Hồi quy đã vá
-------------
F-12 Kéo–thả hoặc dán tệp vào ô chat ném NameError. R08 tách `_Input` sang
`chat_input_box.py` nhưng để `_paths_from_mime()` ở lại
`composer_widget.py`, nên hai hàm sự kiện Qt gọi một cái tên không tồn
tại. Bốn hàm dùng chung chuyển sang `composer_mime.py` — module thứ ba
là chỗ duy nhất không lặp lại được lỗi này. Đo lại: cả thả lẫn dán đều
gắn 1 tệp, khớp bản trước refactor.
F-01 Đổi provider thì bộ chọn model AI-Edit không làm gì. Hook cũ kiểm
`folder.ai_model_combo`, thuộc tính R08-T12 đã dời sang
`ai_panel.resolver`. Làm mới vô điều kiện, đúng như tab cũ: lần lấy đầu
tiên hỏng thì đổi provider chính là lúc phải thử lại.
F-07 Hàng chọn kỳ của Dashboard bị đẩy xuống dưới các thẻ số liệu. Hàng này
lọc CẢ BA thẻ con chứ không riêng biểu đồ, nên để nó nằm dưới là bắt
người dùng đọc con số trước khi thấy con số đó tính cho kỳ nào. Kèm
theo: `TokenUsageCardWidget` bị bỏ sót `setContentsMargins(0,0,0,0)`
mà hai thẻ con còn lại đã có, đẩy cả hàng thẻ lệch 9px.
`check_layout_geometry` nay khớp TỪNG BYTE với bản trước refactor.
F-11 Hai lớp khai trùng tên phương thức; Python giữ bản sau nên bản đầu là
mã chết. `co4e_tab.py::showEvent` bản đầu gọi `_narrow_guard.attach()`
và không bao giờ chạy.
Tách file (F-09)
----------------
Bốn file chạm trần 400 dòng, mỗi lần cắt ra một trách nhiệm thật:
graph_renderer.py -> graph_scene_builder.py + graph_export.py
co4e_workflow_service.py -> co4e_run_history.py
json_config_repository.py -> config_sections.py
agents_admin_tab.py -> shared/agent_kind_visuals.py
File cuối còn xoá 3 bản sao của hàm đã có trong `shared/formatters.py`,
giống hệt đến từng dòng — nay định dạng thời gian và avatar không lệch nhau
giữa các bảng Giám sát nữa.
Docstring
---------
41,6% -> 100% (3.478/3.478 định nghĩa production), kể cả module dormant và
phương thức dunder. Toàn bộ phần bổ sung viết bằng tiếng Việt; comment tiếng
Anh có sẵn giữ nguyên — dịch ngược là một đợt riêng.
Seam chưa nối dây (F-05)
------------------------
9 seam mang nhãn `SEAM · dựng <ngày>` kèm hai câu: được nối khi nào, và để
dormant thì hỏng gì. Ngày lấy từ lịch sử git, không phải hạn tự đặt. Gate O
đọc nhãn đó và nhắc khi quá 30 ngày.
859 test xanh · 4/4 cổng CASAN · 19/24 checker khớp từng byte bản cũ.
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
313 lines
12 KiB
Python
313 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:
|
|
"""Ước lượng số token của một đoạn văn bản theo tỉ lệ 4 ký tự ≈ 1 token.
|
|
|
|
Ước lượng thô là đủ: con số này chỉ dùng để quyết định khi nào nén lịch sử,
|
|
không dùng để tính tiền (tiền lấy từ số token thật provider trả về).
|
|
"""
|
|
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,
|
|
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|