Sylpheed/tools/port/check-claims

#!/usr/bin/env bash
# Every refuted claim must appear only inside its own correction.
#
#   tools/port/check-claims
#
# 🔴 WHY THIS IS A CHECK AND NOT AN AUDIT. The Decoder's rule -- *grep the corpus
# for the claim, not for the file you were working in* -- found a refuted sentence
# still shipping in this port's `manifest.json`, and a withdrawn one still
# standing in `DECISIONS.md`. Running that by hand finds the instances present on
# the day it is run. It does not stop the next one.
#
# So: a REGISTER. Each row is a claim this corpus has refuted, plus a marker that
# must appear near every occurrence. A hit without its marker fails the run.
#
# ⚠️ Two things learned building it, both from the other agent:
#
#  * a "kept for the record" block STILL ASSERTS. Marking the heading superseded
#    does not mark the sentence a reader lands on, so the marker must sit near
#    the CLAIM, not at the top of the section.
#  * naming a refuted claim keeps it greppable, so this check returns its own
#    corrections as hits -- which is the point. The marker is what distinguishes
#    "quoted while being refuted" from "still asserted".
set -euo pipefail
cd "${PROJECT_DIR:-/work}"
WINDOW=400   # characters either side of a hit in which the marker must appear
fail=0; total_marked=0

# 🔴 THE MARKER IS AN EXPLICIT SENTINEL, NOT A KEYWORD.
#
# The first version matched a per-claim keyword -- "refuted", "WITHDRAWN" -- near
# the hit. Every one of its four failures was a quotation sitting INSIDE a
# correction whose wording happened not to contain the keyword: a table cell
# reading "standing, unmarked", a sentence reading "the real count was ten".
#
# Widening the window or adding synonyms until those passed would have been
# tuning a threshold until the answer came out right, which is the failure this
# corpus has spent a fortnight cataloguing. So the marker is a TOKEN THE AUTHOR
# PLACES: `[refuted]` near any quotation of a registered claim. It cannot be
# satisfied by phrasing, and its absence means exactly one thing.
#
# ⚠️ The cost is honest: every quotation must be marked by hand, and a new
# refuted claim means a new row plus marking its existing quotations. That work
# is the check.
MARKER='[refuted]'
REGISTER=$(cat <<'ROWS'
TAIL of the kept stream
known too fast
only thing making the plate
no loop-point field has been identified
AUDIBLY WRONG AT THE SEAM
1 of 3 streams
six expected DIFFERS
goes against the port
the capture turns out to determine it
COMPOSITED rather than standalone
structural limit, not an unrun experiment
HANDOFF Q10 says nothing on the disc
ROWS
)

# ─── THE WITHDRAWAL-TIME HOOK ────────────────────────────────────────────────
# The register enforces claims it KNOWS ABOUT; knowing about them was manual, and
# that is how ~8 claims were withdrawn this session and 0 registered. A sweep
# cannot fix it -- by the time you sweep, the withdrawal is already unpublished.
# The hook fires where the withdrawal is WRITTEN.
#
# A correction in DECISIONS.md has a shape: a heading carrying WITHDRAWN /
# CORRECTION / "refuted". A section like that containing no registered phrase is
# a death argued and never indexed.
#
# ⚠️ The register is passed in the ENVIRONMENT, not inlined. The first version
# pasted the rows into this file's own heredoc -- which made every phrase an
# unmarked quotation, and the checker flagged its own source. A tool that
# violates the rule it enforces by being written is worth a comment.
#
# 🟡 REPORTED, NOT ASSERTED: not every correction retires a CLAIM -- some fix a
# number, a scope, a wrong floor -- and forcing a row for those would push rows
# in to silence the check, the failure this file exists to prevent.
#
# ⚠️ AND IT WILL ALWAYS OVER-REPORT ON WELL-WRITTEN CORRECTIONS. The detection is
# "does this section contain a registered phrase", which requires the correction
# to QUOTE the dead claim. A good correction paraphrases it away: the JP heading
# now reads "does NOT go against the port", which does not contain the registered
# "goes against the port" [refuted] and is flagged despite being registered.
#
# The Decoder's resolution is the right one and costs the correction nothing:
# **the register entry is the verbatim home of the dead phrase; prose paraphrases
# freely.** They are different documents, so the phrase always has one exact
# place to live without any correction having to carry it. What follows for this
# hook is that its candidate list mixes "never registered" with "registered and
# paraphrased", and it cannot separate them -- so the list is a prompt to check,
# never a defect count.
echo
echo "withdrawal-time hook -- correction sections that registered nothing:"
REG="$REGISTER" python3 - <<'HOOK'
import os, re
reg = [r.strip() for r in os.environ["REG"].split("\n") if r.strip()]
doc = open("docs/port/DECISIONS.md").read()
heads = [(m.start(), m.group(0)) for m in re.finditer(r"(?m)^##+ .*$", doc)]
flagged = 0
for i, (pos, head) in enumerate(heads):
    # 🔴 THE FIRST REGEX MATCHED HEADINGS *ABOUT* CORRECTIONS, NOT HEADINGS
    # MAKING THEM -- "withdraw" caught "rather than withdrawing", "refuted"
    # caught a section discussing the register itself. 33 candidates was a
    # measurement of the regex. Narrowed to headings that RETIRE something:
    # a leading WITHDRAWN/CORRECTION/Refuted, or an explicit "is withdrawn".
    if not re.search(r"^#+\s*(?:[^A-Za-z]*\s*)?(WITHDRAWN|CORRECTION|Refuted)\b"
                     r"|\bis withdrawn\b|\bnow refuted\b", head):
        continue
    end = heads[i + 1][0] if i + 1 < len(heads) else len(doc)
    if not any(c in doc[pos:end] for c in reg):
        flagged += 1
        print("  candidate: %s" % head[:92].lstrip("# "))
print("  none -- every correction section names a registered claim" if not flagged
      else "  %d correction section(s) argue a withdrawal the register does not carry" % flagged)
HOOK

while IFS= read -r claim; do
  [ -z "$claim" ] && continue
  hits=0; bad=0; marked=0
  while IFS= read -r loc; do
    [ -z "$loc" ] && continue
    f=${loc%%:*}
    hits=$((hits+1))
    out=$(python3 - "$f" "$claim" "$MARKER" "$WINDOW" <<'PY' 
import sys
f, claim, marker, w = sys.argv[1], sys.argv[2], sys.argv[3], int(sys.argv[4])
s = open(f, encoding="utf-8", errors="ignore").read()
i = n = 0
low, claim_low = s.lower(), claim.lower()
while True:
    i = low.find(claim_low, i)
    if i < 0:
        break
    if marker.lower() not in low[max(0, i-w):i+w+len(claim)]:
        print("      unmarked in %s at char %d" % (f, i))
        sys.exit(1)
    n += 1
    i += len(claim)
# Every suppression, counted. A checker that can discard an occurrence in silence
# reports the same clean run whether or not a live assertion is hiding among the
# marked ones, and its zero is unfalsifiable. Reached from the loud end here and
# from the quiet end by the Decoder on the same day: their marker language was
# vouching for 8 of 8 mentions, so their 0 was going to be 0 either way.
print(n)
sys.exit(0)
PY
) && marked=$((marked + out)) || { printf '%s\n' "$out"; bad=$((bad+1)); }
  # 🔴 CASE-INSENSITIVE since 2026-08-30, and the reason is a live miss. The
  # register held "no loop-point field has been identified" [refuted]; `BLOCKED.md`
  # it capitalised at the start of a sentence, and the check reported clean while
  # a refuted claim stood unmarked in the file whose whole job is to say what is
  # still open. The Decoder found the same class the same day from the other end
  # -- their register missed a revival that kept the claim and changed the second
  # clause. A register matching EXACT wording does not protect the documents that
  # rewrite most, and a capital letter is the cheapest rewrite there is.
  done < <(grep -ril -- "$claim" docs/ crates/ port/ tools/ authored/ 2>/dev/null || true)
  if [ "$bad" -eq 0 ]; then
    printf '  %-42s %d file(s), %d occurrence(s) suppressed\n' "$claim" "$hits" "$marked"
    total_marked=$((total_marked + marked))
  else
    printf '  %-42s 🔴 %d file(s) assert it unmarked\n' "$claim" "$bad"; fail=1
  fi
done <<< "$REGISTER"

echo
printf '  %d occurrence(s) were SUPPRESSED by a neighbouring `%s`.\n' "$total_marked" "$MARKER"
echo "  That number is the size of what this check chose not to look at. A"
echo "  detector that can discard a candidate without saying how many has an"
echo "  unfalsifiable clean run -- its zero reads the same whether or not a live"
echo "  assertion is hiding among the marked ones."
echo
[ $fail -eq 0 ] && echo "every refuted claim appears only inside its correction" \
                || echo "🔴 a refuted claim is still being asserted"
exit $fail