Allow ledger passes to ignore (symcache) unknown fqmes

For example in the paper-eng, if you have a backend that doesn't fully
support a symcache (yet) it's handy to be able to ignore processing
other paper-eng txns when all you care about at the moment is the
simulated symbol.

NOTE, that currently this will still result in a key-error when you load
more then one mkt with the paper engine (for which the backend does not
have the symcache implemented) since no fqme ad-hoc query was made for
the 2nd symbol (and i'm not sure we should support that kinda hackery
over just encouraging the sym-cache being added?). Def needs a little
more thought depending on how many backends are never going to be able
to (easily) support caching..

piker/accounting/_pos.py

@@ -30,7 +30,8 @@ from types import ModuleType
 from typing import (
     Any,
     Iterator,
-    Generator
+    Generator,
+    TYPE_CHECKING,
 )
 
 import pendulum
@@ -59,8 +60,10 @@ from ..clearing._messages import (
     BrokerdPosition,
 )
 from piker.types import Struct
-from piker.data._symcache import SymbologyCache
-from ..log import get_logger
+from piker.log import get_logger
+
+if TYPE_CHECKING:
+    from piker.data._symcache import SymbologyCache
 
 log = get_logger(__name__)
 
@@ -493,6 +496,17 @@ class Account(Struct):
 
         _mktmap_table: dict[str, MktPair] | None = None,
 
+        only_require: list[str]|True = True,
+        # ^list of fqmes that are "required" to be processed from
+        # this ledger pass; we often don't care about others and
+        # definitely shouldn't always error in such cases.
+        # (eg. broker backend loaded that doesn't yet supsport the
+        # symcache but also, inside the paper engine we don't ad-hoc
+        # request `get_mkt_info()` for every symbol in the ledger,
+        # only the one for which we're simulating against).
+        # TODO, not sure if there's a better soln for this, ideally
+        # all backends get symcache support afap i guess..
+
     ) -> dict[str, Position]:
         '''
         Update the internal `.pps[str, Position]` table from input
@@ -535,11 +549,32 @@ class Account(Struct):
                 if _mktmap_table is None:
                     raise
 
+                required: bool = (
+                    only_require is True
+                    or (
+                        only_require is not True
+                        and
+                        fqme in only_require
+                    )
+                )
                 # XXX: caller is allowed to provide a fallback
                 # mktmap table for the case where a new position is
                 # being added and the preloaded symcache didn't
                 # have this entry prior (eg. with frickin IB..)
-                mkt = _mktmap_table[fqme]
+                if (
+                    not (mkt := _mktmap_table.get(fqme))
+                    and
+                    required
+                ):
+                    raise
+
+                elif not required:
+                    continue
+
+                else:
+                    # should be an entry retreived somewhere
+                    assert mkt
+
 
             if not (pos := pps.get(bs_mktid)):
 
@@ -656,7 +691,7 @@ class Account(Struct):
     def write_config(self) -> None:
         '''
         Write the current account state to the user's account TOML file, normally
-        something like ``pps.toml``.
+        something like `pps.toml`.
 
         '''
         # TODO: show diff output?

piker/brokers/_daemon.py

@@ -23,6 +23,7 @@ from __future__ import annotations
 from contextlib import (
     asynccontextmanager as acm,
 )
+from functools import partial
 from types import ModuleType
 from typing import (
     TYPE_CHECKING,
@@ -190,14 +191,17 @@ def broker_init(
 
 
 async def spawn_brokerd(
-
     brokername: str,
     loglevel: str | None = None,
 
     **tractor_kwargs,
 
 ) -> bool:
+    '''
+    Spawn a `brokerd.<backendname>` subactor service daemon
+    using `pikerd`'s service mngr.
 
+    '''
     from piker.service._util import log  # use service mngr log
     log.info(f'Spawning {brokername} broker daemon')
 
@@ -217,27 +221,35 @@ async def spawn_brokerd(
 
     # ask `pikerd` to spawn a new sub-actor and manage it under its
     # actor nursery
-    from piker.service import Services
-
+    from piker.service import (
+        get_service_mngr,
+        ServiceMngr,
+    )
     dname: str = tractor_kwargs.pop('name')  # f'brokerd.{brokername}'
-    portal = await Services.actor_n.start_actor(
-        dname,
-        enable_modules=_data_mods + tractor_kwargs.pop('enable_modules'),
-        debug_mode=Services.debug_mode,
+    mngr: ServiceMngr = get_service_mngr()
+    ctx: tractor.Context = await mngr.start_service(
+        daemon_name=dname,
+        ctx_ep=partial(
+            # signature of target root-task endpoint
+            daemon_fixture_ep,
+
+            # passed to daemon_fixture_ep(**kwargs)
+            brokername=brokername,
+            loglevel=loglevel,
+        ),
+        debug_mode=mngr.debug_mode,
+        loglevel=loglevel,
+        enable_modules=(
+            _data_mods
+            +
+            tractor_kwargs.pop('enable_modules')
+        ),
         **tractor_kwargs
     )
-
-    # NOTE: the service mngr expects an already spawned actor + its
-    # portal ref in order to do non-blocking setup of brokerd
-    # service nursery.
-    await Services.start_service_task(
-        dname,
-        portal,
-
-        # signature of target root-task endpoint
-        daemon_fixture_ep,
-        brokername=brokername,
-        loglevel=loglevel,
+    assert (
+        not ctx.cancel_called
+        and ctx.portal  # parent side
+        and dname in ctx.chan.uid  # subactor is named as desired
     )
     return True
 
@@ -262,8 +274,7 @@ async def maybe_spawn_brokerd(
     from piker.service import maybe_spawn_daemon
 
     async with maybe_spawn_daemon(
-
-        f'brokerd.{brokername}',
+        service_name=f'brokerd.{brokername}',
         service_task_target=spawn_brokerd,
         spawn_args={
             'brokername': brokername,

piker/brokers/binance/api.py

@@ -567,6 +567,7 @@ class Client:
     ) -> str:
         return {
             'USDTM': 'usdtm_futes',
+            'SPOT': 'spot',
             # 'COINM': 'coin_futes',
             # ^-TODO-^ bc someone might want it..?
         }[pair.venue]

piker/brokers/binance/venues.py

@@ -181,7 +181,6 @@ class FutesPair(Pair):
     quoteAsset: str  # 'USDT',
     quotePrecision: int  # 8,
     requiredMarginPercent: float  # '5.0000',
-    settlePlan: int  # 0,
     timeInForce: list[str]  # ['GTC', 'IOC', 'FOK', 'GTX'],
     triggerProtect: float  # '0.0500',
     underlyingSubType: list[str]  # ['PoW'],

piker/brokers/kucoin.py

@@ -111,6 +111,10 @@ class KucoinMktPair(Struct, frozen=True):
     quoteMaxSize: float
     quoteMinSize: float
     symbol: str  # our bs_mktid, kucoin's internal id
+    feeCategory: int
+    makerFeeCoefficient: float
+    takerFeeCoefficient: float
+    st: bool
 
 
 class AccountTrade(Struct, frozen=True):
@@ -593,7 +597,7 @@ async def get_client() -> AsyncGenerator[Client, None]:
     '''
     async with (
         httpx.AsyncClient(
-            base_url=f'https://api.kucoin.com/api',
+            base_url='https://api.kucoin.com/api',
         ) as trio_client,
     ):
         client = Client(httpx_client=trio_client)
@@ -637,7 +641,7 @@ async def open_ping_task(
                 await trio.sleep((ping_interval - 1000) / 1000)
                 await ws.send_msg({'id': connect_id, 'type': 'ping'})
 
-        log.info('Starting ping task for kucoin ws connection')
+        log.warning('Starting ping task for kucoin ws connection')
         n.start_soon(ping_server)
 
         yield
@@ -649,9 +653,14 @@ async def open_ping_task(
 async def get_mkt_info(
     fqme: str,
 
-) -> tuple[MktPair, KucoinMktPair]:
+) -> tuple[
+    MktPair,
+    KucoinMktPair,
+]:
     '''
-    Query for and return a `MktPair` and `KucoinMktPair`.
+    Query for and return both a `piker.accounting.MktPair` and
+    `KucoinMktPair` from provided `fqme: str`
+    (fully-qualified-market-endpoint).
 
     '''
     async with open_cached_client('kucoin') as client:
@@ -726,6 +735,8 @@ async def stream_quotes(
 
         log.info(f'Starting up quote stream(s) for {symbols}')
         for sym_str in symbols:
+            mkt: MktPair
+            pair: KucoinMktPair
             mkt, pair = await get_mkt_info(sym_str)
             init_msgs.append(
                 FeedInit(mkt_info=mkt)
@@ -733,7 +744,11 @@ async def stream_quotes(
 
         ws: NoBsWs
         token, ping_interval = await client._get_ws_token()
-        connect_id = str(uuid4())
+        log.info('API reported ping_interval: {ping_interval}\n')
+
+        connect_id: str = str(uuid4())
+        typ: str
+        quote: dict
         async with (
             open_autorecon_ws(
                 (
@@ -747,20 +762,37 @@ async def stream_quotes(
                 ),
             ) as ws,
             open_ping_task(ws, ping_interval, connect_id),
-            aclosing(stream_messages(ws, sym_str)) as msg_gen,
+            aclosing(
+                iter_normed_quotes(
+                    ws, sym_str
+                )
+            ) as iter_quotes,
         ):
-            typ, quote = await anext(msg_gen)
+            typ, quote = await anext(iter_quotes)
 
-            while typ != 'trade':
-                # take care to not unblock here until we get a real
-                # trade quote
-                typ, quote = await anext(msg_gen)
+            # take care to not unblock here until we get a real
+            # trade quote?
+            # ^TODO, remove this right?
+            # -[ ] what often blocks chart boot/new-feed switching
+            #   since we'ere waiting for a live quote instead of just
+            #   loading history afap..
+            #  |_ XXX, not sure if we require a bit of rework to core
+            #    feed init logic or if backends justg gotta be
+            #    changed up.. feel like there was some causality
+            #    dilema prolly only seen with IB too..
+            # while typ != 'trade':
+            #     typ, quote = await anext(iter_quotes)
 
             task_status.started((init_msgs, quote))
             feed_is_live.set()
 
-            async for typ, msg in msg_gen:
-                await send_chan.send({sym_str: msg})
+            # XXX NOTE, DO NOT include the `.<backend>` suffix!
+            # OW the sampling loop will not broadcast correctly..
+            # since `bus._subscribers.setdefault(bs_fqme, set())`
+            # is used inside `.data.open_feed_bus()` !!!
+            topic: str = mkt.bs_fqme
+            async for typ, quote in iter_quotes:
+                await send_chan.send({topic: quote})
 
 
 @acm
@@ -815,7 +847,7 @@ async def subscribe(
             )
 
 
-async def stream_messages(
+async def iter_normed_quotes(
     ws: NoBsWs,
     sym: str,
 
@@ -846,6 +878,9 @@ async def stream_messages(
 
                 yield 'trade', {
                     'symbol': sym,
+                    # TODO, is 'last' even used elsewhere/a-good
+                    # semantic? can't we just read the ticks with our
+                    # .data.ticktools.frame_ticks()`/
                     'last': trade_data.price,
                     'brokerd_ts': last_trade_ts,
                     'ticks': [
@@ -938,7 +973,7 @@ async def open_history_client(
             if end_dt is None:
                 inow = round(time.time())
 
-                print(
+                log.debug(
                     f'difference in time between load and processing'
                     f'{inow - times[-1]}'
                 )

piker/clearing/_ems.py

@@ -653,7 +653,11 @@ class Router(Struct):
             flume = feed.flumes[fqme]
             first_quote: dict = flume.first_quote
             book: DarkBook = self.get_dark_book(broker)
-            book.lasts[fqme]: float = float(first_quote['last'])
+
+            if not (last := first_quote.get('last')):
+                last: float = flume.rt_shm.array[-1]['close']
+
+            book.lasts[fqme]: float = float(last)
 
             async with self.maybe_open_brokerd_dialog(
                 brokermod=brokermod,
@@ -716,7 +720,7 @@ class Router(Struct):
             subs = self.subscribers[sub_key]
 
         sent_some: bool = False
-        for client_stream in subs:
+        for client_stream in subs.copy():
             try:
                 await client_stream.send(msg)
                 sent_some = True
@@ -1010,10 +1014,14 @@ async def translate_and_relay_brokerd_events(
                 status_msg.brokerd_msg = msg
                 status_msg.src = msg.broker_details['name']
 
-                await router.client_broadcast(
-                    status_msg.req.symbol,
-                    status_msg,
-                )
+                if not status_msg.req:
+                    # likely some order change state?
+                    await tractor.pause()
+                else:
+                    await router.client_broadcast(
+                        status_msg.req.symbol,
+                        status_msg,
+                    )
 
                 if status == 'closed':
                     log.info(f'Execution for {oid} is complete!')

piker/clearing/_paper_engine.py

@@ -653,6 +653,7 @@ async def open_trade_dialog(
                 # in) use manually constructed table from calling
                 # the `.get_mkt_info()` provider EP above.
                 _mktmap_table=mkt_by_fqme,
+                only_require=list(mkt_by_fqme),
             )
 
             pp_msgs: list[BrokerdPosition] = []

piker/cli/__init__.py

@@ -335,7 +335,7 @@ def services(config, tl, ports):
                 name='service_query',
                 loglevel=config['loglevel'] if tl else None,
             ),
-            tractor.get_arbiter(
+            tractor.get_registry(
                 host=host,
                 port=ports[0]
             ) as portal

piker/data/_sampling.py

@@ -25,6 +25,7 @@ from collections import (
     defaultdict,
 )
 from contextlib import asynccontextmanager as acm
+from functools import partial
 import time
 from typing import (
     Any,
@@ -42,7 +43,7 @@ from tractor.trionics import (
     maybe_open_nursery,
 )
 import trio
-from trio_typing import TaskStatus
+from trio import TaskStatus
 
 from .ticktools import (
     frame_ticks,
@@ -70,6 +71,7 @@ if TYPE_CHECKING:
 _default_delay_s: float = 1.0
 
 
+# TODO: use new `tractor.singleton_acm` API for this!
 class Sampler:
     '''
     Global sampling engine registry.
@@ -79,9 +81,9 @@ class Sampler:
 
     This non-instantiated type is meant to be a singleton within
     a `samplerd` actor-service spawned once by the user wishing to
-    time-step-sample (real-time) quote feeds, see
-    ``.service.maybe_open_samplerd()`` and the below
-    ``register_with_sampler()``.
+    time-step-sample a (real-time) quote feeds, see
+    `.service.maybe_open_samplerd()` and the below
+    `register_with_sampler()`.
 
     '''
     service_nursery: None | trio.Nursery = None
@@ -375,7 +377,10 @@ async def register_with_sampler(
                 assert Sampler.ohlcv_shms
 
             # unblock caller
-            await ctx.started(set(Sampler.ohlcv_shms.keys()))
+            await ctx.started(
+                # XXX bc msgpack only allows one array type!
+                list(Sampler.ohlcv_shms.keys())
+            )
 
             if open_index_stream:
                 try:
@@ -419,7 +424,6 @@ async def register_with_sampler(
 
 
 async def spawn_samplerd(
-
     loglevel: str | None = None,
     **extra_tractor_kwargs
 
@@ -429,7 +433,10 @@ async def spawn_samplerd(
     update and increment count write and stream broadcasting.
 
     '''
-    from piker.service import Services
+    from piker.service import (
+        get_service_mngr,
+        ServiceMngr,
+    )
 
     dname = 'samplerd'
     log.info(f'Spawning `{dname}`')
@@ -437,26 +444,33 @@ async def spawn_samplerd(
     # singleton lock creation of ``samplerd`` since we only ever want
     # one daemon per ``pikerd`` proc tree.
     # TODO: make this built-into the service api?
-    async with Services.locks[dname + '_singleton']:
+    mngr: ServiceMngr = get_service_mngr()
+    already_started: bool = dname in mngr.service_tasks
 
-        if dname not in Services.service_tasks:
-
-            portal = await Services.actor_n.start_actor(
-                dname,
-                enable_modules=[
-                    'piker.data._sampling',
-                ],
-                loglevel=loglevel,
-                debug_mode=Services.debug_mode,  # set by pikerd flag
-                **extra_tractor_kwargs
-            )
-
-            await Services.start_service_task(
-                dname,
-                portal,
+    async with mngr._locks[dname + '_singleton']:
+        ctx: Context = await mngr.start_service(
+            daemon_name=dname,
+            ctx_ep=partial(
                 register_with_sampler,
                 period_s=1,
                 sub_for_broadcasts=False,
+            ),
+            debug_mode=mngr.debug_mode,  # set by pikerd flag
+
+            # proxy-through to tractor
+            enable_modules=[
+                'piker.data._sampling',
+            ],
+            loglevel=loglevel,
+            **extra_tractor_kwargs
+        )
+        if not already_started:
+            assert (
+                ctx
+                and
+                ctx.portal
+                and
+                not ctx.cancel_called
             )
             return True
 
@@ -889,6 +903,7 @@ async def uniform_rate_send(
             # to consumers which crash or lose network connection.
             # I.e. we **DO NOT** want to crash and propagate up to
             # ``pikerd`` these kinds of errors!
+            trio.EndOfChannel,
             trio.ClosedResourceError,
             trio.BrokenResourceError,
             ConnectionResetError,

piker/data/_web_bs.py

@@ -273,7 +273,7 @@ async def _reconnect_forever(
                 nobsws._connected.set()
                 await trio.sleep_forever()
         except HandshakeError:
-            log.exception(f'Retrying connection')
+            log.exception('Retrying connection')
 
         # ws & nursery block ends
 
@@ -359,8 +359,8 @@ async def open_autorecon_ws(
 
 
 '''
-JSONRPC response-request style machinery for transparent multiplexing of msgs
-over a NoBsWs.
+JSONRPC response-request style machinery for transparent multiplexing
+of msgs over a NoBsWs.
 
 '''
 
@@ -377,16 +377,20 @@ async def open_jsonrpc_session(
     url: str,
     start_id: int = 0,
     response_type: type = JSONRPCResult,
-    request_type: Optional[type] = None,
-    request_hook: Optional[Callable] = None,
-    error_hook: Optional[Callable] = None,
+    # request_type: Optional[type] = None,
+    # request_hook: Optional[Callable] = None,
+    # error_hook: Optional[Callable] = None,
 ) -> Callable[[str, dict], dict]:
 
+    # NOTE, store all request msgs so we can raise errors on the
+    # caller side!
+    req_msgs: dict[int, dict] = {}
+
     async with (
         trio.open_nursery() as n,
         open_autorecon_ws(url) as ws
     ):
-        rpc_id: Iterable = count(start_id)
+        rpc_id: Iterable[int] = count(start_id)
         rpc_results: dict[int, dict] = {}
 
         async def json_rpc(method: str, params: dict) -> dict:
@@ -394,26 +398,40 @@ async def open_jsonrpc_session(
             perform a json rpc call and wait for the result, raise exception in
             case of error field present on response
             '''
+            nonlocal req_msgs
+
+            req_id: int = next(rpc_id)
             msg = {
                 'jsonrpc': '2.0',
-                'id': next(rpc_id),
+                'id': req_id,
                 'method': method,
                 'params': params
             }
             _id = msg['id']
 
-            rpc_results[_id] = {
+            result = rpc_results[_id] = {
                 'result': None,
-                'event': trio.Event()
+                'error': None,
+                'event': trio.Event(),  # signal caller resp arrived
             }
+            req_msgs[_id] = msg
 
             await ws.send_msg(msg)
 
+            # wait for reponse before unblocking requester code
             await rpc_results[_id]['event'].wait()
 
-            ret = rpc_results[_id]['result']
+            if (maybe_result := result['result']):
+                ret = maybe_result
+                del rpc_results[_id]
 
-            del rpc_results[_id]
+            else:
+                err = result['error']
+                raise Exception(
+                    f'JSONRPC request failed\n'
+                    f'req: {msg}\n'
+                    f'resp: {err}\n'
+                )
 
             if ret.error is not None:
                 raise Exception(json.dumps(ret.error, indent=4))
@@ -428,6 +446,7 @@ async def open_jsonrpc_session(
             the server side.
 
             '''
+            nonlocal req_msgs
             async for msg in ws:
                 match msg:
                     case {
@@ -451,15 +470,29 @@ async def open_jsonrpc_session(
                         'params': _,
                     }:
                         log.debug(f'Recieved\n{msg}')
-                        if request_hook:
-                            await request_hook(request_type(**msg))
+                        # if request_hook:
+                        #     await request_hook(request_type(**msg))
 
                     case {
                         'error': error
                     }:
-                        log.warning(f'Recieved\n{error}')
-                        if error_hook:
-                            await error_hook(response_type(**msg))
+                        # if error_hook:
+                        #     await error_hook(response_type(**msg))
+
+                        # retreive orig request msg, set error
+                        # response in original "result" msg,
+                        # THEN FINALLY set the event to signal caller
+                        # to raise the error in the parent task.
+                        req_id: int = error['id']
+                        req_msg: dict = req_msgs[req_id]
+                        result: dict = rpc_results[req_id]
+                        result['error'] = error
+                        result['event'].set()
+                        log.error(
+                            f'JSONRPC request failed\n'
+                            f'req: {req_msg}\n'
+                            f'resp: {error}\n'
+                        )
 
                     case _:
                         log.warning(f'Unhandled JSON-RPC msg!?\n{msg}')

piker/service/__init__.py

@@ -30,7 +30,11 @@ Actor runtime primtives and (distributed) service APIs for,
   => TODO: maybe to (re)move elsewhere?
 
 '''
-from ._mngr import Services as Services
+from ._mngr import (
+    get_service_mngr as get_service_mngr,
+    open_service_mngr as open_service_mngr,
+    ServiceMngr as ServiceMngr,
+)
 from ._registry import (
     _tractor_kwargs as _tractor_kwargs,
     _default_reg_addr as _default_reg_addr,

piker/service/_actor_runtime.py

@@ -21,7 +21,6 @@
 from __future__ import annotations
 import os
 from typing import (
-    Optional,
     Any,
     ClassVar,
 )
@@ -30,13 +29,13 @@ from contextlib import (
 )
 
 import tractor
-import trio
 
 from ._util import (
     get_console_log,
 )
 from ._mngr import (
-    Services,
+    open_service_mngr,
+    ServiceMngr,
 )
 from ._registry import (  # noqa
     _tractor_kwargs,
@@ -59,7 +58,7 @@ async def open_piker_runtime(
     registry_addrs: list[tuple[str, int]] = [],
 
     enable_modules: list[str] = [],
-    loglevel: Optional[str] = None,
+    loglevel: str|None = None,
 
     # XXX NOTE XXX: you should pretty much never want debug mode
     # for data daemons when running in production.
@@ -69,7 +68,7 @@ async def open_piker_runtime(
     # and spawn the service tree distributed per that.
     start_method: str = 'trio',
 
-    tractor_runtime_overrides: dict | None = None,
+    tractor_runtime_overrides: dict|None = None,
     **tractor_kwargs,
 
 ) -> tuple[
@@ -119,6 +118,10 @@ async def open_piker_runtime(
                 # spawn other specialized daemons I think?
                 enable_modules=enable_modules,
 
+                # TODO: how to configure this?
+                # keep it on by default if debug mode is set?
+                # maybe_enable_greenback=debug_mode,
+
                 **tractor_kwargs,
             ) as actor,
 
@@ -167,12 +170,13 @@ async def open_pikerd(
 
     **kwargs,
 
-) -> Services:
+) -> ServiceMngr:
     '''
-    Start a root piker daemon with an indefinite lifetime.
+    Start a root piker daemon actor (aka `pikerd`) with an indefinite
+    lifetime.
 
-    A root actor nursery is created which can be used to create and keep
-    alive underling services (see below).
+    A root actor-nursery is created which can be used to spawn and
+    supervise underling service sub-actors (see below).
 
     '''
     # NOTE: for the root daemon we always enable the root
@@ -199,8 +203,6 @@ async def open_pikerd(
             root_actor,
             reg_addrs,
         ),
-        tractor.open_nursery() as actor_nursery,
-        trio.open_nursery() as service_nursery,
     ):
         for addr in reg_addrs:
             if addr not in root_actor.accept_addrs:
@@ -209,25 +211,17 @@ async def open_pikerd(
                     'Maybe you have another daemon already running?'
                 )
 
-        # assign globally for future daemon/task creation
-        Services.actor_n = actor_nursery
-        Services.service_n = service_nursery
-        Services.debug_mode = debug_mode
-
-        try:
-            yield Services
-
-        finally:
-            # TODO: is this more clever/efficient?
-            # if 'samplerd' in Services.service_tasks:
-            #     await Services.cancel_service('samplerd')
-            service_nursery.cancel_scope.cancel()
+        mngr: ServiceMngr
+        async with open_service_mngr(
+            debug_mode=debug_mode,
+        ) as mngr:
+            yield mngr
 
 
 # TODO: do we even need this?
 # @acm
 # async def maybe_open_runtime(
-#     loglevel: Optional[str] = None,
+#     loglevel: str|None = None,
 #     **kwargs,
 
 # ) -> None:
@@ -256,7 +250,7 @@ async def maybe_open_pikerd(
     loglevel: str | None = None,
     **kwargs,
 
-) -> tractor._portal.Portal | ClassVar[Services]:
+) -> tractor._portal.Portal | ClassVar[ServiceMngr]:
     '''
     If no ``pikerd`` daemon-root-actor can be found start it and
     yield up (we should probably figure out returning a portal to self

piker/service/_ahab.py

@@ -49,7 +49,7 @@ from requests.exceptions import (
     ReadTimeout,
 )
 
-from ._mngr import Services
+from ._mngr import ServiceMngr
 from ._util import (
     log,  # sub-sys logger
     get_console_log,
@@ -453,7 +453,7 @@ async def open_ahabd(
 
 @acm
 async def start_ahab_service(
-    services: Services,
+    services: ServiceMngr,
     service_name: str,
 
     # endpoint config passed as **kwargs
@@ -549,7 +549,8 @@ async def start_ahab_service(
         log.warning('Failed to cancel root permsed container')
 
     except (
-        trio.MultiError,
+        # trio.MultiError,
+        ExceptionGroup,
     ) as err:
         for subexc in err.exceptions:
             if isinstance(subexc, PermissionError):

piker/service/_daemon.py

@@ -26,14 +26,17 @@ from typing import (
 from contextlib import (
     asynccontextmanager as acm,
 )
+from collections import defaultdict
 
 import tractor
+import trio
 
 from ._util import (
     log,  # sub-sys logger
 )
 from ._mngr import (
-    Services,
+    get_service_mngr,
+    ServiceMngr,
 )
 from ._actor_runtime import maybe_open_pikerd
 from ._registry import find_service
@@ -41,15 +44,14 @@ from ._registry import find_service
 
 @acm
 async def maybe_spawn_daemon(
-
     service_name: str,
     service_task_target: Callable,
-
     spawn_args: dict[str, Any],
 
     loglevel: str | None = None,
     singleton: bool = False,
 
+    _locks = defaultdict(trio.Lock),
     **pikerd_kwargs,
 
 ) -> tractor.Portal:
@@ -67,7 +69,7 @@ async def maybe_spawn_daemon(
     '''
     # serialize access to this section to avoid
     # 2 or more tasks racing to create a daemon
-    lock = Services.locks[service_name]
+    lock = _locks[service_name]
     await lock.acquire()
 
     async with find_service(
@@ -102,6 +104,12 @@ async def maybe_spawn_daemon(
         # service task for that actor.
         started: bool
         if pikerd_portal is None:
+
+            # await tractor.pause()
+            if tractor_kwargs.get('debug_mode', False):
+                from tractor.devx._debug import maybe_init_greenback
+                await maybe_init_greenback()
+
             started = await service_task_target(
                 loglevel=loglevel,
                 **spawn_args,
@@ -132,7 +140,65 @@ async def maybe_spawn_daemon(
         async with tractor.wait_for_actor(service_name) as portal:
             lock.release()
             yield portal
-            await portal.cancel_actor()
+            # --- ---- ---
+            # XXX NOTE XXX
+            # --- ---- ---
+            # DO NOT PUT A `portal.cancel_actor()` here (as was prior)!
+            #
+            # Doing so will cause an "out-of-band" ctxc
+            # (`tractor.ContextCancelled`) to be raised inside the
+            # `ServiceMngr.open_context_in_task()`'s call to
+            # `ctx.wait_for_result()` AND the internal self-ctxc
+            # "graceful capture" WILL NOT CATCH IT!
+            #
+            # This can cause certain types of operations to raise
+            # that ctxc BEFORE THEY `return`, resulting in
+            # a "false-negative" ctxc being raised when really
+            # nothing actually failed, other then our semantic
+            # "failure" to suppress an expected, graceful,
+            # self-cancel scenario..
+            #
+            # bUt wHy duZ It WorK lIKe dis..
+            # ------------------------------
+            # from the perspective of the `tractor.Context` this
+            # cancel request was conducted "out of band" since
+            # `Context.cancel()` was never called and thus the
+            # `._cancel_called: bool` was never set. Despite the
+            # remote `.canceller` being set to `pikerd` (i.e. the
+            # same `Actor.uid` of the raising service-mngr task) the
+            # service-task's ctx itself was never marked as having
+            # requested cancellation and thus still raises the ctxc
+            # bc it was unaware of any such request.
+            #
+            # How to make grokin these cases easier tho?
+            # ------------------------------------------
+            # Because `Portal.cancel_actor()` was called it requests
+            # "full-`Actor`-runtime-cancellation" of it's peer
+            # process which IS NOT THE SAME as a single inter-actor
+            # RPC task cancelling its local context with a remote
+            # peer `Task` in that same peer process.
+            #
+            # ?TODO? It might be better if we do one (or all) of the
+            # following:
+            #
+            # -[ ] at least set a special message for the
+            #    `ContextCancelled` when raised locally by the
+            #    unaware ctx task such that we check for the
+            #    `.canceller` being *our `Actor`* and in the case
+            #    where `Context._cancel_called == False` we specially
+            #    note that this is likely an "out-of-band"
+            #    runtime-cancel request triggered by some call to
+            #    `Portal.cancel_actor()`, possibly even reporting the
+            #    exact LOC of that caller by tracking it inside our
+            #    portal-type?
+            # -[ ] possibly add another field `ContextCancelled` like
+            #    maybe a,
+            #    `.request_type: Literal['os', 'proc', 'actor',
+            #    'ctx']` type thing which would allow immediately
+            #    being able to tell what kind of cancellation caused
+            #    the unexpected ctxc?
+            # -[ ] REMOVE THIS COMMENT, once we've settled on how to
+            #     better augment `tractor` to be more explicit on this!
 
 
 async def spawn_emsd(
@@ -147,26 +213,25 @@ async def spawn_emsd(
     """
     log.info('Spawning emsd')
 
-    portal = await Services.actor_n.start_actor(
+    smngr: ServiceMngr = get_service_mngr()
+    portal = await smngr.an.start_actor(
         'emsd',
         enable_modules=[
             'piker.clearing._ems',
             'piker.clearing._client',
         ],
         loglevel=loglevel,
-        debug_mode=Services.debug_mode,  # set by pikerd flag
+        debug_mode=smngr.debug_mode,  # set by pikerd flag
         **extra_tractor_kwargs
     )
 
     # non-blocking setup of clearing service
     from ..clearing._ems import _setup_persistent_emsd
 
-    await Services.start_service_task(
-        'emsd',
-        portal,
-
-        # signature of target root-task endpoint
-        _setup_persistent_emsd,
+    await smngr.start_service_ctx(
+        name='emsd',
+        portal=portal,
+        ctx_fn=_setup_persistent_emsd,
         loglevel=loglevel,
     )
     return True

piker/service/_mngr.py

@@ -18,148 +18,36 @@
 daemon-service management API.
 
 """
-from collections import defaultdict
-from typing import (
-    Callable,
-    Any,
+from contextlib import (
+    asynccontextmanager as acm,
 )
 
-import trio
-from trio_typing import TaskStatus
 import tractor
-from tractor import (
-    current_actor,
-    ContextCancelled,
-    Context,
-    Portal,
+from tractor.hilevel import (
+    ServiceMngr,
+    # open_service_mngr as _open_service_mngr,
+    get_service_mngr as get_service_mngr,
 )
+# TODO:
+# -[ ] factor all the common shit from `.data._sampling`
+#   and `.brokers._daemon` into here / `ServiceMngr`
+#   in terms of allocating the `Portal` as part of the
+#   "service-in-subactor" starting!
+# -[ ] move to `tractor.hilevel._service`, import and use here!
+# NOTE: purposely leaks the ref to the mod-scope Bo
 
-from ._util import (
-    log,  # sub-sys logger
-)
+Services: ServiceMngr|None = None
 
+@acm
+async def open_service_mngr(
+    **kwargs,
+) -> ServiceMngr:
 
-# TODO: we need remote wrapping and a general soln:
-# - factor this into a ``tractor.highlevel`` extension # pack for the
-#   library.
-# - wrap a "remote api" wherein you can get a method proxy
-#   to the pikerd actor for starting services remotely!
-# - prolly rename this to ActorServicesNursery since it spawns
-#   new actors and supervises them to completion?
-class Services:
-
-    actor_n: tractor._supervise.ActorNursery
-    service_n: trio.Nursery
-    debug_mode: bool  # tractor sub-actor debug mode flag
-    service_tasks: dict[
-        str,
-        tuple[
-            trio.CancelScope,
-            Portal,
-            trio.Event,
-        ]
-    ] = {}
-    locks = defaultdict(trio.Lock)
-
-    @classmethod
-    async def start_service_task(
-        self,
-        name: str,
-        portal: Portal,
-        target: Callable,
-        allow_overruns: bool = False,
-        **ctx_kwargs,
-
-    ) -> (trio.CancelScope, Context):
-        '''
-        Open a context in a service sub-actor, add to a stack
-        that gets unwound at ``pikerd`` teardown.
-
-        This allows for allocating long-running sub-services in our main
-        daemon and explicitly controlling their lifetimes.
-
-        '''
-        async def open_context_in_task(
-            task_status: TaskStatus[
-                tuple[
-                    trio.CancelScope,
-                    trio.Event,
-                    Any,
-                ]
-            ] = trio.TASK_STATUS_IGNORED,
-
-        ) -> Any:
-
-            with trio.CancelScope() as cs:
-
-                async with portal.open_context(
-                    target,
-                    allow_overruns=allow_overruns,
-                    **ctx_kwargs,
-
-                ) as (ctx, first):
-
-                    # unblock once the remote context has started
-                    complete = trio.Event()
-                    task_status.started((cs, complete, first))
-                    log.info(
-                        f'`pikerd` service {name} started with value {first}'
-                    )
-                    try:
-                        # wait on any context's return value
-                        # and any final portal result from the
-                        # sub-actor.
-                        ctx_res: Any = await ctx.result()
-
-                        # NOTE: blocks indefinitely until cancelled
-                        # either by error from the target context
-                        # function or by being cancelled here by the
-                        # surrounding cancel scope.
-                        return (await portal.result(), ctx_res)
-                    except ContextCancelled as ctxe:
-                        canceller: tuple[str, str] = ctxe.canceller
-                        our_uid: tuple[str, str] = current_actor().uid
-                        if (
-                            canceller != portal.channel.uid
-                            and
-                            canceller != our_uid
-                        ):
-                            log.cancel(
-                                f'Actor-service {name} was remotely cancelled?\n'
-                                f'remote canceller: {canceller}\n'
-                                f'Keeping {our_uid} alive, ignoring sub-actor cancel..\n'
-                            )
-                        else:
-                            raise
-
-
-
-                    finally:
-                        await portal.cancel_actor()
-                        complete.set()
-                        self.service_tasks.pop(name)
-
-        cs, complete, first = await self.service_n.start(open_context_in_task)
-
-        # store the cancel scope and portal for later cancellation or
-        # retstart if needed.
-        self.service_tasks[name] = (cs, portal, complete)
-
-        return cs, first
-
-    @classmethod
-    async def cancel_service(
-        self,
-        name: str,
-
-    ) -> Any:
-        '''
-        Cancel the service task and actor for the given ``name``.
-
-        '''
-        log.info(f'Cancelling `pikerd` service {name}')
-        cs, portal, complete = self.service_tasks[name]
-        cs.cancel()
-        await complete.wait()
-        assert name not in self.service_tasks, \
-            f'Serice task for {name} not terminated?'
+    global Services
+    async with tractor.hilevel.open_service_mngr(
+        **kwargs,
+    ) as mngr:
+        # Services = proxy(mngr)
+        Services = mngr
+        yield mngr
+        Services = None

piker/service/elastic.py

@@ -21,11 +21,13 @@ from typing import (
     TYPE_CHECKING,
 )
 
+# TODO: oof, needs to be changed to `httpx`!
 import asks
 
 if TYPE_CHECKING:
     import docker
     from ._ahab import DockerContainer
+    from . import ServiceMngr
 
 from ._util import log  # sub-sys logger
 from ._util import (
@@ -127,7 +129,7 @@ def start_elasticsearch(
 
 @acm
 async def start_ahab_daemon(
-    service_mngr: Services,
+    service_mngr: ServiceMngr,
     user_config: dict | None = None,
     loglevel: str | None = None,
 

piker/service/marketstore.py

@@ -53,7 +53,7 @@ import pendulum
 # import purerpc
 
 from ..data.feed import maybe_open_feed
-from . import Services
+from . import ServiceMngr
 from ._util import (
     log,  # sub-sys logger
     get_console_log,
@@ -233,7 +233,7 @@ def start_marketstore(
 
 @acm
 async def start_ahab_daemon(
-    service_mngr: Services,
+    service_mngr: ServiceMngr,
     user_config: dict | None = None,
     loglevel: str | None = None,
 

piker/tsp/__init__.py

@@ -458,13 +458,15 @@ async def start_backfill(
                     'bf_until <- last_start_dt:\n'
                     f'{backfill_until_dt} <- {last_start_dt}\n'
                 )
-
-                # ugh, what's a better way?
-                # TODO: fwiw, we probably want a way to signal a throttle
-                # condition (eg. with ib) so that we can halt the
-                # request loop until the condition is resolved?
-                if timeframe > 1:
-                    await tractor.pause()
+                # UGH: what's a better way?
+                # TODO: backends are responsible for being correct on
+                # this right!?
+                # -[ ] in the `ib` case we could maybe offer some way
+                #     to halt the request loop until the condition is
+                #     resolved or should the backend be entirely in
+                #     charge of solving such faults? yes, right?
+                # if timeframe > 1:
+                #     await tractor.pause()
                 return
 
             assert (
@@ -578,6 +580,7 @@ async def start_backfill(
                     'crypto',
                     'crypto_currency',
                     'fiat',  # a "forex pair"
+                    'perpetual_future',  # stupid "perps" from cex land
                 }:
                     # for now, our table key schema is not including
                     # the dst[/src] source asset token.

tests/conftest.py

@@ -10,7 +10,7 @@ from piker import (
     config,
 )
 from piker.service import (
-    Services,
+    get_service_mngr,
 )
 from piker.log import get_console_log
 
@@ -129,7 +129,7 @@ async def _open_test_pikerd(
         ) as service_manager,
     ):
         # this proc/actor is the pikerd
-        assert service_manager is Services
+        assert service_manager is get_service_mngr()
 
         async with tractor.wait_for_actor(
             'pikerd',

tests/test_ems.py

@@ -26,7 +26,7 @@ import pytest
 import tractor
 from uuid import uuid4
 
-from piker.service import Services
+from piker.service import ServiceMngr
 from piker.log import get_logger
 from piker.clearing._messages import (
     Order,
@@ -158,7 +158,7 @@ def load_and_check_pos(
 
 
 def test_ems_err_on_bad_broker(
-    open_test_pikerd: Services,
+    open_test_pikerd: ServiceMngr,
     loglevel: str,
 ):
     async def load_bad_fqme():

tests/test_services.py

@@ -15,7 +15,7 @@ import tractor
 
 from piker.service import (
     find_service,
-    Services,
+    ServiceMngr,
 )
 from piker.data import (
     open_feed,
@@ -44,7 +44,7 @@ def test_runtime_boot(
     async def main():
         port = 6666
         daemon_addr = ('127.0.0.1', port)
-        services: Services
+        services: ServiceMngr
 
         async with (
             open_test_pikerd(