feat(R03): unify model routing and centralise the provider catalogue

EPIC R03 (Team Duy) — Model Providers & Routing. All six tasks done.

R03-T02 — Provider catalogue
  domain/models/provider_descriptor.py     ProviderDescriptor (frozen), WireProtocol, AuthKind
  infrastructure/providers/provider_registry.py
                                           thread-safe registry: id/alias lookup, dynamic
                                           lookup by model id, adapter selection by protocol
  providers/factory.py                     drops its own _REGISTRY table and delegates to the
                                           registry, still raising ProviderError for callers

R03-T03 — RoutingApplicationService (pure Python, 4 modes)
  application/model_routing/routing_models.py
                                           RoutingMode (off/auto/manual/fallback),
                                           RoutingRequest (immutable snapshot), RouteEvaluation,
                                           RoutingOutcome
  application/model_routing/routing_application_service.py
                                           the single decision flow, reached through two narrow
                                           ports plus a caller-supplied confirm callback, so no
                                           Qt import is needed
  application/model_routing/core_routing_adapter.py
                                           binds the ports to core/routing and AppContext

  Fallback is a new resilience mode: keep the selected model while it can serve the turn,
  re-route only when it cannot. Wired end to end through config.py, state.py,
  ui/routing_toggle.py and i18n.py (EN/JA/VI).

R03-T04 / T05 — Remove the duplicated routing flow
  ui/chat_panel.py (#L638), ui/co4e_tab.py, ui/folder_tab.py each drop ~35 lines of copied
  logic and call the shared service; the widgets now only build a RoutingRequest, host the
  Manual-mode modal and render the outcome.

R03-T06 — Token usage as an event
  infrastructure/telemetry/usage_sink.py   UsageEvent + UsageEventSink protocol, with tracker,
                                           in-memory and composite sinks
  providers/openai_compat.py, providers/anthropic.py
                                           publish a UsageEvent instead of writing to the
                                           usage tracker themselves
  core/usage_tracker.py                    adds current_context() so a sink can borrow and
                                           restore a thread's attribution

R03-T01 — Contract tests
  tests/contracts/test_providers.py parametrises over every provider in the registry: chat()
  signature, canonical assistant message, normalised tool calls, response closed, tool schema
  translation, ProviderError, list_models/test_connection, one UsageEvent per turn.

Test infrastructure fix (required to verify any of the above): tests/conftest.py used to put
the repository's PARENT directory on sys.path, so `import cowork_local.*` resolved against
whichever sibling folder happened to carry that name — on a dev machine, an unrelated older
checkout. The suite reported green while exercising different code. The conftest now binds
this checkout to the cowork_local name in sys.modules.

Verification
  pytest tests/                    236 passed in ~1.8s (102 before this change)
  scripts/check_imports.py         PASS, 0 forbidden imports in domain/ and application/
  new production files             largest is 288 lines, all under the 400 LOC ceiling
  new tests                        134 (50 contract, 70 unit, 14 integration), all offline

scripts/run_quality_gate.py does not exist yet (R10-T02), so DoD item 7 was covered by
check_imports.py plus the full suite.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-08-22 19:36:20 +09:00
co-authored by Claude Opus 5
parent 10739f19aa
commit f61c5474b0
30 changed files with 3458 additions and 166 deletions
+288
View File
@@ -0,0 +1,288 @@
"""Token-usage telemetry as a publish/subscribe seam (R03-T06).
Before this module every provider adapter reached straight into
``core/usage_tracker.py`` and wrote a dashboard row itself, which meant the
provider layer owned a telemetry policy decision ("where do usage numbers go?")
and no test could observe a turn's token accounting without touching the real
``~/.cowork_local/usage/`` files.
Now a provider only *describes what happened* — it publishes an immutable
:class:`UsageEvent` — and subscribers decide what to do with it. The default
subscriber, :class:`UsageTrackerSink`, forwards to the existing usage tracker so
the Dashboard keeps working byte-for-byte; tests swap in
:class:`InMemoryUsageSink` and assert on the events directly.
Every publish path is failure-tolerant on purpose: telemetry must never be the
reason a chat turn dies, which is the same contract
``usage_tracker.record()`` already documents.
"""
from __future__ import annotations
import logging
import threading
from dataclasses import dataclass, field
from typing import Any, Dict, List, Optional, Protocol, runtime_checkable
logger = logging.getLogger("cowork_local.telemetry.usage")
@dataclass(frozen=True)
class UsageEvent:
"""One provider turn's token accounting.
Frozen so a subscriber cannot mutate an event the next subscriber in the
chain is about to receive. ``source``/``label`` stay optional: the usage
tracker already derives them from thread-local context set by whoever ran
the turn, and a provider adapter has no business knowing which UI surface
invoked it.
"""
provider: str
model: str
input_tokens: int = 0
output_tokens: int = 0
cached_tokens: int = 0
# True when the counts are a ~4-chars-per-token approximation because the
# gateway never sent a usage block. Surfaced in the Dashboard so users know
# which rows are measured and which are guessed.
estimated: bool = False
source: Optional[str] = None # None -> tracker's thread-local context
label: Optional[str] = None # None -> tracker's thread-local context
extras: Dict[str, Any] = field(default_factory=dict)
@property
def total_tokens(self) -> int:
"""Billable token count for this turn (cached tokens are already part
of the input count reported by every gateway we support, so adding them
again would double-count)."""
return int(self.input_tokens) + int(self.output_tokens)
def to_dict(self) -> Dict[str, Any]:
"""JSON-friendly view, using the same short keys as the usage tracker's
on-disk rows so a caller can diff an event against a stored row."""
return {
"provider": self.provider,
"model": self.model,
"in": int(self.input_tokens),
"out": int(self.output_tokens),
"cache": int(self.cached_tokens),
"estimated": bool(self.estimated),
"source": self.source or "",
"label": self.label or "",
}
@runtime_checkable
class UsageEventSink(Protocol):
"""Anything that can receive :class:`UsageEvent`s.
A ``Protocol`` rather than a base class so a plain object (or a test double,
or a Qt-side adapter that re-emits a signal) qualifies without inheriting
from infrastructure code.
"""
def emit(self, event: UsageEvent) -> None:
"""Handle one usage event. Implementations MUST NOT raise."""
class UsageTrackerSink:
"""Default subscriber: writes each event through ``core/usage_tracker.py``.
Keeps the existing Dashboard/telemetry pipeline (daily JSONL files, shared
cross-machine mirror, per-thread accumulator) as the single writer, so
routing this through an event seam changed the plumbing without changing
a single stored byte.
"""
def __init__(self, recorder=None) -> None:
# The recorder is injectable so a test can verify the forwarding
# contract without importing the real tracker (and its config paths).
self._recorder = recorder
def _resolve_recorder(self):
"""Late-bind ``usage_tracker.record``.
Imported on first use rather than at module import so telemetry stays
out of the import graph of anything that merely *declares* a sink.
"""
if self._recorder is None:
from ...core import usage_tracker as tracker
self._recorder = tracker.record
return self._recorder
def emit(self, event: UsageEvent) -> None:
"""Forward one event; swallow every failure (telemetry is never fatal)."""
try:
record = self._resolve_recorder()
if event.source is None:
# Normal path: the worker thread already tagged its own
# source/label via set_context(), so record() attributes the row.
record(
event.provider, event.model,
int(event.input_tokens), int(event.output_tokens),
int(event.cached_tokens), estimated=bool(event.estimated),
)
return
# Event carries its own attribution: apply it for this single write
# and restore the thread's previous context afterwards, so a
# re-attributed event cannot silently relabel every later turn that
# runs on the same worker thread.
from ...core import usage_tracker as tracker
previous_source, previous_label = tracker.current_context()
tracker.set_context(event.source, event.label or "")
try:
record(
event.provider, event.model,
int(event.input_tokens), int(event.output_tokens),
int(event.cached_tokens), estimated=bool(event.estimated),
)
finally:
tracker.set_context(previous_source, previous_label)
except Exception: # noqa: BLE001 — usage tracking must never break a turn
logger.debug("usage sink: forwarding to usage_tracker failed", exc_info=True)
class InMemoryUsageSink:
"""Collects events in a list — the test double for usage assertions."""
def __init__(self) -> None:
self.events: List[UsageEvent] = []
self._lock = threading.Lock()
def emit(self, event: UsageEvent) -> None:
"""Append under a lock: parallel Co4E flows publish from several worker
threads at once and ``list.append`` alone would still be atomic, but the
lock also makes :meth:`snapshot` a consistent read."""
with self._lock:
self.events.append(event)
def snapshot(self) -> List[UsageEvent]:
"""A copy of everything received so far."""
with self._lock:
return list(self.events)
def clear(self) -> None:
with self._lock:
self.events.clear()
@property
def total_tokens(self) -> int:
return sum(e.total_tokens for e in self.snapshot())
class CompositeUsageSink:
"""Fans one event out to several subscribers.
This is what makes the seam useful beyond the Dashboard: a future consumer
(per-workspace budget guard, live cost meter) subscribes alongside the
tracker instead of patching provider code again. One failing subscriber is
logged and skipped so it cannot starve the others.
"""
def __init__(self, sinks=None) -> None:
self._sinks: List[UsageEventSink] = list(sinks or ())
self._lock = threading.RLock()
def add(self, sink: UsageEventSink) -> None:
with self._lock:
self._sinks.append(sink)
def remove(self, sink: UsageEventSink) -> None:
"""Detach a subscriber; a sink that was never added is ignored so
teardown code can call this unconditionally."""
with self._lock:
if sink in self._sinks:
self._sinks.remove(sink)
def sinks(self) -> List[UsageEventSink]:
with self._lock:
return list(self._sinks)
def emit(self, event: UsageEvent) -> None:
for sink in self.sinks():
try:
sink.emit(event)
except Exception: # noqa: BLE001 — one bad subscriber must not stop the rest
logger.debug("usage sink: subscriber %r failed", sink, exc_info=True)
# --------------------------------------------------------------------------- #
# Process-wide sink.
#
# Providers publish through the module-level helpers below rather than holding a
# sink reference, because a provider instance is created fresh for every turn
# (see AppContext.build_provider_for) and would otherwise have to be handed the
# telemetry wiring on every construction.
# --------------------------------------------------------------------------- #
_sink_lock = threading.RLock()
_sink: Optional[CompositeUsageSink] = None
def get_usage_sink() -> CompositeUsageSink:
"""The shared sink, seeded with :class:`UsageTrackerSink` on first use."""
global _sink
if _sink is None:
with _sink_lock:
if _sink is None:
_sink = CompositeUsageSink([UsageTrackerSink()])
return _sink
def set_usage_sink(sink: Optional[CompositeUsageSink]) -> None:
"""Replace the shared sink (``None`` restores the default on next use).
Used by tests and by the app shell when it wants a different fan-out; kept
explicit so nothing silently reconfigures telemetry mid-run.
"""
global _sink
with _sink_lock:
_sink = sink
def subscribe(sink: UsageEventSink) -> UsageEventSink:
"""Attach an extra subscriber to the shared sink and return it (so callers
can keep the handle for a later :func:`unsubscribe`)."""
get_usage_sink().add(sink)
return sink
def unsubscribe(sink: UsageEventSink) -> None:
"""Detach a subscriber previously passed to :func:`subscribe`."""
get_usage_sink().remove(sink)
def publish(event: UsageEvent) -> None:
"""Publish one usage event to every subscriber.
Never raises: called from inside a provider's streaming loop, where an
exception would abort an otherwise successful turn.
"""
try:
get_usage_sink().emit(event)
except Exception: # noqa: BLE001
logger.debug("usage sink: publish failed", exc_info=True)
def estimate_tokens(text: str) -> int:
"""~4 chars per token approximation, re-exported so provider adapters need
exactly ONE telemetry import instead of also importing the tracker."""
return max(0, len(text or "") // 4)
__all__ = [
"UsageEvent",
"UsageEventSink",
"UsageTrackerSink",
"InMemoryUsageSink",
"CompositeUsageSink",
"get_usage_sink",
"set_usage_sink",
"subscribe",
"unsubscribe",
"publish",
"estimate_tokens",
]