.github/workflows/ci.yml

@@ -8,70 +8,46 @@ on:
   workflow_dispatch:
 
 jobs:
-  # ------ sdist ------
+
+  mypy:
+    name: 'MyPy'
+    runs-on: ubuntu-latest
+
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v2
+
+      - name: Setup python
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.11'
+
+      - name: Install dependencies
+        run: pip install -U . --upgrade-strategy eager -r requirements-test.txt
+
+      - name: Run MyPy check
+        run: mypy tractor/ --ignore-missing-imports --show-traceback
+
   # test that we can generate a software distribution and install it
   # thus avoid missing file issues after packaging.
-  #
-  # -[x] produce sdist with uv
-  # ------ - ------
   sdist-linux:
     name: 'sdist'
     runs-on: ubuntu-latest
 
     steps:
       - name: Checkout
-        uses: actions/checkout@v4
+        uses: actions/checkout@v2
 
-      - name: Install latest uv
+      - name: Setup python
-        uses: astral-sh/setup-uv@v6
+        uses: actions/setup-python@v2
+        with:
+          python-version: '3.11'
 
-      - name: Build sdist as tar.gz
+      - name: Build sdist
-        run: uv build --sdist --python=3.13
+        run: python setup.py sdist --formats=zip
 
-      - name: Install sdist from .tar.gz
+      - name: Install sdist from .zips
-        run: python -m pip install dist/*.tar.gz
+        run: python -m pip install dist/*.zip
-
-  # ------ type-check ------
-  # mypy:
-  #   name: 'MyPy'
-  #   runs-on: ubuntu-latest
-
-  #   steps:
-  #     - name: Checkout
-  #       uses: actions/checkout@v4
-
-  #     - name: Install latest uv
-  #       uses: astral-sh/setup-uv@v6
-
-  #     # faster due to server caching?
-  #     # https://docs.astral.sh/uv/guides/integration/github/#setting-up-python
-  #     - name: "Set up Python"
-  #       uses: actions/setup-python@v6
-  #       with:
-  #         python-version-file: "pyproject.toml"
-
-  #     # w uv
-  #     # - name: Set up Python
-  #     #   run: uv python install
-
-  #     - name: Setup uv venv
-  #       run: uv venv .venv --python=3.13
-
-  #     - name: Install
-  #       run: uv sync --dev
-
-  #     # TODO, ty cmd over repo
-  #     # - name: type check with ty
-  #     #   run: ty ./tractor/
-
-  #     # - uses: actions/cache@v3
-  #     #     name: Cache uv virtenv as default .venv
-  #     #     with:
-  #     #       path: ./.venv
-  #     #       key: venv-${{ hashFiles('uv.lock') }}
-
-  #     - name: Run MyPy check
-  #       run: mypy tractor/ --ignore-missing-imports --show-traceback
 
 
   testing-linux:
@@ -83,45 +59,32 @@ jobs:
       fail-fast: false
       matrix:
         os: [ubuntu-latest]
-        python-version: ['3.13']
+        python: ['3.11']
         spawn_backend: [
           'trio',
-          # 'mp_spawn',
+          'mp_spawn',
-          # 'mp_forkserver',
+          'mp_forkserver',
         ]
 
     steps:
 
-      - uses: actions/checkout@v4
+      - name: Checkout
+        uses: actions/checkout@v2
 
-      - name: 'Install uv + py-${{ matrix.python-version }}'
+      - name: Setup python
-        uses: astral-sh/setup-uv@v6
+        uses: actions/setup-python@v2
         with:
-          python-version: ${{ matrix.python-version }}
+          python-version: '${{ matrix.python }}'
 
-      # GH way.. faster?
+      - name: Install dependencies
-      # - name: setup-python@v6
+        run: pip install -U . -r requirements-test.txt -r requirements-docs.txt --upgrade-strategy eager
-      #   uses: actions/setup-python@v6
-      #   with:
-      #     python-version: '${{ matrix.python-version }}'
 
-      # consider caching for speedups?
+      - name: List dependencies
-      # https://docs.astral.sh/uv/guides/integration/github/#caching
+        run: pip list
-
-      - name: Install the project w uv
-        run: uv sync --all-extras --dev
-
-      # - name: Install dependencies
-      #   run: pip install -U . -r requirements-test.txt -r requirements-docs.txt --upgrade-strategy eager
-
-      - name: List deps tree
-        run: uv tree
 
       - name: Run tests
-        run: uv run pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rsx
+        run: pytest tests/ --spawn-backend=${{ matrix.spawn_backend }} -rsx
 
-  # XXX legacy NOTE XXX
-  #
   # We skip 3.10 on windows for now due to not having any collabs to
   # debug the CI failures. Anyone wanting to hack and solve them is very
   # welcome, but our primary user base is not using that OS.

default.nix

@@ -1,19 +0,0 @@
-{ pkgs ? import <nixpkgs> {} }:
-let
-  nativeBuildInputs = with pkgs; [
-    stdenv.cc.cc.lib
-    uv
-  ];
-
-in
-pkgs.mkShell {
-  inherit nativeBuildInputs;
-
-  LD_LIBRARY_PATH = pkgs.lib.makeLibraryPath nativeBuildInputs;
-  TMPDIR = "/tmp";
-
-  shellHook = ''
-    set -e
-    uv venv .venv --python=3.12
-  '';
-}

docs/README.rst

@@ -1,5 +1,8 @@
 |logo| ``tractor``: distributed structurred concurrency
 
+|gh_actions|
+|docs|
+
 ``tractor`` is a `structured concurrency`_ (SC), multi-processing_ runtime built on trio_.
 
 Fundamentally, ``tractor`` provides parallelism via
@@ -63,13 +66,6 @@ Features
   - (WIP) a ``TaskMngr``: one-cancels-one style nursery supervisor.
 
 
-Status of `main` / infra
-------------------------
-
-- |gh_actions|
-- |docs|
-
-
 Install
 -------
 ``tractor`` is still in a *alpha-near-beta-stage* for many
@@ -693,11 +689,9 @@ channel`_!
 .. _msgspec: https://jcristharif.com/msgspec/
 .. _guest: https://trio.readthedocs.io/en/stable/reference-lowlevel.html?highlight=guest%20mode#using-guest-mode-to-run-trio-on-top-of-other-event-loops
 
-..
+
-   NOTE, on generating badge links from the UI
+.. |gh_actions| image:: https://img.shields.io/endpoint.svg?url=https%3A%2F%2Factions-badge.atrox.dev%2Fgoodboy%2Ftractor%2Fbadge&style=popout-square
-   https://docs.github.com/en/actions/how-tos/monitoring-and-troubleshooting-workflows/monitoring-workflows/adding-a-workflow-status-badge?ref=gitguardian-blog-automated-secrets-detection#using-the-ui
+    :target: https://actions-badge.atrox.dev/goodboy/tractor/goto
-.. |gh_actions| image:: https://github.com/goodboy/tractor/actions/workflows/ci.yml/badge.svg?branch=main
-    :target: https://github.com/goodboy/tractor/actions/workflows/ci.yml
 
 .. |docs| image:: https://readthedocs.org/projects/tractor/badge/?version=latest
     :target: https://tractor.readthedocs.io/en/latest/?badge=latest

examples/advanced_faults/ipc_failure_during_stream.py

@@ -16,7 +16,6 @@ from tractor import (
     ContextCancelled,
     MsgStream,
     _testing,
-    trionics,
 )
 import trio
 import pytest
@@ -63,8 +62,9 @@ async def recv_and_spawn_net_killers(
     await ctx.started()
     async with (
         ctx.open_stream() as stream,
-        trionics.collapse_eg(),
+        trio.open_nursery(
-        trio.open_nursery() as tn,
+            strict_exception_groups=False,
+        ) as tn,
     ):
         async for i in stream:
             print(f'child echoing {i}')
@@ -120,7 +120,6 @@ async def main(
     break_parent_ipc_after: int|bool = False,
     break_child_ipc_after: int|bool = False,
     pre_close: bool = False,
-    tpt_proto: str = 'tcp',
 
 ) -> None:
 
@@ -132,7 +131,6 @@ async def main(
             # a hang since it never engages due to broken IPC
             debug_mode=debug_mode,
             loglevel=loglevel,
-            enable_transports=[tpt_proto],
 
         ) as an,
     ):
@@ -147,8 +145,7 @@ async def main(
             _testing.expect_ctxc(
                 yay=(
                     break_parent_ipc_after
-                    or
+                    or break_child_ipc_after
-                    break_child_ipc_after
                 ),
                 # TODO: we CAN'T remove this right?
                 # since we need the ctxc to bubble up from either

examples/debugging/asyncio_bp.py

@@ -29,7 +29,7 @@ async def bp_then_error(
     to_trio.send_nowait('start')
 
     # NOTE: what happens here inside the hook needs some refinement..
-    # => seems like it's still `.debug._set_trace()` but
+    # => seems like it's still `._debug._set_trace()` but
     #    we set `Lock.local_task_in_debug = 'sync'`, we probably want
     #    some further, at least, meta-data about the task/actor in debug
     #    in terms of making it clear it's `asyncio` mucking about.

examples/debugging/restore_builtin_breakpoint.py

@@ -4,11 +4,6 @@ import sys
 import trio
 import tractor
 
-# ensure mod-path is correct!
-from tractor.devx.debug import (
-    _sync_pause_from_builtin as _sync_pause_from_builtin,
-)
-
 
 async def main() -> None:
 
@@ -18,23 +13,19 @@ async def main() -> None:
 
     async with tractor.open_nursery(
         debug_mode=True,
-        loglevel='devx',
+    ) as an:
-        maybe_enable_greenback=True,
+        assert an
-        # ^XXX REQUIRED to enable `breakpoint()` support (from sync
-        # fns) and thus required here to avoid an assertion err
-        # on the next line
-    ):
         assert (
             (pybp_var := os.environ['PYTHONBREAKPOINT'])
             ==
-            'tractor.devx.debug._sync_pause_from_builtin'
+            'tractor.devx._debug._sync_pause_from_builtin'
         )
 
         # TODO: an assert that verifies the hook has indeed been, hooked
         # XD
         assert (
             (pybp_hook := sys.breakpointhook)
-            is not tractor.devx.debug._set_trace
+            is not tractor.devx._debug._set_trace
         )
 
         print(

examples/debugging/root_cancelled_but_child_is_in_tty_lock.py

@@ -24,9 +24,10 @@ async def spawn_until(depth=0):
 
 
 async def main():
-    '''
+    """The main ``tractor`` routine.
-    The process tree should look as approximately as follows when the
+
-    debugger first engages:
+    The process tree should look as approximately as follows when the debugger
+    first engages:
 
     python examples/debugging/multi_nested_subactors_bp_forever.py
     ├─ python -m tractor._child --uid ('spawner1', '7eab8462 ...)
@@ -36,11 +37,10 @@ async def main():
     └─ python -m tractor._child --uid ('spawner0', '1d42012b ...)
        └─ python -m tractor._child --uid ('name_error', '6c2733b8 ...)
 
-    '''
+    """
     async with tractor.open_nursery(
         debug_mode=True,
-        loglevel='devx',
+        loglevel='warning'
-        enable_transports=['uds'],
     ) as n:
 
         # spawn both actors

examples/debugging/root_self_cancelled_w_error.py

@@ -1,35 +0,0 @@
-import trio
-import tractor
-
-
-async def main():
-    async with tractor.open_root_actor(
-        debug_mode=True,
-        loglevel='cancel',
-    ) as _root:
-
-        # manually trigger self-cancellation and wait
-        # for it to fully trigger.
-        _root.cancel_soon()
-        await _root._cancel_complete.wait()
-        print('root cancelled')
-
-        # now ensure we can still use the REPL
-        try:
-            await tractor.pause()
-        except trio.Cancelled as _taskc:
-            assert (root_cs := _root._root_tn.cancel_scope).cancel_called
-            # NOTE^^ above logic but inside `open_root_actor()` and
-            # passed to the `shield=` expression is effectively what
-            # we're testing here!
-            await tractor.pause(shield=root_cs.cancel_called)
-
-        # XXX, if shield logic *is wrong* inside `open_root_actor()`'s
-        # crash-handler block this should never be interacted,
-        # instead `trio.Cancelled` would be bubbled up: the original
-        # BUG.
-        assert 0
-
-
-if __name__ == '__main__':
-    trio.run(main)

examples/debugging/shield_hang_in_sub.py

@@ -37,7 +37,6 @@ async def main(
             enable_stack_on_sig=True,
             # maybe_enable_greenback=False,
             loglevel='devx',
-            enable_transports=['uds'],
         ) as an,
     ):
         ptl: tractor.Portal  = await an.start_actor(

examples/debugging/subactor_bp_in_ctx.py

@@ -33,11 +33,8 @@ async def just_bp(
 
 
 async def main():
-
     async with tractor.open_nursery(
         debug_mode=True,
-        enable_transports=['uds'],
-        loglevel='devx',
     ) as n:
         p = await n.start_actor(
             'bp_boi',

examples/debugging/sync_bp.py

@@ -6,7 +6,7 @@ import tractor
 
 # TODO: only import these when not running from test harness?
 # can we detect `pexpect` usage maybe?
-# from tractor.devx.debug import (
+# from tractor.devx._debug import (
 #     get_lock,
 #     get_debug_req,
 # )

examples/quick_cluster.py

@@ -23,8 +23,9 @@ async def main():
             modules=[__name__]
         ) as portal_map,
 
-        tractor.trionics.collapse_eg(),
+        trio.open_nursery(
-        trio.open_nursery() as tn,
+            strict_exception_groups=False,
+        ) as tn,
     ):
 
         for (name, portal) in portal_map.items():

examples/service_discovery.py

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

examples/trio/lockacquire_not_unmasked.py

@@ -1,85 +0,0 @@
-from contextlib import (
-    asynccontextmanager as acm,
-)
-from functools import partial
-
-import tractor
-import trio
-
-
-log = tractor.log.get_logger(
-    name=__name__
-)
-
-_lock: trio.Lock|None = None
-
-
-@acm
-async def acquire_singleton_lock(
-) -> None:
-    global _lock
-    if _lock is None:
-        log.info('Allocating LOCK')
-        _lock = trio.Lock()
-
-    log.info('TRYING TO LOCK ACQUIRE')
-    async with _lock:
-        log.info('ACQUIRED')
-        yield _lock
-
-    log.info('RELEASED')
-
-
-
-async def hold_lock_forever(
-    task_status=trio.TASK_STATUS_IGNORED
-):
-    async with (
-        tractor.trionics.maybe_raise_from_masking_exc(),
-        acquire_singleton_lock() as lock,
-    ):
-        task_status.started(lock)
-        await trio.sleep_forever()
-
-
-async def main(
-    ignore_special_cases: bool,
-    loglevel: str = 'info',
-    debug_mode: bool = True,
-):
-    async with (
-        trio.open_nursery() as tn,
-
-        # tractor.trionics.maybe_raise_from_masking_exc()
-        # ^^^ XXX NOTE, interestingly putting the unmasker
-        # here does not exhibit the same behaviour ??
-    ):
-        if not ignore_special_cases:
-            from tractor.trionics import _taskc
-            _taskc._mask_cases.clear()
-
-        _lock = await tn.start(
-            hold_lock_forever,
-        )
-        with trio.move_on_after(0.2):
-            await tn.start(
-                hold_lock_forever,
-            )
-
-        tn.cancel_scope.cancel()
-
-
-# XXX, manual test as script
-if __name__ == '__main__':
-    tractor.log.get_console_log(level='info')
-    for case in [True, False]:
-        log.info(
-            f'\n'
-            f'------ RUNNING SCRIPT TRIAL ------\n'
-            f'ignore_special_cases: {case!r}\n'
-        )
-        trio.run(partial(
-            main,
-            ignore_special_cases=case,
-            loglevel='info',
-        ))

examples/trio/send_chan_aclose_masks_beg.py

@@ -1,195 +0,0 @@
-from contextlib import (
-    contextmanager as cm,
-    # TODO, any diff in async case(s)??
-    # asynccontextmanager as acm,
-)
-from functools import partial
-
-import tractor
-import trio
-
-
-log = tractor.log.get_logger(
-    name=__name__
-)
-
-
-@cm
-def teardown_on_exc(
-    raise_from_handler: bool = False,
-):
-    '''
-    You could also have a teardown handler which catches any exc and
-    does some required teardown. In this case the problem is
-    compounded UNLESS you ensure the handler's scope is OUTSIDE the
-    `ux.aclose()`.. that is in the caller's enclosing scope.
-
-    '''
-    try:
-        yield
-    except BaseException as _berr:
-        berr = _berr
-        log.exception(
-            f'Handling termination teardown in child due to,\n'
-            f'{berr!r}\n'
-        )
-        if raise_from_handler:
-            # XXX teardown ops XXX
-            # on termination these steps say need to be run to
-            # ensure wider system consistency (like the state of
-            # remote connections/services).
-            #
-            # HOWEVER, any bug in this teardown code is also
-            # masked by the `tx.aclose()`!
-            # this is also true if `_tn.cancel_scope` is
-            # `.cancel_called` by the parent in a graceful
-            # request case..
-
-            # simulate a bug in teardown handler.
-            raise RuntimeError(
-                'woopsie teardown bug!'
-            )
-
-        raise  # no teardown bug.
-
-
-async def finite_stream_to_rent(
-    tx: trio.abc.SendChannel,
-    child_errors_mid_stream: bool,
-    raise_unmasked: bool,
-
-    task_status: trio.TaskStatus[
-        trio.CancelScope,
-    ] = trio.TASK_STATUS_IGNORED,
-):
-    async with (
-        # XXX without this unmasker the mid-streaming RTE is never
-        # reported since it is masked by the `tx.aclose()`
-        # call which in turn raises `Cancelled`!
-        #
-        # NOTE, this is WITHOUT doing any exception handling
-        # inside the child  task!
-        #
-        # TODO, uncomment next LoC to see the supprsessed beg[RTE]!
-        tractor.trionics.maybe_raise_from_masking_exc(
-            raise_unmasked=raise_unmasked,
-        ),
-
-        tx as tx,  # .aclose() is the guilty masker chkpt!
-
-        # XXX, this ONLY matters in the
-        # `child_errors_mid_stream=False` case oddly!?
-        # THAT IS, if no tn is opened in that case then the
-        # test will not fail; it raises the RTE correctly?
-        #
-        # -> so it seems this new scope somehow affects the form of
-        #    eventual in the parent EG?
-        tractor.trionics.maybe_open_nursery(
-            nursery=(
-                None
-                if not child_errors_mid_stream
-                else True
-            ),
-        ) as _tn,
-    ):
-        # pass our scope back to parent for supervision\
-        # control.
-        cs: trio.CancelScope|None = (
-            None
-            if _tn is True
-            else _tn.cancel_scope
-        )
-        task_status.started(cs)
-
-        with teardown_on_exc(
-            raise_from_handler=not child_errors_mid_stream,
-        ):
-            for i in range(100):
-                log.debug(
-                    f'Child tx {i!r}\n'
-                )
-                if (
-                    child_errors_mid_stream
-                    and
-                    i == 66
-                ):
-                    # oh wait but WOOPS there's a bug
-                    # in that teardown code!?
-                    raise RuntimeError(
-                        'woopsie, a mid-streaming bug!?'
-                    )
-
-                await tx.send(i)
-
-
-async def main(
-    # TODO! toggle this for the 2 cases!
-    # 1. child errors mid-stream while parent is also requesting
-    #   (graceful) cancel of that child streamer.
-    #
-    # 2. child contains a teardown handler which contains a
-    #   bug and raises.
-    #
-    child_errors_mid_stream: bool,
-
-    raise_unmasked: bool = False,
-    loglevel: str = 'info',
-):
-    tractor.log.get_console_log(level=loglevel)
-
-    # the `.aclose()` being checkpoints on these
-    # is the source of the problem..
-    tx, rx = trio.open_memory_channel(1)
-
-    async with (
-        tractor.trionics.collapse_eg(),
-        trio.open_nursery() as tn,
-        rx as rx,
-    ):
-        _child_cs = await tn.start(
-            partial(
-                finite_stream_to_rent,
-                child_errors_mid_stream=child_errors_mid_stream,
-                raise_unmasked=raise_unmasked,
-                tx=tx,
-            )
-        )
-        async for msg in rx:
-            log.debug(
-                f'Rent rx {msg!r}\n'
-            )
-
-            # simulate some external cancellation
-            # request **JUST BEFORE** the child errors.
-            if msg == 65:
-                log.cancel(
-                    f'Cancelling parent on,\n'
-                    f'msg={msg}\n'
-                    f'\n'
-                    f'Simulates OOB cancel request!\n'
-                )
-                tn.cancel_scope.cancel()
-
-
-# XXX, manual test as script
-if __name__ == '__main__':
-    tractor.log.get_console_log(level='info')
-    for case in [True, False]:
-        log.info(
-            f'\n'
-            f'------ RUNNING SCRIPT TRIAL ------\n'
-            f'child_errors_midstream: {case!r}\n'
-        )
-        try:
-            trio.run(partial(
-                main,
-                child_errors_mid_stream=case,
-                # raise_unmasked=True,
-                loglevel='info',
-            ))
-        except Exception as _exc:
-            exc = _exc
-            log.exception(
-                'Should have raised an RTE or Cancelled?\n'
-            )
-            breakpoint()

pyproject.toml

@@ -45,8 +45,6 @@ dependencies = [
   "pdbp>=1.6,<2", # windows only (from `pdbp`)
   # typed IPC msging
   "msgspec>=0.19.0",
-  "cffi>=1.17.1",
-  "bidict>=0.23.1",
 ]
 
 # ------ project ------
@@ -61,13 +59,9 @@ dev = [
   # `tractor.devx` tooling
   "greenback>=1.2.1,<2",
   "stackscope>=0.2.2,<0.3",
-  # ^ requires this?
-  "typing-extensions>=4.14.1",
-
   "pyperclip>=1.9.0",
   "prompt-toolkit>=3.0.50",
   "xonsh>=0.19.2",
-  "psutil>=7.0.0",
 ]
 # TODO, add these with sane versions; were originally in
 # `requirements-docs.txt`..

tests/conftest.py

@@ -1,27 +1,24 @@
 """
-Top level of the testing suites!
+``tractor`` testing!!
-
 """
-from __future__ import annotations
 import sys
 import subprocess
 import os
+import random
 import signal
 import platform
 import time
 
 import pytest
+import tractor
 from tractor._testing import (
     examples_dir as examples_dir,
     tractor_test as tractor_test,
     expect_ctxc as expect_ctxc,
 )
 
-pytest_plugins: list[str] = [
+# TODO: include wtv plugin(s) we build in `._testing.pytest`?
-    'pytester',
+pytest_plugins = ['pytester']
-    'tractor._testing.pytest',
-]
-
 
 # Sending signal.SIGINT on subprocess fails on windows. Use CTRL_* alternatives
 if platform.system() == 'Windows':
@@ -33,11 +30,7 @@ else:
     _KILL_SIGNAL = signal.SIGKILL
     _INT_SIGNAL = signal.SIGINT
     _INT_RETURN_CODE = 1 if sys.version_info < (3, 8) else -signal.SIGINT.value
-    _PROC_SPAWN_WAIT = (
+    _PROC_SPAWN_WAIT = 0.6 if sys.version_info < (3, 7) else 0.4
-        0.6
-        if sys.version_info < (3, 7)
-        else 0.4
-    )
 
 
 no_windows = pytest.mark.skipif(
@@ -46,12 +39,7 @@ no_windows = pytest.mark.skipif(
 )
 
 
-def pytest_addoption(
+def pytest_addoption(parser):
-    parser: pytest.Parser,
-):
-    # ?TODO? should this be exposed from our `._testing.pytest`
-    # plugin or should we make it more explicit with `--tl` for
-    # tractor logging like we do in other client projects?
     parser.addoption(
         "--ll",
         action="store",
@@ -59,10 +47,42 @@ def pytest_addoption(
         default='ERROR', help="logging level to set when testing"
     )
 
+    parser.addoption(
+        "--spawn-backend",
+        action="store",
+        dest='spawn_backend',
+        default='trio',
+        help="Processing spawning backend to use for test run",
+    )
+
+    parser.addoption(
+        "--tpdb", "--debug-mode",
+        action="store_true",
+        dest='tractor_debug_mode',
+        # default=False,
+        help=(
+            'Enable a flag that can be used by tests to to set the '
+            '`debug_mode: bool` for engaging the internal '
+            'multi-proc debugger sys.'
+        ),
+    )
+
+
+def pytest_configure(config):
+    backend = config.option.spawn_backend
+    tractor._spawn.try_set_start_method(backend)
+
+
+@pytest.fixture(scope='session')
+def debug_mode(request):
+    debug_mode: bool = request.config.option.tractor_debug_mode
+    # if debug_mode:
+    #     breakpoint()
+    return debug_mode
+
 
 @pytest.fixture(scope='session', autouse=True)
 def loglevel(request):
-    import tractor
     orig = tractor.log._default_loglevel
     level = tractor.log._default_loglevel = request.config.option.loglevel
     tractor.log.get_console_log(level)
@@ -70,44 +90,106 @@ def loglevel(request):
     tractor.log._default_loglevel = orig
 
 
+@pytest.fixture(scope='session')
+def spawn_backend(request) -> str:
+    return request.config.option.spawn_backend
+
+
+# @pytest.fixture(scope='function', autouse=True)
+# def debug_enabled(request) -> str:
+#     from tractor import _state
+#     if _state._runtime_vars['_debug_mode']:
+#         breakpoint()
+
 _ci_env: bool = os.environ.get('CI', False)
 
 
 @pytest.fixture(scope='session')
 def ci_env() -> bool:
     '''
-    Detect CI environment.
+    Detect CI envoirment.
 
     '''
     return _ci_env
 
 
-def sig_prog(
+# TODO: also move this to `._testing` for now?
-    proc: subprocess.Popen,
+# -[ ] possibly generalize and re-use for multi-tree spawning
-    sig: int,
+#    along with the new stuff for multi-addrs in distribute_dis
-    canc_timeout: float = 0.1,
+#    branch?
-) -> int:
+#
+# choose randomly at import time
+_reg_addr: tuple[str, int] = (
+    '127.0.0.1',
+    random.randint(1000, 9999),
+)
+
+
+@pytest.fixture(scope='session')
+def reg_addr() -> tuple[str, int]:
+
+    # globally override the runtime to the per-test-session-dynamic
+    # addr so that all tests never conflict with any other actor
+    # tree using the default.
+    from tractor import _root
+    _root._default_lo_addrs = [_reg_addr]
+
+    return _reg_addr
+
+
+def pytest_generate_tests(metafunc):
+    spawn_backend = metafunc.config.option.spawn_backend
+
+    if not spawn_backend:
+        # XXX some weird windows bug with `pytest`?
+        spawn_backend = 'trio'
+
+    # TODO: maybe just use the literal `._spawn.SpawnMethodKey`?
+    assert spawn_backend in (
+        'mp_spawn',
+        'mp_forkserver',
+        'trio',
+    )
+
+    # NOTE: used to be used to dyanmically parametrize tests for when
+    # you just passed --spawn-backend=`mp` on the cli, but now we expect
+    # that cli input to be manually specified, BUT, maybe we'll do
+    # something like this again in the future?
+    if 'start_method' in metafunc.fixturenames:
+        metafunc.parametrize("start_method", [spawn_backend], scope='module')
+
+
+# TODO: a way to let test scripts (like from `examples/`)
+# guarantee they won't registry addr collide!
+# @pytest.fixture
+# def open_test_runtime(
+#     reg_addr: tuple,
+# ) -> AsyncContextManager:
+#     return partial(
+#         tractor.open_nursery,
+#         registry_addrs=[reg_addr],
+#     )
+
+
+def sig_prog(proc, sig):
     "Kill the actor-process with ``sig``."
     proc.send_signal(sig)
-    time.sleep(canc_timeout)
+    time.sleep(0.1)
     if not proc.poll():
         # TODO: why sometimes does SIGINT not work on teardown?
         # seems to happen only when trace logging enabled?
         proc.send_signal(_KILL_SIGNAL)
-    ret: int = proc.wait()
+    ret = proc.wait()
     assert ret
 
 
 # TODO: factor into @cm and move to `._testing`?
 @pytest.fixture
 def daemon(
-    debug_mode: bool,
     loglevel: str,
-    testdir: pytest.Pytester,
+    testdir,
     reg_addr: tuple[str, int],
-    tpt_proto: str,
+):
-
-) -> subprocess.Popen:
     '''
     Run a daemon root actor as a separate actor-process tree and
     "remote registrar" for discovery-protocol related tests.
@@ -118,100 +200,28 @@ def daemon(
         loglevel: str = 'info'
 
     code: str = (
-        "import tractor; "
+            "import tractor; "
-        "tractor.run_daemon([], "
+            "tractor.run_daemon([], registry_addrs={reg_addrs}, loglevel={ll})"
-        "registry_addrs={reg_addrs}, "
-        "debug_mode={debug_mode}, "
-        "loglevel={ll})"
     ).format(
         reg_addrs=str([reg_addr]),
         ll="'{}'".format(loglevel) if loglevel else None,
-        debug_mode=debug_mode,
     )
     cmd: list[str] = [
         sys.executable,
         '-c', code,
     ]
-    # breakpoint()
     kwargs = {}
     if platform.system() == 'Windows':
         # without this, tests hang on windows forever
         kwargs['creationflags'] = subprocess.CREATE_NEW_PROCESS_GROUP
 
-    proc: subprocess.Popen = testdir.popen(
+    proc = testdir.popen(
         cmd,
+        stdout=subprocess.PIPE,
+        stderr=subprocess.PIPE,
         **kwargs,
     )
-
-    # UDS sockets are **really** fast to bind()/listen()/connect()
-    # so it's often required that we delay a bit more starting
-    # the first actor-tree..
-    if tpt_proto == 'uds':
-        global _PROC_SPAWN_WAIT
-        _PROC_SPAWN_WAIT = 0.6
-
-    time.sleep(_PROC_SPAWN_WAIT)
-
     assert not proc.returncode
+    time.sleep(_PROC_SPAWN_WAIT)
     yield proc
     sig_prog(proc, _INT_SIGNAL)
-
-    # XXX! yeah.. just be reaaal careful with this bc sometimes it
-    # can lock up on the `_io.BufferedReader` and hang..
-    stderr: str = proc.stderr.read().decode()
-    if stderr:
-        print(
-            f'Daemon actor tree produced STDERR:\n'
-            f'{proc.args}\n'
-            f'\n'
-            f'{stderr}\n'
-        )
-    if proc.returncode != -2:
-        raise RuntimeError(
-            'Daemon actor tree failed !?\n'
-            f'{proc.args}\n'
-        )
-
-
-# @pytest.fixture(autouse=True)
-# def shared_last_failed(pytestconfig):
-#     val = pytestconfig.cache.get("example/value", None)
-#     breakpoint()
-#     if val is None:
-#         pytestconfig.cache.set("example/value", val)
-#     return val
-
-
-# TODO: a way to let test scripts (like from `examples/`)
-# guarantee they won't `registry_addrs` collide!
-# -[ ] maybe use some kinda standard `def main()` arg-spec that
-#     we can introspect from a fixture that is called from the test
-#     body?
-# -[ ] test and figure out typing for below prototype! Bp
-#
-# @pytest.fixture
-# def set_script_runtime_args(
-#     reg_addr: tuple,
-# ) -> Callable[[...], None]:
-
-#     def import_n_partial_in_args_n_triorun(
-#         script: Path,  # under examples?
-#         **runtime_args,
-#     ) -> Callable[[], Any]:  # a `partial`-ed equiv of `trio.run()`
-
-#         # NOTE, below is taken from
-#         # `.test_advanced_faults.test_ipc_channel_break_during_stream`
-#         mod: ModuleType = import_path(
-#             examples_dir() / 'advanced_faults'
-#             / 'ipc_failure_during_stream.py',
-#             root=examples_dir(),
-#             consider_namespace_packages=False,
-#         )
-#         return partial(
-#             trio.run,
-#             partial(
-#                 mod.main,
-#                 **runtime_args,
-#             )
-#         )
-#     return import_n_partial_in_args_n_triorun

tests/devx/conftest.py

@@ -2,11 +2,9 @@
 `tractor.devx.*` tooling sub-pkg test space.
 
 '''
-from __future__ import annotations
 import time
 from typing import (
     Callable,
-    TYPE_CHECKING,
 )
 
 import pytest
@@ -18,7 +16,7 @@ from pexpect.spawnbase import SpawnBase
 from tractor._testing import (
     mk_cmd,
 )
-from tractor.devx.debug import (
+from tractor.devx._debug import (
     _pause_msg as _pause_msg,
     _crash_msg as _crash_msg,
     _repl_fail_msg as _repl_fail_msg,
@@ -28,22 +26,14 @@ from ..conftest import (
     _ci_env,
 )
 
-if TYPE_CHECKING:
-    from pexpect import pty_spawn
-
-
-# a fn that sub-instantiates a `pexpect.spawn()`
-# and returns it.
-type PexpectSpawner = Callable[[str], pty_spawn.spawn]
-
 
 @pytest.fixture
 def spawn(
-    start_method: str,
+    start_method,
     testdir: pytest.Pytester,
     reg_addr: tuple[str, int],
 
-) -> PexpectSpawner:
+) -> Callable[[str], None]:
     '''
     Use the `pexpect` module shipped via `testdir.spawn()` to
     run an `./examples/..` script by name.
@@ -69,7 +59,7 @@ def spawn(
     def _spawn(
         cmd: str,
         **mkcmd_kwargs,
-    ) -> pty_spawn.spawn:
+    ):
         unset_colors()
         return testdir.spawn(
             cmd=mk_cmd(
@@ -83,7 +73,7 @@ def spawn(
         )
 
     # such that test-dep can pass input script name.
-    return _spawn  # the `PexpectSpawner`, type alias.
+    return _spawn
 
 
 @pytest.fixture(
@@ -121,7 +111,7 @@ def ctlc(
         # XXX: disable pygments highlighting for auto-tests
         # since some envs (like actions CI) will struggle
         # the the added color-char encoding..
-        from tractor.devx.debug import TractorConfig
+        from tractor.devx._debug import TractorConfig
         TractorConfig.use_pygements = False
 
     yield use_ctlc

tests/devx/test_debugger.py

@@ -1,23 +1,19 @@
 """
 That "native" debug mode better work!
 
-All these tests can be understood (somewhat) by running the
+All these tests can be understood (somewhat) by running the equivalent
-equivalent `examples/debugging/` scripts manually.
+`examples/debugging/` scripts manually.
 
 TODO:
-  - none of these tests have been run successfully on windows yet but
+    - none of these tests have been run successfully on windows yet but
-    there's been manual testing that verified it works.
+      there's been manual testing that verified it works.
-  - wonder if any of it'll work on OS X?
+    - wonder if any of it'll work on OS X?
 
 """
-from __future__ import annotations
 from functools import partial
 import itertools
 import platform
 import time
-from typing import (
-    TYPE_CHECKING,
-)
 
 import pytest
 from pexpect.exceptions import (
@@ -38,9 +34,6 @@ from .conftest import (
     assert_before,
 )
 
-if TYPE_CHECKING:
-    from ..conftest import PexpectSpawner
-
 # TODO: The next great debugger audit could be done by you!
 # - recurrent entry to breakpoint() from single actor *after* and an
 #   error in another task?
@@ -317,6 +310,7 @@ def test_subactor_breakpoint(
 
     assert in_prompt_msg(
         child, [
+        'MessagingError:',
         'RemoteActorError:',
          "('breakpoint_forever'",
          'bdb.BdbQuit',
@@ -534,7 +528,7 @@ def test_multi_daemon_subactors(
     # now the root actor won't clobber the bp_forever child
     # during it's first access to the debug lock, but will instead
     # wait for the lock to release, by the edge triggered
-    # ``devx.debug.Lock.no_remote_has_tty`` event before sending cancel messages
+    # ``devx._debug.Lock.no_remote_has_tty`` event before sending cancel messages
     # (via portals) to its underlings B)
 
     # at some point here there should have been some warning msg from
@@ -925,7 +919,6 @@ def test_post_mortem_api(
             "<Task 'name_error'",
             "NameError",
             "('child'",
-            'getattr(doggypants)',  # exc-LoC
         ]
     )
     if ctlc:
@@ -942,8 +935,8 @@ def test_post_mortem_api(
             "<Task '__main__.main'",
             "('root'",
             "NameError",
+            "tractor.post_mortem()",
             "src_uid=('child'",
-            "tractor.post_mortem()",  # in `main()`-LoC
         ]
     )
     if ctlc:
@@ -961,10 +954,6 @@ def test_post_mortem_api(
             "('root'",
             "NameError",
             "src_uid=('child'",
-
-            # raising line in `main()` but from crash-handling
-            # in `tractor.open_nursery()`.
-            'async with p.open_context(name_error) as (ctx, first):',
         ]
     )
     if ctlc:
@@ -1074,136 +1063,6 @@ def test_shield_pause(
     child.expect(EOF)
 
 
-@pytest.mark.parametrize(
-    'quit_early', [False, True]
-)
-def test_ctxep_pauses_n_maybe_ipc_breaks(
-    spawn: PexpectSpawner,
-    quit_early: bool,
-):
-    '''
-    Audit generator embedded `.pause()`es from within a `@context`
-    endpoint with a chan close at the end, requiring that ctl-c is
-    mashed and zombie reaper kills sub with no hangs.
-
-    '''
-    child = spawn('subactor_bp_in_ctx')
-    child.expect(PROMPT)
-
-    # 3 iters for the `gen()` pause-points
-    for i in range(3):
-        assert_before(
-            child,
-            [
-                _pause_msg,
-                "('bp_boi'",  # actor name
-                "<Task 'just_bp'",  # task name
-            ]
-        )
-        if (
-            i == 1
-            and
-            quit_early
-        ):
-            child.sendline('q')
-            child.expect(PROMPT)
-            assert_before(
-                child,
-                ["tractor._exceptions.RemoteActorError: remote task raised a 'BdbQuit'",
-                 "bdb.BdbQuit",
-                 "('bp_boi'",
-                ]
-            )
-            child.sendline('c')
-            child.expect(EOF)
-            assert_before(
-                child,
-                ["tractor._exceptions.RemoteActorError: remote task raised a 'BdbQuit'",
-                 "bdb.BdbQuit",
-                 "('bp_boi'",
-                ]
-            )
-            break  # end-of-test
-
-        child.sendline('c')
-        try:
-            child.expect(PROMPT)
-        except TIMEOUT:
-            # no prompt since we hang due to IPC chan purposely
-            # closed so verify we see error reporting as well as
-            # a failed crash-REPL request msg and can CTL-c our way
-            # out.
-            assert_before(
-                child,
-                ['peer IPC channel closed abruptly?',
-                 'another task closed this fd',
-                 'Debug lock request was CANCELLED?',
-                 "TransportClosed: 'MsgpackUDSStream' was already closed locally ?",]
-
-                # XXX races on whether these show/hit?
-                 # 'Failed to REPl via `_pause()` You called `tractor.pause()` from an already cancelled scope!',
-                 # 'AssertionError',
-            )
-            # OSc(ancel) the hanging tree
-            do_ctlc(
-                child=child,
-                expect_prompt=False,
-            )
-            child.expect(EOF)
-            assert_before(
-                child,
-                ['KeyboardInterrupt'],
-            )
-
-
-def test_crash_handling_within_cancelled_root_actor(
-    spawn: PexpectSpawner,
-):
-    '''
-    Ensure that when only a root-actor is started via `open_root_actor()`
-    we can crash-handle in debug-mode despite self-cancellation.
-
-    More-or-less ensures we conditionally shield the pause in
-    `._root.open_root_actor()`'s `await debug._maybe_enter_pm()`
-    call.
-
-    '''
-    child = spawn('root_self_cancelled_w_error')
-    child.expect(PROMPT)
-
-    assert_before(
-        child,
-        [
-            "Actor.cancel_soon()` was called!",
-            "root cancelled",
-            _pause_msg,
-            "('root'",  # actor name
-        ]
-    )
-
-    child.sendline('c')
-    child.expect(PROMPT)
-    assert_before(
-        child,
-        [
-            _crash_msg,
-            "('root'",  # actor name
-            "AssertionError",
-            "assert 0",
-        ]
-    )
-
-    child.sendline('c')
-    child.expect(EOF)
-    assert_before(
-        child,
-        [
-            "AssertionError",
-            "assert 0",
-        ]
-    )
-
-
 # TODO: better error for "non-ideal" usage from the root actor.
 # -[ ] if called from an async scope emit a message that suggests
 #    using `await tractor.pause()` instead since it's less overhead

tests/devx/test_tooling.py

@@ -13,16 +13,9 @@ TODO:
   when debugging a problem inside the stack vs. in their app.
 
 '''
-from __future__ import annotations
-from contextlib import (
-    contextmanager as cm,
-)
 import os
 import signal
 import time
-from typing import (
-    TYPE_CHECKING,
-)
 
 from .conftest import (
     expect,
@@ -31,19 +24,14 @@ from .conftest import (
     PROMPT,
     _pause_msg,
 )
-
-import pytest
 from pexpect.exceptions import (
     # TIMEOUT,
     EOF,
 )
 
-if TYPE_CHECKING:
-    from ..conftest import PexpectSpawner
-
 
 def test_shield_pause(
-    spawn: PexpectSpawner,
+    spawn,
 ):
     '''
     Verify the `tractor.pause()/.post_mortem()` API works inside an
@@ -121,11 +109,9 @@ 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(
@@ -140,7 +126,7 @@ def test_shield_pause(
 
 
 def test_breakpoint_hook_restored(
-    spawn: PexpectSpawner,
+    spawn,
 ):
     '''
     Ensures our actor runtime sets a custom `breakpoint()` hook
@@ -154,22 +140,16 @@ def test_breakpoint_hook_restored(
     child = spawn('restore_builtin_breakpoint')
 
     child.expect(PROMPT)
-    try:
+    assert_before(
-        assert_before(
+        child,
-            child,
+        [
-            [
+            _pause_msg,
-                _pause_msg,
+            "<Task '__main__.main'",
-                "<Task '__main__.main'",
+            "('root'",
-                "('root'",
+            "first bp, tractor hook set",
-                "first bp, tractor hook set",
+        ]
-            ]
+    )
-        )
+    child.sendline('c')
-    # XXX if the above raises `AssertionError`, without sending
-    # the final 'continue' cmd to the REPL-active sub-process,
-    # we'll hang waiting for that pexpect instance to terminate..
-    finally:
-        child.sendline('c')
-
     child.expect(PROMPT)
     assert_before(
         child,
@@ -190,117 +170,3 @@ def test_breakpoint_hook_restored(
     )
     child.sendline('c')
     child.expect(EOF)
-
-
-
-_to_raise = Exception('Triggering a crash')
-
-
-@pytest.mark.parametrize(
-    'to_raise',
-    [
-        None,
-        _to_raise,
-        RuntimeError('Never crash handle this!'),
-    ],
-)
-@pytest.mark.parametrize(
-    'raise_on_exit',
-    [
-        True,
-        [type(_to_raise)],
-        False,
-    ]
-)
-def test_crash_handler_cms(
-    debug_mode: bool,
-    to_raise: Exception,
-    raise_on_exit: bool|list[Exception],
-):
-    '''
-    Verify the `.devx.open_crash_handler()` API(s) by also
-    (conveniently enough) tesing its `repl_fixture: ContextManager`
-    param support which for this suite allows use to avoid use of
-    a `pexpect`-style-test since we use the fixture to avoid actually
-    entering `PdbpREPL.iteract()` :smirk:
-
-    '''
-    import tractor
-    # import trio
-
-    # state flags
-    repl_acquired: bool = False
-    repl_released: bool = False
-
-    @cm
-    def block_repl_ux(
-        repl: tractor.devx.debug.PdbREPL,
-        maybe_bxerr: (
-            tractor.devx._debug.BoxedMaybeException
-            |None
-        ) = None,
-        enter_repl: bool = True,
-
-    ) -> bool:
-        '''
-        Set pre/post-REPL state vars and bypass actual conole
-        interaction.
-
-        '''
-        nonlocal repl_acquired, repl_released
-
-        # task: trio.Task = trio.lowlevel.current_task()
-        # print(f'pre-REPL active_task={task.name}')
-
-        print('pre-REPL')
-        repl_acquired = True
-        yield False  # never actually .interact()
-        print('post-REPL')
-        repl_released = True
-
-    try:
-        # TODO, with runtime's `debug_mode` setting
-        # -[ ] need to open runtime tho obvi..
-        #
-        # with tractor.devx.maybe_open_crash_handler(
-        #     pdb=True,
-
-        with tractor.devx.open_crash_handler(
-            raise_on_exit=raise_on_exit,
-            repl_fixture=block_repl_ux
-        ) as bxerr:
-            if to_raise is not None:
-                raise to_raise
-
-    except Exception as _exc:
-        exc = _exc
-        if (
-            raise_on_exit is True
-            or
-            type(to_raise) in raise_on_exit
-        ):
-            assert (
-                exc
-                is
-                to_raise
-                is
-                bxerr.value
-            )
-
-        else:
-            raise
-    else:
-        assert (
-            to_raise is None
-            or
-            not raise_on_exit
-            or
-            type(to_raise) not in raise_on_exit
-        )
-        assert bxerr.value is to_raise
-
-    assert bxerr.raise_on_exit == raise_on_exit
-
-    if to_raise is not None:
-        assert repl_acquired
-        assert repl_released

tests/ipc/__init__.py

@@ -1,4 +0,0 @@
-'''
-`tractor.ipc` subsystem(s)/unit testing suites.
-
-'''

tests/ipc/test_each_tpt.py

@@ -1,114 +0,0 @@
-'''
-Unit-ish tests for specific IPC transport protocol backends.
-
-'''
-from __future__ import annotations
-from pathlib import Path
-
-import pytest
-import trio
-import tractor
-from tractor import (
-    Actor,
-    _state,
-    _addr,
-)
-
-
-@pytest.fixture
-def bindspace_dir_str() -> str:
-
-    rt_dir: Path = tractor._state.get_rt_dir()
-    bs_dir: Path = rt_dir / 'doggy'
-    bs_dir_str: str = str(bs_dir)
-    assert not bs_dir.is_dir()
-
-    yield bs_dir_str
-
-    # delete it on suite teardown.
-    # ?TODO? should we support this internally
-    # or is leaking it ok?
-    if bs_dir.is_dir():
-        bs_dir.rmdir()
-
-
-def test_uds_bindspace_created_implicitly(
-    debug_mode: bool,
-    bindspace_dir_str: str,
-):
-    registry_addr: tuple = (
-        f'{bindspace_dir_str}',
-        'registry@doggy.sock',
-    )
-    bs_dir_str: str = registry_addr[0]
-
-    # XXX, ensure bindspace-dir DNE beforehand!
-    assert not Path(bs_dir_str).is_dir()
-
-    async def main():
-        async with tractor.open_nursery(
-            enable_transports=['uds'],
-            registry_addrs=[registry_addr],
-            debug_mode=debug_mode,
-        ) as _an:
-
-            # XXX MUST be created implicitly by
-            # `.ipc._uds.start_listener()`!
-            assert Path(bs_dir_str).is_dir()
-
-            root: Actor = tractor.current_actor()
-            assert root.is_registrar
-
-            assert registry_addr in root.reg_addrs
-            assert (
-                registry_addr
-                in
-                _state._runtime_vars['_registry_addrs']
-            )
-            assert (
-                _addr.wrap_address(registry_addr)
-                in
-                root.registry_addrs
-            )
-
-    trio.run(main)
-
-
-def test_uds_double_listen_raises_connerr(
-    debug_mode: bool,
-    bindspace_dir_str: str,
-):
-    registry_addr: tuple = (
-        f'{bindspace_dir_str}',
-        'registry@doggy.sock',
-    )
-
-    async def main():
-        async with tractor.open_nursery(
-            enable_transports=['uds'],
-            registry_addrs=[registry_addr],
-            debug_mode=debug_mode,
-        ) as _an:
-
-            # runtime up
-            root: Actor = tractor.current_actor()
-
-            from tractor.ipc._uds import (
-                start_listener,
-                UDSAddress,
-            )
-            ya_bound_addr: UDSAddress = root.registry_addrs[0]
-            try:
-                await start_listener(
-                    addr=ya_bound_addr,
-                )
-            except ConnectionError as connerr:
-                assert type(src_exc := connerr.__context__) is OSError
-                assert 'Address already in use' in src_exc.args
-                # complete, exit test.
-
-            else:
-                pytest.fail('It dint raise a connerr !?')
-
-
-    trio.run(main)

tests/ipc/test_multi_tpt.py

@@ -1,95 +0,0 @@
-'''
-Verify the `enable_transports` param drives various
-per-root/sub-actor IPC endpoint/server settings.
-
-'''
-from __future__ import annotations
-
-import pytest
-import trio
-import tractor
-from tractor import (
-    Actor,
-    Portal,
-    ipc,
-    msg,
-    _state,
-    _addr,
-)
-
-@tractor.context
-async def chk_tpts(
-    ctx: tractor.Context,
-    tpt_proto_key: str,
-):
-    rtvars = _state._runtime_vars
-    assert (
-        tpt_proto_key
-        in
-        rtvars['_enable_tpts']
-    )
-    actor: Actor = tractor.current_actor()
-    spec: msg.types.SpawnSpec = actor._spawn_spec
-    assert spec._runtime_vars == rtvars
-
-    # ensure individual IPC ep-addr types
-    serv: ipc._server.Server = actor.ipc_server
-    addr: ipc._types.Address
-    for addr in serv.addrs:
-        assert addr.proto_key == tpt_proto_key
-
-    # Actor delegate-props enforcement
-    assert (
-        actor.accept_addrs
-        ==
-        serv.accept_addrs
-    )
-
-    await ctx.started(serv.accept_addrs)
-
-
-# TODO, parametrize over mis-matched-proto-typed `registry_addrs`
-# since i seems to work in `piker` but not exactly sure if both tcp
-# & uds are being deployed then?
-#
-@pytest.mark.parametrize(
-    'tpt_proto_key',
-    ['tcp', 'uds'],
-    ids=lambda item: f'ipc_tpt={item!r}'
-)
-def test_root_passes_tpt_to_sub(
-    tpt_proto_key: str,
-    reg_addr: tuple,
-    debug_mode: bool,
-):
-    async def main():
-        async with tractor.open_nursery(
-            enable_transports=[tpt_proto_key],
-            registry_addrs=[reg_addr],
-            debug_mode=debug_mode,
-        ) as an:
-
-            assert (
-                tpt_proto_key
-                in
-                _state._runtime_vars['_enable_tpts']
-            )
-
-            ptl: Portal = await an.start_actor(
-                name='sub',
-                enable_modules=[__name__],
-            )
-            async with ptl.open_context(
-                chk_tpts,
-                tpt_proto_key=tpt_proto_key,
-            ) as (ctx, accept_addrs):
-
-                uw_addr: tuple
-                for uw_addr in accept_addrs:
-                    addr = _addr.wrap_address(uw_addr)
-                    assert addr.is_valid
-
-            # shudown sub-actor(s)
-            await an.cancel()
-
-    trio.run(main)

tests/ipc/test_server.py

@@ -1,72 +0,0 @@
-'''
-High-level `.ipc._server` unit tests.
-
-'''
-from __future__ import annotations
-
-import pytest
-import trio
-from tractor import (
-    devx,
-    ipc,
-    log,
-)
-from tractor._testing.addr import (
-    get_rando_addr,
-)
-# TODO, use/check-roundtripping with some of these wrapper types?
-#
-# from .._addr import Address
-# from ._chan import Channel
-# from ._transport import MsgTransport
-# from ._uds import UDSAddress
-# from ._tcp import TCPAddress
-
-
-@pytest.mark.parametrize(
-    '_tpt_proto',
-    ['uds', 'tcp']
-)
-def test_basic_ipc_server(
-    _tpt_proto: str,
-    debug_mode: bool,
-    loglevel: str,
-):
-
-    # so we see the socket-listener reporting on console
-    log.get_console_log("INFO")
-
-    rando_addr: tuple = get_rando_addr(
-        tpt_proto=_tpt_proto,
-    )
-    async def main():
-        async with ipc._server.open_ipc_server() as server:
-
-            assert (
-                server._parent_tn
-                and
-                server._parent_tn is server._stream_handler_tn
-            )
-            assert server._no_more_peers.is_set()
-
-            eps: list[ipc._server.Endpoint] = await server.listen_on(
-                accept_addrs=[rando_addr],
-                stream_handler_nursery=None,
-            )
-            assert (
-                len(eps) == 1
-                and
-                (ep := eps[0])._listener
-                and
-                not ep.peer_tpts
-            )
-
-            server._parent_tn.cancel_scope.cancel()
-
-        # !TODO! actually make a bg-task connection from a client
-        # using `ipc._chan._connect_chan()`
-
-    with devx.maybe_open_crash_handler(
-        pdb=debug_mode,
-    ):
-        trio.run(main)

tests/test_advanced_faults.py

@@ -10,9 +10,6 @@ import pytest
 from _pytest.pathlib import import_path
 import trio
 import tractor
-from tractor import (
-    TransportClosed,
-)
 from tractor._testing import (
     examples_dir,
     break_ipc,
@@ -77,7 +74,6 @@ def test_ipc_channel_break_during_stream(
     spawn_backend: str,
     ipc_break: dict|None,
     pre_aclose_msgstream: bool,
-    tpt_proto: str,
 ):
     '''
     Ensure we can have an IPC channel break its connection during
@@ -95,7 +91,7 @@ def test_ipc_channel_break_during_stream(
         # non-`trio` spawners should never hit the hang condition that
         # requires the user to do ctl-c to cancel the actor tree.
         # expect_final_exc = trio.ClosedResourceError
-        expect_final_exc = TransportClosed
+        expect_final_exc = tractor.TransportClosed
 
     mod: ModuleType = import_path(
         examples_dir() / 'advanced_faults'
@@ -108,8 +104,6 @@ def test_ipc_channel_break_during_stream(
     # period" wherein the user eventually hits ctl-c to kill the
     # root-actor tree.
     expect_final_exc: BaseException = KeyboardInterrupt
-    expect_final_cause: BaseException|None = None
-
     if (
         # only expect EoC if trans is broken on the child side,
         ipc_break['break_child_ipc_after'] is not False
@@ -144,9 +138,6 @@ def test_ipc_channel_break_during_stream(
         # a user sending ctl-c by raising a KBI.
         if pre_aclose_msgstream:
             expect_final_exc = KeyboardInterrupt
-            if tpt_proto == 'uds':
-                expect_final_exc = TransportClosed
-                expect_final_cause = trio.BrokenResourceError
 
             # XXX OLD XXX
             # if child calls `MsgStream.aclose()` then expect EoC.
@@ -166,10 +157,6 @@ def test_ipc_channel_break_during_stream(
         if pre_aclose_msgstream:
             expect_final_exc = KeyboardInterrupt
 
-            if tpt_proto == 'uds':
-                expect_final_exc = TransportClosed
-                expect_final_cause = trio.BrokenResourceError
-
     # NOTE when the parent IPC side dies (even if the child does as well
     # but the child fails BEFORE the parent) we always expect the
     # IPC layer to raise a closed-resource, NEVER do we expect
@@ -182,8 +169,8 @@ def test_ipc_channel_break_during_stream(
         and
         ipc_break['break_child_ipc_after'] is False
     ):
+        # expect_final_exc = trio.ClosedResourceError
         expect_final_exc = tractor.TransportClosed
-        expect_final_cause = trio.ClosedResourceError
 
     # BOTH but, PARENT breaks FIRST
     elif (
@@ -194,8 +181,8 @@ def test_ipc_channel_break_during_stream(
             ipc_break['break_parent_ipc_after']
         )
     ):
+        # expect_final_exc = trio.ClosedResourceError
         expect_final_exc = tractor.TransportClosed
-        expect_final_cause = trio.ClosedResourceError
 
     with pytest.raises(
         expected_exception=(
@@ -211,7 +198,6 @@ def test_ipc_channel_break_during_stream(
                     start_method=spawn_backend,
                     loglevel=loglevel,
                     pre_close=pre_aclose_msgstream,
-                    tpt_proto=tpt_proto,
                     **ipc_break,
                 )
             )
@@ -234,15 +220,10 @@ def test_ipc_channel_break_during_stream(
                 )
             cause: Exception = tc.__cause__
             assert (
-                # type(cause) is trio.ClosedResourceError
+                type(cause) is trio.ClosedResourceError
-                type(cause) is expect_final_cause
+                and
-
+                cause.args[0] == 'another task closed this fd'
-                # TODO, should we expect a certain exc-message (per
-                # tpt) as well??
-                # and
-                # cause.args[0] == 'another task closed this fd'
             )
-
             raise
 
     # get raw instance from pytest wrapper

tests/test_advanced_streaming.py

@@ -313,8 +313,9 @@ async def inf_streamer(
         # `trio.EndOfChannel` doesn't propagate directly to the above
         # .open_stream() parent, resulting in it also raising instead
         # of gracefully absorbing as normal.. so how to handle?
-        tractor.trionics.collapse_eg(),
+        trio.open_nursery(
-        trio.open_nursery() as tn,
+            strict_exception_groups=False,
+        ) as tn,
     ):
         async def close_stream_on_sentinel():
             async for msg in stream:

tests/test_cancellation.py

@@ -236,10 +236,7 @@ async def stream_forever():
 async def test_cancel_infinite_streamer(start_method):
 
     # stream for at most 1 seconds
-    with (
+    with trio.move_on_after(1) as cancel_scope:
-        trio.fail_after(4),
-        trio.move_on_after(1) as cancel_scope
-    ):
         async with tractor.open_nursery() as n:
             portal = await n.start_actor(
                 'donny',
@@ -287,32 +284,20 @@ async def test_cancel_infinite_streamer(start_method):
     ],
 )
 @tractor_test
-async def test_some_cancels_all(
+async def test_some_cancels_all(num_actors_and_errs, start_method, loglevel):
-    num_actors_and_errs: tuple,
+    """Verify a subset of failed subactors causes all others in
-    start_method: str,
-    loglevel: str,
-):
-    '''
-    Verify a subset of failed subactors causes all others in
     the nursery to be cancelled just like the strategy in trio.
 
     This is the first and only supervisory strategy at the moment.
-
+    """
-    '''
+    num_actors, first_err, err_type, ria_func, da_func = num_actors_and_errs
-    (
-        num_actors,
-        first_err,
-        err_type,
-        ria_func,
-        da_func,
-    ) = num_actors_and_errs
     try:
-        async with tractor.open_nursery() as an:
+        async with tractor.open_nursery() as n:
 
             # spawn the same number of deamon actors which should be cancelled
             dactor_portals = []
             for i in range(num_actors):
-                dactor_portals.append(await an.start_actor(
+                dactor_portals.append(await n.start_actor(
                     f'deamon_{i}',
                     enable_modules=[__name__],
                 ))
@@ -322,7 +307,7 @@ async def test_some_cancels_all(
             for i in range(num_actors):
                 # start actor(s) that will fail immediately
                 riactor_portals.append(
-                    await an.run_in_actor(
+                    await n.run_in_actor(
                         func,
                         name=f'actor_{i}',
                         **kwargs
@@ -352,8 +337,7 @@ async def test_some_cancels_all(
 
         # should error here with a ``RemoteActorError`` or ``MultiError``
 
-    except first_err as _err:
+    except first_err as err:
-        err = _err
         if isinstance(err, BaseExceptionGroup):
             assert len(err.exceptions) == num_actors
             for exc in err.exceptions:
@@ -364,8 +348,8 @@ async def test_some_cancels_all(
         elif isinstance(err, tractor.RemoteActorError):
             assert err.boxed_type == err_type
 
-        assert an.cancelled is True
+        assert n.cancelled is True
-        assert not an._children
+        assert not n._children
     else:
         pytest.fail("Should have gotten a remote assertion error?")
 
@@ -535,15 +519,10 @@ def test_cancel_via_SIGINT_other_task(
     async def main():
         # should never timeout since SIGINT should cancel the current program
         with trio.fail_after(timeout):
-            async with (
+            async with trio.open_nursery(
-
+                strict_exception_groups=False,
-                # XXX ?TODO? why no work!?
+            ) as n:
-                # tractor.trionics.collapse_eg(),
+                await n.start(spawn_and_sleep_forever)
-                trio.open_nursery(
-                    strict_exception_groups=False,
-                ) as tn,
-            ):
-                await tn.start(spawn_and_sleep_forever)
                 if 'mp' in spawn_backend:
                     time.sleep(0.1)
                 os.kill(pid, signal.SIGINT)
@@ -554,123 +533,38 @@ def test_cancel_via_SIGINT_other_task(
 
 async def spin_for(period=3):
     "Sync sleep."
-    print(f'sync sleeping in sub-sub for {period}\n')
     time.sleep(period)
 
 
-async def spawn_sub_with_sync_blocking_task():
+async def spawn():
-    async with tractor.open_nursery() as an:
+    async with tractor.open_nursery() as tn:
-        print('starting sync blocking subactor..\n')
+        await tn.run_in_actor(
-        await an.run_in_actor(
             spin_for,
             name='sleeper',
         )
-        print('exiting first subactor layer..\n')
 
 
-@pytest.mark.parametrize(
-    'man_cancel_outer',
-    [
-        False,  # passes if delay != 2
-
-        # always causes an unexpected eg-w-embedded-assert-err?
-        pytest.param(True,
-             marks=pytest.mark.xfail(
-                 reason=(
-                    'always causes an unexpected eg-w-embedded-assert-err?'
-                )
-            ),
-        ),
-    ],
-)
 @no_windows
 def test_cancel_while_childs_child_in_sync_sleep(
-    loglevel: str,
+    loglevel,
-    start_method: str,
+    start_method,
-    spawn_backend: str,
+    spawn_backend,
-    debug_mode: bool,
-    reg_addr: tuple,
-    man_cancel_outer: bool,
 ):
-    '''
+    """Verify that a child cancelled while executing sync code is torn
-    Verify that a child cancelled while executing sync code is torn
     down even when that cancellation is triggered by the parent
     2 nurseries "up".
-
+    """
-    Though the grandchild should stay blocking its actor runtime, its
-    parent should issue a "zombie reaper" to hard kill it after
-    sufficient timeout.
-
-    '''
     if start_method == 'forkserver':
         pytest.skip("Forksever sux hard at resuming from sync sleep...")
 
     async def main():
-        #
+        with trio.fail_after(2):
-        # XXX BIG TODO NOTE XXX
+            async with tractor.open_nursery() as tn:
-        #
+                await tn.run_in_actor(
-        # it seems there's a strange race that can happen
+                    spawn,
-        # where where the fail-after will trigger outer scope
+                    name='spawn',
-        # .cancel() which then causes the inner scope to raise,
-        #
-        # BaseExceptionGroup('Exceptions from Trio nursery', [
-        #   BaseExceptionGroup('Exceptions from Trio nursery',
-        #   [
-        #       Cancelled(),
-        #       Cancelled(),
-        #   ]
-        #   ),
-        #   AssertionError('assert 0')
-        # ])
-        #
-        # WHY THIS DOESN'T MAKE SENSE:
-        # ---------------------------
-        # - it should raise too-slow-error when too slow..
-        #  * verified that using simple-cs and manually cancelling
-        #    you get same outcome -> indicates that the fail-after
-        #    can have its TooSlowError overriden!
-        #  |_ to check this it's easy, simplly decrease the timeout
-        #     as per the var below.
-        #
-        # - when using the manual simple-cs the outcome is different
-        #   DESPITE the `assert 0` which means regardless of the
-        #   inner scope effectively failing in the same way, the
-        #   bubbling up **is NOT the same**.
-        #
-        # delays trigger diff outcomes..
-        # ---------------------------
-        # as seen by uncommenting various lines below there is from
-        # my POV an unexpected outcome due to the delay=2 case.
-        #
-        # delay = 1  # no AssertionError in eg, TooSlowError raised.
-        # delay = 2  # is AssertionError in eg AND no TooSlowError !?
-        delay = 4  # is AssertionError in eg AND no _cs cancellation.
-
-        with trio.fail_after(delay) as _cs:
-        # with trio.CancelScope() as cs:
-        # ^XXX^ can be used instead to see same outcome.
-
-            async with (
-                # tractor.trionics.collapse_eg(),  # doesn't help
-                tractor.open_nursery(
-                    hide_tb=False,
-                    debug_mode=debug_mode,
-                    registry_addrs=[reg_addr],
-                ) as an,
-            ):
-                await an.run_in_actor(
-                    spawn_sub_with_sync_blocking_task,
-                    name='sync_blocking_sub',
                 )
                 await trio.sleep(1)
-
-                if man_cancel_outer:
-                    print('Cancelling manually in root')
-                    _cs.cancel()
-
-                # trigger exc-srced taskc down
-                # the actor tree.
-                print('RAISING IN ROOT')
                 assert 0
 
     with pytest.raises(AssertionError):

tests/test_child_manages_service_nursery.py

@@ -117,10 +117,9 @@ async def open_actor_local_nursery(
     ctx: tractor.Context,
 ):
     global _nursery
-    async with (
+    async with trio.open_nursery(
-        tractor.trionics.collapse_eg(),
+        strict_exception_groups=False,
-        trio.open_nursery() as tn
+    ) as tn:
-    ):
         _nursery = tn
         await ctx.started()
         await trio.sleep(10)

tests/test_clustering.py

@@ -13,24 +13,26 @@ MESSAGE = 'tractoring at full speed'
 def test_empty_mngrs_input_raises() -> None:
 
     async def main():
-        with trio.fail_after(3):
+        with trio.fail_after(1):
             async with (
                 open_actor_cluster(
                     modules=[__name__],
 
                     # NOTE: ensure we can passthrough runtime opts
-                    loglevel='cancel',
+                    loglevel='info',
-                    debug_mode=False,
+                    # debug_mode=True,
 
                 ) as portals,
 
-                gather_contexts(mngrs=()),
+                gather_contexts(
+                    # NOTE: it's the use of inline-generator syntax
+                    # here that causes the empty input.
+                    mngrs=(
+                        p.open_context(worker) for p in portals.values()
+                    ),
+                ),
             ):
-                # should fail before this?
+                assert 0
-                assert portals
-
-                # test should fail if we mk it here!
-                assert 0, 'Should have raised val-err !?'
 
     with pytest.raises(ValueError):
         trio.run(main)

tests/test_context_stream_semantics.py

@@ -252,7 +252,7 @@ def test_simple_context(
             pass
         except BaseExceptionGroup as beg:
             # XXX: on windows it seems we may have to expect the group error
-            from tractor.trionics import is_multi_cancelled
+            from tractor._exceptions import is_multi_cancelled
             assert is_multi_cancelled(beg)
     else:
         trio.run(main)

tests/test_discovery.py

@@ -7,11 +7,8 @@ import platform
 from functools import partial
 import itertools
 
-import psutil
 import pytest
-import subprocess
 import tractor
-from tractor.trionics import collapse_eg
 from tractor._testing import tractor_test
 import trio
 
@@ -29,7 +26,7 @@ async def test_reg_then_unreg(reg_addr):
         portal = await n.start_actor('actor', enable_modules=[__name__])
         uid = portal.channel.uid
 
-        async with tractor.get_registry(reg_addr) as aportal:
+        async with tractor.get_registry(*reg_addr) as aportal:
             # this local actor should be the arbiter
             assert actor is aportal.actor
 
@@ -155,25 +152,15 @@ async def unpack_reg(actor_or_portal):
 async def spawn_and_check_registry(
     reg_addr: tuple,
     use_signal: bool,
-    debug_mode: bool = False,
     remote_arbiter: bool = False,
     with_streaming: bool = False,
-    maybe_daemon: tuple[
-        subprocess.Popen,
-        psutil.Process,
-    ]|None = None,
 
 ) -> None:
 
-    if maybe_daemon:
-        popen, proc = maybe_daemon
-        # breakpoint()
-
     async with tractor.open_root_actor(
         registry_addrs=[reg_addr],
-        debug_mode=debug_mode,
     ):
-        async with tractor.get_registry(reg_addr) as portal:
+        async with tractor.get_registry(*reg_addr) as portal:
             # runtime needs to be up to call this
             actor = tractor.current_actor()
 
@@ -189,30 +176,30 @@ async def spawn_and_check_registry(
                 extra = 2  # local root actor + remote arbiter
 
             # ensure current actor is registered
-            registry: dict = await get_reg()
+            registry = await get_reg()
             assert actor.uid in registry
 
             try:
-                async with tractor.open_nursery() as an:
+                async with tractor.open_nursery() as n:
-                    async with (
+                    async with trio.open_nursery(
-                        collapse_eg(),
+                        strict_exception_groups=False,
-                        trio.open_nursery() as trion,
+                    ) as trion:
-                    ):
+
                         portals = {}
                         for i in range(3):
                             name = f'a{i}'
                             if with_streaming:
-                                portals[name] = await an.start_actor(
+                                portals[name] = await n.start_actor(
                                     name=name, enable_modules=[__name__])
 
                             else:  # no streaming
-                                portals[name] = await an.run_in_actor(
+                                portals[name] = await n.run_in_actor(
                                     trio.sleep_forever, name=name)
 
                         # wait on last actor to come up
                         async with tractor.wait_for_actor(name):
                             registry = await get_reg()
-                            for uid in an._children:
+                            for uid in n._children:
                                 assert uid in registry
 
                         assert len(portals) + extra == len(registry)
@@ -245,7 +232,6 @@ async def spawn_and_check_registry(
 @pytest.mark.parametrize('use_signal', [False, True])
 @pytest.mark.parametrize('with_streaming', [False, True])
 def test_subactors_unregister_on_cancel(
-    debug_mode: bool,
     start_method,
     use_signal,
     reg_addr,
@@ -262,7 +248,6 @@ def test_subactors_unregister_on_cancel(
                 spawn_and_check_registry,
                 reg_addr,
                 use_signal,
-                debug_mode=debug_mode,
                 remote_arbiter=False,
                 with_streaming=with_streaming,
             ),
@@ -272,8 +257,7 @@ def test_subactors_unregister_on_cancel(
 @pytest.mark.parametrize('use_signal', [False, True])
 @pytest.mark.parametrize('with_streaming', [False, True])
 def test_subactors_unregister_on_cancel_remote_daemon(
-    daemon: subprocess.Popen,
+    daemon,
-    debug_mode: bool,
     start_method,
     use_signal,
     reg_addr,
@@ -289,13 +273,8 @@ def test_subactors_unregister_on_cancel_remote_daemon(
                 spawn_and_check_registry,
                 reg_addr,
                 use_signal,
-                debug_mode=debug_mode,
                 remote_arbiter=True,
                 with_streaming=with_streaming,
-                maybe_daemon=(
-                    daemon,
-                    psutil.Process(daemon.pid)
-                ),
             ),
         )
 
@@ -321,7 +300,7 @@ async def close_chans_before_nursery(
     async with tractor.open_root_actor(
         registry_addrs=[reg_addr],
     ):
-        async with tractor.get_registry(reg_addr) as aportal:
+        async with tractor.get_registry(*reg_addr) as aportal:
             try:
                 get_reg = partial(unpack_reg, aportal)
 
@@ -339,12 +318,11 @@ async def close_chans_before_nursery(
                         async with portal2.open_stream_from(
                             stream_forever
                         ) as agen2:
-                            async with (
+                            async with trio.open_nursery(
-                                collapse_eg(),
+                                strict_exception_groups=False,
-                                trio.open_nursery() as tn,
+                            ) as n:
-                            ):
+                                n.start_soon(streamer, agen1)
-                                tn.start_soon(streamer, agen1)
+                                n.start_soon(cancel, use_signal, .5)
-                                tn.start_soon(cancel, use_signal, .5)
                                 try:
                                     await streamer(agen2)
                                 finally:
@@ -395,7 +373,7 @@ def test_close_channel_explicit(
 
 @pytest.mark.parametrize('use_signal', [False, True])
 def test_close_channel_explicit_remote_arbiter(
-    daemon: subprocess.Popen,
+    daemon,
     start_method,
     use_signal,
     reg_addr,

tests/test_docs_examples.py

@@ -66,9 +66,6 @@ def run_example_in_subproc(
         # due to backpressure!!!
         proc = testdir.popen(
             cmdargs,
-            stdin=subprocess.PIPE,
-            stdout=subprocess.PIPE,
-            stderr=subprocess.PIPE,
             **kwargs,
         )
         assert not proc.returncode
@@ -95,7 +92,6 @@ def run_example_in_subproc(
             and 'integration' not in p[0]
             and 'advanced_faults' not in p[0]
             and 'multihost' not in p[0]
-            and 'trio' not in p[0]
         )
     ],
     ids=lambda t: t[1],
@@ -123,14 +119,10 @@ def test_example(
         code = ex.read()
 
         with run_example_in_subproc(code) as proc:
-            err = None
+            proc.wait()
-            try:
+            err, _ = proc.stderr.read(), proc.stdout.read()
-                if not proc.poll():
+            # print(f'STDERR: {err}')
-                    _, err = proc.communicate(timeout=15)
+            # print(f'STDOUT: {out}')
-
-            except subprocess.TimeoutExpired as e:
-                proc.kill()
-                err = e.stderr
 
             # if we get some gnarly output let's aggregate and raise
             if err:

tests/test_infected_asyncio.py

@@ -234,8 +234,10 @@ async def trio_ctx(
     with trio.fail_after(1 + delay):
         try:
             async with (
-                tractor.trionics.collapse_eg(),
+                trio.open_nursery(
-                trio.open_nursery() as tn,
+                    # TODO, for new `trio` / py3.13
+                    # strict_exception_groups=False,
+                ) as tn,
                 tractor.to_asyncio.open_channel_from(
                     sleep_and_err,
                 ) as (first, chan),
@@ -571,16 +573,14 @@ def test_basic_interloop_channel_stream(
     fan_out: bool,
 ):
     async def main():
-        # TODO, figure out min timeout here!
+        async with tractor.open_nursery() as an:
-        with trio.fail_after(6):
+            portal = await an.run_in_actor(
-            async with tractor.open_nursery() as an:
+                stream_from_aio,
-                portal = await an.run_in_actor(
+                infect_asyncio=True,
-                    stream_from_aio,
+                fan_out=fan_out,
-                    infect_asyncio=True,
+            )
-                    fan_out=fan_out,
+            # should raise RAE diectly
-                )
+            await portal.result()
-                # should raise RAE diectly
-                await portal.result()
 
     trio.run(main)
 
@@ -889,7 +889,7 @@ async def manage_file(
 
         # NOTE: turns out you don't even need to sched an aio task
         # since the original issue, even though seemingly was due to
-        # the guest-run being abandoned + a `.debug.pause()` inside
+        # the guest-run being abandoned + a `._debug.pause()` inside
         # `._runtime._async_main()` (which was originally trying to
         # debug the `.lifetime_stack` not closing), IS NOT actually
         # the core issue?
@@ -1088,108 +1088,6 @@ def test_sigint_closes_lifetime_stack(
     trio.run(main)
 
 
-
-# ?TODO asyncio.Task fn-deco?
-# -[ ] do sig checkingat import time like @context?
-# -[ ] maybe name it @aio_task ??
-# -[ ] chan: to_asyncio.InterloopChannel ??
-async def raise_before_started(
-    # from_trio: asyncio.Queue,
-    # to_trio: trio.abc.SendChannel,
-    chan: to_asyncio.LinkedTaskChannel,
-
-) -> None:
-    '''
-    `asyncio.Task` entry point which RTEs before calling
-    `to_trio.send_nowait()`.
-
-    '''
-    await asyncio.sleep(0.2)
-    raise RuntimeError('Some shite went wrong before `.send_nowait()`!!')
-
-    # to_trio.send_nowait('Uhh we shouldve RTE-d ^^ ??')
-    chan.started_nowait('Uhh we shouldve RTE-d ^^ ??')
-    await asyncio.sleep(float('inf'))
-
-
-@tractor.context
-async def caching_ep(
-    ctx: tractor.Context,
-):
-
-    log = tractor.log.get_logger('caching_ep')
-    log.info('syncing via `ctx.started()`')
-    await ctx.started()
-
-    # XXX, allocate the `open_channel_from()` inside
-    # a `.trionics.maybe_open_context()`.
-    chan: to_asyncio.LinkedTaskChannel
-    async with (
-        tractor.trionics.maybe_open_context(
-            acm_func=tractor.to_asyncio.open_channel_from,
-            kwargs={
-                'target': raise_before_started,
-                # ^XXX, kwarg to `open_channel_from()`
-            },
-
-            # lock around current actor task access
-            key=tractor.current_actor().uid,
-
-        ) as (cache_hit, (clients, chan)),
-    ):
-        if cache_hit:
-            log.error(
-                'Re-using cached `.open_from_channel()` call!\n'
-            )
-
-        else:
-            log.info(
-                'Allocating SHOULD-FAIL `.open_from_channel()`\n'
-            )
-
-        await trio.sleep_forever()
-
-
-def test_aio_side_raises_before_started(
-    reg_addr: tuple[str, int],
-    debug_mode: bool,
-    loglevel: str,
-):
-    '''
-    Simulates connection-err from `piker.brokers.ib.api`..
-
-    Ensure any error raised by child-`asyncio.Task` BEFORE
-    `chan.started()`
-
-    '''
-    # delay = 999 if debug_mode else 1
-    async def main():
-        with trio.fail_after(3):
-            an: tractor.ActorNursery
-            async with tractor.open_nursery(
-                debug_mode=debug_mode,
-                loglevel=loglevel,
-            ) as an:
-                p: tractor.Portal = await an.start_actor(
-                    'lchan_cacher_that_raises_fast',
-                    enable_modules=[__name__],
-                    infect_asyncio=True,
-                )
-                async with p.open_context(
-                    caching_ep,
-                ) as (ctx, first):
-                    assert not first
-
-    with pytest.raises(
-        expected_exception=(RemoteActorError),
-    ) as excinfo:
-        trio.run(main)
-
-    # ensure `asyncio.Task` exception is bubbled
-    # allll the way erp!!
-    rae = excinfo.value
-    assert rae.boxed_type is RuntimeError
-
 # TODO: debug_mode tests once we get support for `asyncio`!
 #
 # -[ ] need tests to wrap both scripts:
@@ -1203,7 +1101,7 @@ def test_aio_side_raises_before_started(
 #    => completed using `.bestow_portal(task)` inside
 #     `.to_asyncio._run_asyncio_task()` right?
 #   -[ ] translation func to get from `asyncio` task calling to 
-#     `.debug.wait_for_parent_stdin_hijack()` which does root
+#     `._debug.wait_for_parent_stdin_hijack()` which does root
 #     call to do TTY locking.
 #
 def test_sync_breakpoint():

tests/test_inter_peer_cancellation.py

@@ -24,10 +24,14 @@ from tractor._testing import (
 )
 
 # XXX TODO cases:
+# - [ ] peer cancelled itself - so other peers should
+#   get errors reflecting that the peer was itself the .canceller?
+
 # - [x] WE cancelled the peer and thus should not see any raised
 #   `ContextCancelled` as it should be reaped silently?
 #   => pretty sure `test_context_stream_semantics::test_caller_cancels()`
 #      already covers this case?
+
 # - [x] INTER-PEER: some arbitrary remote peer cancels via
 #   Portal.cancel_actor().
 #   => all other connected peers should get that cancel requesting peer's
@@ -40,6 +44,16 @@ from tractor._testing import (
 #   that also spawned a remote task task in that same peer-parent.
 
 
+# def test_self_cancel():
+#     '''
+#     2 cases:
+#     - calls `Actor.cancel()` locally in some task
+#     - calls LocalPortal.cancel_actor()` ?
+
+#     '''
+#     ...
+
+
 @tractor.context
 async def open_stream_then_sleep_forever(
     ctx: Context,
@@ -396,6 +410,7 @@ 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(
@@ -792,7 +807,7 @@ async def basic_echo_server(
     ctx: Context,
     peer_name: str = 'wittle_bruv',
 
-    err_after_imsg: int|None = None,
+    err_after: int|None = None,
 
 ) -> None:
     '''
@@ -821,9 +836,8 @@ async def basic_echo_server(
             await ipc.send(resp)
 
             if (
-                err_after_imsg
+                err_after
-                and
+                and i > err_after
-                i > err_after_imsg
             ):
                 raise RuntimeError(
                     f'Simulated error in `{peer_name}`'
@@ -857,7 +871,7 @@ async def serve_subactors(
                 )
                 await ipc.send((
                     peer.chan.uid,
-                    peer.chan.raddr.unwrap(),
+                    peer.chan.raddr,
                 ))
 
         print('Spawner exiting spawn serve loop!')
@@ -965,8 +979,7 @@ async def tell_little_bro(
     actor_name: str,
 
     caller: str = '',
-    err_after: float|None = None,
+    err_after: int|None = None,
-    rng_seed: int = 50,
 ):
     # contact target actor, do a stream dialog.
     async with (
@@ -977,18 +990,14 @@ async def tell_little_bro(
             basic_echo_server,
 
             # XXX proxy any delayed err condition
-            err_after_imsg=(
+            err_after=err_after,
-                err_after * rng_seed
-                if err_after is not None
-                else None
-            ),
         ) as (sub_ctx, first),
 
         sub_ctx.open_stream() as echo_ipc,
     ):
         actor: Actor = current_actor()
         uid: tuple = actor.uid
-        for i in range(rng_seed):
+        for i in range(100):
             msg: tuple = (
                 uid,
                 i,
@@ -1013,13 +1022,13 @@ async def tell_little_bro(
 )
 @pytest.mark.parametrize(
     'raise_sub_spawn_error_after',
-    [None, 0.5],
+    [None, 50],
 )
 def test_peer_spawns_and_cancels_service_subactor(
     debug_mode: bool,
     raise_client_error: str,
     reg_addr: tuple[str, int],
-    raise_sub_spawn_error_after: float|None,
+    raise_sub_spawn_error_after: int|None,
 ):
     # NOTE: this tests for the modden `mod wks open piker` bug
     # discovered as part of implementing workspace ctx
@@ -1033,7 +1042,6 @@ def test_peer_spawns_and_cancels_service_subactor(
     #   and the server's spawned child should cancel and terminate!
     peer_name: str = 'little_bro'
 
-
     def check_inner_rte(rae: RemoteActorError):
         '''
         Validate the little_bro's relayed inception!
@@ -1127,7 +1135,8 @@ def test_peer_spawns_and_cancels_service_subactor(
                         )
 
                     try:
-                        res = await client_ctx.wait_for_result(hide_tb=False)
+                        res = await client_ctx.result(hide_tb=False)
+
                         # in remote (relayed inception) error
                         # case, we should error on the line above!
                         if raise_sub_spawn_error_after:
@@ -1138,23 +1147,6 @@ def test_peer_spawns_and_cancels_service_subactor(
                         assert isinstance(res, ContextCancelled)
                         assert client_ctx.cancel_acked
                         assert res.canceller == root.uid
-                        assert not raise_sub_spawn_error_after
-
-                        # cancelling the spawner sub should
-                        # transitively cancel it's sub, the little
-                        # bruv.
-                        print('root cancelling server/client sub-actors')
-                        await spawn_ctx.cancel()
-                        async with tractor.find_actor(
-                            name=peer_name,
-                        ) as sub:
-                            assert not sub
-
-                    # XXX, only for tracing
-                    # except BaseException as _berr:
-                    #     berr = _berr
-                    #     await tractor.pause(shield=True)
-                    #     raise berr
 
                     except RemoteActorError as rae:
                         _err = rae
@@ -1183,8 +1175,19 @@ def test_peer_spawns_and_cancels_service_subactor(
                         raise
                         # await tractor.pause()
 
+                    else:
+                        assert not raise_sub_spawn_error_after
+
+                        # cancelling the spawner sub should
+                        # transitively cancel it's sub, the little
+                        # bruv.
+                        print('root cancelling server/client sub-actors')
+                        await spawn_ctx.cancel()
+                        async with tractor.find_actor(
+                            name=peer_name,
+                        ) as sub:
+                            assert not sub
 
-                    # await tractor.pause()
                     # await server.cancel_actor()
 
             except RemoteActorError as rae:
@@ -1197,7 +1200,7 @@ def test_peer_spawns_and_cancels_service_subactor(
 
             # since we called `.cancel_actor()`, `.cancel_ack`
             # will not be set on the ctx bc `ctx.cancel()` was not
-            # called directly for this confext.
+            # called directly fot this confext.
             except ContextCancelled as ctxc:
                 _ctxc = ctxc
                 print(
@@ -1237,19 +1240,12 @@ def test_peer_spawns_and_cancels_service_subactor(
 
                 # assert spawn_ctx.cancelled_caught
 
-    async def _main():
-        with trio.fail_after(
-            3 if not debug_mode
-            else 999
-        ):
-            await main()
-
     if raise_sub_spawn_error_after:
         with pytest.raises(RemoteActorError) as excinfo:
-            trio.run(_main)
+            trio.run(main)
 
         rae: RemoteActorError = excinfo.value
         check_inner_rte(rae)
 
     else:
-        trio.run(_main)
+        trio.run(main)

tests/test_legacy_one_way_streaming.py

@@ -235,16 +235,10 @@ async def cancel_after(wait, reg_addr):
 
 
 @pytest.fixture(scope='module')
-def time_quad_ex(
+def time_quad_ex(reg_addr, ci_env, spawn_backend):
-    reg_addr: tuple,
-    ci_env: bool,
-    spawn_backend: str,
-):
     if spawn_backend == 'mp':
-        '''
+        """no idea but the  mp *nix runs are flaking out here often...
-        no idea but the  mp *nix runs are flaking out here often...
+        """
-
-        '''
         pytest.skip("Test is too flaky on mp in CI")
 
     timeout = 7 if platform.system() in ('Windows', 'Darwin') else 4
@@ -255,24 +249,12 @@ def time_quad_ex(
     return results, diff
 
 
-def test_a_quadruple_example(
+def test_a_quadruple_example(time_quad_ex, ci_env, spawn_backend):
-    time_quad_ex: tuple,
+    """This also serves as a kind of "we'd like to be this fast test"."""
-    ci_env: bool,
-    spawn_backend: str,
-):
-    '''
-    This also serves as a kind of "we'd like to be this fast test".
 
-    '''
     results, diff = time_quad_ex
     assert results
-    this_fast = (
+    this_fast = 6 if platform.system() in ('Windows', 'Darwin') else 3
-        6 if platform.system() in (
-            'Windows',
-            'Darwin',
-        )
-        else 3
-    )
     assert diff < this_fast
 
 

tests/test_local.py

@@ -38,7 +38,7 @@ async def test_self_is_registered_localportal(reg_addr):
     "Verify waiting on the arbiter to register itself using a local portal."
     actor = tractor.current_actor()
     assert actor.is_arbiter
-    async with tractor.get_registry(reg_addr) as portal:
+    async with tractor.get_registry(*reg_addr) as portal:
         assert isinstance(portal, tractor._portal.LocalPortal)
 
         with trio.fail_after(0.2):

tests/test_multi_program.py

@@ -32,7 +32,7 @@ def test_abort_on_sigint(daemon):
 @tractor_test
 async def test_cancel_remote_arbiter(daemon, reg_addr):
     assert not tractor.current_actor().is_arbiter
-    async with tractor.get_registry(reg_addr) as portal:
+    async with tractor.get_registry(*reg_addr) as portal:
         await portal.cancel_actor()
 
     time.sleep(0.1)
@@ -41,7 +41,7 @@ async def test_cancel_remote_arbiter(daemon, reg_addr):
 
     # no arbiter socket should exist
     with pytest.raises(OSError):
-        async with tractor.get_registry(reg_addr) as portal:
+        async with tractor.get_registry(*reg_addr) as portal:
             pass
 
 

tests/test_oob_cancellation.py

@@ -1,239 +0,0 @@
-'''
-Define the details of inter-actor "out-of-band" (OoB) cancel
-semantics, that is how cancellation works when a cancel request comes
-from the different concurrency (primitive's) "layer" then where the
-eventual `trio.Task` actually raises a signal.
-
-'''
-from functools import partial
-# from contextlib import asynccontextmanager as acm
-# import itertools
-
-import pytest
-import trio
-import tractor
-from tractor import (  # typing
-    ActorNursery,
-    Portal,
-    Context,
-    # ContextCancelled,
-    # RemoteActorError,
-)
-# from tractor._testing import (
-#     tractor_test,
-#     expect_ctxc,
-# )
-
-# XXX TODO cases:
-# - [ ] peer cancelled itself - so other peers should
-#   get errors reflecting that the peer was itself the .canceller?
-
-# def test_self_cancel():
-#     '''
-#     2 cases:
-#     - calls `Actor.cancel()` locally in some task
-#     - calls LocalPortal.cancel_actor()` ?
-#
-# things to ensure!
-# -[ ] the ctxc raised in a child should ideally show the tb of the
-#     underlying `Cancelled` checkpoint, i.e.
-#     `raise scope_error from ctxc`?
-#
-# -[ ] a self-cancelled context, if not allowed to block on
-#     `ctx.result()` at some point will hang since the `ctx._scope`
-#     is never `.cancel_called`; cases for this include,
-#     - an `open_ctx()` which never starteds before being OoB actor
-#       cancelled.
-#       |_ parent task will be blocked in `.open_context()` for the
-#         `Started` msg, and when the OoB ctxc arrives `ctx._scope`
-#         will never have been signalled..
-
-#     '''
-#     ...
-
-# TODO, sanity test against the case in `/examples/trio/lockacquire_not_unmasked.py`
-# but with the `Lock.acquire()` from a `@context` to ensure the
-# implicit ignore-case-non-unmasking.
-#
-# @tractor.context
-# async def acquire_actor_global_lock(
-#     ctx: tractor.Context,
-#     ignore_special_cases: bool,
-# ):
-
-#     async with maybe_unmask_excs(
-#         ignore_special_cases=ignore_special_cases,
-#     ):
-#         await ctx.started('locked')
-
-#     # block til cancelled
-#     await trio.sleep_forever()
-
-
-@tractor.context
-async def sleep_forever(
-    ctx: tractor.Context,
-    # ignore_special_cases: bool,
-    do_started: bool,
-):
-
-    # async with maybe_unmask_excs(
-    #     ignore_special_cases=ignore_special_cases,
-    # ):
-    #     await ctx.started('locked')
-    if do_started:
-        await ctx.started()
-
-    # block til cancelled
-    print('sleepin on child-side..')
-    await trio.sleep_forever()
-
-
-@pytest.mark.parametrize(
-    'cancel_ctx',
-    [True, False],
-)
-def test_cancel_ctx_with_parent_side_entered_in_bg_task(
-    debug_mode: bool,
-    loglevel: str,
-    cancel_ctx: bool,
-):
-    '''
-    The most "basic" out-of-band-task self-cancellation case where
-    `Portal.open_context()` is entered in a bg task and the
-    parent-task (of the containing nursery) calls `Context.cancel()`
-    without the child knowing; the `Context._scope` should be
-    `.cancel_called` when the IPC ctx's child-side relays
-    a `ContextCancelled` with a `.canceller` set to the parent
-    actor('s task).
-
-    '''
-    async def main():
-        with trio.fail_after(
-            2 if not debug_mode else 999,
-        ):
-            an: ActorNursery
-            async with (
-                tractor.open_nursery(
-                    debug_mode=debug_mode,
-                    loglevel='devx',
-                    enable_stack_on_sig=True,
-                ) as an,
-                trio.open_nursery() as tn,
-            ):
-                ptl: Portal = await an.start_actor(
-                    'sub',
-                    enable_modules=[__name__],
-                )
-
-                async def _open_ctx_async(
-                    do_started: bool = True,
-                    task_status=trio.TASK_STATUS_IGNORED,
-                ):
-                    # do we expect to never enter the
-                    # `.open_context()` below.
-                    if not do_started:
-                        task_status.started()
-
-                    async with ptl.open_context(
-                        sleep_forever,
-                        do_started=do_started,
-                    ) as (ctx, first):
-                        task_status.started(ctx)
-                        await trio.sleep_forever()
-
-                # XXX, this is the key OoB part!
-                #
-                # - start the `.open_context()` in a bg task which
-                #   blocks inside the embedded scope-body,
-                #
-                # -  when we call `Context.cancel()` it **is
-                #   not** from the same task which eventually runs
-                #   `.__aexit__()`,
-                #
-                # - since the bg "opener" task will be in
-                #   a `trio.sleep_forever()`, it must be interrupted
-                #   by the `ContextCancelled` delivered from the
-                #   child-side; `Context._scope: CancelScope` MUST
-                #   be `.cancel_called`!
-                #
-                print('ASYNC opening IPC context in subtask..')
-                maybe_ctx: Context|None = await tn.start(partial(
-                    _open_ctx_async,
-                ))
-
-                if (
-                    maybe_ctx
-                    and
-                    cancel_ctx
-                ):
-                    print('cancelling first IPC ctx!')
-                    await maybe_ctx.cancel()
-
-                # XXX, note that despite `maybe_context.cancel()`
-                # being called above, it's the parent (bg) task
-                # which was originally never interrupted in
-                # the `ctx._scope` body due to missing case logic in
-                # `ctx._maybe_cancel_and_set_remote_error()`.
-                #
-                # It didn't matter that the subactor process was
-                # already terminated and reaped, nothing was
-                # cancelling the ctx-parent task's scope!
-                #
-                print('cancelling subactor!')
-                await ptl.cancel_actor()
-
-                if maybe_ctx:
-                    try:
-                        await maybe_ctx.wait_for_result()
-                    except tractor.ContextCancelled as ctxc:
-                        assert not cancel_ctx
-                        assert (
-                            ctxc.canceller
-                            ==
-                            tractor.current_actor().aid.uid
-                        )
-                        # don't re-raise since it'll trigger
-                        # an EG from the above tn.
-
-    if cancel_ctx:
-        # graceful self-cancel
-        trio.run(main)
-
-    else:
-        # ctx parent task should see OoB ctxc due to
-        # `ptl.cancel_actor()`.
-        with pytest.raises(tractor.ContextCancelled) as excinfo:
-            trio.run(main)
-
-        assert 'root' in excinfo.value.canceller[0]
-
-
-# def test_parent_actor_cancels_subactor_with_gt1_ctxs_open_to_it(
-#     debug_mode: bool,
-#     loglevel: str,
-# ):
-#     '''
-#     Demos OoB cancellation from the perspective of a ctx opened with
-#     a child subactor where the parent cancels the child at the "actor
-#     layer" using `Portal.cancel_actor()` and thus the
-#     `ContextCancelled.canceller` received by the ctx's parent-side
-#     task will appear to be a "self cancellation" even though that
-#     specific task itself was not cancelled and thus
-#     `Context.cancel_called ==False`.
-#     '''
-                # TODO, do we have an existing implied ctx
-                # cancel test like this?
-                # with trio.move_on_after(0.5):# as cs:
-                #     await _open_ctx_async(
-                #         do_started=False,
-                #     )
-
-
-                # in-line ctx scope should definitely raise
-                # a ctxc with `.canceller = 'root'`
-                # async with ptl.open_context(
-                #     sleep_forever,
-                #     do_started=True,
-                # ) as pair:
-

tests/test_remote_exc_relay.py

@@ -1,237 +0,0 @@
-'''
-Special case testing for issues not (dis)covered in the primary
-`Context` related functional/scenario suites.
-
-**NOTE: this mod is a WIP** space for handling
-odd/rare/undiscovered/not-yet-revealed faults which either
-loudly (ideal case) breakl our supervision protocol
-or (worst case) result in distributed sys hangs.
-
-Suites here further try to clarify (if [partially] ill-defined) and
-verify our edge case semantics for inter-actor-relayed-exceptions
-including,
-
-- lowlevel: what remote obj-data is interchanged for IPC and what is
-  native-obj form is expected from unpacking in the the new
-  mem-domain.
-
-- which kinds of `RemoteActorError` (and its derivs) are expected by which
-  (types of) peers (parent, child, sibling, etc) with what
-  particular meta-data set such as,
-
-  - `.src_uid`: the original (maybe) peer who raised.
-  - `.relay_uid`: the next-hop-peer who sent it.
-  - `.relay_path`: the sequence of peer actor hops.
-  - `.is_inception`: a predicate that denotes multi-hop remote errors.
-
-- when should `ExceptionGroup`s be relayed from a particular
-  remote endpoint, they should never be caused by implicit `._rpc`
-  nursery machinery!
-
-- various special `trio` edge cases around its cancellation semantics
-  and how we (currently) leverage `trio.Cancelled` as a signal for
-  whether a `Context` task should raise `ContextCancelled` (ctx).
-
-'''
-import pytest
-import trio
-import tractor
-from tractor import (  # typing
-    ActorNursery,
-    Portal,
-    Context,
-    ContextCancelled,
-)
-
-
-@tractor.context
-async def sleep_n_chkpt_in_finally(
-    ctx: Context,
-    sleep_n_raise: bool,
-
-    chld_raise_delay: float,
-    chld_finally_delay: float,
-
-    rent_cancels: bool,
-    rent_ctxc_delay: float,
-
-    expect_exc: str|None = None,
-
-) -> None:
-    '''
-    Sync, open a tn, then wait for cancel, run a chkpt inside
-    the user's `finally:` teardown.
-
-    This covers a footgun case that `trio` core doesn't seem to care about
-    wherein an exc can be masked by a `trio.Cancelled` raised inside a tn emedded
-    `finally:`.
-
-    Also see `test_trioisms::test_acm_embedded_nursery_propagates_enter_err`
-    for the down and gritty details.
-
-    Since a `@context` endpoint fn can also contain code like this,
-    **and** bc we currently have no easy way other then
-    `trio.Cancelled` to signal cancellation on each side of an IPC `Context`,
-    the footgun issue can compound itself as demonstrated in this suite..
-
-    Here are some edge cases codified with our WIP "sclang" syntax
-    (note the parent(rent)/child(chld) naming here is just
-    pragmatism, generally these most of these cases can occurr
-    regardless of the distributed-task's supervision hiearchy),
-
-    - rent c)=> chld.raises-then-taskc-in-finally
-     |_ chld's body raises an `exc: BaseException`.
-      _ in its `finally:` block it runs a chkpoint
-        which raises a taskc (`trio.Cancelled`) which
-        masks `exc` instead raising taskc up to the first tn.
-      _ the embedded/chld tn captures the masking taskc and then
-        raises it up to the ._rpc-ep-tn instead of `exc`.
-      _ the rent thinks the child ctxc-ed instead of errored..
-
-    '''
-    await ctx.started()
-
-    if expect_exc:
-        expect_exc: BaseException = tractor._exceptions.get_err_type(
-            type_name=expect_exc,
-        )
-
-    berr: BaseException|None = None
-    try:
-        if not sleep_n_raise:
-            await trio.sleep_forever()
-        elif sleep_n_raise:
-
-            # XXX this sleep is less then the sleep the parent
-            # does before calling `ctx.cancel()`
-            await trio.sleep(chld_raise_delay)
-
-            # XXX this will be masked by a taskc raised in
-            # the `finally:` if this fn doesn't terminate
-            # before any ctxc-req arrives AND a checkpoint is hit
-            # in that `finally:`.
-            raise RuntimeError('my app krurshed..')
-
-    except BaseException as _berr:
-        berr = _berr
-
-        # TODO: it'd sure be nice to be able to inject our own
-        # `ContextCancelled` here instead of of `trio.Cancelled`
-        # so that our runtime can expect it and this "user code"
-        # would be able to tell the diff between a generic trio
-        # cancel and a tractor runtime-IPC cancel.
-        if expect_exc:
-            if not isinstance(
-                berr,
-                expect_exc,
-            ):
-                raise ValueError(
-                    f'Unexpected exc type ??\n'
-                    f'{berr!r}\n'
-                    f'\n'
-                    f'Expected a {expect_exc!r}\n'
-                )
-
-        raise berr
-
-    # simulate what user code might try even though
-    # it's a known boo-boo..
-    finally:
-        # maybe wait for rent ctxc to arrive
-        with trio.CancelScope(shield=True):
-            await trio.sleep(chld_finally_delay)
-
-        # !!XXX this will raise `trio.Cancelled` which
-        # will mask the RTE from above!!!
-        #
-        # YES, it's the same case as our extant
-        # `test_trioisms::test_acm_embedded_nursery_propagates_enter_err`
-        try:
-            await trio.lowlevel.checkpoint()
-        except trio.Cancelled as taskc:
-            if (scope_err := taskc.__context__):
-                print(
-                    f'XXX MASKED REMOTE ERROR XXX\n'
-                    f'ENDPOINT exception -> {scope_err!r}\n'
-                    f'will be masked by -> {taskc!r}\n'
-                )
-                # await tractor.pause(shield=True)
-
-            raise taskc
-
-
-@pytest.mark.parametrize(
-    'chld_callspec',
-    [
-        dict(
-            sleep_n_raise=None,
-            chld_raise_delay=0.1,
-            chld_finally_delay=0.1,
-            expect_exc='Cancelled',
-            rent_cancels=True,
-            rent_ctxc_delay=0.1,
-        ),
-        dict(
-            sleep_n_raise='RuntimeError',
-            chld_raise_delay=0.1,
-            chld_finally_delay=1,
-            expect_exc='RuntimeError',
-            rent_cancels=False,
-            rent_ctxc_delay=0.1,
-        ),
-    ],
-    ids=lambda item: f'chld_callspec={item!r}'
-)
-def test_unmasked_remote_exc(
-    debug_mode: bool,
-    chld_callspec: dict,
-    tpt_proto: str,
-):
-    expect_exc_str: str|None = chld_callspec['sleep_n_raise']
-    rent_ctxc_delay: float|None = chld_callspec['rent_ctxc_delay']
-    async def main():
-        an: ActorNursery
-        async with tractor.open_nursery(
-            debug_mode=debug_mode,
-            enable_transports=[tpt_proto],
-        ) as an:
-            ptl: Portal = await an.start_actor(
-                'cancellee',
-                enable_modules=[__name__],
-            )
-            ctx: Context
-            async with (
-                ptl.open_context(
-                    sleep_n_chkpt_in_finally,
-                    **chld_callspec,
-                ) as (ctx, sent),
-            ):
-                assert not sent
-                await trio.sleep(rent_ctxc_delay)
-                await ctx.cancel()
-
-                # recv error or result from chld
-                ctxc: ContextCancelled = await ctx.wait_for_result()
-                assert (
-                    ctxc is ctx.outcome
-                    and
-                    isinstance(ctxc, ContextCancelled)
-                )
-
-            # always graceful terminate the sub in non-error cases
-            await an.cancel()
-
-    if expect_exc_str:
-        expect_exc: BaseException = tractor._exceptions.get_err_type(
-            type_name=expect_exc_str,
-        )
-        with pytest.raises(
-            expected_exception=tractor.RemoteActorError,
-        ) as excinfo:
-            trio.run(main)
-
-        rae = excinfo.value
-        assert expect_exc == rae.boxed_type
-
-    else:
-        trio.run(main)

tests/test_resource_cache.py

@@ -1,6 +1,5 @@
 '''
-Suites for our `.trionics.maybe_open_context()` multi-task
+Async context manager cache api testing: ``trionics.maybe_open_context():``
-shared-cached `@acm` API.
 
 '''
 from contextlib import asynccontextmanager as acm
@@ -10,15 +9,6 @@ from typing import Awaitable
 import pytest
 import trio
 import tractor
-from tractor.trionics import (
-    maybe_open_context,
-)
-from tractor.log import (
-    get_console_log,
-    get_logger,
-)
-log = get_logger(__name__)
-
 
 
 _resource: int = 0
@@ -62,7 +52,7 @@ def test_resource_only_entered_once(key_on):
                 # different task names per task will be used
                 kwargs = {'task_name': name}
 
-            async with maybe_open_context(
+            async with tractor.trionics.maybe_open_context(
                 maybe_increment_counter,
                 kwargs=kwargs,
                 key=key,
@@ -82,13 +72,11 @@ 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 tn,
+                trio.open_nursery() as n,
             ):
+
                 for i in range(10):
-                    tn.start_soon(
+                    n.start_soon(enter_cached_mngr, f'task_{i}')
-                        enter_cached_mngr,
-                        f'task_{i}',
-                    )
                     await trio.sleep(0.001)
 
     trio.run(main)
@@ -110,55 +98,27 @@ async def streamer(
 
 
 @acm
-async def open_stream() -> Awaitable[
+async def open_stream() -> Awaitable[tractor.MsgStream]:
-    tuple[
-        tractor.ActorNursery,
-        tractor.MsgStream,
-    ]
-]:
-    try:
-        async with tractor.open_nursery() as an:
-            portal = await an.start_actor(
-                'streamer',
-                enable_modules=[__name__],
-            )
-            try:
-                async with (
-                    portal.open_context(streamer) as (ctx, first),
-                    ctx.open_stream() as stream,
-                ):
-                    print('Entered open_stream() caller')
-                    yield an, stream
-                    print('Exited open_stream() caller')
 
-            finally:
+    async with tractor.open_nursery() as tn:
-                print(
+        portal = await tn.start_actor('streamer', enable_modules=[__name__])
-                    'Cancelling streamer with,\n'
+        async with (
-                    '=> `Portal.cancel_actor()`'
+            portal.open_context(streamer) as (ctx, first),
-                )
+            ctx.open_stream() as stream,
-                await portal.cancel_actor()
+        ):
-                print('Cancelled streamer')
+            yield stream
 
-    except Exception as err:
+        await portal.cancel_actor()
-        print(
+    print('CANCELLED STREAMER')
-            f'`open_stream()` errored?\n'
-            f'{err!r}\n'
-        )
-        await tractor.pause(shield=True)
-        raise err
 
 
 @acm
 async def maybe_open_stream(taskname: str):
-    async with maybe_open_context(
+    async with tractor.trionics.maybe_open_context(
         # NOTE: all secondary tasks should cache hit on the same key
         acm_func=open_stream,
-    ) as (
+    ) as (cache_hit, stream):
-        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')
 
@@ -166,77 +126,27 @@ 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 an, bstream
+                yield 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
-            try:
+            yield stream
-                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(
+def test_open_local_sub_to_stream():
-    debug_mode: bool,
-):
     '''
     Verify a single inter-actor stream can can be fanned-out shared to
-    N local tasks using `trionics.maybe_open_context()`.
+    N local tasks using ``trionics.maybe_open_context():``.
 
     '''
-    timeout: float = 3.6
+    timeout: float = 3.6 if platform.system() != "Windows" else 10
-    if platform.system() == "Windows":
-        timeout: float = 10
-
-    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 (
+                maybe_open_stream(taskname) as stream,
-                    an,
-                    stream,
-                ),
             ):
                 if '0' in taskname:
                     assert isinstance(stream, tractor.MsgStream)
@@ -248,159 +158,24 @@ def test_open_local_sub_to_stream(
 
                 first = await stream.receive()
                 print(f'{taskname} started with value {first}')
-                seq: list[int] = []
+                seq = []
                 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):
-        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(
+            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,
+                    trio.open_nursery() as nurse,
                 ):
-                    for i in range(num_tasks):
+                    for i in range(10):
-                        tn.start_soon(
+                        nurse.start_soon(get_sub_and_pull, f'task_{i}')
-                            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)
-
-
-
-@acm
-async def cancel_outer_cs(
-    cs: trio.CancelScope|None = None,
-    delay: float = 0,
-):
-    # on first task delay this enough to block
-    # the 2nd task but then cancel it mid sleep
-    # so that the tn.start() inside the key-err handler block
-    # is cancelled and would previously corrupt the
-    # mutext state.
-    log.info(f'task entering sleep({delay})')
-    await trio.sleep(delay)
-    if cs:
-        log.info('task calling cs.cancel()')
-        cs.cancel()
-    trio.lowlevel.checkpoint()
-    yield
-    await trio.sleep_forever()
-
-
-def test_lock_not_corrupted_on_fast_cancel(
-    debug_mode: bool,
-    loglevel: str,
-):
-    '''
-    Verify that if the caching-task (the first to enter
-    `maybe_open_context()`) is cancelled mid-cache-miss, the embedded
-    mutex can never be left in a corrupted state.
-
-    That is, the lock is always eventually released ensuring a peer
-    (cache-hitting) task will never,
-
-    - be left to inf-block/hang on the `lock.acquire()`.
-    - try to release the lock when still owned by the caching-task
-      due to it having erronously exited without calling
-      `lock.release()`.
-
-
-    '''
-    delay: float = 1.
-
-    async def use_moc(
-        cs: trio.CancelScope|None,
-        delay: float,
-    ):
-        log.info('task entering moc')
-        async with maybe_open_context(
-            cancel_outer_cs,
-            kwargs={
-                'cs': cs,
-                'delay': delay,
-            },
-        ) as (cache_hit, _null):
-            if cache_hit:
-                log.info('2nd task entered')
-            else:
-                log.info('1st task entered')
-
-            await trio.sleep_forever()
-
-    async def main():
-        with trio.fail_after(delay + 2):
-            async with (
-                tractor.open_root_actor(
-                    debug_mode=debug_mode,
-                    loglevel=loglevel,
-                ),
-                trio.open_nursery() as tn,
-            ):
-                get_console_log('info')
-                log.info('yo starting')
-                cs = tn.cancel_scope
-                tn.start_soon(
-                    use_moc,
-                    cs,
-                    delay,
-                    name='child',
-                )
-                with trio.CancelScope() as rent_cs:
-                    await use_moc(
-                        cs=rent_cs,
-                        delay=delay,
-                    )
-
 
     trio.run(main)

tests/test_ringbuf.py

@@ -1,211 +0,0 @@
-import time
-
-import trio
-import pytest
-
-import tractor
-from tractor.ipc._ringbuf import (
-    open_ringbuf,
-    RBToken,
-    RingBuffSender,
-    RingBuffReceiver
-)
-from tractor._testing.samples import (
-    generate_sample_messages,
-)
-
-# in case you don't want to melt your cores, uncomment dis!
-pytestmark = pytest.mark.skip
-
-
-@tractor.context
-async def child_read_shm(
-    ctx: tractor.Context,
-    msg_amount: int,
-    token: RBToken,
-    total_bytes: int,
-) -> None:
-    recvd_bytes = 0
-    await ctx.started()
-    start_ts = time.time()
-    async with RingBuffReceiver(token) as receiver:
-        while recvd_bytes < total_bytes:
-            msg = await receiver.receive_some()
-            recvd_bytes += len(msg)
-
-        # make sure we dont hold any memoryviews
-        # before the ctx manager aclose()
-        msg = None
-
-    end_ts = time.time()
-    elapsed = end_ts - start_ts
-    elapsed_ms = int(elapsed * 1000)
-
-    print(f'\n\telapsed ms: {elapsed_ms}')
-    print(f'\tmsg/sec: {int(msg_amount / elapsed):,}')
-    print(f'\tbytes/sec: {int(recvd_bytes / elapsed):,}')
-
-
-@tractor.context
-async def child_write_shm(
-    ctx: tractor.Context,
-    msg_amount: int,
-    rand_min: int,
-    rand_max: int,
-    token: RBToken,
-) -> None:
-    msgs, total_bytes = generate_sample_messages(
-        msg_amount,
-        rand_min=rand_min,
-        rand_max=rand_max,
-    )
-    await ctx.started(total_bytes)
-    async with RingBuffSender(token) as sender:
-        for msg in msgs:
-            await sender.send_all(msg)
-
-
-@pytest.mark.parametrize(
-    'msg_amount,rand_min,rand_max,buf_size',
-    [
-        # simple case, fixed payloads, large buffer
-        (100_000, 0, 0, 10 * 1024),
-
-        # guaranteed wrap around on every write
-        (100, 10 * 1024, 20 * 1024, 10 * 1024),
-
-        # large payload size, but large buffer
-        (10_000, 256 * 1024, 512 * 1024, 10 * 1024 * 1024)
-    ],
-    ids=[
-        'fixed_payloads_large_buffer',
-        'wrap_around_every_write',
-        'large_payloads_large_buffer',
-    ]
-)
-def test_ringbuf(
-    msg_amount: int,
-    rand_min: int,
-    rand_max: int,
-    buf_size: int
-):
-    async def main():
-        with open_ringbuf(
-            'test_ringbuf',
-            buf_size=buf_size
-        ) as token:
-            proc_kwargs = {
-                'pass_fds': (token.write_eventfd, token.wrap_eventfd)
-            }
-
-            common_kwargs = {
-                'msg_amount': msg_amount,
-                'token': token,
-            }
-            async with tractor.open_nursery() as an:
-                send_p = await an.start_actor(
-                    'ring_sender',
-                    enable_modules=[__name__],
-                    proc_kwargs=proc_kwargs
-                )
-                recv_p = await an.start_actor(
-                    'ring_receiver',
-                    enable_modules=[__name__],
-                    proc_kwargs=proc_kwargs
-                )
-                async with (
-                    send_p.open_context(
-                        child_write_shm,
-                        rand_min=rand_min,
-                        rand_max=rand_max,
-                        **common_kwargs
-                    ) as (sctx, total_bytes),
-                    recv_p.open_context(
-                        child_read_shm,
-                        **common_kwargs,
-                        total_bytes=total_bytes,
-                    ) as (sctx, _sent),
-                ):
-                    await recv_p.result()
-
-                await send_p.cancel_actor()
-                await recv_p.cancel_actor()
-
-
-    trio.run(main)
-
-
-@tractor.context
-async def child_blocked_receiver(
-    ctx: tractor.Context,
-    token: RBToken
-):
-    async with RingBuffReceiver(token) as receiver:
-        await ctx.started()
-        await receiver.receive_some()
-
-
-def test_ring_reader_cancel():
-    async def main():
-        with open_ringbuf('test_ring_cancel_reader') as token:
-            async with (
-                tractor.open_nursery() as an,
-                RingBuffSender(token) as _sender,
-            ):
-                recv_p = await an.start_actor(
-                    'ring_blocked_receiver',
-                    enable_modules=[__name__],
-                    proc_kwargs={
-                        'pass_fds': (token.write_eventfd, token.wrap_eventfd)
-                    }
-                )
-                async with (
-                    recv_p.open_context(
-                        child_blocked_receiver,
-                        token=token
-                    ) as (sctx, _sent),
-                ):
-                    await trio.sleep(1)
-                    await an.cancel()
-
-
-    with pytest.raises(tractor._exceptions.ContextCancelled):
-        trio.run(main)
-
-
-@tractor.context
-async def child_blocked_sender(
-    ctx: tractor.Context,
-    token: RBToken
-):
-    async with RingBuffSender(token) as sender:
-        await ctx.started()
-        await sender.send_all(b'this will wrap')
-
-
-def test_ring_sender_cancel():
-    async def main():
-        with open_ringbuf(
-            'test_ring_cancel_sender',
-            buf_size=1
-        ) as token:
-            async with tractor.open_nursery() as an:
-                recv_p = await an.start_actor(
-                    'ring_blocked_sender',
-                    enable_modules=[__name__],
-                    proc_kwargs={
-                        'pass_fds': (token.write_eventfd, token.wrap_eventfd)
-                    }
-                )
-                async with (
-                    recv_p.open_context(
-                        child_blocked_sender,
-                        token=token
-                    ) as (sctx, _sent),
-                ):
-                    await trio.sleep(1)
-                    await an.cancel()
-
-
-    with pytest.raises(tractor._exceptions.ContextCancelled):
-        trio.run(main)

tests/test_root_infect_asyncio.py

@@ -147,7 +147,8 @@ def test_trio_prestarted_task_bubbles(
         await trio.sleep_forever()
 
     async def _trio_main():
-        with trio.fail_after(2 if not debug_mode else 999):
+        # with trio.fail_after(2):
+        with trio.fail_after(999):
             first: str
             chan: to_asyncio.LinkedTaskChannel
             aio_ev = asyncio.Event()
@@ -216,25 +217,32 @@ def test_trio_prestarted_task_bubbles(
                         ):
                             aio_ev.set()
 
+    with pytest.raises(
+        expected_exception=ExceptionGroup,
+    ) as excinfo:
+        tractor.to_asyncio.run_as_asyncio_guest(
+            trio_main=_trio_main,
+        )
+
+    eg = excinfo.value
+    rte_eg, rest_eg = eg.split(RuntimeError)
+
     # ensure the trio-task's error bubbled despite the aio-side
     # having (maybe) errored first.
     if aio_err_trigger in (
         'after_trio_task_starts',
         'after_start_point',
     ):
-        patt: str = 'trio-side'
+        assert len(errs := rest_eg.exceptions) == 1
-        expect_exc = TypeError
+        typerr = errs[0]
+        assert (
+            type(typerr) is TypeError
+            and
+            'trio-side' in typerr.args
+        )
 
     # when aio errors BEFORE (last) trio task is scheduled, we should
     # never see anythinb but the aio-side.
     else:
-        patt: str = 'asyncio-side'
+        assert len(rtes := rte_eg.exceptions) == 1
-        expect_exc = RuntimeError
+        assert 'asyncio-side' in rtes[0].args[0]
-
-    with pytest.raises(expect_exc) as excinfo:
-        tractor.to_asyncio.run_as_asyncio_guest(
-            trio_main=_trio_main,
-        )
-
-    caught_exc = excinfo.value
-    assert patt in caught_exc.args

tests/test_root_runtime.py

@@ -1,108 +0,0 @@
-'''
-Runtime boot/init sanity.
-
-'''
-
-import pytest
-import trio
-
-import tractor
-from tractor._exceptions import RuntimeFailure
-
-
-@tractor.context
-async def open_new_root_in_sub(
-    ctx: tractor.Context,
-) -> None:
-
-    async with tractor.open_root_actor():
-        pass
-
-
-@pytest.mark.parametrize(
-    'open_root_in',
-    ['root', 'sub'],
-    ids='open_2nd_root_in={}'.format,
-)
-def test_only_one_root_actor(
-    open_root_in: str,
-    reg_addr: tuple,
-    debug_mode: bool
-):
-    '''
-    Verify we specially fail whenever more then one root actor
-    is attempted to be opened within an already opened tree.
-
-    '''
-    async def main():
-        async with tractor.open_nursery() as an:
-
-            if open_root_in == 'root':
-                async with tractor.open_root_actor(
-                    registry_addrs=[reg_addr],
-                ):
-                    pass
-
-            ptl: tractor.Portal = await an.start_actor(
-                name='bad_rooty_boi',
-                enable_modules=[__name__],
-            )
-
-            async with ptl.open_context(
-                open_new_root_in_sub,
-            ) as (ctx, first):
-                pass
-
-    if open_root_in == 'root':
-        with pytest.raises(
-            RuntimeFailure
-        ) as excinfo:
-            trio.run(main)
-
-    else:
-        with pytest.raises(
-            tractor.RemoteActorError,
-        ) as excinfo:
-            trio.run(main)
-
-        assert excinfo.value.boxed_type is RuntimeFailure
-
-
-def test_implicit_root_via_first_nursery(
-    reg_addr: tuple,
-    debug_mode: bool
-):
-    '''
-    The first `ActorNursery` open should implicitly call
-    `_root.open_root_actor()`.
-
-    '''
-    async def main():
-        async with tractor.open_nursery() as an:
-            assert an._implicit_runtime_started
-            assert tractor.current_actor().aid.name == 'root'
-
-    trio.run(main)
-
-
-def test_runtime_vars_unset(
-    reg_addr: tuple,
-    debug_mode: bool
-):
-    '''
-    Ensure any `._state._runtime_vars` are restored to default values
-    after the root actor-runtime exits!
-
-    '''
-    assert not tractor._state._runtime_vars['_debug_mode']
-    async def main():
-        assert not tractor._state._runtime_vars['_debug_mode']
-        async with tractor.open_nursery(
-            debug_mode=True,
-        ):
-            assert tractor._state._runtime_vars['_debug_mode']
-
-        # after runtime closure, should be reverted!
-        assert not tractor._state._runtime_vars['_debug_mode']
-
-    trio.run(main)

tests/test_shm.py

@@ -8,7 +8,7 @@ import uuid
 import pytest
 import trio
 import tractor
-from tractor.ipc._shm import (
+from tractor._shm import (
     open_shm_list,
     attach_shm_list,
 )

tests/test_spawning.py

@@ -2,7 +2,6 @@
 Spawning basics
 
 """
-from functools import partial
 from typing import (
     Any,
 )
@@ -13,99 +12,74 @@ import tractor
 
 from tractor._testing import tractor_test
 
-data_to_pass_down = {
+data_to_pass_down = {'doggy': 10, 'kitty': 4}
-    'doggy': 10,
-    'kitty': 4,
-}
 
 
 async def spawn(
-    should_be_root: bool,
+    is_arbiter: bool,
     data: dict,
     reg_addr: tuple[str, int],
-
-    debug_mode: bool = False,
 ):
+    namespaces = [__name__]
+
     await trio.sleep(0.1)
-    actor = tractor.current_actor(err_on_no_runtime=False)
 
-    if should_be_root:
+    async with tractor.open_root_actor(
-        assert actor is None  # no runtime yet
+        arbiter_addr=reg_addr,
-        async with (
+    ):
-            tractor.open_root_actor(
+        actor = tractor.current_actor()
-                arbiter_addr=reg_addr,
+        assert actor.is_arbiter == is_arbiter
-            ),
+        data = data_to_pass_down
-            tractor.open_nursery() as an,
-        ):
-            # now runtime exists
-            actor: tractor.Actor = tractor.current_actor()
-            assert actor.is_arbiter == should_be_root
 
-            # spawns subproc here
+        if actor.is_arbiter:
-            portal: tractor.Portal = await an.run_in_actor(
+            async with tractor.open_nursery() as nursery:
-                fn=spawn,
 
-                # spawning args
+                # forks here
-                name='sub-actor',
+                portal = await nursery.run_in_actor(
-                enable_modules=[__name__],
+                    spawn,
+                    is_arbiter=False,
+                    name='sub-actor',
+                    data=data,
+                    reg_addr=reg_addr,
+                    enable_modules=namespaces,
+                )
 
-                # passed to a subactor-recursive RPC invoke
+                assert len(nursery._children) == 1
-                # of this same `spawn()` fn.
+                assert portal.channel.uid in tractor.current_actor()._peers
-                should_be_root=False,
+                # be sure we can still get the result
-                data=data_to_pass_down,
+                result = await portal.result()
-                reg_addr=reg_addr,
+                assert result == 10
-            )
+                return result
-
+        else:
-            assert len(an._children) == 1
+            return 10
-            assert (
-                portal.channel.uid
-                in
-                tractor.current_actor().ipc_server._peers
-            )
-
-            # get result from child subactor
-            result = await portal.result()
-            assert result == 10
-            return result
-    else:
-        assert actor.is_arbiter == should_be_root
-        return 10
 
 
-def test_run_in_actor_same_func_in_child(
+def test_local_arbiter_subactor_global_state(
-    reg_addr: tuple,
+    reg_addr,
-    debug_mode: bool,
 ):
     result = trio.run(
-        partial(
+        spawn,
-            spawn,
+        True,
-            should_be_root=True,
+        data_to_pass_down,
-            data=data_to_pass_down,
+        reg_addr,
-            reg_addr=reg_addr,
-            debug_mode=debug_mode,
-        )
     )
     assert result == 10
 
 
 async def movie_theatre_question():
-    '''
+    """A question asked in a dark theatre, in a tangent
-    A question asked in a dark theatre, in a tangent
     (errr, I mean different) process.
-
+    """
-    '''
     return 'have you ever seen a portal?'
 
 
 @tractor_test
 async def test_movie_theatre_convo(start_method):
-    '''
+    """The main ``tractor`` routine.
-    The main ``tractor`` routine.
+    """
+    async with tractor.open_nursery() as n:
 
-    '''
+        portal = await n.start_actor(
-    async with tractor.open_nursery(debug_mode=True) as an:
-
-        portal = await an.start_actor(
             'frank',
             # enable the actor to run funcs from this current module
             enable_modules=[__name__],
@@ -144,8 +118,8 @@ async def test_most_beautiful_word(
     with trio.fail_after(1):
         async with tractor.open_nursery(
             debug_mode=debug_mode,
-        ) as an:
+        ) as n:
-            portal = await an.run_in_actor(
+            portal = await n.run_in_actor(
                 cellar_door,
                 return_value=return_value,
                 name='some_linguist',

tests/test_trioisms.py

@@ -6,18 +6,10 @@ want to see changed.
 from contextlib import (
     asynccontextmanager as acm,
 )
-from types import ModuleType
-
-from functools import partial
 
 import pytest
-from _pytest import pathlib
-from tractor.trionics import collapse_eg
 import trio
 from trio import TaskStatus
-from tractor._testing import (
-    examples_dir,
-)
 
 
 @pytest.mark.parametrize(
@@ -72,8 +64,9 @@ def test_stashed_child_nursery(use_start_soon):
     async def main():
 
         async with (
-            collapse_eg(),
+            trio.open_nursery(
-            trio.open_nursery() as pn,
+                strict_exception_groups=False,
+            ) as pn,
         ):
             cn = await pn.start(mk_child_nursery)
             assert cn
@@ -113,21 +106,66 @@ def test_acm_embedded_nursery_propagates_enter_err(
     debug_mode: bool,
 ):
     '''
-    Demo how a masking `trio.Cancelled` could be handled by unmasking
+    Demo how a masking `trio.Cancelled` could be handled by unmasking from the
-    from the `.__context__` field when a user (by accident) re-raises
+    `.__context__` field when a user (by accident) re-raises from a `finally:`.
-    from a `finally:`.
 
     '''
     import tractor
 
+    @acm
+    async def maybe_raise_from_masking_exc(
+        tn: trio.Nursery,
+        unmask_from: BaseException|None = trio.Cancelled
+
+        # TODO, maybe offer a collection?
+        # unmask_from: set[BaseException] = {
+        #     trio.Cancelled,
+        # },
+    ):
+        if not unmask_from:
+            yield
+            return
+
+        try:
+            yield
+        except* unmask_from as be_eg:
+
+            # TODO, if we offer `unmask_from: set`
+            # for masker_exc_type in unmask_from:
+
+            matches, rest = be_eg.split(unmask_from)
+            if not matches:
+                raise
+
+            for exc_match in be_eg.exceptions:
+                if (
+                    (exc_ctx := exc_match.__context__)
+                    and
+                    type(exc_ctx) not in {
+                        # trio.Cancelled,  # always by default?
+                        unmask_from,
+                    }
+                ):
+                    exc_ctx.add_note(
+                        f'\n'
+                        f'WARNING: the above error was masked by a {unmask_from!r} !?!\n'
+                        f'Are you always cancelling? Say from a `finally:` ?\n\n'
+
+                        f'{tn!r}'
+                    )
+                    raise exc_ctx from exc_match
+
+
     @acm
     async def wraps_tn_that_always_cancels():
         async with (
             trio.open_nursery() as tn,
-            tractor.trionics.maybe_raise_from_masking_exc(
+            maybe_raise_from_masking_exc(
+                tn=tn,
                 unmask_from=(
-                    (trio.Cancelled,) if unmask_from_canc
+                    trio.Cancelled
-                    else ()
+                    if unmask_from_canc
+                    else None
                 ),
             )
         ):
@@ -150,12 +188,11 @@ def test_acm_embedded_nursery_propagates_enter_err(
                 assert not tn.cancel_scope.cancel_called
                 assert 0
 
-        if debug_mode:
+        assert (
-            assert (
+            (err := bxerr.value)
-                (err := bxerr.value)
+            and
-                and
+            type(err) is AssertionError
-                type(err) is AssertionError
+        )
-            )
 
     with pytest.raises(ExceptionGroup) as excinfo:
         trio.run(_main)
@@ -164,139 +201,3 @@ def test_acm_embedded_nursery_propagates_enter_err(
     assert_eg, rest_eg = eg.split(AssertionError)
 
     assert len(assert_eg.exceptions) == 1
-
-
-def test_gatherctxs_with_memchan_breaks_multicancelled(
-    debug_mode: bool,
-):
-    '''
-    Demo how a using an `async with sndchan` inside
-    a `.trionics.gather_contexts()` task will break a strict-eg-tn's
-    multi-cancelled absorption..
-
-    '''
-    from tractor import (
-        trionics,
-    )
-
-    @acm
-    async def open_memchan() -> trio.abc.ReceiveChannel:
-
-        task: trio.Task = trio.lowlevel.current_task()
-        print(
-            f'Opening {task!r}\n'
-        )
-
-        # 1 to force eager sending
-        send, recv = trio.open_memory_channel(16)
-
-        try:
-            async with send:
-                yield recv
-        finally:
-            print(
-                f'Closed {task!r}\n'
-            )
-
-    async def main():
-        async with (
-            # XXX should ensure ONLY the KBI
-            # is relayed upward
-            collapse_eg(),
-            trio.open_nursery(), # as tn,
-
-            trionics.gather_contexts([
-                open_memchan(),
-                open_memchan(),
-            ]) as recv_chans,
-        ):
-            assert len(recv_chans) == 2
-
-            await trio.sleep(1)
-            raise KeyboardInterrupt
-            # tn.cancel_scope.cancel()
-
-    with pytest.raises(KeyboardInterrupt):
-        trio.run(main)
-
-
-@pytest.mark.parametrize(
-    'raise_unmasked', [
-        True,
-        pytest.param(
-            False,
-            marks=pytest.mark.xfail(
-                reason="see examples/trio/send_chan_aclose_masks.py"
-            )
-        ),
-    ]
-)
-@pytest.mark.parametrize(
-    'child_errors_mid_stream',
-    [True, False],
-)
-def test_unmask_aclose_as_checkpoint_on_aexit(
-    raise_unmasked: bool,
-    child_errors_mid_stream: bool,
-    debug_mode: bool,
-):
-    '''
-    Verify that our unmasker util works over the common case where
-    a mem-chan's `.aclose()` is included in an `@acm` stack
-    and it being currently a checkpoint, can `trio.Cancelled`-mask an embedded
-    exception from user code resulting in a silent failure which
-    appears like graceful cancellation.
-
-    This test suite is mostly implemented as an example script so it
-    could more easily be shared with `trio`-core peeps as `tractor`-less
-    minimum reproducing example.
-
-    '''
-    mod: ModuleType = pathlib.import_path(
-        examples_dir()
-        / 'trio'
-        / 'send_chan_aclose_masks_beg.py',
-        root=examples_dir(),
-        consider_namespace_packages=False,
-    )
-    with pytest.raises(RuntimeError):
-        trio.run(partial(
-            mod.main,
-            raise_unmasked=raise_unmasked,
-            child_errors_mid_stream=child_errors_mid_stream,
-        ))
-
-
-
-@pytest.mark.parametrize(
-    'ignore_special_cases', [
-        True,
-        pytest.param(
-            False,
-            marks=pytest.mark.xfail(
-                reason="see examples/trio/lockacquire_not_umasked.py"
-            )
-        ),
-    ]
-)
-def test_cancelled_lockacquire_in_ipctx_not_unmasked(
-    ignore_special_cases: bool,
-    loglevel: str,
-    debug_mode: bool,
-):
-    mod: ModuleType = pathlib.import_path(
-        examples_dir()
-        / 'trio'
-        / 'lockacquire_not_unmasked.py',
-        root=examples_dir(),
-        consider_namespace_packages=False,
-    )
-    async def _main():
-        with trio.fail_after(2):
-            await mod.main(
-                ignore_special_cases=ignore_special_cases,
-                loglevel=loglevel,
-                debug_mode=debug_mode,
-            )
-
-    trio.run(_main)

tractor/__init__.py

@@ -64,7 +64,7 @@ from ._root import (
     run_daemon as run_daemon,
     open_root_actor as open_root_actor,
 )
-from .ipc import Channel as Channel
+from ._ipc import Channel as Channel
 from ._portal import Portal as Portal
 from ._runtime import Actor as Actor
 # from . import hilevel as hilevel

tractor/_addr.py

@@ -1,282 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-from __future__ import annotations
-from uuid import uuid4
-from typing import (
-    Protocol,
-    ClassVar,
-    Type,
-    TYPE_CHECKING,
-)
-
-from bidict import bidict
-from trio import (
-    SocketListener,
-)
-
-from .log import get_logger
-from ._state import (
-    _def_tpt_proto,
-)
-from .ipc._tcp import TCPAddress
-from .ipc._uds import UDSAddress
-
-if TYPE_CHECKING:
-    from ._runtime import Actor
-
-log = get_logger(__name__)
-
-
-# TODO, maybe breakout the netns key to a struct?
-# class NetNs(Struct)[str, int]:
-#     ...
-
-# TODO, can't we just use a type alias
-# for this? namely just some `tuple[str, int, str, str]`?
-#
-# -[ ] would also just be simpler to keep this as SockAddr[tuple]
-#     or something, implying it's just a simple pair of values which can
-#     presumably be mapped to all transports?
-# -[ ] `pydoc socket.socket.getsockname()` delivers a 4-tuple for
-#     ipv6 `(hostaddr, port, flowinfo, scope_id)`.. so how should we
-#     handle that?
-# -[ ] as a further alternative to this wrap()/unwrap() approach we
-#     could just implement `enc/dec_hook()`s for the `Address`-types
-#     and just deal with our internal objs directly and always and
-#     leave it to the codec layer to figure out marshalling?
-#    |_ would mean only one spot to do the `.unwrap()` (which we may
-#       end up needing to call from the hook()s anyway?)
-# -[x] rename to `UnwrappedAddress[Descriptor]` ??
-#    seems like the right name as per,
-#    https://www.geeksforgeeks.org/introduction-to-address-descriptor/
-#
-UnwrappedAddress = (
-    # tcp/udp/uds
-    tuple[
-        str,  # host/domain(tcp), filesys-dir(uds)
-        int|str,  # port/path(uds)
-    ]
-    # ?TODO? should we also include another 2 fields from
-    # our `Aid` msg such that we include the runtime `Actor.uid`
-    # of `.name` and `.uuid`?
-    # - would ensure uniqueness across entire net?
-    # - allows for easier runtime-level filtering of "actors by
-    #   service name"
-)
-
-
-# TODO, maybe rename to `SocketAddress`?
-class Address(Protocol):
-    proto_key: ClassVar[str]
-    unwrapped_type: ClassVar[UnwrappedAddress]
-
-    # TODO, i feel like an `.is_bound()` is a better thing to
-    # support?
-    # Lke, what use does this have besides a noop and if it's not
-    # valid why aren't we erroring on creation/use?
-    @property
-    def is_valid(self) -> bool:
-        ...
-
-    # TODO, maybe `.netns` is a better name?
-    @property
-    def namespace(self) -> tuple[str, int]|None:
-        '''
-        The if-available, OS-specific "network namespace" key.
-
-        '''
-        ...
-
-    @property
-    def bindspace(self) -> str:
-        '''
-        Deliver the socket address' "bindable space" from
-        a `socket.socket.bind()` and thus from the perspective of
-        specific transport protocol domain.
-
-        I.e. for most (layer-4) network-socket protocols this is
-        normally the ipv4/6 address, for UDS this is normally
-        a filesystem (sub-directory).
-
-        For (distributed) network protocols this is normally the routing
-        layer's domain/(ip-)address, though it might also include a "network namespace"
-        key different then the default.
-
-        For local-host-only transports this is either an explicit
-        namespace (with types defined by the OS: netns, Cgroup, IPC,
-        pid, etc. on linux) or failing that the sub-directory in the
-        filesys in which socket/shm files are located *under*.
-
-        '''
-        ...
-
-    @classmethod
-    def from_addr(cls, addr: UnwrappedAddress) -> Address:
-        ...
-
-    def unwrap(self) -> UnwrappedAddress:
-        '''
-        Deliver the underying minimum field set in
-        a primitive python data type-structure.
-        '''
-        ...
-
-    @classmethod
-    def get_random(
-        cls,
-        current_actor: Actor,
-        bindspace: str|None = None,
-    ) -> Address:
-        ...
-
-    # TODO, this should be something like a `.get_def_registar_addr()`
-    # or similar since,
-    # - it should be a **host singleton** (not root/tree singleton)
-    # - we **only need this value** when one isn't provided to the
-    #   runtime at boot and we want to implicitly provide a host-wide
-    #   registrar.
-    # - each rooted-actor-tree should likely have its own
-    #   micro-registry (likely the root being it), also see
-    @classmethod
-    def get_root(cls) -> Address:
-        ...
-
-    def __repr__(self) -> str:
-        ...
-
-    def __eq__(self, other) -> bool:
-        ...
-
-    async def open_listener(
-        self,
-        **kwargs,
-    ) -> SocketListener:
-        ...
-
-    async def close_listener(self):
-        ...
-
-
-_address_types: bidict[str, Type[Address]] = {
-    'tcp': TCPAddress,
-    'uds': UDSAddress
-}
-
-
-# TODO! really these are discovery sys default addrs ONLY useful for
-# when none is provided to a root actor on first boot.
-_default_lo_addrs: dict[
-    str,
-    UnwrappedAddress
-] = {
-    'tcp': TCPAddress.get_root().unwrap(),
-    'uds': UDSAddress.get_root().unwrap(),
-}
-
-
-def get_address_cls(name: str) -> Type[Address]:
-    return _address_types[name]
-
-
-def is_wrapped_addr(addr: any) -> bool:
-    return type(addr) in _address_types.values()
-
-
-def mk_uuid() -> str:
-    '''
-    Encapsulate creation of a uuid4 as `str` as used
-    for creating `Actor.uid: tuple[str, str]` and/or
-    `.msg.types.Aid`.
-
-    '''
-    return str(uuid4())
-
-
-def wrap_address(
-    addr: UnwrappedAddress
-) -> Address:
-    '''
-    Wrap an `UnwrappedAddress` as an `Address`-type based
-    on matching builtin python data-structures which we adhoc
-    use for each.
-
-    XXX NOTE, careful care must be placed to ensure
-    `UnwrappedAddress` cases are **definitely unique** otherwise the
-    wrong transport backend may be loaded and will break many
-    low-level things in our runtime in a not-fun-to-debug way!
-
-    XD
-
-    '''
-    if is_wrapped_addr(addr):
-        return addr
-
-    cls: Type|None = None
-    # if 'sock' in addr[0]:
-    #     import pdbp; pdbp.set_trace()
-    match addr:
-
-        # classic network socket-address as tuple/list
-        case (
-            (str(), int())
-            |
-            [str(), int()]
-        ):
-            cls = TCPAddress
-
-        case (
-            # (str()|Path(), str()|Path()),
-            # ^TODO? uhh why doesn't this work!?
-
-            (_, filename)
-        ) if type(filename) is str:
-            cls = UDSAddress
-
-        # likely an unset UDS or TCP reg address as defaulted in
-        # `_state._runtime_vars['_root_mailbox']`
-        #
-        # TODO? figure out when/if we even need this?
-        case (
-            None
-            |
-            [None, None]
-        ):
-            cls: Type[Address] = get_address_cls(_def_tpt_proto)
-            addr: UnwrappedAddress = cls.get_root().unwrap()
-
-        case _:
-            # import pdbp; pdbp.set_trace()
-            raise TypeError(
-                f'Can not wrap unwrapped-address ??\n'
-                f'type(addr): {type(addr)!r}\n'
-                f'addr: {addr!r}\n'
-            )
-
-    return cls.from_addr(addr)
-
-
-def default_lo_addrs(
-    transports: list[str],
-) -> list[Type[Address]]:
-    '''
-    Return the default, host-singleton, registry address
-    for an input transport key set.
-
-    '''
-    return [
-        _default_lo_addrs[transport]
-        for transport in transports
-    ]

tractor/_child.py

@@ -31,12 +31,8 @@ def parse_uid(arg):
     return str(name), str(uuid)  # ensures str encoding
 
 def parse_ipaddr(arg):
-    try:
+    host, port = literal_eval(arg)
-        return literal_eval(arg)
+    return (str(host), int(port))
-
-    except (ValueError, SyntaxError):
-        # UDS: try to interpret as a straight up str
-        return arg
 
 
 if __name__ == "__main__":
@@ -50,8 +46,8 @@ if __name__ == "__main__":
     args = parser.parse_args()
 
     subactor = Actor(
-        name=args.uid[0],
+        args.uid[0],
-        uuid=args.uid[1],
+        uid=args.uid[1],
         loglevel=args.loglevel,
         spawn_method="trio"
     )

tractor/_clustering.py

@@ -55,17 +55,10 @@ async def open_actor_cluster(
         raise ValueError(
             'Number of names is {len(names)} but count it {count}')
 
-    async with (
+    async with tractor.open_nursery(
-        # tractor.trionics.collapse_eg(),
+        **runtime_kwargs,
-        tractor.open_nursery(
+    ) as an:
-            **runtime_kwargs,
+        async with trio.open_nursery() as n:
-        ) as an
-    ):
-        async with (
-            # tractor.trionics.collapse_eg(),
-            trio.open_nursery() as tn,
-            tractor.trionics.maybe_raise_from_masking_exc()
-        ):
             uid = tractor.current_actor().uid
 
             async def _start(name: str) -> None:
@@ -76,8 +69,9 @@ async def open_actor_cluster(
                 )
 
             for name in names:
-                tn.start_soon(_start, name)
+                n.start_soon(_start, name)
 
         assert len(portals) == count
         yield portals
+
         await an.cancel(hard_kill=hard_kill)

tractor/_context.py

@@ -89,7 +89,7 @@ from .msg import (
     pretty_struct,
     _ops as msgops,
 )
-from .ipc import (
+from ._ipc import (
     Channel,
 )
 from ._streaming import (
@@ -101,14 +101,11 @@ from ._state import (
     debug_mode,
     _ctxvar_Context,
 )
-from .trionics import (
-    collapse_eg,
-)
 # ------ - ------
 if TYPE_CHECKING:
     from ._portal import Portal
     from ._runtime import Actor
-    from .ipc._transport import MsgTransport
+    from ._ipc import MsgTransport
     from .devx._frame_stack import (
         CallerInfo,
     )
@@ -154,7 +151,7 @@ class Context:
     2 cancel-scope-linked, communicating and parallel executing
     `Task`s. Contexts are allocated on each side of any task
     RPC-linked msg dialog, i.e. for every request to a remote
-    actor from a `Portal`. On the "child" side a context is
+    actor from a `Portal`. On the "callee" side a context is
     always allocated inside `._rpc._invoke()`.
 
     TODO: more detailed writeup on cancellation, error and
@@ -222,8 +219,8 @@ class Context:
     # `._runtime.invoke()`.
     _remote_func_type: str | None = None
 
-    # NOTE: (for now) only set (a portal) on the parent side since
+    # NOTE: (for now) only set (a portal) on the caller side since
-    # the child doesn't generally need a ref to one and should
+    # the callee doesn't generally need a ref to one and should
     # normally need to explicitly ask for handle to its peer if
     # more the the `Context` is needed?
     _portal: Portal | None = None
@@ -252,12 +249,12 @@ class Context:
     _outcome_msg: Return|Error|ContextCancelled = Unresolved
 
     # on a clean exit there should be a final value
-    # delivered from the far end "child" task, so
+    # delivered from the far end "callee" task, so
     # this value is only set on one side.
     # _result: Any | int = None
     _result: PayloadT|Unresolved = Unresolved
 
-    # if the local "parent"  task errors this value is always set
+    # if the local "caller"  task errors this value is always set
     # to the error that was captured in the
     # `Portal.open_context().__aexit__()` teardown block OR, in
     # 2 special cases when an (maybe) expected remote error
@@ -293,9 +290,9 @@ class Context:
     # a `ContextCancelled` due to a call to `.cancel()` triggering
     # "graceful closure" on either side:
     # - `._runtime._invoke()` will check this flag before engaging
-    #   the crash handler REPL in such cases where the "child"
+    #   the crash handler REPL in such cases where the "callee"
     #   raises the cancellation,
-    # - `.devx.debug.lock_stdio_for_peer()` will set it to `False` if
+    # - `.devx._debug.lock_stdio_for_peer()` will set it to `False` if
     #   the global tty-lock has been configured to filter out some
     #   actors from being able to acquire the debugger lock.
     _enter_debugger_on_cancel: bool = True
@@ -307,8 +304,8 @@ class Context:
     _stream_opened: bool = False
     _stream: MsgStream|None = None
 
-    # the parent-task's calling-fn's frame-info, the frame above
+    # caller of `Portal.open_context()` for
-    # `Portal.open_context()`, for introspection/logging.
+    # logging purposes mostly
     _caller_info: CallerInfo|None = None
 
     # overrun handling machinery
@@ -369,7 +366,7 @@ class Context:
             # f'   ---\n'
             f' |_ipc: {self.dst_maddr}\n'
             # f'   dst_maddr{ds}{self.dst_maddr}\n'
-            f"   uid{ds}'{self.chan.aid}'\n"
+            f"   uid{ds}'{self.chan.uid}'\n"
             f"   cid{ds}'{self.cid}'\n"
             # f'   ---\n'
             f'\n'
@@ -442,25 +439,25 @@ class Context:
         '''
         Records whether cancellation has been requested for this context
         by a call to  `.cancel()` either due to,
-        - an explicit call by some local task,
+        - either an explicit call by some local task,
         - or an implicit call due to an error caught inside
-          the `Portal.open_context()` block.
+          the ``Portal.open_context()`` block.
 
         '''
         return self._cancel_called
 
-    # XXX, to debug who frickin sets it..
+    @cancel_called.setter
-    # @cancel_called.setter
+    def cancel_called(self, val: bool) -> None:
-    # def cancel_called(self, val: bool) -> None:
+        '''
-    #     '''
+        Set the self-cancelled request `bool` value.
-    #     Set the self-cancelled request `bool` value.
 
-    #     '''
+        '''
-    #     if val:
+        # to debug who frickin sets it..
-    #         from .devx import pause_from_sync
+        # if val:
-    #         pause_from_sync()
+        #     from .devx import pause_from_sync
+        #     pause_from_sync()
 
-    #     self._cancel_called = val
+        self._cancel_called = val
 
     @property
     def canceller(self) -> tuple[str, str]|None:
@@ -529,11 +526,11 @@ class Context:
         '''
         Exactly the value of `self._scope.cancelled_caught`
         (delegation) and should only be (able to be read as)
-        `True` for a `.side == "parent"` ctx wherein the
+        `True` for a `.side == "caller"` ctx wherein the
         `Portal.open_context()` block was exited due to a call to
         `._scope.cancel()` - which should only ocurr in 2 cases:
 
-        - a parent side calls `.cancel()`, the far side cancels
+        - a caller side calls `.cancel()`, the far side cancels
           and delivers back a `ContextCancelled` (making
           `.cancel_acked == True`) and `._scope.cancel()` is
           called by `._maybe_cancel_and_set_remote_error()` which
@@ -542,20 +539,20 @@ class Context:
           => `._scope.cancelled_caught == True` by normal `trio`
           cs semantics.
 
-        - a parent side is delivered a `._remote_error:
+        - a caller side is delivered a `._remote_error:
           RemoteActorError` via `._deliver_msg()` and a transitive
           call to `_maybe_cancel_and_set_remote_error()` calls
           `._scope.cancel()` and that cancellation eventually
           results in `trio.Cancelled`(s) caught in the
           `.open_context()` handling around the @acm's `yield`.
 
-        Only as an FYI, in the "child" side case it can also be
+        Only as an FYI, in the "callee" side case it can also be
         set but never is readable by any task outside the RPC
         machinery in `._invoke()` since,:
-        - when a child side calls `.cancel()`, `._scope.cancel()`
+        - when a callee side calls `.cancel()`, `._scope.cancel()`
           is called immediately and handled specially inside
           `._invoke()` to raise a `ContextCancelled` which is then
-          sent to the parent side.
+          sent to the caller side.
 
           However, `._scope.cancelled_caught` can NEVER be
           accessed/read as `True` by any RPC invoked task since it
@@ -635,71 +632,6 @@ class Context:
         '''
         await self.chan.send(Stop(cid=self.cid))
 
-    @property
-    def parent_task(self) -> trio.Task:
-        '''
-        This IPC context's "owning task" which is a `trio.Task`
-        on one of the "sides" of the IPC.
-
-        Note that the "parent_" prefix here refers to the local
-        `trio` task tree using the same interface as
-        `trio.Nursery.parent_task` whereas for IPC contexts,
-        a different cross-actor task hierarchy exists:
-
-        - a "parent"-side which originally entered
-          `Portal.open_context()`,
-
-        - the "child"-side which was spawned and scheduled to invoke
-          a function decorated with `@tractor.context`.
-
-        This task is thus a handle to mem-domain-distinct/per-process
-        `Nursery.parent_task` depending on in which of the above
-        "sides" this context exists.
-
-        '''
-        return self._task
-
-    def _is_blocked_on_rx_chan(self) -> bool:
-        '''
-        Predicate to indicate whether the owner `._task: trio.Task` is
-        currently blocked (by `.receive()`-ing) on its underlying RPC
-        feeder `._rx_chan`.
-
-        This knowledge is highly useful when handling so called
-        "out-of-band" (OoB) cancellation conditions where a peer
-        actor's task transmitted some remote error/cancel-msg and we
-        must know whether to signal-via-cancel currently executing
-        "user-code" (user defined code embedded in `ctx._scope`) or
-        simply to forward the IPC-msg-as-error **without calling**
-        `._scope.cancel()`.
-
-        In the latter case it is presumed that if the owner task is
-        blocking for the next IPC msg, it will eventually receive,
-        process and raise the equivalent local error **without**
-        requiring `._scope.cancel()` to be explicitly called by the
-        *delivering OoB RPC-task* (via `_deliver_msg()`).
-
-        '''
-        # NOTE, see the mem-chan meth-impls for *why* this
-        # logic works,
-        # `trio._channel.MemoryReceiveChannel.receive[_nowait]()`
-        #
-        # XXX realize that this is NOT an
-        # official/will-be-loudly-deprecated API:
-        # - https://trio.readthedocs.io/en/stable/reference-lowlevel.html#trio.lowlevel.Task.custom_sleep_data
-        #  |_https://trio.readthedocs.io/en/stable/reference-lowlevel.html#trio.lowlevel.wait_task_rescheduled
-        #
-        # orig repo intro in the mem-chan change over patch:
-        # - https://github.com/python-trio/trio/pull/586#issuecomment-414039117
-        #  |_https://github.com/python-trio/trio/pull/616
-        #  |_https://github.com/njsmith/trio/commit/98c38cef6f62e731bf8c7190e8756976bface8f0
-        #
-        return (
-            self._task.custom_sleep_data
-            is
-            self._rx_chan
-        )
-
     def _maybe_cancel_and_set_remote_error(
         self,
         error: BaseException,
@@ -731,7 +663,7 @@ class Context:
         when called/closed by actor local task(s).
 
         NOTEs: 
-          - It is expected that the parent has previously unwrapped
+          - It is expected that the caller has previously unwrapped
             the remote error using a call to `unpack_error()` and
             provides that output exception value as the input
             `error` argument *here*.
@@ -741,7 +673,7 @@ class Context:
             `Portal.open_context()` (ideally) we want to interrupt
             any ongoing local tasks operating within that
             `Context`'s cancel-scope so as to be notified ASAP of
-            the remote error and engage any parent handling (eg.
+            the remote error and engage any caller handling (eg.
             for cross-process task supervision).
 
           - In some cases we may want to raise the remote error
@@ -808,8 +740,6 @@ 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
@@ -852,27 +782,13 @@ class Context:
         if self._canceller is None:
             log.error('Ctx has no canceller set!?')
 
-        cs: trio.CancelScope = self._scope
-
-        # ?TODO? see comment @ .start_remote_task()`
-        #
-        # if not cs:
-        #     from .devx import mk_pdb
-        #     mk_pdb().set_trace()
-        #     raise RuntimeError(
-        #         f'IPC ctx was not be opened prior to remote error delivery !?\n'
-        #         f'{self}\n'
-        #         f'\n'
-        #         f'`Portal.open_context()` must be entered (somewhere) beforehand!\n'
-        #     )
-
         # Cancel the local `._scope`, catch that
         # `._scope.cancelled_caught` and re-raise any remote error
         # once exiting (or manually calling `.wait_for_result()`) the
         # `.open_context()`  block.
+        cs: trio.CancelScope = self._scope
         if (
             cs
-            and not cs.cancel_called
 
             # XXX this is an expected cancel request response
             # message and we **don't need to raise it** in the
@@ -881,7 +797,8 @@ class Context:
             # if `._cancel_called` then `.cancel_acked and .cancel_called`
             # always should be set.
             and not self._is_self_cancelled()
-            # and not cs.cancelled_caught
+            and not cs.cancel_called
+            and not cs.cancelled_caught
         ):
             if (
                 msgerr
@@ -892,7 +809,7 @@ class Context:
                 not self._cancel_on_msgerr
             ):
                 message: str = (
-                    f'NOT Cancelling `Context._scope` since,\n'
+                    'NOT Cancelling `Context._scope` since,\n'
                     f'Context._cancel_on_msgerr = {self._cancel_on_msgerr}\n\n'
                     f'AND we got a msg-type-error!\n'
                     f'{error}\n'
@@ -902,43 +819,13 @@ class Context:
                 # `trio.Cancelled` subtype here ;)
                 # https://github.com/goodboy/tractor/issues/368
                 message: str = 'Cancelling `Context._scope` !\n\n'
-                cs.cancel()
+                # from .devx import pause_from_sync
-
+                # pause_from_sync()
-        # TODO, explicit condition for OoB (self-)cancellation?
+                self._scope.cancel()
-        # - we called `Portal.cancel_actor()` from this actor
+        else:
-        #   and the peer ctx task delivered ctxc due to it.
+            message: str = 'NOT cancelling `Context._scope` !\n\n'
-        # - currently `self._is_self_cancelled()` will be true
-        #   since the ctxc.canceller check will match us even though it
-        #   wasn't from this ctx specifically!
-        elif (
-            cs
-            and self._is_self_cancelled()
-            and not cs.cancel_called
-        ):
-            message: str = (
-                'Cancelling `ctx._scope` due to OoB self-cancel ?!\n'
-                '\n'
-            )
             # from .devx import mk_pdb
             # mk_pdb().set_trace()
-            # TODO XXX, required to fix timeout failure in
-            # `test_cancelled_lockacquire_in_ipctx_not_unmaskeed`
-            #
-
-            # XXX NOTE XXX, this is SUPER SUBTLE!
-            # we only want to cancel our embedded `._scope`
-            # if the ctx's current/using task is NOT blocked
-            # on `._rx_chan.receive()` and on some other
-            # `trio`-checkpoint since in the former case
-            # any `._remote_error` will be relayed through
-            # the rx-chan and appropriately raised by the owning
-            # `._task` directly. IF the owner task is however
-            # blocking elsewhere we need to interrupt it **now**.
-            if not self._is_blocked_on_rx_chan():
-                cs.cancel()
-        else:
-            # rx_stats = self._rx_chan.statistics()
-            message: str = 'NOT cancelling `Context._scope` !\n\n'
 
         fmt_str: str = 'No `self._scope: CancelScope` was set/used ?\n'
         if (
@@ -962,7 +849,6 @@ class Context:
                 +
                 cs_fmt
             )
-
         log.cancel(
             message
             +
@@ -973,10 +859,19 @@ class Context:
     @property
     def dst_maddr(self) -> str:
         chan: Channel = self.chan
+        dst_addr, dst_port = chan.raddr
         trans: MsgTransport = chan.transport
         # cid: str = self.cid
         # cid_head, cid_tail = cid[:6], cid[-6:]
-        return trans.maddr
+        return (
+            f'/ipv4/{dst_addr}'
+            f'/{trans.name_key}/{dst_port}'
+            # f'/{self.chan.uid[0]}'
+            # f'/{self.cid}'
+
+            # f'/cid={cid_head}..{cid_tail}'
+            # TODO: ? not use this ^ right ?
+        )
 
     dmaddr = dst_maddr
 
@@ -995,11 +890,6 @@ class Context:
 
     @property
     def repr_caller(self) -> str:
-        '''
-        Render a "namespace-path" style representation of the calling
-        task-fn.
-
-        '''
         ci: CallerInfo|None = self._caller_info
         if ci:
             return (
@@ -1013,7 +903,7 @@ class Context:
     def repr_api(self) -> str:
         return 'Portal.open_context()'
 
-        # TODO: use `.dev._frame_stack` scanning to find caller fn!
+        # TODO: use `.dev._frame_stack` scanning to find caller!
         # ci: CallerInfo|None = self._caller_info
         # if ci:
         #     return (
@@ -1048,27 +938,26 @@ class Context:
         => That is, an IPC `Context` (this) **does not**
            have the same semantics as a `trio.CancelScope`.
 
-        If the parent (who entered the `Portal.open_context()`)
+        If the caller (who entered the `Portal.open_context()`)
         desires that the internal block's cancel-scope  be
         cancelled it should open its own `trio.CancelScope` and
         manage it as needed.
 
         '''
         side: str = self.side
-        self._cancel_called = True
+        # XXX for debug via the `@.setter`
-        # ^ XXX for debug via the `@.setter`
+        self.cancel_called = True
-        # self.cancel_called = True
 
         header: str = (
-            f'Cancelling ctx from {side!r}-side\n'
+            f'Cancelling ctx from {side.upper()}-side\n'
         )
         reminfo: str = (
             # ' =>\n'
             # f'Context.cancel() => {self.chan.uid}\n'
-            f'\n'
             f'c)=> {self.chan.uid}\n'
-            f'   |_[{self.dst_maddr}\n'
+            # f'{self.chan.uid}\n'
-            f'     >> {self.repr_rpc}\n'
+            f'  |_ @{self.dst_maddr}\n'
+            f'    >> {self.repr_rpc}\n'
             # f'    >> {self._nsf}() -> {codec}[dict]:\n\n'
             # TODO: pull msg-type from spec re #320
         )
@@ -1121,6 +1010,7 @@ class Context:
                 else:
                     log.cancel(
                         f'Timed out on cancel request of remote task?\n'
+                        f'\n'
                         f'{reminfo}'
                     )
 
@@ -1131,7 +1021,7 @@ class Context:
         # `_invoke()` RPC task.
         #
         # NOTE: on this side we ALWAYS cancel the local scope
-        # since the parent expects a `ContextCancelled` to be sent
+        # since the caller expects a `ContextCancelled` to be sent
         # from `._runtime._invoke()` back to the other side. The
         # logic for catching the result of the below
         # `._scope.cancel()` is inside the `._runtime._invoke()`
@@ -1188,25 +1078,9 @@ class Context:
         |RemoteActorError  # stream overrun caused and ignored by us
     ):
         '''
-        Maybe raise a remote error depending on the type of error and
+        Maybe raise a remote error depending on the type of error
-        *who*, i.e. which side of the task pair across actors,
+        and *who* (i.e. which task from which actor) requested
-        requested a cancellation (if any).
+        a  cancellation (if any).
-
-        Depending on the input config-params suppress raising
-        certain remote excs:
-
-        - if `remote_error: ContextCancelled` (ctxc) AND this side's
-          task is the "requester", it at somem point called
-          `Context.cancel()`, then the peer's ctxc is treated
-          as a "cancel ack".
-
-         |_ this behaves exactly like how `trio.Nursery.cancel_scope`
-            absorbs any `BaseExceptionGroup[trio.Cancelled]` wherein the
-            owning parent task never will raise a `trio.Cancelled`
-            if `CancelScope.cancel_called == True`.
-
-        - `remote_error: StreamOverrrun` (overrun) AND
-           `raise_overrun_from_self` is set.
 
         '''
         __tracebackhide__: bool = hide_tb
@@ -1248,19 +1122,18 @@ class Context:
             # for this ^, NO right?
 
         ) or (
-            # NOTE: whenever this side is the cause of an
+            # NOTE: whenever this context is the cause of an
-            # overrun on the peer side, i.e. we sent msgs too
+            # overrun on the remote side (aka we sent msgs too
-            # fast and the peer task was overrun according
+            # fast that the remote task was overrun according
-            # to `MsgStream` buffer settings, AND this was
+            # to `MsgStream` buffer settings) AND the caller
-            # called with `raise_overrun_from_self=True` (the
+            # has requested to not raise overruns this side
-            # default), silently absorb any `StreamOverrun`.
+            # caused, we also silently absorb any remotely
-            #
+            # boxed `StreamOverrun`. This is mostly useful for
-            # XXX, this is namely useful for supressing such faults
+            # supressing such faults during
-            # during cancellation/error/final-result handling inside
+            # cancellation/error/final-result handling inside
-            # `.msg._ops.drain_to_final_msg()` such that we do not
+            # `msg._ops.drain_to_final_msg()` such that we do not
-            # raise during a cancellation-request, i.e. when
+            # raise such errors particularly in the case where
             # `._cancel_called == True`.
-            #
             not raise_overrun_from_self
             and isinstance(remote_error, RemoteActorError)
             and remote_error.boxed_type is StreamOverrun
@@ -1304,8 +1177,8 @@ class Context:
 
     ) -> Any|Exception:
         '''
-        From some (parent) side task, wait for and return the final
+        From some (caller) side task, wait for and return the final
-        result from the remote (child) side's task.
+        result from the remote (callee) side's task.
 
         This provides a mechanism for one task running in some actor to wait
         on another task at the other side, in some other actor, to terminate.
@@ -1370,8 +1243,8 @@ class Context:
 
             # ?XXX, should already be set in `._deliver_msg()` right?
             if self._outcome_msg is not Unresolved:
-                # from .devx import debug
+                # from .devx import _debug
-                # await debug.pause()
+                # await _debug.pause()
                 assert self._outcome_msg is outcome_msg
             else:
                 self._outcome_msg = outcome_msg
@@ -1601,12 +1474,6 @@ class Context:
                 ):
                     status = 'peer-cancelled'
 
-            case (
-                Unresolved,
-                trio.Cancelled(),  # any error-type
-            ) if self.canceller:
-                status = 'actor-cancelled'
-
             # (remote) error condition
             case (
                 Unresolved,
@@ -1720,7 +1587,7 @@ class Context:
                 raise err
 
         # TODO: maybe a flag to by-pass encode op if already done
-        # here in parent?
+        # here in caller?
         await self.chan.send(started_msg)
 
         # set msg-related internal runtime-state
@@ -1796,7 +1663,7 @@ class Context:
 
          XXX RULES XXX
         ------ - ------
-        - NEVER raise remote errors from this method; a calling runtime-task.
+        - NEVER raise remote errors from this method; a runtime task caller.
           An error "delivered" to a ctx should always be raised by
           the corresponding local task operating on the
           `Portal`/`Context` APIs.
@@ -1872,7 +1739,7 @@ class Context:
 
             else:
                 report = (
-                    'Queueing OVERRUN msg on parent task:\n\n'
+                    'Queueing OVERRUN msg on caller task:\n\n'
                     + report
                 )
                 log.debug(report)
@@ -2068,12 +1935,12 @@ async def open_context_from_portal(
     IPC protocol.
 
     The yielded `tuple` is a pair delivering a `tractor.Context`
-    and any first value "sent" by the "child" task via a call
+    and any first value "sent" by the "callee" task via a call
     to `Context.started(<value: Any>)`; this side of the
-    context does not unblock until the "child" task calls
+    context does not unblock until the "callee" task calls
     `.started()` in similar style to `trio.Nursery.start()`.
-    When the "child" (side that is "called"/started by a call
+    When the "callee" (side that is "called"/started by a call
-    to *this* method) returns, the parent side (this) unblocks
+    to *this* method) returns, the caller side (this) unblocks
     and any final value delivered from the other end can be
     retrieved using the `Contex.wait_for_result()` api.
 
@@ -2086,7 +1953,7 @@ async def open_context_from_portal(
     __tracebackhide__: bool = hide_tb
 
     # denote this frame as a "runtime frame" for stack
-    # introspection where we report the parent code in logging
+    # introspection where we report the caller code in logging
     # and error message content.
     # NOTE: 2 bc of the wrapping `@acm`
     __runtimeframe__: int = 2  # noqa
@@ -2121,9 +1988,6 @@ async def open_context_from_portal(
             f'|_{portal.actor}\n'
         )
 
-    # ?TODO? could we move this to inside the `tn` block?
-    # -> would allow doing `ctx.parent_task = tn.parent_task` ?
-    # -> would allow a `if not ._scope: => raise RTE` ?
     ctx: Context = await portal.actor.start_remote_task(
         portal.channel,
         nsf=nsf,
@@ -2148,12 +2012,13 @@ async def open_context_from_portal(
     # placeholder for any exception raised in the runtime
     # or by user tasks which cause this context's closure.
     scope_err: BaseException|None = None
-    ctxc_from_child: ContextCancelled|None = None
+    ctxc_from_callee: ContextCancelled|None = None
     try:
-        # from .devx import pause
         async with (
-            collapse_eg(),
+            trio.open_nursery(
-            trio.open_nursery() as tn,
+                strict_exception_groups=False,
+            ) as tn,
+
             msgops.maybe_limit_plds(
                 ctx=ctx,
                 spec=ctx_meta.get('pld_spec'),
@@ -2173,10 +2038,6 @@ async def open_context_from_portal(
             # the dialog, the `Error` msg should be raised from the `msg`
             # handling block below.
             try:
-                log.runtime(
-                    f'IPC ctx parent waiting on Started msg..\n'
-                    f'ctx.cid: {ctx.cid!r}\n'
-                )
                 started_msg, first = await ctx._pld_rx.recv_msg(
                     ipc=ctx,
                     expect_msg=Started,
@@ -2185,16 +2046,16 @@ async def open_context_from_portal(
                 )
             except trio.Cancelled as taskc:
                 ctx_cs: trio.CancelScope = ctx._scope
-                log.cancel(
-                    f'IPC ctx was cancelled during "child" task sync due to\n\n'
-                    f'.cid: {ctx.cid!r}\n'
-                    f'.maybe_error: {ctx.maybe_error!r}\n'
-                )
-                # await pause(shield=True)
-
                 if not ctx_cs.cancel_called:
                     raise
 
+                # from .devx import pause
+                # await pause(shield=True)
+
+                log.cancel(
+                    'IPC ctx was cancelled during "child" task sync due to\n\n'
+                    f'{ctx.maybe_error}\n'
+                )
                 # OW if the ctx's scope was cancelled manually,
                 # likely the `Context` was cancelled via a call to
                 # `._maybe_cancel_and_set_remote_error()` so ensure
@@ -2232,7 +2093,7 @@ async def open_context_from_portal(
             # that we can re-use it around the `yield` ^ here
             # or vice versa?
             #
-            # maybe TODO NOTE: between the parent exiting and
+            # maybe TODO NOTE: between the caller exiting and
             # arriving here the far end may have sent a ctxc-msg or
             # other error, so the quetion is whether we should check
             # for it here immediately and maybe raise so as to engage
@@ -2298,16 +2159,16 @@ async def open_context_from_portal(
     #   request in which case we DO let the error bubble to the
     #   opener.
     #
-    # 2-THIS "parent" task somewhere invoked `Context.cancel()`
+    # 2-THIS "caller" task somewhere invoked `Context.cancel()`
-    #   and received a `ContextCanclled` from the "child"
+    #   and received a `ContextCanclled` from the "callee"
     #   task, in which case we mask the `ContextCancelled` from
-    #   bubbling to this "parent" (much like how `trio.Nursery`
+    #   bubbling to this "caller" (much like how `trio.Nursery`
     #   swallows any `trio.Cancelled` bubbled by a call to
     #   `Nursery.cancel_scope.cancel()`)
     except ContextCancelled as ctxc:
         scope_err = ctxc
         ctx._local_error: BaseException = scope_err
-        ctxc_from_child = ctxc
+        ctxc_from_callee = ctxc
 
         # XXX TODO XXX: FIX THIS debug_mode BUGGGG!!!
         # using this code and then resuming the REPL will
@@ -2317,8 +2178,8 @@ async def open_context_from_portal(
         #   documenting it as a definittive example of
         #   debugging the tractor-runtime itself using it's
         #   own `.devx.` tooling!
-        #
+        # 
-        # await debug.pause()
+        # await _debug.pause()
 
         # CASE 2: context was cancelled by local task calling
         # `.cancel()`, we don't raise and the exit block should
@@ -2344,11 +2205,11 @@ async def open_context_from_portal(
     # the above `._scope` can be cancelled due to:
     # 1. an explicit self cancel via `Context.cancel()` or
     #    `Actor.cancel()`,
-    # 2. any "child"-side remote error, possibly also a cancellation
+    # 2. any "callee"-side remote error, possibly also a cancellation
     #    request by some peer,
-    # 3. any "parent" (aka THIS scope's) local error raised in the above `yield`
+    # 3. any "caller" (aka THIS scope's) local error raised in the above `yield`
     except (
-        # CASE 3: standard local error in this parent/yieldee
+        # CASE 3: standard local error in this caller/yieldee
         Exception,
 
         # CASES 1 & 2: can manifest as a `ctx._scope_nursery`
@@ -2362,9 +2223,9 @@ async def open_context_from_portal(
         #   any `Context._maybe_raise_remote_err()` call.
         #
         # 2.-`BaseExceptionGroup[ContextCancelled | RemoteActorError]`
-        #    from any error delivered from the "child" side
+        #    from any error delivered from the "callee" side
         #    AND a group-exc is only raised if there was > 1
-        #    tasks started *here* in the "parent" / opener
+        #    tasks started *here* in the "caller" / opener
         #    block. If any one of those tasks calls
         #    `.wait_for_result()` or `MsgStream.receive()`
         #    `._maybe_raise_remote_err()` will be transitively
@@ -2377,37 +2238,34 @@ async def open_context_from_portal(
         trio.Cancelled,  # NOTE: NOT from inside the ctx._scope
         KeyboardInterrupt,
 
-    ) as rent_err:
+    ) as caller_err:
-        scope_err = rent_err
+        scope_err = caller_err
         ctx._local_error: BaseException = scope_err
 
         # XXX: ALWAYS request the context to CANCEL ON any ERROR.
         # NOTE: `Context.cancel()` is conversely NEVER CALLED in
         # the `ContextCancelled` "self cancellation absorbed" case
         # handled in the block above ^^^ !!
-        # await debug.pause()
+        # await _debug.pause()
         # log.cancel(
         match scope_err:
-            case trio.Cancelled():
+            case trio.Cancelled:
                 logmeth = log.cancel
-                cause: str = 'cancelled'
 
             # XXX explicitly report on any non-graceful-taskc cases
             case _:
-                cause: str = 'errored'
                 logmeth = log.exception
 
         logmeth(
-            f'ctx {ctx.side!r}-side {cause!r} with,\n'
+            f'ctx {ctx.side!r}-side exited with {ctx.repr_outcome()}\n'
-            f'{ctx.repr_outcome()!r}\n'
         )
 
         if debug_mode():
-            # async with debug.acquire_debug_lock(portal.actor.uid):
+            # async with _debug.acquire_debug_lock(portal.actor.uid):
             #     pass
             # TODO: factor ^ into below for non-root cases?
             #
-            from .devx.debug import maybe_wait_for_debugger
+            from .devx._debug import maybe_wait_for_debugger
             was_acquired: bool = await maybe_wait_for_debugger(
                 # header_msg=(
                 #     'Delaying `ctx.cancel()` until debug lock '
@@ -2420,11 +2278,10 @@ async def open_context_from_portal(
                     'Calling `ctx.cancel()`!\n'
                 )
 
-        # we don't need to cancel the child if it already
+        # we don't need to cancel the callee if it already
         # told us it's cancelled ;p
-        if ctxc_from_child is None:
+        if ctxc_from_callee is None:
             try:
-                # await pause(shield=True)
                 await ctx.cancel()
             except (
                 trio.BrokenResourceError,
@@ -2454,8 +2311,8 @@ async def open_context_from_portal(
             # via a call to
             # `Context._maybe_cancel_and_set_remote_error()`.
             # As per `Context._deliver_msg()`, that error IS
-            # ALWAYS SET any time "child" side fails and causes
+            # ALWAYS SET any time "callee" side fails and causes "caller
-            # "parent side" cancellation via a `ContextCancelled` here.
+            # side" cancellation via a `ContextCancelled` here.
             try:
                 result_or_err: Exception|Any = await ctx.wait_for_result()
             except BaseException as berr:
@@ -2471,8 +2328,8 @@ async def open_context_from_portal(
                 raise
 
             # yes this worx!
-            # from .devx import debug
+            # from .devx import _debug
-            # await debug.pause()
+            # await _debug.pause()
 
             # an exception type boxed in a `RemoteActorError`
             # is returned (meaning it was obvi not raised)
@@ -2491,7 +2348,7 @@ async def open_context_from_portal(
                     )
                 case (None, _):
                     log.runtime(
-                        'Context returned final result from child task:\n'
+                        'Context returned final result from callee task:\n'
                         f'<= peer: {uid}\n'
                         f'  |_ {nsf}()\n\n'
 
@@ -2507,7 +2364,7 @@ async def open_context_from_portal(
         # where the root is waiting on the lock to clear but the
         # child has already cleared it and clobbered IPC.
         if debug_mode():
-            from .devx.debug import maybe_wait_for_debugger
+            from .devx._debug import maybe_wait_for_debugger
             await maybe_wait_for_debugger()
 
         # though it should be impossible for any tasks
@@ -2581,14 +2438,12 @@ async def open_context_from_portal(
                 log.cancel(
                     f'Context cancelled by local {ctx.side!r}-side task\n'
                     f'c)>\n'
-                    f'  |_{ctx.parent_task}\n'
+                    f' |_{ctx._task}\n\n'
-                    f'   .cid={ctx.cid!r}\n'
+                    f'{repr(scope_err)}\n'
-                    f'\n'
-                    f'{scope_err!r}\n'
                 )
 
             # TODO: should we add a `._cancel_req_received`
-            # flag to determine if the child manually called
+            # flag to determine if the callee manually called
             # `ctx.cancel()`?
             # -[ ] going to need a cid check no?
 
@@ -2644,7 +2499,7 @@ def mk_context(
     recv_chan: trio.MemoryReceiveChannel
     send_chan, recv_chan = trio.open_memory_channel(msg_buffer_size)
 
-    # TODO: only scan parent-info if log level so high!
+    # TODO: only scan caller-info if log level so high!
     from .devx._frame_stack import find_caller_info
     caller_info: CallerInfo|None = find_caller_info()
 

tractor/_discovery.py

@@ -28,16 +28,8 @@ from typing import (
 from contextlib import asynccontextmanager as acm
 
 from tractor.log import get_logger
-from .trionics import (
+from .trionics import gather_contexts
-    gather_contexts,
+from ._ipc import _connect_chan, Channel
-    collapse_eg,
-)
-from .ipc import _connect_chan, Channel
-from ._addr import (
-    UnwrappedAddress,
-    Address,
-    wrap_address
-)
 from ._portal import (
     Portal,
     open_portal,
@@ -46,7 +38,6 @@ from ._portal import (
 from ._state import (
     current_actor,
     _runtime_vars,
-    _def_tpt_proto,
 )
 
 if TYPE_CHECKING:
@@ -58,7 +49,9 @@ log = get_logger(__name__)
 
 @acm
 async def get_registry(
-    addr: UnwrappedAddress|None = None,
+    host: str,
+    port: int,
+
 ) -> AsyncGenerator[
     Portal | LocalPortal | None,
     None,
@@ -76,20 +69,19 @@ async def get_registry(
         # (likely a re-entrant call from the arbiter actor)
         yield LocalPortal(
             actor,
-            Channel(transport=None)
+            Channel((host, port))
-            # ^XXX, we DO NOT actually provide nor connect an
-            # underlying transport since this is merely an API shim.
         )
     else:
         # TODO: try to look pre-existing connection from
-        # `Server._peers` and use it instead?
+        # `Actor._peers` and use it instead?
         async with (
-            _connect_chan(addr) as chan,
+            _connect_chan(host, port) as chan,
             open_portal(chan) as regstr_ptl,
         ):
             yield regstr_ptl
 
 
+
 @acm
 async def get_root(
     **kwargs,
@@ -97,10 +89,11 @@ async def get_root(
 
     # TODO: rename mailbox to `_root_maddr` when we finally
     # add and impl libp2p multi-addrs?
-    addr = _runtime_vars['_root_mailbox']
+    host, port = _runtime_vars['_root_mailbox']
+    assert host is not None
 
     async with (
-        _connect_chan(addr) as chan,
+        _connect_chan(host, port) as chan,
         open_portal(chan, **kwargs) as portal,
     ):
         yield portal
@@ -113,23 +106,17 @@ def get_peer_by_name(
 ) -> list[Channel]|None:  # at least 1
     '''
     Scan for an existing connection (set) to a named actor
-    and return any channels from `Server._peers: dict`.
+    and return any channels from `Actor._peers`.
 
     This is an optimization method over querying the registrar for
     the same info.
 
     '''
     actor: Actor = current_actor()
-    to_scan: dict[tuple, list[Channel]] = actor.ipc_server._peers.copy()
+    to_scan: dict[tuple, list[Channel]] = actor._peers.copy()
-
+    pchan: Channel|None = actor._parent_chan
-    # TODO: is this ever needed? creates a duplicate channel on actor._peers
+    if pchan:
-    # when multiple find_actor calls are made to same actor from a single ctx
+        to_scan[pchan.uid].append(pchan)
-    # which causes actor exit to hang waiting forever on
-    # `actor._no_more_peers.wait()` in `_runtime.async_main`
-
-    # pchan: Channel|None = actor._parent_chan
-    # if pchan and pchan.uid not in to_scan:
-    #     to_scan[pchan.uid].append(pchan)
 
     for aid, chans in to_scan.items():
         _, peer_name = aid
@@ -147,10 +134,10 @@ def get_peer_by_name(
 @acm
 async def query_actor(
     name: str,
-    regaddr: UnwrappedAddress|None = None,
+    regaddr: tuple[str, int]|None = None,
 
 ) -> AsyncGenerator[
-    UnwrappedAddress|None,
+    tuple[str, int]|None,
     None,
 ]:
     '''
@@ -176,31 +163,31 @@ async def query_actor(
         return
 
     reg_portal: Portal
-    regaddr: Address = wrap_address(regaddr) or actor.reg_addrs[0]
+    regaddr: tuple[str, int] = regaddr or actor.reg_addrs[0]
-    async with get_registry(regaddr) as reg_portal:
+    async with get_registry(*regaddr) as reg_portal:
         # TODO: return portals to all available actors - for now
         # just the last one that registered
-        addr: UnwrappedAddress = await reg_portal.run_from_ns(
+        sockaddr: tuple[str, int] = await reg_portal.run_from_ns(
             'self',
             'find_actor',
             name=name,
         )
-        yield addr
+        yield sockaddr
 
 
 @acm
 async def maybe_open_portal(
-    addr: UnwrappedAddress,
+    addr: tuple[str, int],
     name: str,
 ):
     async with query_actor(
         name=name,
         regaddr=addr,
-    ) as addr:
+    ) as sockaddr:
         pass
 
-    if addr:
+    if sockaddr:
-        async with _connect_chan(addr) as chan:
+        async with _connect_chan(*sockaddr) as chan:
             async with open_portal(chan) as portal:
                 yield portal
     else:
@@ -210,8 +197,7 @@ async def maybe_open_portal(
 @acm
 async def find_actor(
     name: str,
-    registry_addrs: list[UnwrappedAddress]|None = None,
+    registry_addrs: list[tuple[str, int]]|None = None,
-    enable_transports: list[str] = [_def_tpt_proto],
 
     only_first: bool = True,
     raise_on_none: bool = False,
@@ -238,15 +224,15 @@ async def find_actor(
         # XXX NOTE: make sure to dynamically read the value on
         # every call since something may change it globally (eg.
         # like in our discovery test suite)!
-        from ._addr import default_lo_addrs
+        from . import _root
         registry_addrs = (
             _runtime_vars['_registry_addrs']
             or
-            default_lo_addrs(enable_transports)
+            _root._default_lo_addrs
         )
 
     maybe_portals: list[
-        AsyncContextManager[UnwrappedAddress]
+        AsyncContextManager[tuple[str, int]]
     ] = list(
         maybe_open_portal(
             addr=addr,
@@ -255,12 +241,9 @@ async def find_actor(
         for addr in registry_addrs
     )
     portals: list[Portal]
-    async with (
+    async with gather_contexts(
-        collapse_eg(),
+        mngrs=maybe_portals,
-        gather_contexts(
+    ) as portals:
-            mngrs=maybe_portals,
-        ) as portals,
-    ):
         # log.runtime(
         #     'Gathered portals:\n'
         #     f'{portals}'
@@ -291,7 +274,7 @@ async def find_actor(
 @acm
 async def wait_for_actor(
     name: str,
-    registry_addr: UnwrappedAddress | None = None,
+    registry_addr: tuple[str, int] | None = None,
 
 ) -> AsyncGenerator[Portal, None]:
     '''
@@ -308,7 +291,7 @@ async def wait_for_actor(
             yield peer_portal
             return
 
-    regaddr: UnwrappedAddress = (
+    regaddr: tuple[str, int] = (
         registry_addr
         or
         actor.reg_addrs[0]
@@ -316,8 +299,8 @@ async def wait_for_actor(
     # TODO: use `.trionics.gather_contexts()` like
     # above in `find_actor()` as well?
     reg_portal: Portal
-    async with get_registry(regaddr) as reg_portal:
+    async with get_registry(*regaddr) as reg_portal:
-        addrs = await reg_portal.run_from_ns(
+        sockaddrs = await reg_portal.run_from_ns(
             'self',
             'wait_for_actor',
             name=name,
@@ -325,8 +308,8 @@ async def wait_for_actor(
 
         # get latest registered addr by default?
         # TODO: offer multi-portal yields in multi-homed case?
-        addr: UnwrappedAddress = addrs[-1]
+        sockaddr: tuple[str, int] = sockaddrs[-1]
 
-        async with _connect_chan(addr) as chan:
+        async with _connect_chan(*sockaddr) as chan:
             async with open_portal(chan) as portal:
                 yield portal

tractor/_entry.py

@@ -21,7 +21,8 @@ Sub-process entry points.
 from __future__ import annotations
 from functools import partial
 import multiprocessing as mp
-# import os
+import os
+import textwrap
 from typing import (
     Any,
     TYPE_CHECKING,
@@ -34,13 +35,8 @@ from .log import (
     get_logger,
 )
 from . import _state
-from .devx import (
+from .devx import _debug
-    _frame_stack,
-    pformat,
-)
-# from .msg import pretty_struct
 from .to_asyncio import run_as_asyncio_guest
-from ._addr import UnwrappedAddress
 from ._runtime import (
     async_main,
     Actor,
@@ -56,10 +52,10 @@ log = get_logger(__name__)
 def _mp_main(
 
     actor: Actor,
-    accept_addrs: list[UnwrappedAddress],
+    accept_addrs: list[tuple[str, int]],
     forkserver_info: tuple[Any, Any, Any, Any, Any],
     start_method: SpawnMethodKey,
-    parent_addr: UnwrappedAddress | None = None,
+    parent_addr: tuple[str, int] | None = None,
     infect_asyncio: bool = False,
 
 ) -> None:
@@ -106,10 +102,111 @@ def _mp_main(
         )
 
 
+# TODO: move this func to some kinda `.devx._conc_lang.py` eventually
+# as we work out our multi-domain state-flow-syntax!
+def nest_from_op(
+    input_op: str,
+    #
+    # ?TODO? an idea for a syntax to the state of concurrent systems
+    # as a "3-domain" (execution, scope, storage) model and using
+    # a minimal ascii/utf-8 operator-set.
+    #
+    # try not to take any of this seriously yet XD
+    #
+    # > is a "play operator" indicating (CPU bound)
+    #   exec/work/ops required at the "lowest level computing"
+    #
+    # execution primititves (tasks, threads, actors..) denote their
+    # lifetime with '(' and ')' since parentheses normally are used
+    # in many langs to denote function calls.
+    #
+    # starting = (
+    # >(  opening/starting; beginning of the thread-of-exec (toe?)
+    # (>  opened/started,  (finished spawning toe)
+    # |_<Task: blah blah..>  repr of toe, in py these look like <objs>
+    #
+    # >) closing/exiting/stopping,
+    # )> closed/exited/stopped,
+    # |_<Task: blah blah..>
+    #   [OR <), )< ?? ]
+    #
+    # ending = )
+    # >c) cancelling to close/exit
+    # c)> cancelled (caused close), OR?
+    #  |_<Actor: ..>
+    #   OR maybe "<c)" which better indicates the cancel being
+    #   "delivered/returned" / returned" to LHS?
+    #
+    # >x)  erroring to eventuall exit
+    # x)>  errored and terminated
+    #  |_<Actor: ...>
+    #
+    # scopes: supers/nurseries, IPC-ctxs, sessions, perms, etc.
+    # >{  opening
+    # {>  opened
+    # }>  closed
+    # >}  closing
+    #
+    # storage: like queues, shm-buffers, files, etc..
+    # >[  opening
+    # [>  opened
+    #  |_<FileObj: ..>
+    #
+    # >]  closing
+    # ]>  closed
+
+    # IPC ops: channels, transports, msging
+    # =>  req msg
+    # <=  resp msg
+    # <=> 2-way streaming (of msgs)
+    # <-  recv 1 msg
+    # ->  send 1 msg
+    #
+    # TODO: still not sure on R/L-HS approach..?
+    # =>(  send-req to exec start (task, actor, thread..)
+    # (<=  recv-req to ^
+    #
+    # (<=  recv-req ^
+    # <=(  recv-resp opened remote exec primitive
+    # <=)  recv-resp closed
+    #
+    # )<=c req to stop due to cancel
+    # c=>) req to stop due to cancel
+    #
+    # =>{  recv-req to open
+    # <={  send-status that it closed
+
+    tree_str: str,
+
+    # NOTE: so move back-from-the-left of the `input_op` by
+    # this amount.
+    back_from_op: int = 0,
+) -> str:
+    '''
+    Depth-increment the input (presumably hierarchy/supervision)
+    input "tree string" below the provided `input_op` execution
+    operator, so injecting a `"\n|_{input_op}\n"`and indenting the
+    `tree_str` to nest content aligned with the ops last char.
+
+    '''
+    return (
+        f'{input_op}\n'
+        +
+        textwrap.indent(
+            tree_str,
+            prefix=(
+                len(input_op)
+                -
+                (back_from_op + 1)
+            ) * ' ',
+        )
+    )
+
+
 def _trio_main(
     actor: Actor,
     *,
-    parent_addr: UnwrappedAddress|None = None,
+    parent_addr: tuple[str, int] | None = None,
     infect_asyncio: bool = False,
 
 ) -> None:
@@ -117,7 +214,7 @@ def _trio_main(
     Entry point for a `trio_run_in_process` subactor.
 
     '''
-    _frame_stack.hide_runtime_frames()
+    _debug.hide_runtime_frames()
 
     _state._current_actor = actor
     trio_main = partial(
@@ -128,23 +225,30 @@ 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(
-            f'Starting `trio` subactor from parent @ '
+            'Starting new `trio` subactor:\n'
-            f'{parent_addr}\n'
             +
-            pformat.nest_from_op(
+            nest_from_op(
                 input_op='>(',  # see syntax ideas above
-                text=f'{actor}',
+                tree_str=actor_info,
+                back_from_op=2,  # since "complete"
             )
         )
     logmeth = log.info
     exit_status: str = (
         'Subactor exited\n'
         +
-        pformat.nest_from_op(
+        nest_from_op(
             input_op=')>',  # like a "closed-to-play"-icon from super perspective
-            text=f'{actor}',
+            tree_str=actor_info,
-            nest_indent=1,
+            back_from_op=1,
         )
     )
     try:
@@ -159,9 +263,9 @@ def _trio_main(
         exit_status: str = (
             'Actor received KBI (aka an OS-cancel)\n'
             +
-            pformat.nest_from_op(
+            nest_from_op(
                 input_op='c)>',  # closed due to cancel (see above)
-                text=f'{actor}',
+                tree_str=actor_info,
             )
         )
     except BaseException as err:
@@ -169,9 +273,9 @@ def _trio_main(
         exit_status: str = (
             'Main actor task exited due to crash?\n'
             +
-            pformat.nest_from_op(
+            nest_from_op(
                 input_op='x)>',  # closed by error
-                text=f'{actor}',
+                tree_str=actor_info,
             )
         )
         # NOTE since we raise a tb will already be shown on the

tractor/_exceptions.py

@@ -23,6 +23,7 @@ import builtins
 import importlib
 from pprint import pformat
 from pdb import bdb
+import sys
 from types import (
     TracebackType,
 )
@@ -64,29 +65,15 @@ if TYPE_CHECKING:
     from ._context import Context
     from .log import StackLevelAdapter
     from ._stream import MsgStream
-    from .ipc import Channel
+    from ._ipc import Channel
 
 log = get_logger('tractor')
 
 _this_mod = importlib.import_module(__name__)
 
 
-class RuntimeFailure(RuntimeError):
+class ActorFailure(Exception):
-    '''
+    "General actor failure"
-    General `Actor`-runtime failure due to,
-
-    - a bad runtime-env,
-    - falied spawning (bad input to process),
-    -   API usage.
-
-    '''
-
-
-class ActorFailure(RuntimeFailure):
-    '''
-    `Actor` failed to boot before/after spawn
-
-    '''
 
 
 class InternalError(RuntimeError):
@@ -139,12 +126,6 @@ class TrioTaskExited(Exception):
     '''
 
 
-class DebugRequestError(RuntimeError):
-    '''
-    Failed to request stdio lock from root actor!
-
-    '''
-
 # NOTE: more or less should be close to these:
 # 'boxed_type',
 # 'src_type',
@@ -210,8 +191,6 @@ def get_err_type(type_name: str) -> BaseException|None:
         ):
             return type_ref
 
-    return None
-
 
 def pack_from_raise(
     local_err: (
@@ -542,6 +521,7 @@ class RemoteActorError(Exception):
             if val:
                 _repr += f'{key}={val_str}{end_char}'
 
+
         return _repr
 
     def reprol(self) -> str:
@@ -620,9 +600,56 @@ class RemoteActorError(Exception):
             the type name is already implicitly shown by python).
 
         '''
+        header: str = ''
+        body: str = ''
+        message: str = ''
+
+        # XXX when the currently raised exception is this instance,
+        # we do not ever use the "type header" style repr.
+        is_being_raised: bool = False
+        if (
+            (exc := sys.exception())
+            and
+            exc is self
+        ):
+            is_being_raised: bool = True
+
+        with_type_header: bool = (
+            with_type_header
+            and
+            not is_being_raised
+        )
+
+        # <RemoteActorError( .. )> style
+        if with_type_header:
+            header: str = f'<{type(self).__name__}('
+
+        if message := self._message:
+
+            # split off the first line so, if needed, it isn't
+            # indented the same like the "boxed content" which
+            # since there is no `.tb_str` is just the `.message`.
+            lines: list[str] = message.splitlines()
+            first: str = lines[0]
+            message: str = message.removeprefix(first)
+
+            # with a type-style header we,
+            # - have no special message "first line" extraction/handling
+            # - place the message a space in from the header:
+            #  `MsgTypeError( <message> ..`
+            #                 ^-here
+            # - indent the `.message` inside the type body.
+            if with_type_header:
+                first = f' {first} )>'
+
+            message: str = textwrap.indent(
+                message,
+                prefix=' '*2,
+            )
+            message: str = first + message
+
         # IFF there is an embedded traceback-str we always
         # draw the ascii-box around it.
-        body: str = ''
         if tb_str := self.tb_str:
             fields: str = self._mk_fields_str(
                 _body_fields
@@ -643,15 +670,21 @@ class RemoteActorError(Exception):
                 boxer_header=self.relay_uid,
             )
 
-        # !TODO, it'd be nice to import these top level without
+        tail = ''
-        # cycles!
+        if (
-        from tractor.devx.pformat import (
+            with_type_header
-            pformat_exc,
+            and not message
-        )
+        ):
-        return pformat_exc(
+            tail: str = '>'
-            exc=self,
+
-            with_type_header=with_type_header,
+        return (
-            body=body,
+            header
+            +
+            message
+            +
+            f'{body}'
+            +
+            tail
         )
 
     __repr__ = pformat
@@ -929,7 +962,7 @@ class StreamOverrun(
     '''
 
 
-class TransportClosed(Exception):
+class TransportClosed(trio.BrokenResourceError):
     '''
     IPC transport (protocol) connection was closed or broke and
     indicates that the wrapping communication `Channel` can no longer
@@ -940,39 +973,24 @@ class TransportClosed(Exception):
         self,
         message: str,
         loglevel: str = 'transport',
-        src_exc: Exception|None = None,
+        cause: BaseException|None = None,
         raise_on_report: bool = False,
 
     ) -> None:
         self.message: str = message
-        self._loglevel: str = loglevel
+        self._loglevel = loglevel
         super().__init__(message)
 
-        self._src_exc = src_exc
+        if cause is not None:
-        # set the cause manually if not already set by python
+            self.__cause__ = cause
-        if (
-            src_exc is not None
-            and
-            not self.__cause__
-        ):
-            self.__cause__ = src_exc
 
         # flag to toggle whether the msg loop should raise
         # the exc in its `TransportClosed` handler block.
         self._raise_on_report = raise_on_report
 
-    @property
-    def src_exc(self) -> Exception:
-        return (
-            self.__cause__
-            or
-            self._src_exc
-        )
-
     def report_n_maybe_raise(
         self,
         message: str|None = None,
-        hide_tb: bool = True,
 
     ) -> None:
         '''
@@ -980,10 +998,9 @@ class TransportClosed(Exception):
         for this error.
 
         '''
-        __tracebackhide__: bool = hide_tb
         message: str = message or self.message
         # when a cause is set, slap it onto the log emission.
-        if cause := self.src_exc:
+        if cause := self.__cause__:
             cause_tb_str: str = ''.join(
                 traceback.format_tb(cause.__traceback__)
             )
@@ -992,86 +1009,13 @@ class TransportClosed(Exception):
                 f'    {cause}\n'  # exc repr
             )
 
-        getattr(
+        getattr(log, self._loglevel)(message)
-            log,
-            self._loglevel
-        )(message)
 
         # some errors we want to blow up from
         # inside the RPC msg loop
         if self._raise_on_report:
             raise self from cause
 
-    @classmethod
-    def repr_src_exc(
-        self,
-        src_exc: Exception|None = None,
-    ) -> str:
-
-        if src_exc is None:
-            return '<unknown>'
-
-        src_msg: tuple[str] = src_exc.args
-        src_exc_repr: str = (
-            f'{type(src_exc).__name__}[ {src_msg} ]'
-        )
-        return src_exc_repr
-
-    def pformat(self) -> str:
-        from tractor.devx.pformat import (
-            pformat_exc,
-        )
-        return pformat_exc(
-            exc=self,
-        )
-
-    # delegate to `str`-ified pformat
-    __repr__ = pformat
-
-    @classmethod
-    def from_src_exc(
-        cls,
-        src_exc: (
-            Exception|
-            trio.ClosedResource|
-            trio.BrokenResourceError
-        ),
-        message: str,
-        body: str = '',
-        **init_kws,
-    ) -> TransportClosed:
-        '''
-        Convenience constructor for creation from an underlying
-        `trio`-sourced async-resource/chan/stream error.
-
-        Embeds the original `src_exc`'s repr within the
-        `Exception.args` via a first-line-in-`.message`-put-in-header
-        pre-processing and allows inserting additional content beyond
-        the main message via a `body: str`.
-
-        '''
-        repr_src_exc: str = cls.repr_src_exc(
-            src_exc,
-        )
-        next_line: str = f'  src_exc: {repr_src_exc}\n'
-        if body:
-            body: str = textwrap.indent(
-                body,
-                prefix=' '*2,
-            )
-
-        return TransportClosed(
-            message=(
-                message
-                +
-                next_line
-                +
-                body
-            ),
-            src_exc=src_exc,
-            **init_kws,
-        )
-
 
 class NoResult(RuntimeError):
     "No final result is expected for this actor"
@@ -1246,6 +1190,55 @@ def unpack_error(
     return exc
 
 
+def is_multi_cancelled(
+    exc: BaseException|BaseExceptionGroup,
+
+    ignore_nested: set[BaseException] = set(),
+
+) -> bool|BaseExceptionGroup:
+    '''
+    Predicate to determine if an `BaseExceptionGroup` only contains
+    some (maybe nested) set of sub-grouped exceptions (like only
+    `trio.Cancelled`s which get swallowed silently by default) and is
+    thus the result of "gracefully cancelling" a collection of
+    sub-tasks (or other conc primitives) and receiving a "cancelled
+    ACK" from each after termination.
+
+    Docs:
+    ----
+    - https://docs.python.org/3/library/exceptions.html#exception-groups
+    - https://docs.python.org/3/library/exceptions.html#BaseExceptionGroup.subgroup
+
+    '''
+
+    if (
+        not ignore_nested
+        or
+        trio.Cancelled in ignore_nested
+        # XXX always count-in `trio`'s native signal
+    ):
+        ignore_nested.update({trio.Cancelled})
+
+    if isinstance(exc, BaseExceptionGroup):
+        matched_exc: BaseExceptionGroup|None = exc.subgroup(
+            tuple(ignore_nested),
+
+            # TODO, complain about why not allowed XD
+            # condition=tuple(ignore_nested),
+        )
+        if matched_exc is not None:
+            return matched_exc
+
+    # NOTE, IFF no excs types match (throughout the error-tree)
+    # -> return `False`, OW return the matched sub-eg.
+    #
+    # IOW, for the inverse of ^ for the purpose of
+    # maybe-enter-REPL--logic: "only debug when the err-tree contains
+    # at least one exc-type NOT in `ignore_nested`" ; i.e. the case where
+    # we fallthrough and return `False` here.
+    return False
+
+
 def _raise_from_unexpected_msg(
     ctx: Context,
     msg: MsgType,

tractor/_ipc.py

@@ -0,0 +1,820 @@
+# tractor: structured concurrent "actors".
+# Copyright 2018-eternity Tyler Goodlet.
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+"""
+Inter-process comms abstractions
+
+"""
+from __future__ import annotations
+from collections.abc import (
+    AsyncGenerator,
+    AsyncIterator,
+)
+from contextlib import (
+    asynccontextmanager as acm,
+    contextmanager as cm,
+)
+import platform
+from pprint import pformat
+import struct
+import typing
+from typing import (
+    Any,
+    Callable,
+    runtime_checkable,
+    Protocol,
+    Type,
+    TypeVar,
+)
+
+import msgspec
+from tricycle import BufferedReceiveStream
+import trio
+
+from tractor.log import get_logger
+from tractor._exceptions import (
+    MsgTypeError,
+    pack_from_raise,
+    TransportClosed,
+    _mk_send_mte,
+    _mk_recv_mte,
+)
+from tractor.msg import (
+    _ctxvar_MsgCodec,
+    # _codec,  XXX see `self._codec` sanity/debug checks
+    MsgCodec,
+    types as msgtypes,
+    pretty_struct,
+)
+
+log = get_logger(__name__)
+
+_is_windows = platform.system() == 'Windows'
+
+
+def get_stream_addrs(
+    stream: trio.SocketStream
+) -> tuple[
+    tuple[str, int],  # local
+    tuple[str, int],  # remote
+]:
+    '''
+    Return the `trio` streaming transport prot's socket-addrs for
+    both the local and remote sides as a pair.
+
+    '''
+    # rn, should both be IP sockets
+    lsockname = stream.socket.getsockname()
+    rsockname = stream.socket.getpeername()
+    return (
+        tuple(lsockname[:2]),
+        tuple(rsockname[:2]),
+    )
+
+
+# from tractor.msg.types import MsgType
+# ?TODO? this should be our `Union[*msgtypes.__spec__]` alias now right..?
+# => BLEH, except can't bc prots must inherit typevar or param-spec
+#   vars..
+MsgType = TypeVar('MsgType')
+
+
+# TODO: break up this mod into a subpkg so we can start adding new
+# backends and move this type stuff into a dedicated file.. Bo
+#
+@runtime_checkable
+class MsgTransport(Protocol[MsgType]):
+#
+# ^-TODO-^ consider using a generic def and indexing with our
+# eventual msg definition/types?
+# - https://docs.python.org/3/library/typing.html#typing.Protocol
+
+    stream: trio.SocketStream
+    drained: list[MsgType]
+
+    def __init__(self, stream: trio.SocketStream) -> None:
+        ...
+
+    # XXX: should this instead be called `.sendall()`?
+    async def send(self, msg: MsgType) -> None:
+        ...
+
+    async def recv(self) -> MsgType:
+        ...
+
+    def __aiter__(self) -> MsgType:
+        ...
+
+    def connected(self) -> bool:
+        ...
+
+    # defining this sync otherwise it causes a mypy error because it
+    # can't figure out it's a generator i guess?..?
+    def drain(self) -> AsyncIterator[dict]:
+        ...
+
+    @property
+    def laddr(self) -> tuple[str, int]:
+        ...
+
+    @property
+    def raddr(self) -> tuple[str, int]:
+        ...
+
+
+# TODO: typing oddity.. not sure why we have to inherit here, but it
+# seems to be an issue with `get_msg_transport()` returning
+# a `Type[Protocol]`; probably should make a `mypy` issue?
+class MsgpackTCPStream(MsgTransport):
+    '''
+    A ``trio.SocketStream`` delivering ``msgpack`` formatted data
+    using the ``msgspec`` codec lib.
+
+    '''
+    layer_key: int = 4
+    name_key: str = 'tcp'
+
+    # TODO: better naming for this?
+    # -[ ] check how libp2p does naming for such things?
+    codec_key: str = 'msgpack'
+
+    def __init__(
+        self,
+        stream: trio.SocketStream,
+        prefix_size: int = 4,
+
+        # XXX optionally provided codec pair for `msgspec`:
+        # https://jcristharif.com/msgspec/extending.html#mapping-to-from-native-types
+        #
+        # TODO: define this as a `Codec` struct which can be
+        # overriden dynamically by the application/runtime?
+        codec: tuple[
+            Callable[[Any], Any]|None,  # coder
+            Callable[[type, Any], Any]|None,  # decoder
+        ]|None = None,
+
+    ) -> None:
+
+        self.stream = stream
+        assert self.stream.socket
+
+        # should both be IP sockets
+        self._laddr, self._raddr = get_stream_addrs(stream)
+
+        # create read loop instance
+        self._aiter_pkts = self._iter_packets()
+        self._send_lock = trio.StrictFIFOLock()
+
+        # public i guess?
+        self.drained: list[dict] = []
+
+        self.recv_stream = BufferedReceiveStream(
+            transport_stream=stream
+        )
+        self.prefix_size = prefix_size
+
+        # allow for custom IPC msg interchange format
+        # dynamic override Bo
+        self._task = trio.lowlevel.current_task()
+
+        # XXX for ctxvar debug only!
+        # self._codec: MsgCodec = (
+        #     codec
+        #     or
+        #     _codec._ctxvar_MsgCodec.get()
+        # )
+
+    async def _iter_packets(self) -> AsyncGenerator[dict, None]:
+        '''
+        Yield `bytes`-blob decoded packets from the underlying TCP
+        stream using the current task's `MsgCodec`.
+
+        This is a streaming routine implemented as an async generator
+        func (which was the original design, but could be changed?)
+        and is allocated by a `.__call__()` inside `.__init__()` where
+        it is assigned to the `._aiter_pkts` attr.
+
+        '''
+        decodes_failed: int = 0
+
+        while True:
+            try:
+                header: bytes = await self.recv_stream.receive_exactly(4)
+            except (
+                ValueError,
+                ConnectionResetError,
+
+                # not sure entirely why we need this but without it we
+                # seem to be getting racy failures here on
+                # arbiter/registry name subs..
+                trio.BrokenResourceError,
+
+            ) as trans_err:
+
+                loglevel = 'transport'
+                match trans_err:
+                    # case (
+                    #     ConnectionResetError()
+                    # ):
+                    #     loglevel = 'transport'
+
+                    # peer actor (graceful??) TCP EOF but `tricycle`
+                    # seems to raise a 0-bytes-read?
+                    case ValueError() if (
+                        'unclean EOF' in trans_err.args[0]
+                    ):
+                        pass
+
+                    # peer actor (task) prolly shutdown quickly due
+                    # to cancellation
+                    case trio.BrokenResourceError() if (
+                        'Connection reset by peer' in trans_err.args[0]
+                    ):
+                        pass
+
+                    # unless the disconnect condition falls under "a
+                    # normal operation breakage" we usualy console warn
+                    # about it.
+                    case _:
+                        loglevel: str = 'warning'
+
+
+                raise TransportClosed(
+                    message=(
+                        f'IPC transport already closed by peer\n'
+                        f'x]> {type(trans_err)}\n'
+                        f'  |_{self}\n'
+                    ),
+                    loglevel=loglevel,
+                ) from trans_err
+
+            # XXX definitely can happen if transport is closed
+            # manually by another `trio.lowlevel.Task` in the
+            # same actor; we use this in some simulated fault
+            # testing for ex, but generally should never happen
+            # under normal operation!
+            #
+            # NOTE: as such we always re-raise this error from the
+            #       RPC msg loop!
+            except trio.ClosedResourceError as closure_err:
+                raise TransportClosed(
+                    message=(
+                        f'IPC transport already manually closed locally?\n'
+                        f'x]> {type(closure_err)} \n'
+                        f'  |_{self}\n'
+                    ),
+                    loglevel='error',
+                    raise_on_report=(
+                        closure_err.args[0] == 'another task closed this fd'
+                        or
+                        closure_err.args[0] in ['another task closed this fd']
+                    ),
+                ) from closure_err
+
+            # graceful TCP EOF disconnect
+            if header == b'':
+                raise TransportClosed(
+                    message=(
+                        f'IPC transport already gracefully closed\n'
+                        f']>\n'
+                        f' |_{self}\n'
+                    ),
+                    loglevel='transport',
+                    # cause=???  # handy or no?
+                )
+
+            size: int
+            size, = struct.unpack("<I", header)
+
+            log.transport(f'received header {size}')  # type: ignore
+            msg_bytes: bytes = await self.recv_stream.receive_exactly(size)
+
+            log.transport(f"received {msg_bytes}")  # type: ignore
+            try:
+                # NOTE: lookup the `trio.Task.context`'s var for
+                # the current `MsgCodec`.
+                codec: MsgCodec = _ctxvar_MsgCodec.get()
+
+                # XXX for ctxvar debug only!
+                # if self._codec.pld_spec != codec.pld_spec:
+                #     assert (
+                #         task := trio.lowlevel.current_task()
+                #     ) is not self._task
+                #     self._task = task
+                #     self._codec = codec
+                #     log.runtime(
+                #         f'Using new codec in {self}.recv()\n'
+                #         f'codec: {self._codec}\n\n'
+                #         f'msg_bytes: {msg_bytes}\n'
+                #     )
+                yield codec.decode(msg_bytes)
+
+            # XXX NOTE: since the below error derives from
+            # `DecodeError` we need to catch is specially
+            # and always raise such that spec violations
+            # are never allowed to be caught silently!
+            except msgspec.ValidationError as verr:
+                msgtyperr: MsgTypeError = _mk_recv_mte(
+                    msg=msg_bytes,
+                    codec=codec,
+                    src_validation_error=verr,
+                )
+                # XXX deliver up to `Channel.recv()` where
+                # a re-raise and `Error`-pack can inject the far
+                # end actor `.uid`.
+                yield msgtyperr
+
+            except (
+                msgspec.DecodeError,
+                UnicodeDecodeError,
+            ):
+                if decodes_failed < 4:
+                    # ignore decoding errors for now and assume they have to
+                    # do with a channel drop - hope that receiving from the
+                    # channel will raise an expected error and bubble up.
+                    try:
+                        msg_str: str|bytes = msg_bytes.decode()
+                    except UnicodeDecodeError:
+                        msg_str = msg_bytes
+
+                    log.exception(
+                        'Failed to decode msg?\n'
+                        f'{codec}\n\n'
+                        'Rxed bytes from wire:\n\n'
+                        f'{msg_str!r}\n'
+                    )
+                    decodes_failed += 1
+                else:
+                    raise
+
+    async def send(
+        self,
+        msg: msgtypes.MsgType,
+
+        strict_types: bool = True,
+        hide_tb: bool = False,
+
+    ) -> None:
+        '''
+        Send a msgpack encoded py-object-blob-as-msg over TCP.
+
+        If `strict_types == True` then a `MsgTypeError` will be raised on any
+        invalid msg type
+
+        '''
+        __tracebackhide__: bool = hide_tb
+
+        # XXX see `trio._sync.AsyncContextManagerMixin` for details
+        # on the `.acquire()`/`.release()` sequencing..
+        async with self._send_lock:
+
+            # NOTE: lookup the `trio.Task.context`'s var for
+            # the current `MsgCodec`.
+            codec: MsgCodec = _ctxvar_MsgCodec.get()
+
+            # XXX for ctxvar debug only!
+            # if self._codec.pld_spec != codec.pld_spec:
+            #     self._codec = codec
+            #     log.runtime(
+            #         f'Using new codec in {self}.send()\n'
+            #         f'codec: {self._codec}\n\n'
+            #         f'msg: {msg}\n'
+            #     )
+
+            if type(msg) not in msgtypes.__msg_types__:
+                if strict_types:
+                    raise _mk_send_mte(
+                        msg,
+                        codec=codec,
+                    )
+                else:
+                    log.warning(
+                        'Sending non-`Msg`-spec msg?\n\n'
+                        f'{msg}\n'
+                    )
+
+            try:
+                bytes_data: bytes = codec.encode(msg)
+            except TypeError as _err:
+                typerr = _err
+                msgtyperr: MsgTypeError = _mk_send_mte(
+                    msg,
+                    codec=codec,
+                    message=(
+                        f'IPC-msg-spec violation in\n\n'
+                        f'{pretty_struct.Struct.pformat(msg)}'
+                    ),
+                    src_type_error=typerr,
+                )
+                raise msgtyperr from typerr
+
+            # supposedly the fastest says,
+            # https://stackoverflow.com/a/54027962
+            size: bytes = struct.pack("<I", len(bytes_data))
+            return await self.stream.send_all(size + bytes_data)
+
+        # ?TODO? does it help ever to dynamically show this
+        # frame?
+        # try:
+        #     <the-above_code>
+        # except BaseException as _err:
+        #     err = _err
+        #     if not isinstance(err, MsgTypeError):
+        #         __tracebackhide__: bool = False
+        #     raise
+
+    @property
+    def laddr(self) -> tuple[str, int]:
+        return self._laddr
+
+    @property
+    def raddr(self) -> tuple[str, int]:
+        return self._raddr
+
+    async def recv(self) -> Any:
+        return await self._aiter_pkts.asend(None)
+
+    async def drain(self) -> AsyncIterator[dict]:
+        '''
+        Drain the stream's remaining messages sent from
+        the far end until the connection is closed by
+        the peer.
+
+        '''
+        try:
+            async for msg in self._iter_packets():
+                self.drained.append(msg)
+        except TransportClosed:
+            for msg in self.drained:
+                yield msg
+
+    def __aiter__(self):
+        return self._aiter_pkts
+
+    def connected(self) -> bool:
+        return self.stream.socket.fileno() != -1
+
+
+def get_msg_transport(
+
+    key: tuple[str, str],
+
+) -> Type[MsgTransport]:
+
+    return {
+        ('msgpack', 'tcp'): MsgpackTCPStream,
+    }[key]
+
+
+class Channel:
+    '''
+    An inter-process channel for communication between (remote) actors.
+
+    Wraps a ``MsgStream``: transport + encoding IPC connection.
+
+    Currently we only support ``trio.SocketStream`` for transport
+    (aka TCP) and the ``msgpack`` interchange format via the ``msgspec``
+    codec libary.
+
+    '''
+    def __init__(
+
+        self,
+        destaddr: tuple[str, int]|None,
+
+        msg_transport_type_key: tuple[str, str] = ('msgpack', 'tcp'),
+
+        # TODO: optional reconnection support?
+        # auto_reconnect: bool = False,
+        # on_reconnect: typing.Callable[..., typing.Awaitable] = None,
+
+    ) -> None:
+
+        # self._recon_seq = on_reconnect
+        # self._autorecon = auto_reconnect
+
+        self._destaddr = destaddr
+        self._transport_key = msg_transport_type_key
+
+        # Either created in ``.connect()`` or passed in by
+        # user in ``.from_stream()``.
+        self._stream: trio.SocketStream|None = None
+        self._transport: MsgTransport|None = None
+
+        # set after handshake - always uid of far end
+        self.uid: tuple[str, str]|None = None
+
+        self._aiter_msgs = self._iter_msgs()
+        self._exc: Exception|None = None  # set if far end actor errors
+        self._closed: bool = False
+
+        # flag set by ``Portal.cancel_actor()`` indicating remote
+        # (possibly peer) cancellation of the far end actor
+        # runtime.
+        self._cancel_called: bool = False
+
+    @property
+    def msgstream(self) -> MsgTransport:
+        log.info(
+            '`Channel.msgstream` is an old name, use `._transport`'
+        )
+        return self._transport
+
+    @property
+    def transport(self) -> MsgTransport:
+        return self._transport
+
+    @classmethod
+    def from_stream(
+        cls,
+        stream: trio.SocketStream,
+        **kwargs,
+
+    ) -> Channel:
+
+        src, dst = get_stream_addrs(stream)
+        chan = Channel(
+            destaddr=dst,
+            **kwargs,
+        )
+
+        # set immediately here from provided instance
+        chan._stream: trio.SocketStream = stream
+        chan.set_msg_transport(stream)
+        return chan
+
+    def set_msg_transport(
+        self,
+        stream: trio.SocketStream,
+        type_key: tuple[str, str]|None = None,
+
+        # XXX optionally provided codec pair for `msgspec`:
+        # https://jcristharif.com/msgspec/extending.html#mapping-to-from-native-types
+        codec: MsgCodec|None = None,
+
+    ) -> MsgTransport:
+        type_key = (
+            type_key
+            or
+            self._transport_key
+        )
+        # get transport type, then
+        self._transport = get_msg_transport(
+            type_key
+        # instantiate an instance of the msg-transport
+        )(
+            stream,
+            codec=codec,
+        )
+        return self._transport
+
+    @cm
+    def apply_codec(
+        self,
+        codec: MsgCodec,
+
+    ) -> None:
+        '''
+        Temporarily override the underlying IPC msg codec for
+        dynamic enforcement of messaging schema.
+
+        '''
+        orig: MsgCodec = self._transport.codec
+        try:
+            self._transport.codec = codec
+            yield
+        finally:
+            self._transport.codec = orig
+
+    # TODO: do a .src/.dst: str for maddrs?
+    def __repr__(self) -> str:
+        if not self._transport:
+            return '<Channel with inactive transport?>'
+
+        return repr(
+            self._transport.stream.socket._sock
+        ).replace(  # type: ignore
+            "socket.socket",
+            "Channel",
+        )
+
+    @property
+    def laddr(self) -> tuple[str, int]|None:
+        return self._transport.laddr if self._transport else None
+
+    @property
+    def raddr(self) -> tuple[str, int]|None:
+        return self._transport.raddr if self._transport else None
+
+    async def connect(
+        self,
+        destaddr: tuple[Any, ...] | None = None,
+        **kwargs
+
+    ) -> MsgTransport:
+
+        if self.connected():
+            raise RuntimeError("channel is already connected?")
+
+        destaddr = destaddr or self._destaddr
+        assert isinstance(destaddr, tuple)
+
+        stream = await trio.open_tcp_stream(
+            *destaddr,
+            **kwargs
+        )
+        transport = self.set_msg_transport(stream)
+
+        log.transport(
+            f'Opened channel[{type(transport)}]: {self.laddr} -> {self.raddr}'
+        )
+        return transport
+
+    # TODO: something like,
+    # `pdbp.hideframe_on(errors=[MsgTypeError])`
+    # instead of the `try/except` hack we have rn..
+    # seems like a pretty useful thing to have in general
+    # along with being able to filter certain stack frame(s / sets)
+    # possibly based on the current log-level?
+    async def send(
+        self,
+        payload: Any,
+
+        hide_tb: bool = False,
+
+    ) -> None:
+        '''
+        Send a coded msg-blob over the transport.
+
+        '''
+        __tracebackhide__: bool = hide_tb
+        try:
+            log.transport(
+                '=> send IPC msg:\n\n'
+                f'{pformat(payload)}\n'
+            )
+            # assert self._transport  # but why typing?
+            await self._transport.send(
+                payload,
+                hide_tb=hide_tb,
+            )
+        except BaseException as _err:
+            err = _err  # bind for introspection
+            if not isinstance(_err, MsgTypeError):
+                # assert err
+                __tracebackhide__: bool = False
+            else:
+                assert err.cid
+
+            raise
+
+    async def recv(self) -> Any:
+        assert self._transport
+        return await self._transport.recv()
+
+        # TODO: auto-reconnect features like 0mq/nanomsg?
+        # -[ ] implement it manually with nods to SC prot
+        #      possibly on multiple transport backends?
+        #  -> seems like that might be re-inventing scalability
+        #     prots tho no?
+        # try:
+        #     return await self._transport.recv()
+        # except trio.BrokenResourceError:
+        #     if self._autorecon:
+        #         await self._reconnect()
+        #         return await self.recv()
+        #     raise
+
+    async def aclose(self) -> None:
+
+        log.transport(
+            f'Closing channel to {self.uid} '
+            f'{self.laddr} -> {self.raddr}'
+        )
+        assert self._transport
+        await self._transport.stream.aclose()
+        self._closed = True
+
+    async def __aenter__(self):
+        await self.connect()
+        return self
+
+    async def __aexit__(self, *args):
+        await self.aclose(*args)
+
+    def __aiter__(self):
+        return self._aiter_msgs
+
+    # ?TODO? run any reconnection sequence?
+    # -[ ] prolly should be impl-ed as deco-API?
+    #
+    # async def _reconnect(self) -> None:
+    #     """Handle connection failures by polling until a reconnect can be
+    #     established.
+    #     """
+    #     down = False
+    #     while True:
+    #         try:
+    #             with trio.move_on_after(3) as cancel_scope:
+    #                 await self.connect()
+    #             cancelled = cancel_scope.cancelled_caught
+    #             if cancelled:
+    #                 log.transport(
+    #                     "Reconnect timed out after 3 seconds, retrying...")
+    #                 continue
+    #             else:
+    #                 log.transport("Stream connection re-established!")
+
+    #                 # on_recon = self._recon_seq
+    #                 # if on_recon:
+    #                 #     await on_recon(self)
+
+    #                 break
+    #         except (OSError, ConnectionRefusedError):
+    #             if not down:
+    #                 down = True
+    #                 log.transport(
+    #                     f"Connection to {self.raddr} went down, waiting"
+    #                     " for re-establishment")
+    #             await trio.sleep(1)
+
+    async def _iter_msgs(
+        self
+    ) -> AsyncGenerator[Any, None]:
+        '''
+        Yield `MsgType` IPC msgs decoded and deliverd from
+        an underlying `MsgTransport` protocol.
+
+        This is a streaming routine alo implemented as an async-gen
+        func (same a `MsgTransport._iter_pkts()`) gets allocated by
+        a `.__call__()` inside `.__init__()` where it is assigned to
+        the `._aiter_msgs` attr.
+
+        '''
+        assert self._transport
+        while True:
+            try:
+                async for msg in self._transport:
+                    match msg:
+                        # NOTE: if transport/interchange delivers
+                        # a type error, we pack it with the far
+                        # end peer `Actor.uid` and relay the
+                        # `Error`-msg upward to the `._rpc` stack
+                        # for normal RAE handling.
+                        case MsgTypeError():
+                            yield pack_from_raise(
+                                local_err=msg,
+                                cid=msg.cid,
+
+                                # XXX we pack it here bc lower
+                                # layers have no notion of an
+                                # actor-id ;)
+                                src_uid=self.uid,
+                            )
+                        case _:
+                            yield msg
+
+            except trio.BrokenResourceError:
+
+                # if not self._autorecon:
+                raise
+
+            await self.aclose()
+
+            # if self._autorecon:  # attempt reconnect
+            #     await self._reconnect()
+            #     continue
+
+    def connected(self) -> bool:
+        return self._transport.connected() if self._transport else False
+
+
+@acm
+async def _connect_chan(
+    host: str,
+    port: int
+
+) -> typing.AsyncGenerator[Channel, None]:
+    '''
+    Create and connect a channel with disconnect on context manager
+    teardown.
+
+    '''
+    chan = Channel((host, port))
+    await chan.connect()
+    yield chan
+    with trio.CancelScope(shield=True):
+        await chan.aclose()

tractor/_portal.py

@@ -39,14 +39,11 @@ import warnings
 
 import trio
 
-from .trionics import (
+from .trionics import maybe_open_nursery
-    maybe_open_nursery,
-    collapse_eg,
-)
 from ._state import (
     current_actor,
 )
-from .ipc import Channel
+from ._ipc import Channel
 from .log import get_logger
 from .msg import (
     # Error,
@@ -55,8 +52,8 @@ from .msg import (
     Return,
 )
 from ._exceptions import (
+    # unpack_error,
     NoResult,
-    TransportClosed,
 )
 from ._context import (
     Context,
@@ -110,18 +107,10 @@ class Portal:
         # point.
         self._expect_result_ctx: Context|None = None
         self._streams: set[MsgStream] = set()
-
-        # TODO, this should be PRIVATE (and never used publicly)! since it's just
-        # a cached ref to the local runtime instead of calling
-        # `current_actor()` everywhere.. XD
         self.actor: Actor = current_actor()
 
     @property
     def chan(self) -> Channel:
-        '''
-        Ref to this ctx's underlying `tractor.ipc.Channel`.
-
-        '''
         return self._chan
 
     @property
@@ -181,17 +170,10 @@ 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 to peer {peer_id} will not deliver a final result?\n'
+                f"Portal for {self.channel.uid} not expecting a final"
-                f'\n'
+                " result?\nresult() should only be called if subactor"
-                f'Context.result() can only be called by the parent of '
+                " was spawned with `ActorNursery.run_in_actor()`")
-                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
@@ -224,7 +206,6 @@ 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(
@@ -236,10 +217,8 @@ class Portal:
         # terminate all locally running async generator
         # IPC calls
         if self._streams:
-            peer_id: str = f'{self.channel.aid.reprol()!r}'
+            log.cancel(
-            report: str = (
+                f"Cancelling all streams with {self.channel.uid}")
-                f'Cancelling all msg-streams with {peer_id}\n'
-            )
             for stream in self._streams.copy():
                 try:
                     await stream.aclose()
@@ -248,18 +227,10 @@ 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?)
-                    report += (
+                    log.debug(f"{stream} was already closed.")
-                        f'->) {stream!r} already closed\n'
-                    )
-
-            log.cancel(report)
 
     async def aclose(self):
-        log.debug(
+        log.debug(f"Closing {self}")
-            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
@@ -285,22 +256,23 @@ 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(
-                'Peer {peer_id} is already disconnected\n'
+                'This channel is already closed, skipping cancel request..'
-                '-> skipping cancel request..\n'
             )
             return False
 
+        reminfo: str = (
+            f'c)=> {self.channel.uid}\n'
+            f'  |_{chan}\n'
+        )
         log.cancel(
-            f'Sending actor-runtime-cancel-req to peer\n'
+            f'Requesting actor-runtime cancel for peer\n\n'
-            f'\n'
+            f'{reminfo}'
-            f'c)=> {peer_id}\n'
         )
 
         # XXX the one spot we set it?
-        chan._cancel_called: bool = True
+        self.channel._cancel_called: bool = True
         try:
             # send cancel cmd - might not get response
             # XXX: sure would be nice to make this work with
@@ -321,43 +293,22 @@ class Portal:
                 # may timeout and we never get an ack (obvi racy)
                 # but that doesn't mean it wasn't cancelled.
                 log.debug(
-                    f'May have failed to cancel peer?\n'
+                    'May have failed to cancel peer?\n'
-                    f'\n'
+                    f'{reminfo}'
-                    f'c)=?> {peer_id}\n'
                 )
 
             # if we get here some weird cancellation case happened
             return False
 
         except (
-            # XXX, should never really get raised unless we aren't
-            # wrapping them in the below type by mistake?
-            #
-            # Leaving the catch here for now until we're very sure
-            # all the cases (for various tpt protos) have indeed been
-            # re-wrapped ;p
             trio.ClosedResourceError,
             trio.BrokenResourceError,
-
+        ):
-            TransportClosed,
+            log.debug(
-        ) as tpt_err:
+                'IPC chan for actor already closed or broken?\n\n'
-            ipc_borked_report: str = (
+                f'{self.channel.uid}\n'
-                f'IPC for actor already closed/broken?\n\n'
+                f' |_{self.channel}\n'
-                f'\n'
-                f'c)=x> {peer_id}\n'
             )
-            match tpt_err:
-                case TransportClosed():
-                    log.debug(ipc_borked_report)
-                case _:
-                    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(ipc_borked_report)
-
             return False
 
     # TODO: do we still need this for low level `Actor`-runtime
@@ -513,13 +464,10 @@ class Portal:
                 with trio.CancelScope(shield=True):
                     await ctx.cancel()
 
-            except trio.ClosedResourceError as cre:
+            except trio.ClosedResourceError:
                 # if the far end terminates before we send a cancel the
                 # underlying transport-channel may already be closed.
-                log.cancel(
+                log.cancel(f'Context {ctx} was already closed?')
-                    f'Context.cancel() -> {cre!r}\n'
-                    f'cid: {ctx.cid!r} already closed?\n'
-                )
 
             # XXX: should this always be done?
             # await recv_chan.aclose()
@@ -556,12 +504,8 @@ class LocalPortal:
         return it's result.
 
         '''
-        obj = (
+        obj = self.actor if ns == 'self' else importlib.import_module(ns)
-            self.actor
+        func = getattr(obj, func_name)
-            if ns == 'self'
-            else importlib.import_module(ns)
-        )
-        func: Callable = getattr(obj, func_name)
         return await func(**kwargs)
 
 
@@ -586,30 +530,30 @@ async def open_portal(
     assert actor
     was_connected: bool = False
 
-    async with (
+    async with maybe_open_nursery(
-        collapse_eg(),
+        tn,
-        maybe_open_nursery(
+        shield=shield,
-            tn,
+        strict_exception_groups=False,
-            shield=shield,
+        # ^XXX^ TODO? soo roll our own then ??
-        ) as tn,
+        # -> since we kinda want the "if only one `.exception` then
-    ):
+        # just raise that" interface?
+    ) as tn:
 
         if not channel.connected():
             await channel.connect()
             was_connected = True
 
-        if channel.aid is None:
+        if channel.uid is None:
-            await channel._do_handshake(
+            await actor._do_handshake(channel)
-                aid=actor.aid,
-            )
 
         msg_loop_cs: trio.CancelScope|None = None
         if start_msg_loop:
-            from . import _rpc
+            from ._runtime import process_messages
             msg_loop_cs = await tn.start(
                 partial(
-                    _rpc.process_messages,
+                    process_messages,
-                    chan=channel,
+                    actor,
+                    channel,
                     # if the local task is cancelled we want to keep
                     # the msg loop running until our block ends
                     shield=True,

tractor/_root.py

@@ -18,9 +18,7 @@
 Root actor runtime ignition(s).
 
 '''
-from contextlib import (
+from contextlib import asynccontextmanager as acm
-    asynccontextmanager as acm,
-)
 from functools import partial
 import importlib
 import inspect
@@ -28,55 +26,96 @@ import logging
 import os
 import signal
 import sys
-from typing import (
+from typing import Callable
-    Any,
-    Callable,
-)
 import warnings
 
 
 import trio
 
-from . import _runtime
+from ._runtime import (
-from .devx import (
+    Actor,
-    debug,
+    Arbiter,
-    _frame_stack,
+    # TODO: rename and make a non-actor subtype?
-    pformat as _pformat,
+    # Arbiter as Registry,
+    async_main,
 )
+from .devx import _debug
 from . import _spawn
 from . import _state
 from . import log
-from .ipc import (
+from ._ipc import _connect_chan
-    _connect_chan,
+from ._exceptions import is_multi_cancelled
-)
+
-from ._addr import (
+
-    Address,
+# set at startup and after forks
-    UnwrappedAddress,
+_default_host: str = '127.0.0.1'
-    default_lo_addrs,
+_default_port: int = 1616
-    mk_uuid,
+
-    wrap_address,
+# default registry always on localhost
-)
+_default_lo_addrs: list[tuple[str, int]] = [(
-from .trionics import (
+    _default_host,
-    is_multi_cancelled,
+    _default_port,
-    collapse_eg,
+)]
-)
-from ._exceptions import (
-    RuntimeFailure,
-)
 
 
 logger = log.get_logger('tractor')
 
 
-# TODO: stick this in a `@acm` defined in `devx.debug`?
-# -[ ] also maybe consider making this a `wrapt`-deco to
-#     save an indent level?
-#
 @acm
-async def maybe_block_bp(
+async def open_root_actor(
-    debug_mode: bool,
+
-    maybe_enable_greenback: bool,
+    *,
-) -> bool:
+    # defaults are above
+    registry_addrs: list[tuple[str, int]]|None = None,
+
+    # defaults are above
+    arbiter_addr: tuple[str, int]|None = None,
+
+    name: str|None = 'root',
+
+    # either the `multiprocessing` start method:
+    # https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods
+    # OR `trio` (the new default).
+    start_method: _spawn.SpawnMethodKey|None = None,
+
+    # enables the multi-process debugger support
+    debug_mode: bool = False,
+    maybe_enable_greenback: bool = True,  # `.pause_from_sync()/breakpoint()` support
+    enable_stack_on_sig: bool = False,
+
+    # internal logging
+    loglevel: str|None = None,
+
+    enable_modules: list|None = None,
+    rpc_module_paths: list|None = None,
+
+    # NOTE: allow caller to ensure that only one registry exists
+    # and that this call creates it.
+    ensure_registry: bool = False,
+
+    hide_tb: bool = True,
+
+    # XXX, proxied directly to `.devx._debug._maybe_enter_pm()`
+    # for REPL-entry logic.
+    debug_filter: Callable[
+        [BaseException|BaseExceptionGroup],
+        bool,
+    ] = lambda err: not is_multi_cancelled(err),
+
+    # TODO, a way for actors to augment passing derived
+    # read-only state to sublayers?
+    # extra_rt_vars: dict|None = None,
+
+) -> Actor:
+    '''
+    Runtime init entry point for ``tractor``.
+
+    '''
+    _debug.hide_runtime_frames()
+    __tracebackhide__: bool = hide_tb
+
+    # TODO: stick this in a `@cm` defined in `devx._debug`?
+    #
     # Override the global debugger hook to make it play nice with
     # ``trio``, see much discussion in:
     # https://github.com/python-trio/trio/issues/1155#issuecomment-742964018
@@ -85,25 +124,23 @@ async def maybe_block_bp(
         'PYTHONBREAKPOINT',
         None,
     )
-    bp_blocked: bool
     if (
         debug_mode
         and maybe_enable_greenback
         and (
-            maybe_mod := await debug.maybe_init_greenback(
+            maybe_mod := await _debug.maybe_init_greenback(
                 raise_not_found=False,
             )
         )
     ):
         logger.info(
             f'Found `greenback` installed @ {maybe_mod}\n'
-            f'Enabling `tractor.pause_from_sync()` support!\n'
+            'Enabling `tractor.pause_from_sync()` support!\n'
         )
         os.environ['PYTHONBREAKPOINT'] = (
-            'tractor.devx.debug._sync_pause_from_builtin'
+            'tractor.devx._debug._sync_pause_from_builtin'
         )
         _state._runtime_vars['use_greenback'] = True
-        bp_blocked = False
 
     else:
         # TODO: disable `breakpoint()` by default (without
@@ -122,489 +159,310 @@ async def maybe_block_bp(
         # lol ok,
         # https://docs.python.org/3/library/sys.html#sys.breakpointhook
         os.environ['PYTHONBREAKPOINT'] = "0"
-        bp_blocked = True
 
-    try:
+    # attempt to retreive ``trio``'s sigint handler and stash it
-        yield bp_blocked
+    # on our debugger lock state.
-    finally:
+    _debug.DebugStatus._trio_handler = signal.getsignal(signal.SIGINT)
-        # restore any prior built-in `breakpoint()` hook state
-        if builtin_bp_handler is not None:
-            sys.breakpointhook = builtin_bp_handler
 
-        if orig_bp_path is not None:
+    # mark top most level process as root actor
-            os.environ['PYTHONBREAKPOINT'] = orig_bp_path
+    _state._runtime_vars['_is_root'] = True
 
-        else:
+    # caps based rpc list
-            # clear env back to having no entry
+    enable_modules = (
-            os.environ.pop('PYTHONBREAKPOINT', None)
+        enable_modules
+        or
+        []
+    )
 
+    if rpc_module_paths:
+        warnings.warn(
+            "`rpc_module_paths` is now deprecated, use "
+            " `enable_modules` instead.",
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        enable_modules.extend(rpc_module_paths)
 
+    if start_method is not None:
+        _spawn.try_set_start_method(start_method)
 
-@acm
+    if arbiter_addr is not None:
-async def open_root_actor(
+        warnings.warn(
-    *,
+            '`arbiter_addr` is now deprecated\n'
-    # defaults are above
+            'Use `registry_addrs: list[tuple]` instead..',
-    registry_addrs: list[UnwrappedAddress]|None = None,
+            DeprecationWarning,
+            stacklevel=2,
+        )
+        registry_addrs = [arbiter_addr]
 
-    # defaults are above
+    registry_addrs: list[tuple[str, int]] = (
-    arbiter_addr: tuple[UnwrappedAddress]|None = None,
+        registry_addrs
+        or
+        _default_lo_addrs
+    )
+    assert registry_addrs
 
-    enable_transports: list[
+    loglevel = (
-        # TODO, this should eventually be the pairs as
+        loglevel
-        # defined by (codec, proto) as on `MsgTransport.
+        or log._default_loglevel
-        _state.TransportProtocolKey,
+    ).upper()
-    ]|None = None,
 
-    name: str|None = 'root',
+    if (
-
+        debug_mode
-    # either the `multiprocessing` start method:
+        and _spawn._spawn_method == 'trio'
-    # https://docs.python.org/3/library/multiprocessing.html#contexts-and-start-methods
-    # OR `trio` (the new default).
-    start_method: _spawn.SpawnMethodKey|None = None,
-
-    # enables the multi-process debugger support
-    debug_mode: bool = False,
-    maybe_enable_greenback: bool = False,  # `.pause_from_sync()/breakpoint()` support
-    # ^XXX NOTE^ the perf implications of use,
-    # https://greenback.readthedocs.io/en/latest/principle.html#performance
-    enable_stack_on_sig: bool = False,
-
-    # internal logging
-    loglevel: str|None = None,
-
-    enable_modules: list|None = None,
-    rpc_module_paths: list|None = None,
-
-    # NOTE: allow caller to ensure that only one registry exists
-    # and that this call creates it.
-    ensure_registry: bool = False,
-
-    hide_tb: bool = True,
-
-    # XXX, proxied directly to `.devx.debug._maybe_enter_pm()`
-    # for REPL-entry logic.
-    debug_filter: Callable[
-        [BaseException|BaseExceptionGroup],
-        bool,
-    ] = lambda err: not is_multi_cancelled(err),
-
-    # TODO, a way for actors to augment passing derived
-    # read-only state to sublayers?
-    # extra_rt_vars: dict|None = None,
-
-) -> _runtime.Actor:
-    '''
-    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,
     ):
-        rtvs: dict[str, Any] = _state._runtime_vars
+        _state._runtime_vars['_debug_mode'] = True
-        root_mailbox: list[str, int] = rtvs['_root_mailbox']
+
-        registry_addrs: list[list[str, int]] = rtvs['_registry_addrs']
+        # expose internal debug module to every actor allowing for
-        raise RuntimeFailure(
+        # use of ``await tractor.pause()``
-            f'A current actor already exists !?\n'
+        enable_modules.append('tractor.devx._debug')
-            f'({already_actor}\n'
+
-            f'\n'
+        # if debug mode get's enabled *at least* use that level of
-            f'You can NOT open a second root actor from within '
+        # logging for some informative console prompts.
-            f'an existing tree and the current root of this '
+        if (
-            f'already exists !!\n'
+            logging.getLevelName(
-            f'\n'
+                # lul, need the upper case for the -> int map?
-            f'_root_mailbox: {root_mailbox!r}\n'
+                # sweet "dynamic function behaviour" stdlib...
-            f'_registry_addrs: {registry_addrs!r}\n'
+                loglevel,
+            ) > logging.getLevelName('PDB')
+        ):
+            loglevel = 'PDB'
+
+
+    elif debug_mode:
+        raise RuntimeError(
+            "Debug mode is only supported for the `trio` backend!"
         )
 
-    async with maybe_block_bp(
+    assert loglevel
-        debug_mode=debug_mode,
+    _log = log.get_console_log(loglevel)
-        maybe_enable_greenback=maybe_enable_greenback,
+    assert _log
+
+    # TODO: factor this into `.devx._stackscope`!!
+    if (
+        debug_mode
+        and
+        enable_stack_on_sig
     ):
-        if enable_transports is None:
+        from .devx._stackscope import enable_stack_on_sig
-            enable_transports: list[str] = _state.current_ipc_protos()
+        enable_stack_on_sig()
-        else:
-            _state._runtime_vars['_enable_tpts'] = enable_transports
 
-        # TODO! support multi-tpts per actor!
+    # closed into below ping task-func
-        # Bo
+    ponged_addrs: list[tuple[str, int]] = []
-        if not len(enable_transports) == 1:
-            raise RuntimeError(
-                f'No multi-tpt support yet!\n'
-                f'enable_transports={enable_transports!r}\n'
-            )
 
-        _frame_stack.hide_runtime_frames()
+    async def ping_tpt_socket(
-        __tracebackhide__: bool = hide_tb
+        addr: tuple[str, int],
+        timeout: float = 1,
+    ) -> None:
+        '''
+        Attempt temporary connection to see if a registry is
+        listening at the requested address by a tranport layer
+        ping.
 
-        # attempt to retreive ``trio``'s sigint handler and stash it
+        If a connection can't be made quickly we assume none no
-        # on our debugger lock state.
+        server is listening at that addr.
-        debug.DebugStatus._trio_handler = signal.getsignal(signal.SIGINT)
 
-        # mark top most level process as root actor
+        '''
-        _state._runtime_vars['_is_root'] = True
-
-        # caps based rpc list
-        enable_modules = (
-            enable_modules
-            or
-            []
-        )
-
-        if rpc_module_paths:
-            warnings.warn(
-                "`rpc_module_paths` is now deprecated, use "
-                " `enable_modules` instead.",
-                DeprecationWarning,
-                stacklevel=2,
-            )
-            enable_modules.extend(rpc_module_paths)
-
-        if start_method is not None:
-            _spawn.try_set_start_method(start_method)
-
-        # TODO! remove this ASAP!
-        if arbiter_addr is not None:
-            warnings.warn(
-                '`arbiter_addr` is now deprecated\n'
-                'Use `registry_addrs: list[tuple]` instead..',
-                DeprecationWarning,
-                stacklevel=2,
-            )
-            uw_reg_addrs = [arbiter_addr]
-
-        uw_reg_addrs = registry_addrs
-        if not uw_reg_addrs:
-            uw_reg_addrs: list[UnwrappedAddress] = default_lo_addrs(
-                enable_transports
-            )
-
-        # 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
-            or log._default_loglevel
-        ).upper()
-
-        if (
-            debug_mode
-            and
-            _spawn._spawn_method == 'trio'
-        ):
-            _state._runtime_vars['_debug_mode'] = True
-
-            # expose internal debug module to every actor allowing for
-            # use of ``await tractor.pause()``
-            enable_modules.append('tractor.devx.debug._tty_lock')
-
-            # if debug mode get's enabled *at least* use that level of
-            # logging for some informative console prompts.
-            if (
-                logging.getLevelName(
-                    # lul, need the upper case for the -> int map?
-                    # sweet "dynamic function behaviour" stdlib...
-                    loglevel,
-                ) > logging.getLevelName('PDB')
-            ):
-                loglevel = 'PDB'
-
-
-        elif debug_mode:
-            raise RuntimeError(
-                "Debug mode is only supported for the `trio` backend!"
-            )
-
-        assert loglevel
-        _log = log.get_console_log(loglevel)
-        assert _log
-
-        # TODO: factor this into `.devx._stackscope`!!
-        if (
-            debug_mode
-            and
-            enable_stack_on_sig
-        ):
-            from .devx._stackscope import enable_stack_on_sig
-            enable_stack_on_sig()
-
-        # closed into below ping task-func
-        ponged_addrs: list[Address] = []
-
-        async def ping_tpt_socket(
-            addr: Address,
-            timeout: float = 1,
-        ) -> None:
-            '''
-            Attempt temporary connection to see if a registry is
-            listening at the requested address by a tranport layer
-            ping.
-
-            If a connection can't be made quickly we assume none no
-            server is listening at that addr.
-
-            '''
-            try:
-                # TODO: this connect-and-bail forces us to have to
-                # carefully rewrap TCP 104-connection-reset errors as
-                # EOF so as to avoid propagating cancel-causing errors
-                # to the channel-msg loop machinery. Likely it would
-                # be better to eventually have a "discovery" protocol
-                # with basic handshake instead?
-                with trio.move_on_after(timeout):
-                    async with _connect_chan(addr.unwrap()):
-                        ponged_addrs.append(addr)
-
-            except OSError:
-                # ?TODO, make this a "discovery" log level?
-                logger.info(
-                    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 uw_addr in uw_reg_addrs:
-                addr: Address = wrap_address(uw_addr)
-                tn.start_soon(
-                    ping_tpt_socket,
-                    addr,
-                )
-
-        trans_bind_addrs: list[UnwrappedAddress] = []
-
-        # Create a new local root-actor instance which IS NOT THE
-        # REGISTRAR
-        if ponged_addrs:
-            if ensure_registry:
-                raise RuntimeError(
-                     f'Failed to open `{name}`@{ponged_addrs}: '
-                    'registry socket(s) already bound'
-                )
-
-            # we were able to connect to an arbiter
-            logger.info(
-                f'Registry(s) seem(s) to exist @ {ponged_addrs}'
-            )
-
-            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
-            # 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:
-                trans_bind_addrs.append(
-                    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 = uw_reg_addrs
-
-            # - it is normally desirable for any registrar to stay up
-            #   indefinitely until either all registered (child/sub)
-            #   actors are terminated (via SC supervision) or,
-            #   a re-election process has taken place.
-            # NOTE: all of ^ which is not implemented yet - see:
-            # https://github.com/goodboy/tractor/issues/216
-            # https://github.com/goodboy/tractor/pull/348
-            # https://github.com/goodboy/tractor/issues/296
-
-            # TODO: rename as `RootActor` or is that even necessary?
-            actor = _runtime.Arbiter(
-                name=name or 'registrar',
-                uuid=mk_uuid(),
-                registry_addrs=registry_addrs,
-                loglevel=loglevel,
-                enable_modules=enable_modules,
-            )
-            # XXX, in case the root actor runtime was actually run from
-            # `tractor.to_asyncio.run_as_asyncio_guest()` and NOt
-            # `.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
+            # TODO: this connect-and-bail forces us to have to
-            _state._current_actor = actor
+            # carefully rewrap TCP 104-connection-reset errors as
-
+            # EOF so as to avoid propagating cancel-causing errors
-            # start local channel-server and fake the portal API
+            # to the channel-msg loop machinery. Likely it would
-            # NOTE: this won't block since we provide the nursery
+            # be better to eventually have a "discovery" protocol
-            report: str = f'Starting actor-runtime for {actor.aid.reprol()!r}\n'
+            # with basic handshake instead?
-            if reg_addrs := actor.registry_addrs:
+            with trio.move_on_after(timeout):
-                report += (
+                async with _connect_chan(*addr):
-                    '-> Opening new registry @ '
+                    ponged_addrs.append(addr)
-                    +
-                    '\n'.join(
-                        f'{addr}' for addr in reg_addrs
-                    )
-                )
-            logger.info(f'{report}\n')
-
-            # start runtime in a bg sub-task, yield to caller.
-            async with (
-                collapse_eg(),
-                trio.open_nursery() as root_tn,
-
-                # ?TODO? finally-footgun below?
-                # -> see note on why shielding.
-                # maybe_raise_from_masking_exc(),
-            ):
-                actor._root_tn = root_tn
-                # `_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
-                # entire hierarchical python sub-process set; all
-                # "actor runtime" primitives are SC-compat and thus all
-                # transitively spawned actors/processes must be as
-                # well.
-                await root_tn.start(
-                    partial(
-                        _runtime.async_main,
-                        actor,
-                        accept_addrs=trans_bind_addrs,
-                        parent_addr=None
-                    )
-                )
-                try:
-                    yield actor
-                except (
-                    Exception,
-                    BaseExceptionGroup,
-                ) as err:
-
-                    # TODO, in beginning to handle the subsubactor with
-                    # crashed grandparent cases..
-                    #
-                    # was_locked: bool = await debug.maybe_wait_for_debugger(
-                    #     child_in_debug=True,
-                    # )
-                    # XXX NOTE XXX see equiv note inside
-                    # `._runtime.Actor._stream_handler()` where in the
-                    # non-root or root-that-opened-this-mahually case we
-                    # wait for the local actor-nursery to exit before
-                    # exiting the transport channel handler.
-                    entered: bool = await debug._maybe_enter_pm(
-                        err,
-                        api_frame=inspect.currentframe(),
-                        debug_filter=debug_filter,
-
-                        # XXX NOTE, required to debug root-actor
-                        # crashes under cancellation conditions; so
-                        # most of them!
-                        shield=root_tn.cancel_scope.cancel_called,
-                    )
-
-                    if (
-                        not entered
-                        and
-                        not is_multi_cancelled(
-                            err,
-                        )
-                    ):
-                        logger.exception(
-                            'Root actor crashed\n'
-                            f'>x)\n'
-                            f' |_{actor}\n'
-                        )
-
-                    # ALWAYS re-raise any error bubbled up from the
-                    # runtime!
-                    raise
-
-                finally:
-                    # 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..')
-                    # nurseries = actor._actoruid2nursery.values()
-                    # async with trio.open_nursery() as tempn:
-                    #     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'{op_nested_actor_repr}'
-                    )
-                    # XXX, THIS IS A *finally-footgun*!
-                    # (also mentioned in with-block above)
-                    # -> 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 (
-                debug_mode
-                and
-                _spawn._spawn_method == 'trio'
-            ):
-                _state._runtime_vars['_debug_mode'] = False
-
-            _state._current_actor = None
-            _state._last_actor_terminated = actor
-
-            sclang_repr: str = _pformat.nest_from_op(
-                input_op=')>',
-                text=actor.pformat(),
-                nest_prefix='|_',
-                nest_indent=1,
-            )
 
+        except OSError:
+            # TODO: make this a "discovery" log level?
             logger.info(
-                f'Root actor terminated\n'
+                f'No actor registry found @ {addr}\n'
-                f'{sclang_repr}'
             )
 
+    async with trio.open_nursery() as tn:
+        for addr in registry_addrs:
+            tn.start_soon(
+                ping_tpt_socket,
+                tuple(addr),  # TODO: just drop this requirement?
+            )
+
+    trans_bind_addrs: list[tuple[str, int]] = []
+
+    # Create a new local root-actor instance which IS NOT THE
+    # REGISTRAR
+    if ponged_addrs:
+        if ensure_registry:
+            raise RuntimeError(
+                 f'Failed to open `{name}`@{ponged_addrs}: '
+                'registry socket(s) already bound'
+            )
+
+        # we were able to connect to an arbiter
+        logger.info(
+            f'Registry(s) seem(s) to exist @ {ponged_addrs}'
+        )
+
+        actor = Actor(
+            name=name or 'anonymous',
+            registry_addrs=ponged_addrs,
+            loglevel=loglevel,
+            enable_modules=enable_modules,
+        )
+        # DO NOT use the registry_addrs as the transport server
+        # addrs for this new non-registar, root-actor.
+        for host, port in ponged_addrs:
+            # NOTE: zero triggers dynamic OS port allocation
+            trans_bind_addrs.append((host, 0))
+
+    # Start this local actor as the "registrar", aka a regular
+    # actor who manages the local registry of "mailboxes" of
+    # other process-tree-local sub-actors.
+    else:
+
+        # NOTE that if the current actor IS THE REGISTAR, the
+        # following init steps are taken:
+        # - the tranport layer server is bound to each (host, port)
+        #   pair defined in provided registry_addrs, or the default.
+        trans_bind_addrs = registry_addrs
+
+        # - it is normally desirable for any registrar to stay up
+        #   indefinitely until either all registered (child/sub)
+        #   actors are terminated (via SC supervision) or,
+        #   a re-election process has taken place. 
+        # NOTE: all of ^ which is not implemented yet - see:
+        # https://github.com/goodboy/tractor/issues/216
+        # https://github.com/goodboy/tractor/pull/348
+        # https://github.com/goodboy/tractor/issues/296
+
+        actor = Arbiter(
+            name or 'registrar',
+            registry_addrs=registry_addrs,
+            loglevel=loglevel,
+            enable_modules=enable_modules,
+        )
+        # XXX, in case the root actor runtime was actually run from
+        # `tractor.to_asyncio.run_as_asyncio_guest()` and NOt
+        # `.trio.run()`.
+        actor._infected_aio = _state._runtime_vars['_is_infected_aio']
+
+    # Start up main task set via core actor-runtime nurseries.
+    try:
+        # assign process-local actor
+        _state._current_actor = actor
+
+        # start local channel-server and fake the portal API
+        # NOTE: this won't block since we provide the nursery
+        ml_addrs_str: str = '\n'.join(
+            f'@{addr}' for addr in trans_bind_addrs
+        )
+        logger.info(
+            f'Starting local {actor.uid} on the following transport addrs:\n'
+            f'{ml_addrs_str}'
+        )
+
+        # start the actor runtime in a new task
+        async with trio.open_nursery(
+            strict_exception_groups=False,
+            # ^XXX^ TODO? instead unpack any RAE as per "loose" style?
+        ) as nursery:
+
+            # ``_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
+            # entire hierarchical python sub-process set; all
+            # "actor runtime" primitives are SC-compat and thus all
+            # transitively spawned actors/processes must be as
+            # well.
+            await nursery.start(
+                partial(
+                    async_main,
+                    actor,
+                    accept_addrs=trans_bind_addrs,
+                    parent_addr=None
+                )
+            )
+            try:
+                yield actor
+            except (
+                Exception,
+                BaseExceptionGroup,
+            ) as err:
+
+                # TODO, in beginning to handle the subsubactor with
+                # crashed grandparent cases..
+                #
+                # was_locked: bool = await _debug.maybe_wait_for_debugger(
+                #     child_in_debug=True,
+                # )
+                # XXX NOTE XXX see equiv note inside
+                # `._runtime.Actor._stream_handler()` where in the
+                # non-root or root-that-opened-this-mahually case we
+                # wait for the local actor-nursery to exit before
+                # exiting the transport channel handler.
+                entered: bool = await _debug._maybe_enter_pm(
+                    err,
+                    api_frame=inspect.currentframe(),
+                    debug_filter=debug_filter,
+                )
+
+                if (
+                    not entered
+                    and
+                    not is_multi_cancelled(
+                        err,
+                    )
+                ):
+                    logger.exception('Root actor crashed\n')
+
+                # ALWAYS re-raise any error bubbled up from the
+                # runtime!
+                raise
+
+            finally:
+                # NOTE: 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..')
+                # nurseries = actor._actoruid2nursery.values()
+                # async with trio.open_nursery() as tempn:
+                #     for an in nurseries:
+                #         tempn.start_soon(an.exited.wait)
+
+                logger.info(
+                    'Closing down root actor'
+                )
+                await actor.cancel(None)  # self cancel
+    finally:
+        _state._current_actor = None
+        _state._last_actor_terminated = actor
+
+        # restore built-in `breakpoint()` hook state
+        if (
+            debug_mode
+            and
+            maybe_enable_greenback
+        ):
+            if builtin_bp_handler is not None:
+                sys.breakpointhook = builtin_bp_handler
+
+            if orig_bp_path is not None:
+                os.environ['PYTHONBREAKPOINT'] = orig_bp_path
+
+            else:
+                # clear env back to having no entry
+                os.environ.pop('PYTHONBREAKPOINT', None)
+
+        logger.runtime("Root actor terminated")
+
 
 def run_daemon(
     enable_modules: list[str],
 
     # runtime kwargs
     name: str | None = 'root',
-    registry_addrs: list[UnwrappedAddress]|None = None,
+    registry_addrs: list[tuple[str, int]] = _default_lo_addrs,
 
     start_method: str | None = None,
     debug_mode: bool = False,

tractor/_rpc.py

@@ -37,13 +37,12 @@ import warnings
 
 import trio
 from trio import (
-    Cancelled,
     CancelScope,
     Nursery,
     TaskStatus,
 )
 
-from .ipc import Channel
+from ._ipc import Channel
 from ._context import (
     Context,
 )
@@ -53,18 +52,13 @@ from ._exceptions import (
     ModuleNotExposed,
     MsgTypeError,
     TransportClosed,
+    is_multi_cancelled,
     pack_error,
     unpack_error,
 )
-from .trionics import (
-    collapse_eg,
-    is_multi_cancelled,
-    maybe_raise_from_masking_exc,
-)
 from .devx import (
-    debug,
+    _debug,
     add_div,
-    pformat as _pformat,
 )
 from . import _state
 from .log import get_logger
@@ -73,7 +67,7 @@ from .msg import (
     MsgCodec,
     PayloadT,
     NamespacePath,
-    pretty_struct,
+    # pretty_struct,
     _ops as msgops,
 )
 from tractor.msg.types import (
@@ -221,18 +215,11 @@ 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(
-                f'RPC task complete\n'
+                'RPC complete:\n'
-                f'\n'
+                f'task: {ctx._task}\n'
-                f'{op_nested_task}\n'
+                f'|_cid={ctx.cid}\n'
-                f'\n'
+                f'|_{fname}() -> {pformat(result)}\n'
-                f')> {fname}() -> {pformat(result)}\n'
             )
 
             # NOTE: only send result if we know IPC isn't down
@@ -263,7 +250,7 @@ async def _errors_relayed_via_ipc(
     ctx: Context,
     is_rpc: bool,
 
-    hide_tb: bool = True,
+    hide_tb: bool = False,
     debug_kbis: bool = False,
     task_status: TaskStatus[
         Context | BaseException
@@ -279,7 +266,7 @@ async def _errors_relayed_via_ipc(
 
     # TODO: a debug nursery when in debug mode!
     # async with maybe_open_debugger_nursery() as debug_tn:
-    # => see matching comment in side `.debug._pause()`
+    # => see matching comment in side `._debug._pause()`
     rpc_err: BaseException|None = None
     try:
         yield  # run RPC invoke body
@@ -331,7 +318,7 @@ async def _errors_relayed_via_ipc(
                     'RPC task crashed, attempting to enter debugger\n'
                     f'|_{ctx}'
                 )
-                entered_debug = await debug._maybe_enter_pm(
+                entered_debug = await _debug._maybe_enter_pm(
                     err,
                     api_frame=inspect.currentframe(),
                 )
@@ -384,13 +371,13 @@ async def _errors_relayed_via_ipc(
 
     # RPC task bookeeping.
     # since RPC tasks are scheduled inside a flat
-    # `Actor._service_tn`, we add "handles" to each such that
+    # `Actor._service_n`, we add "handles" to each such that
     # they can be individually ccancelled.
     finally:
 
-        # if the error is not from user code and instead a failure of
+        # if the error is not from user code and instead a failure
-        # an internal-runtime-RPC or IPC-connection, we do (prolly) want
+        # of a runtime RPC or transport failure we do prolly want to
-        # to show this frame!
+        # show this frame
         if (
             rpc_err
             and (
@@ -462,7 +449,7 @@ async def _invoke(
     connected IPC channel.
 
     This is the core "RPC" `trio.Task` scheduling machinery used to start every
-    remotely invoked function, normally in `Actor._service_tn: Nursery`.
+    remotely invoked function, normally in `Actor._service_n: Nursery`.
 
     '''
     __tracebackhide__: bool = hide_tb
@@ -475,7 +462,7 @@ async def _invoke(
     ):
         # XXX for .pause_from_sync()` usage we need to make sure
         # `greenback` is boostrapped in the subactor!
-        await debug.maybe_init_greenback()
+        await _debug.maybe_init_greenback()
 
     # TODO: possibly a specially formatted traceback
     # (not sure what typing is for this..)?
@@ -629,39 +616,32 @@ async def _invoke(
         #  -> the below scope is never exposed to the
         #     `@context` marked RPC function.
         # - `._portal` is never set.
-        scope_err: BaseException|None = None
         try:
-            # TODO: better `trionics` primitive/tooling usage here!
+            tn: trio.Nursery
-            # -[ ] should would be nice to have our `TaskMngr`
-            #   nursery here!
-            # -[ ] payload value checking like we do with
-            #   `.started()` such that the debbuger can engage
-            #   here in the child task instead of waiting for the
-            #   parent to crash with it's own MTE..
-            #
-            tn: Nursery
             rpc_ctx_cs: CancelScope
             async with (
-                collapse_eg(hide_tb=False),
+                trio.open_nursery(
-                trio.open_nursery() as tn,
+                    strict_exception_groups=False,
+                    # ^XXX^ TODO? instead unpack any RAE as per "loose" style?
+
+                ) as tn,
                 msgops.maybe_limit_plds(
                     ctx=ctx,
                     spec=ctx_meta.get('pld_spec'),
                     dec_hook=ctx_meta.get('dec_hook'),
                 ),
-
-                # XXX NOTE, this being the "most embedded"
-                # scope ensures unasking of the `await coro` below
-                # *should* never be interfered with!!
-                maybe_raise_from_masking_exc(
-                    unmask_from=(Cancelled,),
-                ) as _mbme,  # maybe boxed masked exc
             ):
                 ctx._scope_nursery = tn
                 rpc_ctx_cs = ctx._scope = tn.cancel_scope
                 task_status.started(ctx)
 
-                # invoke user endpoint fn.
+                # TODO: better `trionics` tooling:
+                # -[ ] should would be nice to have our `TaskMngr`
+                #   nursery here!
+                # -[ ] payload value checking like we do with
+                #   `.started()` such that the debbuger can engage
+                #   here in the child task instead of waiting for the
+                #   parent to crash with it's own MTE..
                 res: Any|PayloadT = await coro
                 return_msg: Return|CancelAck = return_msg_type(
                     cid=cid,
@@ -671,8 +651,7 @@ async def _invoke(
                 ctx._result = res
                 log.runtime(
                     f'Sending result msg and exiting {ctx.side!r}\n'
-                    f'\n'
+                    f'{return_msg}\n'
-                    f'{pretty_struct.pformat(return_msg)}\n'
                 )
                 await chan.send(return_msg)
 
@@ -764,52 +743,43 @@ async def _invoke(
             BaseExceptionGroup,
             BaseException,
             trio.Cancelled,
-        ) as _scope_err:
+
-            scope_err = _scope_err
+        ) as scope_error:
             if (
-                isinstance(scope_err, RuntimeError)
+                isinstance(scope_error, RuntimeError)
-                and
+                and scope_error.args
-                scope_err.args
+                and 'Cancel scope stack corrupted' in scope_error.args[0]
-                and
-                'Cancel scope stack corrupted' in scope_err.args[0]
             ):
                 log.exception('Cancel scope stack corrupted!?\n')
-                # debug.mk_pdb().set_trace()
+                # _debug.mk_pdb().set_trace()
 
             # always set this (child) side's exception as the
             # local error on the context
-            ctx._local_error: BaseException = scope_err
+            ctx._local_error: BaseException = scope_error
             # ^-TODO-^ question,
             # does this matter other then for
             # consistentcy/testing?
             # |_ no user code should be in this scope at this point
             #    AND we already set this in the block below?
 
-            # XXX if a remote error was set then likely the
+            # if a remote error was set then likely the
-            # exc group was raised due to that, so
+            # exception group was raised due to that, so
             # and we instead raise that error immediately!
-            maybe_re: (
+            ctx.maybe_raise()
-                ContextCancelled|RemoteActorError
-            ) = ctx.maybe_raise()
-            if maybe_re:
-                log.cancel(
-                    f'Suppressing remote-exc from peer,\n'
-                    f'{maybe_re!r}\n'
-                )
 
             # maybe TODO: pack in come kinda
             # `trio.Cancelled.__traceback__` here so they can be
             # unwrapped and displayed on the caller side? no se..
-            raise scope_err
+            raise
 
         # `@context` entrypoint task bookeeping.
         # i.e. only pop the context tracking if used ;)
         finally:
-            assert chan.aid
+            assert chan.uid
 
             # don't pop the local context until we know the
             # associated child isn't in debug any more
-            await debug.maybe_wait_for_debugger()
+            await _debug.maybe_wait_for_debugger()
             ctx: Context = actor._contexts.pop((
                 chan.uid,
                 cid,
@@ -822,49 +792,26 @@ async def _invoke(
                 f'after having {ctx.repr_state!r}\n'
             )
             if merr:
+
                 logmeth: Callable = log.error
-                if (
+                if isinstance(merr, ContextCancelled):
-                    # ctxc: by `Context.cancel()`
+                    logmeth: Callable = log.runtime
-                    isinstance(merr, ContextCancelled)
 
-                    # out-of-layer cancellation, one of:
+                if not isinstance(merr, RemoteActorError):
-                    # - actorc: by `Portal.cancel_actor()`
+                    tb_str: str = ''.join(traceback.format_exception(merr))
-                    # - OSc: by SIGINT or `Process.signal()`
-                    or (
-                        isinstance(merr, trio.Cancelled)
-                        and
-                        ctx.canceller
-                    )
-                ):
-                    logmeth: Callable = log.cancel
-                    descr_str += (
-                        f' with {merr!r}\n'
-                    )
-
-                elif (
-                    not isinstance(merr, RemoteActorError)
-                ):
-                    tb_str: str = ''.join(
-                        traceback.format_exception(merr)
-                    )
                     descr_str += (
                         f'\n{merr!r}\n'  # needed?
                         f'{tb_str}\n'
                     )
                 else:
-                    descr_str += (
+                    descr_str += f'\n{merr!r}\n'
-                        f'{merr!r}\n'
-                    )
             else:
-                descr_str += (
+                descr_str += f'\nand final result {ctx.outcome!r}\n'
-                    f'\n'
-                    f'with final result {ctx.outcome!r}\n'
-                )
 
             logmeth(
-                f'{message}\n'
+                message
-                f'\n'
+                +
-                f'{descr_str}\n'
+                descr_str
             )
 
 
@@ -922,6 +869,7 @@ async def try_ship_error_to_remote(
 
 
 async def process_messages(
+    actor: Actor,
     chan: Channel,
     shield: bool = False,
     task_status: TaskStatus[CancelScope] = trio.TASK_STATUS_IGNORED,
@@ -935,7 +883,7 @@ async def process_messages(
 
     Receive (multiplexed) per-`Channel` RPC requests as msgs from
     remote processes; schedule target async funcs as local
-    `trio.Task`s inside the `Actor._service_tn: Nursery`.
+    `trio.Task`s inside the `Actor._service_n: Nursery`.
 
     Depending on msg type, non-`cmd` (task spawning/starting)
     request payloads (eg. `started`, `yield`, `return`, `error`)
@@ -959,8 +907,7 @@ async def process_messages(
       (as utilized inside `Portal.cancel_actor()` ).
 
     '''
-    actor: Actor = _state.current_actor()
+    assert actor._service_n  # runtime state sanity
-    assert actor._service_tn  # runtime state sanity
 
     # TODO: once `trio` get's an "obvious way" for req/resp we
     # should use it?
@@ -1031,10 +978,12 @@ 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!
-                        pdb_complete: trio.Event|None = debug.DebugStatus.repl_release
+                        pdb_complete: trio.Event|None = _debug.DebugStatus.repl_release
                         if pdb_complete:
                             await pdb_complete.wait()
 
@@ -1049,14 +998,14 @@ async def process_messages(
                                 cid,
                                 chan,
                                 actor.cancel,
-                                kwargs | {'req_chan': chan},
+                                kwargs,
                                 is_rpc=False,
                                 return_msg_type=CancelAck,
                             )
 
                         log.runtime(
-                            'Cancelling RPC-msg-loop with peer\n'
+                            'Cancelling IPC transport msg-loop with peer:\n'
-                            f'->c}} {chan.aid.reprol()}@[{chan.maddr}]\n'
+                            f'|_{chan}\n'
                         )
                         loop_cs.cancel()
                         break
@@ -1069,7 +1018,7 @@ async def process_messages(
                     ):
                         target_cid: str = kwargs['cid']
                         kwargs |= {
-                            'requesting_aid': chan.aid,
+                            'requesting_uid': chan.uid,
                             'ipc_msg': msg,
 
                             # XXX NOTE! ONLY the rpc-task-owning
@@ -1105,34 +1054,21 @@ async def process_messages(
                         ns=ns,
                         func=funcname,
                         kwargs=kwargs,  # type-spec this? see `msg.types`
-                        uid=actor_uuid,
+                        uid=actorid,
                     ):
-                        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 request\n'
+                            'Handling RPC `Start` request\n'
-                            f'{req_repr}\n'
+                            f'<= peer: {actorid}\n\n'
-                            f'\n'
+                            f'  |_{chan}\n'
-                            f'->{{ ipc-context-id: {cid!r}\n'
+                            f'  |_cid: {cid}\n\n'
-                            f'->{{ nsp for fn: `{ns}.{funcname}({kwargs})`\n'
+                            # f'  |_{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>`
@@ -1161,6 +1097,10 @@ 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".
                         #
@@ -1168,10 +1108,10 @@ 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_tn.start(
+                            ctx: Context = await actor._service_n.start(
                                 partial(
                                     _invoke,
                                     actor,
@@ -1216,7 +1156,7 @@ async def process_messages(
                                 trio.Event(),
                             )
 
-                    # XXX RUNTIME-SCOPED! remote (likely internal) error
+                    # runtime-scoped remote (internal) error
                     # (^- bc no `Error.cid` -^)
                     #
                     # NOTE: this is the non-rpc error case, that
@@ -1252,24 +1192,12 @@ 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'IPC channel disconnected\n'
+                f'channel for {chan.uid} disconnected, cancelling RPC tasks\n'
-                f'{chan_repr}\n'
+                f'|_{chan}\n'
-                f'\n'
-                f'->c) cancelling RPC tasks.\n'
             )
             await actor.cancel_rpc_tasks(
-                req_aid=actor.aid,
+                req_uid=actor.uid,
                 # 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.
@@ -1291,10 +1219,8 @@ async def process_messages(
         # -[ ] figure out how this will break with other transports?
         tc.report_n_maybe_raise(
             message=(
-                f'peer IPC channel closed abruptly?\n'
+                f'peer IPC channel closed abruptly?\n\n'
-                f'\n'
+                f'<=x {chan}\n'
-                f'<=x[\n'
-                f'  {chan}\n'
                 f'  |_{chan.raddr}\n\n'
             )
             +
@@ -1311,7 +1237,7 @@ async def process_messages(
     ) as err:
 
         if nursery_cancelled_before_task:
-            sn: Nursery = actor._service_tn
+            sn: Nursery = actor._service_n
             assert sn and sn.cancel_scope.cancel_called  # sanity
             log.cancel(
                 f'Service nursery cancelled before it handled {funcname}'
@@ -1341,37 +1267,13 @@ async def process_messages(
     finally:
         # msg debugging for when he machinery is brokey
         if msg is None:
-            message: str = 'Exiting RPC-loop without receiving a msg?'
+            message: str = 'Exiting IPC msg 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 = (
-                f'Exiting RPC-loop with final msg\n'
+                'Exiting IPC msg loop with final msg\n\n'
-                f'\n'
+                f'<= peer: {chan.uid}\n'
-                # f'{chan_repr}\n'
+                f'  |_{chan}\n\n'
-                f'{task_repr}\n'
+                # f'{pretty_struct.pformat(msg)}'
-                f'\n'
-                f'{pretty_struct.pformat(msg)}'
-                f'\n'
             )
 
         log.runtime(message)

tractor/_shm.py

@@ -23,24 +23,19 @@ considered optional within the context of this runtime-library.
 
 """
 from __future__ import annotations
-from multiprocessing import shared_memory as shm
-from multiprocessing.shared_memory import (
-    # SharedMemory,
-    ShareableList,
-)
-import platform
 from sys import byteorder
 import time
 from typing import Optional
-
+from multiprocessing import shared_memory as shm
-from msgspec import (
+from multiprocessing.shared_memory import (
-    Struct,
+    SharedMemory,
-    to_builtins
+    ShareableList,
 )
+
+from msgspec import Struct
 import tractor
 
-from tractor.ipc._mp_bs import disable_mantracker
+from .log import get_logger
-from tractor.log import get_logger
 
 
 _USE_POSIX = getattr(shm, '_USE_POSIX', False)
@@ -51,10 +46,7 @@ if _USE_POSIX:
 try:
     import numpy as np
     from numpy.lib import recfunctions as rfn
-    # TODO ruff complains with,
+    import nptyping
-    # warning| F401: `nptyping` imported but unused; consider using
-    # `importlib.util.find_spec` to test for availability
-    import nptyping  # noqa
 except ImportError:
     pass
 
@@ -62,7 +54,35 @@ except ImportError:
 log = get_logger(__name__)
 
 
-SharedMemory = disable_mantracker()
+def disable_mantracker():
+    '''
+    Disable all ``multiprocessing``` "resource tracking" machinery since
+    it's an absolute multi-threaded mess of non-SC madness.
+
+    '''
+    from multiprocessing import resource_tracker as mantracker
+
+    # Tell the "resource tracker" thing to fuck off.
+    class ManTracker(mantracker.ResourceTracker):
+        def register(self, name, rtype):
+            pass
+
+        def unregister(self, name, rtype):
+            pass
+
+        def ensure_running(self):
+            pass
+
+    # "know your land and know your prey"
+    # https://www.dailymotion.com/video/x6ozzco
+    mantracker._resource_tracker = ManTracker()
+    mantracker.register = mantracker._resource_tracker.register
+    mantracker.ensure_running = mantracker._resource_tracker.ensure_running
+    mantracker.unregister = mantracker._resource_tracker.unregister
+    mantracker.getfd = mantracker._resource_tracker.getfd
+
+
+disable_mantracker()
 
 
 class SharedInt:
@@ -122,7 +142,7 @@ class NDToken(Struct, frozen=True):
         ).descr
 
     def as_msg(self):
-        return to_builtins(self)
+        return self.to_dict()
 
     @classmethod
     def from_msg(cls, msg: dict) -> NDToken:
@@ -790,23 +810,11 @@ 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()
-
         actor.lifetime_stack.callback(shml.shm.close)
-
+        actor.lifetime_stack.callback(shml.shm.unlink)
-        # XXX on 3.13+ we don't need to call this?
-        # -> bc we pass `track=False` for `SharedMemeory` orr?
-        if (
-            platform.python_version_tuple()[:-1] < ('3', '13')
-        ):
-            actor.lifetime_stack.callback(shml.shm.unlink)
     except RuntimeError:
         log.warning('tractor runtime not active, skipping teardown steps')
 

tractor/_spawn.py

@@ -34,9 +34,9 @@ from typing import (
 import trio
 from trio import TaskStatus
 
-from .devx import (
+from .devx._debug import (
-    debug,
+    maybe_wait_for_debugger,
-    pformat as _pformat
+    acquire_debug_lock,
 )
 from tractor._state import (
     current_actor,
@@ -46,26 +46,19 @@ from tractor._state import (
     _runtime_vars,
 )
 from tractor.log import get_logger
-from tractor._addr import UnwrappedAddress
 from tractor._portal import Portal
 from tractor._runtime import Actor
 from tractor._entry import _mp_main
 from tractor._exceptions import ActorFailure
-from tractor.msg import (
+from tractor.msg.types import (
-    types as msgtypes,
+    SpawnSpec,
-    pretty_struct,
 )
 
 
 if TYPE_CHECKING:
-    from ipc import (
-        _server,
-        Channel,
-    )
     from ._supervise import ActorNursery
     ProcessType = TypeVar('ProcessType', mp.Process, trio.Process)
 
-
 log = get_logger('tractor')
 
 # placeholder for an mp start context if so using that backend
@@ -170,7 +163,7 @@ async def exhaust_portal(
         # TODO: merge with above?
         log.warning(
             'Cancelled portal result waiter task:\n'
-            f'uid: {portal.channel.aid}\n'
+            f'uid: {portal.channel.uid}\n'
             f'error: {err}\n'
         )
         return err
@@ -178,7 +171,7 @@ async def exhaust_portal(
     else:
         log.debug(
             f'Returning final result from portal:\n'
-            f'uid: {portal.channel.aid}\n'
+            f'uid: {portal.channel.uid}\n'
             f'result: {final}\n'
         )
         return final
@@ -236,6 +229,10 @@ async def hard_kill(
     # whilst also hacking on it XD
     # terminate_after: int = 99999,
 
+    # NOTE: for mucking with `.pause()`-ing inside the runtime
+    # whilst also hacking on it XD
+    # terminate_after: int = 99999,
+
 ) -> None:
     '''
     Un-gracefully terminate an OS level `trio.Process` after timeout.
@@ -297,23 +294,6 @@ async def hard_kill(
     # zombies (as a feature) we ask the OS to do send in the
     # removal swad as the last resort.
     if cs.cancelled_caught:
-
-        # TODO? attempt at intermediary-rent-sub
-        # with child in debug lock?
-        # |_https://github.com/goodboy/tractor/issues/320
-        #
-        # if not is_root_process():
-        #     log.warning(
-        #         'Attempting to acquire debug-REPL-lock before zombie reap!'
-        #     )
-        #     with trio.CancelScope(shield=True):
-        #         async with debug.acquire_debug_lock(
-        #             subactor_uid=current_actor().uid,
-        #         ) as _ctx:
-        #             log.warning(
-        #                 'Acquired debug lock, child ready to be killed ??\n'
-        #             )
-
         # TODO: toss in the skynet-logo face as ascii art?
         log.critical(
             # 'Well, the #ZOMBIE_LORD_IS_HERE# to collect\n'
@@ -344,21 +324,20 @@ async def soft_kill(
     see `.hard_kill()`).
 
     '''
-    chan: Channel = portal.channel
+    uid: tuple[str, str] = portal.channel.uid
-    peer_aid: msgtypes.Aid = chan.aid
     try:
         log.cancel(
             f'Soft killing sub-actor via portal request\n'
             f'\n'
-            f'c)=> {peer_aid.reprol()}@[{chan.maddr}]\n'
+            f'(c=> {portal.chan.uid}\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 debug.maybe_wait_for_debugger(
+            await maybe_wait_for_debugger(
                 child_in_debug=_runtime_vars.get(
                     '_debug_mode', False
                 ),
@@ -399,7 +378,7 @@ async def soft_kill(
             if proc.poll() is None:  # type: ignore
                 log.warning(
                     'Subactor still alive after cancel request?\n\n'
-                    f'uid: {peer_aid}\n'
+                    f'uid: {uid}\n'
                     f'|_{proc}\n'
                 )
                 n.cancel_scope.cancel()
@@ -413,15 +392,14 @@ async def new_proc(
     errors: dict[tuple[str, str], Exception],
 
     # passed through to actor main
-    bind_addrs: list[UnwrappedAddress],
+    bind_addrs: list[tuple[str, int]],
-    parent_addr: UnwrappedAddress,
+    parent_addr: tuple[str, int],
     _runtime_vars: dict[str, Any],  # serialized and sent to _child
 
     *,
 
     infect_asyncio: bool = False,
-    task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED,
+    task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED
-    proc_kwargs: dict[str, any] = {}
 
 ) -> None:
 
@@ -441,7 +419,6 @@ async def new_proc(
         _runtime_vars,  # run time vars
         infect_asyncio=infect_asyncio,
         task_status=task_status,
-        proc_kwargs=proc_kwargs
     )
 
 
@@ -452,13 +429,12 @@ async def trio_proc(
     errors: dict[tuple[str, str], Exception],
 
     # passed through to actor main
-    bind_addrs: list[UnwrappedAddress],
+    bind_addrs: list[tuple[str, int]],
-    parent_addr: UnwrappedAddress,
+    parent_addr: tuple[str, int],
     _runtime_vars: dict[str, Any],  # serialized and sent to _child
     *,
     infect_asyncio: bool = False,
-    task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED,
+    task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED
-    proc_kwargs: dict[str, any] = {}
 
 ) -> None:
     '''
@@ -480,9 +456,6 @@ async def trio_proc(
         # the OS; it otherwise can be passed via the parent channel if
         # we prefer in the future (for privacy).
         "--uid",
-        # TODO, how to pass this over "wire" encodings like
-        # cmdline args?
-        # -[ ] maybe we can add an `msgtypes.Aid.min_tuple()` ?
         str(subactor.uid),
         # Address the child must connect to on startup
         "--parent_addr",
@@ -500,20 +473,18 @@ async def trio_proc(
 
     cancelled_during_spawn: bool = False
     proc: trio.Process|None = None
-    ipc_server: _server.Server = actor_nursery._actor.ipc_server
     try:
         try:
-            proc: trio.Process = await trio.lowlevel.open_process(spawn_cmd, **proc_kwargs)
+            proc: trio.Process = await trio.lowlevel.open_process(spawn_cmd)
             log.runtime(
-                f'Started new child subproc\n'
+                'Started new child\n'
-                f'(>\n'
+                f'|_{proc}\n'
-                f' |_{proc}\n'
             )
 
             # wait for actor to spawn and connect back to us
             # channel should have handshake completed by the
             # local actor by the time we get a ref to it
-            event, chan = await ipc_server.wait_for_peer(
+            event, chan = await actor_nursery._actor.wait_for_peer(
                 subactor.uid
             )
 
@@ -525,10 +496,10 @@ async def trio_proc(
                 with trio.CancelScope(shield=True):
                     # don't clobber an ongoing pdb
                     if is_root_process():
-                        await debug.maybe_wait_for_debugger()
+                        await maybe_wait_for_debugger()
 
                     elif proc is not None:
-                        async with debug.acquire_debug_lock(subactor.uid):
+                        async with acquire_debug_lock(subactor.uid):
                             # soft wait on the proc to terminate
                             with trio.move_on_after(0.5):
                                 await proc.wait()
@@ -546,20 +517,15 @@ async def trio_proc(
 
         # send a "spawning specification" which configures the
         # initial runtime state of the child.
-        sspec = msgtypes.SpawnSpec(
+        await chan.send(
-            _parent_main_data=subactor._parent_main_data,
+            SpawnSpec(
-            enable_modules=subactor.enable_modules,
+                _parent_main_data=subactor._parent_main_data,
-            reg_addrs=subactor.reg_addrs,
+                enable_modules=subactor.enable_modules,
-            bind_addrs=bind_addrs,
+                reg_addrs=subactor.reg_addrs,
-            _runtime_vars=_runtime_vars,
+                bind_addrs=bind_addrs,
+                _runtime_vars=_runtime_vars,
+            )
         )
-        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
         curr_actor: Actor = current_actor()
@@ -586,7 +552,7 @@ async def trio_proc(
             # condition.
             await soft_kill(
                 proc,
-                trio.Process.wait,  # XXX, uses `pidfd_open()` below.
+                trio.Process.wait,
                 portal
             )
 
@@ -594,7 +560,8 @@ async def trio_proc(
             # tandem if not done already
             log.cancel(
                 'Cancelling portal result reaper task\n'
-                f'c)> {subactor.aid.reprol()!r}\n'
+                f'>c)\n'
+                f' |_{subactor.uid}\n'
             )
             nursery.cancel_scope.cancel()
 
@@ -603,24 +570,21 @@ 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'{reap_repr}'
+                f'>x)\n'
+                f' |_{subactor}@{subactor.uid}\n'
             )
 
             with trio.CancelScope(shield=True):
                 # don't clobber an ongoing pdb
                 if cancelled_during_spawn:
                     # Try again to avoid TTY clobbering.
-                    async with debug.acquire_debug_lock(subactor.uid):
+                    async with acquire_debug_lock(subactor.uid):
                         with trio.move_on_after(0.5):
                             await proc.wait()
 
-                await debug.maybe_wait_for_debugger(
+                await maybe_wait_for_debugger(
                     child_in_debug=_runtime_vars.get(
                         '_debug_mode', False
                     ),
@@ -649,7 +613,7 @@ 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 debug.acquire_debug_lock(this_uid)
+                # await acquire_debug_lock(this_uid)
 
                 if proc.poll() is None:
                     log.cancel(f"Attempting to hard kill {proc}")
@@ -671,13 +635,12 @@ async def mp_proc(
     subactor: Actor,
     errors: dict[tuple[str, str], Exception],
     # passed through to actor main
-    bind_addrs: list[UnwrappedAddress],
+    bind_addrs: list[tuple[str, int]],
-    parent_addr: UnwrappedAddress,
+    parent_addr: tuple[str, int],
     _runtime_vars: dict[str, Any],  # serialized and sent to _child
     *,
     infect_asyncio: bool = False,
-    task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED,
+    task_status: TaskStatus[Portal] = trio.TASK_STATUS_IGNORED
-    proc_kwargs: dict[str, any] = {}
 
 ) -> None:
 
@@ -752,14 +715,12 @@ async def mp_proc(
 
     log.runtime(f"Started {proc}")
 
-    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
         # local actor by the time we get a ref to it
-        event, chan = await ipc_server.wait_for_peer(
+        event, chan = await actor_nursery._actor.wait_for_peer(
-            subactor.uid,
+            subactor.uid)
-        )
 
         # XXX: monkey patch poll API to match the ``subprocess`` API..
         # not sure why they don't expose this but kk.

tractor/_state.py

@@ -14,19 +14,16 @@
 # You should have received a copy of the GNU Affero General Public License
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
-'''
+"""
-Per actor-process runtime state mgmt APIs.
+Per process state
 
-'''
+"""
 from __future__ import annotations
 from contextvars import (
     ContextVar,
 )
-import os
-from pathlib import Path
 from typing import (
     Any,
-    Literal,
     TYPE_CHECKING,
 )
 
@@ -37,39 +34,20 @@ if TYPE_CHECKING:
     from ._context import Context
 
 
-# default IPC transport protocol settings
-TransportProtocolKey = Literal[
-    'tcp',
-    'uds',
-]
-_def_tpt_proto: TransportProtocolKey = 'tcp'
-
 _current_actor: Actor|None = None  # type: ignore # noqa
 _last_actor_terminated: Actor|None = None
 
 # TODO: mk this a `msgspec.Struct`!
-# -[ ] type out all fields obvi!
-# -[ ] (eventually) mk wire-ready for monitoring?
 _runtime_vars: dict[str, Any] = {
-    # root of actor-process tree info
+    '_debug_mode': False,
-    '_is_root': False,  # bool
+    '_is_root': False,
-    '_root_mailbox': (None, None),  # tuple[str|None, str|None]
+    '_root_mailbox': (None, None),
-    '_root_addrs': [],  # tuple[str|None, str|None]
-
-    # parent->chld ipc protocol caps
-    '_enable_tpts': [_def_tpt_proto],
-
-    # registrar info
     '_registry_addrs': [],
 
-    # `debug_mode: bool` settings
+    '_is_infected_aio': False,
-    '_debug_mode': False,  # bool
+
-    'repl_fixture': False,  # |AbstractContextManager[bool]
     # for `tractor.pause_from_sync()` & `breakpoint()` support
     'use_greenback': False,
-
-    # infected-`asyncio`-mode: `trio` running as guest.
-    '_is_infected_aio': False,
 }
 
 
@@ -121,7 +99,7 @@ def current_actor(
     return _current_actor
 
 
-def is_root_process() -> bool:
+def is_main_process() -> bool:
     '''
     Bool determining if this actor is running in the top-most process.
 
@@ -130,10 +108,8 @@ def is_root_process() -> bool:
     return mp.current_process().name == 'MainProcess'
 
 
-is_main_process = is_root_process
+# TODO, more verby name?
-
+def debug_mode() -> bool:
-
-def is_debug_mode() -> bool:
     '''
     Bool determining if "debug mode" is on which enables
     remote subactor pdb entry on crashes.
@@ -142,9 +118,6 @@ def is_debug_mode() -> bool:
     return bool(_runtime_vars['_debug_mode'])
 
 
-debug_mode = is_debug_mode
-
-
 def is_root_process() -> bool:
     return _runtime_vars['_is_root']
 
@@ -170,34 +143,3 @@ def current_ipc_ctx(
             f'|_{current_task()}\n'
         )
     return ctx
-
-
-# std ODE (mutable) app state location
-_rtdir: Path = Path(os.environ['XDG_RUNTIME_DIR'])
-
-
-def get_rt_dir(
-    subdir: str = 'tractor'
-) -> Path:
-    '''
-    Return the user "runtime dir" where most userspace apps stick
-    their IPC and cache related system util-files; we take hold
-    of a `'XDG_RUNTIME_DIR'/tractor/` subdir by default.
-
-    '''
-    rtdir: Path = _rtdir / subdir
-    if not rtdir.is_dir():
-        rtdir.mkdir()
-    return rtdir
-
-
-def current_ipc_protos() -> list[str]:
-    '''
-    Return the list of IPC transport protocol keys currently
-    in use by this actor.
-
-    The keys are as declared by `MsgTransport` and `Address`
-    concrete-backend sub-types defined throughout `tractor.ipc`.
-
-    '''
-    return _runtime_vars['_enable_tpts']

tractor/_streaming.py

@@ -56,7 +56,7 @@ from tractor.msg import (
 if TYPE_CHECKING:
     from ._runtime import Actor
     from ._context import Context
-    from .ipc import Channel
+    from ._ipc import Channel
 
 
 log = get_logger(__name__)
@@ -426,8 +426,8 @@ class MsgStream(trio.abc.Channel):
             self._closed = re
 
         # if caught_eoc:
-        #     # from .devx import debug
+        #     # from .devx import _debug
-        #     # await debug.pause()
+        #     # await _debug.pause()
         #     with trio.CancelScope(shield=True):
         #         await rx_chan.aclose()
 
@@ -437,23 +437,22 @@ class MsgStream(trio.abc.Channel):
             message: str = (
                 f'Stream self-closed by {this_side!r}-side before EoC from {peer_side!r}\n'
                 # } bc a stream is a "scope"/msging-phase inside an IPC
-                f'c}}>\n'
+                f'x}}>\n'
                 f'  |_{self}\n'
             )
+            log.cancel(message)
+            self._eoc = trio.EndOfChannel(message)
+
             if (
                 (rx_chan := self._rx_chan)
                 and
                 (stats := rx_chan.statistics()).tasks_waiting_receive
             ):
-                message += (
+                log.cancel(
-                    f'AND there is still reader tasks,\n'
+                    f'Msg-stream is closing but there is still reader tasks,\n'
-                    f'\n'
                     f'{stats}\n'
                 )
 
-            log.cancel(message)
-            self._eoc = trio.EndOfChannel(message)
-
         # ?XXX WAIT, why do we not close the local mem chan `._rx_chan` XXX?
         # => NO, DEFINITELY NOT! <=
         # if we're a bi-dir `MsgStream` BECAUSE this same
@@ -596,17 +595,8 @@ class MsgStream(trio.abc.Channel):
             trio.ClosedResourceError,
             trio.BrokenResourceError,
             BrokenPipeError,
-        ) as _trans_err:
+        ) as trans_err:
-            trans_err = _trans_err
+            if hide_tb:
-            if (
-                hide_tb
-                and
-                self._ctx.chan._exc is trans_err
-                # ^XXX, IOW, only if the channel is marked errored
-                # for the same reason as whatever its underlying
-                # transport raised, do we keep the full low-level tb
-                # suppressed from the user.
-            ):
                 raise type(trans_err)(
                     *trans_err.args
                 ) from trans_err
@@ -812,12 +802,13 @@ async def open_stream_from_ctx(
                 # sanity, can remove?
                 assert eoc is stream._eoc
 
-                log.runtime(
+                log.warning(
                     'Stream was terminated by EoC\n\n'
                     # NOTE: won't show the error <Type> but
                     # does show txt followed by IPC msg.
                     f'{str(eoc)}\n'
                 )
+
         finally:
             if ctx._portal:
                 try:

tractor/_supervise.py

@@ -21,49 +21,34 @@
 from contextlib import asynccontextmanager as acm
 from functools import partial
 import inspect
-from typing import (
+from pprint import pformat
-    TYPE_CHECKING,
+from typing import TYPE_CHECKING
-)
 import typing
 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,
-)
 from ._state import current_actor, is_main_process
 from .log import get_logger, get_loglevel
 from ._runtime import Actor
 from ._portal import Portal
-from .trionics import (
-    is_multi_cancelled,
-    collapse_eg,
-)
 from ._exceptions import (
+    is_multi_cancelled,
     ContextCancelled,
 )
-from ._root import (
+from ._root import open_root_actor
-    open_root_actor,
-)
 from . import _state
 from . import _spawn
 
 
 if TYPE_CHECKING:
     import multiprocessing as mp
-    # from .ipc._server import IPCServer
-    from .ipc import IPCServer
-
 
 log = get_logger(__name__)
 
+_default_bind_addr: tuple[str, int] = ('127.0.0.1', 0)
+
 
 class ActorNursery:
     '''
@@ -117,6 +102,7 @@ class ActorNursery:
             ]
         ] = {}
 
+        self.cancelled: bool = False
         self._join_procs = trio.Event()
         self._at_least_one_child_in_debug: bool = False
         self.errors = errors
@@ -134,62 +120,18 @@ 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,
 
         *,
 
-        bind_addrs: list[UnwrappedAddress]|None = None,
+        bind_addrs: list[tuple[str, int]] = [_default_bind_addr],
         rpc_module_paths: list[str]|None = None,
-        enable_transports: list[str] = [_state._def_tpt_proto],
         enable_modules: list[str]|None = None,
         loglevel: str|None = None,  # set log level per subactor
         debug_mode: bool|None = None,
@@ -199,7 +141,6 @@ class ActorNursery:
         # a `._ria_nursery` since the dependent APIs have been
         # removed!
         nursery: trio.Nursery|None = None,
-        proc_kwargs: dict[str, any] = {}
 
     ) -> Portal:
         '''
@@ -236,17 +177,15 @@ class ActorNursery:
             enable_modules.extend(rpc_module_paths)
 
         subactor = Actor(
-            name=name,
+            name,
-            uuid=mk_uuid(),
-
             # modules allowed to invoked funcs from
             enable_modules=enable_modules,
             loglevel=loglevel,
 
             # verbatim relay this actor's registrar addresses
-            registry_addrs=current_actor().registry_addrs,
+            registry_addrs=current_actor().reg_addrs,
         )
-        parent_addr: UnwrappedAddress = self._actor.accept_addr
+        parent_addr = self._actor.accept_addr
         assert parent_addr
 
         # start a task to spawn a process
@@ -265,7 +204,6 @@ class ActorNursery:
                 parent_addr,
                 _rtv,  # run time vars
                 infect_asyncio=infect_asyncio,
-                proc_kwargs=proc_kwargs
             )
         )
 
@@ -284,12 +222,11 @@ class ActorNursery:
         *,
 
         name: str | None = None,
-        bind_addrs: UnwrappedAddress|None = None,
+        bind_addrs: tuple[str, int] = [_default_bind_addr],
         rpc_module_paths: list[str] | None = None,
         enable_modules: list[str] | None = None,
         loglevel: str | None = None,  # set log level per subactor
         infect_asyncio: bool = False,
-        proc_kwargs: dict[str, any] = {},
 
         **kwargs,  # explicit args to ``fn``
 
@@ -320,7 +257,6 @@ class ActorNursery:
             # use the run_in_actor nursery
             nursery=self._ria_nursery,
             infect_asyncio=infect_asyncio,
-            proc_kwargs=proc_kwargs
         )
 
         # XXX: don't allow stream funcs
@@ -358,21 +294,15 @@ class ActorNursery:
 
         '''
         __runtimeframe__: int = 1  # noqa
-        self._cancel_called = True
+        self.cancelled = True
 
         # TODO: impl a repr for spawn more compact
         # then `._children`..
         children: dict = self._children
         child_count: int = len(children)
         msg: str = f'Cancelling actor nursery with {child_count} children\n'
-
-        server: IPCServer = self._actor.ipc_server
-
         with trio.move_on_after(3) as cs:
-            async with (
+            async with trio.open_nursery() as tn:
-                collapse_eg(),
-                trio.open_nursery() as tn,
-            ):
 
                 subactor: Actor
                 proc: trio.Process
@@ -391,7 +321,7 @@ class ActorNursery:
 
                     else:
                         if portal is None:  # actor hasn't fully spawned yet
-                            event: trio.Event = server._peer_connected[subactor.uid]
+                            event = self._actor._peer_connected[subactor.uid]
                             log.warning(
                                 f"{subactor.uid} never 't finished spawning?"
                             )
@@ -407,7 +337,7 @@ class ActorNursery:
                             if portal is None:
                                 # cancelled while waiting on the event
                                 # to arrive
-                                chan = server._peers[subactor.uid][-1]
+                                chan = self._actor._peers[subactor.uid][-1]
                                 if chan:
                                     portal = Portal(chan)
                                 else:  # there's no other choice left
@@ -436,8 +366,6 @@ 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()
@@ -446,12 +374,12 @@ class ActorNursery:
 @acm
 async def _open_and_supervise_one_cancels_all_nursery(
     actor: Actor,
-    hide_tb: bool = True,
+    tb_hide: bool = False,
 
 ) -> typing.AsyncGenerator[ActorNursery, None]:
 
     # normally don't need to show user by default
-    __tracebackhide__: bool = hide_tb
+    __tracebackhide__: bool = tb_hide
 
     outer_err: BaseException|None = None
     inner_err: BaseException|None = None
@@ -467,10 +395,10 @@ async def _open_and_supervise_one_cancels_all_nursery(
     # `ActorNursery.start_actor()`).
 
     # errors from this daemon actor nursery bubble up to caller
-    async with (
+    async with trio.open_nursery(
-        collapse_eg(),
+        strict_exception_groups=False,
-        trio.open_nursery() as da_nursery,
+        # ^XXX^ TODO? instead unpack any RAE as per "loose" style?
-    ):
+    ) as da_nursery:
         try:
             # This is the inner level "run in actor" nursery. It is
             # awaited first since actors spawned in this way (using
@@ -480,10 +408,11 @@ 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 (
+            async with trio.open_nursery(
-                collapse_eg(),
+                strict_exception_groups=False,
-                trio.open_nursery() as ria_nursery,
+                # ^XXX^ TODO? instead unpack any RAE as per "loose" style?
-            ):
+            ) as ria_nursery:
+
                 an = ActorNursery(
                     actor,
                     ria_nursery,
@@ -500,7 +429,7 @@ async def _open_and_supervise_one_cancels_all_nursery(
                     # the "hard join phase".
                     log.runtime(
                         'Waiting on subactors to complete:\n'
-                        f'>}} {len(an._children)}\n'
+                        f'{pformat(an._children)}\n'
                     )
                     an._join_procs.set()
 
@@ -514,7 +443,7 @@ 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 debug.maybe_wait_for_debugger(
+                    await maybe_wait_for_debugger(
                         child_in_debug=an._at_least_one_child_in_debug
                     )
 
@@ -590,7 +519,7 @@ 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 debug.maybe_wait_for_debugger(
+            await maybe_wait_for_debugger(
                 child_in_debug=an._at_least_one_child_in_debug
             )
 
@@ -639,15 +568,9 @@ async def _open_and_supervise_one_cancels_all_nursery(
     # final exit
 
 
-_shutdown_msg: str = (
-    'Actor-runtime-shutdown'
-)
-
-
 @acm
 # @api_frame
 async def open_nursery(
-    *,  # named params only!
     hide_tb: bool = True,
     **kwargs,
     # ^TODO, paramspec for `open_root_actor()`
@@ -732,26 +655,17 @@ async def open_nursery(
         ):
             __tracebackhide__: bool = False
 
-
+        msg: str = (
-        op_nested_an_repr: str = _pformat.nest_from_op(
+            'Actor-nursery exited\n'
-            input_op=')>',
+            f'|_{an}\n'
-            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: str = (
+            msg += '=> Shutting down actor runtime <=\n'
-                '\n'
-                '\n'
-                f'{_shutdown_msg} )>\n'
-            )
             log.info(msg)
+
+        else:
+            # keep noise low during std operation.
+            log.runtime(msg)

tractor/_testing/__init__.py

@@ -26,7 +26,7 @@ import os
 import pathlib
 
 import tractor
-from tractor.devx.debug import (
+from tractor.devx._debug import (
     BoxedMaybeException,
 )
 from .pytest import (
@@ -37,9 +37,6 @@ from .fault_simulation import (
 )
 
 
-# TODO, use dulwhich for this instead?
-# -> we're going to likely need it (or something similar)
-#   for supporting hot-coad reload feats eventually anyway!
 def repodir() -> pathlib.Path:
     '''
     Return the abspath to the repo directory.

tractor/_testing/addr.py

@@ -1,70 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-
-'''
-Random IPC addr generation for isolating
-the discovery space between test sessions.
-
-Might be eventually useful to expose as a util set from
-our `tractor.discovery` subsys?
-
-'''
-import random
-from typing import (
-    Type,
-)
-from tractor import (
-    _addr,
-)
-
-
-def get_rando_addr(
-    tpt_proto: str,
-    *,
-
-    # choose random port at import time
-    _rando_port: str = random.randint(1000, 9999)
-
-) -> tuple[str, str|int]:
-    '''
-    Used to globally override the runtime to the
-    per-test-session-dynamic addr so that all tests never conflict
-    with any other actor tree using the default.
-
-    '''
-    addr_type: Type[_addr.Addres] = _addr._address_types[tpt_proto]
-    def_reg_addr: tuple[str, int] = _addr._default_lo_addrs[tpt_proto]
-
-    # this is the "unwrapped" form expected to be passed to
-    # `.open_root_actor()` by test body.
-    testrun_reg_addr: tuple[str, int|str]
-    match tpt_proto:
-        case 'tcp':
-            testrun_reg_addr = (
-                addr_type.def_bindspace,
-                _rando_port,
-            )
-
-        # NOTE, file-name uniqueness (no-collisions) will be based on
-        # the runtime-directory and root (pytest-proc's) pid.
-        case 'uds':
-            testrun_reg_addr = addr_type.get_random().unwrap()
-
-    # XXX, as sanity it should never the same as the default for the
-    # host-singleton registry actor.
-    assert def_reg_addr != testrun_reg_addr
-
-    return testrun_reg_addr

tractor/_testing/pytest.py

@@ -26,46 +26,29 @@ from functools import (
 import inspect
 import platform
 
-import pytest
 import tractor
 import trio
 
 
 def tractor_test(fn):
     '''
-    Decorator for async test fns to decorator-wrap them as "native"
+    Decorator for async test funcs to present them as "native"
-    looking sync funcs runnable by `pytest` and auto invoked with
+    looking sync funcs runnable by `pytest` using `trio.run()`.
-    `trio.run()` (much like the `pytest-trio` plugin's approach).
 
-    Further the test fn body will be invoked AFTER booting the actor
+    Use:
-    runtime, i.e. from inside a `tractor.open_root_actor()` block AND
-    with various runtime and tooling parameters implicitly passed as
-    requested by by the test session's config; see immediately below.
 
-    Basic deco use:
+    @tractor_test
-    ---------------
+    async def test_whatever():
+        await ...
 
-      @tractor_test
+    If fixtures:
-      async def test_whatever():
-          await ...
 
+        - ``reg_addr`` (a socket addr tuple where arbiter is listening)
+        - ``loglevel`` (logging level passed to tractor internals)
+        - ``start_method`` (subprocess spawning backend)
 
-    Runtime config via special fixtures:
+    are defined in the `pytest` fixture space they will be automatically
-    ------------------------------------
+    injected to tests declaring these funcargs.
-    If any of the following fixture are requested by the wrapped test
-    fn (via normal func-args declaration),
-
-    - `reg_addr` (a socket addr tuple where arbiter is listening)
-    - `loglevel` (logging level passed to tractor internals)
-    - `start_method` (subprocess spawning backend)
-
-    (TODO support)
-    - `tpt_proto` (IPC transport protocol key)
-
-    they will be automatically injected to each test as normally
-    expected as well as passed to the initial
-    `tractor.open_root_actor()` funcargs.
-
     '''
     @wraps(fn)
     def wrapper(
@@ -128,164 +111,3 @@ def tractor_test(fn):
         return trio.run(main)
 
     return wrapper
-
-
-def pytest_addoption(
-    parser: pytest.Parser,
-):
-    # parser.addoption(
-    #     "--ll",
-    #     action="store",
-    #     dest='loglevel',
-    #     default='ERROR', help="logging level to set when testing"
-    # )
-
-    parser.addoption(
-        "--spawn-backend",
-        action="store",
-        dest='spawn_backend',
-        default='trio',
-        help="Processing spawning backend to use for test run",
-    )
-
-    parser.addoption(
-        "--tpdb",
-        "--debug-mode",
-        action="store_true",
-        dest='tractor_debug_mode',
-        # default=False,
-        help=(
-            'Enable a flag that can be used by tests to to set the '
-            '`debug_mode: bool` for engaging the internal '
-            'multi-proc debugger sys.'
-        ),
-    )
-
-    # provide which IPC transport protocols opting-in test suites
-    # should accumulatively run against.
-    parser.addoption(
-        "--tpt-proto",
-        nargs='+',  # accumulate-multiple-args
-        action="store",
-        dest='tpt_protos',
-        default=['tcp'],
-        help="Transport protocol to use under the `tractor.ipc.Channel`",
-    )
-
-
-def pytest_configure(config):
-    backend = config.option.spawn_backend
-    tractor._spawn.try_set_start_method(backend)
-
-
-@pytest.fixture(scope='session')
-def debug_mode(request) -> bool:
-    '''
-    Flag state for whether `--tpdb` (for `tractor`-py-debugger)
-    was passed to the test run.
-
-    Normally tests should pass this directly to `.open_root_actor()`
-    to allow the user to opt into suite-wide crash handling.
-
-    '''
-    debug_mode: bool = request.config.option.tractor_debug_mode
-    return debug_mode
-
-
-@pytest.fixture(scope='session')
-def spawn_backend(request) -> str:
-    return request.config.option.spawn_backend
-
-
-@pytest.fixture(scope='session')
-def tpt_protos(request) -> list[str]:
-
-    # allow quoting on CLI
-    proto_keys: list[str] = [
-        proto_key.replace('"', '').replace("'", "")
-        for proto_key in request.config.option.tpt_protos
-    ]
-
-    # ?TODO, eventually support multiple protos per test-sesh?
-    if len(proto_keys) > 1:
-        pytest.fail(
-            'We only support one `--tpt-proto <key>` atm!\n'
-        )
-
-    # XXX ensure we support the protocol by name via lookup!
-    for proto_key in proto_keys:
-        addr_type = tractor._addr._address_types[proto_key]
-        assert addr_type.proto_key == proto_key
-
-    yield proto_keys
-
-
-@pytest.fixture(
-    scope='session',
-    autouse=True,
-)
-def tpt_proto(
-    tpt_protos: list[str],
-) -> str:
-    proto_key: str = tpt_protos[0]
-
-    from tractor import _state
-    if _state._def_tpt_proto != proto_key:
-        _state._def_tpt_proto = proto_key
-
-    yield proto_key
-
-
-@pytest.fixture(scope='session')
-def reg_addr(
-    tpt_proto: str,
-) -> tuple[str, int|str]:
-    '''
-    Deliver a test-sesh unique registry address such
-    that each run's (tests which use this fixture) will
-    have no conflicts/cross-talk when running simultaneously
-    nor will interfere with other live `tractor` apps active
-    on the same network-host (namespace).
-
-    '''
-    from tractor._testing.addr import get_rando_addr
-    return get_rando_addr(
-        tpt_proto=tpt_proto,
-    )
-
-
-def pytest_generate_tests(
-    metafunc: pytest.Metafunc,
-):
-    spawn_backend: str = metafunc.config.option.spawn_backend
-
-    if not spawn_backend:
-        # XXX some weird windows bug with `pytest`?
-        spawn_backend = 'trio'
-
-    # TODO: maybe just use the literal `._spawn.SpawnMethodKey`?
-    assert spawn_backend in (
-        'mp_spawn',
-        'mp_forkserver',
-        'trio',
-    )
-
-    # NOTE: used-to-be-used-to dyanmically parametrize tests for when
-    # you just passed --spawn-backend=`mp` on the cli, but now we expect
-    # that cli input to be manually specified, BUT, maybe we'll do
-    # something like this again in the future?
-    if 'start_method' in metafunc.fixturenames:
-        metafunc.parametrize(
-            "start_method",
-            [spawn_backend],
-            scope='module',
-        )
-
-    # TODO, parametrize any `tpt_proto: str` declaring tests!
-    # proto_tpts: list[str] = metafunc.config.option.proto_tpts
-    # if 'tpt_proto' in metafunc.fixturenames:
-    #     metafunc.parametrize(
-    #         'tpt_proto',
-    #         proto_tpts,  # TODO, double check this list usage!
-    #         scope='module',
-    #     )

tractor/_testing/samples.py

@@ -1,35 +0,0 @@
-import os
-import random
-
-
-def generate_sample_messages(
-    amount: int,
-    rand_min: int = 0,
-    rand_max: int = 0,
-    silent: bool = False
-) -> tuple[list[bytes], int]:
-
-    msgs = []
-    size = 0
-
-    if not silent:
-        print(f'\ngenerating {amount} messages...')
-
-    for i in range(amount):
-        msg = f'[{i:08}]'.encode('utf-8')
-
-        if rand_max > 0:
-            msg += os.urandom(
-                random.randint(rand_min, rand_max))
-
-        size += len(msg)
-
-        msgs.append(msg)
-
-        if not silent and i and i % 10_000 == 0:
-            print(f'{i} generated')
-
-    if not silent:
-        print(f'done, {size:,} bytes in total')
-
-    return msgs, size

tractor/devx/__init__.py

@@ -20,7 +20,7 @@ Runtime "developer experience" utils and addons to aid our
 and working with/on the actor runtime.
 
 """
-from .debug import (
+from ._debug import (
     maybe_wait_for_debugger as maybe_wait_for_debugger,
     acquire_debug_lock as acquire_debug_lock,
     breakpoint as breakpoint,

tractor/devx/_frame_stack.py

@@ -20,18 +20,13 @@ as it pertains to improving the grok-ability of our runtime!
 
 '''
 from __future__ import annotations
-from contextlib import (
-    _GeneratorContextManager,
-    _AsyncGeneratorContextManager,
-)
 from functools import partial
 import inspect
-import textwrap
 from types import (
     FrameType,
     FunctionType,
     MethodType,
-    CodeType,
+    # CodeType,
 )
 from typing import (
     Any,
@@ -39,9 +34,6 @@ from typing import (
     Type,
 )
 
-import pdbp
-from tractor.log import get_logger
-import trio
 from tractor.msg import (
     pretty_struct,
     NamespacePath,
@@ -49,8 +41,6 @@ from tractor.msg import (
 import wrapt
 
 
-log = get_logger(__name__)
-
 # TODO: yeah, i don't love this and we should prolly just
 # write a decorator that actually keeps a stupid ref to the func
 # obj..
@@ -311,70 +301,3 @@ def api_frame(
 #     error_set: set[BaseException],
 # ) -> TracebackType:
 #     ...
-
-
-def hide_runtime_frames() -> dict[FunctionType, CodeType]:
-    '''
-    Hide call-stack frames for various std-lib and `trio`-API primitives
-    such that the tracebacks presented from our runtime are as minimized
-    as possible, particularly from inside a `PdbREPL`.
-
-    '''
-    # XXX HACKZONE XXX
-    #  hide exit stack frames on nurseries and cancel-scopes!
-    # |_ so avoid seeing it when the `pdbp` REPL is first engaged from
-    #    inside a `trio.open_nursery()` scope (with no line after it
-    #    in before the block end??).
-    #
-    # TODO: FINALLY got this workin originally with
-    #  `@pdbp.hideframe` around the `wrapper()` def embedded inside
-    #  `_ki_protection_decoratior()`.. which is in the module:
-    #  /home/goodboy/.virtualenvs/tractor311/lib/python3.11/site-packages/trio/_core/_ki.py
-    #
-    # -[ ] make an issue and patch for `trio` core? maybe linked
-    #    to the long outstanding `pdb` one below?
-    #   |_ it's funny that there's frame hiding throughout `._run.py`
-    #      but not where it matters on the below exit funcs..
-    #
-    # -[ ] provide a patchset for the lonstanding
-    #   |_ https://github.com/python-trio/trio/issues/1155
-    #
-    # -[ ] make a linked issue to ^ and propose allowing all the
-    #     `._core._run` code to have their `__tracebackhide__` value
-    #     configurable by a `RunVar` to allow getting scheduler frames
-    #     if desired through configuration?
-    #
-    # -[ ] maybe dig into the core `pdb` issue why the extra frame is shown
-    #      at all?
-    #
-    funcs: list[FunctionType] = [
-        trio._core._run.NurseryManager.__aexit__,
-        trio._core._run.CancelScope.__exit__,
-         _GeneratorContextManager.__exit__,
-         _AsyncGeneratorContextManager.__aexit__,
-         _AsyncGeneratorContextManager.__aenter__,
-         trio.Event.wait,
-    ]
-    func_list_str: str = textwrap.indent(
-        "\n".join(f.__qualname__ for f in funcs),
-        prefix=' |_ ',
-    )
-    log.devx(
-        'Hiding the following runtime frames by default:\n'
-        f'{func_list_str}\n'
-    )
-
-    codes: dict[FunctionType, CodeType] = {}
-    for ref in funcs:
-        # stash a pre-modified version of each ref's code-obj
-        # so it can be reverted later if needed.
-        codes[ref] = ref.__code__
-        pdbp.hideframe(ref)
-    #
-    # pdbp.hideframe(trio._core._run.NurseryManager.__aexit__)
-    # pdbp.hideframe(trio._core._run.CancelScope.__exit__)
-    # pdbp.hideframe(_GeneratorContextManager.__exit__)
-    # pdbp.hideframe(_AsyncGeneratorContextManager.__aexit__)
-    # pdbp.hideframe(_AsyncGeneratorContextManager.__aenter__)
-    # pdbp.hideframe(trio.Event.wait)
-    return codes

tractor/devx/_stackscope.py

@@ -49,7 +49,7 @@ from tractor import (
     _state,
     log as logmod,
 )
-from tractor.devx import debug
+from tractor.devx import _debug
 
 log = logmod.get_logger(__name__)
 
@@ -82,7 +82,7 @@ def dump_task_tree() -> None:
     if (
         current_sigint_handler
         is not
-        debug.DebugStatus._trio_handler
+        _debug.DebugStatus._trio_handler
     ):
         sigint_handler_report: str = (
             'The default `trio` SIGINT handler was replaced?!'
@@ -238,8 +238,7 @@ def enable_stack_on_sig(
         import stackscope
     except ImportError:
         log.warning(
-            'The `stackscope` lib is not installed!\n'
+            '`stackscope` not installed for use in debug mode!'
-            '`Ignoring enable_stack_on_sig() call!\n'
         )
         return None
 
@@ -256,8 +255,8 @@ def enable_stack_on_sig(
         dump_tree_on_sig,
     )
     log.devx(
-        f'Enabling trace-trees on `SIGUSR1` '
+        'Enabling trace-trees on `SIGUSR1` '
-        f'since `stackscope` is installed @ \n'
+        'since `stackscope` is installed @ \n'
         f'{stackscope!r}\n\n'
         f'With `SIGUSR1` handler\n'
         f'|_{dump_tree_on_sig}\n'

tractor/devx/debug/__init__.py

@@ -1,100 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or
-# modify it under the terms of the GNU Affero General Public License
-# as published by the Free Software Foundation, either version 3 of
-# the License, or (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful, but
-# WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-# Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public
-# License along with this program.  If not, see
-# <https://www.gnu.org/licenses/>.
-
-'''
-Multi-actor debugging for da peeps!
-
-'''
-from __future__ import annotations
-from tractor.log import get_logger
-from ._repl import (
-    PdbREPL as PdbREPL,
-    mk_pdb as mk_pdb,
-    TractorConfig as TractorConfig,
-)
-from ._tty_lock import (
-    DebugStatus as DebugStatus,
-    DebugStateError as DebugStateError,
-)
-from ._trace import (
-    Lock as Lock,
-    _pause_msg as _pause_msg,
-    _repl_fail_msg as _repl_fail_msg,
-    _set_trace as _set_trace,
-    _sync_pause_from_builtin as _sync_pause_from_builtin,
-    breakpoint as breakpoint,
-    maybe_init_greenback as maybe_init_greenback,
-    maybe_import_greenback as maybe_import_greenback,
-    pause as pause,
-    pause_from_sync as pause_from_sync,
-)
-from ._post_mortem import (
-    BoxedMaybeException as BoxedMaybeException,
-    maybe_open_crash_handler as maybe_open_crash_handler,
-    open_crash_handler as open_crash_handler,
-    post_mortem as post_mortem,
-    _crash_msg as _crash_msg,
-    _maybe_enter_pm as _maybe_enter_pm,
-)
-from ._sync import (
-    maybe_wait_for_debugger as maybe_wait_for_debugger,
-    acquire_debug_lock as acquire_debug_lock,
-)
-from ._sigint import (
-    sigint_shield as sigint_shield,
-    _ctlc_ignore_header as _ctlc_ignore_header
-)
-
-log = get_logger(__name__)
-
-# ----------------
-# XXX PKG TODO XXX
-# ----------------
-# refine the internal impl and APIs!
-#
-# -[ ] rework `._pause()` and it's branch-cases for root vs.
-#     subactor:
-#  -[ ] `._pause_from_root()` + `_pause_from_subactor()`?
-#  -[ ]  do the de-factor based on bg-thread usage in
-#    `.pause_from_sync()` & `_pause_from_bg_root_thread()`.
-#  -[ ] drop `debug_func == None` case which is confusing af..
-#  -[ ]  factor out `_enter_repl_sync()` into a util func for calling
-#    the `_set_trace()` / `_post_mortem()` APIs?
-#
-# -[ ] figure out if we need `acquire_debug_lock()` and/or re-implement
-#    it as part of the `.pause_from_sync()` rework per above?
-#
-# -[ ] pair the `._pause_from_subactor()` impl with a "debug nursery"
-#   that's dynamically allocated inside the `._rpc` task thus
-#   avoiding the `._service_n.start()` usage for the IPC request?
-#  -[ ] see the TODO inside `._rpc._errors_relayed_via_ipc()`
-#
-# -[ ] impl a `open_debug_request()` which encaps all
-#   `request_root_stdio_lock()` task scheduling deats
-#   + `DebugStatus` state mgmt; which should prolly be re-branded as
-#   a `DebugRequest` type anyway AND with suppoort for bg-thread
-#   (from root actor) usage?
-#
-# -[ ] handle the `xonsh` case for bg-root-threads in the SIGINT
-#     handler!
-#   -[ ] do we need to do the same for subactors?
-#   -[ ] make the failing tests finally pass XD
-#
-# -[ ] simplify `maybe_wait_for_debugger()` to be a root-task only
-#     API?
-#   -[ ] currently it's implemented as that so might as well make it
-#     formal?

tractor/devx/debug/_post_mortem.py

@@ -1,412 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or
-# modify it under the terms of the GNU Affero General Public License
-# as published by the Free Software Foundation, either version 3 of
-# the License, or (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful, but
-# WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-# Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public
-# License along with this program.  If not, see
-# <https://www.gnu.org/licenses/>.
-
-'''
-Post-mortem debugging APIs and surrounding machinery for both
-sync and async contexts.
-
-Generally we maintain the same semantics a `pdb.post.mortem()` but
-with actor-tree-wide sync/cooperation around any (sub)actor's use of
-the root's TTY.
-
-'''
-from __future__ import annotations
-import bdb
-from contextlib import (
-    AbstractContextManager,
-    contextmanager as cm,
-    nullcontext,
-)
-from functools import (
-    partial,
-)
-import inspect
-import sys
-import traceback
-from typing import (
-    Callable,
-    Sequence,
-    Type,
-    TYPE_CHECKING,
-)
-from types import (
-    TracebackType,
-    FrameType,
-)
-
-from msgspec import Struct
-import trio
-from tractor._exceptions import (
-    NoRuntime,
-)
-from tractor import _state
-from tractor._state import (
-    current_actor,
-    debug_mode,
-)
-from tractor.log import get_logger
-from tractor.trionics import (
-    is_multi_cancelled,
-)
-from ._trace import (
-    _pause,
-)
-from ._tty_lock import (
-    DebugStatus,
-)
-from ._repl import (
-    PdbREPL,
-    mk_pdb,
-    TractorConfig as TractorConfig,
-)
-
-if TYPE_CHECKING:
-    from trio.lowlevel import Task
-    from tractor._runtime import (
-        Actor,
-    )
-
-_crash_msg: str = (
-    'Opening a pdb REPL in crashed actor'
-)
-
-log = get_logger(__package__)
-
-
-class BoxedMaybeException(Struct):
-    '''
-    Box a maybe-exception for post-crash introspection usage
-    from the body of a `open_crash_handler()` scope.
-
-    '''
-    value: BaseException|None = None
-
-    # handler can suppress crashes dynamically
-    raise_on_exit: bool|Sequence[Type[BaseException]] = True
-
-    def pformat(self) -> str:
-        '''
-        Repr the boxed `.value` error in more-than-string
-        repr form.
-
-        '''
-        if not self.value:
-            return f'<{type(self).__name__}( .value=None )>'
-
-        return (
-            f'<{type(self.value).__name__}(\n'
-            f' |_.value = {self.value}\n'
-            f')>\n'
-        )
-
-    __repr__ = pformat
-
-
-def _post_mortem(
-    repl: PdbREPL,  # normally passed by `_pause()`
-
-    # XXX all `partial`-ed in by `post_mortem()` below!
-    tb: TracebackType,
-    api_frame: FrameType,
-
-    shield: bool = False,
-    hide_tb: bool = True,
-
-    # maybe pre/post REPL entry
-    repl_fixture: (
-        AbstractContextManager[bool]
-        |None
-    ) = None,
-
-    boxed_maybe_exc: BoxedMaybeException|None = None,
-
-) -> None:
-    '''
-    Enter the ``pdbpp`` port mortem entrypoint using our custom
-    debugger instance.
-
-    '''
-    __tracebackhide__: bool = hide_tb
-
-    # maybe enter any user fixture
-    enter_repl: bool = DebugStatus.maybe_enter_repl_fixture(
-        repl=repl,
-        repl_fixture=repl_fixture,
-        boxed_maybe_exc=boxed_maybe_exc,
-    )
-    try:
-        if not enter_repl:
-            # XXX, trigger `.release()` below immediately!
-            return
-        try:
-            actor: Actor = current_actor()
-            actor_repr: str = str(actor.uid)
-            # ^TODO, instead a nice runtime-info + maddr + uid?
-            # -[ ] impl a `Actor.__repr()__`??
-            #  |_ <task>:<thread> @ <actor>
-
-        except NoRuntime:
-            actor_repr: str = '<no-actor-runtime?>'
-
-        try:
-            task_repr: Task = trio.lowlevel.current_task()
-        except RuntimeError:
-            task_repr: str = '<unknown-Task>'
-
-        # TODO: print the actor supervion tree up to the root
-        # here! Bo
-        log.pdb(
-            f'{_crash_msg}\n'
-            f'x>(\n'
-            f' |_ {task_repr} @ {actor_repr}\n'
-
-        )
-
-        # XXX NOTE(s) on `pdbp.xpm()` version..
-        #
-        # - seems to lose the up-stack tb-info?
-        # - currently we're (only) replacing this from `pdbp.xpm()`
-        #   to add the `end=''` to the print XD
-        #
-        print(traceback.format_exc(), end='')
-        caller_frame: FrameType = api_frame.f_back
-
-        # NOTE, see the impl details of these in the lib to
-        # understand usage:
-        # - `pdbp.post_mortem()`
-        # - `pdbp.xps()`
-        # - `bdb.interaction()`
-        repl.reset()
-        repl.interaction(
-            frame=caller_frame,
-            # frame=None,
-            traceback=tb,
-        )
-    finally:
-        # XXX NOTE XXX: this is abs required to avoid hangs!
-        #
-        # Since we presume the post-mortem was enaged to
-        # a task-ending error, we MUST release the local REPL request
-        # so that not other local task nor the root remains blocked!
-        DebugStatus.release()
-
-
-async def post_mortem(
-    *,
-    tb: TracebackType|None = None,
-    api_frame: FrameType|None = None,
-    hide_tb: bool = False,
-
-    # TODO: support shield here just like in `pause()`?
-    # shield: bool = False,
-
-    **_pause_kwargs,
-
-) -> None:
-    '''
-    Our builtin async equivalient of `pdb.post_mortem()` which can be
-    used inside exception handlers.
-
-    It's also used for the crash handler when `debug_mode == True` ;)
-
-    '''
-    __tracebackhide__: bool = hide_tb
-
-    tb: TracebackType = tb or sys.exc_info()[2]
-
-    # TODO: do upward stack scan for highest @api_frame and
-    # use its parent frame as the expected user-app code
-    # interact point.
-    api_frame: FrameType = api_frame or inspect.currentframe()
-
-    # TODO, move to submod `._pausing` or ._api? _trace
-    await _pause(
-        debug_func=partial(
-            _post_mortem,
-            api_frame=api_frame,
-            tb=tb,
-        ),
-        hide_tb=hide_tb,
-        **_pause_kwargs
-    )
-
-
-async def _maybe_enter_pm(
-    err: BaseException,
-    *,
-    tb: TracebackType|None = None,
-    api_frame: FrameType|None = None,
-    hide_tb: bool = True,
-
-    # only enter debugger REPL when returns `True`
-    debug_filter: Callable[
-        [BaseException|BaseExceptionGroup],
-        bool,
-    ] = lambda err: not is_multi_cancelled(err),
-    **_pause_kws,
-):
-    if (
-        debug_mode()
-
-        # NOTE: don't enter debug mode recursively after quitting pdb
-        # Iow, don't re-enter the repl if the `quit` command was issued
-        # by the user.
-        and not isinstance(err, bdb.BdbQuit)
-
-        # XXX: if the error is the likely result of runtime-wide
-        # cancellation, we don't want to enter the debugger since
-        # there's races between when the parent actor has killed all
-        # comms and when the child tries to contact said parent to
-        # acquire the tty lock.
-
-        # Really we just want to mostly avoid catching KBIs here so there
-        # might be a simpler check we can do?
-        and
-        debug_filter(err)
-    ):
-        api_frame: FrameType = api_frame or inspect.currentframe()
-        tb: TracebackType = tb or sys.exc_info()[2]
-        await post_mortem(
-            api_frame=api_frame,
-            tb=tb,
-            **_pause_kws,
-        )
-        return True
-
-    else:
-        return False
-
-
-# TODO: better naming and what additionals?
-# - [ ] optional runtime plugging?
-# - [ ] detection for sync vs. async code?
-# - [ ] specialized REPL entry when in distributed mode?
-# -[x] hide tb by def
-# - [x] allow ignoring kbi Bo
-@cm
-def open_crash_handler(
-    catch: set[BaseException] = {
-        BaseException,
-    },
-    ignore: set[BaseException] = {
-        KeyboardInterrupt,
-        trio.Cancelled,
-    },
-    hide_tb: bool = True,
-
-    repl_fixture: (
-        AbstractContextManager[bool]  # pre/post REPL entry
-        |None
-    ) = None,
-    raise_on_exit: bool|Sequence[Type[BaseException]] = True,
-):
-    '''
-    Generic "post mortem" crash handler using `pdbp` REPL debugger.
-
-    We expose this as a CLI framework addon to both `click` and
-    `typer` users so they can quickly wrap cmd endpoints which get
-    automatically wrapped to use the runtime's `debug_mode: bool`
-    AND `pdbp.pm()` around any code that is PRE-runtime entry
-    - any sync code which runs BEFORE the main call to
-      `trio.run()`.
-
-    '''
-    __tracebackhide__: bool = hide_tb
-
-    # TODO, yield a `outcome.Error`-like boxed type?
-    # -[~] use `outcome.Value/Error` X-> frozen!
-    # -[x] write our own..?
-    # -[ ] consider just wtv is used by `pytest.raises()`?
-    #
-    boxed_maybe_exc = BoxedMaybeException(
-        raise_on_exit=raise_on_exit,
-    )
-    err: BaseException
-    try:
-        yield boxed_maybe_exc
-    except tuple(catch) as err:
-        boxed_maybe_exc.value = err
-        if (
-            type(err) not in ignore
-            and
-            not is_multi_cancelled(
-                err,
-                ignore_nested=ignore
-            )
-        ):
-            try:
-                # use our re-impl-ed version of `pdbp.xpm()`
-                _post_mortem(
-                    repl=mk_pdb(),
-                    tb=sys.exc_info()[2],
-                    api_frame=inspect.currentframe().f_back,
-                    hide_tb=hide_tb,
-
-                    repl_fixture=repl_fixture,
-                    boxed_maybe_exc=boxed_maybe_exc,
-                )
-            except bdb.BdbQuit:
-                __tracebackhide__: bool = False
-                raise err
-
-        if (
-            raise_on_exit is True
-            or (
-                raise_on_exit is not False
-                and (
-                    set(raise_on_exit)
-                    and
-                    type(err) in raise_on_exit
-                )
-            )
-            and
-            boxed_maybe_exc.raise_on_exit == raise_on_exit
-        ):
-            raise err
-
-
-@cm
-def maybe_open_crash_handler(
-    pdb: bool|None = None,
-    hide_tb: bool = True,
-
-    **kwargs,
-):
-    '''
-    Same as `open_crash_handler()` but with bool input flag
-    to allow conditional handling.
-
-    Normally this is used with CLI endpoints such that if the --pdb
-    flag is passed the pdb REPL is engaed on any crashes B)
-
-    '''
-    __tracebackhide__: bool = hide_tb
-
-    if pdb is None:
-        pdb: bool = _state.is_debug_mode()
-
-    rtctx = nullcontext(
-        enter_result=BoxedMaybeException()
-    )
-    if pdb:
-        rtctx = open_crash_handler(
-            hide_tb=hide_tb,
-            **kwargs,
-        )
-
-    with rtctx as boxed_maybe_exc:
-        yield boxed_maybe_exc

tractor/devx/debug/_repl.py

@@ -1,207 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or
-# modify it under the terms of the GNU Affero General Public License
-# as published by the Free Software Foundation, either version 3 of
-# the License, or (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful, but
-# WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-# Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public
-# License along with this program.  If not, see
-# <https://www.gnu.org/licenses/>.
-
-'''
-`pdpp.Pdb` extentions/customization and other delegate usage.
-
-'''
-from functools import (
-    cached_property,
-)
-import os
-
-import pdbp
-from tractor._state import (
-    is_root_process,
-)
-
-from ._tty_lock import (
-    Lock,
-    DebugStatus,
-)
-
-
-class TractorConfig(pdbp.DefaultConfig):
-    '''
-    Custom `pdbp` config which tries to use the best tradeoff
-    between pretty and minimal.
-
-    '''
-    use_pygments: bool = True
-    sticky_by_default: bool = False
-    enable_hidden_frames: bool = True
-
-    # much thanks @mdmintz for the hot tip!
-    # fixes line spacing issue when resizing terminal B)
-    truncate_long_lines: bool = False
-
-    # ------ - ------
-    # our own custom config vars mostly
-    # for syncing with the actor tree's singleton
-    # TTY `Lock`.
-
-
-class PdbREPL(pdbp.Pdb):
-    '''
-    Add teardown hooks and local state describing any
-    ongoing TTY `Lock` request dialog.
-
-    '''
-    # override the pdbp config with our coolio one
-    # NOTE: this is only loaded when no `~/.pdbrc` exists
-    # so we should prolly pass it into the .__init__() instead?
-    # i dunno, see the `DefaultFactory` and `pdb.Pdb` impls.
-    DefaultConfig = TractorConfig
-
-    status = DebugStatus
-
-    # NOTE: see details in stdlib's `bdb.py`
-    # def user_exception(self, frame, exc_info):
-    #     '''
-    #     Called when we stop on an exception.
-    #     '''
-    #     log.warning(
-    #         'Exception during REPL sesh\n\n'
-    #         f'{frame}\n\n'
-    #         f'{exc_info}\n\n'
-    #     )
-
-    # NOTE: this actually hooks but i don't see anyway to detect
-    # if an error was caught.. this is why currently we just always
-    # call `DebugStatus.release` inside `_post_mortem()`.
-    # def preloop(self):
-    #     print('IN PRELOOP')
-    #     super().preloop()
-
-    # TODO: cleaner re-wrapping of all this?
-    # -[ ] figure out how to disallow recursive .set_trace() entry
-    #     since that'll cause deadlock for us.
-    # -[ ] maybe a `@cm` to call `super().<same_meth_name>()`?
-    # -[ ] look at hooking into the `pp` hook specially with our
-    #     own set of pretty-printers?
-    #    * `.pretty_struct.Struct.pformat()`
-    #    * `.pformat(MsgType.pld)`
-    #    * `.pformat(Error.tb_str)`?
-    #    * .. maybe more?
-    #
-    def set_continue(self):
-        try:
-            super().set_continue()
-        finally:
-            # NOTE: for subactors the stdio lock is released via the
-            # allocated RPC locker task, so for root we have to do it
-            # manually.
-            if (
-                is_root_process()
-                and
-                Lock._debug_lock.locked()
-                and
-                DebugStatus.is_main_trio_thread()
-            ):
-                # Lock.release(raise_on_thread=False)
-                Lock.release()
-
-            # XXX AFTER `Lock.release()` for root local repl usage
-            DebugStatus.release()
-
-    def set_quit(self):
-        try:
-            super().set_quit()
-        finally:
-            if (
-                is_root_process()
-                and
-                Lock._debug_lock.locked()
-                and
-                DebugStatus.is_main_trio_thread()
-            ):
-                # Lock.release(raise_on_thread=False)
-                Lock.release()
-
-            # XXX after `Lock.release()` for root local repl usage
-            DebugStatus.release()
-
-    # XXX NOTE: we only override this because apparently the stdlib pdb
-    # bois likes to touch the SIGINT handler as much as i like to touch
-    # my d$%&.
-    def _cmdloop(self):
-        self.cmdloop()
-
-    @cached_property
-    def shname(self) -> str | None:
-        '''
-        Attempt to return the login shell name with a special check for
-        the infamous `xonsh` since it seems to have some issues much
-        different from std shells when it comes to flushing the prompt?
-
-        '''
-        # SUPER HACKY and only really works if `xonsh` is not used
-        # before spawning further sub-shells..
-        shpath = os.getenv('SHELL', None)
-
-        if shpath:
-            if (
-                os.getenv('XONSH_LOGIN', default=False)
-                or 'xonsh' in shpath
-            ):
-                return 'xonsh'
-
-            return os.path.basename(shpath)
-
-        return None
-
-
-def mk_pdb() -> PdbREPL:
-    '''
-    Deliver a new `PdbREPL`: a multi-process safe `pdbp.Pdb`-variant
-    using the magic of `tractor`'s SC-safe IPC.
-
-    B)
-
-    Our `pdb.Pdb` subtype accomplishes multi-process safe debugging
-    by:
-
-    - mutexing access to the root process' std-streams (& thus parent
-      process TTY) via an IPC managed `Lock` singleton per
-      actor-process tree.
-
-    - temporarily overriding any subactor's SIGINT handler to shield
-      during live REPL sessions in sub-actors such that cancellation
-      is never (mistakenly) triggered by a ctrl-c and instead only by
-      explicit runtime API requests or after the
-      `pdb.Pdb.interaction()` call has returned.
-
-    FURTHER, the `pdbp.Pdb` instance is configured to be `trio`
-    "compatible" from a SIGINT handling perspective; we mask out
-    the default `pdb` handler and instead apply `trio`s default
-    which mostly addresses all issues described in:
-
-     - https://github.com/python-trio/trio/issues/1155
-
-    The instance returned from this factory should always be
-    preferred over the default `pdb[p].set_trace()` whenever using
-    a `pdb` REPL inside a `trio` based runtime.
-
-    '''
-    pdb = PdbREPL()
-
-    # XXX: These are the important flags mentioned in
-    # https://github.com/python-trio/trio/issues/1155
-    # which resolve the traceback spews to console.
-    pdb.allow_kbdint = True
-    pdb.nosigint = True
-    return pdb

tractor/devx/debug/_sigint.py

@@ -1,333 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or
-# modify it under the terms of the GNU Affero General Public License
-# as published by the Free Software Foundation, either version 3 of
-# the License, or (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful, but
-# WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-# Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public
-# License along with this program.  If not, see
-# <https://www.gnu.org/licenses/>.
-
-'''
-A custom SIGINT handler which mainly shields actor (task)
-cancellation during REPL interaction.
-
-'''
-from __future__ import annotations
-from typing import (
-    TYPE_CHECKING,
-)
-import trio
-from tractor.log import get_logger
-from tractor._state import (
-    current_actor,
-    is_root_process,
-)
-from ._repl import (
-    PdbREPL,
-)
-from ._tty_lock import (
-    any_connected_locker_child,
-    DebugStatus,
-    Lock,
-)
-
-if TYPE_CHECKING:
-    from tractor.ipc import (
-        Channel,
-    )
-    from tractor._runtime import (
-        Actor,
-    )
-
-log = get_logger(__name__)
-
-_ctlc_ignore_header: str = (
-    'Ignoring SIGINT while debug REPL in use'
-)
-
-
-def sigint_shield(
-    signum: int,
-    frame: 'frame',  # type: ignore # noqa
-    *args,
-
-) -> None:
-    '''
-    Specialized, debugger-aware SIGINT handler.
-
-    In childred we always ignore/shield for SIGINT to avoid
-    deadlocks since cancellation should always be managed by the
-    supervising parent actor. The root actor-proces is always
-    cancelled on ctrl-c.
-
-    '''
-    __tracebackhide__: bool = True
-    actor: Actor = current_actor()
-
-    def do_cancel():
-        # If we haven't tried to cancel the runtime then do that instead
-        # of raising a KBI (which may non-gracefully destroy
-        # a ``trio.run()``).
-        if not actor._cancel_called:
-            actor.cancel_soon()
-
-        # If the runtime is already cancelled it likely means the user
-        # hit ctrl-c again because teardown didn't fully take place in
-        # which case we do the "hard" raising of a local KBI.
-        else:
-            raise KeyboardInterrupt
-
-    # only set in the actor actually running the REPL
-    repl: PdbREPL|None = DebugStatus.repl
-
-    # TODO: maybe we should flatten out all these cases using
-    # a match/case?
-    #
-    # root actor branch that reports whether or not a child
-    # has locked debugger.
-    if is_root_process():
-        # log.warning(
-        log.devx(
-            'Handling SIGINT in root actor\n'
-            f'{Lock.repr()}'
-            f'{DebugStatus.repr()}\n'
-        )
-        # try to see if the supposed (sub)actor in debug still
-        # has an active connection to *this* actor, and if not
-        # it's likely they aren't using the TTY lock / debugger
-        # and we should propagate SIGINT normally.
-        any_connected: bool = any_connected_locker_child()
-
-        problem = (
-            f'root {actor.uid} handling SIGINT\n'
-            f'any_connected: {any_connected}\n\n'
-
-            f'{Lock.repr()}\n'
-        )
-
-        if (
-            (ctx := Lock.ctx_in_debug)
-            and
-            (uid_in_debug := ctx.chan.uid) # "someone" is (ostensibly) using debug `Lock`
-        ):
-            name_in_debug: str = uid_in_debug[0]
-            assert not repl
-            # if not repl:  # but it's NOT us, the root actor.
-            # sanity: since no repl ref is set, we def shouldn't
-            # be the lock owner!
-            assert name_in_debug != 'root'
-
-            # IDEAL CASE: child has REPL as expected
-            if any_connected:  # there are subactors we can contact
-                # XXX: only if there is an existing connection to the
-                # (sub-)actor in debug do we ignore SIGINT in this
-                # parent! Otherwise we may hang waiting for an actor
-                # which has already terminated to unlock.
-                #
-                # NOTE: don't emit this with `.pdb()` level in
-                # root without a higher level.
-                log.runtime(
-                    _ctlc_ignore_header
-                    +
-                    f' by child '
-                    f'{uid_in_debug}\n'
-                )
-                problem = None
-
-            else:
-                problem += (
-                    '\n'
-                    f'A `pdb` REPL is SUPPOSEDLY in use by child {uid_in_debug}\n'
-                    f'BUT, no child actors are IPC contactable!?!?\n'
-                )
-
-        # IDEAL CASE: root has REPL as expected
-        else:
-            # root actor still has this SIGINT handler active without
-            # an actor using the `Lock` (a bug state) ??
-            # => so immediately cancel any stale lock cs and revert
-            # the handler!
-            if not DebugStatus.repl:
-                # TODO: WHEN should we revert back to ``trio``
-                # handler if this one is stale?
-                # -[ ] maybe after a counts work of ctl-c mashes?
-                # -[ ] use a state var like `stale_handler: bool`?
-                problem += (
-                    'No subactor is using a `pdb` REPL according `Lock.ctx_in_debug`?\n'
-                    'BUT, the root should be using it, WHY this handler ??\n\n'
-                    'So either..\n'
-                    '- some root-thread is using it but has no `.repl` set?, OR\n'
-                    '- something else weird is going on outside the runtime!?\n'
-                )
-            else:
-                # NOTE: since we emit this msg on ctl-c, we should
-                # also always re-print the prompt the tail block!
-                log.pdb(
-                    _ctlc_ignore_header
-                    +
-                    f' by root actor..\n'
-                    f'{DebugStatus.repl_task}\n'
-                    f' |_{repl}\n'
-                )
-                problem = None
-
-        # XXX if one is set it means we ARE NOT operating an ideal
-        # case where a child subactor or us (the root) has the
-        # lock without any other detected problems.
-        if problem:
-
-            # detect, report and maybe clear a stale lock request
-            # cancel scope.
-            lock_cs: trio.CancelScope = Lock.get_locking_task_cs()
-            maybe_stale_lock_cs: bool = (
-                lock_cs is not None
-                and not lock_cs.cancel_called
-            )
-            if maybe_stale_lock_cs:
-                problem += (
-                    '\n'
-                    'Stale `Lock.ctx_in_debug._scope: CancelScope` detected?\n'
-                    f'{Lock.ctx_in_debug}\n\n'
-
-                    '-> Calling ctx._scope.cancel()!\n'
-                )
-                lock_cs.cancel()
-
-            # TODO: wen do we actually want/need this, see above.
-            # DebugStatus.unshield_sigint()
-            log.warning(problem)
-
-    # child actor that has locked the debugger
-    elif not is_root_process():
-        log.debug(
-            f'Subactor {actor.uid} handling SIGINT\n\n'
-            f'{Lock.repr()}\n'
-        )
-
-        rent_chan: Channel = actor._parent_chan
-        if (
-            rent_chan is None
-            or
-            not rent_chan.connected()
-        ):
-            log.warning(
-                'This sub-actor thinks it is debugging '
-                'but it has no connection to its parent ??\n'
-                f'{actor.uid}\n'
-                'Allowing SIGINT propagation..'
-            )
-            DebugStatus.unshield_sigint()
-
-        repl_task: str|None = DebugStatus.repl_task
-        req_task: str|None = DebugStatus.req_task
-        if (
-            repl_task
-            and
-            repl
-        ):
-            log.pdb(
-                _ctlc_ignore_header
-                +
-                f' by local task\n\n'
-                f'{repl_task}\n'
-                f' |_{repl}\n'
-            )
-        elif req_task:
-            log.debug(
-                _ctlc_ignore_header
-                +
-                f' by local request-task and either,\n'
-                f'- someone else is already REPL-in and has the `Lock`, or\n'
-                f'- some other local task already is replin?\n\n'
-                f'{req_task}\n'
-            )
-
-        # TODO can we remove this now?
-        # -[ ] does this path ever get hit any more?
-        else:
-            msg: str = (
-                'SIGINT shield handler still active BUT, \n\n'
-            )
-            if repl_task is None:
-                msg += (
-                    '- No local task claims to be in debug?\n'
-                )
-
-            if repl is None:
-                msg += (
-                    '- No local REPL is currently active?\n'
-                )
-
-            if req_task is None:
-                msg += (
-                    '- No debug request task is active?\n'
-                )
-
-            log.warning(
-                msg
-                +
-                'Reverting handler to `trio` default!\n'
-            )
-            DebugStatus.unshield_sigint()
-
-            # XXX ensure that the reverted-to-handler actually is
-            # able to rx what should have been **this** KBI ;)
-            do_cancel()
-
-        # TODO: how to handle the case of an intermediary-child actor
-        # that **is not** marked in debug mode? See oustanding issue:
-        # https://github.com/goodboy/tractor/issues/320
-        # elif debug_mode():
-
-    # maybe redraw/print last REPL output to console since
-    # we want to alert the user that more input is expect since
-    # nothing has been done dur to ignoring sigint.
-    if (
-        DebugStatus.repl  # only when current actor has a REPL engaged
-    ):
-        flush_status: str = (
-            'Flushing stdout to ensure new prompt line!\n'
-        )
-
-        # XXX: yah, mega hack, but how else do we catch this madness XD
-        if (
-            repl.shname == 'xonsh'
-        ):
-            flush_status += (
-                '-> ALSO re-flushing due to `xonsh`..\n'
-            )
-            repl.stdout.write(repl.prompt)
-
-        # log.warning(
-        log.devx(
-            flush_status
-        )
-        repl.stdout.flush()
-
-        # TODO: better console UX to match the current "mode":
-        # -[ ] for example if in sticky mode where if there is output
-        #   detected as written to the tty we redraw this part underneath
-        #   and erase the past draw of this same bit above?
-        # repl.sticky = True
-        # repl._print_if_sticky()
-
-        # also see these links for an approach from `ptk`:
-        # https://github.com/goodboy/tractor/issues/130#issuecomment-663752040
-        # https://github.com/prompt-toolkit/python-prompt-toolkit/blob/c2c6af8a0308f9e5d7c0e28cb8a02963fe0ce07a/prompt_toolkit/patch_stdout.py
-    else:
-        log.devx(
-        # log.warning(
-            'Not flushing stdout since not needed?\n'
-            f'|_{repl}\n'
-        )
-
-    # XXX only for tracing this handler
-    log.devx('exiting SIGINT')

tractor/devx/debug/_sync.py

@@ -1,220 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or
-# modify it under the terms of the GNU Affero General Public License
-# as published by the Free Software Foundation, either version 3 of
-# the License, or (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful, but
-# WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
-# Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public
-# License along with this program.  If not, see
-# <https://www.gnu.org/licenses/>.
-
-'''
-Debugger synchronization APIs to ensure orderly access and
-non-TTY-clobbering graceful teardown.
-
-
-'''
-from __future__ import annotations
-from contextlib import (
-    asynccontextmanager as acm,
-)
-from functools import (
-    partial,
-)
-from typing import (
-    AsyncGenerator,
-    Callable,
-)
-
-from tractor.log import get_logger
-import trio
-from trio.lowlevel import (
-    current_task,
-    Task,
-)
-from tractor._context import Context
-from tractor._state import (
-    current_actor,
-    debug_mode,
-    is_root_process,
-)
-from ._repl import (
-    TractorConfig as TractorConfig,
-)
-from ._tty_lock import (
-    Lock,
-    request_root_stdio_lock,
-    any_connected_locker_child,
-)
-from ._sigint import (
-    sigint_shield as sigint_shield,
-    _ctlc_ignore_header as _ctlc_ignore_header
-)
-
-log = get_logger(__package__)
-
-
-async def maybe_wait_for_debugger(
-    poll_steps: int = 2,
-    poll_delay: float = 0.1,
-    child_in_debug: bool = False,
-
-    header_msg: str = '',
-    _ll: str = 'devx',
-
-) -> bool:  # was locked and we polled?
-
-    if (
-        not debug_mode()
-        and
-        not child_in_debug
-    ):
-        return False
-
-    logmeth: Callable = getattr(log, _ll)
-
-    msg: str = header_msg
-    if (
-        is_root_process()
-    ):
-        # If we error in the root but the debugger is
-        # engaged we don't want to prematurely kill (and
-        # thus clobber access to) the local tty since it
-        # will make the pdb repl unusable.
-        # Instead try to wait for pdb to be released before
-        # tearing down.
-        ctx_in_debug: Context|None = Lock.ctx_in_debug
-        in_debug: tuple[str, str]|None = (
-            ctx_in_debug.chan.uid
-            if ctx_in_debug
-            else None
-        )
-        if in_debug == current_actor().uid:
-            log.debug(
-                msg
-                +
-                'Root already owns the TTY LOCK'
-            )
-            return True
-
-        elif in_debug:
-            msg += (
-                f'Debug `Lock` in use by subactor\n|\n|_{in_debug}\n'
-            )
-            # TODO: could this make things more deterministic?
-            # wait to see if a sub-actor task will be
-            # scheduled and grab the tty lock on the next
-            # tick?
-            # XXX => but it doesn't seem to work..
-            # await trio.testing.wait_all_tasks_blocked(cushion=0)
-        else:
-            logmeth(
-                msg
-                +
-                'Root immediately acquired debug TTY LOCK'
-            )
-            return False
-
-        for istep in range(poll_steps):
-            if (
-                Lock.req_handler_finished is not None
-                and not Lock.req_handler_finished.is_set()
-                and in_debug is not None
-            ):
-                # caller_frame_info: str = pformat_caller_frame()
-                logmeth(
-                    msg
-                    +
-                    '\n^^ Root is waiting on tty lock release.. ^^\n'
-                    # f'{caller_frame_info}\n'
-                )
-
-                if not any_connected_locker_child():
-                    Lock.get_locking_task_cs().cancel()
-
-                with trio.CancelScope(shield=True):
-                    await Lock.req_handler_finished.wait()
-
-                log.devx(
-                    f'Subactor released debug lock\n'
-                    f'|_{in_debug}\n'
-                )
-                break
-
-            # is no subactor locking debugger currently?
-            if (
-                in_debug is None
-                and (
-                    Lock.req_handler_finished is None
-                    or Lock.req_handler_finished.is_set()
-                )
-            ):
-                logmeth(
-                    msg
-                    +
-                    'Root acquired tty lock!'
-                )
-                break
-
-            else:
-                logmeth(
-                    'Root polling for debug:\n'
-                    f'poll step: {istep}\n'
-                    f'poll delya: {poll_delay}\n\n'
-                    f'{Lock.repr()}\n'
-                )
-                with trio.CancelScope(shield=True):
-                    await trio.sleep(poll_delay)
-                    continue
-
-        return True
-
-    # else:
-    #     # TODO: non-root call for #320?
-    #     this_uid: tuple[str, str] = current_actor().uid
-    #     async with acquire_debug_lock(
-    #         subactor_uid=this_uid,
-    #     ):
-    #         pass
-    return False
-
-
-@acm
-async def acquire_debug_lock(
-    subactor_uid: tuple[str, str],
-) -> AsyncGenerator[
-    trio.CancelScope|None,
-    tuple,
-]:
-    '''
-    Request to acquire the TTY `Lock` in the root actor, release on
-    exit.
-
-    This helper is for actor's who don't actually need to acquired
-    the debugger but want to wait until the lock is free in the
-    process-tree root such that they don't clobber an ongoing pdb
-    REPL session in some peer or child!
-
-    '''
-    if not debug_mode():
-        yield None
-        return
-
-    task: Task = current_task()
-    async with trio.open_nursery() as n:
-        ctx: Context = await n.start(
-            partial(
-                request_root_stdio_lock,
-                actor_uid=subactor_uid,
-                task_uid=(task.name, id(task)),
-            )
-        )
-        yield ctx
-        ctx.cancel()

tractor/devx/pformat.py

@@ -15,13 +15,10 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 '''
-Pretty formatters for use throughout our internals.
+Pretty formatters for use throughout the code base.
-
+Mostly handy for logging and exception message content.
-Handy for logging and exception message content but also for `repr()`
-in REPL(s).
 
 '''
-import sys
 import textwrap
 import traceback
 
@@ -118,85 +115,6 @@ def pformat_boxed_tb(
     )
 
 
-def pformat_exc(
-    exc: Exception,
-    header: str = '',
-    message: str = '',
-    body: str = '',
-    with_type_header: bool = True,
-) -> str:
-
-    # XXX when the currently raised exception is this instance,
-    # we do not ever use the "type header" style repr.
-    is_being_raised: bool = False
-    if (
-        (curr_exc := sys.exception())
-        and
-        curr_exc is exc
-    ):
-        is_being_raised: bool = True
-
-    with_type_header: bool = (
-        with_type_header
-        and
-        not is_being_raised
-    )
-
-    # <RemoteActorError( .. )> style
-    if (
-        with_type_header
-        and
-        not header
-    ):
-        header: str = f'<{type(exc).__name__}('
-
-    message: str = (
-        message
-        or
-        exc.message
-    )
-    if message:
-        # split off the first line so, if needed, it isn't
-        # indented the same like the "boxed content" which
-        # since there is no `.tb_str` is just the `.message`.
-        lines: list[str] = message.splitlines()
-        first: str = lines[0]
-        message: str = message.removeprefix(first)
-
-        # with a type-style header we,
-        # - have no special message "first line" extraction/handling
-        # - place the message a space in from the header:
-        #  `MsgTypeError( <message> ..`
-        #                 ^-here
-        # - indent the `.message` inside the type body.
-        if with_type_header:
-            first = f' {first} )>'
-
-        message: str = textwrap.indent(
-            message,
-            prefix=' '*2,
-        )
-        message: str = first + message
-
-    tail: str = ''
-    if (
-        with_type_header
-        and
-        not message
-    ):
-        tail: str = '>'
-
-    return (
-        header
-        +
-        message
-        +
-        f'{body}'
-        +
-        tail
-    )
-
-
 def pformat_caller_frame(
     stack_limit: int = 1,
     box_tb: bool = True,
@@ -226,8 +144,8 @@ def pformat_cs(
     field_prefix: str = ' |_',
 ) -> str:
     '''
-    Pretty format info about a `trio.CancelScope` including most of
+    Pretty format info about a `trio.CancelScope` including most
-    its public state and `._cancel_status`.
+    of its public state and `._cancel_status`.
 
     The output can be modified to show a "var name" for the
     instance as a field prefix, just a simple str before each
@@ -249,279 +167,3 @@ def pformat_cs(
         +
         fields
     )
-
-
-def nest_from_op(
-    input_op: str,  # TODO, Literal of all op-"symbols" from below?
-    text: str,
-    prefix_op: bool = True,  # unset is to suffix the first line
-    # optionally suffix `text`, by def on a newline
-    op_suffix='\n',
-
-    nest_prefix: str = '|_',
-    nest_indent: int|None = None,
-    # XXX indent `next_prefix` "to-the-right-of" `input_op`
-    # by this count of whitespaces (' ').
-    rm_from_first_ln: str|None = None,
-
-) -> str:
-    '''
-    Depth-increment the input (presumably hierarchy/supervision)
-    input "tree string" below the provided `input_op` execution
-    operator, so injecting a `"\n|_{input_op}\n"`and indenting the
-    `tree_str` to nest content aligned with the ops last char.
-
-    '''
-    # `sclang` "structurred-concurrency-language": an ascii-encoded
-    # symbolic alphabet to describe concurrent systems.
-    #
-    # ?TODO? aa more fomal idea for a syntax to the state of
-    # concurrent systems as a "3-domain" (execution, scope, storage)
-    # model and using a minimal ascii/utf-8 operator-set.
-    #
-    # try not to take any of this seriously yet XD
-    #
-    # > is a "play operator" indicating (CPU bound)
-    #   exec/work/ops required at the "lowest level computing"
-    #
-    # execution primititves (tasks, threads, actors..) denote their
-    # lifetime with '(' and ')' since parentheses normally are used
-    # in many langs to denote function calls.
-    #
-    # starting = (
-    # >(  opening/starting; beginning of the thread-of-exec (toe?)
-    # (>  opened/started,  (finished spawning toe)
-    # |_<Task: blah blah..>  repr of toe, in py these look like <objs>
-    #
-    # >) closing/exiting/stopping,
-    # )> closed/exited/stopped,
-    # |_<Task: blah blah..>
-    #   [OR <), )< ?? ]
-    #
-    # ending = )
-    # >c) cancelling to close/exit
-    # c)> cancelled (caused close), OR?
-    #  |_<Actor: ..>
-    #   OR maybe "<c)" which better indicates the cancel being
-    #   "delivered/returned" / returned" to LHS?
-    #
-    # >x)  erroring to eventuall exit
-    # x)>  errored and terminated
-    #  |_<Actor: ...>
-    #
-    # scopes: supers/nurseries, IPC-ctxs, sessions, perms, etc.
-    # >{  opening
-    # {>  opened
-    # }>  closed
-    # >}  closing
-    #
-    # storage: like queues, shm-buffers, files, etc..
-    # >[  opening
-    # [>  opened
-    #  |_<FileObj: ..>
-    #
-    # >]  closing
-    # ]>  closed
-
-    # IPC ops: channels, transports, msging
-    # =>  req msg
-    # <=  resp msg
-    # <=> 2-way streaming (of msgs)
-    # <-  recv 1 msg
-    # ->  send 1 msg
-    #
-    # TODO: still not sure on R/L-HS approach..?
-    # =>(  send-req to exec start (task, actor, thread..)
-    # (<=  recv-req to ^
-    #
-    # (<=  recv-req ^
-    # <=(  recv-resp opened remote exec primitive
-    # <=)  recv-resp closed
-    #
-    # )<=c req to stop due to cancel
-    # c=>) req to stop due to cancel
-    #
-    # =>{  recv-req to open
-    # <={  send-status that it closed
-    #
-    if (
-        nest_prefix
-        and
-        nest_indent != 0
-    ):
-        if nest_indent is not None:
-            nest_prefix: str = textwrap.indent(
-                nest_prefix,
-                prefix=nest_indent*' ',
-            )
-        nest_indent: int = len(nest_prefix)
-
-    # determine body-text indent either by,
-    # - using wtv explicit indent value is provided,
-    # OR
-    # - auto-calcing the indent to embed `text` under
-    #   the `nest_prefix` if provided, **IFF** `nest_indent=None`.
-    tree_str_indent: int = 0
-    if nest_indent not in {0, None}:
-        tree_str_indent = nest_indent
-    elif (
-        nest_prefix
-        and
-        nest_indent != 0
-    ):
-        tree_str_indent = len(nest_prefix)
-
-    indented_tree_str: str = text
-    if tree_str_indent:
-        indented_tree_str: str = textwrap.indent(
-            text,
-            prefix=' '*tree_str_indent,
-        )
-
-    # inject any provided nesting-prefix chars
-    # into the head of the first line.
-    if nest_prefix:
-        indented_tree_str: str = (
-            f'{nest_prefix}{indented_tree_str[tree_str_indent:]}'
-        )
-
-    if (
-        not prefix_op
-        or
-        rm_from_first_ln
-    ):
-        tree_lns: list[str] = indented_tree_str.splitlines()
-        first: str = tree_lns[0]
-        if rm_from_first_ln:
-            first = first.strip().replace(
-                rm_from_first_ln,
-                '',
-            )
-        indented_tree_str: str = '\n'.join(tree_lns[1:])
-
-        if prefix_op:
-            indented_tree_str = (
-                f'{first}\n'
-                f'{indented_tree_str}'
-            )
-
-    if prefix_op:
-        return (
-            f'{input_op}{op_suffix}'
-            f'{indented_tree_str}'
-        )
-    else:
-        return (
-            f'{first}{input_op}{op_suffix}'
-            f'{indented_tree_str}'
-        )
-
-
-# ------ modden.repr ------
-# XXX originally taken verbaatim from `modden.repr`
-'''
-More "multi-line" representation then the stdlib's `pprint` equivs.
-
-'''
-from inspect import (
-    FrameInfo,
-    stack,
-)
-import pprint
-import reprlib
-from typing import (
-    Callable,
-)
-
-
-def mk_repr(
-    **repr_kws,
-) -> Callable[[str], str]:
-    '''
-    Allocate and deliver a `repr.Repr` instance with provided input
-    settings using the std-lib's `reprlib` mod,
-     * https://docs.python.org/3/library/reprlib.html
-
-    ------ Ex. ------
-    An up to 6-layer-nested `dict` as multi-line:
-    - https://stackoverflow.com/a/79102479
-    - https://docs.python.org/3/library/reprlib.html#reprlib.Repr.maxlevel
-
-    '''
-    def_kws: dict[str, int] = dict(
-        indent=3,  # indent used for repr of recursive objects
-        maxlevel=616,  # recursion levels
-        maxdict=616,  # max items shown for `dict`
-        maxlist=616,  # max items shown for `dict`
-        maxstring=616,  # match editor line-len limit
-        maxtuple=616,  # match editor line-len limit
-        maxother=616,  # match editor line-len limit
-    )
-    def_kws |= repr_kws
-    reprr = reprlib.Repr(**def_kws)
-    return reprr.repr
-
-
-def ppfmt(
-    obj: object,
-    do_print: bool = False,
-) -> str:
-    '''
-    The `pprint.pformat()` version of `pprint.pp()`, namely
-    a default `sort_dicts=False`.. (which i think should be
-    the normal default in the stdlib).
-
-    '''
-    pprepr: Callable = mk_repr()
-    repr_str: str = pprepr(obj)
-
-    if do_print:
-        return pprint.pp(repr_str)
-
-    return repr_str
-
-
-pformat = ppfmt
-
-
-def pfmt_frame_info(fi: FrameInfo) -> str:
-    '''
-    Like a std `inspect.FrameInfo.__repr__()` but multi-line..
-
-    '''
-    return (
-        'FrameInfo(\n'
-        '  frame={!r},\n'
-        '  filename={!r},\n'
-        '  lineno={!r},\n'
-        '  function={!r},\n'
-        '  code_context={!r},\n'
-        '  index={!r},\n'
-        '  positions={!r})'
-        ).format(
-            fi.frame,
-            fi.filename,
-            fi.lineno,
-            fi.function,
-            fi.code_context,
-            fi.index,
-            fi.positions
-        )
-
-
-def pfmt_callstack(frames: int = 1) -> str:
-    '''
-    Generate a string of nested `inspect.FrameInfo` objects returned
-    from a `inspect.stack()` call such that only the `.frame` field
-    for each  layer is pprinted.
-
-    '''
-    caller_frames: list[FrameInfo] =  stack()[1:1+frames]
-    frames_str: str = ''
-    for i, frame_info in enumerate(caller_frames):
-        frames_str += textwrap.indent(
-            f'{frame_info.frame!r}\n',
-            prefix=' '*i,
-
-        )
-    return frames_str

tractor/experimental/_pubsub.py

@@ -45,8 +45,6 @@ __all__ = ['pub']
 log = get_logger('messaging')
 
 
-# TODO! this needs to reworked to use the modern
-# `Context`/`MsgStream` APIs!!
 async def fan_out_to_ctxs(
     pub_async_gen_func: typing.Callable,  # it's an async gen ... gd mypy
     topics2ctxs: dict[str, list],

tractor/ipc/__init__.py

@@ -1,24 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-
-'''
-A modular IPC layer supporting the power of cross-process SC!
-
-'''
-from ._chan import (
-    _connect_chan as _connect_chan,
-    Channel as Channel
-)

tractor/ipc/_chan.py

@@ -1,503 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-
-"""
-Inter-process comms abstractions
-
-"""
-from __future__ import annotations
-from collections.abc import AsyncGenerator
-from contextlib import (
-    asynccontextmanager as acm,
-    contextmanager as cm,
-)
-import platform
-from pprint import pformat
-import typing
-from typing import (
-    Any,
-    TYPE_CHECKING,
-)
-import warnings
-
-import trio
-
-from ._types import (
-    transport_from_addr,
-    transport_from_stream,
-)
-from tractor._addr import (
-    is_wrapped_addr,
-    wrap_address,
-    Address,
-    UnwrappedAddress,
-)
-from tractor.log import get_logger
-from tractor._exceptions import (
-    MsgTypeError,
-    pack_from_raise,
-    TransportClosed,
-)
-from tractor.msg import (
-    Aid,
-    MsgCodec,
-)
-
-if TYPE_CHECKING:
-    from ._transport import MsgTransport
-
-
-log = get_logger(__name__)
-
-_is_windows = platform.system() == 'Windows'
-
-
-class Channel:
-    '''
-    An inter-process channel for communication between (remote) actors.
-
-    Wraps a ``MsgStream``: transport + encoding IPC connection.
-
-    Currently we only support ``trio.SocketStream`` for transport
-    (aka TCP) and the ``msgpack`` interchange format via the ``msgspec``
-    codec libary.
-
-    '''
-    def __init__(
-
-        self,
-        transport: MsgTransport|None = None,
-        # TODO: optional reconnection support?
-        # auto_reconnect: bool = False,
-        # on_reconnect: typing.Callable[..., typing.Awaitable] = None,
-
-    ) -> None:
-
-        # self._recon_seq = on_reconnect
-        # self._autorecon = auto_reconnect
-
-        # Either created in ``.connect()`` or passed in by
-        # user in ``.from_stream()``.
-        self._transport: MsgTransport|None = transport
-
-        # set after handshake - always info from peer end
-        self.aid: Aid|None = None
-
-        self._aiter_msgs = self._iter_msgs()
-        self._exc: Exception|None = None
-        # ^XXX! ONLY set if a remote actor sends an `Error`-msg
-        self._closed: bool = False
-
-        # flag set by `Portal.cancel_actor()` indicating remote
-        # (possibly peer) cancellation of the far end actor 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]:
-        '''
-        Peer actor's unique id.
-
-        '''
-        msg: str = (
-            f'`{type(self).__name__}.uid` is now deprecated.\n'
-            'Use the new `.aid: tractor.msg.Aid` (struct) instead '
-            'which also provides additional named (optional) fields '
-            'beyond just the `.name` and `.uuid`.'
-        )
-        warnings.warn(
-            msg,
-            DeprecationWarning,
-            stacklevel=2,
-        )
-        peer_aid: Aid = self.aid
-        return (
-            peer_aid.name,
-            peer_aid.uuid,
-        )
-
-    @property
-    def stream(self) -> trio.abc.Stream | None:
-        return self._transport.stream if self._transport else None
-
-    @property
-    def msgstream(self) -> MsgTransport:
-        log.info(
-            '`Channel.msgstream` is an old name, use `._transport`'
-        )
-        return self._transport
-
-    @property
-    def transport(self) -> MsgTransport:
-        return self._transport
-
-    @classmethod
-    def from_stream(
-        cls,
-        stream: trio.abc.Stream,
-    ) -> Channel:
-        transport_cls = transport_from_stream(stream)
-        return Channel(
-            transport=transport_cls(stream)
-        )
-
-    @classmethod
-    async def from_addr(
-        cls,
-        addr: UnwrappedAddress,
-        **kwargs
-    ) -> Channel:
-
-        if not is_wrapped_addr(addr):
-            addr: Address = wrap_address(addr)
-
-        transport_cls = transport_from_addr(addr)
-        transport = await transport_cls.connect_to(
-            addr,
-            **kwargs,
-        )
-        # XXX, for UDS *no!* since we recv the peer-pid and build out
-        # a new addr..
-        # assert transport.raddr == addr
-        chan = Channel(transport=transport)
-
-        # ?TODO, compact this into adapter level-methods?
-        # -[ ] would avoid extra repr-calcs if level not active?
-        #   |_ 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
-    def apply_codec(
-        self,
-        codec: MsgCodec,
-    ) -> None:
-        '''
-        Temporarily override the underlying IPC msg codec for
-        dynamic enforcement of messaging schema.
-
-        '''
-        orig: MsgCodec = self._transport.codec
-        try:
-            self._transport.codec = codec
-            yield
-        finally:
-            self._transport.codec = orig
-
-    # TODO: do a .src/.dst: str for maddrs?
-    def pformat(
-        self,
-        privates: bool = False,
-    ) -> str:
-        if not self._transport:
-            return '<Channel( with inactive transport? )>'
-
-        tpt: MsgTransport = self._transport
-        tpt_name: str = type(tpt).__name__
-        tpt_status: str = (
-            'connected' if self.connected()
-            else 'closed'
-        )
-        repr_str: str = (
-            f'<Channel(\n'
-            f' |_status: {tpt_status!r}\n'
-        ) + (
-            f'   _closed={self._closed}\n'
-            f'   _cancel_called={self._cancel_called}\n'
-            if privates else ''
-        ) + (  # peer-actor (processs) section
-            f' |_peer: {self.aid.reprol()!r}\n'
-            if self.aid else ' |_peer: <unknown>\n'
-        ) + (
-            f' |_msgstream: {tpt_name}\n'
-            f'   maddr: {tpt.maddr!r}\n'
-            f'   proto: {tpt.laddr.proto_key!r}\n'
-            f'   layer: {tpt.layer_key!r}\n'
-            f'   codec: {tpt.codec_key!r}\n'
-            f'   .laddr={tpt.laddr}\n'
-            f'   .raddr={tpt.raddr}\n'
-        ) + (
-            f'   ._transport.stream={tpt.stream}\n'
-            f'   ._transport.drained={tpt.drained}\n'
-            if privates else ''
-        ) + (
-            f'   _send_lock={tpt._send_lock.statistics()}\n'
-            if privates else ''
-        ) + (
-            ')>\n'
-        )
-        return repr_str
-
-    # NOTE: making this return a value that can be passed to
-    # `eval()` is entirely **optional** FYI!
-    # https://docs.python.org/3/library/functions.html#repr
-    # https://docs.python.org/3/reference/datamodel.html#object.__repr__
-    #
-    # Currently we target **readability** from a (console)
-    # logging perspective over `eval()`-ability since we do NOT
-    # target serializing non-struct instances!
-    # def __repr__(self) -> str:
-    __str__ = pformat
-    __repr__ = pformat
-
-    @property
-    def laddr(self) -> Address|None:
-        return self._transport.laddr if self._transport else None
-
-    @property
-    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..
-    # seems like a pretty useful thing to have in general
-    # along with being able to filter certain stack frame(s / sets)
-    # possibly based on the current log-level?
-    async def send(
-        self,
-        payload: Any,
-
-        hide_tb: bool = False,
-
-    ) -> None:
-        '''
-        Send a coded msg-blob over the transport.
-
-        '''
-        __tracebackhide__: bool = hide_tb
-        try:
-            log.transport(
-                '=> send IPC msg:\n\n'
-                f'{pformat(payload)}\n'
-            )
-            # assert self._transport  # but why typing?
-            await self._transport.send(
-                payload,
-                hide_tb=hide_tb,
-            )
-        except (
-            BaseException,
-            MsgTypeError,
-            TransportClosed,
-        )as _err:
-            err = _err  # bind for introspection
-            match err:
-                case MsgTypeError():
-                    try:
-                        assert err.cid
-                    except KeyError:
-                        raise err
-                case TransportClosed():
-                    log.transport(
-                        f'Transport stream closed due to\n'
-                        f'{err.repr_src_exc()}\n'
-                    )
-
-                case _:
-                    # never suppress non-tpt sources
-                    __tracebackhide__: bool = False
-            raise
-
-    async def recv(self) -> Any:
-        assert self._transport
-        return await self._transport.recv()
-
-        # TODO: auto-reconnect features like 0mq/nanomsg?
-        # -[ ] implement it manually with nods to SC prot
-        #      possibly on multiple transport backends?
-        #  -> seems like that might be re-inventing scalability
-        #     prots tho no?
-        # try:
-        #     return await self._transport.recv()
-        # except trio.BrokenResourceError:
-        #     if self._autorecon:
-        #         await self._reconnect()
-        #         return await self.recv()
-        #     raise
-
-    async def aclose(self) -> None:
-
-        log.transport(
-            f'Closing channel to {self.aid} '
-            f'{self.laddr} -> {self.raddr}'
-        )
-        assert self._transport
-        await self._transport.stream.aclose()
-        self._closed = True
-
-    async def __aenter__(self):
-        await self.connect()
-        return self
-
-    async def __aexit__(self, *args):
-        await self.aclose(*args)
-
-    def __aiter__(self):
-        return self._aiter_msgs
-
-    # ?TODO? run any reconnection sequence?
-    # -[ ] prolly should be impl-ed as deco-API?
-    #
-    # async def _reconnect(self) -> None:
-    #     """Handle connection failures by polling until a reconnect can be
-    #     established.
-    #     """
-    #     down = False
-    #     while True:
-    #         try:
-    #             with trio.move_on_after(3) as cancel_scope:
-    #                 await self.connect()
-    #             cancelled = cancel_scope.cancelled_caught
-    #             if cancelled:
-    #                 log.transport(
-    #                     "Reconnect timed out after 3 seconds, retrying...")
-    #                 continue
-    #             else:
-    #                 log.transport("Stream connection re-established!")
-
-    #                 # on_recon = self._recon_seq
-    #                 # if on_recon:
-    #                 #     await on_recon(self)
-
-    #                 break
-    #         except (OSError, ConnectionRefusedError):
-    #             if not down:
-    #                 down = True
-    #                 log.transport(
-    #                     f"Connection to {self.raddr} went down, waiting"
-    #                     " for re-establishment")
-    #             await trio.sleep(1)
-
-    async def _iter_msgs(
-        self
-    ) -> AsyncGenerator[Any, None]:
-        '''
-        Yield `MsgType` IPC msgs decoded and deliverd from
-        an underlying `MsgTransport` protocol.
-
-        This is a streaming routine alo implemented as an async-gen
-        func (same a `MsgTransport._iter_pkts()`) gets allocated by
-        a `.__call__()` inside `.__init__()` where it is assigned to
-        the `._aiter_msgs` attr.
-
-        '''
-        assert self._transport
-        while True:
-            try:
-                async for msg in self._transport:
-                    match msg:
-                        # NOTE: if transport/interchange delivers
-                        # a type error, we pack it with the far
-                        # end peer `Actor.uid` and relay the
-                        # `Error`-msg upward to the `._rpc` stack
-                        # for normal RAE handling.
-                        case MsgTypeError():
-                            yield pack_from_raise(
-                                local_err=msg,
-                                cid=msg.cid,
-
-                                # XXX we pack it here bc lower
-                                # layers have no notion of an
-                                # actor-id ;)
-                                src_uid=self.uid,
-                            )
-                        case _:
-                            yield msg
-
-            except trio.BrokenResourceError:
-
-                # if not self._autorecon:
-                raise
-
-            await self.aclose()
-
-            # if self._autorecon:  # attempt reconnect
-            #     await self._reconnect()
-            #     continue
-
-    def connected(self) -> bool:
-        return self._transport.connected() if self._transport else False
-
-    async def _do_handshake(
-        self,
-        aid: Aid,
-
-    ) -> Aid:
-        '''
-        Exchange `(name, UUIDs)` identifiers as the first
-        communication step with any (peer) remote `Actor`.
-
-        These are essentially the "mailbox addresses" found in
-        "actor model" parlance.
-
-        '''
-        await self.send(aid)
-        peer_aid: Aid = await self.recv()
-        log.runtime(
-            f'Received hanshake with peer\n'
-            f'<= {peer_aid.reprol(sin_uuid=False)}\n'
-        )
-        # NOTE, we always are referencing the remote peer!
-        self.aid = peer_aid
-        return peer_aid
-
-
-@acm
-async def _connect_chan(
-    addr: UnwrappedAddress
-) -> typing.AsyncGenerator[Channel, None]:
-    '''
-    Create and connect a channel with disconnect on context manager
-    teardown.
-
-    '''
-    chan = await Channel.from_addr(addr)
-    yield chan
-    with trio.CancelScope(shield=True):
-        await chan.aclose()

tractor/ipc/_fd_share.py

@@ -1,163 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-'''
-File-descriptor-sharing on `linux` by "wilhelm_of_bohemia".
-
-'''
-from __future__ import annotations
-import os
-import array
-import socket
-import tempfile
-from pathlib import Path
-from contextlib import ExitStack
-
-import trio
-import tractor
-from tractor.ipc import RBToken
-
-
-actor_name = 'ringd'
-
-
-_rings: dict[str, dict] = {}
-
-
-async def _attach_to_ring(
-    ring_name: str
-) -> tuple[int, int, int]:
-    actor = tractor.current_actor()
-
-    fd_amount = 3
-    sock_path = (
-        Path(tempfile.gettempdir())
-        /
-        f'{os.getpid()}-pass-ring-fds-{ring_name}-to-{actor.name}.sock'
-    )
-    sock = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
-    sock.bind(sock_path)
-    sock.listen(1)
-
-    async with (
-        tractor.find_actor(actor_name) as ringd,
-        ringd.open_context(
-            _pass_fds,
-            name=ring_name,
-            sock_path=sock_path
-        ) as (ctx, _sent)
-    ):
-        # prepare array to receive FD
-        fds = array.array("i", [0] * fd_amount)
-
-        conn, _ = sock.accept()
-
-        # receive FD
-        msg, ancdata, flags, addr = conn.recvmsg(
-            1024,
-            socket.CMSG_LEN(fds.itemsize * fd_amount)
-        )
-
-        for (
-            cmsg_level,
-            cmsg_type,
-            cmsg_data,
-        ) in ancdata:
-            if (
-                cmsg_level == socket.SOL_SOCKET
-                and
-                cmsg_type == socket.SCM_RIGHTS
-            ):
-                fds.frombytes(cmsg_data[:fds.itemsize * fd_amount])
-                break
-            else:
-                raise RuntimeError("Receiver: No FDs received")
-
-        conn.close()
-        sock.close()
-        sock_path.unlink()
-
-        return RBToken.from_msg(
-            await ctx.wait_for_result()
-        )
-
-
-@tractor.context
-async def _pass_fds(
-    ctx: tractor.Context,
-    name: str,
-    sock_path: str
-) -> RBToken:
-    global _rings
-    token = _rings[name]
-    client = socket.socket(socket.AF_UNIX, socket.SOCK_STREAM)
-    client.connect(sock_path)
-    await ctx.started()
-    fds = array.array('i', token.fds)
-    client.sendmsg([b'FDs'], [(socket.SOL_SOCKET, socket.SCM_RIGHTS, fds)])
-    client.close()
-    return token
-
-
-@tractor.context
-async def _open_ringbuf(
-    ctx: tractor.Context,
-    name: str,
-    buf_size: int
-) -> RBToken:
-    global _rings
-    is_owner = False
-    if name not in _rings:
-        stack = ExitStack()
-        token = stack.enter_context(
-            tractor.open_ringbuf(
-                name,
-                buf_size=buf_size
-            )
-        )
-        _rings[name] = {
-            'token': token,
-            'stack': stack,
-        }
-        is_owner = True
-
-    ring = _rings[name]
-    await ctx.started()
-
-    try:
-        await trio.sleep_forever()
-
-    except tractor.ContextCancelled:
-        ...
-
-    finally:
-        if is_owner:
-            ring['stack'].close()
-
-
-async def open_ringbuf(
-    name: str,
-    buf_size: int
-) -> RBToken:
-    async with (
-        tractor.find_actor(actor_name) as ringd,
-        ringd.open_context(
-            _open_ringbuf,
-            name=name,
-            buf_size=buf_size
-        ) as (rd_ctx, _)
-    ):
-        yield await _attach_to_ring(name)
-        await rd_ctx.cancel()

tractor/ipc/_linux.py

@@ -1,153 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-'''
-Linux specifics, for now we are only exposing EventFD
-
-'''
-import os
-import errno
-
-import cffi
-import trio
-
-ffi = cffi.FFI()
-
-# Declare the C functions and types we plan to use.
-#    - eventfd: for creating the event file descriptor
-#    - write:   for writing to the file descriptor
-#    - read:    for reading from the file descriptor
-#    - close:   for closing the file descriptor
-ffi.cdef(
-    '''
-    int eventfd(unsigned int initval, int flags);
-
-    ssize_t write(int fd, const void *buf, size_t count);
-    ssize_t read(int fd, void *buf, size_t count);
-
-    int close(int fd);
-    '''
-)
-
-
-# Open the default dynamic library (essentially 'libc' in most cases)
-C = ffi.dlopen(None)
-
-
-# Constants from <sys/eventfd.h>, if needed.
-EFD_SEMAPHORE = 1
-EFD_CLOEXEC = 0o2000000
-EFD_NONBLOCK = 0o4000
-
-
-def open_eventfd(initval: int = 0, flags: int = 0) -> int:
-    '''
-    Open an eventfd with the given initial value and flags.
-    Returns the file descriptor on success, otherwise raises OSError.
-
-    '''
-    fd = C.eventfd(initval, flags)
-    if fd < 0:
-        raise OSError(errno.errorcode[ffi.errno], 'eventfd failed')
-    return fd
-
-
-def write_eventfd(fd: int, value: int) -> int:
-    '''
-    Write a 64-bit integer (uint64_t) to the eventfd's counter.
-
-    '''
-    # Create a uint64_t* in C, store `value`
-    data_ptr = ffi.new('uint64_t *', value)
-
-    # Call write(fd, data_ptr, 8)
-    # We expect to write exactly 8 bytes (sizeof(uint64_t))
-    ret = C.write(fd, data_ptr, 8)
-    if ret < 0:
-        raise OSError(errno.errorcode[ffi.errno], 'write to eventfd failed')
-    return ret
-
-
-def read_eventfd(fd: int) -> int:
-    '''
-    Read a 64-bit integer (uint64_t) from the eventfd, returning the value.
-    Reading resets the counter to 0 (unless using EFD_SEMAPHORE).
-
-    '''
-    # Allocate an 8-byte buffer in C for reading
-    buf = ffi.new('char[]', 8)
-
-    ret = C.read(fd, buf, 8)
-    if ret < 0:
-        raise OSError(errno.errorcode[ffi.errno], 'read from eventfd failed')
-    # Convert the 8 bytes we read into a Python integer
-    data_bytes = ffi.unpack(buf, 8)  # returns a Python bytes object of length 8
-    value = int.from_bytes(data_bytes, byteorder='little', signed=False)
-    return value
-
-
-def close_eventfd(fd: int) -> int:
-    '''
-    Close the eventfd.
-
-    '''
-    ret = C.close(fd)
-    if ret < 0:
-        raise OSError(errno.errorcode[ffi.errno], 'close failed')
-
-
-class EventFD:
-    '''
-    Use a previously opened eventfd(2), meant to be used in
-    sub-actors after root actor opens the eventfds then passes
-    them through pass_fds
-
-    '''
-
-    def __init__(
-        self,
-        fd: int,
-        omode: str
-    ):
-        self._fd: int = fd
-        self._omode: str = omode
-        self._fobj = None
-
-    @property
-    def fd(self) -> int | None:
-        return self._fd
-
-    def write(self, value: int) -> int:
-        return write_eventfd(self._fd, value)
-
-    async def read(self) -> int:
-        return await trio.to_thread.run_sync(
-            read_eventfd, self._fd,
-            abandon_on_cancel=True
-        )
-
-    def open(self):
-        self._fobj = os.fdopen(self._fd, self._omode)
-
-    def close(self):
-        if self._fobj:
-            self._fobj.close()
-
-    def __enter__(self):
-        self.open()
-        return self
-
-    def __exit__(self, exc_type, exc_value, traceback):
-        self.close()

tractor/ipc/_mp_bs.py

@@ -1,75 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-'''
-Utils to tame mp non-SC madeness
-
-'''
-import platform
-
-
-def disable_mantracker():
-    '''
-    Disable all `multiprocessing` "resource tracking" machinery since
-    it's an absolute multi-threaded mess of non-SC madness.
-
-    '''
-    from multiprocessing.shared_memory import SharedMemory
-
-
-    # 3.13+ only.. can pass `track=False` to disable
-    # all the resource tracker bs.
-    # https://docs.python.org/3/library/multiprocessing.shared_memory.html
-    if (_py_313 := (
-            platform.python_version_tuple()[:-1]
-            >=
-            ('3', '13')
-        )
-    ):
-        from functools import partial
-        return partial(
-            SharedMemory,
-            track=False,
-        )
-
-    # !TODO, once we drop 3.12- we can obvi remove all this!
-    else:
-        from multiprocessing import (
-            resource_tracker as mantracker,
-        )
-
-        # Tell the "resource tracker" thing to fuck off.
-        class ManTracker(mantracker.ResourceTracker):
-            def register(self, name, rtype):
-                pass
-
-            def unregister(self, name, rtype):
-                pass
-
-            def ensure_running(self):
-                pass
-
-        # "know your land and know your prey"
-        # https://www.dailymotion.com/video/x6ozzco
-        mantracker._resource_tracker = ManTracker()
-        mantracker.register = mantracker._resource_tracker.register
-        mantracker.ensure_running = mantracker._resource_tracker.ensure_running
-        mantracker.unregister = mantracker._resource_tracker.unregister
-        mantracker.getfd = mantracker._resource_tracker.getfd
-
-        # use std type verbatim
-        shmT = SharedMemory
-
-    return shmT

tractor/ipc/_ringbuf.py

@@ -1,253 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-'''
-IPC Reliable RingBuffer implementation
-
-'''
-from __future__ import annotations
-from contextlib import contextmanager as cm
-from multiprocessing.shared_memory import SharedMemory
-
-import trio
-from msgspec import (
-    Struct,
-    to_builtins
-)
-
-from ._linux import (
-    EFD_NONBLOCK,
-    open_eventfd,
-    EventFD
-)
-from ._mp_bs import disable_mantracker
-
-
-disable_mantracker()
-
-
-class RBToken(Struct, frozen=True):
-    '''
-    RingBuffer token contains necesary info to open the two
-    eventfds and the shared memory
-
-    '''
-    shm_name: str
-    write_eventfd: int
-    wrap_eventfd: int
-    buf_size: int
-
-    def as_msg(self):
-        return to_builtins(self)
-
-    @classmethod
-    def from_msg(cls, msg: dict) -> RBToken:
-        if isinstance(msg, RBToken):
-            return msg
-
-        return RBToken(**msg)
-
-
-@cm
-def open_ringbuf(
-    shm_name: str,
-    buf_size: int = 10 * 1024,
-    write_efd_flags: int = 0,
-    wrap_efd_flags: int = 0
-) -> RBToken:
-    shm = SharedMemory(
-        name=shm_name,
-        size=buf_size,
-        create=True
-    )
-    try:
-        token = RBToken(
-            shm_name=shm_name,
-            write_eventfd=open_eventfd(flags=write_efd_flags),
-            wrap_eventfd=open_eventfd(flags=wrap_efd_flags),
-            buf_size=buf_size
-        )
-        yield token
-
-    finally:
-        shm.unlink()
-
-
-class RingBuffSender(trio.abc.SendStream):
-    '''
-    IPC Reliable Ring Buffer sender side implementation
-
-    `eventfd(2)` is used for wrap around sync, and also to signal
-    writes to the reader.
-
-    '''
-    def __init__(
-        self,
-        token: RBToken,
-        start_ptr: int = 0,
-    ):
-        token = RBToken.from_msg(token)
-        self._shm = SharedMemory(
-            name=token.shm_name,
-            size=token.buf_size,
-            create=False
-        )
-        self._write_event = EventFD(token.write_eventfd, 'w')
-        self._wrap_event = EventFD(token.wrap_eventfd, 'r')
-        self._ptr = start_ptr
-
-    @property
-    def key(self) -> str:
-        return self._shm.name
-
-    @property
-    def size(self) -> int:
-        return self._shm.size
-
-    @property
-    def ptr(self) -> int:
-        return self._ptr
-
-    @property
-    def write_fd(self) -> int:
-        return self._write_event.fd
-
-    @property
-    def wrap_fd(self) -> int:
-        return self._wrap_event.fd
-
-    async def send_all(self, data: bytes | bytearray | memoryview):
-        # while data is larger than the remaining buf
-        target_ptr = self.ptr + len(data)
-        while target_ptr > self.size:
-            # write all bytes that fit
-            remaining = self.size - self.ptr
-            self._shm.buf[self.ptr:] = data[:remaining]
-            # signal write and wait for reader wrap around
-            self._write_event.write(remaining)
-            await self._wrap_event.read()
-
-            # wrap around and trim already written bytes
-            self._ptr = 0
-            data = data[remaining:]
-            target_ptr = self._ptr + len(data)
-
-        # remaining data fits on buffer
-        self._shm.buf[self.ptr:target_ptr] = data
-        self._write_event.write(len(data))
-        self._ptr = target_ptr
-
-    async def wait_send_all_might_not_block(self):
-        raise NotImplementedError
-
-    async def aclose(self):
-        self._write_event.close()
-        self._wrap_event.close()
-        self._shm.close()
-
-    async def __aenter__(self):
-        self._write_event.open()
-        self._wrap_event.open()
-        return self
-
-
-class RingBuffReceiver(trio.abc.ReceiveStream):
-    '''
-    IPC Reliable Ring Buffer receiver side implementation
-
-    `eventfd(2)` is used for wrap around sync, and also to signal
-    writes to the reader.
-
-    '''
-    def __init__(
-        self,
-        token: RBToken,
-        start_ptr: int = 0,
-        flags: int = 0
-    ):
-        token = RBToken.from_msg(token)
-        self._shm = SharedMemory(
-            name=token.shm_name,
-            size=token.buf_size,
-            create=False
-        )
-        self._write_event = EventFD(token.write_eventfd, 'w')
-        self._wrap_event = EventFD(token.wrap_eventfd, 'r')
-        self._ptr = start_ptr
-        self._flags = flags
-
-    @property
-    def key(self) -> str:
-        return self._shm.name
-
-    @property
-    def size(self) -> int:
-        return self._shm.size
-
-    @property
-    def ptr(self) -> int:
-        return self._ptr
-
-    @property
-    def write_fd(self) -> int:
-        return self._write_event.fd
-
-    @property
-    def wrap_fd(self) -> int:
-        return self._wrap_event.fd
-
-    async def receive_some(
-        self,
-        max_bytes: int | None = None,
-        nb_timeout: float = 0.1
-    ) -> memoryview:
-        # if non blocking eventfd enabled, do polling
-        # until next write, this allows signal handling
-        if self._flags | EFD_NONBLOCK:
-            delta = None
-            while delta is None:
-                try:
-                    delta = await self._write_event.read()
-
-                except OSError as e:
-                    if e.errno == 'EAGAIN':
-                        continue
-
-                    raise e
-
-        else:
-            delta = await self._write_event.read()
-
-        # fetch next segment and advance ptr
-        next_ptr = self._ptr + delta
-        segment = self._shm.buf[self._ptr:next_ptr]
-        self._ptr = next_ptr
-
-        if self.ptr == self.size:
-            # reached the end, signal wrap around
-            self._ptr = 0
-            self._wrap_event.write(1)
-
-        return segment
-
-    async def aclose(self):
-        self._write_event.close()
-        self._wrap_event.close()
-        self._shm.close()
-
-    async def __aenter__(self):
-        self._write_event.open()
-        self._wrap_event.open()
-        return self

tractor/ipc/_tcp.py

@@ -1,254 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-'''
-TCP implementation of tractor.ipc._transport.MsgTransport protocol 
-
-'''
-from __future__ import annotations
-import ipaddress
-from typing import (
-    ClassVar,
-)
-# from contextlib import (
-#     asynccontextmanager as acm,
-# )
-
-import msgspec
-import trio
-from trio import (
-    SocketListener,
-    open_tcp_listeners,
-)
-
-from tractor.msg import MsgCodec
-from tractor.log import get_logger
-from tractor.ipc._transport import (
-    MsgTransport,
-    MsgpackTransport,
-)
-
-
-log = get_logger(__name__)
-
-
-class TCPAddress(
-    msgspec.Struct,
-    frozen=True,
-):
-    _host: str
-    _port: int
-
-    def __post_init__(self):
-        try:
-            ipaddress.ip_address(self._host)
-        except ValueError as valerr:
-            raise ValueError(
-                'Invalid {type(self).__name__}._host = {self._host!r}\n'
-            ) from valerr
-
-    proto_key: ClassVar[str] = 'tcp'
-    unwrapped_type: ClassVar[type] = tuple[str, int]
-    def_bindspace: ClassVar[str] = '127.0.0.1'
-
-    # ?TODO, actually validate ipv4/6 with stdlib's `ipaddress`
-    @property
-    def is_valid(self) -> bool:
-        '''
-        Predicate to ensure a valid socket-address pair.
-
-        '''
-        return (
-            self._port != 0
-            and
-            (ipaddr := ipaddress.ip_address(self._host))
-            and not (
-                ipaddr.is_reserved
-                or
-                ipaddr.is_unspecified
-                or
-                ipaddr.is_link_local
-                or
-                ipaddr.is_link_local
-                or
-                ipaddr.is_multicast
-                or
-                ipaddr.is_global
-            )
-        )
-        # ^XXX^ see various properties of invalid addrs here,
-        # https://docs.python.org/3/library/ipaddress.html#ipaddress.IPv4Address
-
-    @property
-    def bindspace(self) -> str:
-        return self._host
-
-    @property
-    def domain(self) -> str:
-        return self._host
-
-    @classmethod
-    def from_addr(
-        cls,
-        addr: tuple[str, int]
-    ) -> TCPAddress:
-        match addr:
-            case (str(), int()):
-                return TCPAddress(addr[0], addr[1])
-            case _:
-                raise ValueError(
-                    f'Invalid unwrapped address for {cls}\n'
-                    f'{addr}\n'
-                )
-
-    def unwrap(self) -> tuple[str, int]:
-        return (
-            self._host,
-            self._port,
-        )
-
-    @classmethod
-    def get_random(
-        cls,
-        bindspace: str = def_bindspace,
-    ) -> TCPAddress:
-        return TCPAddress(bindspace, 0)
-
-    @classmethod
-    def get_root(cls) -> TCPAddress:
-        return TCPAddress(
-            '127.0.0.1',
-            1616,
-        )
-
-    def __repr__(self) -> str:
-        return (
-            f'{type(self).__name__}[{self.unwrap()}]'
-        )
-
-    @classmethod
-    def get_transport(
-        cls,
-        codec: str = 'msgpack',
-    ) -> MsgTransport:
-        match codec:
-            case 'msgspack':
-                return MsgpackTCPStream
-            case _:
-                raise ValueError(
-                    f'No IPC transport with {codec!r} supported !'
-                )
-
-
-async def start_listener(
-    addr: TCPAddress,
-    **kwargs,
-) -> SocketListener:
-    '''
-    Start a TCP socket listener on the given `TCPAddress`.
-
-    '''
-    log.runtime(
-        f'Trying socket bind\n'
-        f'>[ {addr}\n'
-    )
-    # ?TODO, maybe we should just change the lower-level call this is
-    # using internall per-listener?
-    listeners: list[SocketListener] = await open_tcp_listeners(
-        host=addr._host,
-        port=addr._port,
-        **kwargs
-    )
-    # NOTE, for now we don't expect non-singleton-resolving
-    # domain-addresses/multi-homed-hosts.
-    # (though it is supported by `open_tcp_listeners()`)
-    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'[> {bound_addr}\n'
-    )
-    return listener
-
-
-# TODO: typing oddity.. not sure why we have to inherit here, but it
-# seems to be an issue with `get_msg_transport()` returning
-# a `Type[Protocol]`; probably should make a `mypy` issue?
-class MsgpackTCPStream(MsgpackTransport):
-    '''
-    A ``trio.SocketStream`` delivering ``msgpack`` formatted data
-    using the ``msgspec`` codec lib.
-
-    '''
-    address_type = TCPAddress
-    layer_key: int = 4
-
-    @property
-    def maddr(self) -> str:
-        host, port = self.raddr.unwrap()
-        return (
-            # TODO, use `ipaddress` from stdlib to handle
-            # first detecting which of `ipv4/6` before
-            # choosing the routing prefix part.
-            f'/ipv4/{host}'
-
-            f'/{self.address_type.proto_key}/{port}'
-            # f'/{self.chan.uid[0]}'
-            # f'/{self.cid}'
-
-            # f'/cid={cid_head}..{cid_tail}'
-            # TODO: ? not use this ^ right ?
-        )
-
-    def connected(self) -> bool:
-        return self.stream.socket.fileno() != -1
-
-    @classmethod
-    async def connect_to(
-        cls,
-        destaddr: TCPAddress,
-        prefix_size: int = 4,
-        codec: MsgCodec|None = None,
-        **kwargs
-    ) -> MsgpackTCPStream:
-        stream = await trio.open_tcp_stream(
-            *destaddr.unwrap(),
-            **kwargs
-        )
-        return MsgpackTCPStream(
-            stream,
-            prefix_size=prefix_size,
-            codec=codec
-        )
-
-    @classmethod
-    def get_stream_addrs(
-        cls,
-        stream: trio.SocketStream
-    ) -> tuple[
-        TCPAddress,
-        TCPAddress,
-    ]:
-        # TODO, what types are these?
-        lsockname = stream.socket.getsockname()
-        l_sockaddr: tuple[str, int] = tuple(lsockname[:2])
-        rsockname = stream.socket.getpeername()
-        r_sockaddr: tuple[str, int] = tuple(rsockname[:2])
-        return (
-            TCPAddress.from_addr(l_sockaddr),
-            TCPAddress.from_addr(r_sockaddr),
-        )

tractor/ipc/_transport.py

@@ -1,536 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-'''
-typing.Protocol based generic msg API, implement this class to add
-backends for tractor.ipc.Channel
-
-'''
-from __future__ import annotations
-from typing import (
-    runtime_checkable,
-    Type,
-    Protocol,
-    # TypeVar,
-    ClassVar,
-    TYPE_CHECKING,
-)
-from collections.abc import (
-    AsyncGenerator,
-    AsyncIterator,
-)
-import struct
-
-import trio
-import msgspec
-from tricycle import BufferedReceiveStream
-
-from tractor.log import get_logger
-from tractor._exceptions import (
-    MsgTypeError,
-    TransportClosed,
-    _mk_send_mte,
-    _mk_recv_mte,
-)
-from tractor.msg import (
-    _ctxvar_MsgCodec,
-    # _codec,  XXX see `self._codec` sanity/debug checks
-    MsgCodec,
-    MsgType,
-    types as msgtypes,
-    pretty_struct,
-)
-
-if TYPE_CHECKING:
-    from tractor._addr import Address
-
-log = get_logger(__name__)
-
-
-# (codec, transport)
-MsgTransportKey = tuple[str, str]
-
-
-# from tractor.msg.types import MsgType
-# ?TODO? this should be our `Union[*msgtypes.__spec__]` alias now right..?
-# => BLEH, except can't bc prots must inherit typevar or param-spec
-#   vars..
-# MsgType = TypeVar('MsgType')
-
-
-@runtime_checkable
-class MsgTransport(Protocol):
-#
-# class MsgTransport(Protocol[MsgType]):
-# ^-TODO-^ consider using a generic def and indexing with our
-# eventual msg definition/types?
-# - https://docs.python.org/3/library/typing.html#typing.Protocol
-
-    stream: trio.SocketStream
-    drained: list[MsgType]
-
-    address_type: ClassVar[Type[Address]]
-    codec_key: ClassVar[str]
-
-    # XXX: should this instead be called `.sendall()`?
-    async def send(self, msg: MsgType) -> None:
-        ...
-
-    async def recv(self) -> MsgType:
-        ...
-
-    def __aiter__(self) -> MsgType:
-        ...
-
-    def connected(self) -> bool:
-        ...
-
-    # defining this sync otherwise it causes a mypy error because it
-    # can't figure out it's a generator i guess?..?
-    def drain(self) -> AsyncIterator[dict]:
-        ...
-
-    @classmethod
-    def key(cls) -> MsgTransportKey:
-        return (
-            cls.codec_key,
-            cls.address_type.proto_key,
-        )
-
-    @property
-    def laddr(self) -> Address:
-        ...
-
-    @property
-    def raddr(self) -> Address:
-        ...
-
-    @property
-    def maddr(self) -> str:
-        ...
-
-    @classmethod
-    async def connect_to(
-        cls,
-        addr: Address,
-        **kwargs
-    ) -> MsgTransport:
-        ...
-
-    @classmethod
-    def get_stream_addrs(
-        cls,
-        stream: trio.abc.Stream
-    ) -> tuple[
-        Address,  # local
-        Address   # remote
-    ]:
-        '''
-        Return the transport protocol's address pair for the local
-        and remote-peer side.
-
-        '''
-        ...
-
-    # TODO, such that all `.raddr`s for each `SocketStream` are
-    # delivered?
-    # -[ ] move `.open_listener()` here and internally track the
-    #     listener set, per address?
-    # def get_peers(
-    #     self,
-    # ) -> list[Address]:
-    #     ...
-
-
-
-class MsgpackTransport(MsgTransport):
-
-    # TODO: better naming for this?
-    # -[ ] check how libp2p does naming for such things?
-    codec_key: str = 'msgpack'
-
-    def __init__(
-        self,
-        stream: trio.abc.Stream,
-        prefix_size: int = 4,
-
-        # XXX optionally provided codec pair for `msgspec`:
-        # https://jcristharif.com/msgspec/extending.html#mapping-to-from-native-types
-        #
-        # TODO: define this as a `Codec` struct which can be
-        # overriden dynamically by the application/runtime?
-        codec: MsgCodec = None,
-
-    ) -> None:
-        self.stream = stream
-        (
-            self._laddr,
-            self._raddr,
-        ) = self.get_stream_addrs(stream)
-
-        # create read loop instance
-        self._aiter_pkts = self._iter_packets()
-        self._send_lock = trio.StrictFIFOLock()
-
-        # public i guess?
-        self.drained: list[dict] = []
-
-        self.recv_stream = BufferedReceiveStream(
-            transport_stream=stream
-        )
-        self.prefix_size = prefix_size
-
-        # allow for custom IPC msg interchange format
-        # dynamic override Bo
-        self._task = trio.lowlevel.current_task()
-
-        # XXX for ctxvar debug only!
-        # self._codec: MsgCodec = (
-        #     codec
-        #     or
-        #     _codec._ctxvar_MsgCodec.get()
-        # )
-
-    async def _iter_packets(self) -> AsyncGenerator[dict, None]:
-        '''
-        Yield `bytes`-blob decoded packets from the underlying TCP
-        stream using the current task's `MsgCodec`.
-
-        This is a streaming routine implemented as an async generator
-        func (which was the original design, but could be changed?)
-        and is allocated by a `.__call__()` inside `.__init__()` where
-        it is assigned to the `._aiter_pkts` attr.
-
-        '''
-        decodes_failed: int = 0
-
-        tpt_name: str = f'{type(self).__name__!r}'
-        while True:
-            try:
-                header: bytes = await self.recv_stream.receive_exactly(4)
-            except (
-                ValueError,
-                ConnectionResetError,
-
-                # not sure entirely why we need this but without it we
-                # seem to be getting racy failures here on
-                # arbiter/registry name subs..
-                trio.BrokenResourceError,
-
-            ) as trans_err:
-
-                loglevel = 'transport'
-                match trans_err:
-                    # case (
-                    #     ConnectionResetError()
-                    # ):
-                    #     loglevel = 'transport'
-
-                    # peer actor (graceful??) TCP EOF but `tricycle`
-                    # seems to raise a 0-bytes-read?
-                    case ValueError() if (
-                        'unclean EOF' in trans_err.args[0]
-                    ):
-                        pass
-
-                    # peer actor (task) prolly shutdown quickly due
-                    # to cancellation
-                    case trio.BrokenResourceError() if (
-                        'Connection reset by peer' in trans_err.args[0]
-                    ):
-                        pass
-
-                    # unless the disconnect condition falls under "a
-                    # normal operation breakage" we usualy console warn
-                    # about it.
-                    case _:
-                        loglevel: str = 'warning'
-
-
-                raise TransportClosed(
-                    message=(
-                        f'{tpt_name} already closed by peer\n'
-                    ),
-                    src_exc=trans_err,
-                    loglevel=loglevel,
-                ) from trans_err
-
-            # XXX definitely can happen if transport is closed
-            # manually by another `trio.lowlevel.Task` in the
-            # same actor; we use this in some simulated fault
-            # testing for ex, but generally should never happen
-            # under normal operation!
-            #
-            # NOTE: as such we always re-raise this error from the
-            #       RPC msg loop!
-            except trio.ClosedResourceError as cre:
-                closure_err = cre
-
-                raise TransportClosed(
-                    message=(
-                        f'{tpt_name} was already closed locally ?\n'
-                    ),
-                    src_exc=closure_err,
-                    loglevel='error',
-                    raise_on_report=(
-                        'another task closed this fd' in closure_err.args
-                    ),
-                ) from closure_err
-
-            # graceful TCP EOF disconnect
-            if header == b'':
-                raise TransportClosed(
-                    message=(
-                        f'{tpt_name} already gracefully closed\n'
-                    ),
-                    loglevel='transport',
-                )
-
-            size: int
-            size, = struct.unpack("<I", header)
-
-            log.transport(f'received header {size}')  # type: ignore
-            msg_bytes: bytes = await self.recv_stream.receive_exactly(size)
-
-            log.transport(f"received {msg_bytes}")  # type: ignore
-            try:
-                # NOTE: lookup the `trio.Task.context`'s var for
-                # the current `MsgCodec`.
-                codec: MsgCodec = _ctxvar_MsgCodec.get()
-
-                # XXX for ctxvar debug only!
-                # if self._codec.pld_spec != codec.pld_spec:
-                #     assert (
-                #         task := trio.lowlevel.current_task()
-                #     ) is not self._task
-                #     self._task = task
-                #     self._codec = codec
-                #     log.runtime(
-                #         f'Using new codec in {self}.recv()\n'
-                #         f'codec: {self._codec}\n\n'
-                #         f'msg_bytes: {msg_bytes}\n'
-                #     )
-                yield codec.decode(msg_bytes)
-
-            # XXX NOTE: since the below error derives from
-            # `DecodeError` we need to catch is specially
-            # and always raise such that spec violations
-            # are never allowed to be caught silently!
-            except msgspec.ValidationError as verr:
-                msgtyperr: MsgTypeError = _mk_recv_mte(
-                    msg=msg_bytes,
-                    codec=codec,
-                    src_validation_error=verr,
-                )
-                # XXX deliver up to `Channel.recv()` where
-                # a re-raise and `Error`-pack can inject the far
-                # end actor `.uid`.
-                yield msgtyperr
-
-            except (
-                msgspec.DecodeError,
-                UnicodeDecodeError,
-            ):
-                if decodes_failed < 4:
-                    # ignore decoding errors for now and assume they have to
-                    # do with a channel drop - hope that receiving from the
-                    # channel will raise an expected error and bubble up.
-                    try:
-                        msg_str: str|bytes = msg_bytes.decode()
-                    except UnicodeDecodeError:
-                        msg_str = msg_bytes
-
-                    log.exception(
-                        'Failed to decode msg?\n'
-                        f'{codec}\n\n'
-                        'Rxed bytes from wire:\n\n'
-                        f'{msg_str!r}\n'
-                    )
-                    decodes_failed += 1
-                else:
-                    raise
-
-    async def send(
-        self,
-        msg: msgtypes.MsgType,
-
-        strict_types: bool = True,
-        hide_tb: bool = True,
-
-    ) -> None:
-        '''
-        Send a msgpack encoded py-object-blob-as-msg over TCP.
-
-        If `strict_types == True` then a `MsgTypeError` will be raised on any
-        invalid msg type
-
-        '''
-        __tracebackhide__: bool = hide_tb
-
-        # XXX see `trio._sync.AsyncContextManagerMixin` for details
-        # on the `.acquire()`/`.release()` sequencing..
-        async with self._send_lock:
-
-            # NOTE: lookup the `trio.Task.context`'s var for
-            # the current `MsgCodec`.
-            codec: MsgCodec = _ctxvar_MsgCodec.get()
-
-            # XXX for ctxvar debug only!
-            # if self._codec.pld_spec != codec.pld_spec:
-            #     self._codec = codec
-            #     log.runtime(
-            #         f'Using new codec in {self}.send()\n'
-            #         f'codec: {self._codec}\n\n'
-            #         f'msg: {msg}\n'
-            #     )
-
-            if type(msg) not in msgtypes.__msg_types__:
-                if strict_types:
-                    raise _mk_send_mte(
-                        msg,
-                        codec=codec,
-                    )
-                else:
-                    log.warning(
-                        'Sending non-`Msg`-spec msg?\n\n'
-                        f'{msg}\n'
-                    )
-
-            try:
-                bytes_data: bytes = codec.encode(msg)
-            except TypeError as _err:
-                typerr = _err
-                msgtyperr: MsgTypeError = _mk_send_mte(
-                    msg,
-                    codec=codec,
-                    message=(
-                        f'IPC-msg-spec violation in\n\n'
-                        f'{pretty_struct.Struct.pformat(msg)}'
-                    ),
-                    src_type_error=typerr,
-                )
-                raise msgtyperr from typerr
-
-            # supposedly the fastest says,
-            # https://stackoverflow.com/a/54027962
-            size: bytes = struct.pack("<I", len(bytes_data))
-            try:
-                return await self.stream.send_all(size + bytes_data)
-            except (
-                trio.BrokenResourceError,
-                trio.ClosedResourceError,
-            ) as _re:
-                trans_err = _re
-                tpt_name: str = f'{type(self).__name__!r}'
-
-                match trans_err:
-
-                    # XXX, specifc to UDS transport and its,
-                    # well, "speediness".. XD
-                    # |_ likely todo with races related to how fast
-                    #    the socket is setup/torn-down on linux
-                    #    as it pertains to rando pings from the
-                    #    `.discovery` subsys and protos.
-                    case trio.BrokenResourceError() if (
-                        '[Errno 32] Broken pipe'
-                        in
-                        trans_err.args[0]
-                    ):
-                        tpt_closed = TransportClosed.from_src_exc(
-                            message=(
-                                f'{tpt_name} already closed by peer\n'
-                            ),
-                            body=f'{self}\n',
-                            src_exc=trans_err,
-                            raise_on_report=True,
-                            loglevel='transport',
-                        )
-                        raise tpt_closed from trans_err
-
-                    # case trio.ClosedResourceError() if (
-                    #     'this socket was already closed'
-                    #     in
-                    #     trans_err.args[0]
-                    # ):
-                    #     tpt_closed = TransportClosed.from_src_exc(
-                    #         message=(
-                    #             f'{tpt_name} already closed by peer\n'
-                    #         ),
-                    #         body=f'{self}\n',
-                    #         src_exc=trans_err,
-                    #         raise_on_report=True,
-                    #         loglevel='transport',
-                    #     )
-                    #     raise tpt_closed from trans_err
-
-                    # unless the disconnect condition falls under "a
-                    # normal operation breakage" we usualy console warn
-                    # about it.
-                    case _:
-                        log.exception(
-                            f'{tpt_name} layer failed pre-send ??\n'
-                        )
-                        raise trans_err
-
-        # ?TODO? does it help ever to dynamically show this
-        # frame?
-        # try:
-        #     <the-above_code>
-        # except BaseException as _err:
-        #     err = _err
-        #     if not isinstance(err, MsgTypeError):
-        #         __tracebackhide__: bool = False
-        #     raise
-
-    async def recv(self) -> msgtypes.MsgType:
-        return await self._aiter_pkts.asend(None)
-
-    async def drain(self) -> AsyncIterator[dict]:
-        '''
-        Drain the stream's remaining messages sent from
-        the far end until the connection is closed by
-        the peer.
-
-        '''
-        try:
-            async for msg in self._iter_packets():
-                self.drained.append(msg)
-        except TransportClosed:
-            for msg in self.drained:
-                yield msg
-
-    def __aiter__(self):
-        return self._aiter_pkts
-
-    @property
-    def laddr(self) -> Address:
-        return self._laddr
-
-    @property
-    def raddr(self) -> Address:
-        return self._raddr
-
-    def pformat(self) -> str:
-        return (
-            f'<{type(self).__name__}(\n'
-            f' |_peers: 1\n'
-            f'   laddr: {self._laddr}\n'
-            f'   raddr: {self._raddr}\n'
-            # f'\n'
-            f' |_task: {self._task}\n'
-            f')>\n'
-        )
-
-    __repr__ = __str__ = pformat

tractor/ipc/_types.py

@@ -1,123 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-
-'''
-IPC subsys type-lookup helpers?
-
-'''
-from typing import (
-    Type,
-    # TYPE_CHECKING,
-)
-
-import trio
-import socket
-
-from tractor.ipc._transport import (
-    MsgTransportKey,
-    MsgTransport
-)
-from tractor.ipc._tcp import (
-    TCPAddress,
-    MsgpackTCPStream,
-)
-from tractor.ipc._uds import (
-    UDSAddress,
-    MsgpackUDSStream,
-)
-
-# if TYPE_CHECKING:
-#     from tractor._addr import Address
-
-
-Address = TCPAddress|UDSAddress
-
-# manually updated list of all supported msg transport types
-_msg_transports = [
-    MsgpackTCPStream,
-    MsgpackUDSStream
-]
-
-
-# convert a MsgTransportKey to the corresponding transport type
-_key_to_transport: dict[
-    MsgTransportKey,
-    Type[MsgTransport],
-] = {
-    ('msgpack', 'tcp'): MsgpackTCPStream,
-    ('msgpack', 'uds'): MsgpackUDSStream,
-}
-
-# convert an Address wrapper to its corresponding transport type
-_addr_to_transport: dict[
-    Type[TCPAddress|UDSAddress],
-    Type[MsgTransport]
-] = {
-    TCPAddress: MsgpackTCPStream,
-    UDSAddress: MsgpackUDSStream,
-}
-
-
-def transport_from_addr(
-    addr: Address,
-    codec_key: str = 'msgpack',
-) -> Type[MsgTransport]:
-    '''
-    Given a destination address and a desired codec, find the
-    corresponding `MsgTransport` type.
-
-    '''
-    try:
-        return _addr_to_transport[type(addr)]
-
-    except KeyError:
-        raise NotImplementedError(
-            f'No known transport for address {repr(addr)}'
-        )
-
-
-def transport_from_stream(
-    stream: trio.abc.Stream,
-    codec_key: str = 'msgpack'
-) -> Type[MsgTransport]:
-    '''
-    Given an arbitrary `trio.abc.Stream` and a desired codec,
-    find the corresponding `MsgTransport` type.
-
-    '''
-    transport = None
-    if isinstance(stream, trio.SocketStream):
-        sock: socket.socket = stream.socket
-        match sock.family:
-            case socket.AF_INET | socket.AF_INET6:
-                transport = 'tcp'
-
-            case socket.AF_UNIX:
-                transport = 'uds'
-
-            case _:
-                raise NotImplementedError(
-                    f'Unsupported socket family: {sock.family}'
-                )
-
-    if not transport:
-        raise NotImplementedError(
-            f'Could not figure out transport type for stream type {type(stream)}'
-        )
-
-    key = (codec_key, transport)
-
-    return _key_to_transport[key]

tractor/ipc/_uds.py

@@ -1,458 +0,0 @@
-# tractor: structured concurrent "actors".
-# Copyright 2018-eternity Tyler Goodlet.
-
-# This program is free software: you can redistribute it and/or modify
-# it under the terms of the GNU Affero General Public License as published by
-# the Free Software Foundation, either version 3 of the License, or
-# (at your option) any later version.
-
-# This program is distributed in the hope that it will be useful,
-# but WITHOUT ANY WARRANTY; without even the implied warranty of
-# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
-# GNU Affero General Public License for more details.
-
-# You should have received a copy of the GNU Affero General Public License
-# along with this program.  If not, see <https://www.gnu.org/licenses/>.
-'''
-Unix Domain Socket implementation of tractor.ipc._transport.MsgTransport protocol 
-
-'''
-from __future__ import annotations
-from contextlib import (
-    contextmanager as cm,
-)
-from pathlib import Path
-import os
-from socket import (
-    AF_UNIX,
-    SOCK_STREAM,
-    SO_PASSCRED,
-    SO_PEERCRED,
-    SOL_SOCKET,
-)
-import struct
-from typing import (
-    Type,
-    TYPE_CHECKING,
-    ClassVar,
-)
-
-import msgspec
-import trio
-from trio import (
-    socket,
-    SocketListener,
-)
-from trio._highlevel_open_unix_stream import (
-    close_on_error,
-    has_unix,
-)
-
-from tractor.msg import MsgCodec
-from tractor.log import get_logger
-from tractor.ipc._transport import (
-    MsgpackTransport,
-)
-from .._state import (
-    get_rt_dir,
-    current_actor,
-    is_root_process,
-)
-
-if TYPE_CHECKING:
-    from ._runtime import Actor
-
-
-log = get_logger(__name__)
-
-
-def unwrap_sockpath(
-    sockpath: Path,
-) -> tuple[Path, Path]:
-    return (
-        sockpath.parent,
-        sockpath.name,
-    )
-
-
-class UDSAddress(
-    msgspec.Struct,
-    frozen=True,
-):
-    filedir: str|Path|None
-    filename: str|Path
-    maybe_pid: int|None = None
-
-    # TODO, maybe we should use better field and value
-    # -[x] really this is a `.protocol_key` not a "name" of anything.
-    # -[ ] consider a 'unix' proto-key instead?
-    # -[ ] need to check what other mult-transport frameworks do
-    #     like zmq, nng, uri-spec et al!
-    proto_key: ClassVar[str] = 'uds'
-    unwrapped_type: ClassVar[type] = tuple[str, int]
-    def_bindspace: ClassVar[Path] = get_rt_dir()
-
-    @property
-    def bindspace(self) -> Path:
-        '''
-        We replicate the "ip-set-of-hosts" part of a UDS socket as
-        just the sub-directory in which we allocate socket files.
-
-        '''
-        return (
-            self.filedir
-            or
-            self.def_bindspace
-        )
-
-    @property
-    def sockpath(self) -> Path:
-        return self.bindspace / self.filename
-
-    @property
-    def is_valid(self) -> bool:
-        '''
-        We block socket files not allocated under the runtime subdir.
-
-        '''
-        return self.bindspace in self.sockpath.parents
-
-    @classmethod
-    def from_addr(
-        cls,
-        addr: (
-            tuple[Path|str, Path|str]|Path|str
-        ),
-    ) -> UDSAddress:
-        match addr:
-            case tuple()|list():
-                filedir = Path(addr[0])
-                filename = Path(addr[1])
-                return UDSAddress(
-                    filedir=filedir,
-                    filename=filename,
-                    # maybe_pid=pid,
-                )
-            # NOTE, in case we ever decide to just `.unwrap()`
-            # to a `Path|str`?
-            case str()|Path():
-                sockpath: Path = Path(addr)
-                return UDSAddress(*unwrap_sockpath(sockpath))
-            case _:
-                # import pdbp; pdbp.set_trace()
-                raise TypeError(
-                    f'Bad unwrapped-address for {cls} !\n'
-                    f'{addr!r}\n'
-                )
-
-    def unwrap(self) -> tuple[str, int]:
-        # XXX NOTE, since this gets passed DIRECTLY to
-        # `.ipc._uds.open_unix_socket_w_passcred()`
-        return (
-            str(self.filedir),
-            str(self.filename),
-        )
-
-    @classmethod
-    def get_random(
-        cls,
-        bindspace: Path|None = None,  # default netns
-    ) -> UDSAddress:
-
-        filedir: Path = bindspace or cls.def_bindspace
-        pid: int = os.getpid()
-        actor: Actor|None = current_actor(
-            err_on_no_runtime=False,
-        )
-        if actor:
-            sockname: str = '::'.join(actor.uid) + f'@{pid}'
-        else:
-            prefix: str = '<unknown-actor>'
-            if is_root_process():
-                prefix: str = 'root'
-            sockname: str = f'{prefix}@{pid}'
-
-        sockpath: Path = Path(f'{sockname}.sock')
-        return UDSAddress(
-            filedir=filedir,
-            filename=sockpath,
-            maybe_pid=pid,
-        )
-
-    @classmethod
-    def get_root(cls) -> UDSAddress:
-        def_uds_filename: Path = 'registry@1616.sock'
-        return UDSAddress(
-            filedir=cls.def_bindspace,
-            filename=def_uds_filename,
-            # maybe_pid=1616,
-        )
-
-    # ?TODO, maybe we should just our .msg.pretty_struct.Struct` for
-    # this instead?
-    # -[ ] is it too "multi-line"y tho?
-    #      the compact tuple/.unwrapped() form is simple enough?
-    #
-    def __repr__(self) -> str:
-        if not (pid := self.maybe_pid):
-            pid: str = '<unknown-peer-pid>'
-
-        body: str = (
-            f'({self.filedir}, {self.filename}, {pid})'
-        )
-        return (
-            f'{type(self).__name__}'
-            f'['
-            f'{body}'
-            f']'
-        )
-
-@cm
-def _reraise_as_connerr(
-    src_excs: tuple[Type[Exception]],
-    addr: UDSAddress,
-):
-    try:
-        yield
-    except src_excs as src_exc:
-        raise ConnectionError(
-            f'Bad UDS socket-filepath-as-address ??\n'
-            f'{addr}\n'
-            f' |_sockpath: {addr.sockpath}\n'
-            f'\n'
-            f'from src: {src_exc!r}\n'
-        ) from src_exc
-
-
-async def start_listener(
-    addr: UDSAddress,
-    **kwargs,
-) -> SocketListener:
-    '''
-    Start listening for inbound connections via
-    a `trio.SocketListener` (task) which `socket.bind()`s on `addr`.
-
-    Note, if the `UDSAddress.bindspace: Path` directory dne it is
-    implicitly created.
-
-    '''
-    sock = socket.socket(
-        socket.AF_UNIX,
-        socket.SOCK_STREAM
-    )
-    log.info(
-        f'Attempting to bind UDS socket\n'
-        f'>[\n'
-        f'|_{addr}\n'
-    )
-
-    # ?TODO? should we use the `actor.lifetime_stack`
-    # to rm on shutdown?
-    bindpath: Path = addr.sockpath
-    if not (bs := addr.bindspace).is_dir():
-        log.info(
-            'Creating bindspace dir in file-sys\n'
-            f'>{{\n'
-            f'|_{bs!r}\n'
-        )
-        bs.mkdir()
-
-    with _reraise_as_connerr(
-        src_excs=(
-            FileNotFoundError,
-            OSError,
-        ),
-        addr=addr
-    ):
-        await sock.bind(str(bindpath))
-
-    sock.listen(1)
-    log.info(
-        f'Listening on UDS socket\n'
-        f'[>\n'
-        f' |_{addr}\n'
-    )
-    return SocketListener(sock)
-
-
-def close_listener(
-    addr: UDSAddress,
-    lstnr: SocketListener,
-) -> None:
-    '''
-    Close and remove the listening unix socket's path.
-
-    '''
-    lstnr.socket.close()
-    os.unlink(addr.sockpath)
-
-
-async def open_unix_socket_w_passcred(
-    filename: str|bytes|os.PathLike[str]|os.PathLike[bytes],
-) -> trio.SocketStream:
-    '''
-    Literally the exact same as `trio.open_unix_socket()` except we set the additiona
-    `socket.SO_PASSCRED` option to ensure the server side (the process calling `accept()`)
-    can extract the connecting peer's credentials, namely OS specific process
-    related IDs.
-
-    See this SO for "why" the extra opts,
-    - https://stackoverflow.com/a/7982749
-
-    '''
-    if not has_unix:
-        raise RuntimeError("Unix sockets are not supported on this platform")
-
-    # much more simplified logic vs tcp sockets - one socket type and only one
-    # possible location to connect to
-    sock = trio.socket.socket(AF_UNIX, SOCK_STREAM)
-    sock.setsockopt(SOL_SOCKET, SO_PASSCRED, 1)
-    with close_on_error(sock):
-        await sock.connect(os.fspath(filename))
-
-    return trio.SocketStream(sock)
-
-
-def get_peer_info(sock: trio.socket.socket) -> tuple[
-    int,  # pid
-    int,  # uid
-    int,  # guid
-]:
-    '''
-    Deliver the connecting peer's "credentials"-info as defined in
-    a very Linux specific way..
-
-    For more deats see,
-    - `man accept`,
-    - `man unix`,
-
-    this great online guide to all things sockets,
-    - https://beej.us/guide/bgnet/html/split-wide/man-pages.html#setsockoptman
-
-    AND this **wonderful SO answer**
-    - https://stackoverflow.com/a/7982749
-
-    '''
-    creds: bytes = sock.getsockopt(
-        SOL_SOCKET,
-        SO_PEERCRED,
-        struct.calcsize('3i')
-    )
-    # i.e a tuple of the fields,
-    # pid: int, "process"
-    # uid: int, "user"
-    # gid: int, "group"
-    return struct.unpack('3i', creds)
-
-
-class MsgpackUDSStream(MsgpackTransport):
-    '''
-    A `trio.SocketStream` around a Unix-Domain-Socket transport
-    delivering `msgpack` encoded msgs using the `msgspec` codec lib.
-
-    '''
-    address_type = UDSAddress
-    layer_key: int = 4
-
-    @property
-    def maddr(self) -> str:
-        if not self.raddr:
-            return '<unknown-peer>'
-
-        filepath: Path = Path(self.raddr.unwrap()[0])
-        return (
-            f'/{self.address_type.proto_key}/{filepath}'
-            # f'/{self.chan.uid[0]}'
-            # f'/{self.cid}'
-
-            # f'/cid={cid_head}..{cid_tail}'
-            # TODO: ? not use this ^ right ?
-        )
-
-    def connected(self) -> bool:
-        return self.stream.socket.fileno() != -1
-
-    @classmethod
-    async def connect_to(
-        cls,
-        addr: UDSAddress,
-        prefix_size: int = 4,
-        codec: MsgCodec|None = None,
-        **kwargs
-    ) -> MsgpackUDSStream:
-
-
-        sockpath: Path = addr.sockpath
-        #
-        # ^XXX NOTE, we don't provide any out-of-band `.pid` info
-        # (like, over the socket as extra msgs) since the (augmented)
-        # `.setsockopt()` call tells the OS provide it; the client
-        # pid can then be read on server/listen() side via
-        # `get_peer_info()` above.
-
-        with _reraise_as_connerr(
-            src_excs=(
-                FileNotFoundError,
-            ),
-            addr=addr
-        ):
-            stream = await open_unix_socket_w_passcred(
-                str(sockpath),
-                **kwargs
-            )
-
-        tpt_stream = MsgpackUDSStream(
-            stream,
-            prefix_size=prefix_size,
-            codec=codec
-        )
-        # XXX assign from new addrs after peer-PID extract!
-        (
-            tpt_stream._laddr,
-            tpt_stream._raddr,
-        ) = cls.get_stream_addrs(stream)
-
-        return tpt_stream
-
-    @classmethod
-    def get_stream_addrs(
-        cls,
-        stream: trio.SocketStream
-    ) -> tuple[
-        Path,
-        int,
-    ]:
-        sock: trio.socket.socket = stream.socket
-
-        # NOTE XXX, it's unclear why one or the other ends up being
-        # `bytes` versus the socket-file-path, i presume it's
-        # something to do with who is the server (called `.listen()`)?
-        # maybe could be better implemented using another info-query
-        # on the socket like,
-        # https://beej.us/guide/bgnet/html/split-wide/system-calls-or-bust.html#gethostnamewho-am-i
-        sockname: str|bytes = sock.getsockname()
-        # https://beej.us/guide/bgnet/html/split-wide/system-calls-or-bust.html#getpeernamewho-are-you
-        peername: str|bytes = sock.getpeername()
-        match (peername, sockname):
-            case (str(), bytes()):
-                sock_path: Path = Path(peername)
-            case (bytes(), str()):
-                sock_path: Path = Path(sockname)
-        (
-            peer_pid,
-            _,
-            _,
-        ) = get_peer_info(sock)
-
-        filedir, filename = unwrap_sockpath(sock_path)
-        laddr = UDSAddress(
-            filedir=filedir,
-            filename=filename,
-            maybe_pid=os.getpid(),
-        )
-        raddr = UDSAddress(
-            filedir=filedir,
-            filename=filename,
-            maybe_pid=peer_pid
-        )
-        return (laddr, raddr)

tractor/log.py

@@ -81,35 +81,10 @@ 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,
@@ -117,7 +92,7 @@ class StackLevelAdapter(LoggerAdapter):
     ) -> None:
         '''
         IPC transport level msg IO; generally anything below
-        `.ipc.Channel` and friends.
+        `._ipc.Channel` and friends.
 
         '''
         return self.log(5, msg)
@@ -295,9 +270,7 @@ def get_logger(
     subsys_spec: str|None = None,
 
 ) -> StackLevelAdapter:
-    '''
+    '''Return the package log or a sub-logger for ``name`` if provided.
-    Return the `tractor`-library root logger or a sub-logger for
-    `name` if provided.
 
     '''
     log: Logger
@@ -309,10 +282,10 @@ def get_logger(
         name != _proj_name
     ):
 
-        # NOTE: for handling for modules that use `get_logger(__name__)`
+        # NOTE: for handling for modules that use ``get_logger(__name__)``
         # we make the following stylistic choice:
         # - always avoid duplicate project-package token
-        #   in msg output: i.e. tractor.tractor.ipc._chan.py in header
+        #   in msg output: i.e. tractor.tractor _ipc.py in header
         #   looks ridiculous XD
         # - never show the leaf module name in the {name} part
         #   since in python the {filename} is always this same
@@ -358,7 +331,7 @@ def get_logger(
 
 def get_console_log(
     level: str|None = None,
-    logger: Logger|StackLevelAdapter|None = None,
+    logger: Logger|None = None,
     **kwargs,
 
 ) -> LoggerAdapter:
@@ -371,23 +344,12 @@ def get_console_log(
     Yeah yeah, i know we can use `logging.config.dictConfig()`. You do it.
 
     '''
-    # get/create a stack-aware-adapter
+    log = get_logger(
-    if (
+        logger=logger,
-        logger
+        **kwargs
-        and
+    )  # set a root logger
-        isinstance(logger, StackLevelAdapter)
+    logger: Logger = log.logger
-    ):
-        # XXX, for ex. when passed in by a caller wrapping some
-        # other lib's logger instance with our level-adapter.
-        log = logger
 
-    else:
-        log: StackLevelAdapter = get_logger(
-            logger=logger,
-            **kwargs
-        )
-
-    logger: Logger|StackLevelAdapter = log.logger
     if not level:
         return log
 
@@ -405,7 +367,10 @@ def get_console_log(
             None,
         )
     ):
-        fmt: str = LOG_FORMAT  # always apply our format?
+        fmt = LOG_FORMAT
+        # if logger:
+        #     fmt = None
+
         handler = StreamHandler()
         formatter = colorlog.ColoredFormatter(
             fmt=fmt,
@@ -426,3 +391,19 @@ 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

@@ -210,14 +210,12 @@ 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:
@@ -263,9 +261,8 @@ class PldRx(Struct):
         if (
             type(msg) is Return
         ):
-            log.runtime(
+            log.info(
                 f'Rxed final result msg\n'
-                f'\n'
                 f'{msg}\n'
             )
         return self.decode_pld(
@@ -307,13 +304,10 @@ class PldRx(Struct):
                 try:
                     pld: PayloadT = self._pld_dec.decode(pld)
                     log.runtime(
-                        f'Decoded payload for\n'
+                        'Decoded msg payload\n\n'
-                        # f'\n'
                         f'{msg}\n'
-                        # ^TODO?, ideally just render with `,
+                        f'where payload decoded as\n'
-                        # pld={decode}` in the `msg.pformat()`??
+                        f'|_pld={pld!r}\n'
-                        f'where, '
-                        f'{type(msg).__name__}.pld={pld!r}\n'
                     )
                     return pld
                 except TypeError as typerr:
@@ -500,8 +494,7 @@ def limit_plds(
 
     finally:
         log.runtime(
-            f'Reverted to previous payload-decoder\n'
+            'Reverted to previous payload-decoder\n\n'
-            f'\n'
             f'{orig_pldec}\n'
         )
         # sanity on orig settings
@@ -613,9 +606,10 @@ async def drain_to_final_msg(
             #       msg: dict = await ctx._rx_chan.receive()
             #   if res_cs.cancelled_caught:
             #
-            # -[x] make sure pause points work here for REPLing
+            # -[ ] make sure pause points work here for REPLing
             #   the runtime itself; i.e. ensure there's no hangs!
-            #  |_see masked code below in .cancel_called path
+            # |_from tractor.devx._debug import pause
+            #   await pause()
 
         # NOTE: we get here if the far end was
         # `ContextCancelled` in 2 cases:
@@ -635,8 +629,7 @@ async def drain_to_final_msg(
                     (local_cs := rent_n.cancel_scope).cancel_called
                 ):
                     log.cancel(
-                        f'RPC-ctx cancelled by local-parent scope during drain!\n'
+                        'RPC-ctx cancelled by local-parent scope during drain!\n\n'
-                        f'\n'
                         f'c}}>\n'
                         f' |_{rent_n}\n'
                         f'   |_.cancel_scope = {local_cs}\n'
@@ -651,10 +644,6 @@ async def drain_to_final_msg(
                     f'IPC ctx cancelled externally during result drain ?\n'
                     f'{ctx}'
                 )
-                # XXX, for tracing `Cancelled`..
-                # from tractor.devx.debug import pause
-                # await pause(shield=True)
-
             # CASE 2: mask the local cancelled-error(s)
             # only when we are sure the remote error is
             # the source cause of this local task's
@@ -674,8 +663,7 @@ async def drain_to_final_msg(
             # final result arrived!
             case Return():
                 log.runtime(
-                    f'Context delivered final draining msg\n'
+                    'Context delivered final draining msg:\n'
-                    f'\n'
                     f'{pretty_struct.pformat(msg)}'
                 )
                 ctx._result: Any = pld
@@ -709,14 +697,12 @@ async def drain_to_final_msg(
                 ):
                     log.cancel(
                         'Cancelling `MsgStream` drain since '
-                        f'{reason}\n'
+                        f'{reason}\n\n'
-                        f'\n'
                         f'<= {ctx.chan.uid}\n'
-                        f'  |_{ctx._nsf}()\n'
+                        f'  |_{ctx._nsf}()\n\n'
-                        f'\n'
                         f'=> {ctx._task}\n'
-                        f'  |_{ctx._stream}\n'
+                        f'  |_{ctx._stream}\n\n'
-                        f'\n'
+
                         f'{pretty_struct.pformat(msg)}\n'
                     )
                     break
@@ -753,8 +739,7 @@ async def drain_to_final_msg(
             case Stop():
                 pre_result_drained.append(msg)
                 log.runtime(  # normal/expected shutdown transaction
-                    f'Remote stream terminated due to "stop" msg\n'
+                    'Remote stream terminated due to "stop" msg:\n\n'
-                    f'\n'
                     f'{pretty_struct.pformat(msg)}\n'
                 )
                 continue
@@ -829,8 +814,7 @@ async def drain_to_final_msg(
 
     else:
         log.cancel(
-            f'Skipping `MsgStream` drain since final outcome is set\n'
+            'Skipping `MsgStream` drain since final outcome is set\n\n'
-            f'\n'
             f'{ctx.outcome}\n'
         )
 

tractor/msg/pretty_struct.py

@@ -20,7 +20,6 @@ Prettified version of `msgspec.Struct` for easier console grokin.
 '''
 from __future__ import annotations
 from collections import UserList
-import textwrap
 from typing import (
     Any,
     Iterator,
@@ -106,11 +105,27 @@ def iter_fields(struct: Struct) -> Iterator[
         )
 
 
-def iter_struct_ppfmt_lines(
+def pformat(
     struct: Struct,
-    field_indent: int = 0,
+    field_indent: int = 2,
-) -> Iterator[tuple[str, str]]:
+    indent: int = 0,
 
+) -> str:
+    '''
+    Recursion-safe `pprint.pformat()` style formatting of
+    a `msgspec.Struct` for sane reading by a human using a REPL.
+
+    '''
+    # global whitespace indent
+    ws: str = ' '*indent
+
+    # field whitespace indent
+    field_ws: str = ' '*(field_indent + indent)
+
+    # qtn: str = ws + struct.__class__.__qualname__
+    qtn: str = struct.__class__.__qualname__
+
+    obj_str: str = ''  # accumulator
     fi: structs.FieldInfo
     k: str
     v: Any
@@ -120,18 +135,15 @@ def iter_struct_ppfmt_lines(
         # ..]` over .__name__ == `Literal` but still get only the
         # latter for simple types like `str | int | None` etc..?
         ft: type = fi.type
-        typ_name: str = getattr(
+        typ_name: str = getattr(ft, '__name__', str(ft))
-            ft,
-            '__name__',
-            str(ft)
-        ).replace(' ', '')
 
         # recurse to get sub-struct's `.pformat()` output Bo
         if isinstance(v, Struct):
-            yield from iter_struct_ppfmt_lines(
+            val_str: str =  v.pformat(
-                struct=v,
+                indent=field_indent + indent,
-                field_indent=field_indent+field_indent,
+                field_indent=indent + field_indent,
             )
+
         else:
             val_str: str = repr(v)
 
@@ -149,39 +161,8 @@ def iter_struct_ppfmt_lines(
                 # raise
                 # return _Struct.__repr__(struct)
 
-        yield (
+        # TODO: LOLOL use `textwrap.indent()` instead dawwwwwg!
-            ' '*field_indent,  # indented ws prefix
+        obj_str += (field_ws + f'{k}: {typ_name} = {val_str},\n')
-            f'{k}: {typ_name} = {val_str},',  # field's repr line content
-        )
-
-
-def pformat(
-    struct: Struct,
-    field_indent: int = 2,
-    indent: int = 0,
-) -> str:
-    '''
-    Recursion-safe `pprint.pformat()` style formatting of
-    a `msgspec.Struct` for sane reading by a human using a REPL.
-
-    '''
-    obj_str: str = ''  # accumulator
-    for prefix, field_repr, in iter_struct_ppfmt_lines(
-        struct,
-        field_indent=field_indent,
-    ):
-        obj_str += f'{prefix}{field_repr}\n'
-
-    # global whitespace indent
-    ws: str = ' '*indent
-    if indent:
-        obj_str: str = textwrap.indent(
-            text=obj_str,
-            prefix=ws,
-        )
-
-    # qtn: str = ws + struct.__class__.__qualname__
-    qtn: str = struct.__class__.__qualname__
 
     return (
         f'{qtn}(\n'

tractor/msg/types.py

@@ -31,7 +31,6 @@ from typing import (
     Type,
     TypeVar,
     TypeAlias,
-    # TYPE_CHECKING,
     Union,
 )
 
@@ -48,7 +47,6 @@ from tractor.msg import (
     pretty_struct,
 )
 from tractor.log import get_logger
-# from tractor._addr import UnwrappedAddress
 
 
 log = get_logger('tractor.msgspec')
@@ -143,49 +141,9 @@ class Aid(
     '''
     name: str
     uuid: str
-    pid: int|None = None
+    # TODO: use built-in support for UUIDs?
-
+    # -[ ] `uuid.UUID` which has multi-protocol support
-    # TODO? can/should we extend this field set?
+    #  https://jcristharif.com/msgspec/supported-types.html#uuid
-    # -[ ] use built-in support for UUIDs? `uuid.UUID` which has
-    #     multi-protocol support
-    #     https://jcristharif.com/msgspec/supported-types.html#uuid
-    #
-    # -[ ] as per the `.ipc._uds` / `._addr` comments, maybe we
-    #     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(
@@ -203,15 +161,14 @@ class SpawnSpec(
     # a hard `Struct` def for all of these fields!
     _parent_main_data: dict
     _runtime_vars: dict[str, Any]
-    # ^NOTE see `._state._runtime_vars: dict`
 
     # module import capability
     enable_modules: dict[str, str]
 
     # TODO: not just sockaddr pairs?
     # -[ ] abstract into a `TransportAddr` type?
-    reg_addrs: list[tuple[str, str|int]]
+    reg_addrs: list[tuple[str, int]]
-    bind_addrs: list[tuple[str, str|int]]|None
+    bind_addrs: list[tuple[str, int]]
 
 
 # TODO: caps based RPC support in the payload?

tractor/to_asyncio.py

@@ -38,6 +38,7 @@ from typing import (
 import tractor
 from tractor._exceptions import (
     InternalError,
+    is_multi_cancelled,
     TrioTaskExited,
     TrioCancelled,
     AsyncioTaskExited,
@@ -48,7 +49,7 @@ from tractor._state import (
     _runtime_vars,
 )
 from tractor._context import Unresolved
-from tractor.devx import debug
+from tractor.devx import _debug
 from tractor.log import (
     get_logger,
     StackLevelAdapter,
@@ -58,9 +59,6 @@ from tractor.log import (
 # from tractor.msg import (
 #     pretty_struct,
 # )
-from tractor.trionics import (
-    is_multi_cancelled,
-)
 from tractor.trionics._broadcast import (
     broadcast_receiver,
     BroadcastReceiver,
@@ -130,7 +128,6 @@ class LinkedTaskChannel(
     _trio_task: trio.Task
     _aio_task_complete: trio.Event
 
-    _closed_by_aio_task: bool = False
     _suppress_graceful_exits: bool = True
 
     _trio_err: BaseException|None = None
@@ -209,15 +206,10 @@ class LinkedTaskChannel(
     async def aclose(self) -> None:
         await self._from_aio.aclose()
 
-    # ?TODO? async version of this?
+    def started(
-    def started_nowait(
         self,
         val: Any = None,
     ) -> None:
-        '''
-        Synchronize aio-side with its trio-parent.
-
-        '''
         self._aio_started_val = val
         return self._to_trio.send_nowait(val)
 
@@ -248,7 +240,6 @@ class LinkedTaskChannel(
             # cycle on the trio side?
             # await trio.lowlevel.checkpoint()
             return await self._from_aio.receive()
-
         except BaseException as err:
             async with translate_aio_errors(
                 chan=self,
@@ -326,7 +317,7 @@ def _run_asyncio_task(
     qsize: int = 1,
     provide_channels: bool = False,
     suppress_graceful_exits: bool = True,
-    hide_tb: bool = True,
+    hide_tb: bool = False,
     **kwargs,
 
 ) -> LinkedTaskChannel:
@@ -354,6 +345,18 @@ def _run_asyncio_task(
         # value otherwise it would just return ;P
         assert qsize > 1
 
+    if provide_channels:
+        assert 'to_trio' in args
+
+    # allow target func to accept/stream results manually by name
+    if 'to_trio' in args:
+        kwargs['to_trio'] = to_trio
+
+    if 'from_trio' in args:
+        kwargs['from_trio'] = from_trio
+
+    coro = func(**kwargs)
+
     trio_task: trio.Task = trio.lowlevel.current_task()
     trio_cs = trio.CancelScope()
     aio_task_complete = trio.Event()
@@ -368,25 +371,6 @@ def _run_asyncio_task(
         _suppress_graceful_exits=suppress_graceful_exits,
     )
 
-    # allow target func to accept/stream results manually by name
-    if 'to_trio' in args:
-        kwargs['to_trio'] = to_trio
-
-    if 'from_trio' in args:
-        kwargs['from_trio'] = from_trio
-
-    if 'chan' in args:
-        kwargs['chan'] = chan
-
-    if provide_channels:
-        assert (
-            'to_trio' in args
-            or
-            'chan' in args
-        )
-
-    coro = func(**kwargs)
-
     async def wait_on_coro_final_result(
         to_trio: trio.MemorySendChannel,
         coro: Awaitable,
@@ -459,23 +443,9 @@ def _run_asyncio_task(
                         f'Task exited with final result: {result!r}\n'
                     )
 
-                # XXX ALWAYS close the child-`asyncio`-task-side's
+                # only close the sender side which will relay
-                # `to_trio` handle which will in turn relay
+                # a `trio.EndOfChannel` to the trio (consumer) side.
-                # a `trio.EndOfChannel` to the `trio`-parent.
-                # Consequently the parent `trio` task MUST ALWAYS
-                # check for any `chan._aio_err` to be raised when it
-                # receives an EoC.
-                #
-                # NOTE, there are 2 EoC cases,
-                # - normal/graceful EoC due to the aio-side actually
-                #   terminating its "streaming", but the task did not
-                #   error and is not yet complete.
-                #
-                # - the aio-task terminated and we specially mark the
-                #   closure as due to the `asyncio.Task`'s exit.
-                #
                 to_trio.close()
-                chan._closed_by_aio_task = True
 
             aio_task_complete.set()
             log.runtime(
@@ -509,12 +479,12 @@ def _run_asyncio_task(
     if (
         debug_mode()
         and
-        (greenback := debug.maybe_import_greenback(
+        (greenback := _debug.maybe_import_greenback(
             force_reload=True,
             raise_not_found=False,
         ))
     ):
-        log.devx(
+        log.info(
             f'Bestowing `greenback` portal for `asyncio`-task\n'
             f'{task}\n'
         )
@@ -673,9 +643,8 @@ def _run_asyncio_task(
                 not trio_cs.cancel_called
             ):
                 log.cancel(
-                    f'Cancelling trio-side due to aio-side src exc\n'
+                    f'Cancelling `trio` side due to aio-side src exc\n'
-                    f'\n'
+                    f'{curr_aio_err}\n'
-                    f'{curr_aio_err!r}\n'
                     f'\n'
                     f'(c>\n'
                     f'  |_{trio_task}\n'
@@ -787,7 +756,6 @@ async def translate_aio_errors(
     aio_done_before_trio: bool = aio_task.done()
     assert aio_task
     trio_err: BaseException|None = None
-    eoc: trio.EndOfChannel|None = None
     try:
         yield  # back to one of the cross-loop apis
     except trio.Cancelled as taskc:
@@ -819,48 +787,12 @@ async def translate_aio_errors(
         # )
         # raise
 
-    # XXX EoC is a special SIGNAL from the aio-side here!
+    # XXX always passthrough EoC since this translator is often
-    # There are 2 cases to handle:
+    # called from `LinkedTaskChannel.receive()` which we want
-    # 1. the "EoC passthrough" case.
+    # passthrough and further we have no special meaning for it in
-    #   - the aio-task actually closed the channel "gracefully" and
+    # terms of relaying errors or signals from the aio side!
-    #     the trio-task should unwind any ongoing channel
+    except trio.EndOfChannel as eoc:
-    #     iteration/receiving,
+        trio_err = chan._trio_err = eoc
-    #  |_this exc-translator wraps calls to `LinkedTaskChannel.receive()`
-    #    in which case we want to relay the actual "end-of-chan" for
-    #    iteration purposes.
-    #
-    # 2. relaying the "asyncio.Task termination" case.
-    #   - if the aio-task terminates, maybe with an error, AND the
-    #    `open_channel_from()` API was used, it will always signal
-    #    that termination.
-    #  |_`wait_on_coro_final_result()` always calls
-    #    `to_trio.close()` when `provide_channels=True` so we need to
-    #    always check if there is an aio-side exc which needs to be
-    #    relayed to the parent trio side!
-    #  |_in this case the special `chan._closed_by_aio_task` is
-    #    ALWAYS set.
-    #
-    except trio.EndOfChannel as _eoc:
-        eoc = _eoc
-        if (
-            chan._closed_by_aio_task
-            and
-            aio_err
-        ):
-            log.cancel(
-                f'The asyncio-child task terminated due to error\n'
-                f'{aio_err!r}\n'
-            )
-            chan._trio_to_raise = aio_err
-            trio_err = chan._trio_err = eoc
-            #
-            # ?TODO?, raise something like a,
-            # chan._trio_to_raise = AsyncioErrored()
-            # BUT, with the tb rewritten to reflect the underlying
-            # call stack?
-        else:
-            trio_err = chan._trio_err = eoc
-
         raise eoc
 
     # NOTE ALSO SEE the matching note in the `cancel_trio()` asyncio
@@ -909,7 +841,7 @@ async def translate_aio_errors(
     except BaseException as _trio_err:
         trio_err = chan._trio_err = _trio_err
         # await tractor.pause(shield=True)  # workx!
-        entered: bool = await debug._maybe_enter_pm(
+        entered: bool = await _debug._maybe_enter_pm(
             trio_err,
             api_frame=inspect.currentframe(),
         )
@@ -1113,7 +1045,7 @@ async def translate_aio_errors(
         #
         if wait_on_aio_task:
             await chan._aio_task_complete.wait()
-            log.debug(
+            log.info(
                 'asyncio-task is done and unblocked trio-side!\n'
             )
 
@@ -1130,17 +1062,11 @@ async def translate_aio_errors(
         trio_to_raise: (
             AsyncioCancelled|
             AsyncioTaskExited|
-            Exception|  # relayed from aio-task
             None
         ) = chan._trio_to_raise
 
-        raise_from: Exception = (
-            trio_err if (aio_err is trio_to_raise)
-            else aio_err
-        )
-
         if not suppress_graceful_exits:
-            raise trio_to_raise from raise_from
+            raise trio_to_raise from (aio_err or trio_err)
 
         if trio_to_raise:
             match (
@@ -1173,7 +1099,7 @@ async def translate_aio_errors(
                         )
                         return
                 case _:
-                    raise trio_to_raise from raise_from
+                    raise trio_to_raise from (aio_err or trio_err)
 
         # Check if the asyncio-side is the cause of the trio-side
         # error.
@@ -1239,6 +1165,7 @@ async def run_task(
 
 @acm
 async def open_channel_from(
+
     target: Callable[..., Any],
     suppress_graceful_exits: bool = True,
     **target_kwargs,
@@ -1272,6 +1199,7 @@ async def open_channel_from(
                     # deliver stream handle upward
                     yield first, chan
             except trio.Cancelled as taskc:
+                # await tractor.pause(shield=True)  # ya it worx ;)
                 if cs.cancel_called:
                     if isinstance(chan._trio_to_raise, AsyncioCancelled):
                         log.cancel(
@@ -1478,7 +1406,7 @@ def run_as_asyncio_guest(
             )
             # XXX make it obvi we know this isn't supported yet!
             assert 0
-            # await debug.maybe_init_greenback(
+            # await _debug.maybe_init_greenback(
             #     force_reload=True,
             # )
 

tractor/trionics/__init__.py

@@ -31,9 +31,4 @@ from ._broadcast import (
 )
 from ._beg import (
     collapse_eg as collapse_eg,
-    get_collapsed_eg as get_collapsed_eg,
-    is_multi_cancelled as is_multi_cancelled,
-)
-from ._taskc import (
-    maybe_raise_from_masking_exc as maybe_raise_from_masking_exc,
 )

tractor/trionics/_beg.py

@@ -15,94 +15,31 @@
 # along with this program.  If not, see <https://www.gnu.org/licenses/>.
 
 '''
-`BaseExceptionGroup` utils and helpers pertaining to
+`BaseExceptionGroup` related utils and helpers pertaining to
-first-class-`trio` from a "historical" perspective, like "loose
+first-class-`trio` from a historical perspective B)
-exception group" task-nurseries.
 
 '''
 from contextlib import (
     asynccontextmanager as acm,
 )
-from typing import (
-    Literal,
-    Type,
-)
-
-import trio
-# from trio._core._concat_tb import (
-#     concat_tb,
-# )
 
 
-# XXX NOTE
+def maybe_collapse_eg(
-# taken verbatim from `trio._core._run` except,
-# - remove the NONSTRICT_EXCEPTIONGROUP_NOTE deprecation-note
-#   guard-check; we know we want an explicit collapse.
-# - mask out tb rewriting in collapse case, i don't think it really
-#   matters?
-#
-def collapse_exception_group(
-    excgroup: BaseExceptionGroup[BaseException],
-) -> BaseException:
-    """Recursively collapse any single-exception groups into that single contained
-    exception.
-
-    """
-    exceptions = list(excgroup.exceptions)
-    modified = False
-    for i, exc in enumerate(exceptions):
-        if isinstance(exc, BaseExceptionGroup):
-            new_exc = collapse_exception_group(exc)
-            if new_exc is not exc:
-                modified = True
-                exceptions[i] = new_exc
-
-    if (
-        len(exceptions) == 1
-        and isinstance(excgroup, BaseExceptionGroup)
-
-        # XXX trio's loose-setting condition..
-        # and NONSTRICT_EXCEPTIONGROUP_NOTE in getattr(excgroup, "__notes__", ())
-    ):
-        # exceptions[0].__traceback__ = concat_tb(
-        #     excgroup.__traceback__,
-        #     exceptions[0].__traceback__,
-        # )
-        return exceptions[0]
-    elif modified:
-        return excgroup.derive(exceptions)
-    else:
-        return excgroup
-
-
-def get_collapsed_eg(
     beg: BaseExceptionGroup,
-
+) -> BaseException:
-) -> BaseException|None:
     '''
-    If the input beg can collapse to a single sub-exception which is
+    If the input beg can collapse to a single non-eg sub-exception,
-    itself **not** an eg, return it.
+    return it instead.
 
     '''
-    maybe_exc = collapse_exception_group(beg)
+    if len(excs := beg.exceptions) == 1:
-    if maybe_exc is beg:
+        return excs[0]
-        return None
 
-    return maybe_exc
+    return beg
 
 
 @acm
-async def collapse_eg(
+async def collapse_eg():
-    hide_tb: bool = True,
-
-    # XXX, for ex. will always show begs containing single taskc
-    ignore: set[Type[BaseException]] = {
-        # trio.Cancelled,
-    },
-    add_notes: bool = True,
-
-    bp: bool = False,
-):
     '''
     If `BaseExceptionGroup` raised in the body scope is
     "collapse-able" (in the same way that
@@ -110,114 +47,12 @@ async def collapse_eg(
     only raise the lone emedded non-eg in in place.
 
     '''
-    __tracebackhide__: bool = hide_tb
     try:
         yield
-    except BaseExceptionGroup as _beg:
+    except* BaseException as beg:
-        beg = _beg
-
         if (
-            bp
+            exc := maybe_collapse_eg(beg)
-            and
+        ) is not beg:
-            len(beg.exceptions) > 1
+            raise exc
-        ):
-            import tractor
-            if tractor.current_actor(
-                err_on_no_runtime=False,
-            ):
-                await tractor.pause(shield=True)
-            else:
-                breakpoint()
 
-        if (
+        raise beg
-            (exc := get_collapsed_eg(beg))
-            and
-            type(exc) not in ignore
-        ):
-
-            # TODO? report number of nested groups it was collapsed
-            # *from*?
-            if add_notes:
-                from_group_note: str = (
-                    '( ^^^ this exc was collapsed from a group ^^^ )\n'
-                )
-                if (
-                    from_group_note
-                    not in
-                    getattr(exc, "__notes__", ())
-                ):
-                    exc.add_note(from_group_note)
-
-            # raise exc
-            # ^^ this will leave the orig beg tb above with the
-            # "during the handling of <beg> the following.."
-            # So, instead do..
-            #
-            if cause := exc.__cause__:
-                raise exc from cause
-            else:
-                # suppress "during handling of <the beg>"
-                # output in tb/console.
-                raise exc from None
-
-        # keep original
-        raise # beg
-
-
-def is_multi_cancelled(
-    beg: BaseException|BaseExceptionGroup,
-
-    ignore_nested: set[BaseException] = set(),
-
-) -> Literal[False]|BaseExceptionGroup:
-    '''
-    Predicate to determine if an `BaseExceptionGroup` only contains
-    some (maybe nested) set of sub-grouped exceptions (like only
-    `trio.Cancelled`s which get swallowed silently by default) and is
-    thus the result of "gracefully cancelling" a collection of
-    sub-tasks (or other conc primitives) and receiving a "cancelled
-    ACK" from each after termination.
-
-    Docs:
-    ----
-    - https://docs.python.org/3/library/exceptions.html#exception-groups
-    - https://docs.python.org/3/library/exceptions.html#BaseExceptionGroup.subgroup
-
-    '''
-
-    if (
-        not ignore_nested
-        or
-        trio.Cancelled not in ignore_nested
-        # XXX always count-in `trio`'s native signal
-    ):
-        ignore_nested.update({trio.Cancelled})
-
-    if isinstance(beg, BaseExceptionGroup):
-        # https://docs.python.org/3/library/exceptions.html#BaseExceptionGroup.subgroup
-        # |_ "The condition can be an exception type or tuple of
-        #   exception types, in which case each exception is checked
-        #   for a match using the same check that is used in an
-        #   except clause. The condition can also be a callable
-        #   (other than a type object) that accepts an exception as
-        #   its single argument and returns true for the exceptions
-        #   that should be in the subgroup."
-        matched_exc: BaseExceptionGroup|None = beg.subgroup(
-            tuple(ignore_nested),
-
-            # ??TODO, complain about why not allowed to use
-            # named arg style calling???
-            # XD .. wtf?
-            # condition=tuple(ignore_nested),
-        )
-        if matched_exc is not None:
-            return matched_exc
-
-    # NOTE, IFF no excs types match (throughout the error-tree)
-    # -> return `False`, OW return the matched sub-eg.
-    #
-    # IOW, for the inverse of ^ for the purpose of
-    # maybe-enter-REPL--logic: "only debug when the err-tree contains
-    # at least one exc-type NOT in `ignore_nested`" ; i.e. the case where
-    # we fallthrough and return `False` here.
-    return False

tractor/trionics/_mngrs.py

@@ -31,6 +31,7 @@ from typing import (
     AsyncIterator,
     Callable,
     Hashable,
+    Optional,
     Sequence,
     TypeVar,
     TYPE_CHECKING,
@@ -39,11 +40,6 @@ from typing import (
 import trio
 from tractor._state import current_actor
 from tractor.log import get_logger
-# from ._beg import collapse_eg
-# from ._taskc import (
-#     maybe_raise_from_masking_exc,
-# )
-
 
 if TYPE_CHECKING:
     from tractor import ActorNursery
@@ -74,8 +70,7 @@ async def maybe_open_nursery(
         yield nursery
     else:
         async with lib.open_nursery(**kwargs) as nursery:
-            if lib == trio:
+            nursery.cancel_scope.shield = shield
-                nursery.cancel_scope.shield = shield
             yield nursery
 
 
@@ -108,9 +103,6 @@ async def _enter_and_wait(
 async def gather_contexts(
     mngrs: Sequence[AsyncContextManager[T]],
 
-    # caller can provide their own scope
-    tn: trio.Nursery|None = None,
-
 ) -> AsyncGenerator[
     tuple[
         T | None,
@@ -119,19 +111,17 @@ async def gather_contexts(
     None,
 ]:
     '''
-    Concurrently enter a sequence of async context managers (`acm`s),
+    Concurrently enter a sequence of async context managers (acms),
-    each scheduled in a separate `trio.Task` and deliver their
+    each from a separate `trio` task and deliver the unwrapped
-    unwrapped `yield`-ed values in the same order once all `@acm`s
+    `yield`-ed values in the same order once all managers have entered.
-    in every task have entered.
 
-    On exit, all `acm`s are subsequently and concurrently exited with
+    On exit, all acms are subsequently and concurrently exited.
-    **no order guarantees**.
 
     This function is somewhat similar to a batch of non-blocking
     calls to `contextlib.AsyncExitStack.enter_async_context()`
     (inside a loop) *in combo with* a `asyncio.gather()` to get the
     `.__aenter__()`-ed values, except the managers are both
-    concurrently entered and exited and *cancellation-just-works™*.
+    concurrently entered and exited and *cancellation just works*(R).
 
     '''
     seed: int = id(mngrs)
@@ -151,47 +141,37 @@ async def gather_contexts(
     if not mngrs:
         raise ValueError(
             '`.trionics.gather_contexts()` input mngrs is empty?\n'
-            '\n'
             'Did try to use inline generator syntax?\n'
-            'Check that list({mngrs}) works!\n'
+            'Use a non-lazy iterator or sequence type intead!'
-            # 'or sequence-type intead!\n'
-            # 'Use a non-lazy iterator or sequence-type intead!\n'
         )
 
-    try:
+    async with trio.open_nursery(
-        async with (
+        strict_exception_groups=False,
-            #
+        # ^XXX^ TODO? soo roll our own then ??
-            # ?TODO, does including these (eg-collapsing,
+        # -> since we kinda want the "if only one `.exception` then
-            # taskc-unmasking) improve tb noise-reduction/legibility?
+        # just raise that" interface?
-            #
+    ) as tn:
-            # collapse_eg(),
+        for mngr in mngrs:
-            maybe_open_nursery(
+            tn.start_soon(
-                nursery=tn,
+                _enter_and_wait,
-            ) as tn,
+                mngr,
-            # maybe_raise_from_masking_exc(),
+                unwrapped,
-        ):
+                all_entered,
-            for mngr in mngrs:
+                parent_exit,
-                tn.start_soon(
+                seed,
-                    _enter_and_wait,
+            )
-                    mngr,
-                    unwrapped,
-                    all_entered,
-                    parent_exit,
-                    seed,
-                )
 
-            # deliver control to caller once all ctx-managers have
+        # deliver control once all managers have started up
-            # started (yielded back to us).
+        await all_entered.wait()
-            await all_entered.wait()
+
+        try:
             yield tuple(unwrapped.values())
+        finally:
+            # NOTE: this is ABSOLUTELY REQUIRED to avoid
+            # the following wacky bug:
+            # <tractorbugurlhere>
             parent_exit.set()
 
-    finally:
-        # XXX NOTE: this is ABSOLUTELY REQUIRED to avoid
-        # the following wacky bug:
-        # <tractorbugurlhere>
-        parent_exit.set()
-
 
 # Per actor task caching helpers.
 # Further potential examples of interest:
@@ -203,7 +183,7 @@ class _Cache:
     a kept-alive-while-in-use async resource.
 
     '''
-    service_tn: trio.Nursery|None = None
+    service_n: Optional[trio.Nursery] = None
     locks: dict[Hashable, trio.Lock] = {}
     users: int = 0
     values: dict[Any,  Any] = {}
@@ -212,7 +192,7 @@ class _Cache:
         tuple[trio.Nursery, trio.Event]
     ] = {}
     # nurseries: dict[int, trio.Nursery] = {}
-    no_more_users: trio.Event|None = None
+    no_more_users: Optional[trio.Event] = None
 
     @classmethod
     async def run_ctx(
@@ -222,18 +202,16 @@ class _Cache:
         task_status: trio.TaskStatus[T] = trio.TASK_STATUS_IGNORED,
 
     ) -> None:
-        try:
+        async with mng as value:
-            async with mng as value:
+            _, no_more_users = cls.resources[ctx_key]
-                _, no_more_users = cls.resources[ctx_key]
+            cls.values[ctx_key] = value
-                try:
+            task_status.started(value)
-                    cls.values[ctx_key] = value
+            try:
-                    task_status.started(value)
+                await no_more_users.wait()
-                    await no_more_users.wait()
+            finally:
-                finally:
+                # discard nursery ref so it won't be re-used (an error)?
-                    value = cls.values.pop(ctx_key)
+                value = cls.values.pop(ctx_key)
-        finally:
+                cls.resources.pop(ctx_key)
-            # discard nursery ref so it won't be re-used (an error)?
-            cls.resources.pop(ctx_key)
 
 
 @acm
@@ -246,9 +224,6 @@ async def maybe_open_context(
     kwargs: dict = {},
     key: Hashable | Callable[..., Hashable] = None,
 
-    # caller can provide their own scope
-    tn: trio.Nursery|None = None,
-
 ) -> AsyncIterator[tuple[bool, T]]:
     '''
     Maybe open an async-context-manager (acm) if there is not already
@@ -281,94 +256,40 @@ async def maybe_open_context(
     # have it not be closed until all consumers have exited (which is
     # currently difficult to implement any other way besides using our
     # pre-allocated runtime instance..)
-    if tn:
+    service_n: trio.Nursery = current_actor()._service_n
-        # TODO, assert tn is eventual parent of this task!
-        task: trio.Task = trio.lowlevel.current_task()
-        task_tn: trio.Nursery = task.parent_nursery
-        if not tn._cancel_status.encloses(
-            task_tn._cancel_status
-        ):
-            raise RuntimeError(
-                f'Mis-nesting of task under provided {tn} !?\n'
-                f'Current task is NOT a child(-ish)!!\n'
-                f'\n'
-                f'task: {task}\n'
-                f'task_tn: {task_tn}\n'
-            )
-        service_tn = tn
-    else:
-        service_tn: trio.Nursery = current_actor()._service_tn
 
     # TODO: is there any way to allocate
     # a 'stays-open-till-last-task-finshed nursery?
-    # service_tn: trio.Nursery
+    # service_n: trio.Nursery
-    # async with maybe_open_nursery(_Cache.service_tn) as service_tn:
+    # async with maybe_open_nursery(_Cache.service_n) as service_n:
-    #     _Cache.service_tn = service_tn
+    #     _Cache.service_n = service_n
 
-    cache_miss_ke: KeyError|None = None
-    maybe_taskc: trio.Cancelled|None = None
     try:
         # **critical section** that should prevent other tasks from
         # checking the _Cache until complete otherwise the scheduler
         # may switch and by accident we create more then one resource.
         yielded = _Cache.values[ctx_key]
 
-    except KeyError as _ke:
+    except KeyError:
-        # XXX, stay mutexed up to cache-miss yield
+        log.debug(f'Allocating new {acm_func} for {ctx_key}')
-        try:
+        mngr = acm_func(**kwargs)
-            cache_miss_ke = _ke
+        resources = _Cache.resources
-            log.debug(
+        assert not resources.get(ctx_key), f'Resource exists? {ctx_key}'
-                f'Allocating new @acm-func entry\n'
+        resources[ctx_key] = (service_n, trio.Event())
-                f'ctx_key={ctx_key}\n'
-                f'acm_func={acm_func}\n'
-            )
-            mngr = acm_func(**kwargs)
-            resources = _Cache.resources
-            assert not resources.get(ctx_key), f'Resource exists? {ctx_key}'
-            resources[ctx_key] = (service_tn, trio.Event())
-            yielded: Any = await service_tn.start(
-                _Cache.run_ctx,
-                mngr,
-                ctx_key,
-            )
-            _Cache.users += 1
-        finally:
-            # XXX, since this runs from an `except` it's a checkpoint
-            # whih can be `trio.Cancelled`-masked.
-            #
-            # NOTE, in that case the mutex is never released by the
-            # (first and) caching task and **we can't** simply shield
-            # bc that will inf-block on the `await
-            # no_more_users.wait()`.
-            #
-            # SO just always unlock!
-            lock.release()
 
-        try:
+        # sync up to the mngr's yielded value
-            yield (
+        yielded = await service_n.start(
-                False,  # cache_hit = "no"
+            _Cache.run_ctx,
-                yielded,
+            mngr,
-            )
+            ctx_key,
-        except trio.Cancelled as taskc:
+        )
-            maybe_taskc = taskc
+        _Cache.users += 1
-            log.cancel(
+        lock.release()
-                f'Cancelled from cache-miss entry\n'
+        yield False, yielded
-                f'\n'
-                f'ctx_key: {ctx_key!r}\n'
-                f'mngr: {mngr!r}\n'
-            )
-            # XXX, always unset ke from cancelled context
-            # since we never consider it a masked exc case!
-            # - bc this can be called directly ty `._rpc._invoke()`?
-            #
-            if maybe_taskc.__context__ is cache_miss_ke:
-                maybe_taskc.__context__ = None
-
-            raise taskc
 
     else:
         _Cache.users += 1
-        log.debug(
+        log.runtime(
             f'Re-using cached resource for user {_Cache.users}\n\n'
             f'{ctx_key!r} -> {type(yielded)}\n'
 
@@ -378,19 +299,9 @@ async def maybe_open_context(
             # f'{ctx_key!r} -> {yielded!r}\n'
         )
         lock.release()
-        yield (
+        yield True, yielded
-            True,  # cache_hit = "yes"
-            yielded,
-        )
 
     finally:
-        if lock.locked():
-            stats: trio.LockStatistics = lock.statistics()
-            log.error(
-                f'Lock left locked by last owner !?\n'
-                f'{stats}\n'
-            )
-
         _Cache.users -= 1
 
         if yielded is not None: