Files
hermes-agent/scripts/code_health/cli.py
teknium1 4f70e88c0e fix(code-health): one-to-one move matching, real deadlines, index-exact hook
Second-round review on #132646 (F1-F10), each reproduced on 2531fb2 first:

- Moves are matched one-to-one: unchanged units are reserved first, then
  same-file body, then cross-file body only when the origin's name is gone,
  then same name. A copy of unchanged debt is new debt; a function moved
  over a same-name stub keeps its own cap (F1, F3).
- Every base hit is owned by exactly one head scope, so a file rename no
  longer counts each old hit twice (F2).
- Ruff runs when either side has Python, so a delete-only .py diff with a
  TS edit no longer crashes on a missing ruff result (F4).
- Deadlines must be finite: timeout=None, **{} and asyncio.timeout(None)
  are no deadline; awaited calls inside `async with asyncio.timeout(x)`
  are bounded (F5, F8).
- HX005 walks only what runs at import: the import-time branch of a
  `__name__` guard (either operator), loops, match, try*, decorators,
  class bases; a lambda value is deferred (F9).
- `health: allow` counts only in real comment tokens (Python tokenize, TS
  comment trivia), never in string literals (F7).
- TS function lines are owned by the innermost function, so siblings on
  one line give it up once (F10).
- The pre-commit hook runs `scripts/check --staged`: health compares the
  index tree, and when the working tree differs from the index the other
  checkers run on a checkout-index copy with a copied index, so commits are
  judged on the staged bytes and unstaged work is never touched (F6).
2026-10-04 21:29:39 -07:00

95 lines
3.8 KiB
Python

"""``python -m scripts.code_health`` / ``scripts/check``: the code-health ratchet."""
from __future__ import annotations
import argparse
import json
import sys
import time
from dataclasses import asdict
from pathlib import Path
from scripts.code_health import gitio
from scripts.code_health.compare import compare
from scripts.code_health.config import in_scope
from scripts.code_health.measure import Measurer
from scripts.code_health.report import (
apply_allows,
format_findings,
summarize_tree,
verdict,
)
from scripts.code_health.ruff_runner import pinned_version, resolve_ruff
_FOOTER = """
Each function and file has its own cap: its value on main if it is already over target,
otherwise the target. New code meets the target; existing code may only go down. Fix the code
(the `fix:` line is the repo's remedy); a genuine exception takes a reviewed comment on the line,
`# health: allow <RULE> -- <why>`. Rules and targets: scripts/code_health/config.py."""
def _parser() -> argparse.ArgumentParser:
p = argparse.ArgumentParser(prog="code_health", description=__doc__)
p.add_argument("--base", help="base revision (default: merge-base of HEAD with origin/main)")
p.add_argument("--head", help="head commit or tree (default: the working tree, untracked included)")
p.add_argument("--report", action="store_true", help="burn-down summary of the whole head tree")
p.add_argument("--json", action="store_true", help="machine-readable findings")
p.add_argument("--print-pins", action="store_true",
help="print the pinned ruff requirement (CI installs exactly this)")
return p
def _report(repo: Path, head: str | None) -> int:
paths = [p for p in gitio.tracked_files(repo, head) if in_scope(p)]
measurer = Measurer(repo, resolve_ruff(repo), known_env=gitio.known_env_names(repo, head))
print(summarize_tree(measurer.measure(head, paths)))
return 0
def run(repo: Path, base: str, head: str | None, as_json: bool = False) -> int:
started = time.monotonic()
changes = gitio.changed_files(repo, base, head)
head_paths = sorted({c.new for c in changes if c.new and in_scope(c.new)})
base_paths = sorted({c.old for c in changes if c.old and in_scope(c.old)})
if not head_paths:
print("code health: no measured files changed")
return 0
# Base files are measured too: a deleted .py still needs ruff on the base side.
needs_ruff = any(p.endswith(".py") for p in (*head_paths, *base_paths))
ruff = resolve_ruff(repo) if needs_ruff else []
measurer = Measurer(repo, ruff, known_env=gitio.known_env_names(repo, base))
base_m = measurer.measure(base, base_paths)
head_m = measurer.measure(head, head_paths)
findings = compare(base_m, head_m, changes)
apply_allows(findings, head_m)
blocking, advisory = verdict(findings)
if as_json:
print(json.dumps([asdict(f) for f in findings], indent=2))
return 1 if blocking else 0
body = format_findings(findings)
if body:
print(body)
elapsed = time.monotonic() - started
print(f"\ncode health: {len(head_paths)} files vs {base[:12]}: {blocking} blocking, "
f"{advisory} advisory ({elapsed:.1f}s)")
if blocking:
print(_FOOTER)
return 1 if blocking else 0
def main(argv: list[str] | None = None) -> int:
args = _parser().parse_args(argv)
repo = gitio.repo_root(Path.cwd())
if args.print_pins:
print(f"ruff=={pinned_version(repo)}")
return 0
head = gitio.resolve_tree(repo, args.head) if args.head else None
try:
if args.report:
return _report(repo, head)
base = gitio.resolve_rev(repo, args.base) if args.base else gitio.default_base(repo)
return run(repo, base, head, as_json=args.json)
except RuntimeError as exc:
print(f"code health: {exc}", file=sys.stderr)
return 2