dotfiles/claude/tests/statusline.isaacaudet.overflow_test.py
Jonny Barnes 697ad5055f
Show the per-model usage limit, and size the status line by measurement
/usage reports a weekly limit scoped to a single model (Fable) that the
status line did not surface. It is absent from both the status line's stdin
JSON and the legacy seven_day_opus/seven_day_sonnet fields, which are always
null now; it lives in the usage API's .limits[] under kind "weekly_scoped".
Render it labelled by scope.model.display_name so it follows whichever model
the limit applies to, inside the 7d segment since both are weekly limits
sharing one reset time.

Fitting it exposed a problem with sizing by width tier. Tiers only know the
terminal width, so content that varies with session state — branch name, cwd,
model display name — could push a line past the edge and be clipped by the
renderer. Measure the assembled line instead (vis_len) and emit the richest of
four rate-limit variants that fits, on one line or two: with reset times, with
extra-usage credits, bars only, or bars without the per-model segment. Every
branch is fit-checked, including with wrapping disabled. Two lines render
correctly in the status line.

Cap the cwd basename as well: nothing else shortened line one, so a long
project directory could overflow it on its own.

Correct the usable width. Claude Code exports COLUMNS but applies the `padding`
setting on top of it rather than deducting it first, so a line sized to COLUMNS
is clipped; deduct padding on both sides plus a column of margin.

Sanitise payload data before rendering. printf %b interprets backslash escapes,
which is how the colour variables work, so a cwd or model name containing a
literal \n — or a real newline, which jq decodes from the JSON — would split
the line and break both the width measurement and the two-line guarantee.

Parse the usage payload in one jq pass rather than ten. The status line runs on
every redraw and per-field parsing had become the dominant cost; this brings a
render back to roughly what it was before (~155ms vs ~115ms parent), the
remainder being the reset times the tiered version did not show at this width.
Fields are read one per line rather than via @tsv: tab is IFS whitespace, so
`read` collapses runs of it and an empty field — no scoped limit, which is the
common case — silently shifted every later field along by one.

Tests cover the API payload shapes including malformed and hostile input, the
width invariants (never exceed the usable width, never more than two lines,
never wrap unnecessarily), and a sweep over widths, branch lengths, model
names, cwd lengths and extra-usage. They restore the live usage cache on exit,
and remove the fixture outright when there was no cache to restore — otherwise
a test run would leave fabricated usage figures live for an hour.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-08-27 18:25:20 +01:00

110 lines
5.2 KiB
Python
Executable file

#!/usr/bin/env python3
"""Exhaustive overflow sweep for claude/statusline.isaacaudet.sh.
Covers the Isaac Audet-inspired status line (the variant symlinked from
~/.claude/statusline.sh); the sibling statusline.burnrate.sh and
statusline.original.sh are not covered.
Asserts the two hard invariants across a grid of terminal widths, branch-name
lengths and model-name lengths:
1. no rendered line exceeds the usable width
2. never more than two lines
Catches the case tier-based sizing missed: content whose width depends on
session state (branch, cwd, model display name) rather than on the terminal.
"""
import subprocess, re, unicodedata, sys, os, itertools, tempfile, shutil
SCRIPT = os.path.join(os.path.dirname(os.path.dirname(os.path.abspath(__file__))),
"statusline.isaacaudet.sh")
BRANCHES = ["main", "feature/some-longer-branch-name",
"feature/an-extremely-long-branch-name-that-keeps-going-and-going"]
MODELS = ["Opus 5", "Opus 5 (1M context)"]
WIDTHS = range(64, 245, 10)
# The cwd basename is rendered at the widest layouts and is capped by
# CWD_MAX_LEN; vary it, since a long project directory was one of the ways
# line one used to overflow.
CWDS = ["proj", "a-really-quite-long-project-directory-name-that-someone-might-have"]
# Extra-usage credits add ~30 columns and used to overflow line two on their own.
EXTRA = {
"off": '"extra_usage":{"is_enabled":false}',
"on": '"extra_usage":{"is_enabled":true,"monthly_limit":200000,'
'"used_credits":123456,"utilization":62.0}',
}
CACHE = "/tmp/claude/statusline-usage-cache.json"
FIXTURE = ('{"five_hour":{"utilization":5.0,"resets_at":"2026-08-27T15:40:00+00:00"},'
'"seven_day":{"utilization":7.0,"resets_at":"2026-08-28T02:00:00+00:00"},%s,'
'"limits":[{"kind":"weekly_scoped","percent":10,'
'"scope":{"model":{"display_name":"Fable"}},"is_active":true}]}')
def width_of(s):
return sum(2 if unicodedata.east_asian_width(c) in "WF" else 1
for c in re.sub(r"\033\[[0-9;]*m", "", s))
def main():
pad = int(subprocess.run(
["jq", "-r", ".statusLine.padding // 0", os.path.expanduser("~/.claude/settings.json")],
capture_output=True, text=True).stdout.strip() or 0)
root = tempfile.mkdtemp()
# Back up the live usage cache. If there wasn't one, remove the fixture at
# the end rather than leaving it: the status line would treat it as a fresh
# response for up to an hour and report fabricated usage.
had_cache = os.path.exists(CACHE)
saved = open(CACHE, "rb").read() if had_cache else None
fails, checked = [], 0
try:
for cwd_name, extra_name in itertools.product(CWDS, EXTRA):
with open(CACHE, "w") as fh:
fh.write(FIXTURE % EXTRA[extra_name])
repo = os.path.join(root, cwd_name)
os.makedirs(repo, exist_ok=True)
subprocess.run(["git", "-C", repo, "init", "-q"], check=True)
subprocess.run(["git", "-C", repo, "-c", "user.email=t@t", "-c", "user.name=t",
"commit", "-q", "--allow-empty", "-m", "i"], check=True)
for br in BRANCHES:
subprocess.run(["git", "-C", repo, "checkout", "-q", "-B", br], capture_output=True)
for f in os.listdir("/tmp/claude"):
if f.startswith("git-"):
os.remove("/tmp/claude/" + f)
for model, cols in itertools.product(MODELS, WIDTHS):
stdin = ('{"model":{"display_name":"%s"},"cwd":"%s",'
'"cost":{"total_cost_usd":8.31},"context_window":'
'{"context_window_size":1000000,"current_usage":'
'{"input_tokens":137000,"cache_read_input_tokens":34000}}}' % (model, repo))
out = subprocess.run(["bash", SCRIPT], input=stdin, capture_output=True,
text=True, env=dict(os.environ, TERM_WIDTH=str(cols))).stdout
usable = max(20, cols - 2 * pad - 1)
lines = out.rstrip("\n").split("\n")
checked += 1
tag = (br, model, cols, cwd_name, extra_name)
if len(lines) > 2:
fails.append(tag + ("more than two lines",))
continue
if not any(l.strip() for l in lines):
fails.append(tag + ("rendered nothing",))
continue
mx = max(width_of(l) for l in lines)
if mx > usable:
fails.append(tag + (f"max {mx} > usable {usable}",))
finally:
shutil.rmtree(root, ignore_errors=True)
if saved is not None:
with open(CACHE, "wb") as fh:
fh.write(saved)
elif os.path.exists(CACHE):
os.remove(CACHE)
print(f"checked {checked} combinations "
f"(widths {WIDTHS.start}-{WIDTHS.stop - 1}, {len(BRANCHES)} branches, "
f"{len(MODELS)} models, {len(CWDS)} cwds, extra-usage on and off)")
if fails:
print(f"FAIL: {len(fails)} overflow(s)")
for f in fails[:10]:
print(" ", f)
return 1
print("PASS: no line exceeded the usable width")
return 0
if __name__ == "__main__":
sys.exit(main())