Support `tractor.pause_from_sync()` in `brokerd`s

By passing down the `tractor.hilevel.ServiceMngr.debug_mode: bool`
(normally proxied in from the `--pdb` CLI flag) to `spawn_brokerd()` and
adjusting the `_setup_persistent_brokerd()` endpoint to do the
`tractor.devx._debug.maybe_init_greenback()` if needed.

Also in the `broker_init()` factory merge all `tractor` related `kwargs`
(i.e. `start_actor_kwargs | datad_kwargs | spawn_kws`) into the 2nd
element returned as to be passed to `ActorNursery.start_actor()`. Start
re-naming some internal vars/fields as `datad` as well.

default.nix

@@ -0,0 +1,82 @@
+with (import <nixpkgs> {});
+with python312Packages;
+let
+  glibStorePath = lib.getLib glib;
+  qtpyStorePath = lib.getLib qtpy;
+  pyqt6StorePath = lib.getLib pyqt6;
+  pyqt6SipStorePath = lib.getLib pyqt6-sip;
+  qt6baseStorePath = lib.getLib qt6.qtbase;
+  rapidfuzzStorePath = lib.getLib rapidfuzz;
+  qdarkstyleStorePath = lib.getLib qdarkstyle;
+in
+stdenv.mkDerivation {
+  name = "piker-qt6-poetry-shell";
+  buildInputs = [
+    # System requirements.
+    glib
+    qt6.qtbase
+    libgcc.lib
+
+    # Python requirements.
+    python312Full
+    poetry-core
+    qdarkstyle
+    rapidfuzz
+    pyqt6
+    qtpy
+  ];
+  src = null;
+  shellHook = ''
+    set -e
+
+    export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:${libgcc.lib}/lib:${glibStorePath}/lib
+
+    # Set the Qt plugin path
+    # export QT_DEBUG_PLUGINS=1
+
+    QTBASE_PATH="${qt6baseStorePath}"
+    echo "qtbase path:    $QTBASE_PATH"
+    echo ""
+    export QT_PLUGIN_PATH="$QTBASE_PATH/lib/qt-6/plugins"
+    export QT_QPA_PLATFORM_PLUGIN_PATH="$QT_PLUGIN_PATH/platforms"
+    echo "qt plugin path: $QT_PLUGIN_PATH"
+    echo ""
+
+    # Maybe create venv & install deps
+    poetry install --with uis
+
+    # Use pyqt6 from System, patch activate script
+    ACTIVATE_SCRIPT_PATH="$(poetry env info --path)/bin/activate"
+
+    export RPDFUZZ_PATH="${rapidfuzzStorePath}/lib/python3.12/site-packages"
+    export QDRKSTYLE_PATH="${qdarkstyleStorePath}/lib/python3.12/site-packages"
+    export QTPY_PATH="${qtpyStorePath}/lib/python3.12/site-packages"
+    export PYQT6_PATH="${pyqt6StorePath}/lib/python3.12/site-packages"
+    export PYQT6_SIP_PATH="${pyqt6SipStorePath}/lib/python3.12/site-packages"
+    echo "rapidfuzz at:   $RPDFUZZ_PATH"
+    echo "qdarkstyle at:  $QDRKSTYLE_PATH"
+    echo "qtpy at:        $QTPY_PATH" 
+    echo "pyqt6 at:       $PYQT6_PATH"
+    echo "pyqt6-sip at:   $PYQT6_SIP_PATH"
+    echo ""
+
+    PATCH="export PYTHONPATH=\""
+
+    PATCH="$PATCH\$RPDFUZZ_PATH"
+    PATCH="$PATCH:\$QDRKSTYLE_PATH"
+    PATCH="$PATCH:\$QTPY_PATH"
+    PATCH="$PATCH:\$PYQT6_PATH"
+    PATCH="$PATCH:\$PYQT6_SIP_PATH"
+
+    PATCH="$PATCH\""
+
+    if grep -q "$PATCH" "$ACTIVATE_SCRIPT_PATH"; then
+        echo "venv is already patched."
+    else
+        echo "patching $ACTIVATE_SCRIPT_PATH to use pyqt6 from nixos..."
+        sed -i "\$i$PATCH" $ACTIVATE_SCRIPT_PATH
+    fi
+
+    poetry shell
+  '';
+}

piker/brokers/__init__.py

@@ -51,6 +51,7 @@ __brokers__: list[str] = [
     'ib',
     'kraken',
     'kucoin',
+    'deribit',
 
     # broken but used to work
     # 'questrade',
@@ -61,7 +62,6 @@ __brokers__: list[str] = [
     # wstrade
     # iex
 
-    # deribit
     # bitso
 ]
 

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,
@@ -60,12 +61,13 @@ async def _setup_persistent_brokerd(
     ctx: tractor.Context,
     brokername: str,
     loglevel: str | None = None,
+    debug_mode: bool = False,
 
 ) -> None:
     '''
-    Allocate a actor-wide service nursery in ``brokerd``
-    such that feeds can be run in the background persistently by
-    the broker backend as needed.
+    Allocate a actor-wide service nursery in `brokerd` such that
+    feeds can be run in the background persistently by the broker
+    backend as needed.
 
     '''
     # NOTE: we only need to setup logging once (and only) here
@@ -86,6 +88,18 @@ async def _setup_persistent_brokerd(
     from piker.data import feed
     assert not feed._bus
 
+    if (
+        debug_mode
+        and
+        tractor.current_actor().is_infected_aio()
+    ):
+        # NOTE, whenever running `asyncio` in provider's actor
+        # runtime be sure we enabled `breakpoint()` support
+        # for non-`trio.Task` usage.
+        from tractor.devx._debug import maybe_init_greenback
+        await maybe_init_greenback()
+        # breakpoint()  # XXX, SHOULD WORK from `trio.Task`!
+
     # allocate a nursery to the bus for spawning background
     # tasks to service client IPC requests, normally
     # `tractor.Context` connections to explicitly required
@@ -145,18 +159,21 @@ def broker_init(
       above.
 
     '''
-    from ..brokers import get_brokermod
-    brokermod = get_brokermod(brokername)
+    brokermod: ModuleType = get_brokermod(brokername)
     modpath: str = brokermod.__name__
-
-    start_actor_kwargs['name'] = f'brokerd.{brokername}'
-    start_actor_kwargs.update(
-        getattr(
-            brokermod,
-            '_spawn_kwargs',
-            {},
-        )
+    spawn_kws: dict = getattr(
+        brokermod,
+        '_spawn_kwargs',
+        {},
     )
+    # ^^ NOTE, here we pull any runtime parameters specific
+    # to spawning the sub-actor for the backend. For ex.
+    # both `ib` and `deribit` rely on,
+    #  `'infect_asyncio': True,` since they both
+    #  use `tractor`'s "infected `asyncio` mode"
+    #  for their libs but you could also do something like
+    #  `'debug_mode: True` which would be like passing
+    #  `--pdb` for just that provider backend.
 
     # XXX TODO: make this not so hacky/monkeypatched..
     # -> we need a sane way to configure the logging level for all
@@ -166,8 +183,7 @@ def broker_init(
 
     # lookup actor-enabled modules declared by the backend offering the
     # `brokerd` endpoint(s).
-    enabled: list[str]
-    enabled = start_actor_kwargs['enable_modules'] = [
+    enabled: list[str] = [
         __name__,  # so that eps from THIS mod can be invoked
         modpath,
     ]
@@ -179,9 +195,13 @@ def broker_init(
         subpath: str = f'{modpath}.{submodname}'
         enabled.append(subpath)
 
+    datad_kwargs: dict = {
+        'name': f'brokerd.{brokername}',
+        'enable_modules': enabled,
+    }
     return (
         brokermod,
-        start_actor_kwargs,  # to `ActorNursery.start_actor()`
+        start_actor_kwargs | datad_kwargs | spawn_kws,  # to `ActorNursery.start_actor()`
 
         # XXX see impl above; contains all (actor global)
         # setup/teardown expected in all `brokerd` actor instances.
@@ -190,14 +210,17 @@ 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')
 
@@ -211,33 +234,41 @@ async def spawn_brokerd(
         **tractor_kwargs,
     )
 
-    brokermod = get_brokermod(brokername)
-    extra_tractor_kwargs = getattr(brokermod, '_spawn_kwargs', {})
-    tractor_kwargs.update(extra_tractor_kwargs)
-
     # 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,
+        ),
+        debug_mode=mngr.debug_mode,
+        # ^TODO, allow overriding this per-daemon from client side?
+        # |_ it's already supported in `tractor` so..
+
+        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 +293,7 @@ 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/deribit/__init__.py

@@ -25,6 +25,7 @@ from .api import (
     get_client,
 )
 from .feed import (
+    get_mkt_info,
     open_history_client,
     open_symbol_search,
     stream_quotes,
@@ -34,15 +35,20 @@ from .feed import (
     # open_trade_dialog,
     # norm_trade_records,
 # )
+from .venues import (
+    OptionPair,
+)
 
 log = get_logger(__name__)
 
 __all__ = [
     'get_client',
 #    'trades_dialogue',
+    'get_mkt_info',
     'open_history_client',
     'open_symbol_search',
     'stream_quotes',
+    'OptionPair',
 #    'norm_trade_records',
 ]
 

piker/brokers/deribit/feed.py

@@ -18,38 +18,59 @@
 Deribit backend.
 
 '''
+from __future__ import annotations
 from contextlib import asynccontextmanager as acm
 from datetime import datetime
-from typing import Any, Optional, Callable
+from typing import (
+    # Any,
+    # Optional,
+    Callable,
+)
+# from pprint import pformat
 import time
 
+import cryptofeed
 import trio
 from trio_typing import TaskStatus
-import pendulum
-from rapidfuzz import process as fuzzy
+from pendulum import (
+    from_timestamp,
+)
 import numpy as np
 import tractor
 
-from piker.brokers import open_cached_client
-from piker.log import get_logger, get_console_log
-from piker.data import ShmArray
-from piker.brokers._util import (
-    BrokerError,
+from piker.accounting import (
+    Asset,
+    MktPair,
+    unpack_fqme,
+)
+from piker.brokers import (
+    open_cached_client,
+    NoData,
     DataUnavailable,
 )
-
-from cryptofeed import FeedHandler
-from cryptofeed.defines import (
-    DERIBIT, L1_BOOK, TRADES, OPTION, CALL, PUT
+from piker._cacheables import (
+    async_lifo_cache,
 )
-from cryptofeed.symbols import Symbol
+from piker.log import (
+    get_logger,
+    mk_repr,
+)
+from piker.data.validate import FeedInit
+
 
 from .api import (
-    Client, Trade,
-    get_config,
-    str_to_cb_sym, piker_sym_to_cb_sym, cb_sym_to_deribit_inst,
+    Client,
+    # get_config,
+    piker_sym_to_cb_sym,
+    cb_sym_to_deribit_inst,
+    str_to_cb_sym,
     maybe_open_price_feed
 )
+from .venues import (
+    Pair,
+    OptionPair,
+    Trade,
+)
 
 _spawn_kwargs = {
     'infect_asyncio': True,
@@ -64,90 +85,215 @@ async def open_history_client(
     mkt: MktPair,
 ) -> tuple[Callable, int]:
 
-    fnstrument: str = mkt.bs_fqme
     # TODO implement history getter for the new storage layer.
     async with open_cached_client('deribit') as client:
 
+        pair: OptionPair = client._pairs[mkt.dst.name]
+        # XXX NOTE, the cuckers use ms !!!
+        creation_time_s: int = pair.creation_timestamp/1000
+
         async def get_ohlc(
-            end_dt: Optional[datetime] = None,
-            start_dt: Optional[datetime] = None,
+            timeframe: float,
+            end_dt: datetime | None = None,
+            start_dt: datetime | None = None,
 
         ) -> tuple[
             np.ndarray,
             datetime,  # start
             datetime,  # end
         ]:
+            if timeframe != 60:
+                raise DataUnavailable('Only 1m bars are supported')
 
-            array = await client.bars(
-                instrument,
+            array: np.ndarray = await client.bars(
+                mkt,
                 start_dt=start_dt,
                 end_dt=end_dt,
             )
             if len(array) == 0:
-                raise DataUnavailable
+                if (
+                    end_dt is None
+                ):
+                    raise DataUnavailable(
+                        'No history seems to exist yet?\n\n'
+                        f'{mkt}'
+                    )
+                elif (
+                    end_dt
+                    and
+                    end_dt.timestamp() < creation_time_s
+                ):
+                    # the contract can't have history
+                    # before it was created.
+                    pair_type_str: str = type(pair).__name__
+                    create_dt: datetime = from_timestamp(creation_time_s)
+                    raise DataUnavailable(
+                        f'No history prior to\n'
+                        f'`{pair_type_str}.creation_timestamp: int = '
+                        f'{pair.creation_timestamp}\n\n'
+                        f'------ deribit sux ------\n'
+                        f'WHICH IN "NORMAL PEOPLE WHO USE EPOCH TIME" form is,\n'
+                        f'creation_time_s: {creation_time_s}\n'
+                        f'create_dt: {create_dt}\n'
+                    )
+                raise NoData(
+                    f'No frame for {start_dt} -> {end_dt}\n'
+                )
 
-            start_dt = pendulum.from_timestamp(array[0]['time'])
-            end_dt = pendulum.from_timestamp(array[-1]['time'])
+            start_dt = from_timestamp(array[0]['time'])
+            end_dt = from_timestamp(array[-1]['time'])
+
+            times = array['time']
+            if not times.any():
+                raise ValueError(
+                    'Bad frame with null-times?\n\n'
+                    f'{times}'
+                )
+
+            if end_dt is None:
+                inow: int = round(time.time())
+                if (inow - times[-1]) > 60:
+                    await tractor.pause()
 
             return array, start_dt, end_dt
 
-        yield get_ohlc, {'erlangs': 3, 'rate': 3}
+        yield (
+            get_ohlc,
+            {  # backfill config
+                'erlangs': 3,
+                'rate': 3,
+            }
+        )
+
+
+@async_lifo_cache()
+async def get_mkt_info(
+    fqme: str,
+
+) -> tuple[MktPair, Pair|OptionPair] | None:
+
+    # uppercase since kraken bs_mktid is always upper
+    if 'deribit' not in fqme.lower():
+        fqme += '.deribit'
+
+    mkt_mode: str = ''
+    broker, mkt_ep, venue, expiry = unpack_fqme(fqme)
+
+    # NOTE: we always upper case all tokens to be consistent with
+    # binance's symbology style for pairs, like `BTCUSDT`, but in
+    # theory we could also just keep things lower case; as long as
+    # we're consistent and the symcache matches whatever this func
+    # returns, always!
+    expiry: str = expiry.upper()
+    venue: str = venue.upper()
+    # venue_lower: str = venue.lower()
+
+    mkt_mode: str = 'option'
+
+    async with open_cached_client(
+        'deribit',
+    ) as client:
+
+        assets: dict[str, Asset] = await client.get_assets()
+        pair_str: str = mkt_ep.lower()
+
+        pair: Pair = await client.exch_info(
+            sym=pair_str,
+        )
+        mkt_mode = pair.venue
+        client.mkt_mode = mkt_mode
+
+        dst: Asset | None = assets.get(pair.bs_dst_asset)
+        src: Asset | None = assets.get(pair.bs_src_asset)
+
+        mkt = MktPair(
+            dst=dst,
+            src=src,
+            price_tick=pair.price_tick,
+            size_tick=pair.size_tick,
+            bs_mktid=pair.symbol,
+            venue=mkt_mode,
+            broker='deribit',
+            _atype=mkt_mode,
+            _fqme_without_src=True,
+
+            # expiry=pair.expiry,
+            # XXX TODO, currently we don't use it since it's
+            # already "described" in the `OptionPair.symbol: str`
+            # and if we slap in the ISO repr it's kinda hideous..
+            # -[ ] figure out the best either std
+        )
+        return mkt, pair
 
 
 async def stream_quotes(
-
     send_chan: trio.abc.SendChannel,
     symbols: list[str],
     feed_is_live: trio.Event,
-    loglevel: str = None,
 
     # startup sync
     task_status: TaskStatus[tuple[dict, dict]] = trio.TASK_STATUS_IGNORED,
 
 ) -> None:
-    # XXX: required to propagate ``tractor`` loglevel to piker logging
-    get_console_log(loglevel or tractor.current_actor().loglevel)
+    '''
+    Open a live quote stream for the market set defined by `symbols`.
 
-    sym = symbols[0]
+    Internally this starts a `cryptofeed.FeedHandler` inside an `asyncio`-side
+    task and relays through L1 and `Trade` msgs here to our `trio.Task`.
+
+    '''
+    sym = symbols[0].split('.')[0]
+    init_msgs: list[FeedInit] = []
+
+    # multiline nested `dict` formatter (since rn quote-msgs are
+    # just that).
+    pfmt: Callable[[str], str] = mk_repr(
+        # so we can see `deribit`'s delightfully mega-long bs fields..
+        maxstring=100,
+    )
 
     async with (
         open_cached_client('deribit') as client,
         send_chan as send_chan
     ):
+        mkt: MktPair
+        pair: Pair
+        mkt, pair = await get_mkt_info(sym)
 
-        init_msgs = {
-            # pass back token, and bool, signalling if we're the writer
-            # and that history has been written
-            sym: {
-                'symbol_info': {
-                    'asset_type': 'option',
-                    'price_tick_size': 0.0005
-                },
-                'shm_write_opts': {'sum_tick_vml': False},
-                'fqsn': sym,
-            },
-        }
+        # build out init msgs according to latest spec
+        init_msgs.append(
+            FeedInit(
+                mkt_info=mkt,
+            )
+        )
+        # build `cryptofeed` feed-handle
+        cf_sym: cryptofeed.Symbol = piker_sym_to_cb_sym(sym)
 
-        nsym = piker_sym_to_cb_sym(sym)
+        from_cf: tractor.to_asyncio.LinkedTaskChannel
+        async with maybe_open_price_feed(sym) as from_cf:
 
-        async with maybe_open_price_feed(sym) as stream:
+            # load the "last trades" summary
+            last_trades_res: cryptofeed.LastTradesResult = await client.last_trades(
+                cb_sym_to_deribit_inst(cf_sym),
+                count=1,
+            )
+            last_trades: list[Trade] = last_trades_res.trades
 
-            cache = await client.cache_symbols()
+            # TODO, do we even need this or will the above always
+            # work?
+            # if not last_trades:
+            #     await tractor.pause()
+            #     async for typ, quote in from_cf:
+            #         if typ == 'trade':
+            #             last_trade = Trade(**(quote['data']))
+            #             break
 
-            last_trades = (await client.last_trades(
-                cb_sym_to_deribit_inst(nsym), count=1)).trades
+            # else:
+            last_trade = Trade(
+                **(last_trades[0])
+            )
 
-            if len(last_trades) == 0:
-                last_trade = None
-                async for typ, quote in stream:
-                    if typ == 'trade':
-                        last_trade = Trade(**(quote['data']))
-                        break
-
-            else:
-                last_trade = Trade(**(last_trades[0]))
-
-            first_quote = {
+            first_quote: dict = {
                 'symbol': sym,
                 'last': last_trade.price,
                 'brokerd_ts': last_trade.timestamp,
@@ -158,13 +304,84 @@ async def stream_quotes(
                     'broker_ts': last_trade.timestamp
                 }]
             }
-            task_status.started((init_msgs,  first_quote))
+            task_status.started((
+                init_msgs,
+                first_quote,
+            ))
 
             feed_is_live.set()
 
-            async for typ, quote in stream:
-                topic = quote['symbol']
-                await send_chan.send({topic: quote})
+            # NOTE XXX, static for now!
+            # => since this only handles ONE mkt feed at a time we
+            # don't need a lookup table to map interleaved quotes
+            # from multiple possible mkt-pairs
+            topic: str = mkt.bs_fqme
+
+            # deliver until cancelled
+            async for typ, ref in from_cf:
+                match typ:
+                    case 'trade':
+                        trade: cryptofeed.types.Trade = ref
+
+                        # TODO, re-impl this according to teh ideal
+                        # fqme for opts that we choose!!
+                        bs_fqme: str = cb_sym_to_deribit_inst(
+                            str_to_cb_sym(trade.symbol)
+                        ).lower()
+
+                        piker_quote: dict = {
+                            'symbol': bs_fqme,
+                            'last': trade.price,
+                            'broker_ts': time.time(),
+                            # ^TODO, name this `brokerd/datad_ts` and
+                            # use `time.time_ns()` ??
+                            'ticks': [{
+                                'type': 'trade',
+                                'price': float(trade.price),
+                                'size': float(trade.amount),
+                                'broker_ts': trade.timestamp,
+                            }],
+                        }
+                        log.info(
+                            f'deribit {typ!r} quote for {sym!r}\n\n'
+                            f'{trade}\n\n'
+                            f'{pfmt(piker_quote)}\n'
+                        )
+
+                    case 'l1':
+                        book: cryptofeed.types.L1Book = ref
+
+                        # TODO, so this is where we can possibly change things
+                        # and instead lever the `MktPair.bs_fqme: str` output?
+                        bs_fqme: str = cb_sym_to_deribit_inst(
+                            str_to_cb_sym(book.symbol)
+                        ).lower()
+
+                        piker_quote: dict = {
+                            'symbol': bs_fqme,
+                            'ticks': [
+
+                                {'type': 'bid',
+                                 'price': float(book.bid_price),
+                                 'size': float(book.bid_size)},
+
+                                {'type': 'bsize',
+                                 'price': float(book.bid_price),
+                                 'size': float(book.bid_size),},
+
+                                {'type': 'ask',
+                                 'price': float(book.ask_price),
+                                 'size': float(book.ask_size),},
+
+                                {'type': 'asize',
+                                 'price': float(book.ask_price),
+                                 'size': float(book.ask_size),}
+                            ]
+                        }
+
+                await send_chan.send({
+                    topic: piker_quote,
+                })
 
 
 @tractor.context
@@ -174,12 +391,21 @@ async def open_symbol_search(
     async with open_cached_client('deribit') as client:
 
         # load all symbols locally for fast search
-        cache = await client.cache_symbols()
+        # cache = client._pairs
         await ctx.started()
 
         async with ctx.open_stream() as stream:
-
+            pattern: str
             async for pattern in stream:
-                # repack in dict form
-                await stream.send(
-                    await client.search_symbols(pattern))
+
+                # NOTE: pattern fuzzy-matching is done within
+                # the methd impl.
+                pairs: dict[str, Pair] = await client.search_symbols(
+                    pattern,
+                )
+                # repack in fqme-keyed table
+                byfqme: dict[str, Pair] = {}
+                for pair in pairs.values():
+                    byfqme[pair.bs_fqme] = pair
+
+                await stream.send(byfqme)

piker/brokers/deribit/venues.py

@@ -0,0 +1,196 @@
+# piker: trading gear for hackers
+# Copyright (C) Tyler Goodlet (in stewardship for pikers)
+
+# 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/>.
+
+"""
+Per market data-type definitions and schemas types.
+
+"""
+from __future__ import annotations
+import pendulum
+from typing import (
+    Literal,
+    Optional,
+)
+from decimal import Decimal
+
+from piker.types import Struct
+
+
+# API endpoint paths by venue / sub-API
+_domain: str = 'deribit.com'
+_url = f'https://www.{_domain}'
+
+# WEBsocketz
+_ws_url: str = f'wss://www.{_domain}/ws/api/v2'
+
+# test nets
+_testnet_ws_url: str = f'wss://test.{_domain}/ws/api/v2'
+
+MarketType = Literal[
+    'option'
+]
+
+
+def get_api_eps(venue: MarketType) -> tuple[str, str]:
+    '''
+    Return API ep root paths per venue.
+
+    '''
+    return {
+        'option': (
+            _ws_url,
+        ),
+    }[venue]
+
+
+class Pair(Struct, frozen=True, kw_only=True):
+
+    symbol: str
+
+    # src
+    quote_currency: str # 'BTC'
+
+    # dst
+    base_currency: str # "BTC",
+
+    tick_size: float # 0.0001 # [{'above_price': 0.005, 'tick_size': 0.0005}]
+    tick_size_steps: list[dict[str, float]] 
+
+    @property
+    def price_tick(self) -> Decimal:
+        return Decimal(str(self.tick_size_steps[0]['above_price']))
+
+    @property
+    def size_tick(self) -> Decimal:
+        return Decimal(str(self.tick_size))
+
+    @property
+    def bs_fqme(self) -> str:
+        return f'{self.symbol}'
+
+    @property
+    def bs_mktid(self) -> str:
+        return f'{self.symbol}.{self.venue}'
+
+
+class OptionPair(Pair, frozen=True):
+
+    taker_commission: float # 0.0003
+    strike: float # 5000.0
+    settlement_period: str # 'day'
+    settlement_currency: str # "BTC",
+    rfq: bool # false
+    price_index: str # 'btc_usd'
+    option_type: str # 'call'
+    min_trade_amount: float # 0.1
+    maker_commission: float # 0.0003
+    kind: str # 'option'
+    is_active: bool # true
+    instrument_type: str # 'reversed'
+    instrument_name: str # 'BTC-1SEP24-55000-C'
+    instrument_id: int # 364671
+    expiration_timestamp: int # 1725177600000
+    creation_timestamp: int # 1724918461000
+    counter_currency: str # 'USD' 
+    contract_size: float # '1.0'
+    block_trade_tick_size: float # '0.0001'
+    block_trade_min_trade_amount: int # '25'
+    block_trade_commission: float # '0.003'
+
+    # NOTE: see `.data._symcache.SymbologyCache.load()` for why
+    ns_path: str = 'piker.brokers.deribit:OptionPair'
+
+    # TODO, impl this without the MM:SS part of
+    # the `'THH:MM:SS..'` etc..
+    @property
+    def expiry(self) -> str:
+        iso_date = pendulum.from_timestamp(
+            self.expiration_timestamp / 1000
+        ).isoformat()
+        return iso_date 
+
+    @property
+    def venue(self) -> str:
+        return f'{self.instrument_type}_option'
+
+    @property
+    def bs_fqme(self) -> str:
+        return f'{self.symbol}'
+
+    @property
+    def bs_src_asset(self) -> str:
+        return f'{self.quote_currency}'
+
+    @property
+    def bs_dst_asset(self) -> str:
+        return f'{self.symbol}'
+
+
+PAIRTYPES: dict[MarketType, Pair] = {
+    'option': OptionPair,
+}
+
+
+class JSONRPCResult(Struct):
+    id: int
+    usIn: int
+    usOut: int
+    usDiff: int
+    testnet: bool
+    jsonrpc: str = '2.0'
+    error: Optional[dict] = None
+    result: Optional[list[dict]] = None
+
+
+class JSONRPCChannel(Struct):
+    method: str
+    params: dict
+    jsonrpc: str = '2.0'
+
+
+class KLinesResult(Struct):
+    low: list[float]
+    cost: list[float]
+    high: list[float]
+    open: list[float]
+    close: list[float]
+    ticks: list[int]
+    status: str
+    volume: list[float]
+
+
+class Trade(Struct):
+    iv: float
+    price: float
+    amount: float
+    trade_id: str
+    contracts: float
+    direction: str
+    trade_seq: int
+    timestamp: int
+    mark_price: float
+    index_price: float
+    tick_direction: int
+    instrument_name: str
+    combo_id: Optional[str] = '',
+    combo_trade_id: Optional[int] = 0,
+    block_trade_id: Optional[str] = '',
+    block_trade_leg_count: Optional[int] = 0,
+
+
+class LastTradesResult(Struct):
+    trades: list[Trade]
+    has_more: bool

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/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

@@ -25,10 +25,12 @@ from collections import (
     defaultdict,
 )
 from contextlib import asynccontextmanager as acm
+from functools import partial
 import time
 from typing import (
     Any,
     AsyncIterator,
+    Callable,
     TYPE_CHECKING,
 )
 
@@ -42,7 +44,7 @@ from tractor.trionics import (
     maybe_open_nursery,
 )
 import trio
-from trio_typing import TaskStatus
+from trio import TaskStatus
 
 from .ticktools import (
     frame_ticks,
@@ -53,6 +55,9 @@ from ._util import (
     get_console_log,
 )
 from ..service import maybe_spawn_daemon
+from piker.log import (
+    mk_repr,
+)
 
 if TYPE_CHECKING:
     from ._sharedmem import (
@@ -70,6 +75,7 @@ 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 +85,9 @@ 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 +381,10 @@ 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 +428,6 @@ async def register_with_sampler(
 
 
 async def spawn_samplerd(
-
     loglevel: str | None = None,
     **extra_tractor_kwargs
 
@@ -429,7 +437,10 @@ 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 +448,33 @@ 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
 
@@ -561,7 +579,6 @@ async def open_sample_stream(
 
 
 async def sample_and_broadcast(
-
     bus: _FeedsBus,  # noqa
     rt_shm: ShmArray,
     hist_shm: ShmArray,
@@ -582,11 +599,22 @@ async def sample_and_broadcast(
 
     overruns = Counter()
 
+    # multiline nested `dict` formatter (since rn quote-msgs are
+    # just that).
+    pfmt: Callable[[str], str] = mk_repr()
+
     # iterate stream delivered by broker
     async for quotes in quote_stream:
-        # print(quotes)
 
-        # TODO: ``numba`` this!
+        # XXX WARNING XXX only enable for debugging bc ow can cost
+        # ALOT of perf with HF-feedz!!!
+        #
+        # log.info(
+        #     'Rx live quotes:\n'
+        #     f'{pfmt(quotes)}'
+        # )
+
+        # TODO: `numba` this!
         for broker_symbol, quote in quotes.items():
             # TODO: in theory you can send the IPC msg *before* writing
             # to the sharedmem array to decrease latency, however, that
@@ -659,6 +687,18 @@ async def sample_and_broadcast(
             sub_key: str = broker_symbol.lower()
             subs: set[Sub] = bus.get_subs(sub_key)
 
+            if not subs:
+                all_bs_fqmes: list[str] = list(
+                    bus._subscribers.keys()
+                )
+                log.warning(
+                    f'No subscribers for {brokername!r} live-quote ??\n'
+                    f'broker_symbol: {broker_symbol}\n\n'
+
+                    f'Maybe the backend-sys symbol does not match one of,\n'
+                    f'{pfmt(all_bs_fqmes)}\n'
+                )
+
             # NOTE: by default the broker backend doesn't append
             # it's own "name" into the fqme schema (but maybe it
             # should?) so we have to manually generate the correct
@@ -889,6 +929,7 @@ 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`.
 
 '''
 
@@ -377,43 +377,77 @@ 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,
+    msg_recv_timeout: float = float('inf'),
+    # ^NOTE, since only `deribit` is using this jsonrpc stuff atm
+    # and options mkts are generally "slow moving"..
+    #
+    # FURTHER if we break the underlying ws connection then since we
+    # don't pass a `fixture` to the task that manages `NoBsWs`, i.e.
+    # `_reconnect_forever()`, the jsonrpc "transport pipe" get's
+    # broken and never restored with wtv init sequence is required to
+    # re-establish a working req-resp session.
+
+    # 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
+        open_autorecon_ws(
+            url=url,
+            msg_recv_timeout=msg_recv_timeout,
+        ) 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:
+        async def json_rpc(
+            method: str,
+            params: dict,
+        ) -> dict:
             '''
             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 +462,7 @@ async def open_jsonrpc_session(
             the server side.
 
             '''
+            nonlocal req_msgs
             async for msg in ws:
                 match msg:
                     case {
@@ -451,15 +486,29 @@ 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 = msg['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/data/feed.py

@@ -540,7 +540,10 @@ async def open_feed_bus(
         # subscription since the backend isn't (yet) expected to
         # append it's own name to the fqme, so we filter on keys
         # which *do not* include that name (e.g .ib) .
-        bus._subscribers.setdefault(bs_fqme, set())
+        bus._subscribers.setdefault(
+            bs_fqme,
+            set(),
+        )
 
     # sync feed subscribers with flume handles
     await ctx.started(

piker/log.py

@@ -18,7 +18,11 @@
 Log like a forester!
 """
 import logging
+import reprlib
 import json
+from typing import (
+    Callable,
+)
 
 import tractor
 from pygments import (
@@ -84,3 +88,27 @@ def colorize_json(
         # likeable styles: algol_nu, tango, monokai
         formatters.TerminalTrueColorFormatter(style=style)
     )
+
+
+def mk_repr(
+    **repr_kws,
+) -> Callable[[str], str]:
+    '''
+    Allocate and deliver a `repr.Repr` instance with provided input
+    settings using the std-lib's `reprlib` mod,
+     * https://docs.python.org/3/library/reprlib.html
+
+    ------ Ex. ------
+    An up to 6-layer-nested `dict` as multi-line:
+    - https://stackoverflow.com/a/79102479
+    - https://docs.python.org/3/library/reprlib.html#reprlib.Repr.maxlevel
+
+    '''
+    def_kws: dict[str, int] = dict(
+        indent=2,
+        maxlevel=6,  # recursion levels
+        maxstring=66,  # match editor line-len limit
+    )
+    def_kws |= repr_kws
+    reprr = reprlib.Repr(**def_kws)
+    return reprr.repr

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(
@@ -132,7 +134,65 @@ 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(
@@ -147,21 +207,22 @@ async def spawn_emsd(
     """
     log.info('Spawning emsd')
 
-    portal = await Services.actor_n.start_actor(
+    smngr: ServiceMngr = get_service_mngr()
+    portal = await smngr.actor_n.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(
+    await smngr.start_service_task(
         'emsd',
         portal,
 

piker/service/_mngr.py

@@ -18,16 +18,29 @@
 daemon-service management API.
 
 """
+from __future__ import annotations
+from contextlib import (
+    asynccontextmanager as acm,
+    # contextmanager as cm,
+)
 from collections import defaultdict
+from dataclasses import (
+    dataclass,
+    field,
+)
+import functools
+import inspect
 from typing import (
     Callable,
     Any,
 )
 
-import trio
-from trio_typing import TaskStatus
+import msgspec
 import tractor
+import trio
+from trio import TaskStatus
 from tractor import (
+    ActorNursery,
     current_actor,
     ContextCancelled,
     Context,
@@ -39,6 +52,130 @@ from ._util import (
 )
 
 
+# TODO: implement a singleton deco-API for wrapping the below
+# factory's impl for general actor-singleton use?
+#
+# @singleton
+# async def open_service_mngr(
+#     **init_kwargs,
+# ) -> ServiceMngr:
+#     '''
+#     Note this function body is invoke IFF no existing singleton instance already
+#     exists in this proc's memory.
+
+#     '''
+#     # setup
+#     yield ServiceMngr(**init_kwargs)
+#     # teardown
+
+
+
+# TODO: singleton factory API instead of a class API
+@acm
+async def open_service_mngr(
+    *,
+    debug_mode: bool = False,
+
+    # impl deat which ensures a single global instance
+    _singleton: list[ServiceMngr|None] = [None],
+    **init_kwargs,
+
+) -> ServiceMngr:
+    '''
+    Open a multi-subactor-as-service-daemon tree supervisor.
+
+    The delivered `ServiceMngr` is a singleton instance for each
+    actor-process and is allocated on first open and never
+    de-allocated unless explicitly deleted by al call to
+    `del_service_mngr()`.
+
+    '''
+    # TODO: factor this an allocation into
+    # a `._mngr.open_service_mngr()` and put in the
+    # once-n-only-once setup/`.__aenter__()` part!
+    # -[ ] how to make this only happen on the `mngr == None` case?
+    #  |_ use `.trionics.maybe_open_context()` (for generic
+    #     async-with-style-only-once of the factory impl, though
+    #     what do we do for the allocation case?
+    #    / `.maybe_open_nursery()` (since for this specific case
+    #    it's simpler?) to activate
+    async with (
+        tractor.open_nursery() as an,
+        trio.open_nursery() as tn,
+    ):
+        # impl specific obvi..
+        init_kwargs.update({
+            'actor_n': an,
+            'service_n': tn,
+        })
+
+        mngr: ServiceMngr|None
+        if (mngr := _singleton[0]) is None:
+
+            log.info('Allocating a new service mngr!')
+            mngr = _singleton[0] = ServiceMngr(**init_kwargs)
+
+            # TODO: put into `.__aenter__()` section of
+            # eventual `@singleton_acm` API wrapper.
+            #
+            # assign globally for future daemon/task creation
+            mngr.actor_n = an
+            mngr.service_n = tn
+
+        else:
+            assert (
+                mngr.actor_n
+                and
+                mngr.service_tn
+            )
+            log.info(
+                'Using extant service mngr!\n\n'
+                f'{mngr!r}\n'  # it has a nice `.__repr__()` of services state
+            )
+
+        try:
+            # NOTE: this is a singleton factory impl specific detail
+            # which should be supported in the condensed
+            # `@singleton_acm` API?
+            mngr.debug_mode = debug_mode
+
+            yield mngr
+        finally:
+            # TODO: is this more clever/efficient?
+            # if 'samplerd' in mngr.service_tasks:
+            #     await mngr.cancel_service('samplerd')
+            tn.cancel_scope.cancel()
+
+
+
+def get_service_mngr() -> ServiceMngr:
+    '''
+    Try to get the singleton service-mngr for this actor presuming it
+    has already been allocated using,
+
+    .. code:: python
+
+        async with open_<@singleton_acm(func)>() as mngr`
+            ... this block kept open ...
+
+    If not yet allocated raise a `ServiceError`.
+
+    '''
+    # https://stackoverflow.com/a/12627202
+    # https://docs.python.org/3/library/inspect.html#inspect.Signature
+    maybe_mngr: ServiceMngr|None = inspect.signature(
+        open_service_mngr
+    ).parameters['_singleton'].default[0]
+
+    if maybe_mngr is None:
+        raise RuntimeError(
+            'Someone must allocate a `ServiceMngr` using\n\n'
+            '`async with open_service_mngr()` beforehand!!\n'
+        )
+
+    return maybe_mngr
+
+
 # TODO: we need remote wrapping and a general soln:
 # - factor this into a ``tractor.highlevel`` extension # pack for the
 #   library.
@@ -46,31 +183,46 @@ from ._util import (
 #   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:
+@dataclass
+class ServiceMngr:
+# class ServiceMngr(msgspec.Struct):
+    '''
+    A multi-subactor-as-service manager.
 
-    actor_n: tractor._supervise.ActorNursery
+    Spawn, supervise and monitor service/daemon subactors in a SC
+    process tree.
+
+    '''
+    actor_n: ActorNursery
     service_n: trio.Nursery
-    debug_mode: bool  # tractor sub-actor debug mode flag
+    debug_mode: bool = False # tractor sub-actor debug mode flag
+
     service_tasks: dict[
         str,
         tuple[
             trio.CancelScope,
+            Context,
             Portal,
             trio.Event,
         ]
-    ] = {}
-    locks = defaultdict(trio.Lock)
+    ] = field(default_factory=dict)
+
+    # internal per-service task mutexs
+    _locks = defaultdict(trio.Lock)
 
-    @classmethod
     async def start_service_task(
         self,
         name: str,
         portal: Portal,
+
+        # TODO: typevar for the return type of the target and then
+        # use it below for `ctx_res`?
         target: Callable,
+
         allow_overruns: bool = False,
         **ctx_kwargs,
 
-    ) -> (trio.CancelScope, Context):
+    ) -> (trio.CancelScope, Context, Any):
         '''
         Open a context in a service sub-actor, add to a stack
         that gets unwound at ``pikerd`` teardown.
@@ -83,6 +235,7 @@ class Services:
             task_status: TaskStatus[
                 tuple[
                     trio.CancelScope,
+                    Context,
                     trio.Event,
                     Any,
                 ]
@@ -90,64 +243,87 @@ class Services:
 
         ) -> Any:
 
+            # TODO: use the ctx._scope directly here instead?
+            # -[ ] actually what semantics do we expect for this
+            #   usage!?
             with trio.CancelScope() as cs:
+                try:
+                    async with portal.open_context(
+                        target,
+                        allow_overruns=allow_overruns,
+                        **ctx_kwargs,
 
-                async with portal.open_context(
-                    target,
-                    allow_overruns=allow_overruns,
-                    **ctx_kwargs,
+                    ) as (ctx, started):
 
-                ) 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:
+                        # unblock once the remote context has started
+                        complete = trio.Event()
+                        task_status.started((
+                            cs,
+                            ctx,
+                            complete,
+                            started,
+                        ))
+                        log.info(
+                            f'`pikerd` service {name} started with value {started}'
+                        )
                         # wait on any context's return value
                         # and any final portal result from the
                         # sub-actor.
-                        ctx_res: Any = await ctx.result()
+                        ctx_res: Any = await ctx.wait_for_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
+                        return (
+                            await portal.wait_for_result(),
+                            ctx_res,
+                        )
 
+                except ContextCancelled as ctxe:
+                    canceller: tuple[str, str] = ctxe.canceller
+                    our_uid: tuple[str, str] = current_actor().uid
+                    if (
+                        canceller != portal.chan.uid
+                        and
+                        canceller != our_uid
+                    ):
+                        log.cancel(
+                            f'Actor-service `{name}` was remotely cancelled by a peer?\n'
 
+                            # TODO: this would be a good spot to use
+                            # a respawn feature Bo
+                            f'-> Keeping `pikerd` service manager alive despite this inter-peer cancel\n\n'
 
-                    finally:
-                        await portal.cancel_actor()
-                        complete.set()
-                        self.service_tasks.pop(name)
+                            f'cancellee: {portal.chan.uid}\n'
+                            f'canceller: {canceller}\n'
+                        )
+                    else:
+                        raise
 
-        cs, complete, first = await self.service_n.start(open_context_in_task)
+                finally:
+                    # NOTE: the ctx MUST be cancelled first if we
+                    # don't want the above `ctx.wait_for_result()` to
+                    # raise a self-ctxc. WHY, well since from the ctx's
+                    # perspective the cancel request will have
+                    # arrived out-out-of-band at the `Actor.cancel()`
+                    # level, thus `Context.cancel_called == False`,
+                    # meaning `ctx._is_self_cancelled() == False`.
+                    # with trio.CancelScope(shield=True):
+                    # await ctx.cancel()
+                    await portal.cancel_actor()
+                    complete.set()
+                    self.service_tasks.pop(name)
+
+        cs, sub_ctx, complete, started = 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)
+        self.service_tasks[name] = (cs, sub_ctx, portal, complete)
+        return cs, sub_ctx, started
 
-        return cs, first
-
-    @classmethod
     async def cancel_service(
         self,
         name: str,
@@ -158,8 +334,80 @@ class Services:
 
         '''
         log.info(f'Cancelling `pikerd` service {name}')
-        cs, portal, complete = self.service_tasks[name]
-        cs.cancel()
+        cs, sub_ctx, portal, complete = self.service_tasks[name]
+
+        # cs.cancel()
+        await sub_ctx.cancel()
         await complete.wait()
-        assert name not in self.service_tasks, \
-            f'Serice task for {name} not terminated?'
+
+        if name in self.service_tasks:
+            # TODO: custom err?
+            # raise ServiceError(
+            raise RuntimeError(
+                f'Serice task for {name} not terminated?'
+            )
+
+        # assert name not in self.service_tasks, \
+        #     f'Serice task for {name} not terminated?'
+
+    async def start_service(
+        self,
+        daemon_name: str,
+        ctx_ep: Callable,  # kwargs must `partial`-ed in!
+
+        debug_mode: bool = False,
+        **tractor_actor_kwargs,
+
+    ) -> Context:
+        '''
+        Start a "service" task in a new sub-actor (daemon) and manage it's lifetime
+        indefinitely.
+
+        Services can be cancelled/shutdown using `.cancel_service()`.
+
+        '''
+        entry: tuple|None = self.service_tasks.get(daemon_name)
+        if entry:
+            (cs, sub_ctx, portal, complete) = entry
+            return sub_ctx
+
+        if daemon_name not in self.service_tasks:
+            portal = await self.actor_n.start_actor(
+                daemon_name,
+                debug_mode=(  # maybe set globally during allocate
+                    debug_mode
+                    or
+                    self.debug_mode
+                ),
+                **tractor_actor_kwargs,
+            )
+            ctx_kwargs: dict[str, Any] = {}
+            if isinstance(ctx_ep, functools.partial):
+                ctx_kwargs: dict[str, Any] = ctx_ep.keywords
+                ctx_ep: Callable = ctx_ep.func
+
+            (cs, sub_ctx, started) = await self.start_service_task(
+                daemon_name,
+                portal,
+                ctx_ep,
+                **ctx_kwargs,
+            )
+
+            return sub_ctx
+
+
+# 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
+# import tractor
+# from tractor.hilevel import (
+#     open_service_mngr,
+#     ServiceMngr,
+# )
+# mngr: ServiceMngr|None = None
+# with tractor.hilevel.open_service_mngr() as mngr:
+#     Services = proxy(mngr)

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/storage/nativedb.py

@@ -161,7 +161,12 @@ class NativeStorageClient:
 
     def index_files(self):
         for path in self._datadir.iterdir():
-            if path.name in {'borked', 'expired',}:
+            if (
+                path.name in {'borked', 'expired',}
+                or
+                '.parquet' not in str(path)
+            ):
+                # ignore all non-apache files (for now)
                 continue
 
             key: str = path.name.rstrip('.parquet')

piker/tsp/__init__.py

@@ -44,8 +44,10 @@ import trio
 from trio_typing import TaskStatus
 import tractor
 from pendulum import (
+    Interval,
     DateTime,
     Duration,
+    duration as mk_duration,
     from_timestamp,
 )
 import numpy as np
@@ -214,7 +216,8 @@ async def maybe_fill_null_segments(
         # pair, immediately stop backfilling?
         if (
             start_dt
-            and end_dt < start_dt
+            and
+            end_dt < start_dt
         ):
             await tractor.pause()
             break
@@ -262,6 +265,7 @@ async def maybe_fill_null_segments(
         except tractor.ContextCancelled:
             # log.exception
             await tractor.pause()
+            raise
 
     null_segs_detected.set()
     # RECHECK for more null-gaps
@@ -349,7 +353,7 @@ async def maybe_fill_null_segments(
 
 async def start_backfill(
     get_hist,
-    frame_types: dict[str, Duration] | None,
+    def_frame_duration: Duration,
     mod: ModuleType,
     mkt: MktPair,
     shm: ShmArray,
@@ -379,22 +383,23 @@ async def start_backfill(
         update_start_on_prepend: bool = False
         if backfill_until_dt is None:
 
-            # TODO: drop this right and just expose the backfill
-            # limits inside a [storage] section in conf.toml?
-            # when no tsdb "last datum" is provided, we just load
-            # some near-term history.
-            # periods = {
-            #     1: {'days': 1},
-            #     60: {'days': 14},
-            # }
-
-            # do a decently sized backfill and load it into storage.
+            # TODO: per-provider default history-durations?
+            # -[ ] inside the `open_history_client()` config allow
+            #    declaring the history duration limits instead of
+            #    guessing and/or applying the same limits to all?
+            #
+            # -[ ] allow declaring (default) per-provider backfill
+            #     limits inside a [storage] sub-section in conf.toml?
+            #
+            # NOTE, when no tsdb "last datum" is provided, we just
+            # load some near-term history by presuming a "decently
+            # large" 60s duration limit and a much shorter 1s range.
             periods = {
                 1: {'days': 2},
                 60: {'years': 6},
             }
             period_duration: int = periods[timeframe]
-            update_start_on_prepend = True
+            update_start_on_prepend: bool = True
 
             # NOTE: manually set the "latest" datetime which we intend to
             # backfill history "until" so as to adhere to the history
@@ -416,7 +421,6 @@ async def start_backfill(
                 f'backfill_until_dt: {backfill_until_dt}\n'
                 f'last_start_dt: {last_start_dt}\n'
             )
-
             try:
                 (
                     array,
@@ -426,71 +430,114 @@ async def start_backfill(
                     timeframe,
                     end_dt=last_start_dt,
                 )
-
             except NoData as _daterr:
-                # 3 cases:
-                # - frame in the middle of a legit venue gap
-                # - history actually began at the `last_start_dt`
-                # - some other unknown error (ib blocking the
-                #   history bc they don't want you seeing how they
-                #   cucked all the tinas..)
-                if dur := frame_types.get(timeframe):
-                    # decrement by a frame's worth of duration and
-                    # retry a few times.
-                    last_start_dt.subtract(
-                        seconds=dur.total_seconds()
+                orig_last_start_dt: datetime = last_start_dt
+                gap_report: str = (
+                    f'EMPTY FRAME for `end_dt: {last_start_dt}`?\n'
+                    f'{mod.name} -> tf@fqme: {timeframe}@{mkt.fqme}\n'
+                    f'last_start_dt: {orig_last_start_dt}\n\n'
+                    f'bf_until: {backfill_until_dt}\n'
+                )
+                # EMPTY FRAME signal with 3 (likely) causes:
+                #
+                # 1. range contains legit gap in venue history
+                # 2. history actually (edge case) **began** at the
+                #    value `last_start_dt`
+                # 3. some other unknown error (ib blocking the
+                #    history-query bc they don't want you seeing how
+                #    they cucked all the tinas.. like with options
+                #    hist)
+                #
+                if def_frame_duration:
+                    # decrement by a duration's (frame) worth of time
+                    # as maybe indicated by the backend to see if we
+                    # can get older data before this possible
+                    # "history gap".
+                    last_start_dt: datetime = last_start_dt.subtract(
+                        seconds=def_frame_duration.total_seconds()
                     )
-                    log.warning(
-                        f'{mod.name} -> EMPTY FRAME for end_dt?\n'
-                        f'tf@fqme: {timeframe}@{mkt.fqme}\n'
-                        'bf_until <- last_start_dt:\n'
-                        f'{backfill_until_dt} <- {last_start_dt}\n'
-                        f'Decrementing `end_dt` by {dur} and retry..\n'
+                    gap_report += (
+                        f'Decrementing `end_dt` and retrying with,\n'
+                        f'def_frame_duration: {def_frame_duration}\n'
+                        f'(new) last_start_dt: {last_start_dt}\n'
                     )
+                    log.warning(gap_report)
+                    # skip writing to shm/tsdb and try the next
+                    # duration's worth of prior history.
                     continue
 
-            # broker says there never was or is no more history to pull
-            except DataUnavailable:
-                log.warning(
-                    f'NO-MORE-DATA in range?\n'
-                    f'`{mod.name}` halted history:\n'
-                    f'tf@fqme: {timeframe}@{mkt.fqme}\n'
-                    'bf_until <- last_start_dt:\n'
-                    f'{backfill_until_dt} <- {last_start_dt}\n'
-                )
+                else:
+                    # await tractor.pause()
+                    raise DataUnavailable(gap_report)
 
-                # 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()
+            # broker says there never was or is no more history to pull
+            except DataUnavailable as due:
+                message: str = due.args[0]
+                log.warning(
+                    f'Provider {mod.name!r} halted backfill due to,\n\n'
+
+                    f'{message}\n'
+
+                    f'fqme: {mkt.fqme}\n'
+                    f'timeframe: {timeframe}\n'
+                    f'last_start_dt: {last_start_dt}\n'
+                    f'bf_until: {backfill_until_dt}\n'
+                )
+                # 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?
                 return
 
+            time: np.ndarray = array['time']
             assert (
-                array['time'][0]
+                time[0]
                 ==
                 next_start_dt.timestamp()
             )
 
-            diff = last_start_dt - next_start_dt
-            frame_time_diff_s = diff.seconds
+            assert time[-1] == next_end_dt.timestamp()
+
+            expected_dur: Interval = last_start_dt - next_start_dt
 
             # frame's worth of sample-period-steps, in seconds
             frame_size_s: float = len(array) * timeframe
-            expected_frame_size_s: float = frame_size_s + timeframe
-            if frame_time_diff_s > expected_frame_size_s:
-
+            recv_frame_dur: Duration = (
+                from_timestamp(array[-1]['time'])
+                -
+                from_timestamp(array[0]['time'])
+            )
+            if (
+                (lt_frame := (recv_frame_dur < expected_dur))
+                or
+                (null_frame := (frame_size_s == 0))
+                # ^XXX, should NEVER hit now!
+            ):
                 # XXX: query result includes a start point prior to our
                 # expected "frame size" and thus is likely some kind of
                 # history gap (eg. market closed period, outage, etc.)
                 # so just report it to console for now.
+                if lt_frame:
+                    reason = 'Possible GAP (or first-datum)'
+                else:
+                    assert null_frame
+                    reason = 'NULL-FRAME'
+
+                missing_dur: Interval = expected_dur.end - recv_frame_dur.end
                 log.warning(
-                    'GAP DETECTED:\n'
-                    f'last_start_dt: {last_start_dt}\n'
-                    f'diff: {diff}\n'
-                    f'frame_time_diff_s: {frame_time_diff_s}\n'
+                    f'{timeframe}s-series {reason} detected!\n'
+                    f'fqme: {mkt.fqme}\n'
+                    f'last_start_dt: {last_start_dt}\n\n'
+                    f'recv interval: {recv_frame_dur}\n'
+                    f'expected interval: {expected_dur}\n\n'
+
+                    f'Missing duration of history of {missing_dur.in_words()!r}\n'
+                    f'{missing_dur}\n'
                 )
+                # await tractor.pause()
 
             to_push = diff_history(
                 array,
@@ -565,7 +612,8 @@ async def start_backfill(
             # long-term storage.
             if (
                 storage is not None
-                and write_tsdb
+                and
+                write_tsdb
             ):
                 log.info(
                     f'Writing {ln} frame to storage:\n'
@@ -578,6 +626,7 @@ 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.
@@ -685,7 +734,7 @@ async def back_load_from_tsdb(
         last_tsdb_dt
         and latest_start_dt
     ):
-        backfilled_size_s = (
+        backfilled_size_s: Duration = (
             latest_start_dt - last_tsdb_dt
         ).seconds
         # if the shm buffer len is not large enough to contain
@@ -908,6 +957,8 @@ async def tsdb_backfill(
             f'{pformat(config)}\n'
         )
 
+        # concurrently load the provider's most-recent-frame AND any
+        # pre-existing tsdb history already saved in `piker` storage.
         dt_eps: list[DateTime, DateTime] = []
         async with trio.open_nursery() as tn:
             tn.start_soon(
@@ -918,7 +969,6 @@ async def tsdb_backfill(
                 timeframe,
                 config,
             )
-
             tsdb_entry: tuple = await load_tsdb_hist(
                 storage,
                 mkt,
@@ -947,6 +997,25 @@ async def tsdb_backfill(
                 mr_end_dt,
             ) = dt_eps
 
+            first_frame_dur_s: Duration = (mr_end_dt - mr_start_dt).seconds
+            calced_frame_size: Duration = mk_duration(
+                seconds=first_frame_dur_s,
+            )
+            # NOTE, attempt to use the backend declared default frame
+            # sizing (as allowed by their time-series query APIs) and
+            # if not provided try to construct a default from the
+            # first frame received above.
+            def_frame_durs: dict[
+                int,
+                Duration,
+            ]|None = config.get('frame_types', None)
+            if def_frame_durs:
+                def_frame_size: Duration = def_frame_durs[timeframe]
+                assert def_frame_size == calced_frame_size
+            else:
+                # use what we calced from first frame above.
+                def_frame_size = calced_frame_size
+
             # NOTE: when there's no offline data, there's 2 cases:
             # - data backend doesn't support timeframe/sample
             #   period (in which case `dt_eps` should be `None` and
@@ -977,7 +1046,7 @@ async def tsdb_backfill(
                     partial(
                         start_backfill,
                         get_hist=get_hist,
-                        frame_types=config.get('frame_types', None),
+                        def_frame_duration=def_frame_size,
                         mod=mod,
                         mkt=mkt,
                         shm=shm,

pyproject.toml

@@ -25,11 +25,11 @@ build-backend = "poetry.core.masonry.api"
 ignore = []
 
 # https://docs.astral.sh/ruff/settings/#lint_per-file-ignores
-"piker/ui/qt.py" = [
-  "E402",
-  'F401',  # unused imports (without __all__ or blah as blah)
-  # "F841", # unused variable rules
-]
+# "piker/ui/qt.py" = [
+#   "E402",
+#   'F401',  # unused imports (without __all__ or blah as blah)
+#   # "F841", # unused variable rules
+# ]
 # ignore-init-module-imports = false
 
 # ------ - ------
@@ -50,10 +50,8 @@ attrs = "^23.1.0"
 bidict = "^0.22.1"
 colorama = "^0.4.6"
 colorlog = "^6.7.0"
-cython = "^3.0.0"
-greenback = "^1.1.1"
 ib-insync = "^0.9.86"
-msgspec = "^0.18.0"
+msgspec = "^0.18.6"
 numba = "^0.59.0"
 numpy = "^1.25"
 polars = "^0.18.13"
@@ -71,13 +69,11 @@ pdbp = "^1.5.0"
 trio = "^0.24"
 pendulum = "^3.0.0"
 httpx = "^0.27.0"
+cryptofeed = "^2.4.0"
+pyarrow = "^17.0.0"
 
-[tool.poetry.dependencies.tractor]
-develop = true
-git = 'https://github.com/goodboy/tractor.git'
-branch = 'asyncio_debugger_support'
-# path = "../tractor"
-
+tractor = {path = "../tractor", develop = true}
+websockets = "12.0"
 [tool.poetry.dependencies.asyncvnc]
 git = 'https://github.com/pikers/asyncvnc.git'
 branch = 'main'
@@ -109,6 +105,8 @@ pytest = "^6.0.0"
 elasticsearch = "^8.9.0"
 xonsh = "^0.14.2"
 prompt-toolkit = "3.0.40"
+cython = "^3.0.0"
+greenback = "^1.1.1"
 
 # console ehancements and eventually remote debugging
 # extras/helpers.

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(