Add Plot

Here is the `plot_graph()` that is in char of the bars, scatter and vertical line plot items.

Also all the necessary code  for the graph to be shown.

examples/max_pain.py

@@ -0,0 +1,239 @@
+#!/usr/bin/env python
+from decimal import (
+    Decimal,
+)
+import trio
+import tractor
+from datetime import datetime
+from pprint import pformat
+from piker.brokers.deribit.api import (
+    get_client,
+    maybe_open_oi_feed,
+)
+import sys
+import pyqtgraph as pg
+from PyQt6 import QtCore
+from pyqtgraph import ScatterPlotItem, InfiniteLine
+from PyQt6.QtWidgets import QApplication
+
+def check_if_complete(
+        oi: dict[str, dict[str, Decimal | None]]
+    ) -> bool:
+    return all(
+        oi[strike]['C'] is not None
+        and
+        oi[strike]['P'] is not None for strike in oi
+    )
+
+
+async def max_pain_daemon(
+) -> None:
+    oi_by_strikes: dict[str, dict[str, Decimal | None]]
+    instruments: list[Symbol] = []
+    expiry_dates: list[str]
+    expiry_date: str
+    currency: str = 'btc'
+    kind: str = 'option'
+
+    async with get_client(
+    ) as client:
+        expiry_dates: list[str] = await client.get_expiration_dates(
+            currency=currency,
+            kind=kind
+        )
+
+        print(f'Available expiration dates for {currency}-{kind}:')
+        print(f'{expiry_dates}')
+        expiry_date = input('Please enter a valid expiration date: ').upper()
+        print('Starting little daemon...')
+
+        oi_by_strikes: dict[str, dict[str, Decimal]]
+        instruments = await client.get_instruments(
+            expiry_date=expiry_date,
+        )
+        oi_by_strikes = client.get_strikes_dict(instruments)
+
+
+    def get_total_intrinsic_values(
+        oi_by_strikes: dict[str, dict[str, Decimal]]
+    ) -> dict[str, dict[str, Decimal]]:
+        call_cash: Decimal = Decimal(0)
+        put_cash: Decimal = Decimal(0)
+        intrinsic_values: dict[str, dict[str, Decimal]] = {}
+        closes: list = sorted(Decimal(close) for close in oi_by_strikes)
+
+        for strike, oi in oi_by_strikes.items():
+            s = Decimal(strike)
+            call_cash = sum(max(0, (s - c) * oi_by_strikes[str(c)]['C']) for c in closes)
+            put_cash = sum(max(0, (c - s) * oi_by_strikes[str(c)]['P']) for c in closes)
+
+            intrinsic_values[strike] = {
+                'C': call_cash,
+                'P': put_cash,
+                'total': call_cash + put_cash,
+            }
+
+        return intrinsic_values
+
+    def get_intrinsic_value_and_max_pain(
+        intrinsic_values: dict[str, dict[str, Decimal]]
+        ):
+        # We meed to find the lowest value, so we start at
+        # infinity to ensure that, and the max_pain must be
+        # an amount greater than zero.
+        total_intrinsic_value: Decimal = Decimal('Infinity')
+        max_pain: Decimal = Decimal(0)
+
+        for strike, oi in oi_by_strikes.items():
+            s = Decimal(strike)
+            if intrinsic_values[strike]['total'] < total_intrinsic_value:
+                total_intrinsic_value = intrinsic_values[strike]['total']
+                max_pain = s
+
+        return total_intrinsic_value, max_pain
+
+    def plot_graph(
+        oi_by_strikes: dict[str, dict[str, Decimal]],
+        plot,
+    ):
+        """Update the bar graph with new open interest data."""
+        plot.clear()
+
+        intrinsic_values = get_total_intrinsic_values(oi_by_strikes)
+
+        for strike_str in sorted(oi_by_strikes, key=lambda x: int(x)):
+            strike = int(strike_str)
+            calls_val = float(oi_by_strikes[strike_str]['C'])
+            puts_val  = float(oi_by_strikes[strike_str]['P'])
+
+            bar_c = pg.BarGraphItem(
+                x=[strike - 100],
+                height=[calls_val],
+                width=200,
+                pen='w',
+                brush=(0, 0, 255, 150)
+            )
+            plot.addItem(bar_c)
+
+            bar_p = pg.BarGraphItem(
+                x=[strike + 100],
+                height=[puts_val],
+                width=200,
+                pen='w',
+                brush=(255, 0, 0, 150)
+            )
+            plot.addItem(bar_p)
+
+            total_val = float(intrinsic_values[strike_str]['total']) / 100000
+
+            scatter_iv = ScatterPlotItem(
+                x=[strike],
+                y=[total_val],
+                pen=pg.mkPen(color=(0, 255, 0), width=2),
+                brush=pg.mkBrush(0, 255, 0, 150),
+                size=3,
+                symbol='o'
+            )
+            plot.addItem(scatter_iv)
+
+        _, max_pain = get_intrinsic_value_and_max_pain(intrinsic_values)
+
+        vertical_line = InfiniteLine(
+            pos=max_pain,
+            angle=90,
+            pen=pg.mkPen(color='yellow', width=1, style=QtCore.Qt.PenStyle.DotLine),
+            label=f'Max pain: {max_pain:,.0f}',
+            labelOpts={
+                'position': 0.85,
+                'color': 'yellow',
+                'movable': True
+            }
+        )
+        plot.addItem(vertical_line)
+
+    def update_oi_by_strikes(msg: tuple):
+        nonlocal oi_by_strikes
+        if 'oi' == msg[0]:
+            strike_price = msg[1]['strike_price']
+            option_type = msg[1]['option_type']
+            open_interest = msg[1]['open_interest']
+            oi_by_strikes.setdefault(
+                strike_price, {}
+            ).update(
+                {option_type: open_interest}
+            )
+
+    def get_max_pain(
+        oi_by_strikes: dict[str, dict[str, Decimal]]
+    ) -> dict[str, str | Decimal]:
+        '''
+        This method requires only the strike_prices and oi for call
+        and puts, the closes list are the same as the strike_prices
+        the idea is to sum all the calls and puts cash for each strike
+        and the ITM strikes from that strike, the lowest value is what we
+        are looking for the intrinsic value.
+
+        '''
+
+        nonlocal timestamp
+
+        intrinsic_values = get_total_intrinsic_values(oi_by_strikes)
+
+        total_intrinsic_value, max_pain = get_intrinsic_value_and_max_pain(intrinsic_values)
+
+        return {
+            'timestamp': timestamp,
+            'expiry_date': expiry_date,
+            'total_intrinsic_value': total_intrinsic_value,
+            'max_pain': max_pain,
+        }
+
+    async with maybe_open_oi_feed(
+        instruments,
+    ) as oi_feed:
+        # Initialize QApplication
+        app = QApplication(sys.argv)
+
+        win = pg.GraphicsLayoutWidget(show=True)
+        win.setWindowTitle('Calls (blue) vs Puts (red)')
+
+        plot = win.addPlot(title='OI by Strikes')
+        plot.showGrid(x=True, y=True)
+        print('Plot initialized...')
+
+        async for msg in oi_feed:
+
+            update_oi_by_strikes(msg)
+            if check_if_complete(oi_by_strikes):
+                if 'oi' == msg[0]:
+                    timestamp = msg[1]['timestamp']
+                    max_pain = get_max_pain(oi_by_strikes)
+                    intrinsic_values = get_total_intrinsic_values(oi_by_strikes)
+
+                    # graph here
+                    plot_graph(oi_by_strikes, plot)
+
+                    print('-----------------------------------------------')
+                    print(f'timestamp:             {datetime.fromtimestamp(max_pain['timestamp'])}')
+                    print(f'expiry_date:           {max_pain['expiry_date']}')
+                    print(f'max_pain:              {max_pain['max_pain']:,.0f}')
+                    print(f'total intrinsic value: {max_pain['total_intrinsic_value']:,.0f}')
+                    print('-----------------------------------------------')
+
+            # Process GUI events to keep the window responsive
+            app.processEvents()
+
+
+async def main():
+
+    async with tractor.open_nursery() as n:
+
+        p: tractor.Portal = await n.start_actor(
+            'max_pain_daemon',
+            enable_modules=[__name__],
+            infect_asyncio=True,
+        )
+        await p.run(max_pain_daemon)
+
+if __name__ == '__main__':
+    trio.run(main)

examples/max_pain_readme.rst

@@ -0,0 +1,19 @@
+## Max Pain Calculation for Deribit Options
+
+This feature, which calculates the max pain point for options traded on the Deribit exchange using cryptofeed library.
+
+- Functions in the api module for fetching options data from Deribit. [commit](https://pikers.dev/pikers/piker/commit/da55856dd2876291f55a06eb0561438a912d8241)
+
+- Compute the max pain point based on open interest data using deribit's api. [commit](https://pikers.dev/pikers/piker/commit/0d9d6e15ba0edeb662ec97f7599dd66af3046b94)
+
+### How to test it?
+
+**Before start:** in order to get this working with `uv`,  you **must** use my `tractor` [fork](https://pikers.dev/ntorres/tractor/src/branch/aio_abandons) and this branch: `aio_abandons`, the reason is that I cherry-pick the `uv_migration` that guille made, for some reason that a didn't dive into, in my system y need tractor using `uv` too. quite hacky I guess.
+
+1. `uv lock`
+
+2. `uv run --no-dev python examples/max_pain.py`
+
+3. A message should be display, enter one of the expiration date available.
+
+4. The script should be up and running.

piker/accounting/_pos.py

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

piker/brokers/__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
 ]
 
@@ -98,13 +98,14 @@ async def open_cached_client(
     If one has not been setup do it and cache it.
 
     '''
-    brokermod = get_brokermod(brokername)
+    brokermod: ModuleType = get_brokermod(brokername)
+
+    # TODO: make abstract or `typing.Protocol`
+    # client: Client
     async with maybe_open_context(
         acm_func=brokermod.get_client,
         kwargs=kwargs,
-
     ) as (cache_hit, client):
-
         if cache_hit:
             log.runtime(f'Reusing existing {client}')
 

piker/brokers/cli.py

@@ -471,11 +471,15 @@ def search(
 
     '''
     # global opts
-    brokermods = list(config['brokermods'].values())
+    brokermods: list[ModuleType] = list(config['brokermods'].values())
+
+    # TODO: this is coming from the `search --pdb` NOT from
+    # the `piker --pdb` XD ..
+    # -[ ] pull from the parent click ctx's values..dumdum
+    # assert pdb
 
     # define tractor entrypoint
     async def main(func):
-
         async with maybe_open_pikerd(
             loglevel=config['loglevel'],
             debug_mode=pdb,

piker/brokers/core.py

@@ -22,7 +22,9 @@ routines should be primitive data types where possible.
 """
 import inspect
 from types import ModuleType
-from typing import List, Dict, Any, Optional
+from typing import (
+    Any,
+)
 
 import trio
 
@@ -34,8 +36,10 @@ from ..accounting import MktPair
 
 
 async def api(brokername: str, methname: str, **kwargs) -> dict:
-    """Make (proxy through) a broker API call by name and return its result.
-    """
+    '''
+    Make (proxy through) a broker API call by name and return its result.
+
+    '''
     brokermod = get_brokermod(brokername)
     async with brokermod.get_client() as client:
         meth = getattr(client, methname, None)
@@ -62,10 +66,14 @@ async def api(brokername: str, methname: str, **kwargs) -> dict:
 
 async def stocks_quote(
     brokermod: ModuleType,
-    tickers: List[str]
-) -> Dict[str, Dict[str, Any]]:
-    """Return quotes dict for ``tickers``.
-    """
+    tickers: list[str]
+
+) -> dict[str, dict[str, Any]]:
+    '''
+    Return a `dict` of snapshot quotes for the provided input
+    `tickers`: a `list` of fqmes.
+
+    '''
     async with brokermod.get_client() as client:
         return await client.quote(tickers)
 
@@ -74,13 +82,15 @@ async def stocks_quote(
 async def option_chain(
     brokermod: ModuleType,
     symbol: str,
-    date: Optional[str] = None,
-) -> Dict[str, Dict[str, Dict[str, Any]]]:
-    """Return option chain for ``symbol`` for ``date``.
+    date: str|None = None,
+) -> dict[str, dict[str, dict[str, Any]]]:
+    '''
+    Return option chain for ``symbol`` for ``date``.
 
     By default all expiries are returned. If ``date`` is provided
     then contract quotes for that single expiry are returned.
-    """
+
+    '''
     async with brokermod.get_client() as client:
         if date:
             id = int((await client.tickers2ids([symbol]))[symbol])
@@ -98,7 +108,7 @@ async def option_chain(
 # async def contracts(
 #     brokermod: ModuleType,
 #     symbol: str,
-# ) -> Dict[str, Dict[str, Dict[str, Any]]]:
+# ) -> dict[str, dict[str, dict[str, Any]]]:
 #     """Return option contracts (all expiries) for ``symbol``.
 #     """
 #     async with brokermod.get_client() as client:
@@ -110,15 +120,24 @@ async def bars(
     brokermod: ModuleType,
     symbol: str,
     **kwargs,
-) -> Dict[str, Dict[str, Dict[str, Any]]]:
-    """Return option contracts (all expiries) for ``symbol``.
-    """
+) -> dict[str, dict[str, dict[str, Any]]]:
+    '''
+    Return option contracts (all expiries) for ``symbol``.
+
+    '''
     async with brokermod.get_client() as client:
         return await client.bars(symbol, **kwargs)
 
 
-async def search_w_brokerd(name: str, pattern: str) -> dict:
+async def search_w_brokerd(
+    name: str,
+    pattern: str,
+) -> dict:
 
+    # TODO: WHY NOT WORK!?!
+    # when we `step` through the next block?
+    # import tractor
+    # await tractor.pause()
     async with open_cached_client(name) as client:
 
         # TODO: support multiple asset type concurrent searches.
@@ -130,12 +149,12 @@ async def symbol_search(
     pattern: str,
     **kwargs,
 
-) -> Dict[str, Dict[str, Dict[str, Any]]]:
+) -> dict[str, dict[str, dict[str, Any]]]:
     '''
     Return symbol info from broker.
 
     '''
-    results = []
+    results: list[str] = []
 
     async def search_backend(
         brokermod: ModuleType
@@ -143,6 +162,13 @@ async def symbol_search(
 
         brokername: str = mod.name
 
+        # TODO: figure this the FUCK OUT
+        # -> ok so obvi in the root actor any async task that's
+        # spawned outside the main tractor-root-actor task needs to
+        # call this..
+        # await tractor.devx._debug.maybe_init_greenback()
+        # tractor.pause_from_sync()
+
         async with maybe_spawn_brokerd(
             mod.name,
             infect_asyncio=getattr(
@@ -162,7 +188,6 @@ async def symbol_search(
             ))
 
     async with trio.open_nursery() as n:
-
         for mod in brokermods:
             n.start_soon(search_backend, mod.name)
 
@@ -172,11 +197,13 @@ async def symbol_search(
 async def mkt_info(
     brokermod: ModuleType,
     fqme: str,
+
     **kwargs,
 
 ) -> MktPair:
     '''
-    Return MktPair info from broker including src and dst assets.
+    Return the `piker.accounting.MktPair` info struct from a given
+    backend broker tradable src/dst asset pair.
 
     '''
     async with open_cached_client(brokermod.name) as client:

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/clearing/_client.py

@@ -168,7 +168,6 @@ class OrderClient(Struct):
 
 
 async def relay_orders_from_sync_code(
-
     client: OrderClient,
     symbol_key: str,
     to_ems_stream: tractor.MsgStream,
@@ -242,6 +241,11 @@ async def open_ems(
 
     async with maybe_open_emsd(
         broker,
+        # XXX NOTE, LOL so this determines the daemon `emsd` loglevel
+        # then FYI.. that's kinda wrong no?
+        # -[ ] shouldn't it be set by `pikerd -l` or no?
+        # -[ ] would make a lot more sense to have a subsys ctl for
+        #     levels.. like `-l emsd.info` or something?
         loglevel=loglevel,
     ) as portal:
 

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
@@ -1010,6 +1014,10 @@ async def translate_and_relay_brokerd_events(
                 status_msg.brokerd_msg = msg
                 status_msg.src = msg.broker_details['name']
 
+                if not status_msg.req:
+                    # likely some order change state?
+                    await tractor.pause()
+                else:
                     await router.client_broadcast(
                         status_msg.req.symbol,
                         status_msg,

piker/clearing/_paper_engine.py

@@ -297,6 +297,8 @@ class PaperBoi(Struct):
 
         # transmit pp msg to ems
         pp: Position = self.acnt.pps[bs_mktid]
+        # TODO, this will break if `require_only=True` was passed to
+        # `.update_from_ledger()`
 
         pp_msg = BrokerdPosition(
             broker=self.broker,
@@ -653,6 +655,7 @@ async def open_trade_dialog(
                 # in) use manually constructed table from calling
                 # the `.get_mkt_info()` provider EP above.
                 _mktmap_table=mkt_by_fqme,
+                only_require=list(mkt_by_fqme),
             )
 
             pp_msgs: list[BrokerdPosition] = []

piker/clearing/_util.py

@@ -30,6 +30,7 @@ subsys: str = 'piker.clearing'
 
 log = get_logger(subsys)
 
+# TODO, oof doesn't this ignore the `loglevel` then???
 get_console_log = partial(
     get_console_log,
     name=subsys,

piker/cli/__init__.py

@@ -140,11 +140,10 @@ def pikerd(
 
         if pdb:
             log.warning((
-                "\n"
-                "!!! YOU HAVE ENABLED DAEMON DEBUG MODE !!!\n"
-                "When a `piker` daemon crashes it will block the "
-                "task-thread until resumed from console!\n"
-                "\n"
+                '\n\n'
+                '!!! YOU HAVE ENABLED DAEMON DEBUG MODE !!!\n'
+                'When a `piker` daemon crashes it will block the '
+                'task-thread until resumed from console!\n'
             ))
 
         # service-actor registry endpoint socket-address set
@@ -177,7 +176,7 @@ def pikerd(
         from .. import service
 
         async def main():
-            service_mngr: service.Services
+            service_mngr: service.ServiceMngr
 
             async with (
                 service.open_pikerd(

piker/data/_sampling.py

@@ -95,6 +95,12 @@ class Sampler:
     # history loading.
     incr_task_cs: trio.CancelScope | None = None
 
+    bcast_errors: tuple[Exception] = (
+        trio.BrokenResourceError,
+        trio.ClosedResourceError,
+        trio.EndOfChannel,
+    )
+
     # holds all the ``tractor.Context`` remote subscriptions for
     # a particular sample period increment event: all subscribers are
     # notified on a step.
@@ -258,14 +264,15 @@ class Sampler:
         subs: set
         last_ts, subs = pair
 
-        task = trio.lowlevel.current_task()
-        log.debug(
-            f'SUBS {self.subscribers}\n'
-            f'PAIR {pair}\n'
-            f'TASK: {task}: {id(task)}\n'
-            f'broadcasting {period_s} -> {last_ts}\n'
+        # NOTE, for debugging pub-sub issues
+        # task = trio.lowlevel.current_task()
+        # log.debug(
+        #     f'AlL-SUBS@{period_s!r}: {self.subscribers}\n'
+        #     f'PAIR: {pair}\n'
+        #     f'TASK: {task}: {id(task)}\n'
+        #     f'broadcasting {period_s} -> {last_ts}\n'
         #     f'consumers: {subs}'
-        )
+        # )
         borked: set[MsgStream] = set()
         sent: set[MsgStream] = set()
         while True:
@@ -282,12 +289,11 @@ class Sampler:
                         await stream.send(msg)
                         sent.add(stream)
 
-                    except (
-                        trio.BrokenResourceError,
-                        trio.ClosedResourceError
-                    ):
+                    except self.bcast_errors as err:
                         log.error(
-                            f'{stream._ctx.chan.uid} dropped connection'
+                            f'Connection dropped for IPC ctx\n'
+                            f'{stream._ctx}\n\n'
+                            f'Due to {type(err)}'
                         )
                         borked.add(stream)
                 else:
@@ -394,7 +400,8 @@ async def register_with_sampler(
                 finally:
                     if (
                         sub_for_broadcasts
-                        and subs
+                        and
+                        subs
                     ):
                         try:
                             subs.remove(stream)
@@ -561,8 +568,7 @@ async def open_sample_stream(
 
 
 async def sample_and_broadcast(
-
-    bus: _FeedsBus,  # noqa
+    bus: _FeedsBus,
     rt_shm: ShmArray,
     hist_shm: ShmArray,
     quote_stream: trio.abc.ReceiveChannel,
@@ -582,11 +588,33 @@ async def sample_and_broadcast(
 
     overruns = Counter()
 
+    # NOTE, only used for debugging live-data-feed issues, though
+    # this should be resolved more correctly in the future using the
+    # new typed-msgspec feats of `tractor`!
+    #
+    # XXX, a 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` or `cython`-nize this loop possibly?
+        #  |_alternatively could we do it in rust somehow by upacking
+        #    arrow msgs instead of using `msgspec`?
+        # -[ ] use `msgspec.Struct` support in new typed-msging from
+        #     `tractor` to ensure only allowed msgs are transmitted?
+        #
         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 +687,21 @@ async def sample_and_broadcast(
             sub_key: str = broker_symbol.lower()
             subs: set[Sub] = bus.get_subs(sub_key)
 
+            # TODO, figure out how to make this useful whilst
+            # incoporating feed "pausing" ..
+            #
+            # 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
@@ -728,18 +771,14 @@ async def sample_and_broadcast(
                         if lags > 10:
                             await tractor.pause()
 
-                except (
-                    trio.BrokenResourceError,
-                    trio.ClosedResourceError,
-                    trio.EndOfChannel,
-                ):
+                except Sampler.bcast_errors as ipc_err:
                     ctx: Context = ipc._ctx
                     chan: Channel = ctx.chan
                     if ctx:
                         log.warning(
-                            'Dropped `brokerd`-quotes-feed connection:\n'
-                            f'{broker_symbol}:'
-                            f'{ctx.cid}@{chan.uid}'
+                            f'Dropped `brokerd`-feed for {broker_symbol!r} due to,\n'
+                            f'x>) {ctx.cid}@{chan.uid}'
+                            f'|_{ipc_err!r}\n\n'
                         )
                     if sub.throttle_rate:
                         assert ipc._closed
@@ -756,12 +795,11 @@ async def sample_and_broadcast(
 
 
 async def uniform_rate_send(
-
     rate: float,
     quote_stream: trio.abc.ReceiveChannel,
     stream: MsgStream,
 
-    task_status: TaskStatus = trio.TASK_STATUS_IGNORED,
+    task_status: TaskStatus[None] = trio.TASK_STATUS_IGNORED,
 
 ) -> None:
     '''
@@ -779,13 +817,16 @@ async def uniform_rate_send(
     https://gist.github.com/njsmith/7ea44ec07e901cb78ebe1dd8dd846cb9
 
     '''
-    # TODO: compute the approx overhead latency per cycle
-    left_to_sleep = throttle_period = 1/rate - 0.000616
+    # ?TODO? dynamically compute the **actual** approx overhead latency per cycle
+    # instead of this magic # bidinezz?
+    throttle_period: float = 1/rate - 0.000616
+    left_to_sleep: float = throttle_period
 
     # send cycle state
+    first_quote: dict|None
     first_quote = last_quote = None
-    last_send = time.time()
-    diff = 0
+    last_send: float = time.time()
+    diff: float = 0
 
     task_status.started()
     ticks_by_type: dict[
@@ -796,22 +837,28 @@ async def uniform_rate_send(
     clear_types = _tick_groups['clears']
 
     while True:
-
         # compute the remaining time to sleep for this throttled cycle
-        left_to_sleep = throttle_period - diff
+        left_to_sleep: float = throttle_period - diff
 
         if left_to_sleep > 0:
+            cs: trio.CancelScope
             with trio.move_on_after(left_to_sleep) as cs:
+                sym: str
+                last_quote: dict
                 try:
                     sym, last_quote = await quote_stream.receive()
                 except trio.EndOfChannel:
-                    log.exception(f"feed for {stream} ended?")
+                    log.exception(
+                        f'Live stream for feed for ended?\n'
+                        f'<=c\n'
+                        f'  |_[{stream!r}\n'
+                    )
                     break
 
-                diff = time.time() - last_send
+                diff: float = time.time() - last_send
 
                 if not first_quote:
-                    first_quote = last_quote
+                    first_quote: float = last_quote
                     # first_quote['tbt'] = ticks_by_type
 
                 if (throttle_period - diff) > 0:
@@ -872,7 +919,9 @@ async def uniform_rate_send(
         # TODO: now if only we could sync this to the display
         # rate timing exactly lul
         try:
-            await stream.send({sym: first_quote})
+            await stream.send({
+                sym: first_quote
+            })
         except tractor.RemoteActorError as rme:
             if rme.type is not tractor._exceptions.StreamOverrun:
                 raise
@@ -883,19 +932,28 @@ async def uniform_rate_send(
                 f'{sym}:{ctx.cid}@{chan.uid}'
             )
 
-        except (
-            # NOTE: any of these can be raised by ``tractor``'s IPC
+        # NOTE: any of these can be raised by `tractor`'s IPC
         # transport-layer and we want to be highly resilient
         # 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.ClosedResourceError,
-            trio.BrokenResourceError,
+        except (
             ConnectionResetError,
-        ):
+        ) + Sampler.bcast_errors as ipc_err:
+            match ipc_err:
+                case trio.EndOfChannel():
+                    log.info(
+                        f'{stream} terminated by peer,\n'
+                        f'{ipc_err!r}'
+                    )
+                case _:
                     # if the feed consumer goes down then drop
                     # out of this rate limiter
-            log.warning(f'{stream} closed')
+                    log.warning(
+                        f'{stream} closed due to,\n'
+                        f'{ipc_err!r}'
+                    )
+
             await stream.aclose()
             return
 

piker/data/_symcache.py

@@ -31,6 +31,7 @@ from pathlib import Path
 from pprint import pformat
 from typing import (
     Any,
+    Callable,
     Sequence,
     Hashable,
     TYPE_CHECKING,
@@ -56,7 +57,7 @@ from piker.brokers import (
 )
 
 if TYPE_CHECKING:
-    from ..accounting import (
+    from piker.accounting import (
         Asset,
         MktPair,
     )
@@ -149,19 +150,36 @@ class SymbologyCache(Struct):
                     'Implement `Client.get_assets()`!'
                 )
 
-            if get_mkt_pairs := getattr(client, 'get_mkt_pairs', None):
+            get_mkt_pairs: Callable|None = getattr(
+                client,
+                'get_mkt_pairs',
+                None,
+            )
+            if not get_mkt_pairs:
+                log.warning(
+                    'No symbology cache `Pair` support for `{provider}`..\n'
+                    'Implement `Client.get_mkt_pairs()`!'
+                )
+                return self
 
             pairs: dict[str, Struct] = await get_mkt_pairs()
-                for bs_fqme, pair in pairs.items():
+            if not pairs:
+                log.warning(
+                    'No pairs from intial {provider!r} sym-cache request?\n\n'
+                    '`Client.get_mkt_pairs()` -> {pairs!r} ?'
+                )
+                return self
 
-                    # NOTE: every backend defined pair should
-                    # declare it's ns path for roundtrip
-                    # serialization lookup.
+            for bs_fqme, pair in pairs.items():
                 if not getattr(pair, 'ns_path', None):
+                    # XXX: every backend defined pair must declare
+                    # a `.ns_path: tractor.NamespacePath` to enable
+                    # roundtrip serialization lookup from a local
+                    # cache file.
                     raise TypeError(
                         f'Pair-struct for {self.mod.name} MUST define a '
-                            '`.ns_path: str`!\n'
-                            f'{pair}'
+                        '`.ns_path: str`!\n\n'
+                        f'{pair!r}'
                     )
 
                 entry = await self.mod.get_mkt_info(pair.bs_fqme)
@@ -195,12 +213,6 @@ class SymbologyCache(Struct):
                 pair,
             )
 
-            else:
-                log.warning(
-                    'No symbology cache `Pair` support for `{provider}`..\n'
-                    'Implement `Client.get_mkt_pairs()`!'
-                )
-
         return self
 
     @classmethod

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`.
 
 '''
 
@@ -377,44 +377,83 @@ 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.
+
 ) -> Callable[[str, dict], dict]:
+    '''
+    Init a json-RPC-over-websocket connection to the provided `url`.
+
+    A `json_rpc: Callable[[str, dict], dict` is delivered to the
+    caller for sending requests and a bg-`trio.Task` handles
+    processing of response msgs including error reporting/raising in
+    the parent/caller task.
+
+    '''
+    # 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
+        trio.open_nursery() as tn,
+        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]
 
+            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 +467,7 @@ async def open_jsonrpc_session(
             the server side.
 
             '''
+            nonlocal req_msgs
             async for msg in ws:
                 match msg:
                     case {
@@ -451,19 +491,28 @@ async def open_jsonrpc_session(
                         'params': _,
                     }:
                         log.debug(f'Recieved\n{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))
+                        # retreive orig request msg, set error
+                        # response in original "result" msg,
+                        # THEN FINALLY set the event to signal caller
+                        # to raise the error in the parent task.
+                        req_id: int = error['id']
+                        req_msg: dict = req_msgs[req_id]
+                        result: dict = rpc_results[req_id]
+                        result['error'] = error
+                        result['event'].set()
+                        log.error(
+                            f'JSONRPC request failed\n'
+                            f'req: {req_msg}\n'
+                            f'resp: {error}\n'
+                        )
 
                     case _:
                         log.warning(f'Unhandled JSON-RPC msg!?\n{msg}')
 
-        n.start_soon(recv_task)
+        tn.start_soon(recv_task)
         yield json_rpc
-        n.cancel_scope.cancel()
+        tn.cancel_scope.cancel()

piker/data/feed.py

@@ -786,7 +786,6 @@ async def install_brokerd_search(
 
 @acm
 async def maybe_open_feed(
-
     fqmes: list[str],
     loglevel: str | None = None,
 
@@ -840,13 +839,12 @@ async def maybe_open_feed(
 
 @acm
 async def open_feed(
-
     fqmes: list[str],
 
-    loglevel: str | None = None,
+    loglevel: str|None = None,
     allow_overruns: bool = True,
     start_stream: bool = True,
-    tick_throttle: float | None = None,  # Hz
+    tick_throttle: float|None = None,  # Hz
 
     allow_remote_ctl_ui: bool = False,
 

piker/data/flows.py

@@ -36,10 +36,10 @@ from ._sharedmem import (
     ShmArray,
     _Token,
 )
+from piker.accounting import MktPair
 
 if TYPE_CHECKING:
-    from ..accounting import MktPair
-    from .feed import Feed
+    from piker.data.feed import Feed
 
 
 class Flume(Struct):
@@ -82,7 +82,7 @@ class Flume(Struct):
 
     # TODO: do we need this really if we can pull the `Portal` from
     # ``tractor``'s internals?
-    feed: Feed | None = None
+    feed: Feed|None = None
 
     @property
     def rt_shm(self) -> ShmArray:

piker/data/validate.py

@@ -113,9 +113,9 @@ def validate_backend(
             )
             if ep is None:
                 log.warning(
-                    f'Provider backend {mod.name} is missing '
-                    f'{daemon_name} support :(\n'
-                    f'The following endpoint is missing: {name}'
+                    f'Provider backend {mod.name!r} is missing '
+                    f'{daemon_name!r} support?\n'
+                    f'|_module endpoint-func missing: {name!r}\n'
                 )
 
     inits: list[

piker/log.py

@@ -19,6 +19,10 @@ Log like a forester!
 """
 import logging
 import json
+import reprlib
+from typing import (
+    Callable,
+)
 
 import tractor
 from pygments import (
@@ -84,3 +88,29 @@ def colorize_json(
         # likeable styles: algol_nu, tango, monokai
         formatters.TerminalTrueColorFormatter(style=style)
     )
+
+
+# TODO, eventually defer to the version in `modden` once
+# it becomes a dep!
+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/_actor_runtime.py

@@ -119,6 +119,10 @@ 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=False,
+
                 **tractor_kwargs,
             ) as actor,
 

piker/storage/cli.py

@@ -386,6 +386,8 @@ def ldshm(
             open_annot_ctl() as actl,
         ):
             shm_df: pl.DataFrame | None = None
+            tf2aids: dict[float, dict] = {}
+
             for (
                 shmfile,
                 shm,
@@ -526,16 +528,17 @@ def ldshm(
                             new_df,
                             step_gaps,
                         )
-
                         # last chance manual overwrites in REPL
-                        await tractor.pause()
+                        # await tractor.pause()
                         assert aids
+                        tf2aids[period_s] = aids
 
                 else:
                     # allow interaction even when no ts problems.
-                    await tractor.pause()
-                    # assert not diff
+                    assert not diff
 
+            await tractor.pause()
+            log.info('Exiting TSP shm anal-izer!')
 
             if shm_df is None:
                 log.error(

piker/storage/nativedb.py

@@ -161,7 +161,13 @@ class NativeStorageClient:
 
     def index_files(self):
         for path in self._datadir.iterdir():
-            if path.name in {'borked', 'expired',}:
+            if (
+                path.is_dir()
+                or
+                '.parquet' not in str(path)
+                # or
+                # path.name in {'borked', 'expired',}
+            ):
                 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'
                 )
-                    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'
+                # 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()
                     )
+                    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,
@@ -565,22 +612,27 @@ 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'
                     f'{next_start_dt} -> {last_start_dt}'
                 )
 
-                # always drop the src asset token for
+                # NOTE, always drop the src asset token for
                 # non-currency-pair like market types (for now)
+                #
+                # THAT IS, for now our table key schema is NOT
+                # including the dst[/src] source asset token. SO,
+                # 'tsla.nasdaq.ib' over 'tsla/usd.nasdaq.ib' for
+                # historical reasons ONLY.
                 if mkt.dst.atype not in {
                     '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.
                     col_sym_key: str = mkt.get_fqme(
                         delim_char='',
                         without_src=True,
@@ -685,7 +737,7 @@ 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 +960,8 @@ 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 +972,6 @@ async def tsdb_backfill(
                 timeframe,
                 config,
             )
-
             tsdb_entry: tuple = await load_tsdb_hist(
                 storage,
                 mkt,
@@ -947,6 +1000,25 @@ 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 +1049,7 @@ 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,

piker/tsp/_anal.py

@@ -616,6 +616,18 @@ def detect_price_gaps(
     # ])
     ...
 
+# TODO: probably just use the null_segs impl above?
+def detect_vlm_gaps(
+    df: pl.DataFrame,
+    col: str = 'volume',
+
+) -> pl.DataFrame:
+
+    vnull: pl.DataFrame = w_dts.filter(
+        pl.col(col) == 0
+    )
+    return vnull
+
 
 def dedupe(
     src_df: pl.DataFrame,
@@ -626,7 +638,6 @@ def dedupe(
 
 ) -> tuple[
     pl.DataFrame,  # with dts
-    pl.DataFrame,  # gaps
     pl.DataFrame,  # with deduplicated dts (aka gap/repeat removal)
     int,  # len diff between input and deduped
 ]:
@@ -639,19 +650,22 @@ def dedupe(
     '''
     wdts: pl.DataFrame = with_dts(src_df)
 
-    # maybe sort on any time field
-    if sort:
-        wdts = wdts.sort(by='time')
-        # TODO: detect out-of-order segments which were corrected!
-        # -[ ] report in log msg
-        # -[ ] possibly return segment sections which were moved?
+    deduped = wdts
 
     # remove duplicated datetime samples/sections
     deduped: pl.DataFrame = wdts.unique(
-        subset=['dt'],
+        # subset=['dt'],
+        subset=['time'],
         maintain_order=True,
     )
 
+    # maybe sort on any time field
+    if sort:
+        deduped = deduped.sort(by='time')
+        # TODO: detect out-of-order segments which were corrected!
+        # -[ ] report in log msg
+        # -[ ] possibly return segment sections which were moved?
+
     diff: int = (
         wdts.height
         -

piker/types.py

@@ -21,230 +21,4 @@ Extensions to built-in or (heavily used but 3rd party) friend-lib
 types.
 
 '''
-from __future__ import annotations
-from collections import UserList
-from pprint import (
-    saferepr,
-)
-from typing import Any
-
-from msgspec import (
-    msgpack,
-    Struct as _Struct,
-    structs,
-)
-
-
-class DiffDump(UserList):
-    '''
-    Very simple list delegator that repr() dumps (presumed) tuple
-    elements of the form `tuple[str, Any, Any]` in a nice
-    multi-line readable form for analyzing `Struct` diffs.
-
-    '''
-    def __repr__(self) -> str:
-        if not len(self):
-            return super().__repr__()
-
-        # format by displaying item pair's ``repr()`` on multiple,
-        # indented lines such that they are more easily visually
-        # comparable when printed to console when printed to
-        # console.
-        repstr: str = '[\n'
-        for k, left, right in self:
-            repstr += (
-                f'({k},\n'
-                f'\t{repr(left)},\n'
-                f'\t{repr(right)},\n'
-                ')\n'
-            )
-        repstr += ']\n'
-        return repstr
-
-
-class Struct(
-    _Struct,
-
-    # https://jcristharif.com/msgspec/structs.html#tagged-unions
-    # tag='pikerstruct',
-    # tag=True,
-):
-    '''
-    A "human friendlier" (aka repl buddy) struct subtype.
-
-    '''
-    def _sin_props(self) -> Iterator[
-        tuple[
-            structs.FieldIinfo,
-            str,
-            Any,
-        ]
-    ]:
-        '''
-        Iterate over all non-@property fields of this struct.
-
-        '''
-        fi: structs.FieldInfo
-        for fi in structs.fields(self):
-            key: str = fi.name
-            val: Any = getattr(self, key)
-            yield fi, key, val
-
-    def to_dict(
-        self,
-        include_non_members: bool = True,
-
-    ) -> dict:
-        '''
-        Like it sounds.. direct delegation to:
-        https://jcristharif.com/msgspec/api.html#msgspec.structs.asdict
-
-        BUT, by default we pop all non-member (aka not defined as
-        struct fields) fields by default.
-
-        '''
-        asdict: dict = structs.asdict(self)
-        if include_non_members:
-            return asdict
-
-        # only return a dict of the struct members
-        # which were provided as input, NOT anything
-        # added as type-defined `@property` methods!
-        sin_props: dict = {}
-        fi: structs.FieldInfo
-        for fi, k, v in self._sin_props():
-            sin_props[k] = asdict[k]
-
-        return sin_props
-
-    def pformat(
-        self,
-        field_indent: int = 2,
-        indent: int = 0,
-
-    ) -> str:
-        '''
-        Recursion-safe `pprint.pformat()` style formatting of
-        a `msgspec.Struct` for sane reading by a human using a REPL.
-
-        '''
-        # global whitespace indent
-        ws: str = ' '*indent
-
-        # field whitespace indent
-        field_ws: str = ' '*(field_indent + indent)
-
-        # qtn: str = ws + self.__class__.__qualname__
-        qtn: str = self.__class__.__qualname__
-
-        obj_str: str = ''  # accumulator
-        fi: structs.FieldInfo
-        k: str
-        v: Any
-        for fi, k, v in self._sin_props():
-
-            # TODO: how can we prefer `Literal['option1',  'option2,
-            # ..]` over .__name__ == `Literal` but still get only the
-            # latter for simple types like `str | int | None` etc..?
-            ft: type = fi.type
-            typ_name: str = getattr(ft, '__name__', str(ft))
-
-            # recurse to get sub-struct's `.pformat()` output Bo
-            if isinstance(v, Struct):
-                val_str: str =  v.pformat(
-                    indent=field_indent + indent,
-                    field_indent=indent + field_indent,
-                )
-
-            else:  # the `pprint` recursion-safe format:
-                # https://docs.python.org/3.11/library/pprint.html#pprint.saferepr
-                val_str: str = saferepr(v)
-
-            obj_str += (field_ws + f'{k}: {typ_name} = {val_str},\n')
-
-        return (
-            f'{qtn}(\n'
-            f'{obj_str}'
-            f'{ws})'
-        )
-
-    # TODO: use a pprint.PrettyPrinter instance around ONLY rendering
-    # inside a known tty?
-    # def __repr__(self) -> str:
-    #     ...
-
-    # __str__ = __repr__ = pformat
-    __repr__ = pformat
-
-    def copy(
-        self,
-        update: dict | None = None,
-
-    ) -> Struct:
-        '''
-        Validate-typecast all self defined fields, return a copy of
-        us with all such fields.
-
-        NOTE: This is kinda like the default behaviour in
-        `pydantic.BaseModel` except a copy of the object is
-        returned making it compat with `frozen=True`.
-
-        '''
-        if update:
-            for k, v in update.items():
-                setattr(self, k, v)
-
-        # NOTE: roundtrip serialize to validate
-        # - enode to msgpack binary format,
-        # - decode that back to a struct.
-        return msgpack.Decoder(type=type(self)).decode(
-            msgpack.Encoder().encode(self)
-        )
-
-    def typecast(
-        self,
-
-        # TODO: allow only casting a named subset?
-        # fields: set[str] | None = None,
-
-    ) -> None:
-        '''
-        Cast all fields using their declared type annotations
-        (kinda like what `pydantic` does by default).
-
-        NOTE: this of course won't work on frozen types, use
-        ``.copy()`` above in such cases.
-
-        '''
-        # https://jcristharif.com/msgspec/api.html#msgspec.structs.fields
-        fi: structs.FieldInfo
-        for fi in structs.fields(self):
-            setattr(
-                self,
-                fi.name,
-                fi.type(getattr(self, fi.name)),
-            )
-
-    def __sub__(
-        self,
-        other: Struct,
-
-    ) -> DiffDump[tuple[str, Any, Any]]:
-        '''
-        Compare fields/items key-wise and return a ``DiffDump``
-        for easy visual REPL comparison B)
-
-        '''
-        diffs: DiffDump[tuple[str, Any, Any]] = DiffDump()
-        for fi in structs.fields(self):
-            attr_name: str = fi.name
-            ours: Any = getattr(self, attr_name)
-            theirs: Any = getattr(other, attr_name)
-            if ours != theirs:
-                diffs.append((
-                    attr_name,
-                    ours,
-                    theirs,
-                ))
-
-        return diffs
+from tractor.msg import Struct as Struct