Add API-modernize-todo on `experimental._pubsub.fan_out_to_ctxs`

By borrowing from the implementation of `RemoteActorError.pformat()`
which is now factored into a new `.devx.pformat_exc()` and re-used for
both error types while maintaining the same func-sig. Obviously delegate
`RemoteActorError.pformat()` to the new helper accordingly and keeping
the prior `body` generation from `.devx.pformat_boxed_tb()` as before.

The new helper allows for,
- passing any of a `header|message|body: str` which are all combined in
  that order in the final output.
- getting the `exc.message` as the default `message` part.
- generating an objecty-looking "type-name" header to be rendered by
  default when `header` is not overridden.
- "first-line-of `message`" processing which we split-off and then
  re-inject as a `f'<{type(exc).__name__}( {first} )>'` top line header.
- an optional `tail: str = '>'` to "close the object"-look only added
  when `with_type_header: bool = True`.

Adjustments to `TransportClosed` around this include,
- replacing the init `cause` arg for a `src_exc` which is now always
  assigned to a same named instance var.
- displaying that new `.src_exc` in the `body: str` arg to the
  `.devx.pformat.pformat_exc()` call so you can always see the
  underlying (normally `trio`) source error.
- just make it inherit from `Exception` not `trio.BrokenResourceError`
  to avoid handlers catching `TransportClosed` as the former
  particularly in testing when we want to sometimes to distinguish them.

default.nix

@@ -0,0 +1,19 @@
+{ 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
+  '';
+}

examples/advanced_faults/ipc_failure_during_stream.py

@@ -120,6 +120,7 @@ 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:
 
@@ -131,6 +132,7 @@ 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,
     ):
@@ -145,7 +147,8 @@ async def main(
             _testing.expect_ctxc(
                 yay=(
                     break_parent_ipc_after
-                    or break_child_ipc_after
+                    or
+                    break_child_ipc_after
                 ),
                 # TODO: we CAN'T remove this right?
                 # since we need the ctxc to bubble up from either

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('127.0.0.1', 1616) as portal:
+        async with tractor.get_registry() as portal:
             print(f"Arbiter is listening on {portal.channel}")
 
         async with tractor.wait_for_actor(service_name) as sockaddr:

pyproject.toml

@@ -45,6 +45,8 @@ 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 ------
@@ -62,6 +64,7 @@ dev = [
   "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

@@ -1,6 +1,8 @@
 """
-``tractor`` testing!!
+Top level of the testing suites!
+
 """
+from __future__ import annotations
 import sys
 import subprocess
 import os
@@ -30,7 +32,11 @@ 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 = 0.6 if sys.version_info < (3, 7) else 0.4
+    _PROC_SPAWN_WAIT = (
+        0.6
+        if sys.version_info < (3, 7)
+        else 0.4
+    )
 
 
 no_windows = pytest.mark.skipif(
@@ -39,7 +45,9 @@ no_windows = pytest.mark.skipif(
 )
 
 
-def pytest_addoption(parser):
+def pytest_addoption(
+    parser: pytest.Parser,
+):
     parser.addoption(
         "--ll",
         action="store",
@@ -56,7 +64,8 @@ def pytest_addoption(parser):
     )
 
     parser.addoption(
-        "--tpdb", "--debug-mode",
+        "--tpdb",
+        "--debug-mode",
         action="store_true",
         dest='tractor_debug_mode',
         # default=False,
@@ -67,6 +76,17 @@ def pytest_addoption(parser):
         ),
     )
 
+    # 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
@@ -74,7 +94,7 @@ def pytest_configure(config):
 
 
 @pytest.fixture(scope='session')
-def debug_mode(request):
+def debug_mode(request) -> bool:
     debug_mode: bool = request.config.option.tractor_debug_mode
     # if debug_mode:
     #     breakpoint()
@@ -95,11 +115,35 @@ 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()
+@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')
+def tpt_proto(
+    tpt_protos: list[str],
+) -> str:
+    yield tpt_protos[0]
+
 
 _ci_env: bool = os.environ.get('CI', False)
 
@@ -107,7 +151,7 @@ _ci_env: bool = os.environ.get('CI', False)
 @pytest.fixture(scope='session')
 def ci_env() -> bool:
     '''
-    Detect CI envoirment.
+    Detect CI environment.
 
     '''
     return _ci_env
@@ -115,30 +159,45 @@ def ci_env() -> bool:
 
 # TODO: also move this to `._testing` for now?
 # -[ ] possibly generalize and re-use for multi-tree spawning
-#    along with the new stuff for multi-addrs in distribute_dis
-#    branch?
+#    along with the new stuff for multi-addrs?
 #
-# choose randomly at import time
-_reg_addr: tuple[str, int] = (
-    '127.0.0.1',
-    random.randint(1000, 9999),
-)
+# choose random port at import time
+_rando_port: str = random.randint(1000, 9999)
 
 
 @pytest.fixture(scope='session')
-def reg_addr() -> tuple[str, int]:
+def reg_addr(
+    tpt_proto: str,
+) -> tuple[str, int|str]:
 
     # 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]
+    from tractor import (
+        _addr,
+    )
+    addr_type = _addr._address_types[tpt_proto]
+    def_reg_addr: tuple[str, int] = _addr._default_lo_addrs[tpt_proto]
 
-    return _reg_addr
+    testrun_reg_addr: tuple[str, int]
+    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()
+
+    assert def_reg_addr != testrun_reg_addr
+    return testrun_reg_addr
 
 
 def pytest_generate_tests(metafunc):
-    spawn_backend = metafunc.config.option.spawn_backend
+    spawn_backend: str = metafunc.config.option.spawn_backend
 
     if not spawn_backend:
         # XXX some weird windows bug with `pytest`?
@@ -151,45 +210,53 @@ def pytest_generate_tests(metafunc):
         'trio',
     )
 
-    # NOTE: used to be used to dyanmically parametrize tests for when
+    # 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')
+        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],
+    # 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',
     #     )
 
 
-def sig_prog(proc, sig):
+def sig_prog(
+    proc: subprocess.Popen,
+    sig: int,
+    canc_timeout: float = 0.1,
+) -> int:
     "Kill the actor-process with ``sig``."
     proc.send_signal(sig)
-    time.sleep(0.1)
+    time.sleep(canc_timeout)
     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 = proc.wait()
+    ret: int = proc.wait()
     assert ret
 
 
 # TODO: factor into @cm and move to `._testing`?
 @pytest.fixture
 def daemon(
+    debug_mode: bool,
     loglevel: str,
     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.
@@ -201,27 +268,99 @@ def daemon(
 
     code: str = (
         "import tractor; "
-            "tractor.run_daemon([], registry_addrs={reg_addrs}, loglevel={ll})"
+        "tractor.run_daemon([], "
+        "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 = testdir.popen(
+    proc: subprocess.Popen = testdir.popen(
         cmd,
-        stdout=subprocess.PIPE,
-        stderr=subprocess.PIPE,
         **kwargs,
     )
-    assert not proc.returncode
+
+    # 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
     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/test_advanced_faults.py

@@ -10,6 +10,9 @@ import pytest
 from _pytest.pathlib import import_path
 import trio
 import tractor
+from tractor import (
+    TransportClosed,
+)
 from tractor._testing import (
     examples_dir,
     break_ipc,
@@ -74,6 +77,7 @@ 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
@@ -91,7 +95,7 @@ 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 = tractor.TransportClosed
+        expect_final_exc = TransportClosed
 
     mod: ModuleType = import_path(
         examples_dir() / 'advanced_faults'
@@ -104,6 +108,8 @@ 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
@@ -138,6 +144,9 @@ 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.
@@ -157,6 +166,10 @@ 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
@@ -169,8 +182,8 @@ 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 (
@@ -181,8 +194,8 @@ 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=(
@@ -198,6 +211,7 @@ def test_ipc_channel_break_during_stream(
                     start_method=spawn_backend,
                     loglevel=loglevel,
                     pre_close=pre_aclose_msgstream,
+                    tpt_proto=tpt_proto,
                     **ipc_break,
                 )
             )
@@ -220,10 +234,15 @@ def test_ipc_channel_break_during_stream(
                 )
             cause: Exception = tc.__cause__
             assert (
-                type(cause) is trio.ClosedResourceError
-                and
-                cause.args[0] == 'another task closed this fd'
+                # type(cause) is trio.ClosedResourceError
+                type(cause) is expect_final_cause
+
+                # 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_discovery.py

@@ -7,7 +7,9 @@ import platform
 from functools import partial
 import itertools
 
+import psutil
 import pytest
+import subprocess
 import tractor
 from tractor._testing import tractor_test
 import trio
@@ -26,7 +28,7 @@ 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
 
@@ -152,15 +154,25 @@ 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()
 
@@ -176,11 +188,11 @@ async def spawn_and_check_registry(
                 extra = 2  # local root actor + remote arbiter
 
             # ensure current actor is registered
-            registry = await get_reg()
+            registry: dict = await get_reg()
             assert actor.uid in registry
 
             try:
-                async with tractor.open_nursery() as n:
+                async with tractor.open_nursery() as an:
                     async with trio.open_nursery(
                         strict_exception_groups=False,
                     ) as trion:
@@ -189,17 +201,17 @@ async def spawn_and_check_registry(
                         for i in range(3):
                             name = f'a{i}'
                             if with_streaming:
-                                portals[name] = await n.start_actor(
+                                portals[name] = await an.start_actor(
                                     name=name, enable_modules=[__name__])
 
                             else:  # no streaming
-                                portals[name] = await n.run_in_actor(
+                                portals[name] = await an.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 n._children:
+                            for uid in an._children:
                                 assert uid in registry
 
                         assert len(portals) + extra == len(registry)
@@ -232,6 +244,7 @@ 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,
@@ -248,6 +261,7 @@ 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,
             ),
@@ -257,7 +271,8 @@ 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,
+    daemon: subprocess.Popen,
+    debug_mode: bool,
     start_method,
     use_signal,
     reg_addr,
@@ -273,8 +288,13 @@ 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)
+                ),
             ),
         )
 
@@ -300,7 +320,7 @@ 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)
 
@@ -373,7 +393,7 @@ def test_close_channel_explicit(
 
 @pytest.mark.parametrize('use_signal', [False, True])
 def test_close_channel_explicit_remote_arbiter(
-    daemon,
+    daemon: subprocess.Popen,
     start_method,
     use_signal,
     reg_addr,

tests/test_docs_examples.py

@@ -66,6 +66,9 @@ 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
@@ -119,10 +122,14 @@ def test_example(
         code = ex.read()
 
         with run_example_in_subproc(code) as proc:
-            proc.wait()
-            err, _ = proc.stderr.read(), proc.stdout.read()
-            # print(f'STDERR: {err}')
-            # print(f'STDOUT: {out}')
+            err = None
+            try:
+                if not proc.poll():
+                    _, err = proc.communicate(timeout=15)
+
+            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_inter_peer_cancellation.py

@@ -871,7 +871,7 @@ async def serve_subactors(
                 )
                 await ipc.send((
                     peer.chan.uid,
-                    peer.chan.raddr,
+                    peer.chan.raddr.unwrap(),
                 ))
 
         print('Spawner exiting spawn serve loop!')

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_ringbuf.py

@@ -0,0 +1,208 @@
+import time
+
+import trio
+import pytest
+import tractor
+from tractor.ipc 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_runtime.py

@@ -0,0 +1,85 @@
+'''
+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)

tests/test_shm.py

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

tests/test_spawning.py

@@ -2,6 +2,7 @@
 Spawning basics
 
 """
+from functools import partial
 from typing import (
     Any,
 )
@@ -12,74 +13,95 @@ import tractor
 
 from tractor._testing import tractor_test
 
-data_to_pass_down = {'doggy': 10, 'kitty': 4}
+data_to_pass_down = {
+    'doggy': 10,
+    'kitty': 4,
+}
 
 
 async def spawn(
-    is_arbiter: bool,
+    should_be_root: bool,
     data: dict,
     reg_addr: tuple[str, int],
-):
-    namespaces = [__name__]
 
+    debug_mode: bool = False,
+):
     await trio.sleep(0.1)
+    actor = tractor.current_actor(err_on_no_runtime=False)
 
-    async with tractor.open_root_actor(
+    if should_be_root:
+        assert actor is None  # no runtime yet
+        async with (
+            tractor.open_root_actor(
                 arbiter_addr=reg_addr,
+            ),
+            tractor.open_nursery() as an,
         ):
-        actor = tractor.current_actor()
-        assert actor.is_arbiter == is_arbiter
-        data = data_to_pass_down
+            # now runtime exists
+            actor: tractor.Actor = tractor.current_actor()
+            assert actor.is_arbiter == should_be_root
 
-        if actor.is_arbiter:
-            async with tractor.open_nursery() as nursery:
+            # spawns subproc here
+            portal: tractor.Portal = await an.run_in_actor(
+                fn=spawn,
 
-                # forks here
-                portal = await nursery.run_in_actor(
-                    spawn,
-                    is_arbiter=False,
+                # spawning args
                 name='sub-actor',
-                    data=data,
+                enable_modules=[__name__],
+
+                # passed to a subactor-recursive RPC invoke
+                # of this same `spawn()` fn.
+                should_be_root=False,
+                data=data_to_pass_down,
                 reg_addr=reg_addr,
-                    enable_modules=namespaces,
             )
 
-                assert len(nursery._children) == 1
+            assert len(an._children) == 1
             assert portal.channel.uid in tractor.current_actor()._peers
-                # be sure we can still get the result
+
+            # 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_local_arbiter_subactor_global_state(
-    reg_addr,
+def test_run_in_actor_same_func_in_child(
+    reg_addr: tuple,
+    debug_mode: bool,
 ):
     result = trio.run(
+        partial(
             spawn,
-        True,
-        data_to_pass_down,
-        reg_addr,
+            should_be_root=True,
+            data=data_to_pass_down,
+            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.
-    """
-    async with tractor.open_nursery() as n:
+    '''
+    The main ``tractor`` routine.
 
-        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__],
@@ -118,8 +140,8 @@ async def test_most_beautiful_word(
     with trio.fail_after(1):
         async with tractor.open_nursery(
             debug_mode=debug_mode,
-        ) as n:
-            portal = await n.run_in_actor(
+        ) as an:
+            portal = await an.run_in_actor(
                 cellar_door,
                 return_value=return_value,
                 name='some_linguist',

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

@@ -0,0 +1,583 @@
+# 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 pathlib import Path
+import os
+# import tempfile
+from uuid import uuid4
+from typing import (
+    Protocol,
+    ClassVar,
+    # TypeVar,
+    # Union,
+    Type,
+    TYPE_CHECKING,
+)
+
+from bidict import bidict
+# import trio
+from trio import (
+    socket,
+    SocketListener,
+    open_tcp_listeners,
+)
+
+from .log import get_logger
+from ._state import (
+    get_rt_dir,
+    current_actor,
+    is_root_process,
+    _def_tpt_proto,
+)
+
+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):
+        ...
+
+
+class TCPAddress(Address):
+    proto_key: str = 'tcp'
+    unwrapped_type: type = tuple[str, int]
+    def_bindspace: str = '127.0.0.1'
+
+    def __init__(
+        self,
+        host: str,
+        port: int
+    ):
+        if (
+            not isinstance(host, str)
+            or
+            not isinstance(port, int)
+        ):
+            raise TypeError(
+                f'Expected host {host!r} to be str and port {port!r} to be int'
+            )
+
+        self._host: str = host
+        self._port: int = port
+
+    @property
+    def is_valid(self) -> bool:
+        return self._port != 0
+
+    @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) -> Address:
+        return TCPAddress(
+            '127.0.0.1',
+            1616,
+        )
+
+    def __repr__(self) -> str:
+        return (
+            f'{type(self).__name__}[{self.unwrap()}]'
+        )
+
+    def __eq__(self, other) -> bool:
+        if not isinstance(other, TCPAddress):
+            raise TypeError(
+                f'Can not compare {type(other)} with {type(self)}'
+            )
+
+        return (
+            self._host == other._host
+            and
+            self._port == other._port
+        )
+
+    async def open_listener(
+        self,
+        **kwargs,
+    ) -> SocketListener:
+        listeners: list[SocketListener] = await open_tcp_listeners(
+            host=self._host,
+            port=self._port,
+            **kwargs
+        )
+        assert len(listeners) == 1
+        listener = listeners[0]
+        self._host, self._port = listener.socket.getsockname()[:2]
+        return listener
+
+    async def close_listener(self):
+        ...
+
+
+def unwrap_sockpath(
+    sockpath: Path,
+) -> tuple[Path, Path]:
+    return (
+        sockpath.parent,
+        sockpath.name,
+    )
+
+
+class UDSAddress(Address):
+    # 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: str = 'uds'
+    unwrapped_type: type = tuple[str, int]
+    def_bindspace: Path = get_rt_dir()
+
+    def __init__(
+        self,
+        filedir: Path|str|None,
+        # TODO, i think i want `.filename` here?
+        filename: str|Path,
+
+        # XXX, in the sense you can also pass
+        # a "non-real-world-process-id" such as is handy to represent
+        # our host-local default "port-like" key for the very first
+        # root actor to create a registry address.
+        maybe_pid: int|None = None,
+    ):
+        fdir = self._filedir = Path(
+            filedir
+            or
+            self.def_bindspace
+        ).absolute()
+        fpath = self._filename = Path(filename)
+        fp: Path = fdir / fpath
+        assert (
+            fp.is_absolute()
+            and
+            fp == self.sockpath
+        )
+
+        # to track which "side" is the peer process by reading socket
+        # credentials-info.
+        self._pid: int = maybe_pid
+
+    @property
+    def sockpath(self) -> Path:
+        return self._filedir / 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
+
+    @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
+
+    @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])
+                # sockpath: Path = Path(addr[0])
+                # filedir, filename = unwrap_sockpath(sockpath)
+                # pid: int = 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) -> Address:
+        def_uds_filename: Path = 'registry@1616.sock'
+        return UDSAddress(
+            filedir=None,
+            filename=def_uds_filename,
+            # maybe_pid=1616,
+        )
+
+    def __repr__(self) -> str:
+        return (
+            f'{type(self).__name__}'
+            f'['
+            f'({self._filedir}, {self._filename})'
+            f']'
+        )
+
+    def __eq__(self, other) -> bool:
+        if not isinstance(other, UDSAddress):
+            raise TypeError(
+                f'Can not compare {type(other)} with {type(self)}'
+            )
+
+        return self.sockpath == other.sockpath
+
+    # async def open_listener(self, **kwargs) -> SocketListener:
+    async def open_listener(
+        self,
+        **kwargs,
+    ) -> SocketListener:
+        sock = self._sock = socket.socket(
+            socket.AF_UNIX,
+            socket.SOCK_STREAM
+        )
+        log.info(
+            f'Attempting to bind UDS socket\n'
+            f'>[\n'
+            f'|_{self}\n'
+        )
+
+        bindpath: Path = self.sockpath
+        await sock.bind(str(bindpath))
+        sock.listen(1)
+        log.info(
+            f'Listening on UDS socket\n'
+            f'[>\n'
+            f' |_{self}\n'
+        )
+        return SocketListener(self._sock)
+
+    def close_listener(self):
+        self._sock.close()
+        os.unlink(self.sockpath)
+
+
+_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

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

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 (
@@ -105,7 +105,7 @@ from ._state import (
 if TYPE_CHECKING:
     from ._portal import Portal
     from ._runtime import Actor
-    from ._ipc import MsgTransport
+    from .ipc import MsgTransport
     from .devx._frame_stack import (
         CallerInfo,
     )
@@ -366,7 +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.uid}'\n"
+            f"   uid{ds}'{self.chan.aid}'\n"
             f"   cid{ds}'{self.cid}'\n"
             # f'   ---\n'
             f'\n'
@@ -859,19 +859,10 @@ 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 (
-            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 ?
-        )
+        return trans.maddr
 
     dmaddr = dst_maddr
 
@@ -954,9 +945,9 @@ class Context:
         reminfo: str = (
             # ' =>\n'
             # f'Context.cancel() => {self.chan.uid}\n'
+            f'\n'
             f'c)=> {self.chan.uid}\n'
-            # f'{self.chan.uid}\n'
-            f'  |_ @{self.dst_maddr}\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

tractor/_discovery.py

@@ -29,7 +29,12 @@ from contextlib import asynccontextmanager as acm
 
 from tractor.log import get_logger
 from .trionics import gather_contexts
-from ._ipc import _connect_chan, Channel
+from .ipc import _connect_chan, Channel
+from ._addr import (
+    UnwrappedAddress,
+    Address,
+    wrap_address
+)
 from ._portal import (
     Portal,
     open_portal,
@@ -38,6 +43,7 @@ from ._portal import (
 from ._state import (
     current_actor,
     _runtime_vars,
+    _def_tpt_proto,
 )
 
 if TYPE_CHECKING:
@@ -49,9 +55,7 @@ log = get_logger(__name__)
 
 @acm
 async def get_registry(
-    host: str,
-    port: int,
-
+    addr: UnwrappedAddress|None = None,
 ) -> AsyncGenerator[
     Portal | LocalPortal | None,
     None,
@@ -69,13 +73,15 @@ async def get_registry(
         # (likely a re-entrant call from the arbiter actor)
         yield LocalPortal(
             actor,
-            Channel((host, port))
+            Channel(transport=None)
+            # ^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
         # `Actor._peers` and use it instead?
         async with (
-            _connect_chan(host, port) as chan,
+            _connect_chan(addr) as chan,
             open_portal(chan) as regstr_ptl,
         ):
             yield regstr_ptl
@@ -89,11 +95,10 @@ async def get_root(
 
     # TODO: rename mailbox to `_root_maddr` when we finally
     # add and impl libp2p multi-addrs?
-    host, port = _runtime_vars['_root_mailbox']
-    assert host is not None
+    addr = _runtime_vars['_root_mailbox']
 
     async with (
-        _connect_chan(host, port) as chan,
+        _connect_chan(addr) as chan,
         open_portal(chan, **kwargs) as portal,
     ):
         yield portal
@@ -134,10 +139,10 @@ def get_peer_by_name(
 @acm
 async def query_actor(
     name: str,
-    regaddr: tuple[str, int]|None = None,
+    regaddr: UnwrappedAddress|None = None,
 
 ) -> AsyncGenerator[
-    tuple[str, int]|None,
+    UnwrappedAddress|None,
     None,
 ]:
     '''
@@ -163,31 +168,31 @@ async def query_actor(
         return
 
     reg_portal: Portal
-    regaddr: tuple[str, int] = regaddr or actor.reg_addrs[0]
-    async with get_registry(*regaddr) as reg_portal:
+    regaddr: Address = wrap_address(regaddr) or actor.reg_addrs[0]
+    async with get_registry(regaddr) as reg_portal:
         # TODO: return portals to all available actors - for now
         # just the last one that registered
-        sockaddr: tuple[str, int] = await reg_portal.run_from_ns(
+        addr: UnwrappedAddress = await reg_portal.run_from_ns(
             'self',
             'find_actor',
             name=name,
         )
-        yield sockaddr
+        yield addr
 
 
 @acm
 async def maybe_open_portal(
-    addr: tuple[str, int],
+    addr: UnwrappedAddress,
     name: str,
 ):
     async with query_actor(
         name=name,
         regaddr=addr,
-    ) as sockaddr:
+    ) as addr:
         pass
 
-    if sockaddr:
-        async with _connect_chan(*sockaddr) as chan:
+    if addr:
+        async with _connect_chan(addr) as chan:
             async with open_portal(chan) as portal:
                 yield portal
     else:
@@ -197,7 +202,8 @@ async def maybe_open_portal(
 @acm
 async def find_actor(
     name: str,
-    registry_addrs: list[tuple[str, int]]|None = None,
+    registry_addrs: list[UnwrappedAddress]|None = None,
+    enable_transports: list[str] = [_def_tpt_proto],
 
     only_first: bool = True,
     raise_on_none: bool = False,
@@ -224,15 +230,15 @@ 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 . import _root
+        from ._addr import default_lo_addrs
         registry_addrs = (
             _runtime_vars['_registry_addrs']
             or
-            _root._default_lo_addrs
+            default_lo_addrs(enable_transports)
         )
 
     maybe_portals: list[
-        AsyncContextManager[tuple[str, int]]
+        AsyncContextManager[UnwrappedAddress]
     ] = list(
         maybe_open_portal(
             addr=addr,
@@ -274,7 +280,7 @@ async def find_actor(
 @acm
 async def wait_for_actor(
     name: str,
-    registry_addr: tuple[str, int] | None = None,
+    registry_addr: UnwrappedAddress | None = None,
 
 ) -> AsyncGenerator[Portal, None]:
     '''
@@ -291,7 +297,7 @@ async def wait_for_actor(
             yield peer_portal
             return
 
-    regaddr: tuple[str, int] = (
+    regaddr: UnwrappedAddress = (
         registry_addr
         or
         actor.reg_addrs[0]
@@ -299,8 +305,8 @@ 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:
-        sockaddrs = await reg_portal.run_from_ns(
+    async with get_registry(regaddr) as reg_portal:
+        addrs = await reg_portal.run_from_ns(
             'self',
             'wait_for_actor',
             name=name,
@@ -308,8 +314,8 @@ async def wait_for_actor(
 
         # get latest registered addr by default?
         # TODO: offer multi-portal yields in multi-homed case?
-        sockaddr: tuple[str, int] = sockaddrs[-1]
+        addr: UnwrappedAddress = addrs[-1]
 
-        async with _connect_chan(*sockaddr) as chan:
+        async with _connect_chan(addr) as chan:
             async with open_portal(chan) as portal:
                 yield portal

tractor/_entry.py

@@ -37,6 +37,7 @@ from .log import (
 from . import _state
 from .devx import _debug
 from .to_asyncio import run_as_asyncio_guest
+from ._addr import UnwrappedAddress
 from ._runtime import (
     async_main,
     Actor,
@@ -52,10 +53,10 @@ log = get_logger(__name__)
 def _mp_main(
 
     actor: Actor,
-    accept_addrs: list[tuple[str, int]],
+    accept_addrs: list[UnwrappedAddress],
     forkserver_info: tuple[Any, Any, Any, Any, Any],
     start_method: SpawnMethodKey,
-    parent_addr: tuple[str, int] | None = None,
+    parent_addr: UnwrappedAddress | None = None,
     infect_asyncio: bool = False,
 
 ) -> None:
@@ -206,7 +207,7 @@ def nest_from_op(
 def _trio_main(
     actor: Actor,
     *,
-    parent_addr: tuple[str, int] | None = None,
+    parent_addr: UnwrappedAddress|None = None,
     infect_asyncio: bool = False,
 
 ) -> None:

tractor/_exceptions.py

@@ -23,7 +23,6 @@ import builtins
 import importlib
 from pprint import pformat
 from pdb import bdb
-import sys
 from types import (
     TracebackType,
 )
@@ -65,15 +64,29 @@ 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 ActorFailure(Exception):
-    "General actor failure"
+class RuntimeFailure(RuntimeError):
+    '''
+    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):
@@ -126,6 +139,12 @@ 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',
@@ -191,6 +210,8 @@ def get_err_type(type_name: str) -> BaseException|None:
         ):
             return type_ref
 
+    return None
+
 
 def pack_from_raise(
     local_err: (
@@ -521,7 +542,6 @@ class RemoteActorError(Exception):
             if val:
                 _repr += f'{key}={val_str}{end_char}'
 
-
         return _repr
 
     def reprol(self) -> str:
@@ -600,56 +620,9 @@ 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
@@ -670,21 +643,15 @@ class RemoteActorError(Exception):
                 boxer_header=self.relay_uid,
             )
 
-        tail = ''
-        if (
-            with_type_header
-            and not message
-        ):
-            tail: str = '>'
-
-        return (
-            header
-            +
-            message
-            +
-            f'{body}'
-            +
-            tail
+        # !TODO, it'd be nice to import these top level without
+        # cycles!
+        from tractor.devx.pformat import (
+            pformat_exc,
+        )
+        return pformat_exc(
+            exc=self,
+            with_type_header=with_type_header,
+            body=body,
         )
 
     __repr__ = pformat
@@ -962,7 +929,7 @@ class StreamOverrun(
     '''
 
 
-class TransportClosed(trio.BrokenResourceError):
+class TransportClosed(Exception):
     '''
     IPC transport (protocol) connection was closed or broke and
     indicates that the wrapping communication `Channel` can no longer
@@ -973,16 +940,21 @@ class TransportClosed(trio.BrokenResourceError):
         self,
         message: str,
         loglevel: str = 'transport',
-        cause: BaseException|None = None,
+        src_exc: Exception|None = None,
         raise_on_report: bool = False,
 
     ) -> None:
         self.message: str = message
-        self._loglevel = loglevel
+        self._loglevel: str = loglevel
         super().__init__(message)
 
-        if cause is not None:
-            self.__cause__ = cause
+        self.src_exc = src_exc
+        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.
@@ -1009,13 +981,36 @@ class TransportClosed(trio.BrokenResourceError):
                 f'    {cause}\n'  # exc repr
             )
 
-        getattr(log, self._loglevel)(message)
+        getattr(
+            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
 
+    def pformat(self) -> str:
+        from tractor.devx.pformat import (
+            pformat_exc,
+        )
+        src_err: Exception|None = self.src_exc or '<unknown>'
+        src_msg: tuple[str] = src_err.args
+        src_exc_repr: str = (
+            f'{type(src_err).__name__}[ {src_msg} ]'
+        )
+        return pformat_exc(
+            exc=self,
+            # message=self.message,  # implicit!
+            body=(
+                f' |_src_exc: {src_exc_repr}\n'
+            ),
+        )
+
+    # delegate to `str`-ified pformat
+    __repr__ = pformat
+
 
 class NoResult(RuntimeError):
     "No final result is expected for this actor"

tractor/_ipc.py

@@ -1,820 +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,
-    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

@@ -43,7 +43,7 @@ from .trionics import maybe_open_nursery
 from ._state import (
     current_actor,
 )
-from ._ipc import Channel
+from .ipc import Channel
 from .log import get_logger
 from .msg import (
     # Error,
@@ -107,6 +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
@@ -171,7 +175,7 @@ class Portal:
         # not expecting a "main" result
         if self._expect_result_ctx is None:
             log.warning(
-                f"Portal for {self.channel.uid} not expecting a final"
+                f"Portal for {self.channel.aid} not expecting a final"
                 " result?\nresult() should only be called if subactor"
                 " was spawned with `ActorNursery.run_in_actor()`")
             return NoResult
@@ -218,7 +222,7 @@ class Portal:
         # IPC calls
         if self._streams:
             log.cancel(
-                f"Cancelling all streams with {self.channel.uid}")
+                f"Cancelling all streams with {self.channel.aid}")
             for stream in self._streams.copy():
                 try:
                     await stream.aclose()
@@ -263,7 +267,7 @@ class Portal:
             return False
 
         reminfo: str = (
-            f'c)=> {self.channel.uid}\n'
+            f'c)=> {self.channel.aid}\n'
             f'  |_{chan}\n'
         )
         log.cancel(
@@ -306,7 +310,7 @@ class Portal:
         ):
             log.debug(
                 'IPC chan for actor already closed or broken?\n\n'
-                f'{self.channel.uid}\n'
+                f'{self.channel.aid}\n'
                 f' |_{self.channel}\n'
             )
             return False
@@ -504,8 +508,12 @@ class LocalPortal:
         return it's result.
 
         '''
-        obj = self.actor if ns == 'self' else importlib.import_module(ns)
-        func = getattr(obj, func_name)
+        obj = (
+            self.actor
+            if ns == 'self'
+            else importlib.import_module(ns)
+        )
+        func: Callable = getattr(obj, func_name)
         return await func(**kwargs)
 
 
@@ -543,8 +551,10 @@ async def open_portal(
             await channel.connect()
             was_connected = True
 
-        if channel.uid is None:
-            await actor._do_handshake(channel)
+        if channel.aid is None:
+            await channel._do_handshake(
+                aid=actor.aid,
+            )
 
         msg_loop_cs: trio.CancelScope|None = None
         if start_msg_loop:

tractor/_root.py

@@ -18,7 +18,9 @@
 Root actor runtime ignition(s).
 
 '''
-from contextlib import asynccontextmanager as acm
+from contextlib import (
+    asynccontextmanager as acm,
+)
 from functools import partial
 import importlib
 import inspect
@@ -26,7 +28,10 @@ import logging
 import os
 import signal
 import sys
-from typing import Callable
+from typing import (
+    Any,
+    Callable,
+)
 import warnings
 
 
@@ -43,33 +48,109 @@ from .devx import _debug
 from . import _spawn
 from . import _state
 from . import log
-from ._ipc import _connect_chan
-from ._exceptions import is_multi_cancelled
-
-
-# set at startup and after forks
-_default_host: str = '127.0.0.1'
-_default_port: int = 1616
-
-# default registry always on localhost
-_default_lo_addrs: list[tuple[str, int]] = [(
-    _default_host,
-    _default_port,
-)]
+from .ipc import (
+    _connect_chan,
+)
+from ._addr import (
+    Address,
+    UnwrappedAddress,
+    default_lo_addrs,
+    mk_uuid,
+    wrap_address,
+)
+from ._exceptions import (
+    RuntimeFailure,
+    is_multi_cancelled,
+)
 
 
 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(
+    debug_mode: bool,
+    maybe_enable_greenback: bool,
+) -> bool:
+    # Override the global debugger hook to make it play nice with
+    # ``trio``, see much discussion in:
+    # https://github.com/python-trio/trio/issues/1155#issuecomment-742964018
+    builtin_bp_handler: Callable = sys.breakpointhook
+    orig_bp_path: str|None = os.environ.get(
+        'PYTHONBREAKPOINT',
+        None,
+    )
+    bp_blocked: bool
+    if (
+        debug_mode
+        and maybe_enable_greenback
+        and (
+            maybe_mod := await _debug.maybe_init_greenback(
+                raise_not_found=False,
+            )
+        )
+    ):
+        logger.info(
+            f'Found `greenback` installed @ {maybe_mod}\n'
+            'Enabling `tractor.pause_from_sync()` support!\n'
+        )
+        os.environ['PYTHONBREAKPOINT'] = (
+            'tractor.devx._debug._sync_pause_from_builtin'
+        )
+        _state._runtime_vars['use_greenback'] = True
+        bp_blocked = False
+
+    else:
+        # TODO: disable `breakpoint()` by default (without
+        # `greenback`) since it will break any multi-actor
+        # usage by a clobbered TTY's stdstreams!
+        def block_bps(*args, **kwargs):
+            raise RuntimeError(
+                'Trying to use `breakpoint()` eh?\n\n'
+                'Welp, `tractor` blocks `breakpoint()` built-in calls by default!\n'
+                'If you need to use it please install `greenback` and set '
+                '`debug_mode=True` when opening the runtime '
+                '(either via `.open_nursery()` or `open_root_actor()`)\n'
+            )
+
+        sys.breakpointhook = block_bps
+        # lol ok,
+        # https://docs.python.org/3/library/sys.html#sys.breakpointhook
+        os.environ['PYTHONBREAKPOINT'] = "0"
+        bp_blocked = True
+
+    try:
+        yield bp_blocked
+    finally:
+        # 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:
+            os.environ['PYTHONBREAKPOINT'] = orig_bp_path
+
+        else:
+            # clear env back to having no entry
+            os.environ.pop('PYTHONBREAKPOINT', None)
+
+
+
 @acm
 async def open_root_actor(
-
     *,
     # defaults are above
-    registry_addrs: list[tuple[str, int]]|None = None,
+    registry_addrs: list[UnwrappedAddress]|None = None,
 
     # defaults are above
-    arbiter_addr: tuple[str, int]|None = None,
+    arbiter_addr: tuple[UnwrappedAddress]|None = None,
+
+    enable_transports: list[
+        _state.TransportProtocolKey,
+    ] = [_state._def_tpt_proto],
 
     name: str|None = 'root',
 
@@ -111,55 +192,30 @@ async def open_root_actor(
     Runtime init entry point for ``tractor``.
 
     '''
+    # XXX NEVER allow nested actor-trees!
+    if already_actor := _state.current_actor(err_on_no_runtime=False):
+        rtvs: dict[str, Any] = _state._runtime_vars
+        root_mailbox: list[str, int] = rtvs['_root_mailbox']
+        registry_addrs: list[list[str, int]] = rtvs['_registry_addrs']
+        raise RuntimeFailure(
+            f'A current actor already exists !?\n'
+            f'({already_actor}\n'
+            f'\n'
+            f'You can NOT open a second root actor from within '
+            f'an existing tree and the current root of this '
+            f'already exists !!\n'
+            f'\n'
+            f'_root_mailbox: {root_mailbox!r}\n'
+            f'_registry_addrs: {registry_addrs!r}\n'
+        )
+
+    async with maybe_block_bp(
+        debug_mode=debug_mode,
+        maybe_enable_greenback=maybe_enable_greenback,
+    ):
         _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
-    builtin_bp_handler: Callable = sys.breakpointhook
-    orig_bp_path: str|None = os.environ.get(
-        'PYTHONBREAKPOINT',
-        None,
-    )
-    if (
-        debug_mode
-        and maybe_enable_greenback
-        and (
-            maybe_mod := await _debug.maybe_init_greenback(
-                raise_not_found=False,
-            )
-        )
-    ):
-        logger.info(
-            f'Found `greenback` installed @ {maybe_mod}\n'
-            'Enabling `tractor.pause_from_sync()` support!\n'
-        )
-        os.environ['PYTHONBREAKPOINT'] = (
-            'tractor.devx._debug._sync_pause_from_builtin'
-        )
-        _state._runtime_vars['use_greenback'] = True
-
-    else:
-        # TODO: disable `breakpoint()` by default (without
-        # `greenback`) since it will break any multi-actor
-        # usage by a clobbered TTY's stdstreams!
-        def block_bps(*args, **kwargs):
-            raise RuntimeError(
-                'Trying to use `breakpoint()` eh?\n\n'
-                'Welp, `tractor` blocks `breakpoint()` built-in calls by default!\n'
-                'If you need to use it please install `greenback` and set '
-                '`debug_mode=True` when opening the runtime '
-                '(either via `.open_nursery()` or `open_root_actor()`)\n'
-            )
-
-        sys.breakpointhook = block_bps
-        # lol ok,
-        # https://docs.python.org/3/library/sys.html#sys.breakpointhook
-        os.environ['PYTHONBREAKPOINT'] = "0"
-
         # attempt to retreive ``trio``'s sigint handler and stash it
         # on our debugger lock state.
         _debug.DebugStatus._trio_handler = signal.getsignal(signal.SIGINT)
@@ -186,6 +242,7 @@ async def open_root_actor(
         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'
@@ -195,11 +252,11 @@ async def open_root_actor(
             )
             registry_addrs = [arbiter_addr]
 
-    registry_addrs: list[tuple[str, int]] = (
-        registry_addrs
-        or
-        _default_lo_addrs
+        if not registry_addrs:
+            registry_addrs: list[UnwrappedAddress] = default_lo_addrs(
+                enable_transports
             )
+
         assert registry_addrs
 
         loglevel = (
@@ -248,10 +305,10 @@ async def open_root_actor(
             enable_stack_on_sig()
 
         # closed into below ping task-func
-    ponged_addrs: list[tuple[str, int]] = []
+        ponged_addrs: list[UnwrappedAddress] = []
 
         async def ping_tpt_socket(
-        addr: tuple[str, int],
+            addr: UnwrappedAddress,
             timeout: float = 1,
         ) -> None:
             '''
@@ -271,7 +328,7 @@ async def open_root_actor(
                 # be better to eventually have a "discovery" protocol
                 # with basic handshake instead?
                 with trio.move_on_after(timeout):
-                async with _connect_chan(*addr):
+                    async with _connect_chan(addr):
                         ponged_addrs.append(addr)
 
             except OSError:
@@ -284,10 +341,10 @@ async def open_root_actor(
             for addr in registry_addrs:
                 tn.start_soon(
                     ping_tpt_socket,
-                tuple(addr),  # TODO: just drop this requirement?
+                    addr,
                 )
 
-    trans_bind_addrs: list[tuple[str, int]] = []
+        trans_bind_addrs: list[UnwrappedAddress] = []
 
         # Create a new local root-actor instance which IS NOT THE
         # REGISTRAR
@@ -305,15 +362,18 @@ async def open_root_actor(
 
             actor = Actor(
                 name=name or 'anonymous',
+                uuid=mk_uuid(),
                 registry_addrs=ponged_addrs,
                 loglevel=loglevel,
                 enable_modules=enable_modules,
             )
             # DO NOT use the registry_addrs as the transport server
             # 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))
+            for addr in ponged_addrs:
+                waddr: Address = wrap_address(addr)
+                trans_bind_addrs.append(
+                    waddr.get_random(bindspace=waddr.bindspace)
+                )
 
         # Start this local actor as the "registrar", aka a regular
         # actor who manages the local registry of "mailboxes" of
@@ -322,7 +382,7 @@ async def open_root_actor(
 
             # 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)
+            # - the tranport layer server is bound to each addr
             #   pair defined in provided registry_addrs, or the default.
             trans_bind_addrs = registry_addrs
 
@@ -336,7 +396,8 @@ async def open_root_actor(
             # https://github.com/goodboy/tractor/issues/296
 
             actor = Arbiter(
-            name or 'registrar',
+                name=name or 'registrar',
+                uuid=mk_uuid(),
                 registry_addrs=registry_addrs,
                 loglevel=loglevel,
                 enable_modules=enable_modules,
@@ -414,7 +475,11 @@ async def open_root_actor(
                             err,
                         )
                     ):
-                    logger.exception('Root actor crashed\n')
+                        logger.exception(
+                            'Root actor crashed\n'
+                            f'>x)\n'
+                            f' |_{actor}\n'
+                        )
 
                     # ALWAYS re-raise any error bubbled up from the
                     # runtime!
@@ -431,30 +496,19 @@ async def open_root_actor(
                     #         tempn.start_soon(an.exited.wait)
 
                     logger.info(
-                    'Closing down root actor'
+                        f'Closing down root actor\n'
+                        f'>)\n'
+                        f'|_{actor}\n'
                     )
                     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")
+            logger.runtime(
+                f'Root actor terminated\n'
+                f')>\n'
+                f' |_{actor}\n'
+            )
 
 
 def run_daemon(
@@ -462,7 +516,7 @@ def run_daemon(
 
     # runtime kwargs
     name: str | None = 'root',
-    registry_addrs: list[tuple[str, int]] = _default_lo_addrs,
+    registry_addrs: list[UnwrappedAddress]|None = None,
 
     start_method: str | None = None,
     debug_mode: bool = False,

tractor/_rpc.py

@@ -42,7 +42,7 @@ from trio import (
     TaskStatus,
 )
 
-from ._ipc import Channel
+from .ipc import Channel
 from ._context import (
     Context,
 )
@@ -1156,7 +1156,7 @@ async def process_messages(
                                 trio.Event(),
                             )
 
-                    # runtime-scoped remote (internal) error
+                    # XXX RUNTIME-SCOPED! remote (likely internal) error
                     # (^- bc no `Error.cid` -^)
                     #
                     # NOTE: this is the non-rpc error case, that
@@ -1219,8 +1219,10 @@ 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\n'
-                f'<=x {chan}\n'
+                f'peer IPC channel closed abruptly?\n'
+                f'\n'
+                f'<=x[\n'
+                f'  {chan}\n'
                 f'  |_{chan.raddr}\n\n'
             )
             +

tractor/_runtime.py

@@ -52,6 +52,7 @@ import sys
 from typing import (
     Any,
     Callable,
+    Type,
     TYPE_CHECKING,
 )
 import uuid
@@ -73,7 +74,14 @@ from tractor.msg import (
     pretty_struct,
     types as msgtypes,
 )
-from ._ipc import Channel
+from .ipc import Channel
+from ._addr import (
+    UnwrappedAddress,
+    Address,
+    default_lo_addrs,
+    get_address_cls,
+    wrap_address,
+)
 from ._context import (
     mk_context,
     Context,
@@ -175,15 +183,15 @@ class Actor:
     def __init__(
         self,
         name: str,
+        uuid: str,
         *,
         enable_modules: list[str] = [],
-        uid: str|None = None,
         loglevel: str|None = None,
-        registry_addrs: list[tuple[str, int]]|None = None,
+        registry_addrs: list[UnwrappedAddress]|None = None,
         spawn_method: str|None = None,
 
         # TODO: remove!
-        arbiter_addr: tuple[str, int]|None = None,
+        arbiter_addr: UnwrappedAddress|None = None,
 
     ) -> None:
         '''
@@ -191,12 +199,14 @@ class Actor:
         phase (aka before a new process is executed).
 
         '''
-        self.name = name
-        self.uid = (
-            name,
-            uid or str(uuid.uuid4())
+        self._aid = msgtypes.Aid(
+            name=name,
+            uuid=uuid,
+            pid=os.getpid(),
         )
+        self._task: trio.Task|None = None
 
+        # state
         self._cancel_complete = trio.Event()
         self._cancel_called_by_remote: tuple[str, tuple]|None = None
         self._cancel_called: bool = False
@@ -223,7 +233,7 @@ class Actor:
                 DeprecationWarning,
                 stacklevel=2,
             )
-            registry_addrs: list[tuple[str, int]] = [arbiter_addr]
+            registry_addrs: list[UnwrappedAddress] = [arbiter_addr]
 
         # marked by the process spawning backend at startup
         # will be None for the parent most process started manually
@@ -257,6 +267,7 @@ class Actor:
         ] = {}
 
         self._listeners: list[trio.abc.Listener] = []
+        self._listen_addrs: list[Address] = []
         self._parent_chan: Channel|None = None
         self._forkserver_info: tuple|None = None
 
@@ -269,13 +280,97 @@ class Actor:
 
         # when provided, init the registry addresses property from
         # input via the validator.
-        self._reg_addrs: list[tuple[str, int]] = []
+        self._reg_addrs: list[UnwrappedAddress] = []
         if registry_addrs:
-            self.reg_addrs: list[tuple[str, int]] = registry_addrs
+            self.reg_addrs: list[UnwrappedAddress] = registry_addrs
             _state._runtime_vars['_registry_addrs'] = registry_addrs
 
     @property
-    def reg_addrs(self) -> list[tuple[str, int]]:
+    def aid(self) -> msgtypes.Aid:
+        '''
+        This process-singleton-actor's "unique actor ID" in struct form.
+
+        See the `tractor.msg.Aid` struct for details.
+
+        '''
+        return self._aid
+
+    @property
+    def name(self) -> str:
+        return self._aid.name
+
+    @property
+    def uid(self) -> tuple[str, str]:
+        '''
+        This process-singleton's "unique (cross-host) ID".
+
+        Delivered from the `.Aid.name/.uuid` fields as a `tuple` pair
+        and should be multi-host unique despite a large distributed
+        process plane.
+
+        '''
+        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,
+        )
+        return (
+            self._aid.name,
+            self._aid.uuid,
+        )
+
+    @property
+    def pid(self) -> int:
+        return self._aid.pid
+
+    def pformat(self) -> str:
+        ds: str = '='
+        parent_uid: tuple|None = None
+        if rent_chan := self._parent_chan:
+            parent_uid = rent_chan.uid
+        peers: list[tuple] = list(self._peer_connected)
+        listen_addrs: str = pformat(self._listen_addrs)
+        fmtstr: str = (
+            f' |_id: {self.aid!r}\n'
+            # f"   aid{ds}{self.aid!r}\n"
+            f"   parent{ds}{parent_uid}\n"
+            f'\n'
+            f' |_ipc: {len(peers)!r} connected peers\n'
+            f"   peers{ds}{peers!r}\n"
+            f"   _listen_addrs{ds}'{listen_addrs}'\n"
+            f"   _listeners{ds}'{self._listeners}'\n"
+            f'\n'
+            f' |_rpc: {len(self._rpc_tasks)} tasks\n'
+            f"   ctxs{ds}{len(self._contexts)}\n"
+            f'\n'
+            f' |_runtime: ._task{ds}{self._task!r}\n'
+            f'   _spawn_method{ds}{self._spawn_method}\n'
+            f'   _actoruid2nursery{ds}{self._actoruid2nursery}\n'
+            f'   _forkserver_info{ds}{self._forkserver_info}\n'
+            f'\n'
+            f' |_state: "TODO: .repr_state()"\n'
+            f'   _cancel_complete{ds}{self._cancel_complete}\n'
+            f'   _cancel_called_by_remote{ds}{self._cancel_called_by_remote}\n'
+            f'   _cancel_called{ds}{self._cancel_called}\n'
+        )
+        return (
+            '<Actor(\n'
+            +
+            fmtstr
+            +
+            ')>\n'
+        )
+
+    __repr__ = pformat
+
+    @property
+    def reg_addrs(self) -> list[UnwrappedAddress]:
         '''
         List of (socket) addresses for all known (and contactable)
         registry actors.
@@ -286,7 +381,7 @@ class Actor:
     @reg_addrs.setter
     def reg_addrs(
         self,
-        addrs: list[tuple[str, int]],
+        addrs: list[UnwrappedAddress],
     ) -> None:
         if not addrs:
             log.warning(
@@ -295,15 +390,6 @@ class Actor:
             )
             return
 
-        # always sanity check the input list since it's critical
-        # that addrs are correct for discovery sys operation.
-        for addr in addrs:
-            if not isinstance(addr, tuple):
-                raise ValueError(
-                    'Expected `Actor.reg_addrs: list[tuple[str, int]]`\n'
-                    f'Got {addrs}'
-                )
-
         self._reg_addrs = addrs
 
     async def wait_for_peer(
@@ -421,14 +507,23 @@ class Actor:
 
         # send/receive initial handshake response
         try:
-            uid: tuple|None = await self._do_handshake(chan)
+            peer_aid: msgtypes.Aid = await chan._do_handshake(
+                aid=self.aid,
+            )
         except (
-            # we need this for ``msgspec`` for some reason?
-            # for now, it's been put in the stream backend.
+            TransportClosed,
+            # ^XXX NOTE, the above wraps `trio` exc types raised
+            # during various `SocketStream.send/receive_xx()` calls
+            # under different fault conditions such as,
+            #
             # trio.BrokenResourceError,
             # trio.ClosedResourceError,
-
-            TransportClosed,
+            #
+            # Inside our `.ipc._transport` layer we absorb and
+            # re-raise our own `TransportClosed` exc such that this
+            # higher level runtime code can only worry one
+            # "kinda-error" that we expect to tolerate during
+            # discovery-sys related pings, queires, DoS etc.
         ):
             # XXX: This may propagate up from `Channel._aiter_recv()`
             # and `MsgpackStream._inter_packets()` on a read from the
@@ -443,6 +538,12 @@ class Actor:
             )
             return
 
+        uid: tuple[str, str] = (
+            peer_aid.name,
+            peer_aid.uuid,
+        )
+        # TODO, can we make this downstream peer tracking use the
+        # `peer_aid` instead?
         familiar: str = 'new-peer'
         if _pre_chan := self._peers.get(uid):
             familiar: str = 'pre-existing-peer'
@@ -1024,11 +1125,12 @@ class Actor:
 
     async def _from_parent(
         self,
-        parent_addr: tuple[str, int]|None,
+        parent_addr: UnwrappedAddress|None,
 
     ) -> tuple[
         Channel,
-        list[tuple[str, int]]|None,
+        list[UnwrappedAddress]|None,
+        list[str]|None,  # preferred tpts
     ]:
         '''
         Bootstrap this local actor's runtime config from its parent by
@@ -1040,23 +1142,25 @@ class Actor:
             # Connect back to the parent actor and conduct initial
             # handshake. From this point on if we error, we
             # attempt to ship the exception back to the parent.
-            chan = Channel(
-                destaddr=parent_addr,
+            chan = await Channel.from_addr(
+                addr=wrap_address(parent_addr)
             )
-            await chan.connect()
+            assert isinstance(chan, Channel)
 
-            # TODO: move this into a `Channel.handshake()`?
             # Initial handshake: swap names.
-            await self._do_handshake(chan)
+            await chan._do_handshake(aid=self.aid)
 
-            accept_addrs: list[tuple[str, int]]|None = None
+            accept_addrs: list[UnwrappedAddress]|None = None
 
             if self._spawn_method == "trio":
 
                 # Receive post-spawn runtime state from our parent.
                 spawnspec: msgtypes.SpawnSpec = await chan.recv()
+                match spawnspec:
+                    case MsgTypeError():
+                        raise spawnspec
+                    case msgtypes.SpawnSpec():
                         self._spawn_spec = spawnspec
-
                         log.runtime(
                             'Received runtime spec from parent:\n\n'
 
@@ -1066,7 +1170,29 @@ class Actor:
                             # if "trace"/"util" mode is enabled?
                             f'{pretty_struct.pformat(spawnspec)}\n'
                         )
-                accept_addrs: list[tuple[str, int]] = spawnspec.bind_addrs
+
+                    case _:
+                        raise InternalError(
+                            f'Received invalid non-`SpawnSpec` payload !?\n'
+                            f'{spawnspec}\n'
+                        )
+
+                # ^^TODO XXX!! when the `SpawnSpec` fails to decode
+                # the above will raise a `MsgTypeError` which if we
+                # do NOT ALSO RAISE it will tried to be pprinted in
+                # the log.runtime() below..
+                #
+                # SO we gotta look at how other `chan.recv()` calls
+                # are wrapped and do the same for this spec receive!
+                # -[ ] see `._rpc` likely has the answer?
+                #
+                # XXX NOTE, can't be called here in subactor
+                # bc we haven't yet received the
+                # `SpawnSpec._runtime_vars: dict` which would
+                # declare whether `debug_mode` is set!
+                # breakpoint()
+                # import pdbp; pdbp.set_trace()
+                accept_addrs: list[UnwrappedAddress] = spawnspec.bind_addrs
 
                 # TODO: another `Struct` for rtvs..
                 rvs: dict[str, Any] = spawnspec._runtime_vars
@@ -1158,11 +1284,19 @@ class Actor:
             return (
                 chan,
                 accept_addrs,
+                None,
+                # ^TODO, preferred tpts list from rent!
+                # -[ ] need to extend the `SpawnSpec` tho!
             )
 
-        except OSError:  # failed to connect
+        # failed to connect back?
+        except (
+            OSError,
+            ConnectionError,
+        ):
             log.warning(
                 f'Failed to connect to spawning parent actor!?\n'
+                f'\n'
                 f'x=> {parent_addr}\n'
                 f'  |_{self}\n\n'
             )
@@ -1173,54 +1307,78 @@ class Actor:
         self,
         handler_nursery: Nursery,
         *,
-        # (host, port) to bind for channel server
-        listen_sockaddrs: list[tuple[str, int]]|None = None,
+        listen_addrs: list[UnwrappedAddress]|None = None,
 
         task_status: TaskStatus[Nursery] = trio.TASK_STATUS_IGNORED,
     ) -> None:
         '''
-        Start the IPC transport server, begin listening for new connections.
+        Start the IPC transport server, begin listening/accepting new
+        `trio.SocketStream` connections.
 
         This will cause an actor to continue living (and thus
         blocking at the process/OS-thread level) until
         `.cancel_server()` is called.
 
         '''
-        if listen_sockaddrs is None:
-            listen_sockaddrs = [(None, 0)]
+        if listen_addrs is None:
+            listen_addrs = default_lo_addrs([
+                _state._def_tpt_proto
+            ])
+
+        else:
+            listen_addrs: list[Address] = [
+                wrap_address(a) for a in listen_addrs
+            ]
 
         self._server_down = trio.Event()
         try:
             async with trio.open_nursery() as server_n:
 
-                for host, port in listen_sockaddrs:
-                    listeners: list[trio.abc.Listener] = await server_n.start(
-                        partial(
-                            trio.serve_tcp,
+                listeners: list[trio.abc.Listener] = []
+                for addr in listen_addrs:
+                    try:
+                        listener: trio.abc.Listener = await addr.open_listener()
+                    except OSError as oserr:
+                        if (
+                            '[Errno 98] Address already in use'
+                            in
+                            oserr.args#[0]
+                        ):
+                            log.exception(
+                                f'Address already in use?\n'
+                                f'{addr}\n'
+                            )
+                        raise
+                    listeners.append(listener)
 
+                await server_n.start(
+                    partial(
+                        trio.serve_listeners,
                         handler=self._stream_handler,
-                            port=port,
-                            host=host,
+                        listeners=listeners,
 
                         # NOTE: configured such that new
                         # connections will stay alive even if
                         # this server is cancelled!
-                            handler_nursery=handler_nursery,
+                        handler_nursery=handler_nursery
                     )
                 )
-                    sockets: list[trio.socket] = [
-                        getattr(listener, 'socket', 'unknown socket')
-                        for listener in listeners
-                    ]
-                    log.runtime(
-                        'Started TCP server(s)\n'
-                        f'|_{sockets}\n'
+                # TODO, wow make this message better! XD
+                log.info(
+                    'Started server(s)\n'
+                    +
+                    '\n'.join([f'|_{addr}' for addr in listen_addrs])
                 )
+                self._listen_addrs.extend(listen_addrs)
                 self._listeners.extend(listeners)
 
                 task_status.started(server_n)
 
         finally:
+            addr: Address
+            for addr in listen_addrs:
+                addr.close_listener()
+
             # signal the server is down since nursery above terminated
             self._server_down.set()
 
@@ -1327,8 +1485,13 @@ class Actor:
             if self._server_down is not None:
                 await self._server_down.wait()
             else:
+                tpt_protos: list[str] = []
+                addr: Address
+                for addr in self._listen_addrs:
+                    tpt_protos.append(addr.proto_key)
                 log.warning(
-                    'Transport[TCP] server was cancelled start?'
+                    'Transport server(s) may have been cancelled before started?\n'
+                    f'protos: {tpt_protos!r}\n'
                 )
 
             # cancel all rpc tasks permanently
@@ -1579,26 +1742,21 @@ class Actor:
         return False
 
     @property
-    def accept_addrs(self) -> list[tuple[str, int]]:
+    def accept_addrs(self) -> list[UnwrappedAddress]:
         '''
         All addresses to which the transport-channel server binds
         and listens for new connections.
 
         '''
-        # throws OSError on failure
-        return [
-            listener.socket.getsockname() 
-            for listener in self._listeners
-        ]  # type: ignore
+        return [a.unwrap() for a in self._listen_addrs]
 
     @property
-    def accept_addr(self) -> tuple[str, int]:
+    def accept_addr(self) -> UnwrappedAddress:
         '''
         Primary address to which the IPC transport server is
         bound and listening for new connections.
 
         '''
-        # throws OSError on failure
         return self.accept_addrs[0]
 
     def get_parent(self) -> Portal:
@@ -1620,43 +1778,6 @@ class Actor:
         '''
         return self._peers[uid]
 
-    # TODO: move to `Channel.handshake(uid)`
-    async def _do_handshake(
-        self,
-        chan: Channel
-
-    ) -> msgtypes.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.
-
-        '''
-        name, uuid = self.uid
-        await chan.send(
-            msgtypes.Aid(
-                name=name,
-                uuid=uuid,
-            )
-        )
-        aid: msgtypes.Aid = await chan.recv()
-        chan.aid = aid
-
-        uid: tuple[str, str] = (
-            # str(value[0]),
-            # str(value[1])
-            aid.name,
-            aid.uuid,
-        )
-
-        if not isinstance(uid, tuple):
-            raise ValueError(f"{uid} is not a valid uid?!")
-
-        chan.uid = uid
-        return uid
-
     def is_infected_aio(self) -> bool:
         '''
         If `True`, this actor is running `trio` in guest mode on
@@ -1670,7 +1791,7 @@ class Actor:
 
 async def async_main(
     actor: Actor,
-    accept_addrs: tuple[str, int]|None = None,
+    accept_addrs: UnwrappedAddress|None = None,
 
     # XXX: currently ``parent_addr`` is only needed for the
     # ``multiprocessing`` backend (which pickles state sent to
@@ -1679,7 +1800,7 @@ async def async_main(
     # change this to a simple ``is_subactor: bool`` which will
     # be False when running as root actor and True when as
     # a subactor.
-    parent_addr: tuple[str, int]|None = None,
+    parent_addr: UnwrappedAddress|None = None,
     task_status: TaskStatus[None] = trio.TASK_STATUS_IGNORED,
 
 ) -> None:
@@ -1694,6 +1815,8 @@ async def async_main(
     the actor's "runtime" and all thus all ongoing RPC tasks.
 
     '''
+    actor._task: trio.Task = trio.lowlevel.current_task()
+
     # attempt to retreive ``trio``'s sigint handler and stash it
     # on our debugger state.
     _debug.DebugStatus._trio_handler = signal.getsignal(signal.SIGINT)
@@ -1703,13 +1826,15 @@ async def async_main(
 
         # establish primary connection with immediate parent
         actor._parent_chan: Channel|None = None
-        if parent_addr is not None:
 
+        if parent_addr is not None:
             (
                 actor._parent_chan,
                 set_accept_addr_says_rent,
+                maybe_preferred_transports_says_rent,
             ) = await actor._from_parent(parent_addr)
 
+            accept_addrs: list[UnwrappedAddress] = []
             # either it's passed in because we're not a child or
             # because we're running in mp mode
             if (
@@ -1718,6 +1843,18 @@ async def async_main(
                 set_accept_addr_says_rent is not None
             ):
                 accept_addrs = set_accept_addr_says_rent
+            else:
+                enable_transports: list[str] = (
+                    maybe_preferred_transports_says_rent
+                    or
+                    [_state._def_tpt_proto]
+                )
+                for transport_key in enable_transports:
+                    transport_cls: Type[Address] = get_address_cls(
+                        transport_key
+                    )
+                    addr: Address = transport_cls.get_random()
+                    accept_addrs.append(addr.unwrap())
 
         # The "root" nursery ensures the channel with the immediate
         # parent is kept alive as a resilient service until
@@ -1769,7 +1906,7 @@ async def async_main(
                         partial(
                             actor._serve_forever,
                             service_nursery,
-                            listen_sockaddrs=accept_addrs,
+                            listen_addrs=accept_addrs,
                         )
                     )
                 except OSError as oserr:
@@ -1785,7 +1922,7 @@ async def async_main(
 
                     raise
 
-                accept_addrs: list[tuple[str, int]] = actor.accept_addrs
+                accept_addrs: list[UnwrappedAddress] = actor.accept_addrs
 
                 # NOTE: only set the loopback addr for the 
                 # process-tree-global "root" mailbox since
@@ -1793,9 +1930,8 @@ async def async_main(
                 # their root actor over that channel.
                 if _state._runtime_vars['_is_root']:
                     for addr in accept_addrs:
-                        host, _ = addr
-                        # TODO: generic 'lo' detector predicate
-                        if '127.0.0.1' in host:
+                        waddr = wrap_address(addr)
+                        if waddr == waddr.get_root():
                             _state._runtime_vars['_root_mailbox'] = addr
 
                 # Register with the arbiter if we're told its addr
@@ -1810,24 +1946,21 @@ async def async_main(
                 # only on unique actor uids?
                 for addr in actor.reg_addrs:
                     try:
-                        assert isinstance(addr, tuple)
-                        assert addr[1]  # non-zero after bind
+                        waddr = wrap_address(addr)
+                        assert waddr.is_valid
                     except AssertionError:
                         await _debug.pause()
 
-                    async with get_registry(*addr) as reg_portal:
+                    async with get_registry(addr) as reg_portal:
                         for accept_addr in accept_addrs:
-
-                            if not accept_addr[1]:
-                                await _debug.pause()
-
-                            assert accept_addr[1]
+                            accept_addr = wrap_address(accept_addr)
+                            assert accept_addr.is_valid
 
                             await reg_portal.run_from_ns(
                                 'self',
                                 'register_actor',
                                 uid=actor.uid,
-                                sockaddr=accept_addr,
+                                addr=accept_addr.unwrap(),
                             )
 
                     is_registered: bool = True
@@ -1954,12 +2087,13 @@ async def async_main(
         ):
             failed: bool = False
             for addr in actor.reg_addrs:
-                assert isinstance(addr, tuple)
+                waddr = wrap_address(addr)
+                assert waddr.is_valid
                 with trio.move_on_after(0.5) as cs:
                     cs.shield = True
                     try:
                         async with get_registry(
-                            *addr,
+                            addr,
                         ) as reg_portal:
                             await reg_portal.run_from_ns(
                                 'self',
@@ -2001,15 +2135,15 @@ async def async_main(
     log.info(teardown_report)
 
 
-# TODO: rename to `Registry` and move to `._discovery`!
+# TODO: rename to `Registry` and move to `.discovery._registry`!
 class Arbiter(Actor):
     '''
-    A special registrar actor who can contact all other actors
-    within its immediate process tree and possibly keeps a registry
-    of others meant to be discoverable in a distributed
-    application. Normally the registrar is also the "root actor"
-    and thus always has access to the top-most-level actor
-    (process) nursery.
+    A special registrar (and for now..) `Actor` who can contact all
+    other actors within its immediate process tree and possibly keeps
+    a registry of others meant to be discoverable in a distributed
+    application. Normally the registrar is also the "root actor" and
+    thus always has access to the top-most-level actor (process)
+    nursery.
 
     By default, the registrar is always initialized when and if no
     other registrar socket addrs have been specified to runtime
@@ -2029,6 +2163,12 @@ class Arbiter(Actor):
     '''
     is_arbiter = True
 
+    # TODO, implement this as a read on there existing a `._state` of
+    # some sort setup by whenever we impl this all as
+    # a `.discovery._registry.open_registry()` API
+    def is_registry(self) -> bool:
+        return self.is_arbiter
+
     def __init__(
         self,
         *args,
@@ -2037,7 +2177,7 @@ class Arbiter(Actor):
 
         self._registry: dict[
             tuple[str, str],
-            tuple[str, int],
+            UnwrappedAddress,
         ] = {}
         self._waiters: dict[
             str,
@@ -2053,18 +2193,18 @@ class Arbiter(Actor):
         self,
         name: str,
 
-    ) -> tuple[str, int]|None:
+    ) -> UnwrappedAddress|None:
 
-        for uid, sockaddr in self._registry.items():
+        for uid, addr in self._registry.items():
             if name in uid:
-                return sockaddr
+                return addr
 
         return None
 
     async def get_registry(
         self
 
-    ) -> dict[str, tuple[str, int]]:
+    ) -> dict[str, UnwrappedAddress]:
         '''
         Return current name registry.
 
@@ -2084,7 +2224,7 @@ class Arbiter(Actor):
         self,
         name: str,
 
-    ) -> list[tuple[str, int]]:
+    ) -> list[UnwrappedAddress]:
         '''
         Wait for a particular actor to register.
 
@@ -2092,44 +2232,41 @@ class Arbiter(Actor):
         registered.
 
         '''
-        sockaddrs: list[tuple[str, int]] = []
-        sockaddr: tuple[str, int]
+        addrs: list[UnwrappedAddress] = []
+        addr: UnwrappedAddress
 
         mailbox_info: str = 'Actor registry contact infos:\n'
-        for uid, sockaddr in self._registry.items():
+        for uid, addr in self._registry.items():
             mailbox_info += (
                 f'|_uid: {uid}\n'
-                f'|_sockaddr: {sockaddr}\n\n'
+                f'|_addr: {addr}\n\n'
             )
             if name == uid[0]:
-                sockaddrs.append(sockaddr)
+                addrs.append(addr)
 
-        if not sockaddrs:
+        if not addrs:
             waiter = trio.Event()
             self._waiters.setdefault(name, []).append(waiter)
             await waiter.wait()
 
             for uid in self._waiters[name]:
                 if not isinstance(uid, trio.Event):
-                    sockaddrs.append(self._registry[uid])
+                    addrs.append(self._registry[uid])
 
         log.runtime(mailbox_info)
-        return sockaddrs
+        return addrs
 
     async def register_actor(
         self,
         uid: tuple[str, str],
-        sockaddr: tuple[str, int]
-
+        addr: UnwrappedAddress
     ) -> None:
         uid = name, hash = (str(uid[0]), str(uid[1]))
-        addr = (host, port) = (
-            str(sockaddr[0]),
-            int(sockaddr[1]),
-        )
-        if port == 0:
+        waddr: Address = wrap_address(addr)
+        if not waddr.is_valid:
+            # should never be 0-dynamic-os-alloc
             await _debug.pause()
-        assert port  # should never be 0-dynamic-os-alloc
+
         self._registry[uid] = addr
 
         # pop and signal all waiter events

tractor/_spawn.py

@@ -46,11 +46,13 @@ 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.types import (
+    Aid,
     SpawnSpec,
 )
 
@@ -163,7 +165,7 @@ async def exhaust_portal(
         # TODO: merge with above?
         log.warning(
             'Cancelled portal result waiter task:\n'
-            f'uid: {portal.channel.uid}\n'
+            f'uid: {portal.channel.aid}\n'
             f'error: {err}\n'
         )
         return err
@@ -171,7 +173,7 @@ async def exhaust_portal(
     else:
         log.debug(
             f'Returning final result from portal:\n'
-            f'uid: {portal.channel.uid}\n'
+            f'uid: {portal.channel.aid}\n'
             f'result: {final}\n'
         )
         return final
@@ -324,12 +326,12 @@ async def soft_kill(
     see `.hard_kill()`).
 
     '''
-    uid: tuple[str, str] = portal.channel.uid
+    peer_aid: Aid = portal.channel.aid
     try:
         log.cancel(
             f'Soft killing sub-actor via portal request\n'
             f'\n'
-            f'(c=> {portal.chan.uid}\n'
+            f'(c=> {peer_aid}\n'
             f'  |_{proc}\n'
         )
         # wait on sub-proc to signal termination
@@ -378,7 +380,7 @@ async def soft_kill(
             if proc.poll() is None:  # type: ignore
                 log.warning(
                     'Subactor still alive after cancel request?\n\n'
-                    f'uid: {uid}\n'
+                    f'uid: {peer_aid}\n'
                     f'|_{proc}\n'
                 )
                 n.cancel_scope.cancel()
@@ -392,14 +394,15 @@ async def new_proc(
     errors: dict[tuple[str, str], Exception],
 
     # passed through to actor main
-    bind_addrs: list[tuple[str, int]],
-    parent_addr: tuple[str, int],
+    bind_addrs: list[UnwrappedAddress],
+    parent_addr: UnwrappedAddress,
     _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:
 
@@ -419,6 +422,7 @@ async def new_proc(
         _runtime_vars,  # run time vars
         infect_asyncio=infect_asyncio,
         task_status=task_status,
+        proc_kwargs=proc_kwargs
     )
 
 
@@ -429,12 +433,13 @@ async def trio_proc(
     errors: dict[tuple[str, str], Exception],
 
     # passed through to actor main
-    bind_addrs: list[tuple[str, int]],
-    parent_addr: tuple[str, int],
+    bind_addrs: list[UnwrappedAddress],
+    parent_addr: UnwrappedAddress,
     _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:
     '''
@@ -456,6 +461,9 @@ 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 `Aid.min_tuple()` ?
         str(subactor.uid),
         # Address the child must connect to on startup
         "--parent_addr",
@@ -475,7 +483,7 @@ async def trio_proc(
     proc: trio.Process|None = None
     try:
         try:
-            proc: trio.Process = await trio.lowlevel.open_process(spawn_cmd)
+            proc: trio.Process = await trio.lowlevel.open_process(spawn_cmd, **proc_kwargs)
             log.runtime(
                 'Started new child\n'
                 f'|_{proc}\n'
@@ -517,15 +525,15 @@ async def trio_proc(
 
         # send a "spawning specification" which configures the
         # initial runtime state of the child.
-        await chan.send(
-            SpawnSpec(
+        sspec = SpawnSpec(
             _parent_main_data=subactor._parent_main_data,
             enable_modules=subactor.enable_modules,
             reg_addrs=subactor.reg_addrs,
             bind_addrs=bind_addrs,
             _runtime_vars=_runtime_vars,
         )
-        )
+        log.runtime(f'Sending spawn spec: {str(sspec)}')
+        await chan.send(sspec)
 
         # track subactor in current nursery
         curr_actor: Actor = current_actor()
@@ -635,12 +643,13 @@ async def mp_proc(
     subactor: Actor,
     errors: dict[tuple[str, str], Exception],
     # passed through to actor main
-    bind_addrs: list[tuple[str, int]],
-    parent_addr: tuple[str, int],
+    bind_addrs: list[UnwrappedAddress],
+    parent_addr: UnwrappedAddress,
     _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:
 
@@ -720,7 +729,8 @@ async def mp_proc(
         # channel should have handshake completed by the
         # local actor by the time we get a ref to it
         event, chan = await actor_nursery._actor.wait_for_peer(
-            subactor.uid)
+            subactor.uid,
+        )
 
         # XXX: monkey patch poll API to match the ``subprocess`` API..
         # not sure why they don't expose this but kk.

tractor/_state.py

@@ -14,16 +14,19 @@
 # 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 process state
+'''
+Per actor-process runtime state mgmt APIs.
 
-"""
+'''
 from __future__ import annotations
 from contextvars import (
     ContextVar,
 )
+import os
+from pathlib import Path
 from typing import (
     Any,
+    Literal,
     TYPE_CHECKING,
 )
 
@@ -143,3 +146,30 @@ 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
+
+
+# default IPC transport protocol settings
+TransportProtocolKey = Literal[
+    'tcp',
+    'uds',
+]
+_def_tpt_proto: TransportProtocolKey = 'tcp'

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__)
@@ -437,22 +437,23 @@ 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'x}}>\n'
+                f'c}}>\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
             ):
-                log.cancel(
-                    f'Msg-stream is closing but there is still reader tasks,\n'
+                message += (
+                    f'AND 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
@@ -595,8 +596,17 @@ class MsgStream(trio.abc.Channel):
             trio.ClosedResourceError,
             trio.BrokenResourceError,
             BrokenPipeError,
-        ) as trans_err:
-            if hide_tb:
+        ) as _trans_err:
+            trans_err = _trans_err
+            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
@@ -802,13 +812,12 @@ async def open_stream_from_ctx(
                 # sanity, can remove?
                 assert eoc is stream._eoc
 
-                log.warning(
+                log.runtime(
                     '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

@@ -22,13 +22,20 @@ from contextlib import asynccontextmanager as acm
 from functools import partial
 import inspect
 from pprint import pformat
-from typing import TYPE_CHECKING
+from typing import (
+    TYPE_CHECKING,
+)
 import typing
 import warnings
 
 import trio
 
+
 from .devx._debug import maybe_wait_for_debugger
+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
@@ -37,7 +44,9 @@ from ._exceptions import (
     is_multi_cancelled,
     ContextCancelled,
 )
-from ._root import open_root_actor
+from ._root import (
+    open_root_actor,
+)
 from . import _state
 from . import _spawn
 
@@ -47,8 +56,6 @@ if TYPE_CHECKING:
 
 log = get_logger(__name__)
 
-_default_bind_addr: tuple[str, int] = ('127.0.0.1', 0)
-
 
 class ActorNursery:
     '''
@@ -130,8 +137,9 @@ class ActorNursery:
 
         *,
 
-        bind_addrs: list[tuple[str, int]] = [_default_bind_addr],
+        bind_addrs: list[UnwrappedAddress]|None = None,
         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,
@@ -141,6 +149,7 @@ class ActorNursery:
         # a `._ria_nursery` since the dependent APIs have been
         # removed!
         nursery: trio.Nursery|None = None,
+        proc_kwargs: dict[str, any] = {}
 
     ) -> Portal:
         '''
@@ -177,7 +186,9 @@ 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,
@@ -185,7 +196,7 @@ class ActorNursery:
             # verbatim relay this actor's registrar addresses
             registry_addrs=current_actor().reg_addrs,
         )
-        parent_addr = self._actor.accept_addr
+        parent_addr: UnwrappedAddress = self._actor.accept_addr
         assert parent_addr
 
         # start a task to spawn a process
@@ -204,6 +215,7 @@ class ActorNursery:
                 parent_addr,
                 _rtv,  # run time vars
                 infect_asyncio=infect_asyncio,
+                proc_kwargs=proc_kwargs
             )
         )
 
@@ -222,11 +234,12 @@ class ActorNursery:
         *,
 
         name: str | None = None,
-        bind_addrs: tuple[str, int] = [_default_bind_addr],
+        bind_addrs: UnwrappedAddress|None = None,
         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``
 
@@ -257,6 +270,7 @@ 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

tractor/_testing/samples.py

@@ -0,0 +1,35 @@
+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/_debug.py

@@ -73,6 +73,7 @@ from tractor.log import get_logger
 from tractor._context import Context
 from tractor import _state
 from tractor._exceptions import (
+    DebugRequestError,
     InternalError,
     NoRuntime,
     is_multi_cancelled,
@@ -91,7 +92,7 @@ from tractor._state import (
 if TYPE_CHECKING:
     from trio.lowlevel import Task
     from threading import Thread
-    from tractor._ipc import Channel
+    from tractor.ipc import Channel
     from tractor._runtime import (
         Actor,
     )
@@ -1740,13 +1741,6 @@ def sigint_shield(
 _pause_msg: str = 'Opening a pdb REPL in paused actor'
 
 
-class DebugRequestError(RuntimeError):
-    '''
-    Failed to request stdio lock from root actor!
-
-    '''
-
-
 _repl_fail_msg: str|None = (
     'Failed to REPl via `_pause()` '
 )

tractor/devx/pformat.py

@@ -19,6 +19,7 @@ Pretty formatters for use throughout the code base.
 Mostly handy for logging and exception message content.
 
 '''
+import sys
 import textwrap
 import traceback
 
@@ -115,6 +116,85 @@ 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,

tractor/experimental/_pubsub.py

@@ -45,6 +45,8 @@ __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

@@ -0,0 +1,55 @@
+# 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/>.
+import platform
+
+from ._transport import (
+    MsgTransportKey as MsgTransportKey,
+    MsgType as MsgType,
+    MsgTransport as MsgTransport,
+    MsgpackTransport as MsgpackTransport
+)
+
+from ._tcp import MsgpackTCPStream as MsgpackTCPStream
+from ._uds import MsgpackUDSStream as MsgpackUDSStream
+
+from ._types import (
+    transport_from_addr as transport_from_addr,
+    transport_from_stream as transport_from_stream,
+)
+
+from ._chan import (
+    _connect_chan as _connect_chan,
+    Channel as Channel
+)
+
+if platform.system() == 'Linux':
+    from ._linux import (
+        EFD_SEMAPHORE as EFD_SEMAPHORE,
+        EFD_CLOEXEC as EFD_CLOEXEC,
+        EFD_NONBLOCK as EFD_NONBLOCK,
+        open_eventfd as open_eventfd,
+        write_eventfd as write_eventfd,
+        read_eventfd as read_eventfd,
+        close_eventfd as close_eventfd,
+        EventFD as EventFD,
+    )
+
+    from ._ringbuf import (
+        RBToken as RBToken,
+        RingBuffSender as RingBuffSender,
+        RingBuffReceiver as RingBuffReceiver,
+        open_ringbuf as open_ringbuf
+    )

tractor/ipc/_chan.py

@@ -0,0 +1,444 @@
+# 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,
+)
+import warnings
+
+import trio
+
+from tractor.ipc._transport import MsgTransport
+from tractor.ipc._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,
+)
+from tractor.msg import (
+    Aid,
+    MsgCodec,
+)
+
+
+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 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,
+        )
+        assert transport.raddr == addr
+        chan = Channel(transport=transport)
+        log.runtime(
+            f'Connected channel IPC transport\n'
+            f'[>\n'
+            f' |_{chan}\n'
+        )
+        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) -> 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'
+        )
+        return (
+            f'<Channel(\n'
+            f' |_status: {tpt_status!r}\n'
+            f'   _closed={self._closed}\n'
+            f'   _cancel_called={self._cancel_called}\n'
+            f'\n'
+            f' |_peer: {self.aid}\n'
+            f'\n'
+            f' |_msgstream: {tpt_name}\n'
+            f'   proto={tpt.laddr.proto_key!r}\n'
+            f'   layer={tpt.layer_key!r}\n'
+            f'   laddr={tpt.laddr}\n'
+            f'   raddr={tpt.raddr}\n'
+            f'   codec={tpt.codec_key!r}\n'
+            f'   stream={tpt.stream}\n'
+            f'   maddr={tpt.maddr!r}\n'
+            f'   drained={tpt.drained}\n'
+            f'   _send_lock={tpt._send_lock.statistics()}\n'
+            f')>\n'
+        )
+
+    # 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
+
+    # 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:
+                try:
+                    assert err.cid
+
+                except KeyError:
+                    raise err
+
+            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 actor,\n'
+            f'{peer_aid}\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/_linux.py

@@ -0,0 +1,153 @@
+# 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

@@ -0,0 +1,45 @@
+# 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
+
+'''
+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

tractor/ipc/_ringbuf.py

@@ -0,0 +1,253 @@
+# 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/_shm.py

@@ -0,0 +1,812 @@
+# tractor: structured concurrent "actors".
+# Copyright 2018-eternity Tyler Goodlet.
+
+# This program is free software: you can redistribute it and/or modify
+# it under the terms of the GNU Affero General Public License as published by
+# the Free Software Foundation, either version 3 of the License, or
+# (at your option) any later version.
+
+# This program is distributed in the hope that it will be useful,
+# but WITHOUT ANY WARRANTY; without even the implied warranty of
+# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+# GNU Affero General Public License for more details.
+
+# You should have received a copy of the GNU Affero General Public License
+# along with this program.  If not, see <https://www.gnu.org/licenses/>.
+
+"""
+SC friendly shared memory management geared at real-time
+processing.
+
+Support for ``numpy`` compatible array-buffers is provided but is
+considered optional within the context of this runtime-library.
+
+"""
+from __future__ import annotations
+from sys import byteorder
+import time
+from typing import Optional
+from multiprocessing import shared_memory as shm
+from multiprocessing.shared_memory import (
+    SharedMemory,
+    ShareableList,
+)
+
+from msgspec import (
+    Struct,
+    to_builtins
+)
+import tractor
+
+from tractor.ipc._mp_bs import disable_mantracker
+from tractor.log import get_logger
+
+
+_USE_POSIX = getattr(shm, '_USE_POSIX', False)
+if _USE_POSIX:
+    from _posixshmem import shm_unlink
+
+
+try:
+    import numpy as np
+    from numpy.lib import recfunctions as rfn
+    # TODO ruff complains with,
+    # warning| F401: `nptyping` imported but unused; consider using
+    # `importlib.util.find_spec` to test for availability
+    import nptyping  # noqa
+except ImportError:
+    pass
+
+
+log = get_logger(__name__)
+
+
+disable_mantracker()
+
+
+class SharedInt:
+    '''
+    Wrapper around a single entry shared memory array which
+    holds an ``int`` value used as an index counter.
+
+    '''
+    def __init__(
+        self,
+        shm: SharedMemory,
+    ) -> None:
+        self._shm = shm
+
+    @property
+    def value(self) -> int:
+        return int.from_bytes(self._shm.buf, byteorder)
+
+    @value.setter
+    def value(self, value) -> None:
+        self._shm.buf[:] = value.to_bytes(self._shm.size, byteorder)
+
+    def destroy(self) -> None:
+        if _USE_POSIX:
+            # We manually unlink to bypass all the "resource tracker"
+            # nonsense meant for non-SC systems.
+            name = self._shm.name
+            try:
+                shm_unlink(name)
+            except FileNotFoundError:
+                # might be a teardown race here?
+                log.warning(f'Shm for {name} already unlinked?')
+
+
+class NDToken(Struct, frozen=True):
+    '''
+    Internal represenation of a shared memory ``numpy`` array "token"
+    which can be used to key and load a system (OS) wide shm entry
+    and correctly read the array by type signature.
+
+    This type is msg safe.
+
+    '''
+    shm_name: str  # this servers as a "key" value
+    shm_first_index_name: str
+    shm_last_index_name: str
+    dtype_descr: tuple
+    size: int  # in struct-array index / row terms
+
+    # TODO: use nptyping here on dtypes
+    @property
+    def dtype(self) -> list[tuple[str, str, tuple[int, ...]]]:
+        return np.dtype(
+            list(
+                map(tuple, self.dtype_descr)
+            )
+        ).descr
+
+    def as_msg(self):
+        return to_builtins(self)
+
+    @classmethod
+    def from_msg(cls, msg: dict) -> NDToken:
+        if isinstance(msg, NDToken):
+            return msg
+
+        # TODO: native struct decoding
+        # return _token_dec.decode(msg)
+
+        msg['dtype_descr'] = tuple(map(tuple, msg['dtype_descr']))
+        return NDToken(**msg)
+
+
+# _token_dec = msgspec.msgpack.Decoder(NDToken)
+
+# TODO: this api?
+# _known_tokens = tractor.ActorVar('_shm_tokens', {})
+# _known_tokens = tractor.ContextStack('_known_tokens', )
+# _known_tokens = trio.RunVar('shms', {})
+
+# TODO: this should maybe be provided via
+# a `.trionics.maybe_open_context()` wrapper factory?
+# process-local store of keys to tokens
+_known_tokens: dict[str, NDToken] = {}
+
+
+def get_shm_token(key: str) -> NDToken | None:
+    '''
+    Convenience func to check if a token
+    for the provided key is known by this process.
+
+    Returns either the ``numpy`` token or a string for a shared list.
+
+    '''
+    return _known_tokens.get(key)
+
+
+def _make_token(
+    key: str,
+    size: int,
+    dtype: np.dtype,
+
+) -> NDToken:
+    '''
+    Create a serializable token that can be used
+    to access a shared array.
+
+    '''
+    return NDToken(
+        shm_name=key,
+        shm_first_index_name=key + "_first",
+        shm_last_index_name=key + "_last",
+        dtype_descr=tuple(np.dtype(dtype).descr),
+        size=size,
+    )
+
+
+class ShmArray:
+    '''
+    A shared memory ``numpy.ndarray`` API.
+
+    An underlying shared memory buffer is allocated based on
+    a user specified ``numpy.ndarray``. This fixed size array
+    can be read and written to by pushing data both onto the "front"
+    or "back" of a set index range. The indexes for the "first" and
+    "last" index are themselves stored in shared memory (accessed via
+    ``SharedInt`` interfaces) values such that multiple processes can
+    interact with the same array using a synchronized-index.
+
+    '''
+    def __init__(
+        self,
+        shmarr: np.ndarray,
+        first: SharedInt,
+        last: SharedInt,
+        shm: SharedMemory,
+        # readonly: bool = True,
+    ) -> None:
+        self._array = shmarr
+
+        # indexes for first and last indices corresponding
+        # to fille data
+        self._first = first
+        self._last = last
+
+        self._len = len(shmarr)
+        self._shm = shm
+        self._post_init: bool = False
+
+        # pushing data does not write the index (aka primary key)
+        self._write_fields: list[str] | None = None
+        dtype = shmarr.dtype
+        if dtype.fields:
+            self._write_fields = list(shmarr.dtype.fields.keys())[1:]
+
+    # TODO: ringbuf api?
+
+    @property
+    def _token(self) -> NDToken:
+        return NDToken(
+            shm_name=self._shm.name,
+            shm_first_index_name=self._first._shm.name,
+            shm_last_index_name=self._last._shm.name,
+            dtype_descr=tuple(self._array.dtype.descr),
+            size=self._len,
+        )
+
+    @property
+    def token(self) -> dict:
+        """Shared memory token that can be serialized and used by
+        another process to attach to this array.
+        """
+        return self._token.as_msg()
+
+    @property
+    def index(self) -> int:
+        return self._last.value % self._len
+
+    @property
+    def array(self) -> np.ndarray:
+        '''
+        Return an up-to-date ``np.ndarray`` view of the
+        so-far-written data to the underlying shm buffer.
+
+        '''
+        a = self._array[self._first.value:self._last.value]
+
+        # first, last = self._first.value, self._last.value
+        # a = self._array[first:last]
+
+        # TODO: eventually comment this once we've not seen it in the
+        # wild in a long time..
+        # XXX: race where first/last indexes cause a reader
+        # to load an empty array..
+        if len(a) == 0 and self._post_init:
+            raise RuntimeError('Empty array race condition hit!?')
+            # breakpoint()
+
+        return a
+
+    def ustruct(
+        self,
+        fields: Optional[list[str]] = None,
+
+        # type that all field values will be cast to
+        # in the returned view.
+        common_dtype: np.dtype = float,
+
+    ) -> np.ndarray:
+
+        array = self._array
+
+        if fields:
+            selection = array[fields]
+            # fcount = len(fields)
+        else:
+            selection = array
+            # fcount = len(array.dtype.fields)
+
+        # XXX: manual ``.view()`` attempt that also doesn't work.
+        # uview = selection.view(
+        #     dtype='<f16',
+        # ).reshape(-1, 4, order='A')
+
+        # assert len(selection) == len(uview)
+
+        u = rfn.structured_to_unstructured(
+            selection,
+            # dtype=float,
+            copy=True,
+        )
+
+        # unstruct = np.ndarray(u.shape, dtype=a.dtype, buffer=shm.buf)
+        # array[:] = a[:]
+        return u
+        # return ShmArray(
+        #     shmarr=u,
+        #     first=self._first,
+        #     last=self._last,
+        #     shm=self._shm
+        # )
+
+    def last(
+        self,
+        length: int = 1,
+
+    ) -> np.ndarray:
+        '''
+        Return the last ``length``'s worth of ("row") entries from the
+        array.
+
+        '''
+        return self.array[-length:]
+
+    def push(
+        self,
+        data: np.ndarray,
+
+        field_map: Optional[dict[str, str]] = None,
+        prepend: bool = False,
+        update_first: bool = True,
+        start: int | None = None,
+
+    ) -> int:
+        '''
+        Ring buffer like "push" to append data
+        into the buffer and return updated "last" index.
+
+        NB: no actual ring logic yet to give a "loop around" on overflow
+        condition, lel.
+
+        '''
+        length = len(data)
+
+        if prepend:
+            index = (start or self._first.value) - length
+
+            if index < 0:
+                raise ValueError(
+                    f'Array size of {self._len} was overrun during prepend.\n'
+                    f'You have passed {abs(index)} too many datums.'
+                )
+
+        else:
+            index = start if start is not None else self._last.value
+
+        end = index + length
+
+        if field_map:
+            src_names, dst_names = zip(*field_map.items())
+        else:
+            dst_names = src_names = self._write_fields
+
+        try:
+            self._array[
+                list(dst_names)
+            ][index:end] = data[list(src_names)][:]
+
+            # NOTE: there was a race here between updating
+            # the first and last indices and when the next reader
+            # tries to access ``.array`` (which due to the index
+            # overlap will be empty). Pretty sure we've fixed it now
+            # but leaving this here as a reminder.
+            if (
+                prepend
+                and update_first
+                and length
+            ):
+                assert index < self._first.value
+
+            if (
+                index < self._first.value
+                and update_first
+            ):
+                assert prepend, 'prepend=True not passed but index decreased?'
+                self._first.value = index
+
+            elif not prepend:
+                self._last.value = end
+
+            self._post_init = True
+            return end
+
+        except ValueError as err:
+            if field_map:
+                raise
+
+            # should raise if diff detected
+            self.diff_err_fields(data)
+            raise err
+
+    def diff_err_fields(
+        self,
+        data: np.ndarray,
+    ) -> None:
+        # reraise with any field discrepancy
+        our_fields, their_fields = (
+            set(self._array.dtype.fields),
+            set(data.dtype.fields),
+        )
+
+        only_in_ours = our_fields - their_fields
+        only_in_theirs = their_fields - our_fields
+
+        if only_in_ours:
+            raise TypeError(
+                f"Input array is missing field(s): {only_in_ours}"
+            )
+        elif only_in_theirs:
+            raise TypeError(
+                f"Input array has unknown field(s): {only_in_theirs}"
+            )
+
+    # TODO: support "silent" prepends that don't update ._first.value?
+    def prepend(
+        self,
+        data: np.ndarray,
+    ) -> int:
+        end = self.push(data, prepend=True)
+        assert end
+
+    def close(self) -> None:
+        self._first._shm.close()
+        self._last._shm.close()
+        self._shm.close()
+
+    def destroy(self) -> None:
+        if _USE_POSIX:
+            # We manually unlink to bypass all the "resource tracker"
+            # nonsense meant for non-SC systems.
+            shm_unlink(self._shm.name)
+
+        self._first.destroy()
+        self._last.destroy()
+
+    def flush(self) -> None:
+        # TODO: flush to storage backend like markestore?
+        ...
+
+
+def open_shm_ndarray(
+    size: int,
+    key: str | None = None,
+    dtype: np.dtype | None = None,
+    append_start_index: int | None = None,
+    readonly: bool = False,
+
+) -> ShmArray:
+    '''
+    Open a memory shared ``numpy`` using the standard library.
+
+    This call unlinks (aka permanently destroys) the buffer on teardown
+    and thus should be used from the parent-most accessor (process).
+
+    '''
+    # create new shared mem segment for which we
+    # have write permission
+    a = np.zeros(size, dtype=dtype)
+    a['index'] = np.arange(len(a))
+
+    shm = SharedMemory(
+        name=key,
+        create=True,
+        size=a.nbytes
+    )
+    array = np.ndarray(
+        a.shape,
+        dtype=a.dtype,
+        buffer=shm.buf
+    )
+    array[:] = a[:]
+    array.setflags(write=int(not readonly))
+
+    token = _make_token(
+        key=key,
+        size=size,
+        dtype=dtype,
+    )
+
+    # create single entry arrays for storing an first and last indices
+    first = SharedInt(
+        shm=SharedMemory(
+            name=token.shm_first_index_name,
+            create=True,
+            size=4,  # std int
+        )
+    )
+
+    last = SharedInt(
+        shm=SharedMemory(
+            name=token.shm_last_index_name,
+            create=True,
+            size=4,  # std int
+        )
+    )
+
+    # Start the "real-time" append-updated (or "pushed-to") section
+    # after some start index: ``append_start_index``. This allows appending
+    # from a start point in the array which isn't the 0 index and looks
+    # something like,
+    # -------------------------
+    # |              |        i
+    # _________________________
+    # <-------------> <------->
+    #  history         real-time
+    #
+    # Once fully "prepended", the history section will leave the
+    # ``ShmArray._start.value: int = 0`` and the yet-to-be written
+    # real-time section will start at ``ShmArray.index: int``.
+
+    # this sets the index to nearly 2/3rds into the the length of
+    # the buffer leaving at least a "days worth of second samples"
+    # for the real-time section.
+    if append_start_index is None:
+        append_start_index = round(size * 0.616)
+
+    last.value = first.value = append_start_index
+
+    shmarr = ShmArray(
+        array,
+        first,
+        last,
+        shm,
+    )
+
+    assert shmarr._token == token
+    _known_tokens[key] = shmarr.token
+
+    # "unlink" created shm on process teardown by
+    # pushing teardown calls onto actor context stack
+    stack = tractor.current_actor().lifetime_stack
+    stack.callback(shmarr.close)
+    stack.callback(shmarr.destroy)
+
+    return shmarr
+
+
+def attach_shm_ndarray(
+    token: tuple[str, str, tuple[str, str]],
+    readonly: bool = True,
+
+) -> ShmArray:
+    '''
+    Attach to an existing shared memory array previously
+    created by another process using ``open_shared_array``.
+
+    No new shared mem is allocated but wrapper types for read/write
+    access are constructed.
+
+    '''
+    token = NDToken.from_msg(token)
+    key = token.shm_name
+
+    if key in _known_tokens:
+        assert NDToken.from_msg(_known_tokens[key]) == token, "WTF"
+
+    # XXX: ugh, looks like due to the ``shm_open()`` C api we can't
+    # actually place files in a subdir, see discussion here:
+    # https://stackoverflow.com/a/11103289
+
+    # attach to array buffer and view as per dtype
+    _err: Optional[Exception] = None
+    for _ in range(3):
+        try:
+            shm = SharedMemory(
+                name=key,
+                create=False,
+            )
+            break
+        except OSError as oserr:
+            _err = oserr
+            time.sleep(0.1)
+    else:
+        if _err:
+            raise _err
+
+    shmarr = np.ndarray(
+        (token.size,),
+        dtype=token.dtype,
+        buffer=shm.buf
+    )
+    shmarr.setflags(write=int(not readonly))
+
+    first = SharedInt(
+        shm=SharedMemory(
+            name=token.shm_first_index_name,
+            create=False,
+            size=4,  # std int
+        ),
+    )
+    last = SharedInt(
+        shm=SharedMemory(
+            name=token.shm_last_index_name,
+            create=False,
+            size=4,  # std int
+        ),
+    )
+
+    # make sure we can read
+    first.value
+
+    sha = ShmArray(
+        shmarr,
+        first,
+        last,
+        shm,
+    )
+    # read test
+    sha.array
+
+    # Stash key -> token knowledge for future queries
+    # via `maybe_opepn_shm_array()` but only after we know
+    # we can attach.
+    if key not in _known_tokens:
+        _known_tokens[key] = token
+
+    # "close" attached shm on actor teardown
+    tractor.current_actor().lifetime_stack.callback(sha.close)
+
+    return sha
+
+
+def maybe_open_shm_ndarray(
+    key: str,  # unique identifier for segment
+    size: int,
+    dtype: np.dtype | None = None,
+    append_start_index: int = 0,
+    readonly: bool = True,
+
+) -> tuple[ShmArray, bool]:
+    '''
+    Attempt to attach to a shared memory block using a "key" lookup
+    to registered blocks in the users overall "system" registry
+    (presumes you don't have the block's explicit token).
+
+    This function is meant to solve the problem of discovering whether
+    a shared array token has been allocated or discovered by the actor
+    running in **this** process. Systems where multiple actors may seek
+    to access a common block can use this function to attempt to acquire
+    a token as discovered by the actors who have previously stored
+    a "key" -> ``NDToken`` map in an actor local (aka python global)
+    variable.
+
+    If you know the explicit ``NDToken`` for your memory segment instead
+    use ``attach_shm_array``.
+
+    '''
+    try:
+        # see if we already know this key
+        token = _known_tokens[key]
+        return (
+            attach_shm_ndarray(
+                token=token,
+                readonly=readonly,
+            ),
+            False,  # not newly opened
+        )
+    except KeyError:
+        log.warning(f"Could not find {key} in shms cache")
+        if dtype:
+            token = _make_token(
+                key,
+                size=size,
+                dtype=dtype,
+            )
+        else:
+
+            try:
+                return (
+                    attach_shm_ndarray(
+                        token=token,
+                        readonly=readonly,
+                    ),
+                    False,
+                )
+            except FileNotFoundError:
+                log.warning(f"Could not attach to shm with token {token}")
+
+        # This actor does not know about memory
+        # associated with the provided "key".
+        # Attempt to open a block and expect
+        # to fail if a block has been allocated
+        # on the OS by someone else.
+        return (
+            open_shm_ndarray(
+                key=key,
+                size=size,
+                dtype=dtype,
+                append_start_index=append_start_index,
+                readonly=readonly,
+            ),
+            True,
+        )
+
+
+class ShmList(ShareableList):
+    '''
+    Carbon copy of ``.shared_memory.ShareableList`` with a few
+    enhancements:
+
+    - readonly mode via instance var flag  `._readonly: bool`
+    - ``.__getitem__()`` accepts ``slice`` inputs
+    - exposes the underlying buffer "name" as a ``.key: str``
+
+    '''
+    def __init__(
+        self,
+        sequence: list | None = None,
+        *,
+        name: str | None = None,
+        readonly: bool = True
+
+    ) -> None:
+        self._readonly = readonly
+        self._key = name
+        return super().__init__(
+            sequence=sequence,
+            name=name,
+        )
+
+    @property
+    def key(self) -> str:
+        return self._key
+
+    @property
+    def readonly(self) -> bool:
+        return self._readonly
+
+    def __setitem__(
+        self,
+        position,
+        value,
+
+    ) -> None:
+
+        # mimick ``numpy`` error
+        if self._readonly:
+            raise ValueError('assignment destination is read-only')
+
+        return super().__setitem__(position, value)
+
+    def __getitem__(
+        self,
+        indexish,
+    ) -> list:
+
+        # NOTE: this is a non-writeable view (copy?) of the buffer
+        # in a new list instance.
+        if isinstance(indexish, slice):
+            return list(self)[indexish]
+
+        return super().__getitem__(indexish)
+
+    # TODO: should we offer a `.array` and `.push()` equivalent
+    # to the `ShmArray`?
+    # currently we have the following limitations:
+    # - can't write slices of input using traditional slice-assign
+    #   syntax due to the ``ShareableList.__setitem__()`` implementation.
+    # - ``list(shmlist)`` returns a non-mutable copy instead of
+    #   a writeable view which would be handier numpy-style ops.
+
+
+def open_shm_list(
+    key: str,
+    sequence: list | None = None,
+    size: int = int(2 ** 10),
+    dtype: float | int | bool | str | bytes | None = float,
+    readonly: bool = True,
+
+) -> ShmList:
+
+    if sequence is None:
+        default = {
+            float: 0.,
+            int: 0,
+            bool: True,
+            str: 'doggy',
+            None: None,
+        }[dtype]
+        sequence = [default] * size
+
+    shml = ShmList(
+        sequence=sequence,
+        name=key,
+        readonly=readonly,
+    )
+
+    # "close" attached shm on actor teardown
+    try:
+        actor = tractor.current_actor()
+        actor.lifetime_stack.callback(shml.shm.close)
+        actor.lifetime_stack.callback(shml.shm.unlink)
+    except RuntimeError:
+        log.warning('tractor runtime not active, skipping teardown steps')
+
+    return shml
+
+
+def attach_shm_list(
+    key: str,
+    readonly: bool = False,
+
+) -> ShmList:
+
+    return ShmList(
+        name=key,
+        readonly=readonly,
+    )

tractor/ipc/_tcp.py

@@ -0,0 +1,99 @@
+# 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 trio
+
+from tractor.msg import MsgCodec
+from tractor.log import get_logger
+from tractor._addr import TCPAddress
+from tractor.ipc._transport import MsgpackTransport
+
+
+log = get_logger(__name__)
+
+
+# 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

@@ -0,0 +1,504 @@
+# 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
+)
+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,
+    types as msgtypes,
+    pretty_struct,
+)
+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[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 `trio` streaming transport prot's addrs for both
+        the local and remote sides as a pair.
+
+        '''
+        ...
+
+    # 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 = 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))
+            try:
+                return await self.stream.send_all(size + bytes_data)
+            except (
+                trio.BrokenResourceError,
+            ) as trans_err:
+                loglevel = 'transport'
+                match trans_err:
+                    case trio.BrokenResourceError() if (
+                        '[Errno 32] Broken pipe' in trans_err.args[0]
+                        # ^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.
+                    ):
+                        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
+
+                    # unless the disconnect condition falls under "a
+                    # normal operation breakage" we usualy console warn
+                    # about it.
+                    case _:
+                        log.exception(
+                            'Transport layer failed for {self.transport!r} ?\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' |_task: {self._task}\n'
+            f'\n'
+            f' |_peers: 2\n'
+            f'   laddr: {self._laddr}\n'
+            f'   raddr: {self._raddr}\n'
+            f')>\n'
+        )
+
+    __repr__ = __str__ = pformat

tractor/ipc/_types.py

@@ -0,0 +1,99 @@
+# 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 typing import Type
+
+import trio
+import socket
+
+from tractor._addr import Address
+from tractor.ipc._transport import (
+    MsgTransportKey,
+    MsgTransport
+)
+from tractor.ipc._tcp import MsgpackTCPStream
+from tractor.ipc._uds import MsgpackUDSStream
+
+
+# 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]] = {
+    cls.key(): cls
+    for cls in _msg_transports
+}
+
+# convert an Address wrapper to its corresponding transport type
+_addr_to_transport: dict[Type[Address], Type[MsgTransport]] = {
+    cls.address_type: cls
+    for cls in _msg_transports
+}
+
+
+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

@@ -0,0 +1,216 @@
+# 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 pathlib import Path
+import os
+from socket import (
+    # socket,
+    AF_UNIX,
+    SOCK_STREAM,
+    SO_PASSCRED,
+    SO_PEERCRED,
+    SOL_SOCKET,
+)
+import struct
+
+import trio
+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._addr import (
+    UDSAddress,
+    unwrap_sockpath,
+)
+from tractor.ipc._transport import MsgpackTransport
+
+
+log = get_logger(__name__)
+
+
+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.
+        try:
+            stream = await open_unix_socket_w_passcred(
+                str(sockpath),
+                **kwargs
+            )
+        except (
+            FileNotFoundError,
+        ) as fdne:
+            raise ConnectionError(
+                f'Bad UDS socket-filepath-as-address ??\n'
+                f'{addr}\n'
+                f' |_sockpath: {sockpath}\n'
+            ) from fdne
+
+        stream = MsgpackUDSStream(
+            stream,
+            prefix_size=prefix_size,
+            codec=codec
+        )
+        stream._raddr = addr
+        return 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

@@ -92,7 +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)
@@ -285,7 +285,7 @@ def get_logger(
         # 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.py in header
+        #   in msg output: i.e. tractor.tractor.ipc._chan.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

tractor/msg/types.py

@@ -31,6 +31,7 @@ from typing import (
     Type,
     TypeVar,
     TypeAlias,
+    # TYPE_CHECKING,
     Union,
 )
 
@@ -47,6 +48,7 @@ from tractor.msg import (
     pretty_struct,
 )
 from tractor.log import get_logger
+from tractor._addr import UnwrappedAddress
 
 
 log = get_logger('tractor.msgspec')
@@ -141,9 +143,16 @@ class Aid(
     '''
     name: str
     uuid: str
-    # TODO: use built-in support for UUIDs?
-    # -[ ] `uuid.UUID` which has multi-protocol support
+    pid: int|None = None
+
+    # TODO? can/should we extend this field set?
+    # -[ ] 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?
 
 
 class SpawnSpec(
@@ -167,8 +176,8 @@ class SpawnSpec(
 
     # TODO: not just sockaddr pairs?
     # -[ ] abstract into a `TransportAddr` type?
-    reg_addrs: list[tuple[str, int]]
-    bind_addrs: list[tuple[str, int]]
+    reg_addrs: list[UnwrappedAddress]
+    bind_addrs: list[UnwrappedAddress]|None
 
 
 # TODO: caps based RPC support in the payload?

uv.lock

@@ -11,6 +11,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/89/aa/ab0f7891a01eeb2d2e338ae8fecbe57fcebea1a24dbb64d45801bfab481d/attrs-24.3.0-py3-none-any.whl", hash = "sha256:ac96cd038792094f438ad1f6ff80837353805ac950cd2aa0e0625ef19850c308", size = 63397 },
 ]
 
+[[package]]
+name = "bidict"
+version = "0.23.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/9a/6e/026678aa5a830e07cd9498a05d3e7e650a4f56a42f267a53d22bcda1bdc9/bidict-0.23.1.tar.gz", hash = "sha256:03069d763bc387bbd20e7d49914e75fc4132a41937fa3405417e1a5a2d006d71", size = 29093 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/99/37/e8730c3587a65eb5645d4aba2d27aae48e8003614d6aaf15dda67f702f1f/bidict-0.23.1-py3-none-any.whl", hash = "sha256:5dae8d4d79b552a71cbabc7deb25dfe8ce710b17ff41711e13010ead2abfc3e5", size = 32764 },
+]
+
 [[package]]
 name = "cffi"
 version = "1.17.1"
@@ -20,10 +29,38 @@ dependencies = [
 ]
 sdist = { url = "https://files.pythonhosted.org/packages/fc/97/c783634659c2920c3fc70419e3af40972dbaf758daa229a7d6ea6135c90d/cffi-1.17.1.tar.gz", hash = "sha256:1c39c6016c32bc48dd54561950ebd6836e1670f2ae46128f67cf49e789c52824", size = 516621 }
 wheels = [
+    { url = "https://files.pythonhosted.org/packages/6b/f4/927e3a8899e52a27fa57a48607ff7dc91a9ebe97399b357b85a0c7892e00/cffi-1.17.1-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:a45e3c6913c5b87b3ff120dcdc03f6131fa0065027d0ed7ee6190736a74cd401", size = 182264 },
+    { url = "https://files.pythonhosted.org/packages/6c/f5/6c3a8efe5f503175aaddcbea6ad0d2c96dad6f5abb205750d1b3df44ef29/cffi-1.17.1-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:30c5e0cb5ae493c04c8b42916e52ca38079f1b235c2f8ae5f4527b963c401caf", size = 178651 },
+    { url = "https://files.pythonhosted.org/packages/94/dd/a3f0118e688d1b1a57553da23b16bdade96d2f9bcda4d32e7d2838047ff7/cffi-1.17.1-cp311-cp311-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:f75c7ab1f9e4aca5414ed4d8e5c0e303a34f4421f8a0d47a4d019ceff0ab6af4", size = 445259 },
+    { url = "https://files.pythonhosted.org/packages/2e/ea/70ce63780f096e16ce8588efe039d3c4f91deb1dc01e9c73a287939c79a6/cffi-1.17.1-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a1ed2dd2972641495a3ec98445e09766f077aee98a1c896dcb4ad0d303628e41", size = 469200 },
+    { url = "https://files.pythonhosted.org/packages/1c/a0/a4fa9f4f781bda074c3ddd57a572b060fa0df7655d2a4247bbe277200146/cffi-1.17.1-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:46bf43160c1a35f7ec506d254e5c890f3c03648a4dbac12d624e4490a7046cd1", size = 477235 },
+    { url = "https://files.pythonhosted.org/packages/62/12/ce8710b5b8affbcdd5c6e367217c242524ad17a02fe5beec3ee339f69f85/cffi-1.17.1-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a24ed04c8ffd54b0729c07cee15a81d964e6fee0e3d4d342a27b020d22959dc6", size = 459721 },
+    { url = "https://files.pythonhosted.org/packages/ff/6b/d45873c5e0242196f042d555526f92aa9e0c32355a1be1ff8c27f077fd37/cffi-1.17.1-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:610faea79c43e44c71e1ec53a554553fa22321b65fae24889706c0a84d4ad86d", size = 467242 },
+    { url = "https://files.pythonhosted.org/packages/1a/52/d9a0e523a572fbccf2955f5abe883cfa8bcc570d7faeee06336fbd50c9fc/cffi-1.17.1-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:a9b15d491f3ad5d692e11f6b71f7857e7835eb677955c00cc0aefcd0669adaf6", size = 477999 },
+    { url = "https://files.pythonhosted.org/packages/44/74/f2a2460684a1a2d00ca799ad880d54652841a780c4c97b87754f660c7603/cffi-1.17.1-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:de2ea4b5833625383e464549fec1bc395c1bdeeb5f25c4a3a82b5a8c756ec22f", size = 454242 },
+    { url = "https://files.pythonhosted.org/packages/f8/4a/34599cac7dfcd888ff54e801afe06a19c17787dfd94495ab0c8d35fe99fb/cffi-1.17.1-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:fc48c783f9c87e60831201f2cce7f3b2e4846bf4d8728eabe54d60700b318a0b", size = 478604 },
     { url = "https://files.pythonhosted.org/packages/34/33/e1b8a1ba29025adbdcda5fb3a36f94c03d771c1b7b12f726ff7fef2ebe36/cffi-1.17.1-cp311-cp311-win32.whl", hash = "sha256:85a950a4ac9c359340d5963966e3e0a94a676bd6245a4b55bc43949eee26a655", size = 171727 },
     { url = "https://files.pythonhosted.org/packages/3d/97/50228be003bb2802627d28ec0627837ac0bf35c90cf769812056f235b2d1/cffi-1.17.1-cp311-cp311-win_amd64.whl", hash = "sha256:caaf0640ef5f5517f49bc275eca1406b0ffa6aa184892812030f04c2abf589a0", size = 181400 },
+    { url = "https://files.pythonhosted.org/packages/5a/84/e94227139ee5fb4d600a7a4927f322e1d4aea6fdc50bd3fca8493caba23f/cffi-1.17.1-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:805b4371bf7197c329fcb3ead37e710d1bca9da5d583f5073b799d5c5bd1eee4", size = 183178 },
+    { url = "https://files.pythonhosted.org/packages/da/ee/fb72c2b48656111c4ef27f0f91da355e130a923473bf5ee75c5643d00cca/cffi-1.17.1-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:733e99bc2df47476e3848417c5a4540522f234dfd4ef3ab7fafdf555b082ec0c", size = 178840 },
+    { url = "https://files.pythonhosted.org/packages/cc/b6/db007700f67d151abadf508cbfd6a1884f57eab90b1bb985c4c8c02b0f28/cffi-1.17.1-cp312-cp312-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1257bdabf294dceb59f5e70c64a3e2f462c30c7ad68092d01bbbfb1c16b1ba36", size = 454803 },
+    { url = "https://files.pythonhosted.org/packages/1a/df/f8d151540d8c200eb1c6fba8cd0dfd40904f1b0682ea705c36e6c2e97ab3/cffi-1.17.1-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:da95af8214998d77a98cc14e3a3bd00aa191526343078b530ceb0bd710fb48a5", size = 478850 },
+    { url = "https://files.pythonhosted.org/packages/28/c0/b31116332a547fd2677ae5b78a2ef662dfc8023d67f41b2a83f7c2aa78b1/cffi-1.17.1-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:d63afe322132c194cf832bfec0dc69a99fb9bb6bbd550f161a49e9e855cc78ff", size = 485729 },
+    { url = "https://files.pythonhosted.org/packages/91/2b/9a1ddfa5c7f13cab007a2c9cc295b70fbbda7cb10a286aa6810338e60ea1/cffi-1.17.1-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f79fc4fc25f1c8698ff97788206bb3c2598949bfe0fef03d299eb1b5356ada99", size = 471256 },
+    { url = "https://files.pythonhosted.org/packages/b2/d5/da47df7004cb17e4955df6a43d14b3b4ae77737dff8bf7f8f333196717bf/cffi-1.17.1-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b62ce867176a75d03a665bad002af8e6d54644fad99a3c70905c543130e39d93", size = 479424 },
+    { url = "https://files.pythonhosted.org/packages/0b/ac/2a28bcf513e93a219c8a4e8e125534f4f6db03e3179ba1c45e949b76212c/cffi-1.17.1-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:386c8bf53c502fff58903061338ce4f4950cbdcb23e2902d86c0f722b786bbe3", size = 484568 },
+    { url = "https://files.pythonhosted.org/packages/d4/38/ca8a4f639065f14ae0f1d9751e70447a261f1a30fa7547a828ae08142465/cffi-1.17.1-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:4ceb10419a9adf4460ea14cfd6bc43d08701f0835e979bf821052f1805850fe8", size = 488736 },
     { url = "https://files.pythonhosted.org/packages/86/c5/28b2d6f799ec0bdecf44dced2ec5ed43e0eb63097b0f58c293583b406582/cffi-1.17.1-cp312-cp312-win32.whl", hash = "sha256:a08d7e755f8ed21095a310a693525137cfe756ce62d066e53f502a83dc550f65", size = 172448 },
     { url = "https://files.pythonhosted.org/packages/50/b9/db34c4755a7bd1cb2d1603ac3863f22bcecbd1ba29e5ee841a4bc510b294/cffi-1.17.1-cp312-cp312-win_amd64.whl", hash = "sha256:51392eae71afec0d0c8fb1a53b204dbb3bcabcb3c9b807eedf3e1e6ccf2de903", size = 181976 },
+    { url = "https://files.pythonhosted.org/packages/8d/f8/dd6c246b148639254dad4d6803eb6a54e8c85c6e11ec9df2cffa87571dbe/cffi-1.17.1-cp313-cp313-macosx_10_13_x86_64.whl", hash = "sha256:f3a2b4222ce6b60e2e8b337bb9596923045681d71e5a082783484d845390938e", size = 182989 },
+    { url = "https://files.pythonhosted.org/packages/8b/f1/672d303ddf17c24fc83afd712316fda78dc6fce1cd53011b839483e1ecc8/cffi-1.17.1-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:0984a4925a435b1da406122d4d7968dd861c1385afe3b45ba82b750f229811e2", size = 178802 },
+    { url = "https://files.pythonhosted.org/packages/0e/2d/eab2e858a91fdff70533cab61dcff4a1f55ec60425832ddfdc9cd36bc8af/cffi-1.17.1-cp313-cp313-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:d01b12eeeb4427d3110de311e1774046ad344f5b1a7403101878976ecd7a10f3", size = 454792 },
+    { url = "https://files.pythonhosted.org/packages/75/b2/fbaec7c4455c604e29388d55599b99ebcc250a60050610fadde58932b7ee/cffi-1.17.1-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:706510fe141c86a69c8ddc029c7910003a17353970cff3b904ff0686a5927683", size = 478893 },
+    { url = "https://files.pythonhosted.org/packages/4f/b7/6e4a2162178bf1935c336d4da8a9352cccab4d3a5d7914065490f08c0690/cffi-1.17.1-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:de55b766c7aa2e2a3092c51e0483d700341182f08e67c63630d5b6f200bb28e5", size = 485810 },
+    { url = "https://files.pythonhosted.org/packages/c7/8a/1d0e4a9c26e54746dc08c2c6c037889124d4f59dffd853a659fa545f1b40/cffi-1.17.1-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:c59d6e989d07460165cc5ad3c61f9fd8f1b4796eacbd81cee78957842b834af4", size = 471200 },
+    { url = "https://files.pythonhosted.org/packages/26/9f/1aab65a6c0db35f43c4d1b4f580e8df53914310afc10ae0397d29d697af4/cffi-1.17.1-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:dd398dbc6773384a17fe0d3e7eeb8d1a21c2200473ee6806bb5e6a8e62bb73dd", size = 479447 },
+    { url = "https://files.pythonhosted.org/packages/5f/e4/fb8b3dd8dc0e98edf1135ff067ae070bb32ef9d509d6cb0f538cd6f7483f/cffi-1.17.1-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:3edc8d958eb099c634dace3c7e16560ae474aa3803a5df240542b305d14e14ed", size = 484358 },
+    { url = "https://files.pythonhosted.org/packages/f1/47/d7145bf2dc04684935d57d67dff9d6d795b2ba2796806bb109864be3a151/cffi-1.17.1-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:72e72408cad3d5419375fc87d289076ee319835bdfa2caad331e377589aebba9", size = 488469 },
     { url = "https://files.pythonhosted.org/packages/bf/ee/f94057fa6426481d663b88637a9a10e859e492c73d0384514a17d78ee205/cffi-1.17.1-cp313-cp313-win32.whl", hash = "sha256:e03eab0a8677fa80d646b5ddece1cbeaf556c313dcfac435ba11f107ba117b5d", size = 172475 },
     { url = "https://files.pythonhosted.org/packages/7c/fc/6a8cb64e5f0324877d503c854da15d76c1e50eb722e320b15345c4d0c6de/cffi-1.17.1-cp313-cp313-win_amd64.whl", hash = "sha256:f6a16c31041f09ead72d69f583767292f750d24913dadacf5756b966aacb3f1a", size = 182009 },
 ]
@@ -220,6 +257,21 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/e4/ea/d836f008d33151c7a1f62caf3d8dd782e4d15f6a43897f64480c2b8de2ad/prompt_toolkit-3.0.50-py3-none-any.whl", hash = "sha256:9b6427eb19e479d98acff65196a307c555eb567989e6d88ebbb1b509d9779198", size = 387816 },
 ]
 
+[[package]]
+name = "psutil"
+version = "7.0.0"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/2a/80/336820c1ad9286a4ded7e845b2eccfcb27851ab8ac6abece774a6ff4d3de/psutil-7.0.0.tar.gz", hash = "sha256:7be9c3eba38beccb6495ea33afd982a44074b78f28c434a1f51cc07fd315c456", size = 497003 }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/ed/e6/2d26234410f8b8abdbf891c9da62bee396583f713fb9f3325a4760875d22/psutil-7.0.0-cp36-abi3-macosx_10_9_x86_64.whl", hash = "sha256:101d71dc322e3cffd7cea0650b09b3d08b8e7c4109dd6809fe452dfd00e58b25", size = 238051 },
+    { url = "https://files.pythonhosted.org/packages/04/8b/30f930733afe425e3cbfc0e1468a30a18942350c1a8816acfade80c005c4/psutil-7.0.0-cp36-abi3-macosx_11_0_arm64.whl", hash = "sha256:39db632f6bb862eeccf56660871433e111b6ea58f2caea825571951d4b6aa3da", size = 239535 },
+    { url = "https://files.pythonhosted.org/packages/2a/ed/d362e84620dd22876b55389248e522338ed1bf134a5edd3b8231d7207f6d/psutil-7.0.0-cp36-abi3-manylinux_2_12_i686.manylinux2010_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:1fcee592b4c6f146991ca55919ea3d1f8926497a713ed7faaf8225e174581e91", size = 275004 },
+    { url = "https://files.pythonhosted.org/packages/bf/b9/b0eb3f3cbcb734d930fdf839431606844a825b23eaf9a6ab371edac8162c/psutil-7.0.0-cp36-abi3-manylinux_2_12_x86_64.manylinux2010_x86_64.manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:4b1388a4f6875d7e2aff5c4ca1cc16c545ed41dd8bb596cefea80111db353a34", size = 277986 },
+    { url = "https://files.pythonhosted.org/packages/eb/a2/709e0fe2f093556c17fbafda93ac032257242cabcc7ff3369e2cb76a97aa/psutil-7.0.0-cp36-abi3-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:a5f098451abc2828f7dc6b58d44b532b22f2088f4999a937557b603ce72b1993", size = 279544 },
+    { url = "https://files.pythonhosted.org/packages/50/e6/eecf58810b9d12e6427369784efe814a1eec0f492084ce8eb8f4d89d6d61/psutil-7.0.0-cp37-abi3-win32.whl", hash = "sha256:ba3fcef7523064a6c9da440fc4d6bd07da93ac726b5733c29027d7dc95b39d99", size = 241053 },
+    { url = "https://files.pythonhosted.org/packages/50/1b/6921afe68c74868b4c9fa424dad3be35b095e16687989ebbb50ce4fceb7c/psutil-7.0.0-cp37-abi3-win_amd64.whl", hash = "sha256:4cf3d4eb1aa9b348dec30105c55cd9b7d4629285735a102beb4441e38db90553", size = 244885 },
+]
+
 [[package]]
 name = "ptyprocess"
 version = "0.7.0"
@@ -321,6 +373,8 @@ name = "tractor"
 version = "0.1.0a6.dev0"
 source = { editable = "." }
 dependencies = [
+    { name = "bidict" },
+    { name = "cffi" },
     { name = "colorlog" },
     { name = "msgspec" },
     { name = "pdbp" },
@@ -334,6 +388,7 @@ dev = [
     { name = "greenback" },
     { name = "pexpect" },
     { name = "prompt-toolkit" },
+    { name = "psutil" },
     { name = "pyperclip" },
     { name = "pytest" },
     { name = "stackscope" },
@@ -342,6 +397,8 @@ dev = [
 
 [package.metadata]
 requires-dist = [
+    { name = "bidict", specifier = ">=0.23.1" },
+    { name = "cffi", specifier = ">=1.17.1" },
     { name = "colorlog", specifier = ">=6.8.2,<7" },
     { name = "msgspec", specifier = ">=0.19.0" },
     { name = "pdbp", specifier = ">=1.6,<2" },
@@ -355,6 +412,7 @@ dev = [
     { name = "greenback", specifier = ">=1.2.1,<2" },
     { name = "pexpect", specifier = ">=4.9.0,<5" },
     { name = "prompt-toolkit", specifier = ">=3.0.50" },
+    { name = "psutil", specifier = ">=7.0.0" },
     { name = "pyperclip", specifier = ">=1.9.0" },
     { name = "pytest", specifier = ">=8.3.5" },
     { name = "stackscope", specifier = ">=0.2.2,<0.3" },