mirror of
https://github.com/kuhyx/testsAndMisc.git
synced 2026-11-11 00:27:01 +01:00
Krzysztof kuhy Rudnicki
11aea86920
Answers "what is billed on every turn regardless of use" by measurement instead of recall, which is the part earlier audits kept getting wrong. A surface is reported dead only when unused in BOTH windows. One earlier audit's seven-day dead list included six servers that had been used within thirty days, so a single window is not evidence. Shares are weighted with cache-read weight 0.1, so a cached surface is not billed as though it were re-read in full each turn. Verified by running it, not just by tests: the report renders over 44,311 turns, putting rules/ at 4,907 tokens (1.77%), MEMORY.md at 4,312 (1.55%), memories/ at 3,758 (1.35%), skill descriptions at 3,279 (1.18%) and CLAUDE.md at 2,057 (0.74%), with per-MCP 7d/30d call counts behind each verdict. The files were found untracked in the tree from an earlier session; every module is already under the 250-line cap, so nothing needed splitting, and the package was already at 100% branch coverage, so nothing needed new tests. This lands the instrument only -- no surface is unregistered on its say-so. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
72 lines
2.4 KiB
Python
72 lines
2.4 KiB
Python
"""The weekly standing-cost checkup.
|
|
|
|
Complements the spend report. That report answers "where did the tokens go";
|
|
this answers "what is still being paid for every turn regardless of use", which
|
|
is the question earlier audits kept answering by memory and kept getting wrong.
|
|
|
|
Run as ``python3 -m python_pkg.token_audit.checkup``.
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import sys
|
|
|
|
from python_pkg.token_audit import surfaces, unused
|
|
from python_pkg.token_audit.probe import weighted_pct
|
|
|
|
|
|
def _fmt_usage(rows: list[unused.Usage]) -> list[str]:
|
|
"""Render call counts, marking only rows dead in BOTH windows."""
|
|
header = (
|
|
f"| name | {unused.SHORT_WINDOW_DAYS}d | {unused.LONG_WINDOW_DAYS}d | verdict |"
|
|
)
|
|
lines = [header, "|---|---|---|---|"]
|
|
for row in rows:
|
|
verdict = "**park**" if row.dead else "keep"
|
|
lines.append(
|
|
f"| {row.name} | {row.short_calls} | {row.long_calls} | {verdict} |"
|
|
)
|
|
return lines
|
|
|
|
|
|
def build(turns: int, weighted_total: int) -> str:
|
|
"""Render the checkup as markdown."""
|
|
out = ["# Standing-cost checkup", ""]
|
|
out.append(
|
|
"Every row below is billed on each of "
|
|
f"{turns:,} turns. Shares are weighted (cache-read weight 0.1)."
|
|
)
|
|
out.append("")
|
|
out.append("## Surfaces")
|
|
out.append("| surface | est tokens | share | detail |")
|
|
out.append("|---|---|---|---|")
|
|
for surface in surfaces.collect():
|
|
share = weighted_pct(surface.est_tokens, turns, weighted_total)
|
|
est = f"{surface.est_tokens:,}" if surface.est_tokens else "A/B only"
|
|
out.append(f"| {surface.name} | {est} | {share:.2f}% | {surface.detail} |")
|
|
out += ["", "## MCP servers", ""]
|
|
out += _fmt_usage(unused.mcp_usage())
|
|
out += ["", "## Skills", ""]
|
|
out += _fmt_usage(unused.skill_usage())
|
|
out += [
|
|
"",
|
|
"_A surface marked `A/B only` cannot be sized from disk; measure it",
|
|
"with `probe.measure()`, which runs non-strict so project `.mcp.json`",
|
|
"files are included._",
|
|
"",
|
|
]
|
|
return "\n".join(out)
|
|
|
|
|
|
def main(argv: list[str] | None = None) -> int:
|
|
"""Print the checkup, taking turns and weighted total from the last report."""
|
|
argv = sys.argv[1:] if argv is None else argv
|
|
turns = int(argv[0]) if argv else 44311
|
|
total = int(argv[1]) if len(argv) > 1 else 1230346533
|
|
sys.stdout.write(build(turns, total))
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|