Files
cowork-local/core/usage_tracker.py
T
Nam Pham Dinh ThanhandClaude Opus 5 6c68417103 refactor: chia nốt theme.py, i18n.py, usage_tracker.py — Gamma hết file vượt 400 dòng
Ba file dữ liệu cuối cùng của Gamma còn trên ngưỡng CASAN Check 2.

i18n.py  3075 -> 94
    Dict STRINGS 3.000 dòng cắt thành 10 cụm theo đúng mốc phân đoạn có sẵn
    trong file (mỗi mốc là một màn/hộp thoại), cụm nào quá dài thì cắt tiếp ở
    ranh giới khoá. i18n.py giờ chỉ gộp lại và giữ 4 hàm set_language/
    get_language/tr/on_language_changed.

    Kiểm bằng cách so với bản gốc lấy từ git: 1437 mục / 1431 khoá duy nhất
    (bản gốc vốn có 6 khoá lặp), sau khi chia vẫn 1431, KHÔNG thiếu khoá nào,
    KHÔNG thừa khoá nào, KHÔNG giá trị nào lệch. Thứ tự gộp giữ nguyên nên
    quy tắc "khoá trùng thì bản sau thắng" không đổi.

theme.py  907 -> 130
    theme_palettes.py 328  hai bảng màu Tối/Sáng + lớp Palette
    theme_qss.py      198  nửa vỏ (reset + shell)
    theme_qss_controls.py 307  nửa điều khiển (nút, ô nhập, tab, badge)

    Khuôn QSS 470 dòng cắt đôi đúng mốc `/* ---- surfaces */` của chính nó.
    Đã đối chiếu: stylesheet('dark') ra đúng 24762 ký tự y như trước — khớp
    từng byte, không phải "trông có vẻ giống".

core/usage_tracker.py  536 -> 307
    usage_cost.py      101  bảng giá, quy đổi token sang tiền, định dạng
    usage_periods.py   144  gộp theo ngày/tuần/tháng/quý, chuỗi vẽ biểu đồ
    usage_ai_report.py  56  dựng câu nhắc cho AI phân tích

HAI LẦN TỰ CẮT HỎNG, ĐỀU CÙNG MỘT GỐC
--------------------------------------
1. Cắt theo m.lineno mà quên dòng @decorator phía trên -> @dataclass của
   Palette bị bỏ lại mồ côi, "Palette() takes no arguments".
2. Đọc số dòng từ AST GỐC trong khi danh sách dòng đã bị cắt -> lần bóc thứ
   hai dùng toạ độ cũ và cắt vào giữa một chữ ký hàm.

Cả hai lộ ngay vì mỗi script tự parse lại sau khi ghi. Bài học đã áp vào cả
ba lần chia: parse lại sau mỗi lần cắt, và luôn tính cả decorator.

KẾT QUẢ CASAN CHECK 2
---------------------
    Nam       0 file vượt 400   (trước: 4, tổng 5.898 dòng)
    Hiệp      0                 (trước: 1)
    Lâm       0                 (trước: 1)
    file mới  0                 (61 file dưới presentation/ application/
                                 domain/ infrastructure/ — chưa cái nào vượt)

Gamma sạch. 23 file còn vượt đều thuộc team khác (chat_panel.py 1802,
folder_tab.py 1589, structure_graph_view.py 1034...) — cần báo lên sớm chứ
đừng để tới hạn 30/08 mới lộ.

714 test xanh. 24/24 checker qua. CASAN Check 1 sạch.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-26 10:57:01 +09:00

308 lines
12 KiB
Python

"""Token-usage tracking for the Dashboard tab.
Every provider turn records one event (JSON line, one file per day under
``~/.cowork_local/usage/``): when, which tab/task ("source" + "label"),
provider/model, input/output/cached token counts. Real counts come from the
server's ``usage`` block when the stream includes one; otherwise a ~4 chars ≈
1 token estimate keeps the dashboard useful on gateways that never report
usage (events carry ``"estimated": true`` so the UI can say so).
The turn's source/label is set by the caller ON THE WORKER THREAD via
:func:`set_context` (thread-local — concurrent turns don't mix labels).
"""
from __future__ import annotations
# Giữ đường vào cũ: nhiều nơi import mấy tên này thẳng từ usage_tracker.
from .usage_ai_report import build_ai_analysis_prompt # noqa: F401
from .usage_cost import ( # noqa: F401
DEFAULT_PRICING, SUPPORTED_CURRENCIES, cost_usd, cost_usd_events,
format_cost, format_cost_compact,
)
from .usage_periods import ( # noqa: F401
bucketed_series, period_bounds, period_breakdown, period_range_label,
period_totals, period_window,
)
import json
import threading
from datetime import date, datetime
from pathlib import Path
from typing import Any, Dict, List, Optional
from ..config import CONFIG_DIR
from . import model_pricing as mp
USAGE_DIR = CONFIG_DIR / "usage"
_local = threading.local()
# Process-global identity (NOT thread-local — who's logged in and which
# machine this is are fixed for the whole process, set once right after
# login in app.py::run(), unlike source/label which vary per worker turn).
_identity_account = ""
_identity_machine = ""
_identity_shared_dir = ""
def set_identity(account: str, machine: str, shared_dir: str = "") -> None:
"""Called once after login succeeds. ``shared_dir``, when reachable,
makes every subsequent :func:`record` ALSO best-effort-append to the
shared cross-machine telemetry store (see :mod:`telemetry_shared`)."""
global _identity_account, _identity_machine, _identity_shared_dir
_identity_account = account or ""
_identity_machine = machine or ""
_identity_shared_dir = shared_dir or ""
def set_context(source: str, label: str = "") -> None:
"""Tag subsequent :func:`record` calls on THIS thread (e.g. ("cowork",
"chat title") / ("task", "task title"))."""
_local.source = source
_local.label = label
def current_context() -> tuple:
"""The ``(source, label)`` currently tagged on THIS thread.
Public counterpart to :func:`set_context`, added for
``infrastructure/telemetry/usage_sink.py``: a subscriber that needs to
attribute one event to a different surface must be able to save the
caller's context and put it back afterwards, instead of leaving the worker
thread permanently retagged.
"""
return getattr(_local, "source", "") or "", getattr(_local, "label", "") or ""
# ---- per-thread usage accumulator -----------------------------------------
# A step/run that wants to know its OWN token/cost (not the all-time file total)
# calls begin_accumulation(), reads accumulated() before/after a unit of work,
# and diffs the two. Because record() runs on the same worker thread that drives
# the work (providers are called synchronously inside it), the thread-local
# total is exactly that thread's usage — concurrent flows on other threads
# accumulate independently, with no locking or label collisions. Used by the
# Co4E runner to attach per-step token/cost to each node's output event.
def begin_accumulation() -> None:
"""Start (or reset) this thread's usage accumulator."""
_local.acc = {"in": 0, "out": 0, "cache": 0, "events": []}
def accumulated() -> Dict[str, Any]:
"""Snapshot of this thread's accumulated usage since :func:`begin_accumulation`
(all zeros / empty if never started). ``events`` is a per-turn list of
``{model, in, out}`` so a caller can price a delta with the per-model table."""
acc = getattr(_local, "acc", None)
if acc is None:
return {"in": 0, "out": 0, "cache": 0, "events": []}
return {"in": acc["in"], "out": acc["out"], "cache": acc["cache"],
"events": list(acc["events"])}
def end_accumulation() -> None:
"""Stop accumulating on this thread (subsequent records aren't tallied)."""
_local.acc = None
def estimate_tokens(text: str) -> int:
return max(0, len(text or "") // 4)
def record(provider: str, model: str, input_tokens: int, output_tokens: int,
cached_tokens: int = 0, estimated: bool = False) -> None:
"""Append one usage event. Never raises — usage tracking must never break
a chat turn."""
try:
now = datetime.now()
event = {
"ts": now.isoformat(timespec="seconds"),
"source": getattr(_local, "source", "") or "other",
"label": getattr(_local, "label", "") or "",
"provider": provider or "",
"model": model or "",
"in": int(input_tokens or 0),
"out": int(output_tokens or 0),
"cache": int(cached_tokens or 0),
"estimated": bool(estimated),
"account": _identity_account,
"machine": _identity_machine,
}
USAGE_DIR.mkdir(parents=True, exist_ok=True)
path = USAGE_DIR / f"{now.strftime('%Y-%m-%d')}.jsonl"
with path.open("a", encoding="utf-8") as f:
f.write(json.dumps(event, ensure_ascii=False) + "\n")
_write_shared(event, now)
# Feed this thread's live accumulator, if one is active (see above).
acc = getattr(_local, "acc", None)
if acc is not None:
acc["in"] += event["in"]
acc["out"] += event["out"]
acc["cache"] += event["cache"]
acc["events"].append({"model": event["model"], "in": event["in"], "out": event["out"]})
except Exception: # noqa: BLE001
pass
def _write_shared(event: Dict[str, Any], now: datetime) -> None:
"""Best-effort mirror of ``event`` into the shared cross-machine store —
one file PER MACHINE per day, so no two machines ever write the same
file (avoids any read-modify-write race). Never raises."""
if not _identity_shared_dir or not _identity_machine:
return
try:
shared = Path(_identity_shared_dir).expanduser() / "telemetry" / "usage"
shared.mkdir(parents=True, exist_ok=True)
path = shared / f"{_identity_machine}-{now.strftime('%Y-%m-%d')}.jsonl"
with path.open("a", encoding="utf-8") as f:
f.write(json.dumps(event, ensure_ascii=False) + "\n")
except Exception: # noqa: BLE001
pass
def load_events(start: Optional[date] = None, end: Optional[date] = None,
directory: Path = None) -> List[Dict[str, Any]]:
"""Events between ``start`` and ``end`` (inclusive; None = unbounded)."""
directory = directory or USAGE_DIR
if not directory.exists():
return []
events: List[Dict[str, Any]] = []
for path in sorted(directory.glob("*.jsonl")):
try:
day = datetime.strptime(path.stem, "%Y-%m-%d").date()
except ValueError:
continue
if (start and day < start) or (end and day > end):
continue
try:
for line in path.read_text(encoding="utf-8").splitlines():
if line.strip():
events.append(json.loads(line))
except (OSError, json.JSONDecodeError):
continue
return events
def summarize(events: List[Dict[str, Any]]) -> Dict[str, Any]:
"""Aggregate a list of events into dashboard numbers + habit stats."""
total_in = sum(e.get("in", 0) for e in events)
total_out = sum(e.get("out", 0) for e in events)
total_cache = sum(e.get("cache", 0) for e in events)
by_label: Dict[str, int] = {}
by_source: Dict[str, int] = {}
by_hour: Dict[int, int] = {}
by_day: Dict[str, int] = {}
for e in events:
tok = e.get("in", 0) + e.get("out", 0)
key = e.get("label") or e.get("source") or "?"
by_label[key] = by_label.get(key, 0) + tok
by_source[e.get("source", "?")] = by_source.get(e.get("source", "?"), 0) + tok
try:
dt = datetime.fromisoformat(e.get("ts", ""))
by_hour[dt.hour] = by_hour.get(dt.hour, 0) + tok
by_day[dt.strftime("%Y-%m-%d")] = by_day.get(dt.strftime("%Y-%m-%d"), 0) + tok
except ValueError:
pass
return {
"turns": len(events),
"in": total_in, "out": total_out, "cache": total_cache,
"total": total_in + total_out,
"avg_per_turn": (total_in + total_out) // len(events) if events else 0,
"estimated_share": (sum(1 for e in events if e.get("estimated")) / len(events)
if events else 0.0),
"top_labels": sorted(by_label.items(), key=lambda kv: -kv[1])[:5],
"by_source": sorted(by_source.items(), key=lambda kv: -kv[1]),
"busiest_hour": max(by_hour.items(), key=lambda kv: kv[1])[0] if by_hour else None,
"busiest_day": max(by_day.items(), key=lambda kv: kv[1])[0] if by_day else None,
}
# ---- cost ------------------------------------------------------------------
# Currencies the display picker offers — exactly the ones format_cost() can
# actually convert to (symbol/precision above + a usd_to_* rate below).
def set_budget(config, amount: float, currency: Optional[str] = None) -> None:
"""Set (or reset) the spending budget. ``amount`` is read in ``currency``
(defaults to the current display currency) and converted + stored as USD.
Remaining balance is always DERIVED fresh from the usage log — never
incrementally decremented — so re-entering a budget starts a clean window
instead of double-subtracting spend the old budget had already accounted
for. The cutoff is an EVENT-COUNT baseline (how many usage events existed
at the moment of setting), not a timestamp: events append in chronological
order and ``budget_set_at`` only has 1-second resolution, so a timestamp
cutoff could mis-include/exclude an event recorded in that same second —
the count baseline is exact regardless of timing."""
usage = config.data.setdefault("usage", {})
ccy = (currency or usage.get("currency") or "USD").upper()
usage["budget_amount_usd"] = mp.convert(float(amount or 0), ccy, "USD", config)
usage["budget_set_at"] = datetime.now().isoformat(timespec="seconds") # display only
usage["budget_baseline_count"] = len(load_events()) # the real cutoff
def clear_budget(config) -> None:
"""Remove the budget entirely (Remaining/Budget box goes back to unset)."""
usage = config.data.setdefault("usage", {})
usage.pop("budget_amount_usd", None)
usage.pop("budget_set_at", None)
usage.pop("budget_baseline_count", None)
def budget_status(config) -> Optional[Dict[str, Any]]:
"""``None`` when no budget is configured. Else a dict with ``amount_usd``,
``spent_usd`` (cost of events recorded AFTER the budget was last set — NOT
the all-time total, so a reset budget never inherits older spend),
``remaining_usd``, ``pct_used`` and ``over_85`` (⚠ the Overview/Dashboard
balance turns red at this point)."""
usage = (getattr(config, "data", {}) or {}).get("usage") or {}
amount = usage.get("budget_amount_usd")
set_at = usage.get("budget_set_at")
if not amount or not set_at:
return None
all_events = load_events()
baseline = usage.get("budget_baseline_count")
if baseline is None:
# backward-compat: a budget set before this field existed — fall back
# to the timestamp cutoff (best-effort, may double-count a same-second event).
events = [e for e in all_events if str(e.get("ts", "")) >= str(set_at)]
else:
events = all_events[int(baseline):]
pricing = {**DEFAULT_PRICING, **usage}
spent = sum(cost_usd_events(events, pricing).values())
amount = float(amount)
pct = (spent / amount) if amount else 0.0
return {
"amount_usd": amount, "spent_usd": spent, "remaining_usd": amount - spent,
"pct_used": pct, "over_85": pct >= 0.85, "set_at": set_at,
}