n\n'
-            f'<=c) {req_uid} [canceller]\n'
+            f'<=c) {req_aid} [canceller]\n'
             f'{rent_chan_repr}'
             f'c)=> {self.uid} [cancellee]\n'
             f'  |_{self} [with {len(tasks)} tasks]\n'
@@ -1216,7 +1333,7 @@ class Actor:
             await self._cancel_task(
                 cid,
                 task_caller_chan,
-                requesting_uid=req_uid,
+                requesting_aid=req_aid,
             )
 
         if tasks:
@@ -1244,25 +1361,13 @@ class Actor:
         '''
         return self.accept_addrs[0]
 
-    def get_parent(self) -> Portal:
+    # TODO, this should delegate ONLY to the
-        '''
+    # `._spawn_spec._runtime_vars: dict` / `._state` APIs?
-        Return a `Portal` to our parent.
+    #
-
+    # XXX, AH RIGHT that's why..
-        '''
+    #   it's bc we pass this as a CLI flag to the child.py precisely
-        assert self._parent_chan, "No parent channel for this actor?"
+    #   bc we need the bootstrapping pre `async_main()`.. but maybe
-        return Portal(self._parent_chan)
+    #   keep this as an impl deat and not part of the pub iface impl?
-
-    def get_chans(
-        self,
-        uid: tuple[str, str],
-
-    ) -> list[Channel]:
-        '''
-        Return all IPC channels to the actor with provided `uid`.
-
-        '''
-        return self._peers[uid]
-
     def is_infected_aio(self) -> bool:
         '''
         If `True`, this actor is running `trio` in guest mode on
@@ -1273,6 +1378,23 @@ class Actor:
         '''
         return self._infected_aio
 
+    # ?TODO, is this the right type for this method?
+    def get_parent(self) -> Portal:
+        '''
+        Return a `Portal` to our parent.
+
+        '''
+        assert self._parent_chan, "No parent channel for this actor?"
+        return Portal(self._parent_chan)
+
+    # XXX: hard kill logic if needed?
+    # def _hard_mofo_kill(self):
+    #     # If we're the root actor or zombied kill everything
+    #     if self._parent_chan is None:  # TODO: more robust check
+    #         root = trio.lowlevel.current_root_task()
+    #         for n in root.child_nurseries:
+    #             n.cancel_scope.cancel()
+
 
 async def async_main(
     actor: Actor,
@@ -1316,6 +1438,8 @@ async def async_main(
         # establish primary connection with immediate parent
         actor._parent_chan: Channel|None = None
 
+        # is this a sub-actor?
+        # get runtime info from parent.
         if parent_addr is not None:
             (
                 actor._parent_chan,
@@ -1350,18 +1474,18 @@ async def async_main(
         # parent is kept alive as a resilient service until
         # cancellation steps have (mostly) occurred in
         # a deterministic way.
-        async with trio.open_nursery(
+        root_tn: trio.Nursery
-            strict_exception_groups=False,
+        async with (
-        ) as root_nursery:
+            collapse_eg(),
-            actor._root_n = root_nursery
+            trio.open_nursery() as root_tn,
+        ):
+            actor._root_n = root_tn
             assert actor._root_n
 
             ipc_server: _server.IPCServer
             async with (
-                trio.open_nursery(
+                collapse_eg(),
-                    strict_exception_groups=False,
+                trio.open_nursery() as service_nursery,
-                ) as service_nursery,
-
                 _server.open_ipc_server(
                     parent_tn=service_nursery,
                     stream_handler_tn=service_nursery,
@@ -1412,9 +1536,6 @@ async def async_main(
 
                 # TODO: why is this not with the root nursery?
                 try:
-                    log.runtime(
-                        'Booting IPC server'
-                    )
                     eps: list = await ipc_server.listen_on(
                         accept_addrs=accept_addrs,
                         stream_handler_nursery=service_nursery,
@@ -1446,18 +1567,6 @@ async def async_main(
                 # TODO, just read direct from ipc_server?
                 accept_addrs: list[UnwrappedAddress] = actor.accept_addrs
 
-                # NOTE: only set the loopback addr for the 
-                # process-tree-global "root" mailbox since
-                # all sub-actors should be able to speak to
-                # their root actor over that channel.
-                if _state._runtime_vars['_is_root']:
-                    raddrs: list[Address] = _state._runtime_vars['_root_addrs']
-                    for addr in accept_addrs:
-                        waddr: Address = wrap_address(addr)
-                        raddrs.append(addr)
-                    else:
-                        _state._runtime_vars['_root_mailbox'] = raddrs[0]
-
                 # Register with the arbiter if we're told its addr
                 log.runtime(
                     f'Registering `{actor.name}` => {pformat(accept_addrs)}\n'
@@ -1475,6 +1584,7 @@ async def async_main(
                     except AssertionError:
                         await debug.pause()
 
+                    # !TODO, get rid of the local-portal crap XD
                     async with get_registry(addr) as reg_portal:
                         for accept_addr in accept_addrs:
                             accept_addr = wrap_address(accept_addr)
@@ -1499,7 +1609,7 @@ async def async_main(
                 # start processing parent requests until our channel
                 # server is 100% up and running.
                 if actor._parent_chan:
-                    await root_nursery.start(
+                    await root_tn.start(
                         partial(
                             _rpc.process_messages,
                             chan=actor._parent_chan,
@@ -1511,8 +1621,9 @@ async def async_main(
                     # 'Blocking on service nursery to exit..\n'
                 )
             log.runtime(
-                "Service nursery complete\n"
+                'Service nursery complete\n'
-                "Waiting on root nursery to complete"
+                '\n'
+                '->} waiting on root nursery to complete..\n'
             )
 
         # Blocks here as expected until the root nursery is
@@ -1567,6 +1678,7 @@ async def async_main(
     finally:
         teardown_report: str = (
             'Main actor-runtime task completed\n'
+            '\n'
         )
 
         # ?TODO? should this be in `._entry`/`._root` mods instead?
@@ -1608,7 +1720,8 @@ async def async_main(
         # Unregister actor from the registry-sys / registrar.
         if (
             is_registered
-            and not actor.is_registrar
+            and
+            not actor.is_registrar
         ):
             failed: bool = False
             for addr in actor.reg_addrs:
@@ -1643,23 +1756,30 @@ async def async_main(
             ipc_server.has_peers(check_chans=True)
         ):
             teardown_report += (
-                f'-> Waiting for remaining peers {ipc_server._peers} to clear..\n'
+                f'-> Waiting for remaining peers to clear..\n'
+                f'   {pformat(ipc_server._peers)}'
             )
             log.runtime(teardown_report)
-            await ipc_server.wait_for_no_more_peers(
+            await ipc_server.wait_for_no_more_peers()
-                shield=True,
-            )
 
         teardown_report += (
-            '-> All peer channels are complete\n'
+            '-]> all peer channels are complete.\n'
         )
 
+    # op_nested_actor_repr: str = _pformat.nest_from_op(
+    #     input_op=')>',
+    #     text=actor.pformat(),
+    #     nest_prefix='|_',
+    #     nest_indent=1,  # under >
+    # )
     teardown_report += (
-        'Actor runtime exiting\n'
+        '-)> actor runtime main task exit.\n'
-        f'>)\n'
+        # f'{op_nested_actor_repr}'
-        f'|_{actor}\n'
     )
-    log.info(teardown_report)
+    # if _state._runtime_vars['_is_root']:
+    #     log.info(teardown_report)
+    # else:
+    log.runtime(teardown_report)
 
 
 # TODO: rename to `Registry` and move to `.discovery._registry`!

tractor/_spawn.py

@@ -34,9 +34,9 @@ from typing import (
 import trio
 from trio import TaskStatus
 
-from .devx.debug import (
+from .devx import (
-    maybe_wait_for_debugger,
+    debug,
-    acquire_debug_lock,
+    pformat as _pformat
 )
 from tractor._state import (
     current_actor,
@@ -51,14 +51,17 @@ 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 (
+from tractor.msg import (
-    Aid,
+    types as msgtypes,
-    SpawnSpec,
+    pretty_struct,
 )
 
 
 if TYPE_CHECKING:
-    from ipc import IPCServer
+    from ipc import (
+        _server,
+        Channel,
+    )
     from ._supervise import ActorNursery
     ProcessType = TypeVar('ProcessType', mp.Process, trio.Process)
 
@@ -328,20 +331,21 @@ async def soft_kill(
     see `.hard_kill()`).
 
     '''
-    peer_aid: Aid = portal.channel.aid
+    chan: Channel = portal.channel
+    peer_aid: msgtypes.Aid = chan.aid
     try:
         log.cancel(
             f'Soft killing sub-actor via portal request\n'
             f'\n'
-            f'(c=> {peer_aid}\n'
+            f'c)=> {peer_aid.reprol()}@[{chan.maddr}]\n'
-            f'  |_{proc}\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(
+            await debug.maybe_wait_for_debugger(
                 child_in_debug=_runtime_vars.get(
                     '_debug_mode', False
                 ),
@@ -465,7 +469,7 @@ async def trio_proc(
         "--uid",
         # TODO, how to pass this over "wire" encodings like
         # cmdline args?
-        # -[ ] maybe we can add an `Aid.min_tuple()` ?
+        # -[ ] maybe we can add an `msgtypes.Aid.min_tuple()` ?
         str(subactor.uid),
         # Address the child must connect to on startup
         "--parent_addr",
@@ -483,13 +487,14 @@ async def trio_proc(
 
     cancelled_during_spawn: bool = False
     proc: trio.Process|None = None
-    ipc_server: IPCServer = actor_nursery._actor.ipc_server
+    ipc_server: _server.Server = actor_nursery._actor.ipc_server
     try:
         try:
             proc: trio.Process = await trio.lowlevel.open_process(spawn_cmd, **proc_kwargs)
             log.runtime(
-                'Started new child\n'
+                f'Started new child subproc\n'
-                f'|_{proc}\n'
+                f'(>\n'
+                f' |_{proc}\n'
             )
 
             # wait for actor to spawn and connect back to us
@@ -507,10 +512,10 @@ async def trio_proc(
                 with trio.CancelScope(shield=True):
                     # don't clobber an ongoing pdb
                     if is_root_process():
-                        await maybe_wait_for_debugger()
+                        await debug.maybe_wait_for_debugger()
 
                     elif proc is not None:
-                        async with acquire_debug_lock(subactor.uid):
+                        async with debug.acquire_debug_lock(subactor.uid):
                             # soft wait on the proc to terminate
                             with trio.move_on_after(0.5):
                                 await proc.wait()
@@ -528,14 +533,19 @@ async def trio_proc(
 
         # send a "spawning specification" which configures the
         # initial runtime state of the child.
-        sspec = SpawnSpec(
+        sspec = msgtypes.SpawnSpec(
             _parent_main_data=subactor._parent_main_data,
             enable_modules=subactor.enable_modules,
             reg_addrs=subactor.reg_addrs,
             bind_addrs=bind_addrs,
             _runtime_vars=_runtime_vars,
         )
-        log.runtime(f'Sending spawn spec: {str(sspec)}')
+        log.runtime(
+            f'Sending spawn spec to child\n'
+            f'{{}}=> {chan.aid.reprol()!r}\n'
+            f'\n'
+            f'{pretty_struct.pformat(sspec)}\n'
+        )
         await chan.send(sspec)
 
         # track subactor in current nursery
@@ -563,7 +573,7 @@ async def trio_proc(
             # condition.
             await soft_kill(
                 proc,
-                trio.Process.wait,
+                trio.Process.wait,  # XXX, uses `pidfd_open()` below.
                 portal
             )
 
@@ -571,8 +581,7 @@ async def trio_proc(
             # tandem if not done already
             log.cancel(
                 'Cancelling portal result reaper task\n'
-                f'>c)\n'
+                f'c)> {subactor.aid.reprol()!r}\n'
-                f' |_{subactor.uid}\n'
             )
             nursery.cancel_scope.cancel()
 
@@ -581,21 +590,24 @@ async def trio_proc(
         # allowed! Do this **after** cancellation/teardown to avoid
         # killing the process too early.
         if proc:
+            reap_repr: str = _pformat.nest_from_op(
+                input_op='>x)',
+                text=subactor.pformat(),
+            )
             log.cancel(
                 f'Hard reap sequence starting for subactor\n'
-                f'>x)\n'
+                f'{reap_repr}'
-                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.
-                    async with acquire_debug_lock(subactor.uid):
+                    async with debug.acquire_debug_lock(subactor.uid):
                         with trio.move_on_after(0.5):
                             await proc.wait()
 
-                await maybe_wait_for_debugger(
+                await debug.maybe_wait_for_debugger(
                     child_in_debug=_runtime_vars.get(
                         '_debug_mode', False
                     ),
@@ -624,7 +636,7 @@ async def trio_proc(
                 #     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)
+                # await debug.acquire_debug_lock(this_uid)
 
                 if proc.poll() is None:
                     log.cancel(f"Attempting to hard kill {proc}")
@@ -727,7 +739,7 @@ async def mp_proc(
 
     log.runtime(f"Started {proc}")
 
-    ipc_server: IPCServer = actor_nursery._actor.ipc_server
+    ipc_server: _server.Server = actor_nursery._actor.ipc_server
     try:
         # wait for actor to spawn and connect back to us
         # channel should have handshake completed by the

tractor/_streaming.py

@@ -102,6 +102,9 @@ class MsgStream(trio.abc.Channel):
         self._eoc: bool|trio.EndOfChannel = False
         self._closed: bool|trio.ClosedResourceError = False
 
+    def is_eoc(self) -> bool|trio.EndOfChannel:
+        return self._eoc
+
     @property
     def ctx(self) -> Context:
         '''
@@ -188,7 +191,14 @@ class MsgStream(trio.abc.Channel):
 
         return pld
 
-    async def receive(
+    # XXX NOTE, this is left private because in `.subscribe()` usage
+    # we rebind the public `.recieve()` to a `BroadcastReceiver` but
+    # on `.subscribe().__aexit__()`, for the first task which enters,
+    # we want to revert to this msg-stream-instance's method since
+    # mult-task-tracking provided by the b-caster is then no longer
+    # necessary.
+    #
+    async def _receive(
         self,
         hide_tb: bool = False,
     ):
@@ -313,6 +323,8 @@ class MsgStream(trio.abc.Channel):
 
             raise src_err
 
+    receive = _receive
+
     async def aclose(self) -> list[Exception|dict]:
         '''
         Cancel associated remote actor task and local memory channel on
@@ -528,10 +540,15 @@ class MsgStream(trio.abc.Channel):
         receiver wrapper.
 
         '''
-        # NOTE: This operation is indempotent and non-reversible, so be
+        # XXX NOTE, This operation was originally implemented as
-        # sure you can deal with any (theoretical) overhead of the the
+        # indempotent and non-reversible, so you had to be **VERY**
-        # allocated ``BroadcastReceiver`` before calling this method for
+        # aware of any (theoretical) overhead from the allocated
-        # the first time.
+        # `BroadcastReceiver.receive()`.
+        #
+        # HOWEVER, NOw we do revert and de-alloc the ._broadcaster
+        # when the final caller (task) exits.
+        #
+        bcast: BroadcastReceiver|None = None
         if self._broadcaster is None:
 
             bcast = self._broadcaster = broadcast_receiver(
@@ -541,29 +558,60 @@ class MsgStream(trio.abc.Channel):
 
                 # TODO: can remove this kwarg right since
                 # by default behaviour is to do this anyway?
-                receive_afunc=self.receive,
+                receive_afunc=self._receive,
             )
 
-            # NOTE: we override the original stream instance's receive
+            # XXX NOTE, we override the original stream instance's
-            # method to now delegate to the broadcaster's ``.receive()``
+            # receive method to instead delegate to the broadcaster's
-            # such that new subscribers will be copied received values
+            # `.receive()` such that new subscribers (multiple
-            # and this stream doesn't have to expect it's original
+            # `trio.Task`s) will be copied received values and the
-            # consumer(s) to get a new broadcast rx handle.
+            # *first* task to enter here doesn't have to expect its original consumer(s)
+            # to get a new broadcast rx handle; everything happens
+            # underneath this iface seemlessly.
+            #
             self.receive = bcast.receive  # type: ignore
-            # seems there's no graceful way to type this with ``mypy``?
+            # seems there's no graceful way to type this with `mypy`?
             # https://github.com/python/mypy/issues/708
 
-        async with self._broadcaster.subscribe() as bstream:
+        # TODO, prevent re-entrant sub scope?
-            assert bstream.key != self._broadcaster.key
+        # if self._broadcaster._closed:
-            assert bstream._recv == self._broadcaster._recv
+        #     raise RuntimeError(
+        #         'This stream
 
-            # NOTE: we patch on a `.send()` to the bcaster so that the
+        try:
-            # caller can still conduct 2-way streaming using this
+            aenter = self._broadcaster.subscribe()
-            # ``bstream`` handle transparently as though it was the msg
+            async with aenter as bstream:
-            # stream instance.
+                # ?TODO, move into test suite?
-            bstream.send = self.send  # type: ignore
+                assert bstream.key != self._broadcaster.key
+                assert bstream._recv == self._broadcaster._recv
 
-            yield bstream
+                # NOTE: we patch on a `.send()` to the bcaster so that the
+                # caller can still conduct 2-way streaming using this
+                # ``bstream`` handle transparently as though it was the msg
+                # stream instance.
+                bstream.send = self.send  # type: ignore
+
+                # newly-allocated instance
+                yield bstream
+
+        finally:
+            # XXX, the first-enterer task should, like all other
+            # subs, close the first allocated bcrx, which adjusts the
+            # common `bcrx.state`
+            with trio.CancelScope(shield=True):
+                if bcast is not None:
+                    await bcast.aclose()
+
+                # XXX, when the bcrx.state reports there are no more subs
+                # we can revert to this obj's method, removing any
+                # delegation overhead!
+                if (
+                    (orig_bcast := self._broadcaster)
+                    and
+                    not orig_bcast.state.subs
+                ):
+                    self.receive = self._receive
+                    # self._broadcaster = None
 
     async def send(
         self,

tractor/_supervise.py

@@ -21,7 +21,6 @@
 from contextlib import asynccontextmanager as acm
 from functools import partial
 import inspect
-from pprint import pformat
 from typing import (
     TYPE_CHECKING,
 )
@@ -31,7 +30,10 @@ import warnings
 import trio
 
 
-from .devx.debug import maybe_wait_for_debugger
+from .devx import (
+    debug,
+    pformat as _pformat,
+)
 from ._addr import (
     UnwrappedAddress,
     mk_uuid,
@@ -42,6 +44,7 @@ from ._runtime import Actor
 from ._portal import Portal
 from .trionics import (
     is_multi_cancelled,
+    collapse_eg,
 )
 from ._exceptions import (
     ContextCancelled,
@@ -114,7 +117,6 @@ class ActorNursery:
             ]
         ] = {}
 
-        self.cancelled: bool = False
         self._join_procs = trio.Event()
         self._at_least_one_child_in_debug: bool = False
         self.errors = errors
@@ -132,10 +134,53 @@ class ActorNursery:
         # 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
+
+        # TODO, factor this into a .hilevel api!
+        #
         # portals spawned with ``run_in_actor()`` are
         # cancelled when their "main" result arrives
         self._cancel_after_result_on_exit: set = set()
 
+        # trio.Nursery-like cancel (request) statuses
+        self._cancelled_caught: bool = False
+        self._cancel_called: bool = False
+
+    @property
+    def cancel_called(self) -> bool:
+        '''
+        Records whether cancellation has been requested for this
+        actor-nursery by a call to  `.cancel()` either due to,
+        - an explicit call by some actor-local-task,
+        - an implicit call due to an error/cancel emited inside
+          the `tractor.open_nursery()` block.
+
+        '''
+        return self._cancel_called
+
+    @property
+    def cancelled_caught(self) -> bool:
+        '''
+        Set when this nursery was able to cance all spawned subactors
+        gracefully via an (implicit) call to `.cancel()`.
+
+        '''
+        return self._cancelled_caught
+
+    # TODO! remove internal/test-suite usage!
+    @property
+    def cancelled(self) -> bool:
+        warnings.warn(
+            "`ActorNursery.cancelled` is now deprecated, use "
+            " `.cancel_called` instead.",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        return (
+            self._cancel_called
+            # and
+            # self._cancelled_caught
+        )
+
     async def start_actor(
         self,
         name: str,
@@ -199,7 +244,7 @@ class ActorNursery:
             loglevel=loglevel,
 
             # verbatim relay this actor's registrar addresses
-            registry_addrs=current_actor().reg_addrs,
+            registry_addrs=current_actor().registry_addrs,
         )
         parent_addr: UnwrappedAddress = self._actor.accept_addr
         assert parent_addr
@@ -313,7 +358,7 @@ class ActorNursery:
 
         '''
         __runtimeframe__: int = 1  # noqa
-        self.cancelled = True
+        self._cancel_called = True
 
         # TODO: impl a repr for spawn more compact
         # then `._children`..
@@ -324,9 +369,10 @@ class ActorNursery:
         server: IPCServer = self._actor.ipc_server
 
         with trio.move_on_after(3) as cs:
-            async with trio.open_nursery(
+            async with (
-                strict_exception_groups=False,
+                collapse_eg(),
-            ) as tn:
+                trio.open_nursery() as tn,
+            ):
 
                 subactor: Actor
                 proc: trio.Process
@@ -390,6 +436,8 @@ class ActorNursery:
             ) in children.values():
                 log.warning(f"Hard killing process {proc}")
                 proc.terminate()
+        else:
+            self._cancelled_caught
 
         # mark ourselves as having (tried to have) cancelled all subactors
         self._join_procs.set()
@@ -419,10 +467,10 @@ async def _open_and_supervise_one_cancels_all_nursery(
     # `ActorNursery.start_actor()`).
 
     # errors from this daemon actor nursery bubble up to caller
-    async with trio.open_nursery(
+    async with (
-        strict_exception_groups=False,
+        collapse_eg(),
-        # ^XXX^ TODO? instead unpack any RAE as per "loose" style?
+        trio.open_nursery() as da_nursery,
-    ) as da_nursery:
+    ):
         try:
             # This is the inner level "run in actor" nursery. It is
             # awaited first since actors spawned in this way (using
@@ -432,11 +480,10 @@ async def _open_and_supervise_one_cancels_all_nursery(
             # immediately raised for handling by a supervisor strategy.
             # As such if the strategy propagates any error(s) upwards
             # the above "daemon actor" nursery will be notified.
-            async with trio.open_nursery(
+            async with (
-                strict_exception_groups=False,
+                collapse_eg(),
-                # ^XXX^ TODO? instead unpack any RAE as per "loose" style?
+                trio.open_nursery() as ria_nursery,
-            ) as ria_nursery:
+            ):
-
                 an = ActorNursery(
                     actor,
                     ria_nursery,
@@ -453,7 +500,7 @@ async def _open_and_supervise_one_cancels_all_nursery(
                     # the "hard join phase".
                     log.runtime(
                         'Waiting on subactors to complete:\n'
-                        f'{pformat(an._children)}\n'
+                        f'>}} {len(an._children)}\n'
                     )
                     an._join_procs.set()
 
@@ -467,7 +514,7 @@ async def _open_and_supervise_one_cancels_all_nursery(
                     # will make the pdb repl unusable.
                     # Instead try to wait for pdb to be released before
                     # tearing down.
-                    await maybe_wait_for_debugger(
+                    await debug.maybe_wait_for_debugger(
                         child_in_debug=an._at_least_one_child_in_debug
                     )
 
@@ -543,7 +590,7 @@ async def _open_and_supervise_one_cancels_all_nursery(
 
             # XXX: yet another guard before allowing the cancel
             # sequence in case a (single) child is in debug.
-            await maybe_wait_for_debugger(
+            await debug.maybe_wait_for_debugger(
                 child_in_debug=an._at_least_one_child_in_debug
             )
 
@@ -592,9 +639,14 @@ async def _open_and_supervise_one_cancels_all_nursery(
     # final exit
 
 
-@acm
+_shutdown_msg: str = (
+    'Actor-runtime-shutdown'
+)
+
 # @api_frame
+@acm
 async def open_nursery(
+    *,  # named params only!
     hide_tb: bool = True,
     **kwargs,
     # ^TODO, paramspec for `open_root_actor()`
@@ -679,17 +731,26 @@ async def open_nursery(
         ):
             __tracebackhide__: bool = False
 
-        msg: str = (
+
-            'Actor-nursery exited\n'
+        op_nested_an_repr: str = _pformat.nest_from_op(
-            f'|_{an}\n'
+            input_op=')>',
+            text=f'{an}',
+            # nest_prefix='|_',
+            nest_indent=1,  # under >
         )
+        an_msg: str = (
+            f'Actor-nursery exited\n'
+            f'{op_nested_an_repr}\n'
+        )
+        # keep noise low during std operation.
+        log.runtime(an_msg)
 
         if implicit_runtime:
             # shutdown runtime if it was started and report noisly
             # that we're did so.
-            msg += '=> Shutting down actor runtime <=\n'
+            msg: str = (
+                '\n'
+                '\n'
+                f'{_shutdown_msg} )>\n'
+            )
             log.info(msg)
-
-        else:
-            # keep noise low during std operation.
-            log.runtime(msg)

tractor/ipc/_chan.py

@@ -101,11 +101,27 @@ class Channel:
         # ^XXX! ONLY set if a remote actor sends an `Error`-msg
         self._closed: bool = False
 
-        # flag set by ``Portal.cancel_actor()`` indicating remote
+        # flag set by `Portal.cancel_actor()` indicating remote
-        # (possibly peer) cancellation of the far end actor
+        # (possibly peer) cancellation of the far end actor runtime.
-        # runtime.
         self._cancel_called: bool = False
 
+    @property
+    def closed(self) -> bool:
+        '''
+        Was `.aclose()` successfully called?
+
+        '''
+        return self._closed
+
+    @property
+    def cancel_called(self) -> bool:
+        '''
+        Set when `Portal.cancel_actor()` is called on a portal which
+        wraps this IPC channel.
+
+        '''
+        return self._cancel_called
+
     @property
     def uid(self) -> tuple[str, str]:
         '''
@@ -171,11 +187,23 @@ class Channel:
         )
         assert transport.raddr == addr
         chan = Channel(transport=transport)
-        log.runtime(
+
-            f'Connected channel IPC transport\n'
+        # ?TODO, compact this into adapter level-methods?
-            f'[>\n'
+        # -[ ] would avoid extra repr-calcs if level not active?
-            f' |_{chan}\n'
+        #   |_ how would the `calc_if_level` look though? func?
-        )
+        if log.at_least_level('runtime'):
+            from tractor.devx import (
+                pformat as _pformat,
+            )
+            chan_repr: str = _pformat.nest_from_op(
+                input_op='[>',
+                text=chan.pformat(),
+                nest_indent=1,
+            )
+            log.runtime(
+                f'Connected channel IPC transport\n'
+                f'{chan_repr}'
+            )
         return chan
 
     @cm
@@ -196,9 +224,12 @@ class Channel:
             self._transport.codec = orig
 
     # TODO: do a .src/.dst: str for maddrs?
-    def pformat(self) -> str:
+    def pformat(
+        self,
+        privates: bool = False,
+    ) -> str:
         if not self._transport:
-            return '<Channel with inactive transport?>'
+            return '<Channel( with inactive transport? )>'
 
         tpt: MsgTransport = self._transport
         tpt_name: str = type(tpt).__name__
@@ -206,26 +237,35 @@ class Channel:
             'connected' if self.connected()
             else 'closed'
         )
-        return (
+        repr_str: str = (
             f'<Channel(\n'
             f' |_status: {tpt_status!r}\n'
+        ) + (
             f'   _closed={self._closed}\n'
             f'   _cancel_called={self._cancel_called}\n'
-            f'\n'
+            if privates else ''
-            f' |_peer: {self.aid}\n'
+        ) + (  # peer-actor (processs) section
-            f'\n'
+            f' |_peer: {self.aid.reprol()!r}\n'
+            if self.aid else ' |_peer: <unknown>\n'
+        ) + (
             f' |_msgstream: {tpt_name}\n'
-            f'   proto={tpt.laddr.proto_key!r}\n'
+            f'   maddr: {tpt.maddr!r}\n'
-            f'   layer={tpt.layer_key!r}\n'
+            f'   proto: {tpt.laddr.proto_key!r}\n'
-            f'   laddr={tpt.laddr}\n'
+            f'   layer: {tpt.layer_key!r}\n'
-            f'   raddr={tpt.raddr}\n'
+            f'   codec: {tpt.codec_key!r}\n'
-            f'   codec={tpt.codec_key!r}\n'
+            f'   .laddr={tpt.laddr}\n'
-            f'   stream={tpt.stream}\n'
+            f'   .raddr={tpt.raddr}\n'
-            f'   maddr={tpt.maddr!r}\n'
+        ) + (
-            f'   drained={tpt.drained}\n'
+            f'   ._transport.stream={tpt.stream}\n'
+            f'   ._transport.drained={tpt.drained}\n'
+            if privates else ''
+        ) + (
             f'   _send_lock={tpt._send_lock.statistics()}\n'
-            f')>\n'
+            if privates else ''
+        ) + (
+            ')>\n'
         )
+        return repr_str
 
     # NOTE: making this return a value that can be passed to
     # `eval()` is entirely **optional** FYI!
@@ -247,6 +287,10 @@ class Channel:
     def raddr(self) -> Address|None:
         return self._transport.raddr if self._transport else None
 
+    @property
+    def maddr(self) -> str:
+        return self._transport.maddr if self._transport else '<no-tpt>'
+
     # TODO: something like,
     # `pdbp.hideframe_on(errors=[MsgTypeError])`
     # instead of the `try/except` hack we have rn..
@@ -434,8 +478,8 @@ class Channel:
         await self.send(aid)
         peer_aid: Aid = await self.recv()
         log.runtime(
-            f'Received hanshake with peer actor,\n'
+            f'Received hanshake with peer\n'
-            f'{peer_aid}\n'
+            f'<= {peer_aid.reprol(sin_uuid=False)}\n'
         )
         # NOTE, we always are referencing the remote peer!
         self.aid = peer_aid

tractor/ipc/_mp_bs.py

@@ -17,9 +17,16 @@
 Utils to tame mp non-SC madeness
 
 '''
+
+# !TODO! in 3.13 this can be disabled (the-same/similarly) using
+# a flag,
+# - [ ] soo if it works like this, drop this module entirely for
+#   3.13+ B)
+#  |_https://docs.python.org/3/library/multiprocessing.shared_memory.html
+#
 def disable_mantracker():
     '''
-    Disable all ``multiprocessing``` "resource tracking" machinery since
+    Disable all `multiprocessing` "resource tracking" machinery since
     it's an absolute multi-threaded mess of non-SC madness.
 
     '''

tractor/ipc/_server.py

@@ -26,7 +26,7 @@ from contextlib import (
 from functools import partial
 from itertools import chain
 import inspect
-from pprint import pformat
+import textwrap
 from types import (
     ModuleType,
 )
@@ -43,7 +43,10 @@ from trio import (
     SocketListener,
 )
 
-# from ..devx import debug
+from ..devx.pformat import (
+    ppfmt,
+    nest_from_op,
+)
 from .._exceptions import (
     TransportClosed,
 )
@@ -141,9 +144,8 @@ async def maybe_wait_on_canced_subs(
 
     ):
         log.cancel(
-            'Waiting on cancel request to peer..\n'
+            'Waiting on cancel request to peer\n'
-            f'c)=>\n'
+            f'c)=> {chan.aid.reprol()}@[{chan.maddr}]\n'
-            f'  |_{chan.aid}\n'
         )
 
         # XXX: this is a soft wait on the channel (and its
@@ -179,7 +181,7 @@ async def maybe_wait_on_canced_subs(
                 log.warning(
                     'Draining msg from disconnected peer\n'
                     f'{chan_info}'
-                    f'{pformat(msg)}\n'
+                    f'{ppfmt(msg)}\n'
                 )
                 # cid: str|None = msg.get('cid')
                 cid: str|None = msg.cid
@@ -248,7 +250,7 @@ async def maybe_wait_on_canced_subs(
                 if children := local_nursery._children:
                     # indent from above local-nurse repr
                     report += (
-                        f'   |_{pformat(children)}\n'
+                        f'   |_{ppfmt(children)}\n'
                     )
 
                 log.warning(report)
@@ -279,8 +281,9 @@ async def maybe_wait_on_canced_subs(
                     log.runtime(
                         f'Peer IPC broke but subproc is alive?\n\n'
 
-                        f'<=x {chan.aid}@{chan.raddr}\n'
+                        f'<=x {chan.aid.reprol()}@[{chan.maddr}]\n'
-                        f'   |_{proc}\n'
+                        f'\n'
+                        f'{proc}\n'
                     )
 
     return local_nursery
@@ -324,9 +327,10 @@ async def handle_stream_from_peer(
 
     chan = Channel.from_stream(stream)
     con_status: str = (
-        'New inbound IPC connection <=\n'
+        f'New inbound IPC transport connection\n'
-        f'|_{chan}\n'
+        f'<=( {stream!r}\n'
     )
+    con_status_steps: str = ''
 
     # initial handshake with peer phase
     try:
@@ -372,7 +376,7 @@ async def handle_stream_from_peer(
     if _pre_chan := server._peers.get(uid):
         familiar: str = 'pre-existing-peer'
     uid_short: str = f'{uid[0]}[{uid[1][-6:]}]'
-    con_status += (
+    con_status_steps += (
         f' -> Handshake with {familiar} `{uid_short}` complete\n'
     )
 
@@ -397,7 +401,7 @@ async def handle_stream_from_peer(
         None,
     )
     if event:
-        con_status += (
+        con_status_steps += (
             ' -> Waking subactor spawn waiters: '
             f'{event.statistics().tasks_waiting}\n'
             f' -> Registered IPC chan for child actor {uid}@{chan.raddr}\n'
@@ -408,7 +412,7 @@ async def handle_stream_from_peer(
         event.set()
 
     else:
-        con_status += (
+        con_status_steps += (
             f' -> Registered IPC chan for peer actor {uid}@{chan.raddr}\n'
         )  # type: ignore
 
@@ -422,8 +426,15 @@ async def handle_stream_from_peer(
     # TODO: can we just use list-ref directly?
     chans.append(chan)
 
-    con_status += ' -> Entering RPC msg loop..\n'
+    con_status_steps += ' -> Entering RPC msg loop..\n'
-    log.runtime(con_status)
+    log.runtime(
+        con_status
+        +
+        textwrap.indent(
+            con_status_steps,
+            prefix=' '*3,  # align to first-ln
+        )
+    )
 
     # Begin channel management - respond to remote requests and
     # process received reponses.
@@ -456,41 +467,67 @@ async def handle_stream_from_peer(
             disconnected=disconnected,
         )
 
-        # ``Channel`` teardown and closure sequence
+        # `Channel` teardown and closure sequence
         # drop ref to channel so it can be gc-ed and disconnected
-        con_teardown_status: str = (
+        #
-            f'IPC channel disconnected:\n'
+        # -[x]TODO mk this be like
-            f'<=x uid: {chan.aid}\n'
+        # <=x Channel(
-            f'   |_{pformat(chan)}\n\n'
+        #     |_field: blah
+        # )>
+        op_repr: str = '<=x '
+        chan_repr: str = nest_from_op(
+            input_op=op_repr,
+            op_suffix='',
+            nest_prefix='',
+            text=chan.pformat(),
+            nest_indent=len(op_repr)-1,
+            rm_from_first_ln='<',
         )
+
+        con_teardown_status: str = (
+            f'IPC channel disconnect\n'
+            f'\n'
+            f'{chan_repr}\n'
+            f'\n'
+        )
+
         chans.remove(chan)
 
         # TODO: do we need to be this pedantic?
         if not chans:
             con_teardown_status += (
-                f'-> No more channels with {chan.aid}'
+                f'-> No more channels with {chan.aid.reprol()!r}\n'
             )
             server._peers.pop(uid, None)
 
-        peers_str: str = ''
+        if peers := list(server._peers.values()):
-        for uid, chans in server._peers.items():
+            peer_cnt: int = len(peers)
-            peers_str += (
+            if (
-                f'uid: {uid}\n'
+                (first := peers[0][0]) is not chan
-            )
+                and
-            for i, chan in enumerate(chans):
+                not disconnected
-                peers_str += (
+                and
-                    f' |_[{i}] {pformat(chan)}\n'
+                peer_cnt > 1
+            ):
+                con_teardown_status += (
+                    f'-> Remaining IPC {peer_cnt-1!r} peers:\n'
                 )
-
+                for chans in server._peers.values():
-        con_teardown_status += (
+                    first: Channel = chans[0]
-            f'-> Remaining IPC {len(server._peers)} peers: {peers_str}\n'
+                    if not (
-        )
+                        first is chan
+                        and
+                        disconnected
+                    ):
+                        con_teardown_status += (
+                            f'  |_{first.aid.reprol()!r} -> {len(chans)!r} chans\n'
+                        )
 
         # No more channels to other actors (at all) registered
         # as connected.
         if not server._peers:
             con_teardown_status += (
-                'Signalling no more peer channel connections'
+                '-> Signalling no more peer connections!\n'
             )
             server._no_more_peers.set()
 
@@ -579,10 +616,10 @@ async def handle_stream_from_peer(
 
 class Endpoint(Struct):
     '''
-    An instance of an IPC "bound" address where the lifetime of the
+    An instance of an IPC "bound" address where the lifetime of an
-    "ability to accept connections" (from clients) and then handle
+    "ability to accept connections" and handle the subsequent
-    those inbound sessions or sequences-of-packets is determined by
+    sequence-of-packets (maybe oriented as sessions) is determined by
-    a (maybe pair of) nurser(y/ies).
+    the underlying nursery scope(s).
 
     '''
     addr: Address
@@ -600,6 +637,24 @@ class Endpoint(Struct):
         MsgTransport,  # handle to encoded-msg transport stream
     ] = {}
 
+    def pformat(
+        self,
+        indent: int = 0,
+        privates: bool = False,
+    ) -> str:
+        type_repr: str = type(self).__name__
+        fmtstr: str = (
+            # !TODO, always be ns aware!
+            # f'|_netns: {netns}\n'
+            f' |.addr: {self.addr!r}\n'
+            f' |_peers: {len(self.peer_tpts)}\n'
+        )
+        return (
+            f'<{type_repr}(\n'
+            f'{fmtstr}'
+            f')>'
+        )
+
     async def start_listener(self) -> SocketListener:
         tpt_mod: ModuleType = inspect.getmodule(self.addr)
         lstnr: SocketListener = await tpt_mod.start_listener(
@@ -639,11 +694,13 @@ class Endpoint(Struct):
 class Server(Struct):
     _parent_tn: Nursery
     _stream_handler_tn: Nursery
+
     # level-triggered sig for whether "no peers are currently
     # connected"; field is **always** set to an instance but
     # initialized with `.is_set() == True`.
     _no_more_peers: trio.Event
 
+    # active eps as allocated by `.listen_on()`
     _endpoints: list[Endpoint] = []
 
     # connection tracking & mgmt
@@ -651,12 +708,19 @@ class Server(Struct):
         str,  # uaid
         list[Channel],  # IPC conns from peer
     ] = defaultdict(list)
+
+    # events-table with entries registered unset while the local
+    # actor is waiting on a new actor to inbound connect, often
+    # a parent waiting on its child just after spawn.
     _peer_connected: dict[
         tuple[str, str],
         trio.Event,
     ] = {}
 
     # syncs for setup/teardown sequences
+    # - null when not yet booted,
+    # - unset when active,
+    # - set when fully shutdown with 0 eps active.
     _shutdown: trio.Event|None = None
 
     # TODO, maybe just make `._endpoints: list[Endpoint]` and
@@ -664,7 +728,6 @@ class Server(Struct):
     # @property
     # def addrs2eps(self) -> dict[Address, Endpoint]:
     #     ...
-
     @property
     def proto_keys(self) -> list[str]:
         return [
@@ -690,7 +753,7 @@ class Server(Struct):
             # TODO: obvi a different server type when we eventually
             # support some others XD
             log.runtime(
-                f'Cancelling server(s) for\n'
+                f'Cancelling server(s) for tpt-protos\n'
                 f'{self.proto_keys!r}\n'
             )
             self._parent_tn.cancel_scope.cancel()
@@ -717,6 +780,14 @@ class Server(Struct):
                 f'protos: {tpt_protos!r}\n'
             )
 
+    def len_peers(
+        self,
+    ) -> int:
+        return len([
+            chan.connected()
+            for chan in chain(*self._peers.values())
+        ])
+
     def has_peers(
         self,
         check_chans: bool = False,
@@ -730,13 +801,11 @@ class Server(Struct):
             has_peers
             and
             check_chans
+            and
+            (peer_cnt := self.len_peers())
         ):
             has_peers: bool = (
-                any(chan.connected()
+                peer_cnt > 0
-                    for chan in chain(
-                        *self._peers.values()
-                    )
-                )
                 and
                 has_peers
             )
@@ -745,10 +814,14 @@ class Server(Struct):
 
     async def wait_for_no_more_peers(
         self,
-        shield: bool = False,
+        # XXX, should this even be allowed?
+        # -> i've seen it cause hangs on teardown
+        #    in `test_resource_cache.py`
+        # _shield: bool = False,
     ) -> None:
-        with trio.CancelScope(shield=shield):
+        await self._no_more_peers.wait()
-            await self._no_more_peers.wait()
+        # with trio.CancelScope(shield=_shield):
+        #     await self._no_more_peers.wait()
 
     async def wait_for_peer(
         self,
@@ -803,30 +876,66 @@ class Server(Struct):
 
         return ev.is_set()
 
-    def pformat(self) -> str:
+    @property
+    def repr_state(self) -> str:
+        '''
+        A `str`-status describing the current state of this
+        IPC server in terms of the current operating "phase".
+
+        '''
+        status = 'server is active'
+        if self.has_peers():
+            peer_cnt: int = self.len_peers()
+            status: str = (
+                f'{peer_cnt!r} peer chans'
+            )
+        else:
+            status: str = 'No peer chans'
+
+        if self.is_shutdown():
+            status: str = 'server-shutdown'
+
+        return status
+
+    def pformat(
+        self,
+        privates: bool = False,
+    ) -> str:
         eps: list[Endpoint] = self._endpoints
 
-        state_repr: str = (
+        # state_repr: str = (
-            f'{len(eps)!r} IPC-endpoints active'
+        #     f'{len(eps)!r} endpoints active'
-        )
+        # )
         fmtstr = (
-            f' |_state: {state_repr}\n'
+            f' |_state: {self.repr_state!r}\n'
-            f'   no_more_peers: {self.has_peers()}\n'
         )
-        if self._shutdown is not None:
+        if privates:
-            shutdown_stats: EventStatistics = self._shutdown.statistics()
+            fmtstr += f'   no_more_peers: {self.has_peers()}\n'
+
+            if self._shutdown is not None:
+                shutdown_stats: EventStatistics = self._shutdown.statistics()
+                fmtstr += (
+                    f'   task_waiting_on_shutdown: {shutdown_stats}\n'
+                )
+
+        if eps := self._endpoints:
+            addrs: list[tuple] = [
+                ep.addr for ep in eps
+            ]
+            repr_eps: str = ppfmt(addrs)
+
             fmtstr += (
-                f'   task_waiting_on_shutdown: {shutdown_stats}\n'
+                f' |_endpoints: {repr_eps}\n'
+                # ^TODO? how to indent closing ']'..
             )
 
-        fmtstr += (
+        if peers := self._peers:
-            # TODO, use the `ppfmt()` helper from `modden`!
+            fmtstr += (
-            f' |_endpoints: {pformat(self._endpoints)}\n'
+                f' |_peers: {len(peers)} connected\n'
-            f' |_peers: {len(self._peers)} connected\n'
+            )
-        )
 
         return (
-            f'<IPCServer(\n'
+            f'<Server(\n'
             f'{fmtstr}'
             f')>\n'
         )
@@ -885,8 +994,8 @@ class Server(Struct):
             )
 
         log.runtime(
-            f'Binding to endpoints for,\n'
+            f'Binding endpoints\n'
-            f'{accept_addrs}\n'
+            f'{ppfmt(accept_addrs)}\n'
         )
         eps: list[Endpoint] = await self._parent_tn.start(
             partial(
@@ -896,13 +1005,19 @@ class Server(Struct):
                 listen_addrs=accept_addrs,
             )
         )
+        self._endpoints.extend(eps)
+
+        serv_repr: str = nest_from_op(
+            input_op='(>',
+            text=self.pformat(),
+            nest_indent=1,
+        )
         log.runtime(
-            f'Started IPC endpoints\n'
+            f'Started IPC server\n'
-            f'{eps}\n'
+            f'{serv_repr}'
         )
 
-        self._endpoints.extend(eps)
+        # XXX, a little sanity on new ep allocations
-        # XXX, just a little bit of sanity
         group_tn: Nursery|None = None
         ep: Endpoint
         for ep in eps:
@@ -956,9 +1071,13 @@ async def _serve_ipc_eps(
                     stream_handler_tn=stream_handler_tn,
                 )
                 try:
+                    ep_sclang: str = nest_from_op(
+                        input_op='>[',
+                        text=f'{ep.pformat()}',
+                    )
                     log.runtime(
                         f'Starting new endpoint listener\n'
-                        f'{ep}\n'
+                        f'{ep_sclang}\n'
                     )
                     listener: trio.abc.Listener = await ep.start_listener()
                     assert listener is ep._listener
@@ -996,17 +1115,6 @@ async def _serve_ipc_eps(
                     handler_nursery=stream_handler_tn
                 )
             )
-            # TODO, wow make this message better! XD
-            log.runtime(
-                'Started server(s)\n'
-                +
-                '\n'.join([f'|_{addr}' for addr in listen_addrs])
-            )
-
-            log.runtime(
-                f'Started IPC endpoints\n'
-                f'{eps}\n'
-            )
             task_status.started(
                 eps,
             )
@@ -1049,8 +1157,7 @@ async def open_ipc_server(
         try:
             yield ipc_server
             log.runtime(
-                f'Waiting on server to shutdown or be cancelled..\n'
+                'Server-tn running until terminated\n'
-                f'{ipc_server}'
             )
             # TODO? when if ever would we want/need this?
             # with trio.CancelScope(shield=True):

tractor/ipc/_shm.py

@@ -789,6 +789,11 @@ def open_shm_list(
         readonly=readonly,
     )
 
+    # TODO, factor into a @actor_fixture acm-API?
+    # -[ ] also `@maybe_actor_fixture()` which inludes
+    #     the .current_actor() convenience check?
+    #   |_ orr can that just be in the sin-maybe-version?
+    #
     # "close" attached shm on actor teardown
     try:
         actor = tractor.current_actor()

tractor/ipc/_tcp.py

@@ -160,10 +160,9 @@ async def start_listener(
     Start a TCP socket listener on the given `TCPAddress`.
 
     '''
-    log.info(
+    log.runtime(
-        f'Attempting to bind TCP socket\n'
+        f'Trying socket bind\n'
-        f'>[\n'
+        f'>[ {addr}\n'
-        f'|_{addr}\n'
     )
     # ?TODO, maybe we should just change the lower-level call this is
     # using internall per-listener?
@@ -178,11 +177,10 @@ async def start_listener(
     assert len(listeners) == 1
     listener = listeners[0]
     host, port = listener.socket.getsockname()[:2]
-
+    bound_addr: TCPAddress = type(addr).from_addr((host, port))
     log.info(
         f'Listening on TCP socket\n'
-        f'[>\n'
+        f'[> {bound_addr}\n'
-        f' |_{addr}\n'
     )
     return listener
 

tractor/log.py

@@ -81,10 +81,35 @@ BOLD_PALETTE = {
 }
 
 
+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
+
+
 # TODO: this isn't showing the correct '{filename}'
 # as it did before..
 class StackLevelAdapter(LoggerAdapter):
 
+    def at_least_level(
+        self,
+        level: str,
+    ) -> bool:
+        return at_least_level(
+            log=self,
+            level=level,
+        )
+
     def transport(
         self,
         msg: str,
@@ -401,19 +426,3 @@ def get_loglevel() -> str:
 
 # global module logger for tractor itself
 log: StackLevelAdapter = 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/_ops.py

@@ -210,12 +210,14 @@ class PldRx(Struct):
         match msg:
             case Return()|Error():
                 log.runtime(
-                    f'Rxed final outcome msg\n'
+                    f'Rxed final-outcome msg\n'
+                    f'\n'
                     f'{msg}\n'
                 )
             case Stop():
                 log.runtime(
                     f'Rxed stream stopped msg\n'
+                    f'\n'
                     f'{msg}\n'
                 )
                 if passthrough_non_pld_msgs:
@@ -261,8 +263,9 @@ class PldRx(Struct):
         if (
             type(msg) is Return
         ):
-            log.info(
+            log.runtime(
                 f'Rxed final result msg\n'
+                f'\n'
                 f'{msg}\n'
             )
         return self.decode_pld(
@@ -304,10 +307,13 @@ class PldRx(Struct):
                 try:
                     pld: PayloadT = self._pld_dec.decode(pld)
                     log.runtime(
-                        'Decoded msg payload\n\n'
+                        f'Decoded payload for\n'
+                        # f'\n'
                         f'{msg}\n'
-                        f'where payload decoded as\n'
+                        # ^TODO?, ideally just render with `,
-                        f'|_pld={pld!r}\n'
+                        # pld={decode}` in the `msg.pformat()`??
+                        f'where, '
+                        f'{type(msg).__name__}.pld={pld!r}\n'
                     )
                     return pld
                 except TypeError as typerr:
@@ -494,7 +500,8 @@ def limit_plds(
 
     finally:
         log.runtime(
-            'Reverted to previous payload-decoder\n\n'
+            f'Reverted to previous payload-decoder\n'
+            f'\n'
             f'{orig_pldec}\n'
         )
         # sanity on orig settings
@@ -629,7 +636,8 @@ async def drain_to_final_msg(
                     (local_cs := rent_n.cancel_scope).cancel_called
                 ):
                     log.cancel(
-                        'RPC-ctx cancelled by local-parent scope during drain!\n\n'
+                        f'RPC-ctx cancelled by local-parent scope during drain!\n'
+                        f'\n'
                         f'c}}>\n'
                         f' |_{rent_n}\n'
                         f'   |_.cancel_scope = {local_cs}\n'
@@ -663,7 +671,8 @@ async def drain_to_final_msg(
             # final result arrived!
             case Return():
                 log.runtime(
-                    'Context delivered final draining msg:\n'
+                    f'Context delivered final draining msg\n'
+                    f'\n'
                     f'{pretty_struct.pformat(msg)}'
                 )
                 ctx._result: Any = pld
@@ -697,12 +706,14 @@ async def drain_to_final_msg(
                 ):
                     log.cancel(
                         'Cancelling `MsgStream` drain since '
-                        f'{reason}\n\n'
+                        f'{reason}\n'
+                        f'\n'
                         f'<= {ctx.chan.uid}\n'
-                        f'  |_{ctx._nsf}()\n\n'
+                        f'  |_{ctx._nsf}()\n'
+                        f'\n'
                         f'=> {ctx._task}\n'
-                        f'  |_{ctx._stream}\n\n'
+                        f'  |_{ctx._stream}\n'
-
+                        f'\n'
                         f'{pretty_struct.pformat(msg)}\n'
                     )
                     break
@@ -739,7 +750,8 @@ async def drain_to_final_msg(
             case Stop():
                 pre_result_drained.append(msg)
                 log.runtime(  # normal/expected shutdown transaction
-                    'Remote stream terminated due to "stop" msg:\n\n'
+                    f'Remote stream terminated due to "stop" msg\n'
+                    f'\n'
                     f'{pretty_struct.pformat(msg)}\n'
                 )
                 continue
@@ -814,7 +826,8 @@ async def drain_to_final_msg(
 
     else:
         log.cancel(
-            'Skipping `MsgStream` drain since final outcome is set\n\n'
+            f'Skipping `MsgStream` drain since final outcome is set\n'
+            f'\n'
             f'{ctx.outcome}\n'
         )
 

tractor/msg/types.py

@@ -154,6 +154,39 @@ class Aid(
     #     should also include at least `.pid` (equiv to port for tcp)
     #     and/or host-part always?
 
+    @property
+    def uid(self) -> tuple[str, str]:
+        '''
+        Legacy actor "unique-id" pair format.
+
+        '''
+        return (
+            self.name,
+            self.uuid,
+        )
+
+    def reprol(
+        self,
+        sin_uuid: bool = True,
+    ) -> str:
+        if not sin_uuid:
+            return (
+                f'{self.name}[{self.uuid[:6]}]@{self.pid!r}'
+            )
+        return (
+            f'{self.name}@{self.pid!r}'
+        )
+
+    # mk hashable via `.uuid`
+    def __hash__(self) -> int:
+        return hash(self.uuid)
+
+    def __eq__(self, other: Aid) -> bool:
+        return self.uuid == other.uuid
+
+    # use pretty fmt since often repr-ed for console/log
+    __repr__ = pretty_struct.Struct.__repr__
+
 
 class SpawnSpec(
     pretty_struct.Struct,

tractor/trionics/_beg.py

@@ -31,7 +31,7 @@ import trio
 
 def maybe_collapse_eg(
     beg: BaseExceptionGroup,
-) -> BaseException:
+) -> BaseException|bool:
     '''
     If the input beg can collapse to a single non-eg sub-exception,
     return it instead.
@@ -40,11 +40,13 @@ def maybe_collapse_eg(
     if len(excs := beg.exceptions) == 1:
         return excs[0]
 
-    return beg
+    return False
 
 
 @acm
-async def collapse_eg():
+async def collapse_eg(
+    hide_tb: bool = True,
+):
     '''
     If `BaseExceptionGroup` raised in the body scope is
     "collapse-able" (in the same way that
@@ -52,12 +54,16 @@ async def collapse_eg():
     only raise the lone emedded non-eg in in place.
 
     '''
+    __tracebackhide__: bool = hide_tb
     try:
         yield
     except* BaseException as beg:
         if (
             exc := maybe_collapse_eg(beg)
-        ) is not beg:
+        ):
+            if cause := exc.__cause__:
+                raise exc from cause
+
             raise exc
 
         raise beg

tractor/trionics/_broadcast.py

@@ -100,6 +100,32 @@ class Lagged(trio.TooSlowError):
     '''
 
 
+def wrap_rx_for_eoc(
+    rx: AsyncReceiver,
+) -> AsyncReceiver:
+
+    match rx:
+        case trio.MemoryReceiveChannel():
+
+            # XXX, taken verbatim from .receive_nowait()
+            def is_eoc() -> bool:
+                if not rx._state.open_send_channels:
+                    return trio.EndOfChannel
+
+                return False
+
+            rx.is_eoc = is_eoc
+
+        case _:
+            # XXX, ensure we define a private field!
+            # case tractor.MsgStream:
+            assert (
+                getattr(rx, '_eoc', False) is not None
+            )
+
+    return rx
+
+
 class BroadcastState(Struct):
     '''
     Common state to all receivers of a broadcast.
@@ -186,11 +212,23 @@ class BroadcastReceiver(ReceiveChannel):
         state.subs[self.key] = -1
 
         # underlying for this receiver
-        self._rx = rx_chan
+        self._rx = wrap_rx_for_eoc(rx_chan)
         self._recv = receive_afunc or rx_chan.receive
         self._closed: bool = False
         self._raise_on_lag = raise_on_lag
 
+    @property
+    def state(self) -> BroadcastState:
+        '''
+        Read-only access to this receivers internal `._state`
+        instance ref.
+
+        If you just want to read the high-level state metrics,
+        use `.state.statistics()`.
+
+        '''
+        return self._state
+
     def receive_nowait(
         self,
         _key: int | None = None,
@@ -215,7 +253,23 @@ class BroadcastReceiver(ReceiveChannel):
         try:
             seq = state.subs[key]
         except KeyError:
+            # from tractor import pause_from_sync
+            # pause_from_sync(shield=True)
+            if (
+                (rx_eoc := self._rx.is_eoc())
+                or
+                self.state.eoc
+            ):
+                raise trio.EndOfChannel(
+                    'Broadcast-Rx underlying already ended!'
+                ) from rx_eoc
+
             if self._closed:
+                # if (rx_eoc := self._rx._eoc):
+                #     raise trio.EndOfChannel(
+                #         'Broadcast-Rx underlying already ended!'
+                #     ) from rx_eoc
+
                 raise trio.ClosedResourceError
 
             raise RuntimeError(
@@ -453,8 +507,9 @@ class BroadcastReceiver(ReceiveChannel):
         self._closed = True
 
 
+# NOTE, this can we use as an `@acm` since `BroadcastReceiver`
+# derives from `ReceiveChannel`.
 def broadcast_receiver(
-
     recv_chan: AsyncReceiver,
     max_buffer_size: int,
     receive_afunc: Callable[[], Awaitable[Any]]|None = None,

tractor/trionics/_mngrs.py

@@ -40,7 +40,7 @@ from typing import (
 import trio
 from tractor._state import current_actor
 from tractor.log import get_logger
-# from ._beg import collapse_eg
+from ._beg import collapse_eg
 
 
 if TYPE_CHECKING:
@@ -152,13 +152,8 @@ async def gather_contexts(
         )
 
     async with (
-        # collapse_eg(),
+        collapse_eg(),
-        trio.open_nursery(
+        trio.open_nursery() as tn,
-            strict_exception_groups=False,
-            # ^XXX^ TODO? soo roll our own then ??
-            # -> since we kinda want the "if only one `.exception` then
-            # just raise that" interface?
-        ) as tn,
     ):
         for mngr in mngrs:
             tn.start_soon(
@@ -294,7 +289,10 @@ async def maybe_open_context(
         )
         _Cache.users += 1
         lock.release()
-        yield False, yielded
+        yield (
+            False,  # cache_hit = "no"
+            yielded,
+        )
 
     else:
         _Cache.users += 1
@@ -308,7 +306,10 @@ async def maybe_open_context(
             # f'{ctx_key!r} -> {yielded!r}\n'
         )
         lock.release()
-        yield True, yielded
+        yield (
+            True,  # cache_hit = "yes"
+            yielded,
+        )
 
     finally:
         _Cache.users -= 1

tractor/trionics/_taskc.py

@@ -60,8 +60,8 @@ def find_masked_excs(
     return None
 
 
-# XXX, relevant discussion @ `trio`-core,
+# XXX, relevant ish discussion @ `trio`-core,
-# https://github.com/python-trio/trio/issues/455
+# https://github.com/python-trio/trio/issues/455#issuecomment-2785122216
 #
 @acm
 async def maybe_raise_from_masking_exc(
@@ -113,6 +113,7 @@ async def maybe_raise_from_masking_exc(
     )
     matching: list[BaseException]|None = None
     maybe_eg: ExceptionGroup|None
+    maybe_eg: ExceptionGroup|None
 
     if tn:
         try:  # handle egs