holocron/plugins/kyberforge/skills/agent-audit/scripts/vale-wrap.sh

#!/usr/bin/env bash
set -euo pipefail

# Works around a Vale limitation: the `text.frontmatter.description` NLP scope
# silently stops matching once the `description:` value spans 2+ physical lines
# in any form YAML joins back into one string — a `>`/`>-`/`>+` folded block
# scalar (the style used by most skills/agents in this repo), a plain scalar
# wrapped onto continuation lines, or a double- or single-quoted scalar wrapped
# the same way. A `|`/`|-`/`|+` literal block scalar is NOT affected: its parsed
# value keeps exactly the line breaks the source has, and vale matches it fine
# (verified against vale 3.15.2), so literal blocks are deliberately left alone.
# This script flattens an affected description to a one-line scalar in a scratch
# copy — or, for the rare value no inline scalar can spell out verbatim, to a
# `|-` literal block with a single content line, which vale matches just as well
# (padding with blank lines so every other line number is unchanged), then
# runs the real `vale` binary against the copies. Drop-in replacement for calling
# `vale` directly: same args, same exit code, bar the two documented divergences
# below.
#
# "Same args" means relative paths — path arguments and the values of the
# path-valued flags (`--config`, `--output`, `--path`) alike — resolve against
# the caller's current directory, exactly as bare `vale` resolves them. The flag
# values are rewritten to absolute form because the run ends up `cd`'d into the
# scratch mirror, where a relative one would no longer resolve. (An earlier
# version resolved path arguments against the repo root, an invented convention
# that hard-errored on `--config ../../.vale.ini` from a subdirectory and, worse,
# silently dropped file arguments that didn't happen to resolve from the repo
# root — skipping the flattening this script exists for.)
#
# Divergence 1: with no `--config` at all, this script's own sibling
# `assets/vale/.vale.ini` is used instead of vale's upward search. pre-commit
# prefixes only `entry[0]` with the hook-repo clone path, so a `--config` in
# `.pre-commit-hooks.yaml` would resolve against the *consuming* repo and
# hard-fail (E100) for every external consumer. The manifest therefore passes the
# script alone, and an explicit `--config` from any other caller still wins.
#
# Divergence 2: a path-shaped argument that does not exist is a hard error
# (exit 2). Bare vale drops it, falls back to reading stdin, and prints
# `0 errors ... in stdin` with exit 0 — a typo'd target is then indistinguishable
# from a clean run. Both audit skills treat a `0 files` report as NOT RUN rather
# than clean, and `in stdin` does not match that guard, so the silent form would
# read as "prefilter clean" and skip the LLM fallback. Erroring is the only way
# to keep that guard honest. Linting prose piped on stdin is therefore
# unsupported here — it already was, since the no-path handoff closes stdin so
# vale can't block on a pipe that will never carry content.
#
# Vale prints each path exactly as it was handed to it, so the scratch tree
# mirrors the caller's absolute cwd: a relative path argument is passed through
# verbatim and resolves to its flattened copy, keeping the report byte-identical
# to bare `vale`'s. An absolute path inside the cwd is relativized to keep that
# property. Only an absolute path outside the cwd is rewritten to its scratch
# copy and so reports a scratch path — unavoidable, since a file can only be
# read from where it actually is.

cwd="$(pwd -P)"

# Every array below is expanded as `${arr[@]+"${arr[@]}"}`: bash before 4.4 —
# including the 3.2 that macOS still ships as /bin/bash — treats `"${arr[@]}"`
# on an empty array as an unbound variable under `set -u`. No expansion site is
# reachable while empty on today's control flow, so this is insurance against a
# later edit breaking that invariant, not a live fix.
vale_args=()
path_args=()
pending_flag=""
config_given=false

# `--output` takes either one of vale's built-in style names or a template file
# path. Only the file form needs absolutizing, and the built-in names have to be
# excluded by name *before* the existence test below: a file or directory
# literally called `line` in the caller's cwd would otherwise rewrite the
# built-in into `$cwd/line`, flipping vale into template mode (`E100 [template]
# Runtime error`) where bare vale just uses the built-in. `--path` has no such
# names — it is always a path — so the check is keyed on the flag too.
is_builtin_output() {
  case "$2" in
    line|JSON|CLI) [[ "$1" == "--output" ]] ;;
    *) false ;;
  esac
}
# Absolutizes a `--config` value against the caller's cwd. Shared by both
# argument forms below — separated (`--config X`) and joined (`--config=X`)
# — so the "already absolute vs. needs $cwd prefixed" check lives in exactly
# one place instead of being duplicated per form.
abs_config_value() {
  if [[ "$1" == /* ]]; then
    printf '%s' "$1"
  else
    printf '%s' "$cwd/$1"
  fi
}
for arg in "$@"; do
  if [[ -n "$pending_flag" ]]; then
    # Value of a separated two-argv flag. It is never a lint target, however
    # file-like it looks. The run ends up `cd`'d into the scratch mirror, so a
    # value naming a file has to be absolutized here or it stops resolving.
    case "$pending_flag" in
      --config)
        # Always a path, and required to exist.
        vale_args+=("$(abs_config_value "$arg")")
        ;;
      --output|--path)
        # See `is_builtin_output` above for why the built-in `--output` names
        # are excluded first. Anything that names nothing is passed through and
        # left for vale to interpret.
        if is_builtin_output "$pending_flag" "$arg"; then
          vale_args+=("$arg")
        elif [[ "$arg" != /* && -e "$arg" ]]; then
          vale_args+=("$cwd/$arg")
        else
          vale_args+=("$arg")
        fi
        ;;
      *)
        vale_args+=("$arg")
        ;;
    esac
    pending_flag=""
    continue
  fi
  case "$arg" in
    --config)
      vale_args+=("$arg")
      pending_flag="$arg"
      config_given=true
      continue
      ;;
    --config=*)
      vale_args+=("--config=$(abs_config_value "${arg#--config=}")")
      config_given=true
      continue
      ;;
    # Same cwd-relative resolution for the `--flag=value` spelling of the two
    # other path-valued flags.
    --output=*|--path=*)
      flag_val="${arg#*=}"
      if is_builtin_output "${arg%%=*}" "$flag_val"; then
        vale_args+=("$arg")
      elif [[ "$flag_val" != /* && -n "$flag_val" && -e "$flag_val" ]]; then
        vale_args+=("${arg%%=*}=$cwd/$flag_val")
      else
        vale_args+=("$arg")
      fi
      continue
      ;;
    # Vale's remaining value-taking flags, per `vale --help` (3.x). In the
    # separated two-argv form the value must not be classified as a lint target
    # — `--output tmpl.tmpl` names a real template file, and treating it as
    # input both lints the template and reorders argv so vale sees
    # `--output --no-wrap`. The `--flag=value` form needs no entry here: it
    # starts with `-` and falls through to vale untouched. A value flag added by
    # some future vale release is simply absent from this list and lands back on
    # today's behaviour, so this list going stale is never worse than not having
    # it.
    --ext|--filter|--glob|--minAlertLevel|--output|--path)
      vale_args+=("$arg")
      pending_flag="$arg"
      continue
      ;;
    # Vale's subcommands are bare words that name no file, so they would trip
    # the not-found error below. A lint target literally named `sync` (no
    # extension, no slash) is misread as the subcommand — accepted, because the
    # alternative is failing every `vale-wrap.sh ls-config`.
    ls-config|ls-dirs|ls-metrics|ls-vars|sync)
      vale_args+=("$arg")
      continue
      ;;
  esac
  if [[ "$arg" == -* ]]; then
    vale_args+=("$arg")
    continue
  fi
  # Everything left is a lint target: `vale [options] [input...]` has no third
  # kind of argument. See divergence 2 above for why a missing one is fatal here.
  if [[ ! -e "$arg" ]]; then
    echo "vale-wrap.sh: no such file or directory: $arg" >&2
    exit 2
  fi
  # An absolute path inside the caller's cwd is relativized so the report cites
  # a path that resolves against the real tree. Left absolute, it would be
  # rewritten to its scratch copy and printed as `/tmp/tmp.XXXX/...` — a real
  # path to a file that is deleted on exit, which reads as a bug in any report
  # quoting it. Absolute paths outside the cwd have no relative form and keep
  # the scratch-path behaviour documented above.
  if [[ "$arg" == "$cwd"/* ]]; then
    path_args+=("${arg#"$cwd"/}")
  else
    path_args+=("$arg")
  fi
done

if [[ "$config_given" == false ]]; then
  vale_args+=(--config "$(cd "$(dirname "${BASH_SOURCE[0]}")/../assets/vale" && pwd)/.vale.ini")
fi

if [[ ${#path_args[@]} -eq 0 ]]; then
  # Nothing to flatten. Hand off directly, with stdin closed so vale doesn't
  # block waiting on a pipe that will never carry content.
  exec vale ${vale_args[@]+"${vale_args[@]}"} < /dev/null
fi

# `realpath -m` would be the obvious normalizer, but `-m` (canonicalize-missing)
# is a GNU extension the BSD realpath on macOS doesn't have — and every dest
# below is a path that doesn't exist yet. python3 is already a hard dependency.
abspath() {
  python3 -c 'import os, sys; print(os.path.abspath(sys.argv[1]))' "$1"
}

flatten() {
  # Two call shapes: `flatten src dest` (dest already resolved and inside the
  # scratch tree — the per-markdown-file calls in the directory branch below)
  # writes straight to `dest`. `flatten src raw_dest tmpdir` (the single-file
  # branch further down) additionally resolves `raw_dest` the way a separate
  # `abspath` call used to, applies the same sandbox-escape guard, and prints
  # the resolved path — folding two python3 spawns per file into one.
  python3 - "$@" <<'PYTHON'
import os
import re
import sys

src, dest_input = sys.argv[1], sys.argv[2]
tmpdir = sys.argv[3] if len(sys.argv) > 3 else None

if tmpdir is None:
    dest = dest_input
else:
    dest = os.path.abspath(dest_input)
    if not dest.startswith(tmpdir + os.sep):
        print(
            f"vale-wrap.sh: refusing to lint '{src}': its scratch copy would "
            f"land outside {tmpdir}",
            file=sys.stderr,
        )
        sys.exit(2)
    os.makedirs(os.path.dirname(dest), exist_ok=True)

# surrogateescape keeps a non-UTF-8 file (reachable via a directory argument)
# a byte-for-byte round trip instead of aborting the whole run on a decode error.
with open(src, encoding='utf-8', errors='surrogateescape') as fh:
    content = fh.read()

# YAML 1.2 double-quoted escapes (spec 5.7 / 7.3.1). `\<newline>` is handled
# separately in unescape_double because it also swallows the next indentation.
DQ_ESCAPES = {
    '0': '\0', 'a': '\a', 'b': '\b', 't': '\t', '\t': '\t', 'n': '\n',
    'v': '\v', 'f': '\f', 'r': '\r', 'e': '\x1b', ' ': ' ', '"': '"',
    '/': '/', '\\': '\\', 'N': '\x85', '_': '\xa0', 'L': '\u2028',
    'P': '\u2029',
}

# First characters that make a plain (unquoted) scalar mean something other than
# text: YAML's c-indicator set.
PLAIN_UNSAFE_FIRST = '-?:,[]{}#&*!|>\'"%@`'


def unescape_double(text):
    """Decode a double-quoted YAML scalar's body to the string YAML parses."""
    out = []
    i = 0
    while i < len(text):
        char = text[i]
        if char != '\\':
            out.append(char)
            i += 1
            continue
        i += 1
        if i >= len(text):
            break
        esc = text[i]
        if esc == '\n':
            i += 1
            while i < len(text) and text[i] in ' \t':
                i += 1
            continue
        if esc in 'xuU':
            width = {'x': 2, 'u': 4, 'U': 8}[esc]
            digits = text[i + 1:i + 1 + width]
            if len(digits) == width:
                try:
                    out.append(chr(int(digits, 16)))
                except ValueError:
                    pass
                else:
                    i += 1 + width
                    continue
        out.append(DQ_ESCAPES.get(esc, esc))
        i += 1
    return ''.join(out)


def close_quote(text, quote):
    """Index of the closing `quote` in `text`, which starts just past the
    opening one. None while the scalar is still unterminated."""
    i = 0
    while i < len(text):
        char = text[i]
        if quote == '"' and char == '\\':
            i += 2
            continue
        if char == quote:
            if quote == "'" and text[i + 1:i + 2] == "'":
                i += 2
                continue
            return i
        i += 1
    return None


def continuation_lines(rest):
    """Yield the physical lines of `rest` that continue the value started on the
    `description:` line. Indentation-based and blank-line-tolerant, per YAML:
    a blank line (any amount of whitespace) always stays inside; the indent is
    set by the first content line; the value ends at the first line indented
    less than that, at any line flush with the key (that is the next mapping
    key, not a continuation), or at EOF."""
    indent = None
    for line in rest.splitlines(keepends=True):
        text = line.rstrip('\n')
        if text.strip() == '':
            yield line
            continue
        line_indent = len(text) - len(text.lstrip(' \t'))
        if line_indent == 0:
            return
        if indent is None:
            indent = line_indent
        elif line_indent < indent:
            return
        yield line


def emit(value):
    """Render `value` as a YAML scalar whose source text spells the value out
    verbatim. Vale locates the description by matching the parsed value back
    against the source, so a scalar carrying any escape — `''` in a
    single-quoted scalar, `\\"` or `\\\\` in a double-quoted one — makes the
    whole `text.frontmatter.description` scope vanish, the same failure this
    script exists to work around. Verbatim forms only, therefore, tried in
    descending order of fidelity. The first three occupy one physical line; the
    `|-` fallback occupies two, which the caller accounts for when padding."""
    if (value
            and value[0] not in PLAIN_UNSAFE_FIRST
            and ': ' not in value
            and not value.endswith(':')
            and ' #' not in value):
        return value                    # plain: nothing needs escaping at all
    if "'" not in value:
        return "'" + value + "'"        # single-quoted: only `'` would escape
    if '"' not in value and '\\' not in value:
        return '"' + value + '"'        # double-quoted: only `"`/`\` would
    # Last resort: the value needs quoting AND holds an apostrophe AND a double
    # quote or backslash, so no *inline* scalar can carry it verbatim. A `|-`
    # literal block can — a block scalar's body has no escape syntax at all, so
    # `'`, `"`, `\` and `: ` all survive byte for byte, and vale still matches
    # the description scope against it (the header above says the same of the
    # `|` blocks this script deliberately leaves alone; verified against vale
    # 3.15.2). One content line, indented two spaces, `-`-chomped so the parsed
    # value is exactly `value` with no trailing newline.
    return '|-\n  ' + value


fm_match = re.match(r'^(---\n)(.*?\n)(---\n)', content, re.DOTALL)
if fm_match:
    fm = fm_match.group(2)
    header_m = re.search(r'^description:[ \t]*', fm, re.MULTILINE)
else:
    header_m = None

if header_m:
    head_start = header_m.start()
    value_start = header_m.end()
    header_end = fm.find('\n', value_start)
    header_end = len(fm) if header_end == -1 else header_end
    first = fm[value_start:header_end]
    body_start = header_end + 1
    indicator = first.rstrip()

    block_m = re.fullmatch(r'([|>])([+-]?[0-9]*|[0-9]*[+-]?)', indicator)
    if block_m and block_m.group(1) == '|':
        kind = None       # literal blocks keep their line breaks; vale is fine
    elif block_m:
        kind = 'block'    # folded (`>`): the value starts on the next line
    elif indicator == '':
        kind = 'block'    # bare `description:`: a plain scalar on later lines
    elif first[:1] == '"':
        kind = 'double'
    elif first[:1] == "'":
        kind = 'single'
    elif first[:1] in '#&*!':
        kind = None       # comment, anchor, alias or tag — not a plain scalar
    else:
        kind = 'plain'

    text = ''
    value_end = value_start
    value_lines = 0
    if kind in ('block', 'plain'):
        body = ''.join(continuation_lines(fm[body_start:]))
        value_end = body_start + len(body)
        if kind == 'block':
            text = body
            value_lines = body.count('\n')
        else:
            text = fm[value_start:value_end]
            value_lines = 1 + body.count('\n')
            if ' #' in text or text.lstrip().startswith('#'):
                # A `#` opens a comment inside a plain scalar. Folding it in
                # would lint text YAML never treats as part of the value, so
                # leave the file alone rather than lint the wrong string.
                kind = None
    elif kind in ('double', 'single'):
        quote = '"' if kind == 'double' else "'"
        inner_start = value_start + 1
        acc = fm[inner_start:body_start]
        idx = close_quote(acc, quote)
        lines = continuation_lines(fm[body_start:])
        while idx is None:
            try:
                acc += next(lines)
            except StopIteration:
                break
            idx = close_quote(acc, quote)
        if idx is None:
            kind = None   # unterminated quote: invalid YAML, leave it to vale
        else:
            inner = acc[:idx]
            value_end = inner_start + idx + 1
            text = unescape_double(inner) if quote == '"' else inner.replace("''", "'")
            value_lines = 1 + inner.count('\n')

    flat = re.sub(r'\s+', ' ', text).strip()
    if kind and flat and value_lines >= 2:
        # `value_end` can land mid-line, just past a closing quote, so extend to
        # the end of that physical line and carry whatever follows (a trailing
        # comment) across unchanged.
        if value_end > 0 and fm[value_end - 1] == '\n':
            span_end = value_end
            trailer = ''
        else:
            newline = fm.find('\n', value_end)
            span_end = len(fm) if newline == -1 else newline + 1
            trailer = fm[value_end:span_end].rstrip('\n')
        scalar = emit(flat)
        # A trailing comment carried across from the original line stays on the
        # `description:` line itself: after a block scalar's `|-` header it is
        # still a comment, but inside the block body it would become part of the
        # value.
        head, newline_sep, block_body = scalar.partition('\n')
        # The replacement displaces the whole span, so the blank-line pad makes
        # up the difference between the lines it displaced and the lines it
        # occupies — every later line number is unchanged. That is one line for
        # the three inline forms and two for the `|-` block; the span itself is
        # at least two lines here (`value_lines >= 2` is a precondition), so the
        # pad count never goes negative.
        pad = '\n' * (fm[head_start:span_end].count('\n') - 1 - scalar.count('\n'))
        new_fm = (fm[:head_start] + 'description: ' + head + trailer
                  + newline_sep + block_body + '\n' + pad + fm[span_end:])
        content = (fm_match.group(1) + new_fm + fm_match.group(3)
                   + content[fm_match.end():])

with open(dest, 'w', encoding='utf-8', errors='surrogateescape') as fh:
    fh.write(content)

if tmpdir is not None:
    print(dest)
PYTHON
}

tmpdir="$(cd "$(mktemp -d)" && pwd -P)"
trap 'rm -rf "$tmpdir"' EXIT

# Mirror of the caller's cwd inside the scratch tree; relative path arguments
# are resolved from here.
mirror="$tmpdir$cwd"
mkdir -p "$mirror"

argv_paths=()
for arg in ${path_args[@]+"${path_args[@]}"}; do
  if [[ "$arg" == /* ]]; then
    raw_dest="$tmpdir$arg"
  else
    raw_dest="$mirror/$arg"
  fi
  if [[ -d "$arg" ]]; then
    dest="$(abspath "$raw_dest")"
    # A path argument with enough leading `..` to climb past the mirror root would
    # write outside the scratch dir. The real filesystem clamps such a path at
    # `/`; the mirror can't, so refuse rather than scribble outside the sandbox.
    case "$dest" in
      "$tmpdir"/*) ;;
      *)
        echo "vale-wrap.sh: refusing to lint '$arg': its scratch copy would land outside $tmpdir" >&2
        exit 2
        ;;
    esac
    mkdir -p "$(dirname "$dest")"
    # A directory is mirrored whole — vale applies its own format filtering to
    # the tree, so any file dropped here would be silently unlinted — and then
    # every markdown file in the copy is flattened in place. `.git` is pruned:
    # vale never lints it and copying it can dwarf the rest of the tree.
    # `find -L` follows symlinks because vale does: it lints both a symlinked
    # file and a file under a symlinked directory, and a bare `-type f` walk
    # would report "0 files" where bare vale reports one. (A symlink loop makes
    # `find` warn on stderr and carry on, which is also what vale does.) The
    # second walk needs no `-L`: the mirror is all real files by construction.
    mkdir -p "$dest"
    while IFS= read -r -d '' rel; do
      mkdir -p "$dest/$(dirname "$rel")"
      cp "$arg/$rel" "$dest/$rel"
    done < <(cd "$arg" && find -L . -name .git -prune -o -type f -print0)
    while IFS= read -r -d '' md; do
      flatten "$md" "$md"
    done < <(find "$dest" -type f -name '*.md' -print0)
  else
    # `abspath` + `flatten` folded into one python3 process — see the comment
    # atop `flatten` above.
    dest="$(flatten "$arg" "$raw_dest" "$tmpdir")"
  fi
  if [[ "$arg" == /* ]]; then
    argv_paths+=("$dest")
  else
    argv_paths+=("$arg")
  fi
done

cd "$mirror"
vale ${vale_args[@]+"${vale_args[@]}"} ${argv_paths[@]+"${argv_paths[@]}"}