`.brokers.cli`: module type and todo for `--pdb` flag to NOT src from sub-cmd

piker/accounting/_pos.py

@@ -30,8 +30,7 @@ from types import ModuleType
 from typing import (
     Any,
     Iterator,
-    Generator,
+    Generator
-    TYPE_CHECKING,
 )
 
 import pendulum
@@ -60,10 +59,8 @@ from ..clearing._messages import (
     BrokerdPosition,
 )
 from piker.types import Struct
-from piker.log import get_logger
-
-if TYPE_CHECKING:
 from piker.data._symcache import SymbologyCache
+from ..log import get_logger
 
 log = get_logger(__name__)
 
@@ -496,17 +493,6 @@ 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
@@ -549,32 +535,11 @@ 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..)
-                if (
+                mkt = _mktmap_table[fqme]
-                    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)):
 
@@ -691,7 +656,7 @@ 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/clearing/_client.py

@@ -168,6 +168,7 @@ class OrderClient(Struct):
 
 
 async def relay_orders_from_sync_code(
+
     client: OrderClient,
     symbol_key: str,
     to_ems_stream: tractor.MsgStream,
@@ -241,11 +242,6 @@ 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

@@ -653,11 +653,7 @@ 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,
@@ -720,7 +716,7 @@ class Router(Struct):
             subs = self.subscribers[sub_key]
 
         sent_some: bool = False
-        for client_stream in subs.copy():
+        for client_stream in subs:
             try:
                 await client_stream.send(msg)
                 sent_some = True
@@ -1014,10 +1010,6 @@ 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

@@ -297,8 +297,6 @@ 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,
@@ -655,7 +653,6 @@ 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

@@ -30,7 +30,6 @@ 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/data/_sampling.py

@@ -95,12 +95,6 @@ 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.
@@ -264,15 +258,14 @@ class Sampler:
         subs: set
         last_ts, subs = pair
 
-        # NOTE, for debugging pub-sub issues
+        task = trio.lowlevel.current_task()
-        # task = trio.lowlevel.current_task()
+        log.debug(
-        # log.debug(
+            f'SUBS {self.subscribers}\n'
-        #     f'AlL-SUBS@{period_s!r}: {self.subscribers}\n'
+            f'PAIR {pair}\n'
-        #     f'PAIR: {pair}\n'
+            f'TASK: {task}: {id(task)}\n'
-        #     f'TASK: {task}: {id(task)}\n'
+            f'broadcasting {period_s} -> {last_ts}\n'
-        #     f'broadcasting {period_s} -> {last_ts}\n'
             # f'consumers: {subs}'
-        # )
+        )
         borked: set[MsgStream] = set()
         sent: set[MsgStream] = set()
         while True:
@@ -289,11 +282,12 @@ class Sampler:
                         await stream.send(msg)
                         sent.add(stream)
 
-                    except self.bcast_errors as err:
+                    except (
+                        trio.BrokenResourceError,
+                        trio.ClosedResourceError
+                    ):
                         log.error(
-                            f'Connection dropped for IPC ctx\n'
+                            f'{stream._ctx.chan.uid} dropped connection'
-                            f'{stream._ctx}\n\n'
-                            f'Due to {type(err)}'
                         )
                         borked.add(stream)
                 else:
@@ -400,8 +394,7 @@ async def register_with_sampler(
                 finally:
                     if (
                         sub_for_broadcasts
-                        and
+                        and subs
-                        subs
                     ):
                         try:
                             subs.remove(stream)
@@ -568,7 +561,8 @@ async def open_sample_stream(
 
 
 async def sample_and_broadcast(
-    bus: _FeedsBus,
+
+    bus: _FeedsBus,  # noqa
     rt_shm: ShmArray,
     hist_shm: ShmArray,
     quote_stream: trio.abc.ReceiveChannel,
@@ -588,33 +582,11 @@ 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)
 
-        # XXX WARNING XXX only enable for debugging bc ow can cost
+        # TODO: ``numba`` this!
-        # 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
@@ -687,21 +659,6 @@ 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
@@ -771,14 +728,18 @@ async def sample_and_broadcast(
                         if lags > 10:
                             await tractor.pause()
 
-                except Sampler.bcast_errors as ipc_err:
+                except (
+                    trio.BrokenResourceError,
+                    trio.ClosedResourceError,
+                    trio.EndOfChannel,
+                ):
                     ctx: Context = ipc._ctx
                     chan: Channel = ctx.chan
                     if ctx:
                         log.warning(
-                            f'Dropped `brokerd`-feed for {broker_symbol!r} due to,\n'
+                            'Dropped `brokerd`-quotes-feed connection:\n'
-                            f'x>) {ctx.cid}@{chan.uid}'
+                            f'{broker_symbol}:'
-                            f'|_{ipc_err!r}\n\n'
+                            f'{ctx.cid}@{chan.uid}'
                         )
                     if sub.throttle_rate:
                         assert ipc._closed
@@ -795,11 +756,12 @@ async def sample_and_broadcast(
 
 
 async def uniform_rate_send(
+
     rate: float,
     quote_stream: trio.abc.ReceiveChannel,
     stream: MsgStream,
 
-    task_status: TaskStatus[None] = trio.TASK_STATUS_IGNORED,
+    task_status: TaskStatus = trio.TASK_STATUS_IGNORED,
 
 ) -> None:
     '''
@@ -817,16 +779,13 @@ async def uniform_rate_send(
     https://gist.github.com/njsmith/7ea44ec07e901cb78ebe1dd8dd846cb9
 
     '''
-    # ?TODO? dynamically compute the **actual** approx overhead latency per cycle
+    # TODO: compute the approx overhead latency per cycle
-    # instead of this magic # bidinezz?
+    left_to_sleep = throttle_period = 1/rate - 0.000616
-    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: float = time.time()
+    last_send = time.time()
-    diff: float = 0
+    diff = 0
 
     task_status.started()
     ticks_by_type: dict[
@@ -837,28 +796,22 @@ 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: float = throttle_period - diff
+        left_to_sleep = 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(
+                    log.exception(f"feed for {stream} ended?")
-                        f'Live stream for feed for ended?\n'
-                        f'<=c\n'
-                        f'  |_[{stream!r}\n'
-                    )
                     break
 
-                diff: float = time.time() - last_send
+                diff = time.time() - last_send
 
                 if not first_quote:
-                    first_quote: float = last_quote
+                    first_quote = last_quote
                     # first_quote['tbt'] = ticks_by_type
 
                 if (throttle_period - diff) > 0:
@@ -919,9 +872,7 @@ async def uniform_rate_send(
         # TODO: now if only we could sync this to the display
         # rate timing exactly lul
         try:
-            await stream.send({
+            await stream.send({sym: first_quote})
-                sym: first_quote
-            })
         except tractor.RemoteActorError as rme:
             if rme.type is not tractor._exceptions.StreamOverrun:
                 raise
@@ -932,28 +883,19 @@ async def uniform_rate_send(
                 f'{sym}:{ctx.cid}@{chan.uid}'
             )
 
-        # NOTE: any of these can be raised by `tractor`'s IPC
+        except (
+            # 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!
-        except (
+            trio.ClosedResourceError,
+            trio.BrokenResourceError,
             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(
+            log.warning(f'{stream} closed')
-                        f'{stream} closed due to,\n'
-                        f'{ipc_err!r}'
-                    )
-
             await stream.aclose()
             return
 

piker/data/_symcache.py

@@ -31,7 +31,6 @@ from pathlib import Path
 from pprint import pformat
 from typing import (
     Any,
-    Callable,
     Sequence,
     Hashable,
     TYPE_CHECKING,
@@ -57,7 +56,7 @@ from piker.brokers import (
 )
 
 if TYPE_CHECKING:
-    from piker.accounting import (
+    from ..accounting import (
         Asset,
         MktPair,
     )
@@ -150,36 +149,19 @@ class SymbologyCache(Struct):
                     'Implement `Client.get_assets()`!'
                 )
 
-            get_mkt_pairs: Callable|None = getattr(
+            if get_mkt_pairs := getattr(client, 'get_mkt_pairs', None):
-                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()
-            if not pairs:
-                log.warning(
-                    'No pairs from intial {provider!r} sym-cache request?\n\n'
-                    '`Client.get_mkt_pairs()` -> {pairs!r} ?'
-                )
-                return self
-
                 for bs_fqme, pair in pairs.items():
+
+                    # NOTE: every backend defined pair should
+                    # declare it's ns path for roundtrip
+                    # serialization lookup.
                     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\n'
+                            '`.ns_path: str`!\n'
-                        f'{pair!r}'
+                            f'{pair}'
                         )
 
                     entry = await self.mod.get_mkt_info(pair.bs_fqme)
@@ -213,6 +195,12 @@ 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('Retrying connection')
+            log.exception(f'Retrying connection')
 
         # ws & nursery block ends
 
@@ -359,8 +359,8 @@ async def open_autorecon_ws(
 
 
 '''
-JSONRPC response-request style machinery for transparent multiplexing
+JSONRPC response-request style machinery for transparent multiplexing of msgs
-of msgs over a `NoBsWs`.
+over a NoBsWs.
 
 '''
 
@@ -377,82 +377,43 @@ async def open_jsonrpc_session(
     url: str,
     start_id: int = 0,
     response_type: type = JSONRPCResult,
-    msg_recv_timeout: float = float('inf'),
+    request_type: Optional[type] = None,
-    # ^NOTE, since only `deribit` is using this jsonrpc stuff atm
+    request_hook: Optional[Callable] = None,
-    # and options mkts are generally "slow moving"..
+    error_hook: Optional[Callable] = None,
-    #
-    # 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 tn,
+        trio.open_nursery() as n,
-        open_autorecon_ws(
+        open_autorecon_ws(url) as ws
-            url=url,
-            msg_recv_timeout=msg_recv_timeout,
-        ) as ws
     ):
-        rpc_id: Iterable[int] = count(start_id)
+        rpc_id: Iterable = count(start_id)
         rpc_results: dict[int, dict] = {}
 
-        async def json_rpc(
+        async def json_rpc(method: str, params: dict) -> dict:
-            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': req_id,
+                'id': next(rpc_id),
                 'method': method,
                 'params': params
             }
             _id = msg['id']
 
-            result = rpc_results[_id] = {
+            rpc_results[_id] = {
                 'result': None,
-                'error': None,
+                'event': trio.Event()
-                '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()
 
-            if (maybe_result := result['result']):
+            ret = rpc_results[_id]['result']
-                ret = maybe_result
-                del rpc_results[_id]
 
-            else:
+            del rpc_results[_id]
-                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))
@@ -467,7 +428,6 @@ async def open_jsonrpc_session(
             the server side.
 
             '''
-            nonlocal req_msgs
             async for msg in ws:
                 match msg:
                     case {
@@ -491,28 +451,19 @@ async def open_jsonrpc_session(
                         'params': _,
                     }:
                         log.debug(f'Recieved\n{msg}')
+                        if request_hook:
+                            await request_hook(request_type(**msg))
 
                     case {
                         'error': error
                     }:
-                        # retreive orig request msg, set error
+                        log.warning(f'Recieved\n{error}')
-                        # response in original "result" msg,
+                        if error_hook:
-                        # THEN FINALLY set the event to signal caller
+                            await error_hook(response_type(**msg))
-                        # 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}')
 
-        tn.start_soon(recv_task)
+        n.start_soon(recv_task)
         yield json_rpc
-        tn.cancel_scope.cancel()
+        n.cancel_scope.cancel()

piker/data/feed.py

@@ -786,6 +786,7 @@ async def install_brokerd_search(
 
 @acm
 async def maybe_open_feed(
+
     fqmes: list[str],
     loglevel: str | None = None,
 
@@ -839,6 +840,7 @@ async def maybe_open_feed(
 
 @acm
 async def open_feed(
+
     fqmes: list[str],
 
     loglevel: str | None = None,

piker/data/flows.py

@@ -36,10 +36,10 @@ from ._sharedmem import (
     ShmArray,
     _Token,
 )
-from piker.accounting import MktPair
 
 if TYPE_CHECKING:
-    from piker.data.feed import Feed
+    from ..accounting import MktPair
+    from .feed import Feed
 
 
 class Flume(Struct):

piker/data/validate.py

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

piker/log.py

@@ -19,10 +19,6 @@ Log like a forester!
 """
 import logging
 import json
-import reprlib
-from typing import (
-    Callable,
-)
 
 import tractor
 from pygments import (
@@ -88,29 +84,3 @@ 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

@@ -119,10 +119,6 @@ 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

@@ -386,8 +386,6 @@ def ldshm(
             open_annot_ctl() as actl,
         ):
             shm_df: pl.DataFrame | None = None
-            tf2aids: dict[float, dict] = {}
-
             for (
                 shmfile,
                 shm,
@@ -528,17 +526,16 @@ 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.
-                    assert not diff
-
                     await tractor.pause()
-            log.info('Exiting TSP shm anal-izer!')
+                    # assert not diff
+
 
             if shm_df is None:
                 log.error(

piker/storage/nativedb.py

@@ -161,13 +161,7 @@ class NativeStorageClient:
 
     def index_files(self):
         for path in self._datadir.iterdir():
-            if (
+            if path.name in {'borked', 'expired',}:
-                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

@@ -44,10 +44,8 @@ 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
@@ -216,8 +214,7 @@ async def maybe_fill_null_segments(
         # pair, immediately stop backfilling?
         if (
             start_dt
-            and
+            and end_dt < start_dt
-            end_dt < start_dt
         ):
             await tractor.pause()
             break
@@ -265,7 +262,6 @@ async def maybe_fill_null_segments(
         except tractor.ContextCancelled:
             # log.exception
             await tractor.pause()
-            raise
 
     null_segs_detected.set()
     # RECHECK for more null-gaps
@@ -353,7 +349,7 @@ async def maybe_fill_null_segments(
 
 async def start_backfill(
     get_hist,
-    def_frame_duration: Duration,
+    frame_types: dict[str, Duration] | None,
     mod: ModuleType,
     mkt: MktPair,
     shm: ShmArray,
@@ -383,23 +379,22 @@ async def start_backfill(
         update_start_on_prepend: bool = False
         if backfill_until_dt is None:
 
-            # TODO: per-provider default history-durations?
+            # TODO: drop this right and just expose the backfill
-            # -[ ] inside the `open_history_client()` config allow
+            # limits inside a [storage] section in conf.toml?
-            #    declaring the history duration limits instead of
+            # when no tsdb "last datum" is provided, we just load
-            #    guessing and/or applying the same limits to all?
+            # some near-term history.
-            #
+            # periods = {
-            # -[ ] allow declaring (default) per-provider backfill
+            #     1: {'days': 1},
-            #     limits inside a [storage] sub-section in conf.toml?
+            #     60: {'days': 14},
-            #
+            # }
-            # NOTE, when no tsdb "last datum" is provided, we just
+
-            # load some near-term history by presuming a "decently
+            # do a decently sized backfill and load it into storage.
-            # 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: bool = True
+            update_start_on_prepend = True
 
             # NOTE: manually set the "latest" datetime which we intend to
             # backfill history "until" so as to adhere to the history
@@ -421,6 +416,7 @@ async def start_backfill(
                 f'backfill_until_dt: {backfill_until_dt}\n'
                 f'last_start_dt: {last_start_dt}\n'
             )
+
             try:
                 (
                     array,
@@ -430,114 +426,71 @@ async def start_backfill(
                     timeframe,
                     end_dt=last_start_dt,
                 )
+
             except NoData as _daterr:
-                orig_last_start_dt: datetime = last_start_dt
+                # 3 cases:
-                gap_report: str = (
+                # - frame in the middle of a legit venue gap
-                    f'EMPTY FRAME for `end_dt: {last_start_dt}`?\n'
+                # - history actually began at the `last_start_dt`
-                    f'{mod.name} -> tf@fqme: {timeframe}@{mkt.fqme}\n'
+                # - some other unknown error (ib blocking the
-                    f'last_start_dt: {orig_last_start_dt}\n\n'
+                #   history bc they don't want you seeing how they
-                    f'bf_until: {backfill_until_dt}\n'
+                #   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()
                     )
-                # EMPTY FRAME signal with 3 (likely) causes:
+                    log.warning(
-                #
+                        f'{mod.name} -> EMPTY FRAME for end_dt?\n'
-                # 1. range contains legit gap in venue history
+                        f'tf@fqme: {timeframe}@{mkt.fqme}\n'
-                # 2. history actually (edge case) **began** at the
+                        'bf_until <- last_start_dt:\n'
-                #    value `last_start_dt`
+                        f'{backfill_until_dt} <- {last_start_dt}\n'
-                # 3. some other unknown error (ib blocking the
+                        f'Decrementing `end_dt` by {dur} and retry..\n'
-                #    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
 
-                else:
-                    # await tractor.pause()
-                    raise DataUnavailable(gap_report)
-
             # broker says there never was or is no more history to pull
-            except DataUnavailable as due:
+            except DataUnavailable:
-                message: str = due.args[0]
                 log.warning(
-                    f'Provider {mod.name!r} halted backfill due to,\n\n'
+                    f'NO-MORE-DATA in range?\n'
-
+                    f'`{mod.name}` halted history:\n'
-                    f'{message}\n'
+                    f'tf@fqme: {timeframe}@{mkt.fqme}\n'
-
+                    'bf_until <- last_start_dt:\n'
-                    f'fqme: {mkt.fqme}\n'
+                    f'{backfill_until_dt} <- {last_start_dt}\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
+                # ugh, what's a better way?
-                # this right!?
+                # TODO: fwiw, we probably want a way to signal a throttle
-                # -[ ] in the `ib` case we could maybe offer some way
+                # condition (eg. with ib) so that we can halt the
-                #     to halt the request loop until the condition is
+                # request loop until the condition is resolved?
-                #     resolved or should the backend be entirely in
+                if timeframe > 1:
-                #     charge of solving such faults? yes, right?
+                    await tractor.pause()
                 return
 
-            time: np.ndarray = array['time']
             assert (
-                time[0]
+                array['time'][0]
                 ==
                 next_start_dt.timestamp()
             )
 
-            assert time[-1] == next_end_dt.timestamp()
+            diff = last_start_dt - next_start_dt
-
+            frame_time_diff_s = diff.seconds
-            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
-            recv_frame_dur: Duration = (
+            expected_frame_size_s: float = frame_size_s + timeframe
-                from_timestamp(array[-1]['time'])
+            if frame_time_diff_s > expected_frame_size_s:
-                -
+
-                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(
-                    f'{timeframe}s-series {reason} detected!\n'
+                    'GAP DETECTED:\n'
-                    f'fqme: {mkt.fqme}\n'
+                    f'last_start_dt: {last_start_dt}\n'
-                    f'last_start_dt: {last_start_dt}\n\n'
+                    f'diff: {diff}\n'
-                    f'recv interval: {recv_frame_dur}\n'
+                    f'frame_time_diff_s: {frame_time_diff_s}\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,
@@ -612,27 +565,22 @@ async def start_backfill(
             # long-term storage.
             if (
                 storage is not None
-                and
+                and write_tsdb
-                write_tsdb
             ):
                 log.info(
                     f'Writing {ln} frame to storage:\n'
                     f'{next_start_dt} -> {last_start_dt}'
                 )
 
-                # NOTE, always drop the src asset token for
+                # 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,
@@ -737,7 +685,7 @@ async def back_load_from_tsdb(
         last_tsdb_dt
         and latest_start_dt
     ):
-        backfilled_size_s: Duration = (
+        backfilled_size_s = (
             latest_start_dt - last_tsdb_dt
         ).seconds
         # if the shm buffer len is not large enough to contain
@@ -960,8 +908,6 @@ 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(
@@ -972,6 +918,7 @@ async def tsdb_backfill(
                 timeframe,
                 config,
             )
+
             tsdb_entry: tuple = await load_tsdb_hist(
                 storage,
                 mkt,
@@ -1000,25 +947,6 @@ 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
@@ -1049,7 +977,7 @@ async def tsdb_backfill(
                     partial(
                         start_backfill,
                         get_hist=get_hist,
-                        def_frame_duration=def_frame_size,
+                        frame_types=config.get('frame_types', None),
                         mod=mod,
                         mkt=mkt,
                         shm=shm,

piker/tsp/_anal.py

@@ -616,18 +616,6 @@ 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,
@@ -638,6 +626,7 @@ 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
 ]:
@@ -650,22 +639,19 @@ def dedupe(
     '''
     wdts: pl.DataFrame = with_dts(src_df)
 
-    deduped = wdts
-
-    # remove duplicated datetime samples/sections
-    deduped: pl.DataFrame = wdts.unique(
-        # subset=['dt'],
-        subset=['time'],
-        maintain_order=True,
-    )
-
     # maybe sort on any time field
     if sort:
-        deduped = deduped.sort(by='time')
+        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?
 
+    # remove duplicated datetime samples/sections
+    deduped: pl.DataFrame = wdts.unique(
+        subset=['dt'],
+        maintain_order=True,
+    )
+
     diff: int = (
         wdts.height
         -

piker/types.py

@@ -21,4 +21,230 @@ Extensions to built-in or (heavily used but 3rd party) friend-lib
 types.
 
 '''
-from tractor.msg import Struct as Struct
+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