clay-borg/tools/dep-weight.py
tegwick 3f1dbac164 CB-WP-0004 T01: fix environment friction at the root
CB-RES-0003 measured 84 turns and $15.33 — the largest mechanical
category — spent prefixing commands with `cd` and
`export PATH="$HOME/.cargo/bin:$PATH"`. Both causes are now fixed once
instead of per-leaf.

tools/repo.py resolves the repo root from __file__ and cargo from PATH
then the standard rustup locations. Every tool imports ROOT from it, so
the repo path is stated once rather than redefined in four files —
single source of fact, the rule DFD earned in InnerLoop v1.2.
rule-coverage and dep-weight now call enter_root(), which is why their
relative paths did not need rewriting one by one.

The Makefile derives REPO from MAKEFILE_LIST and resolves CARGO the same
way, so `make -C <repo> <target>` works from any directory with no
prefix.

make env-test is the positive control, and is in `make all`: every tool
runs from / with PATH=/usr/bin:/bin. Without it this fix could regress
silently and invalidate T05's measurement — the whole point of the
control loop.

dep-weight's "cargo not on PATH" error is kept rather than deleted. It
should now be unreachable, and --self-test asserts cargo_bin() resolves
unaided; a control that never fires is cheaper than a regression.

loop-lint failed on repo.py on its first run — a reporting tool with a
positive control but no --self-test entry point. Second time the gate
has caught work from its own pass within the hour.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-07-31 10:13:52 +02:00

215 lines
7.5 KiB
Python
Executable file

#!/usr/bin/env python3
"""AM-4: third-party dependency weight, measured as source under audit.
Crate count is a poor cross-ecosystem proxy — Rust splits crates far more
finely than npm, so "33 crates vs 120 npm packages" flatters us in one
direction and a low crate-count target punishes us in the other. What the
count stands in for is how much third-party source a reviewer would have
to audit. This measures that directly, in two configurations:
shipped-runtime cargo build --no-default-features (what a game ships)
dev-toolchain cargo build (adds scenario YAML)
Positive control (InnerLoop v1.0 §Step 5): every crate in the dependency
graph must be located on disk and produce a non-zero line count. A crate
that cannot be found is reported and the run exits non-zero rather than
silently under-reporting the total — under-reporting is the exact
direction this metric could be gamed.
Usage: python3 tools/dep-weight.py [--json] [--self-test]
"""
import glob
import json
import os
import subprocess
import sys
from repo import cargo_bin, enter_root
PACKAGE = "games-ground"
CONFIGS = {
"shipped-runtime": ["--no-default-features"],
"dev-toolchain": [],
}
# AM-4a / AM-4b targets from specs/GameKernel.md §4. Breaching one fails
# the build: a gate that only reports is a suggestion.
TARGETS = {
"shipped-runtime": 250_000,
"dev-toolchain": 350_000,
}
def crates(extra_args):
"""Third-party crates in the normal (non-dev) dependency graph."""
# T01: locate cargo rather than demanding the caller export PATH. The
# error below is kept as a positive control — it should now be
# unreachable on a machine with rustup installed, and a control that
# never fires is still cheaper than a regression.
cargo = cargo_bin()
if not cargo:
print(
"ERROR: cargo not found on PATH or in ~/.cargo/bin — is rustup installed?",
file=sys.stderr,
)
sys.exit(1)
out = subprocess.run(
[cargo, "tree", "-p", PACKAGE, "--edges", "normal", "--prefix", "none"]
+ extra_args,
capture_output=True,
text=True,
check=True,
).stdout
found = {}
for line in out.splitlines():
parts = line.split()
if len(parts) < 2 or not parts[1].startswith("v"):
continue
name, version = parts[0], parts[1].lstrip("v")
# Path dependencies are our own code, not third-party.
if "(/" in line:
continue
found[name] = version
return found
def source_lines(name, version):
"""Lines of Rust in the vendored source for one crate."""
roots = glob.glob(os.path.expanduser("~/.cargo/registry/src/*/"))
for root in roots:
# Version may carry a build suffix (e.g. 0.9.34+deprecated).
for d in glob.glob(f"{root}{name}-{version}*/") + glob.glob(f"{root}{name}-*/"):
total = 0
for dirpath, _, files in os.walk(d):
for f in files:
if f.endswith(".rs"):
try:
with open(os.path.join(dirpath, f), "rb") as fh:
total += fh.read().count(b"\n")
except OSError:
pass
if total:
return total
return 0
def self_test():
"""Each assertion pins a failure this tool must detect.
The controls that matter here are: an unlocatable crate must not be
silently counted as zero lines (that under-reports, the direction this
metric could be gamed), and a target breach must fail rather than
merely print.
"""
results = []
def check(name, ok, detail=""):
results.append((name, ok, detail))
# A crate that does not exist must measure zero, so the caller's
# `lines == 0` guard fires rather than silently shrinking the total.
check("unlocatable crate measures zero (so the guard fires)",
source_lines("definitely-not-a-real-crate-xyz", "9.9.9") == 0)
# A crate we do depend on must measure non-zero, or the guard above
# would fire on everything and the tool would never report at all.
real = source_lines("serde", "1")
check("a real vendored crate measures non-zero", real > 0,
f"{real:,} lines")
# Targets must be present and numeric — a missing target would make
# the breach check vacuous.
# T01: this tool is useless without cargo, and used to demand the caller
# put it on PATH. Assert it resolves unaided.
check("cargo resolves without caller PATH setup", bool(cargo_bin()),
cargo_bin() or "NOT FOUND")
check("targets defined for every configuration",
set(TARGETS) == set(CONFIGS) and all(
isinstance(v, int) and v > 0 for v in TARGETS.values()),
f"{TARGETS}")
print("dep-weight self-test (positive control)")
ok = True
for name, passed, detail in results:
print(f" [{'ok ' if passed else 'FAIL'}] {name}"
+ (f"{detail}" if detail else ""))
ok &= passed
return 0 if ok else 1
def main():
# T01: `cargo tree` and the own-source walk are both repo-relative.
enter_root()
if "--self-test" in sys.argv:
return self_test()
report = {}
missing = []
for label, args in CONFIGS.items():
found = crates(args)
per_crate = {}
for name, version in sorted(found.items()):
lines = source_lines(name, version)
if lines == 0:
missing.append(f"{name} {version} ({label})")
per_crate[name] = lines
report[label] = {
"crates": len(found),
"third_party_loc": sum(per_crate.values()),
"per_crate": per_crate,
}
own = 0
for base in ("crates", "games", "tools"):
for dirpath, _, files in os.walk(base):
if "target" in dirpath.split(os.sep):
continue
for f in files:
if f.endswith(".rs"):
with open(os.path.join(dirpath, f), "rb") as fh:
own += fh.read().count(b"\n")
report["own_loc"] = own
if "--json" in sys.argv:
print(json.dumps(report, indent=2))
else:
print("AM-4 dependency weight")
print(f" own source {own:>9,} lines")
for label in CONFIGS:
r = report[label]
limit = TARGETS[label]
mark = "ok " if r["third_party_loc"] <= limit else "FAIL"
print(
f" {label:<18}{r['crates']:>3} crates "
f"{r['third_party_loc']:>9,} lines third-party "
f"[{mark} target {limit:,}]"
)
delta = (
report["dev-toolchain"]["third_party_loc"]
- report["shipped-runtime"]["third_party_loc"]
)
print(f" scenario tooling costs {delta:>9,} lines (dev only)")
if missing:
# Positive control: a crate we could not measure would silently
# shrink the total, so refuse to report rather than under-report.
print("\nERROR — source not found for:", ", ".join(missing), file=sys.stderr)
return 1
breached = [
(label, report[label]["third_party_loc"], limit)
for label, limit in TARGETS.items()
if report[label]["third_party_loc"] > limit
]
for label, actual, limit in breached:
print(
f"\nFAIL AM-4 — {label}: {actual:,} lines exceeds target {limit:,}",
file=sys.stderr,
)
return 1 if breached else 0
if __name__ == "__main__":
sys.exit(main())