The gates existed; CI ran half of them and tolerated the failure case. - cb-sim no longer has a "tolerable" non-zero exit. An unregistered game prefix is a failure, and a run in which nothing executed is a failure. Previously CI carried `|| test $? -eq 2`, so renaming a scenario prefix would have skipped every scenario while the pipeline stayed green. Verified with a negative control. - CI now runs make coverage (AM-1) and make dep-weight (AM-4), both added after CI was written and neither enforced until now. - dep-weight enforces its targets instead of only reporting them. - CI lints the shipped-runtime configuration separately, so the feature split cannot rot unnoticed. - Dropped the stale `make deps` target, which still measured the retired crate-count metric. The positive-control rule is now executable: CI runs `cargo bench -- --test`, which executes every benchmark once, so a workload that stalls fails the build. That step immediately found a fourth instance of the error class it was written for. The committed replay benchmark was the broken version — an earlier patch never applied, leaving a command sequence that omits Resolve, so every round produced nothing and the log-building loop spun forever. It had never run to completion; the reported AM-7 replay numbers came from a probe test instead. Fixed, given the same positive control as the round loop, and re-measured from the benchmark: 100k events fold in 2.18ms (95% CI 2.14-2.23), against a 5s budget. Evidence now reports confidence intervals rather than point estimates, so the 3% regression rule in MetricsAndScenarios is enforceable. The finding worth carrying: writing the positive-control rule into InnerLoop v1.0 did not prevent the next instance. Making it a CI step did. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
159 lines
5.3 KiB
Python
Executable file
159 lines
5.3 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]
|
|
"""
|
|
|
|
import glob
|
|
import json
|
|
import os
|
|
import shutil
|
|
import subprocess
|
|
import sys
|
|
|
|
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."""
|
|
if not shutil.which("cargo"):
|
|
print(
|
|
"ERROR: cargo not on PATH. Try: export PATH=\"$HOME/.cargo/bin:$PATH\"",
|
|
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 main():
|
|
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())
|