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>
308 lines
12 KiB
Python
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,
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|