Frank
8775e64ed0
Point-of-use enforcement needs hands, not advice: - `destroy-vault.py` — moves the pages on a kill list to `.AGENTTRASH/` and then deletes every reference to them from the survivors, including the whole line when the dead link was the line's only content. Stems are seeded from the trash so the pass is re-runnable; `pathlib.Path.stem` is NOT used to compare link targets, because it strips the real suffix off names like `sd.cpp`. - `axe-measurements.py` — deletes bench/throughput ledger sections and rate rows, blanks any table cell that reports a rate, and folds Eras older than the current one into a single row that says the numbers were destroyed and that rollback is a commit. Never touches a shape number or a Law/Wire/Rollback section. - `repair-damage.py` — fixes the two artifacts those passes can leave (a list marker that lost its space, a table separator left without its header). - `restore-punctuation.py` — restores a line whose only difference from HEAD is stripped trailing punctuation. Written after `repair-damage.py`'s first version matched every wrapped prose line ending in a comma and deleted 660 of them: the rule is now `… see .` only, and the incident is recorded in its docstring. - `gen-vault-index.py` — never walks into `.AGENTTRASH/`, and sweeps rows whose page cell is empty (a description left nameless by a destruction). Full suite: 451 tests pass.
110 lines
4.2 KiB
Python
Executable File
110 lines
4.2 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Destroy the vault's dead weight: era ledgers, retired runtimes, dead experiments.
|
|
|
|
`AGENTS.md` was treating a measurement as a record worth keeping forever. It is not: a
|
|
throughput figure for a payload that no longer runs, on a runtime that no longer exists,
|
|
is a liability — the next agent spends context on a number that AI progress has already
|
|
obsolete. This pass moves those pages to `.AGENTTRASH/` (repo law: never `rm`) and then
|
|
deletes every reference to them from the surviving pages, including the sentence that
|
|
carried the link when the link was the sentence's only content.
|
|
|
|
Usage: destroy-vault.py <list-file>
|
|
List file: one vault-relative path per line; a directory path destroys the whole tree.
|
|
"""
|
|
import pathlib
|
|
import re
|
|
import shutil
|
|
import sys
|
|
|
|
VAULT = pathlib.Path("serverAppConfigs-docs")
|
|
TRASH = VAULT / ".AGENTTRASH" / "20261019-destruction"
|
|
|
|
|
|
def targets(list_file):
|
|
out = []
|
|
for line in pathlib.Path(list_file).read_text().splitlines():
|
|
line = line.strip()
|
|
if not line or line.startswith("#"):
|
|
continue
|
|
p = VAULT / line
|
|
if p.is_dir():
|
|
out += [f for f in sorted(p.rglob("*.md"))]
|
|
elif p.is_file():
|
|
out.append(p)
|
|
else:
|
|
print(f" SKIP (missing): {line}")
|
|
return out
|
|
|
|
|
|
def main(argv):
|
|
if len(argv) < 2:
|
|
print(__doc__)
|
|
return 2
|
|
doomed = targets(argv[1])
|
|
# Stems come from the trash too, so re-running the pass (or running it after a
|
|
# partial destruction) still knows which names are dead and keeps scrubbing.
|
|
stems = {p.stem for p in doomed}
|
|
if TRASH.is_dir():
|
|
stems |= {p.stem for p in TRASH.rglob("*.md")}
|
|
moved = 0
|
|
for p in doomed:
|
|
dest = TRASH / p.relative_to(VAULT)
|
|
dest.parent.mkdir(parents=True, exist_ok=True)
|
|
shutil.move(str(p), str(dest))
|
|
moved += 1
|
|
print(f"destroyed {moved} pages ({sum(len(p.read_text(errors='replace').splitlines()) for p in TRASH.rglob('*.md'))} lines staged in trash)")
|
|
|
|
# Repoint-or-delete: a link to a destroyed page is itself dead information.
|
|
link_wl = re.compile(r"\[\[([^\]|#]+)(?:#[^\]|]*)?(?:\|([^\]]*))?\]\]")
|
|
link_md = re.compile(r"\[[^\]]*\]\(([^)#]*\.md)(?:#[^)]*)?\)")
|
|
pages_cleaned = links_dropped = lines_dropped = 0
|
|
for page in sorted(VAULT.rglob("*.md")):
|
|
s = str(page)
|
|
if ".AGENTTRASH" in s or ".obsidian" in s:
|
|
continue
|
|
text = page.read_text(errors="replace")
|
|
lines = text.split("\n")
|
|
out = []
|
|
hits = 0
|
|
|
|
def dead(target):
|
|
# NOT pathlib.Path(...).stem: that strips a real suffix off names like
|
|
# `Lemonade and sd.cpp`, so a link to a destroyed page survives and the
|
|
# vault then fails its own link check.
|
|
t = target.strip()
|
|
if t.endswith(".md"):
|
|
t = t[:-3]
|
|
return t in stems or pathlib.PurePosixPath(t).name in stems
|
|
|
|
for line in lines:
|
|
found = [t for t in link_wl.findall(line) if dead(t[0])]
|
|
for m in link_md.finditer(line):
|
|
if dead(m.group(1)):
|
|
found.append(m.group(1))
|
|
if not found:
|
|
out.append(line)
|
|
continue
|
|
hits += len(found)
|
|
stripped = link_wl.sub(
|
|
lambda m: m.group(2) if (m.group(2) and not dead(m.group(1))) else "",
|
|
line)
|
|
stripped = link_md.sub(
|
|
lambda m: "" if dead(m.group(1)) else m.group(0), stripped)
|
|
# What is left of the line after the dead links are gone?
|
|
residue = re.sub(r"[\s\-*•·|:;,.\u2014\u2013]+", "", stripped)
|
|
if residue:
|
|
out.append(re.sub(r"\s+$", "", re.sub(r"^(\s*[-*]\s*)[\s:;,.\u2014-]+", r"\1", stripped)))
|
|
else:
|
|
lines_dropped += 1
|
|
if hits:
|
|
page.write_text("\n".join(out))
|
|
pages_cleaned += 1
|
|
links_dropped += hits
|
|
print(f"cleaned {pages_cleaned} surviving pages: {links_dropped} dead links dropped, "
|
|
f"{lines_dropped} lines left empty and deleted")
|
|
return 0
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main(sys.argv))
|