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

- use more compact optional value style with `|`-union
- fix `.flows` typing-only import since we need `MktPair` to be
  immediately defined for use on a `msgspec.Struct` field.
- more "tree-like" warning msg in `.validate()` reporting.

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 piker.log import get_logger
-from ..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

@@ -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]
+    tickers: list[str]
-) -> Dict[str, Dict[str, Any]]:
+
-    """Return quotes dict for ``tickers``.
+) -> 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,
+    date: str|None = None,
-) -> Dict[str, Dict[str, Dict[str, Any]]]:
+) -> dict[str, dict[str, dict[str, Any]]]:
-    """Return option chain for ``symbol`` for ``date``.
+    '''
+    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]]]:
+) -> dict[str, dict[str, dict[str, Any]]]:
-    """Return option contracts (all expiries) for ``symbol``.
+    '''
-    """
+    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/clearing/_paper_engine.py

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

piker/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
+            for bs_fqme, pair in pairs.items():
-                    # 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'
+                        '`.ns_path: str`!\n\n'
-                            f'{pair}'
+                        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
+JSONRPC response-request style machinery for transparent multiplexing
-over a NoBsWs.
+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,
+    msg_recv_timeout: float = float('inf'),
-    request_hook: Optional[Callable] = None,
+    # ^NOTE, since only `deribit` is using this jsonrpc stuff atm
-    error_hook: Optional[Callable] = None,
+    # 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,
+        trio.open_nursery() as tn,
-        open_autorecon_ws(url) as ws
+        open_autorecon_ws(
+            url=url,
+            msg_recv_timeout=msg_recv_timeout,
+        ) as ws
     ):
-        rpc_id: Iterable = count(start_id)
+        rpc_id: Iterable[int] = count(start_id)
         rpc_results: dict[int, dict] = {}
 
-        async def json_rpc(method: str, params: dict) -> dict:
+        async def json_rpc(
+            method: str,
+            params: dict,
+        ) -> dict:
             '''
             perform a json rpc call and wait for the result, raise exception in
             case of error field present on response
             '''
+            nonlocal req_msgs
+
+            req_id: int = next(rpc_id)
             msg = {
                 'jsonrpc': '2.0',
-                'id': next(rpc_id),
+                'id': req_id,
                 'method': method,
                 'params': params
             }
             _id = msg['id']
 
-            rpc_results[_id] = {
+            result = rpc_results[_id] = {
                 'result': None,
-                'event': trio.Event()
+                'error': None,
+                'event': trio.Event(),  # signal caller resp arrived
             }
+            req_msgs[_id] = msg
 
             await ws.send_msg(msg)
 
+            # wait for reponse before unblocking requester code
             await rpc_results[_id]['event'].wait()
 
-            ret = rpc_results[_id]['result']
+            if (maybe_result := result['result']):
-
+                ret = maybe_result
                 del rpc_results[_id]
 
+            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}')
+                        # retreive orig request msg, set error
-                        if error_hook:
+                        # response in original "result" msg,
-                            await error_hook(response_type(**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 piker.data.feed import Feed
-    from .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'Provider backend {mod.name!r} is missing '
-                    f'{daemon_name} support :(\n'
+                    f'{daemon_name!r} support?\n'
-                    f'The following endpoint is missing: {name}'
+                    f'|_module endpoint-func missing: {name!r}\n'
                 )
 
     inits: list[

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
+            # TODO: per-provider default history-durations?
-            # limits inside a [storage] section in conf.toml?
+            # -[ ] inside the `open_history_client()` config allow
-            # when no tsdb "last datum" is provided, we just load
+            #    declaring the history duration limits instead of
-            # some near-term history.
+            #    guessing and/or applying the same limits to all?
-            # periods = {
+            #
-            #     1: {'days': 1},
+            # -[ ] allow declaring (default) per-provider backfill
-            #     60: {'days': 14},
+            #     limits inside a [storage] sub-section in conf.toml?
-            # }
+            #
-
+            # NOTE, when no tsdb "last datum" is provided, we just
-            # do a decently sized backfill and load it into storage.
+            # 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:
+                orig_last_start_dt: datetime = last_start_dt
-                # - frame in the middle of a legit venue gap
+                gap_report: str = (
-                # - history actually began at the `last_start_dt`
+                    f'EMPTY FRAME for `end_dt: {last_start_dt}`?\n'
-                # - some other unknown error (ib blocking the
+                    f'{mod.name} -> tf@fqme: {timeframe}@{mkt.fqme}\n'
-                #   history bc they don't want you seeing how they
+                    f'last_start_dt: {orig_last_start_dt}\n\n'
-                #   cucked all the tinas..)
+                    f'bf_until: {backfill_until_dt}\n'
-                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()
                 )
-                    log.warning(
+                # EMPTY FRAME signal with 3 (likely) causes:
-                        f'{mod.name} -> EMPTY FRAME for end_dt?\n'
+                #
-                        f'tf@fqme: {timeframe}@{mkt.fqme}\n'
+                # 1. range contains legit gap in venue history
-                        'bf_until <- last_start_dt:\n'
+                # 2. history actually (edge case) **began** at the
-                        f'{backfill_until_dt} <- {last_start_dt}\n'
+                #    value `last_start_dt`
-                        f'Decrementing `end_dt` by {dur} and retry..\n'
+                # 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
+                else:
-            except DataUnavailable:
+                    # await tractor.pause()
-                log.warning(
+                    raise DataUnavailable(gap_report)
-                    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'
-                )
 
-                # ugh, what's a better way?
+            # broker says there never was or is no more history to pull
-                # TODO: fwiw, we probably want a way to signal a throttle
+            except DataUnavailable as due:
-                # condition (eg. with ib) so that we can halt the
+                message: str = due.args[0]
-                # request loop until the condition is resolved?
+                log.warning(
-                if timeframe > 1:
+                    f'Provider {mod.name!r} halted backfill due to,\n\n'
-                    await tractor.pause()
+
+                    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
+            assert time[-1] == next_end_dt.timestamp()
-            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
-            expected_frame_size_s: float = frame_size_s + timeframe
+            recv_frame_dur: Duration = (
-            if frame_time_diff_s > expected_frame_size_s:
+                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'{timeframe}s-series {reason} detected!\n'
-                    f'last_start_dt: {last_start_dt}\n'
+                    f'fqme: {mkt.fqme}\n'
-                    f'diff: {diff}\n'
+                    f'last_start_dt: {last_start_dt}\n\n'
-                    f'frame_time_diff_s: {frame_time_diff_s}\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
+    deduped = wdts
-    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?
 
     # 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
         -